CN116868558A - Optimizing detection performance for radio frequency based sensing - Google Patents

Abstract

The present invention relates to a Radio Frequency (RF) system having a plurality of nodes (34, 36, 38, 44, 46, 48) and a method for optimizing detection performance for performing RF-based sensing in a sensing region (32) based on RF system configuration parameters. The RF system configuration parameters that have the greatest impact on the detection performance of the RF-based sensing are determined. Then, the RF system configuration parameters that have the greatest impact on the detection performance of the RF-based sensing are adjusted in order to optimize the detection performance of the RF-based sensing. The root cause of the detection performance degradation and the corresponding RF system configuration parameters for mitigating the detection performance degradation may be determined based on the current context. To optimize detection performance, for example, the settings of the sensing parameters of the nodes (34, …, 48) may be adjusted, or the nodes (34, …, 38) may be moved, removed, added or replaced.

Description

Optimizing detection performance for radio frequency based sensing

Technical Field

The present invention relates to a Radio Frequency (RF) system, a method for optimizing detection performance of RF-based sensing, and a computer program product.

Background

RF-based sensing is used to detect different types of sensed events in a sensing region, such as: human movement or room occupancy, for example for controlling light settings; and more detailed human biological features such as respiratory movement rate or human gait, for example for context awareness and detailed daily activity monitoring.

US 2017/366938 A1 shows a system that uses signal absorption and signal forward and reflected back scattering of RF waves caused by the presence of biological substances in a communication network to detect the presence of a body in the network. The system can automate various aspects of the setup, particularly with respect to grouping nodes into detection regions and nominally building functional levels based on machine learning methods. The system that determines the closest node by inference and estimates the detection area need not be set by the user. Based on the best estimate, the user can simply place nodes throughout the building and automatically group the nodes into detection areas using unsupervised machine learning, ultimately resulting in the building system learning how to detect occupants.

US 2020/0096345 A1 shows a computer-implemented method for cognitive fingerprinting of indoor locations. The method includes determining calibration information for using the sensing device within the indoor environment; based at least in part on the calibration information, generating instructions corresponding to one or more suggested position sensor placements throughout the indoor environment; and issuing instructions corresponding to the one or more suggested position sensor placements via the sensing device when a user operating the sensing device navigates the indoor environment. The proposed position sensor placement may be based on one or more Received Signal Strength Indicators (RSSI), each RSSI received by the sensing device and from a position sensor in the indoor environment. The instructions may include instructions to place a new position sensor at a position where a signal strength received from one or more neighboring position sensors is less than a predetermined minimum signal strength threshold.

Disclosure of Invention

It may be seen as an object of the present invention to provide an RF system, a method for optimizing detection performance for performing RF-based sensing, a computer program product for optimizing detection performance for performing RF-based sensing, and a computer readable medium allowing an improved optimization of detection performance for performing RF-based sensing.

In a first aspect of the invention, an RF system for optimizing detection performance for performing RF-based sensing based on RF system configuration parameters is presented. The RF system includes a plurality of nodes, wherein a group of at least two nodes is configured to perform RF-based sensing in a sensing region. The RF system is configured to determine the RF system configuration parameters that have the greatest impact on the detection performance of the RF-based sensing among the RF system configuration parameters. In addition, the RF system is configured to adjust RF system configuration parameters that have the greatest impact on the detection performance of the RF-based sensing in order to optimize the detection performance of the RF-based sensing.

Since the RF system is configured to determine the RF system configuration parameter having the greatest influence on the detection performance of the RF-based sensing among the RF system configuration parameters and to adjust the RF system configuration parameter having the greatest influence on the detection performance of the RF-based sensing so as to optimize the detection performance of the RF-based sensing, the root cause of adversely affecting the detection performance can be alleviated. This allows improved optimisation of the detection performance. Which RF system configuration parameters have the greatest impact on detection performance depends on the root cause that negatively impacts detection performance. This allows determining which adjustments to the RF system allow for maximum alleviation of the root cause and thus allow for maximum improvement of detection performance.

The greatest impact on detection performance means that the adjustment of the RF system configuration parameters that most impact detection performance of RF-based sensing has a greater impact on detection performance than a corresponding adjustment of another RF system configuration parameter. For example, one of the RF system configuration parameters may be the location of the first node and another of the RF system configuration parameters may be the location of the second node. Moving the first node a certain length in the vertical direction may have only a small impact on the detection performance, while moving the second node the same length in the vertical direction may have a much larger impact on the detection performance. For example, if the RF system is arranged in a sensing area in the form of a room for performing the breathing rate identification of two different persons lying on a double bed, and the first node is a ceiling luminaire arranged in the centre of the ceiling of the room, and the second node is a bedside lamp arranged on a bedside table on one side of the double bed, moving the bedside lamp in a vertical direction has a much larger influence on identifying the breathing rate of a person lying on the double bed on the side on which the bedside lamp is arranged than moving the ceiling luminaire. In general, moving ceiling lights have a much smaller impact on breath rate recognition than moving bed headlamps because the ceiling lights are much farther from the person on the twin bed.

RF-based sensing presents unique characteristics compared to optimizing other sensing modalities such as Passive Infrared (PIR) sensors, cameras, radars, etc., because it is a distributed sensing modality. Unlike PIR sensors, cameras, radars, etc., there is no single, physically identifiable device to perform sensing. Instead, a set of nodes generates data between them, processes the data (e.g., sensing algorithms or sensing analysis algorithms involving various complexities), and infers whether a sensing event occurred as a set. Thus, for example, different numbers of nodes in different groups or different relative positions of nodes to each other may affect the detection performance of the different groups of RF-based sensing.

When sensing is performed using other sensing modalities than RF-based sensing, the field of view (FoV) of a sensing device (e.g., a camera) may be adjusted by steering the camera lens of the camera in the direction of the desired new sensing area in order to improve detection performance. In the case of RF-based sensing, improving detection performance by adjusting the sensing region (e.g., modifying the detection region of the group performing RF-based sensing) is not trivial. RF-based sensing may be affected by node location, but may also be affected by, for example, complex multipath effects. The RF signal is not limited to a predefined FOV with a clear line. Furthermore, the presence of tangible entities (e.g., objects) in the sensing region may alter multipath behavior.

The RF system may allow for determining which RF system configuration parameters have the greatest impact on detection performance and for adjusting this RF system configuration parameter that has the greatest impact on detection performance of the RF-based sensing in order to improve detection performance. The RF system may also be used to provide feedback to the user to improve detection performance.

RF-based sensing allows detection of various sensed events occurring in a sensing region, i.e. a specific space or a specific volume, e.g. a room in a building, a building or any other space. The sensing algorithm or the sensing analysis algorithm may detect and analyze how a tangible entity (such as an object or user) within the sensing region affects the RF signal. The RF signal is used to transmit RF messages. RF-based sensing may be used as a means to detect and classify sensed events, such as user activity in a home, office, etc. For example, based on WiFi RF-based sensing messages transmitted and received by nodes in the form of smart lights, RF-based sensing may determine movement in a room and automatically turn the lights on or off, nodes in the form of WiFi routers may estimate the person's respiratory rate, etc.

The basic principle of RF-based sensing is that the distortion of an RF signal in space is a function of both the physical entity in space (e.g. a moving object) and the frequency of the RF signal. Radio waves propagate through electromagnetic radiation and interact with the environment by reflection, refraction, diffraction, absorption, polarization, and scattering. The wireless attenuation of different materials is different in the typical frequency range used for RF-based sensing applications. Thus, characteristics of the sensing region (e.g., the building form of the room, the spatial arrangement, and the integrated surface area of each material type present in the sensing region) may affect the RF multipath signal characteristics of the sensing region.

To perform RF-based sensing, one node may act as a transmitting node, transmitting an RF signal comprising an RF message to another node acting as a receiving node. The received RF signal may then be analyzed. If the RF signal interacts with one or more tangible entities (e.g., objects or persons) on the transmission path between its nodes, the RF signal is disturbed, e.g., scattered, absorbed, reflected, or any combination thereof. These disturbances may be analyzed and used to perform RF-based sensing. The disturbed and/or reflected RF signal may comprise an RF-based sensed fingerprint based on signal parameters, such as real and imaginary parts of permittivity and susceptibility. Performing RF-based sensing by at least two nodes is also referred to as passive RF sensing.

A first node of the at least two nodes may be configured to transmit radio frequency signals and a second node of the at least two nodes may be configured to receive the transmitted radio frequency signals, and wherein radio frequency based sensing may be performed by analyzing interference of radio frequency signals caused by interactions of the radio frequency signals with one or more objects or persons on their transmission path between the at least two nodes. The analysis may be based on comparing the received radio frequency signal to a baseline defined for the sensing region. The baseline may include propagation of radio frequency signals in the sensing region. Those skilled in the art of (passive) RF sensing know to obtain/determine a baseline and will therefore not be discussed further herein.

The radio frequency system may be configured to perform presence detection in the sensing region. The radio frequency system may be configured to perform one or more of motion detection, position tracking, vital sign detection (e.g., respiratory detection, heart rate monitoring, sleep monitoring, fall detection, posture detection, activity detection, gait detection, gesture detection, etc.) in the sensing region. Other known or future applications of radio frequency sensing are not precluded. The presence detection may be an explicit detection of the presence of the user, or it may be implicitly derived from other sensing functions related to the presence of the user, such as motion detection, location tracking, health related detection (e.g. respiratory detection, heart rate detection, fall detection, etc.).

The RF system configuration parameters may relate to RF system configuration parameters of at least two nodes or more nodes forming a group that performs RF-based sensing in the sensing region (i.e., all nodes of the RF system including at least two nodes of the group that perform RF-based sensing in the sensing region). Operations of nodes in a group that do not include performing RF-based sensing in the sensing region may impact detection performance, for example, due to wireless interference or jamming of the wireless network of the RF system.

The RF system configuration parameters may include one or more of the following:

the spatial arrangement of at least two nodes of the group,

grouping of a plurality of nodes into the group,

the number of nodes in the group,

-the capabilities of the nodes in the group, and

-one or more sensing parameters for performing RF-based sensing.

The radio frequency system configuration parameters affect the detection performance. The detection performance may be higher or lower depending on the setting of the RF system configuration parameters. This allows for optimizing detection performance by adjusting one or more of the RF system configuration parameters. Since the RF system configuration parameters that have the greatest influence on the detection performance are adjusted, the optimization can be improved.

The spatial arrangement of at least two nodes of the group may include spatial arrangements of nodes with respect to each other, with respect to other groups of nodes, and with respect to other tangible entities, such as walls, corners, or other objects, such as twin beds or bookshelf. The spatial arrangement may also include the relative position of at least one of the two nodes with respect to the other tangible entity. For example, the spatial arrangement of the set of nodes may be adjusted by moving one or more of the at least two nodes. The movement may be in any three-dimensional direction, i.e. horizontally, vertically or a combination thereof. Adjusting the spatial arrangement may allow for improved detection performance, for example, by adjusting the sensing region and/or by moving the node closer to the region of interest in which the sensing event is expected to occur. For example, the bedside lamp may be moved to a side closer to the double bed, which side corresponds to the region of interest identified by the respiration rate, as the intended user sleeps on this bed side. This may allow for improved detection performance of the side-lights for breath rate identification.

The RF system may be configured to determine which node to remove, replace or move in order to maximize detection performance, e.g., by comparing detection performance of different spatial arrangements. For example, moving ceiling illuminators will have only a minor impact on improving detection performance. Thus, the RF system may be configured to determine information about the root cause that negatively affects the detection performance based on computer simulation, actual moving of the ceiling luminaires, or information about RF system configuration parameters received by, for example, a user, corresponding to the RF system configuration parameters that determine the greatest impact on the detection performance, the node may be moved so as to have the greatest impact on the detection performance.

Grouping of multiple nodes into a group may be adjusted by removing one of at least two nodes, adding one node from multiple nodes (e.g., from another group of RF systems) to the group performing RF-based sensing in the sensing region, or a combination thereof (such as replacing one node with another node, for example). The RF system may be configured to add only the nodes of another group to the group performing RF-based sensing in the sensing region if the other group is capable of operating without the node. The RF system may be configured to determine that removing a node from another group and adding the node to the group to perform RF-based sensing in the sensing region may have an effect on the other group and on the group in order to decide whether the node should be moved.

The number of nodes in the group used to perform RF-based sensing in the sensing region may be adjusted by removing or adding one node from or to the group, for example by regrouping nodes of the RF system and/or by removing or adding one node to the RF system.

The sensing parameters may include, for example, transmit power, sensitivity, signal strength, signal link, beam shape, beam directivity, threshold level, radio type for performing RF-based sensing, communication protocol for performing RF-based sensing, or any other sensing parameter. The threshold level may be, for example, a threshold level of sensitivity, a threshold level of signal strength, or any other threshold level. The type of radio used to perform RF-based sensing may be different for different nodes, e.g., a first node may use 2.4GHz WiFi, while second and third nodes may use 2.4GHz WiFi and additional 5GHz WiFi. Communication protocols for performing RF-based sensing may include, for example, bluetooth Low Energy (BLE), wiFi, cellular radio, zigbee, or any other communication protocol that may be used to perform RF-based sensing.

The RF system may be configured to determine RF system configuration parameters that most affect the detection performance of the RF-based sensing based on the current context. This allows for dynamic adjustment of the RF system configuration parameters that have the greatest impact on detection performance in order to optimize detection performance of RF-based sensing. The RF system may be configured to determine a current context in which RF-based sensing is performed by a group or the entire RF system in the sensing region. Information about the current context may be provided as input by a user to the RF system, which information is then processed by the RF system to determine the current context. Alternatively, the RF system may be configured to determine the current context in any other way, e.g., based on data stored in the RF system or sensor data obtained by the RF system.

The current context may include one or more of the following:

a setting of one or more of the RF system configuration parameters,

the sensing application is performed in a manner that,

the delay requirement is set up in such a way that,

an expected sensing event in the sensing region,

the need for privacy is to be understood,

the radio power consumption requirements are that,

the radio transmission power requirements are set,

the radio beam shape requirements,

the radio reception beamforming requirements,

the current location of the RF system,

A current location of at least one of the at least two nodes,

sensing the current position of the tangible entity in the area,

the current date of the day,

a current operation mode of at least one of the at least two nodes,

the effect of the environment is to be taken care of,

the bandwidth currently available in the RF system,

current capabilities of at least one of the at least two nodes,

sensing a current property of the area,

-error event detection rate requirement, and

missing event detection requirements.

The RF system may be configured to determine the settings of one or more of the RF system configuration parameters by checking the current stored settings of the RF system configuration parameters.

The sensing applications may include, for example, which type of sensed event is detected by performing RF-based sensing, such as fast, low-latency motion detection, occupancy detection, idle detection, fall detection, heartbeat detection, respiratory rate identification, heart rate identification, or any other sensed event. The sensing application may also provide the current context by including requirements of the sensing application, such as standby power requirements of the sensing application, such as a currently required standby power level.

The current context may also include different sensing applications, e.g., ordered by priority of the sensing applications, in order to provide certain sensing functions. For example, sensing applications may include occupancy detection and breath rate identification. Occupancy may have a lower priority than breath rate identification so that adjusting the position of the node may be performed by the RF system, which improves the detection performance of the breath rate identification, but reduces the detection performance of the occupancy detection, not vice versa, wherein the detection performance of the breath rate identification is reduced and the detection performance of the occupancy detection is improved. This may allow for improved detection performance based on the priority of the sensing application.

The delay requirement may include, for example, a duration during which data processing needs to be completed and whether a sensed event needs to be detected or not, e.g., for life safety critical sensing applications that require a quick response. Another delay requirement may be, for example, a lighting control delay requirement according to which lighting needs to be activated for a certain duration (e.g. 200 ms) in response to a user entering a sensing area.

The expected sensing event in the sensing region may be any sensing event detected by performing RF-based sensing for a particular sensing application, such as occupancy detection, fall detection, respiratory rate recognition, heart rate recognition, gesture recognition, etc.

Privacy requirements may include, for example, that certain RF-based sensing applications are not allowed for certain privacy requirements. For example, if there is a romantic context, e.g., the RF system uses romantic light scenes, e.g., in the form of a Connected Lighting (CL) system in which the nodes are luminaires, then a specific RF sensing configuration may be used that prohibits certain sensing applications, which is privacy-respecting in nature. For example, the RF system may be allowed to perform RF-based sensing in order to detect occupancy (i.e., occupancy detection), but may not perform RF-based sensing to identify respiration rate and/or heart rate (i.e., respiration rate identification and/or heart rate identification).

The radio power consumption requirements may include, for example, standby power management requirements. Standby mode may include, for example, not performing the primary function of a node. The node may be configured to perform RF-based sensing, for example, in a standby mode, i.e. when it does not perform its main function. For example, the node may be a luminaire that does not provide light in standby mode, but performs RF-based sensing. In this case, the standby power consumed by the node corresponds to the power consumed by the node when processing the RF sense messages (e.g., including receiving the RF sense messages and processing them, e.g., using a sense analysis algorithm). The power consumption for performing RF-based sensing depends on the settings of the RF system configuration parameters, so that the power consumption can be adjusted depending on the RF system configuration parameters, so that the radio power consumption requirements can be met.

The radio transmit power requirements may include, for example, limits of transmit power, such as radio interference due to high transmit power. For example, in a hospital room, a medical machine may be interfered with by wireless interference such that the allowable RF transmit power for performing RF-based sensing may be limited based on the radio transmit power requirements.

The radio beam shape requirements and the radio receive beam shaping requirements relate to how the beam requirements for performing RF based sensing are shaped. The beam may be, for example, a narrow beam or a divergent beam. The beam shape may affect the sensing area that may be covered by performing RF-based sensing. A narrow beam may, for example, allow coverage of a longer sensing area, while a divergent beam may, for example, allow coverage of a wider sensing area. The use of a narrow beam may allow RF-based sensing to be performed between two nodes that are farther away from each other than if a divergent beam was used. Furthermore, the use of narrow beams allows for focusing the RF signal to a specific direction, such that beamforming in this way may allow for providing a higher signal quality to the receiving node.

The current location of at least one of the two nodes may comprise, for example, a relative location of at least one of the two nodes with respect to another of the at least two nodes. This may affect the transmission length between the nodes. The current location of at least one of the at least two nodes may be, for example, near the tangible entity.

The current location of the tangible entity (e.g., user) may include a relative location of the tangible entity in or relative to the sensing region and/or node. In case a part of the sensing area is not well covered by the group, this may reduce the detection performance. For example, the tangible entity may also be a door or a room divider in a room. Where the tangible entity is a door, its position (e.g., open, closed, or its corresponding opening angle) may affect RF-based sensing and thus also affect detection performance. Where the tangible entity is a room divider, such as in a restaurant, its location may divide the room into two smaller rooms and affect the RF-based sensing and detection performance.

The current date may include the time of day (e.g., night or day), or the day of the week (e.g., weekday or weekend). The RF system may be configured to determine the current date based on a clock and/or calendar.

The requirements such as standby power management requirements or radio transmit power requirements may depend on e.g. the current location of the RF system and/or at least one of the two nodes and/or on e.g. the current date.

The current mode of operation of the respective node may include, for example, performing a primary function, such as providing illumination, performing RF-based sensing, and/or operating in a standby mode.

The environmental impact may include, for example, radio interference, background noise level, or a combination thereof. The environmental impact may be caused based on, for example, humidity in the air, smoke, cigarette smoke, activity in areas adjacent to the sensing area, or a combination thereof. Background noise may be caused by, for example, noise sources such as microwave ovens or streaming televisions. Background noise may degrade the signal-to-noise ratio (SNR) of RF-based sensing and increase the number of lost RF messages between nodes, i.e. decrease the sampling rate or the effective messaging rate, respectively.

Considering the bandwidth currently available in an RF system may allow compensating for a lack of sampling rate to some extent, e.g., due to lost RF messages. For example, the RF system configuration parameters may be adapted so as to avoid wireless congestion of the network used by the RF system to exchange data.

The properties of the sensing region may include, for example, shape, regularity, material, prototypes of the room in which the nodes are arranged, or any other property of the sensing region. This allows the properties of the room to be taken into account to optimize the detection performance.

The error event detection rate requirement corresponds to a tolerance for error detection. The error event detection rate requirements may include, for example, false positive rates and false negative rates.

Missing event detection requires a margin corresponding to the missing event, i.e. it corresponds to missing report detection. Missing event detection requirements may be, for example, allowing only a certain percentage of events, such as 5% of events, to be missed.

The RF system may be configured to determine an impact on other sensing applications of adjusting RF system configuration parameters that have the greatest impact on detection performance of a particular sensing application. The RF system may be configured to adjust RF system configuration parameters that maximally impact detection performance based on their impact on other sensing applications. This allows for a compromise to be considered which adjusts the RF system configuration parameters that have the greatest impact on the detection performance of different sensing applications, e.g. respiratory rate recognition and fast motion sensing and fall detection.

The detection performance may include one or more sensing metrics. The sensing metrics may include one or more of the following:

The delay time is set to be equal to the delay time,

the degree of accuracy is chosen to be,

the spatial resolution of the optical system is chosen,

a false positive detection rate of the detection of the presence of a signal,

-a rate of detection of false negatives,

confidence level for detecting a sensed event,

-sensing noise in the event detection,

-a data traffic volume to be generated,

energy consumption, and

-spatial limitation of RF signals for performing RF-based sensing.

The RF system may be configured to determine how adjusting the RF system configuration parameters affects one or more sensing metrics contained in the detection performance. If one of the sensing metrics is mitigated by adjusting the RF system configuration parameters, the RF system may be configured not to adjust the RF system configuration parameters. Alternatively, the RF system may be configured to determine whether one or more of the sensing metrics improve detection performance while mitigating one or more of the other sensing metrics. The detection performance may be a function of the sensing metrics contained therein, such as an average, a weighted sum, or the like. Considering different sensing metrics of detection performance may allow fine-grained optimization of RF system configuration parameters, and in particular adjusting RF system configuration parameters that have the greatest impact on RF-based sensing in order to optimize detection performance.

For example, if detection is caused by the detection signal swinging around a threshold, and if the signal is above the threshold, then it is considered that a sensing event is detected, noise in the detection of the sensing event may be caused. In this case the amplitude of the signal swinging up and down the threshold does have an effect.

The limitation of the RF signal depends at least on the frequency used to perform the RF-based sensing. For example 5GHz WiFi is more limited than 2.4GHz WiFi. For some sensing applications, such as for example the respiratory rate identification of a twin bed, it may be beneficial to provide a limited RF signal on one side of the twin bed, especially when two people are sleeping on both sides of the twin bed.

The RF system may be configured to determine RF system configuration parameters that most affect the detection performance of the RF-based sensing based on one or more sensing metrics included in the detection performance, e.g., based on which of the one or more sensing metrics is included in the detection performance and/or based on one or more sensing metric levels of the sensing metrics. Determining the RF system configuration parameters that most affect the detection performance of the RF-based sensing based on one or more sensing metrics included in the detection performance may allow for improved optimization of the detection performance.

The user may provide one or more sensed metrics that detect performance, such as one or more sensed metrics that are unsatisfactory to the user. For example, if the user is not satisfied with the delay, the user may provide the delay as the only sensing metric included in the detection performance. The RF system may be configured to determine RF system configuration parameters that most affect the delay of the RF-based sensing. The RF system may be configured to adjust corresponding RF system configuration parameters to optimize the delay. The RF system may be configured to automatically adjust the RF system configuration parameters that have the greatest impact on detection performance or the user may adjust the RF system configuration parameters that have the greatest impact on detection performance.

The RF system may be configured to determine whether a respective current sensing metric level of the one or more sensing metrics included in the detection performance is above or below a respective threshold sensing metric level. Additionally, the RF system may be configured to determine RF system configuration parameters that most affect the detection performance of the RF-based sensing based on which respective current sensing metric level of the one or more sensing metrics included in the detection performance is above or below the respective threshold sensing metric level. Taking into account the threshold sensing metric level of the sensing metric may allow for an easy and quick determination of which sensing metric performances are below expected, e.g., below a minimum feasible level or below an average value. This may allow root causes to be derived that negatively impact detection performance. Based on the root cause, the RF system configuration parameters that have the greatest impact on detection performance can be readily determined, e.g., based on rules and/or experience of the RF system. The RF system may be configured to determine a current sensing level of each of the one or more sensing metrics or a subset thereof comprised in the detection performance, e.g. a predetermined subset of sensing metrics of interest for performing RF-based sensing, such as a subset of sensing metrics that have the greatest impact on the detection performance, e.g. because the sensing metrics have the highest weight, based on rules and/or experience of the RF system.

The RF system may be configured for determining a current detection performance level of the RF-based sensing and for optimizing the detection performance based on whether the current detection performance level is above or below a threshold detection performance level. This allows providing a trigger for optimizing the detection performance, for example, in case the detection performance level is below a threshold detection performance level.

The detection performance may include one or more sensing metrics. The RF system may be configured to determine whether one or more of the sensing metrics have a respective current sensing metric level below a respective sensing metric threshold level. The RF system may be configured to determine the RF system configuration parameters based on which of the sensing metrics has a respective sensing metric level below a respective sensing metric threshold level. This allows poor performance of which sensing measure is considered in order to determine which RF system configuration parameters allow improved detection performance.

The RF system may be configured to determine the root cause that negatively affects detection performance, the RF system configuration parameters that most affect detection performance, or both, e.g., based on analyzing the RF system configuration parameters, detection performance, current context, or a combination thereof.

Alternatively, the root cause, the RF system configuration parameters that have the greatest impact on detection performance, or both, may be provided by the user, e.g., via a communication interface from a server or via direct input where the communication interface includes a user interface. This allows the user to trigger an adjustment of the RF system configuration parameters, and in particular the RF system configuration parameters that have the greatest impact on the detection performance, in order to optimize the detection performance of the RF-based sensing.

In other words, the RF system may be triggered to optimize detection performance based on feedback from the user or based on an automatic determination of whether there is a current amount of sensing to optimize. The RF system may then adjust the RF system configuration parameters, and in particular the RF system configuration parameters that have the greatest impact on the current sensing metric, in order to optimize detection performance. Current sensing metrics may need to be optimized, for example, because of performance shortages, such as respiratory rate identification often losing synchronization with respiratory motion. For example, in the event of insufficient respiratory rate identification performance, the RF system may be configured to determine only the presence of a person, but not the respiratory rate of the person.

The RF system may be configured to determine a ranking of one or more RF system configuration parameters, the ranking being ranked according to their respective degrees of influence on the detection performance of the RF-based sensing, and to adjust the RF system configuration parameters based on the ranking so as to optimize the detection performance of the RF-based sensing. This may allow further optimization of detection performance, as various RF system configuration parameters may be adjusted according to their impact on detection performance in order to optimize detection performance. The RF systems may be configured to provide weights to each RF system configuration parameter based on their respective ordering. The RF systems may be configured to sequentially adjust RF system configuration parameters based on their respective ordering. This may allow for a faster optimization of the detection performance, since the RF system configuration parameters having a larger impact on the detection performance are adjusted before the RF system configuration parameters having a smaller impact on the detection performance are adjusted in order to optimize the detection performance.

The RF system may be configured to provide RF system configuration parameters that have the greatest impact on the detection performance of the RF-based sensing, to provide how to adjust the RF system configuration parameters that have the greatest impact on the detection performance of the RF-based sensing to optimize the detection performance, or a combination thereof. This may allow for improved detection performance in case external interaction with, for example, an external system or user is required, for example, in order to replace, add or remove one or more nodes. The RF system may also be configured to provide an ordering of the RF system configuration parameters, the ordering being ordered according to their respective degrees of influence on the detection performance of the RF-based sensing. Additionally or alternatively, the RF system may be configured to provide how the RF system configuration parameters are to be adjusted according to the ordering to optimize detection performance.

The RF system may include a communication interface. The communication interface may be configured to provide the user with RF system configuration parameters that have the greatest impact on the detection performance of the RF-based sensing, to provide the user with RF system configuration parameters that have the greatest impact on the detection performance of the RF-based sensing to be adjusted to optimize the detection performance, or a combination thereof.

The communication interface may comprise or be a user interface, for example a display for displaying RF system configuration parameters to a user or a touch display that otherwise allows a user to provide input, such as information about the current context for performing RF-based sensing. Alternatively, the communication interface may comprise a transceiver and an antenna for transmitting the RF system configuration parameters to the user device or server, such that the user may obtain the RF system configuration parameters from the user device or server. The user may use information about the RF system configuration parameters in order to optimize detection performance.

In a further aspect of the invention, a method for optimizing detection performance for performing RF-based sensing based on RF system configuration parameters is presented. The method may be a computer-implemented method, such as a computer-implemented method performed on a computer system (e.g., an RF system) that includes a processor and a communication interface. The method comprises the following steps:

performing RF-based sensing in a sensing region by a group of at least two nodes of an RF system comprising a plurality of nodes,

-determining the RF system configuration parameters that have the greatest influence on the detection performance of the RF-based sensing, and

-adjusting RF system configuration parameters in order to optimize detection performance of the RF-based sensing.

The method may include one or more of the following steps:

determining a current context in which RF-based sensing is performed by the group in the sensing region,

determining RF system configuration parameters that have the greatest impact on the detection performance of the RF-based sensing based on the current context,

determining RF system configuration parameters that have the greatest impact on the detection performance of the RF-based sensing based on one or more sensing metrics included in the detection performance,

determining whether a respective current sensing level of one or more sensing metrics included in the detection performance is above or below a respective threshold sensing level,

Determining an RF system configuration parameter that affects most of the detection performance of the RF-based sensing based on which respective current sensing metric level of the one or more sensing metrics included in the detection performance is above or below the respective threshold sensing metric level,

determining a current detection performance level of the RF-based sensing,

optimizing the detection performance based on whether the current detection performance level is above or below a threshold detection performance level,

determining an ordering of one or more RF system configuration parameters, the ordering being ordered according to their respective degrees of influence on the detection performance of the RF-based sensing,

adjusting RF system configuration parameters based on the ordering so as to optimize detection performance of the RF-based sensing,

providing RF system configuration parameters that have the greatest impact on the detection performance of RF-based sensing,

providing how to adjust RF system configuration parameters that have the greatest impact on the detection performance of RF-based sensing to optimize the detection performance,

-providing the user with RF system configuration parameters that have the greatest impact on the detection performance of the RF-based sensing, and

-providing the user with how to adjust RF system configuration parameters that have the greatest impact on the detection performance of the RF-based sensing to optimize the detection performance.

In a further aspect of the invention, a computer program product for optimizing detection performance of RF-based sensing is presented. The computer program product comprising program code means for causing a processor to perform the method according to claim 12, claim 13 or any embodiment of the method when the computer program product is run on a processor.

In a further aspect, a computer readable medium having stored the computer program product of claim 14 is presented. Alternatively or additionally, the computer-readable medium may cause a computer program product according to any embodiment of the computer program product to be stored.

It shall be understood that the RF system of claim 1, the method of claim 12, the computer program product of claim 14, and the computer readable medium of claim 15 have similar and/or identical preferred embodiments, in particular as defined in the dependent claims.

It is to be understood that the preferred embodiments of the invention may also be any combination of the dependent claims or the above embodiments with the corresponding independent claims.

These and other aspects of the invention are apparent from and will be elucidated with reference to the embodiments described hereinafter.

Drawings

In the following figures:

figure 1 schematically and exemplarily shows a node for an RF system,

figure 2 schematically and exemplarily shows an embodiment of an RF system having two sets of nodes in a first configuration,

figure 3 schematically and exemplarily shows an embodiment of an RF system in a second configuration,

figure 4 schematically and exemplarily shows an embodiment of an RF system in a third configuration,

figure 5 schematically and exemplarily shows an embodiment of an RF system in a fourth configuration,

FIG. 6 schematically and exemplarily shows an embodiment of an RF system in a fifth configuration, an

Fig. 7 illustrates an embodiment of a method for optimizing detection performance for performing RF-based sensing.

Detailed Description

Fig. 1 schematically and exemplarily illustrates nodes of an RF system, such as CL system 100 presented in various configurations in fig. 2-6. In the following, before providing details regarding the functionality of the CL system 100, we describe details of an exemplary node 10 that may be used in the CL system 100.

Node 10 includes a control unit 12 and a communication interface 14 including an antenna array 16. Instead of an antenna array, a single antenna may also be included in the node.

The control unit 12 includes a computer readable medium in the form of a processor 18 and a memory 20.

In this embodiment, the communication interface 14 additionally includes: a WiFi transceiver 22 for transmitting and receiving RF signals including WiFi-based RF messages (i.e., wiFi RF messages); and a user interface 24 in the form of a touch display. In other embodiments, the communication interface may also exchange data based on one or more other communication protocols (e.g., threads, cellular radio, bluetooth, BLE, or any other communication protocol). The communication interface may also include two or more transceivers configured to exchange data based on different communication protocols.

Communication interface 14 uses antenna array 16 to transmit RF signals to and receive RF signals from nodes of CL system 100, respectively, to wirelessly exchange data including RF messages between the nodes and perform RF-based sensing. RF signals transmitted from one node to another may be subject to interference by, for example, tangible entities (e.g., users) within the transmission path between the nodes. The RF signals disturbed by the user may be analyzed in the control unit 12 for performing RF based sensing.

The memory 20 of the control unit 12 stores a computer program product for operating the CL system 100. The computer program product comprises program code means for causing the processor 18 to perform a method for optimizing detection performance for performing RF-based sensing, e.g. a method for optimizing detection performance for performing RF-based sensing based on RF system configuration parameters as presented in fig. 7, when the computer program product is run on the processor 18. The memory 20 further comprises a computer program product for operating the node 10 and optionally the entire CL system 100, respectively, e.g. for controlling the functions of the node and the functions of the node controlling the CL system 100, e.g. for providing illumination and for performing RF-based sensing.

Fig. 2 shows an embodiment of an RF system in the form of a CL system 100, which includes a first set 30 of nodes 34, 36 and 38 and a second set 40 of nodes 44, 46 and 48. CL system 100 is shown in a top perspective view of a first configuration disposed in a building having two rooms. The first group 30 performs RF-based sensing in a first sensing region 32 in a first room and the second group 40 performs RF-based sensing in a second sensing region 42 in a second room. In other embodiments, the RF system may have a different number of nodes, such as two, three, four or more and/or a different number of groups. In other embodiments, the sensing region may have different sizes, shapes, and locations. Furthermore, in different embodiments, the RF systems may be arranged in different buildings or in open spaces.

Node 34 is a WiFi router and the other nodes 36, 38, 44, 46 and 48 are luminaires for providing light and for performing RF-based sensing. In other embodiments, the node may also be of another type and perform another function, such as a switch, a light, a bridge, etc. The node 34 is wirelessly connected to the external server 200. External server 200 may be used to control nodes 36-48 of CL system 100, for example by transmitting control signals to one or more of them. The external server may be, for example, a server of a Building Management System (BMS). In this embodiment, the external server 200 only exchanges data directly with the node 34. Node 34 may then exchange data with other nodes 36-48 to control their functions. Node 34 may also transmit control signals to another node (e.g., node 36), which node 36 may forward to another node, such as nodes 44, 46, and 48.

In this embodiment, the locations of nodes 34, 36, and 38 of first set 30 define first sensing region 32, and the locations of nodes 44, 46, and 48 of second set 40 define second sensing region 42. In other embodiments or configurations of CL system 100, the sensing regions may be different. The sensing area may also be predefined, for example, as appropriate for a room of a building.

The CL system 100 is used to optimize detection performance to perform RF-based sensing based on RF system configuration parameters and to perform RF-based sensing with optimized detection performance. In the configuration of CL system 100 shown in fig. 2, CL system 100 optimizes the detection performance of first set 30. The CL system 100 may also optimize the detection performance of the second set 40. In other embodiments, CL system 100 may optimize the detection performance of the overall CL system 100, including, for example, the detection performance of first set 30 and second set 40.

In this embodiment, the detection performance includes various sensing metrics including one or more of the following: delay, confidence level for detecting sensed events, accuracy, spatial resolution, false positive detection rate, false negative detection rate, noise in sensed event detection, generated data traffic, energy consumption, and spatial limitation of RF signals for performing RF-based sensing.

The RF system configuration parameters include the spatial arrangement of the nodes 34 to 48 of the respective groups 30 and 40, the grouping of the nodes 34 to 48 into the groups 30 and 40, the number of nodes in the groups 30 and 40, and various sensing parameters for performing RF-based sensing. The sensing parameters include, for example, transmit power, sensitivity, signal strength, signal link, beam shape, beam directivity, threshold level, radio type for performing RF-based sensing, and communication protocol for performing RF-based sensing.

Before the CL system 100 optimizes the detection performance, it determines the current detection performance level of the RF-based sensing in order to decide whether it is necessary to optimize it or whether the current detection performance is adequate. This step is optional.

In this embodiment, the processing is performed by node 34. In other embodiments, the processing may also be performed by other nodes of the RF system or on an external server. To determine the current detection performance level of the first set 30, the CL system 100 performs RF-based sensing in the sensing region 32 using current RF system configuration parameters. In this embodiment, the CL system 100 only optimizes the detection performance if the current detection performance level is below the threshold detection performance level. In other embodiments, the RF system may be configured to optimize detection performance based on whether the current detection performance level is above or below a threshold detection performance level. If the CL system 100 decides that detection performance does not need to be optimized, the CL system 100 performs RF-based sensing using current RF system configuration parameters. Otherwise, CL system 100 optimizes the detection performance.

To optimize the detection performance, CL system 100 determines which RF system configuration parameters most impact the detection performance based on the current context and based on the level of the sensing metric of the sensing metrics included in the detection performance. In other embodiments, the RF system may be configured to determine the RF system configuration parameters that have the greatest impact on detection performance, e.g., based on which of the one or more sensing metrics is included in the detection performance, instead of or in addition to its sensing metric level.

In this embodiment, the current context includes the sensing application executed by the first group and the environmental impact in the form of wireless interference 50 caused in the first sensing region 32 by operating the second group 40. The sensing applications are determined by inputs provided by the user 26, i.e., the user 26 decides which sensing applications are to be executed by the CL system 100. In this embodiment, CL system 100 is used for occupancy detection. The radio interference 50 is determined based on a sensing analysis algorithm that detects radio interference based on RF signals comprising RF messages exchanged between nodes, i.e. depending on signal strength and lost RF message rate.

In other embodiments, the current context may also include, for example, a setting of one or more of the RF system configuration parameters, a latency requirement, an expected sensed event in the sensing region, a privacy requirement, a radio power consumption requirement, a radio transmit power requirement, a radio beam shape requirement, a radio receive beam forming requirement, a current location of the RF system, a current location of at least one of the at least two nodes, a current location of a tangible entity in the sensing region, a current date, a current mode of operation of at least one of the at least two nodes, a current available bandwidth in the RF system, a current capability of at least one of the at least two nodes, a current attribute of the sensing region, an error event detection rate requirement, and a missed event detection requirement.

CL system 100 determines whether the respective current sensing level of the sensing metrics included in the detection performance is above or below the respective threshold sensing level, e.g., whether the current delay level is above or below a threshold delay level of, e.g., 0.2 s. In this embodiment, the user provides a current delay level of, for example, 0.5s to the CL system 100. Thus, the current stall level is higher than the threshold stall level. In other embodiments, the current sensing metric level may also be automatically determined, for example, in the event that the current energy consumption level is above a threshold energy consumption level.

An RF system configuration parameter that affects most of the detection performance of the RF-based sensing is then determined based on which respective current sensing metric level of the one or more sensing metrics included in the detection performance is above or below the respective threshold sensing metric level. For example, if the current delay level is above a threshold delay level, the performance of the delay is considered suboptimal. This needs to be considered when determining the root cause that negatively affects the detection performance. CL system 100 may include a database, such as a look-up table (LUT), in which RF system configuration parameters that most affect detection performance are associated with a combination of sub-optimal performance of sensing metrics. In other embodiments, the root cause may not be an RF system configuration parameter and the RF system configuration parameter may be associated with the root cause. The LUT may be provided empirically, e.g., learned by trial and error or heuristically.

After CL system 100 determines which RF system configuration parameters have the greatest impact on detection performance, CL system 100 adjusts the RF system configuration parameters to optimize detection performance. In this embodiment, CL system 100 simulates how to adjust the RF system configuration parameters by simulating its adjustment and determining the impact on detection performance. Alternatively or additionally, CL system 100 may also determine how to adjust RF system configuration parameters based on rules (e.g., rules stored in a memory of one of the nodes), e.g., adjust particular RF system configuration parameters in a particular manner based on the current context. In other embodiments, adjusting the RF system configuration parameters that have the greatest impact on detection performance may also be performed by iteratively adjusting individual RF system configuration parameters of CL system 100 and comparing the previous detection performance to subsequent detection performance obtained by performing RF-based sensing using the individual adjusted RF system configuration parameters. This adjustment may be performed automatically by CL system 100 and/or may instruct user 26 to adjust the RF system configuration parameters, e.g., depending on which RF system configuration parameters are to be adjusted.

Accordingly, CL system 100 may use the communication interface of node 34 to provide user 26 with RF system configuration parameters that have the greatest impact on the detection performance of RF-based sensing, and how to adjust the RF system configuration parameters that have the greatest impact on the detection performance of RF-based sensing to optimize detection performance. The user 26 may receive this information, for example, via the touch display 24 or via a user device such as a mobile phone (not shown). User 26 may then adjust the RF system configuration parameters that have the greatest impact on detection performance accordingly in order to optimize detection performance.

In other embodiments, after optimizing detection performance for the RF system configuration parameters that have the greatest impact on detection performance, additional RF system configuration parameters may be adjusted to optimize detection performance. In other embodiments, for example, where adjusting the RF system configuration parameters that have the greatest impact on detection performance does not sufficiently improve detection performance, CL system 100 may determine the ordering of RF system configuration parameters that are ordered according to their respective degrees of impact on detection performance. CL system 100 may then adjust the RF system configuration parameters according to their ordering in order to optimize detection performance, i.e., may continuously adjust the RF system configuration parameters one after the other until detection performance is substantially improved, e.g., when the current detection performance level is above a threshold detection performance level. Adjustment of RF system configuration parameters may also take into account whether several RF system configuration parameters are interdependent or not, and iteratively adjust these RF system configuration parameters according to one of the techniques known to those skilled in the art

Fig. 3-6 illustrate various configurations of CL system 100 based on different adjustments to CL system 100 in order to optimize the detection performance of RF-based sensing for different contexts.

In fig. 3, a second configuration of CL system 100 is shown, wherein nodes 36 and 38 of first group 30 are moved in a horizontal plane relative to the first room so as to bring them closer to each other. This allows compensating for low RF signal strengths. In this embodiment, the sensing region 32 is also adjusted. The other nodes 34, 44, 46 and 48 do not move.

In the following, details are presented of how CL system 100 determines that mobile nodes 36 and 38 allow optimizing detection performance in the context of fig. 3.

CL system 100 first determines the extent to which the adjustment sensitivity of nodes 34, 36, and 38 affects the detection performance and finds that it does not significantly affect the detection performance. CL system 100 then examines the effect of radio interference 50 in the signal links between nodes 34, 36, and 38 on detection performance. In this case, the effect of radio interference 50 is negligible. The CL system 100 then determines the extent to which other RF system configuration parameters affect the detection performance in order to find the root cause that negatively affects the detection performance. CL system 100 finds that the signal link between two nodes (e.g., 36 and 38) has only low RF signal strength. Low RF signal strength may result in lower detection performance because RF messages are more likely to be affected by even small environmental effects and therefore they may not be received.

Based on the knowledge that the low RF signal strength between nodes 36 and 38 is the root cause of the poor detection performance of RF-based sensing, CL system 100 determines how to optimize the detection performance. Thus, CL system 100 uses an optimization method based on previous experience, i.e., adding additional new nodes does not necessarily improve detection performance, as this does not improve RF signal strength and thus does not improve the signal link between nodes 36 and 38. Accordingly, CL system 100 determines that moving node 36 and node 38 closer to each other improves detection performance because the RF path between them is stronger. Alternatively, CL system 100 may simulate several slightly modified locations of nodes 36 and 38 in order to identify the spatial arrangement of nodes 36 and 38, wherein multipath effects become more pronounced and allow for an increase in the RF signal strength of the signal link between nodes 36 and 38.

Alternatively, the position of the node may also be adjusted by moving the node in a vertical plane (i.e., in a vertical direction) rather than in a horizontal plane (i.e., in a horizontal direction). For example, a node in the form of a stand-up luminaire may have an adjustable bracket for adjusting the vertical position of the antenna array of the node transmitting and receiving RF signals, and a node in the form of a pendant may have an adjustable chain or wire for adjusting the vertical position of its antenna array. The CL system 100 may determine that adjusting the vertical position has the greatest impact on detection performance, e.g., based on metadata like a luminaire prototype, or based on direct measurement information, e.g., obtained based on an Augmented Reality (AR) measurement tool, light detection and ranging (LiDAR), laser distance measurement, etc.

If the mobile node is restricted in the horizontal direction, the CL system 100 may also determine that the vertical position of the node may be adjusted instead of moving the node in the horizontal direction. Some locations of the node may not be available, e.g., some horizontal and/or vertical locations may not be reachable by the node. Adjusting the vertical and/or horizontal position of the node increases the number of available positions. For example, ceiling luminaires have limited options in the position where they can be placed horizontally, but can be adjusted more freely in the vertical direction. This may allow for improved automatic or manual adjustment of the node position.

Alternatively, the user 26 may provide information to the CL system 100 regarding the root cause or current context of performing the RF-based sensing. This information can be used to determine which RF system configuration parameters have the greatest impact on detection performance and how to adjust the RF system configuration parameters to optimize detection performance.

For example, user 26 may indicate that RF-based sensing is not performing well near certain objects (not shown), or is not active at certain times of the day (e.g., at night), or is often not active during certain activities (e.g., another user in a neighboring room streaming video via the internet), or that RF-based sensing is not active in portions of the first room (e.g., occupancy detection fails while the user is working on a table, or respiratory rate identification fails while the user is lying on the left side of a twin bed instead of the right side).

For these contexts, CL system 100 may combine information provided by the user with additional current contexts (e.g., current settings of RF system configuration parameters) determined by CL system 100, for example. Further, for example, the CL system 100 may determine the extent to which they each affect detection performance for RF system configuration parameters, taking into account the current context.

User 26 may also, for example, provide information regarding whether certain RF system configuration parameters are adjustable. For example, if a node in the form of a luminaire spotlight with a swivel head is included in CL system 100, the directionality of the RF mode may be changed by aiming the spotlight at a different angle. In contrast, such RF system configuration parameters may not be adjustable for nodes in the form of, for example, hanging luminaires.

If user 26 inputs to CL system 100 an option to add a new node to first group 30, either by adding a node to first group 30 (e.g., node 46 from second group 40 (see fig. 4)), or adding a new node 39 to CL system 100 (see fig. 5), CL system 100 can determine how this adjustment affects detection performance and which spatial location of the newly added node optimizes detection performance.

For example, CL system 100 may determine that adding a new node as close as possible to the table on which the user is working optimizes detection performance. Alternatively, CL system 100 may also optimize detection performance based on additional current context, e.g., based on analyzing signal links between all nodes in the sensing area, and focusing on those signal links that allow for the provision of specific metadata that may infer that the node is near the location of the table where the user is working, i.e., the location where improved RF-based sensing is desired. For example, the node near the desk location may be a reading light type or have a name like "desk Left," etc. This may lead to the discovery of non-trivial RF system configuration parameters, such as new nodes in the form of ceiling lights at a central location in a room, that have the greatest impact on detection performance. Such ceiling lights may provide a signal link across the volume of the area where the table is located and may thus allow improved coverage of RF-based sensing on the table and thus optimize detection performance.

In the event that adding a node is not possible or acceptable, CL system 100 may provide the user with alternative RF system configuration parameters and information about how to adjust it. This alternative RF system configuration parameter may be, for example, a parameter that does not damage other signal links already present. For example, CL system 100 may find that one or more RF system configuration parameters that may be adjusted to optimize detection performance are the corresponding locations or locations of nodes that have the strongest signal links relative to other nodes. For these nodes, small movements do not significantly disrupt the quality of these signal links and do not result in lost RF messages that would cause RF-based sensing to be disrupted. Thus, the positions of the nodes may be adjusted to bring them closer to the table, e.g., the mobile sensing area and its coverage area.

On the other hand, the location of the mobile node may negatively impact other parts of the sensing area or other sensing applications. The CL system 100 may be configured to take this into account when optimizing detection performance. For example, nodes that have acceptable performance in the original configuration but are close to the quality threshold that are considered noisy may be further degraded by emphasis to improve RF-based sensing near the table. This may result in optimizing detection performance at the table, but reducing detection performance in another portion of the sensing area (e.g., near the door). The CL system 100 may also consider which portions of the sensing region are the region of interest and optimize detection performance such that detection in or near the region of interest is optimized.

In fig. 4, a third configuration of CL system 100 is shown, where nodes 46 are removed from second set 40 and added to first set 30. This allows to increase the detection performance of the first group 30, while it may decrease the detection performance of the second group 40. In this case, the nodes 46 are not only regrouped from the second group 40 to the first group 30, but are also spatially mobile.

Alternatively, the CL system 100 may also regroup the first set 30 and the second set 40 by removing the nodes 46 from the second set 40 and adding them to the first set 30 without adjusting the spatial location, i.e., without moving the nodes 46. This may also allow optimizing the detection performance.

The CL system 100 can determine whether the node 46 is critical to the sensing application of the second set 40 before removing it and adding it to the first set 30. CL system 100 may decide whether to remove node 46 from second set 40 and add node 46 to first set 30 based on whether node 46 is critical to the sensing application of second set 40. This may allow avoiding a significant reduction of the detection performance in the second sensing region 42.

For example, CL system 100 may determine that node 46 is disposed in sensing region 42 adjacent to first group 30, which first group 30 has strong signal links to nodes 36 and 38, based on, for example, a universal ZigBee neighbor table. CL system 100 may then determine that adding node 46 to first set 30 may be the RF system configuration parameter that has the greatest impact on detection performance to adjust. Before adjusting the RF system configuration parameters by adding node 46 to first set 30, CL system 100 may check whether the adjustment reduces the detection performance of second set 40 and/or whether and how the detection performance is optimized in first sensing region 32. The CL system 100 may alternatively or additionally determine how adding the node 46 to the first set 30 affects the operation of the second set 40, e.g., whether detection performance is reduced in the second sensing region 42, or whether the false positive rate of performing RF-based sensing in the first sensing region 32 increases due to activity in the second sensing region 42, where the node 46 is still in a position where it is not moved.

Still alternatively, the node 46 may also be included in both groups 30 and 40, and perform RF-based sensing in both sensing regions 32 and 42. In this case, CL system 100 may, for example, adjust or suggest to the user to adjust one or more sensing parameters for RF-based sensing of both groups 30 and 40. CL system 100 may also adjust or suggest to the user to adjust other RF system configuration parameters in addition to the sensed parameters. For example, the user may be instructed to move another node of the second set 40 to a new location to compensate for the lack of resolution or reliability in performing RF-based sensing in the first sensing region 32 or the second sensing region 42.

In fig. 5, a fourth configuration of CL system 100 is presented, wherein node 39 is added to first group 30 for mitigating wireless interference 50. In this configuration, radio interference 50 is caused by operation of the second group 40. Environmental effects may also include, for example, RF noise provided by any other noise source, such as a microwave oven or video streaming television.

The first group 30 is arranged in a corridor and the user 26 has spent some time configuring the nodes 34, 36 and 38 of the first group 30 for performing RF-based sensing in the corridor to ensure a satisfactory balance between fast motion detection and avoiding false positives in adjacent living rooms comprising the second group 40.

If the detection performance is unsatisfactory, user 26 may report his dissatisfaction to CL system 100, e.g., via the communication interface of node 34, e.g., using an app on the user device and transmitting this information to node 34 or using any other available user interface (such as a touch display).

In response, CL system 100 first checks the effect of all RF system configuration parameters on detection performance. The CL system 100 then determines that the root cause that negatively affects detection performance is that the signal link between nodes 34, 36, and 38 is too noisy, i.e., in this case, the Received Signal Strength Indication (RSSI) or Channel State Information (CSI) fluctuates too much (e.g., above a threshold). The CL system 100 then determines the best solution for mitigating the root cause of the negatively impacted detection performance (i.e., the noise signal links between nodes 34, 36, and 38) is to add additional nodes to the group 30. The CL system 100 understands that adding data from the additional signal links will enable the sensing analysis algorithm to further correlate what has been observed by the original signal links, but with a higher confidence. This allows detection of sensed events with higher confidence.

For example, the RF system may determine that any signal link having an amplitude fluctuation of, for example, more than 20% of the historical value (e.g., the historical average determined for a certain time window) is considered noisy. Alternatively, the RF system may also measure the frequency of the amplitude peaks and determine that the signal link is currently extremely noisy based on the frequency of the amplitude peaks.

In fig. 6, a fifth configuration of CL system 100 is shown, where nodes 34, 36, 44, and 46 are regrouped into first group 30 and groups 38 and 48 are regrouped into second group 40. This also adjusts sensing regions 32 and 42. Regrouping the nodes 34 to 48 may allow optimizing the detection performance based on the current context, e.g. in case adjusting the sensing area improves the detection performance, e.g. when the sensing event occurs in a part of the sensing area that is not well covered and the adjusting the sensing area optimizes the coverage. In other cases, the node may additionally be moved.

In the following, without the figures, further scenarios are presented, i.e. CL systems 100 operating in different current contexts.

The CL system 100 can determine not only the node that has the greatest impact on detection performance when moving, but also how moving that node affects other sensing applications. For example, if a particular sensing metric is to be optimized for a particular sensing application (e.g., for detecting a delay in occupancy of a user entering a sensing area), this may affect other sensing applications (e.g., respiratory rate identification of the respiratory rate of the first of two users lying in a twin bed).

For example, if a bedroom has two nodes in the form of a free-fall night light and a ceiling light, this configuration may not be sufficient to achieve a sufficiently low delay in turning on the light when the user enters the room. The CL system 100 may determine that moving one of the free-standing night lights 30cm closer to the room entrance due to the size of the bedroom, the type of room being bedroom, etc., allows for optimizing detection performance. In this case, such adjustment simulating the location of the free-fall night light reduces the delay without significantly degrading the signal link between the nodes, and the simulation can then be checked by performing RF-based sensing to confirm the simulation.

However, moving one of the free-standing night lights 30cm when the second user is lying on the second side of the twin bed can significantly affect the detection performance of the breath rate identification of the first user lying on the first side of the twin bed. For example, since 2.4GHz or 5GHz WiFi signals show low restrictions, i.e. they have no clear demarcation, the RF signal can now interact not only with the first user, but also with a second user lying on the second side of the twin bed after the free-standing night light has been moved 30 cm. Thus, moving a free-fall night light 30cm may greatly interfere with the RF sensing analysis algorithm for respiratory rate identification.

In this case, CL system 100 may defer moving the free-fall night light 30cm and instead determine to adjust alternative RF system configuration parameters, such as RF system configuration parameters that have the greatest impact on the detection performance of occupancy detection while not significantly degrading or even improving the detection performance of breath rate identification. For example, new nodes may be added to groups closer to the room entrance for performing RF-based sensing in the sensing region. Alternatively, for example, the messaging rate may be increased.

Still alternatively, CL system 100 may also determine that moving a free-fall night light in a horizontal plane or adjusting its height may be preferable to adding a new node. Adding new nodes may increase the resources required for each node in the group to perform RF-based sensing because, for example, more nodes need to be tracked and the amount of data traffic between nodes increases. Thus, adding new nodes may have an adverse effect on detection performance, as for example data traffic, radio interference and energy consumption are increased.

Accordingly, CL system 100 can determine whether to improve detection performance by increasing one sensing metric while decreasing another sensing metric (e.g., increasing data traffic). CL system 100 may, for example, determine that data traffic in the sensing region has approached a network congestion threshold, for example, at which messages were successfully received. Thus, adding yet another new node to the group performing RF-based sensing in the sensing region will further reduce this already weak sensing metric and may even cause the data traffic to exceed the network blocking threshold such that RF messages will be lost. Based on this current context, CL system 100 may determine that it is preferable to adjust another RF system configuration parameter rather than adding a new node or increasing the message transfer rate, e.g., moving a free-fall night light in a horizontal or vertical plane.

In summary, the RF system may automatically improve or provide feedback to the user to improve detection performance in a particular sensing region. The RF system may identify the root cause that negatively affects detection performance because the user considers RF-based sensing to be suboptimal. Based on this root cause, the RF system may provide advice to improve detection performance by adjusting one or more RF system configuration parameters, and in particular the RF system configuration parameters that have the greatest impact on detection performance. The suggestions for improving detection performance may also take into account the current context, including for example, the sensing application or desired sensing function, respectively prioritized, the type of primary activity in the sensing area, tolerance to false detection, latency requirements, latency expectations, or any other context. For example, the different contexts cause the RF system to adjust or suggest which RF system configuration parameter or parameters should be adjusted by, for example, adding nodes or changing the spatial location of existing nodes. The current context may also allow deciding how the RF system intentionally trades off between the performance of different sensing metrics that are simultaneously served by the same RF system, e.g. breath detection in the sensing region versus faster motion sensing and fall detection in the adjacent sensing region, in order to improve the detection performance including the performance of the different sensing metrics.

The overall goal of the RF system is to improve detection performance, for example, by providing the user with more relevant advice or options to adjust RF system configuration parameters, rather than simply adjusting sensitivity levels of the prior art. Adjustment of RF system configuration parameters allows for fine tuning of RF-based sensing in a highly context-aware, and in particular sensing application-aware, manner.

The RF system may allow guiding the user to optimize the detection performance, especially without the user knowing the root cause of the detection performance degradation and/or how to optimize the detection performance. The RF system may guide the user in response to information provided by the user about the current context and information obtained by the RF system itself about the current context. For example, a user may indicate that the delay is too long (i.e., RF-based sensing takes too long) whenever the user enters the sensing area from the front door, and not when the user enters from the other door. In this case, the user may provide the RF system with the current context of why the detection performance is inadequate without himself knowing the root cause of the detection performance degradation, e.g., too many or too few nodes performing RF-based sensing, insufficient sampling rate, too low transmission power, etc. However, combining information provided by the user about the current context with information about the current context of the RF system may allow finding the root cause and then determining how to optimize the detection performance.

Fig. 7 illustrates an embodiment of a method 700 for optimizing detection performance for performing RF-based sensing based on RF system configuration parameters. The method may be performed, for example, by an RF system (e.g., CL system 100 presented with respect to fig. 2-6).

In step 702, the user provides information about the current context for performing RF-based sensing by a set of nodes in a sensing region and a sensing metric of user dissatisfaction. For example, a user provides an RF system for occupancy detection and a delay requirement of 0.2s is provided to complete detection in order to allow a fast reaction of the RF system, e.g. to turn on the illumination when the user enters the sensing area. The user may also provide that he is not satisfied with the delay, for example because the delay exceeds 0.2s (e.g. 0.4 s).

In step 704, a current context in which RF-based sensing is performed by the group in the sensing region is determined based on information provided by the user and information obtained by the nodes, e.g., current settings of RF system configuration parameters including a current spatial arrangement of the nodes, and a number of nodes in the group for performing RF-based sensing in the sensing region. Information provided by the user and obtained by the node is analyzed.

In step 706, RF-based sensing is performed in a sensing region by a set of nodes of the RF system.

In step 708, a current detection performance level of the RF-based sensing is determined based on the performed RF-based sensing. In this case, the current detection performance level depends on the current delay of detecting occupancy. If the detection performance level is above the threshold detection performance level, then the current RF system configuration parameters are used to perform RF-based sensing in the sensing region, i.e., step 706 is performed whenever the current detection performance level of the RF-based sensing is above the threshold detection performance level. If the current detection performance level is below the threshold detection performance level, step 710 is performed to optimize the detection performance of the RF-based sensing. In this case, the delay is higher than the delay requirement of 0.2s, and the resulting current detection performance level is lower than the threshold detection performance level, so that step 710 is performed.

In step 710, the RF system configuration parameter that affects most on the detection performance of the RF-based sensing is determined from among the RF system configuration parameters based on the current context of the sensing metric included in the detection performance and the current sensing metric level. Accordingly, it is determined whether a respective current sensing measure level of the sensing measure included in the detection performance is lower than a respective threshold sensing measure level. In this case, the delay is determined to be higher than the delay requirement, which corresponds to the sensing metric level being lower than the threshold sensing metric level. In response, the RF system configuration parameters affecting the respective sensing metrics having a sensing metric level lower than the respective threshold sensing metric level are determined from the LUT comprising information associated with which RF system configuration parameter most affects which sensing metric. In this case, delays are generated due to the limited processing power of the nodes in the group.

In step 712, the user is provided with information of which RF system configuration parameters most affect the detection performance of the RF-based sensing. In this case, the user is provided with information that the capabilities of the nodes in the group have the greatest impact on the detection performance, since the processing power of the nodes is too low to perform RF-based sensing with low latency.

Additionally, the user is provided with information on how to adjust the RF system configuration parameters that have the greatest impact on the detection performance of the RF-based sensing to optimize the detection performance. In this case, the user is provided with information that the node having the lower processing power may be replaced by the node having the higher processing power or that the node having the higher processing power may be added to the group. In other embodiments, this information may be provided to the RF system node that optimizes the RF system configuration parameters that have the greatest impact on detection performance. For example, if the transmit power is the RF system configuration parameter that has the greatest impact on detection performance, one or more of the respective nodes may adjust their transmit power to optimize detection performance.

In step 714, the user adjusts RF system configuration parameters that have the greatest impact on the detection performance of the RF-based sensing in order to optimize the detection performance of the RF-based sensing. In this case, additional nodes with higher processing power are added to the group in order to reduce the delay.

In other embodiments, the node of the RF system may automatically adjust the RF system configuration parameters that have the greatest impact on the detection performance of the RF-based sensing based on information (e.g., increasing transmit power) on how to adjust the RF system configuration parameters that have the greatest impact on the detection performance to optimize the detection performance.

In other embodiments, an ordering of one or more RF system configuration parameters may be determined that respectively order the degree of impact of the RF-based sensed detection performance according to the one or more RF system configuration parameters, and the RF system configuration parameters may be adjusted based on the ordering in order to optimize the RF-based sensed detection performance.

While the invention has been illustrated and described in detail in the drawings and foregoing description, such illustration and description are to be considered illustrative or exemplary and not restrictive; the invention is not limited to the disclosed embodiments. For example, it is possible to operate the invention in an embodiment where the RF system is a heating, ventilation and air conditioning (HVAC) system or any other smart home system. The RF system may also operate in the context of a BMS environment, a smart home environment, an office environment, or a residential environment.

Other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims.

In the claims, the words "comprise" and "comprising" do not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality.

A single unit, processor or device may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

Operations performed by one or several units or devices (e.g., performing RF-based sensing in a sensing region by a group of at least two nodes of an RF system comprising a plurality of nodes, determining an RF system configuration parameter of the one or more RF system configuration parameters that affects most of the detection performance of the RF-based sensing, adjusting the RF system configuration parameter that affects most of the detection performance in order to optimize the detection performance of the RF-based sensing, etc.) may be performed by any other number of units or devices. The operations and/or methods may be implemented as program code means of a computer program and/or as dedicated hardware.

A computer program product may be stored/distributed on a suitable medium, such as an optical storage medium or a solid-state medium, provided together with or as part of other hardware; but may also be distributed in other forms, such as via the internet, ethernet, or other wired or wireless telecommunication systems.

Any reference signs in the claims shall not be construed as limiting the scope.

The present invention relates to an RF system having a plurality of nodes and a method for optimizing detection performance for performing RF-based sensing in a sensing region based on RF system configuration parameters. The RF system configuration parameters that have the greatest impact on the detection performance of the RF-based sensing are determined. Then, the RF system configuration parameters that have the greatest impact on the detection performance of the RF-based sensing are adjusted in order to optimize the detection performance of the RF-based sensing. The root cause of the detection performance degradation and the corresponding RF system configuration parameters for mitigating the detection performance degradation may be determined based on the current context. To optimize detection performance, for example, the settings of the sensing parameters of the nodes may be adjusted, or the nodes may be moved, removed, added, or replaced.

Claims (15)

1. A radio frequency system (100) for optimizing detection performance for performing radio frequency based sensing based on radio frequency system configuration parameters, the radio frequency system (100) comprising a plurality of nodes (34, 36, 38, 39, 44, 46, 48), a group (30) of at least two of the nodes (34, 36, 38;39; 46) being configured for performing radio frequency based sensing in a sensing region (32), wherein a first node of the at least two nodes (34, 36, 38;39; 46) is configured for transmitting radio frequency signals and a second node of the at least two nodes (34, 36, 38;39; 46) is configured for receiving the transmitted radio frequency signals, and wherein radio frequency based sensing is performed by analyzing interference to the radio frequency signals caused by one or more objects or persons interacting on a transmission path between the radio frequency signals and the at least two nodes (34, 36, 38;39; 46),

Wherein the radio frequency system (100) is configured for determining radio frequency system configuration parameters having the greatest influence on the detection performance of the radio frequency based sensing among the radio frequency system configuration parameters, and for adjusting the radio frequency system configuration parameters having the greatest influence on the detection performance of the radio frequency based sensing in order to optimize the detection performance of the radio frequency based sensing.

2. The radio frequency system (100) of claim 1, wherein the radio frequency system configuration parameters include one or more of:

a spatial arrangement of at least two nodes (34, 36, 38) of the group (32),

grouping of the plurality of nodes (34, …, 48) into the group (30),

the number of nodes (34, 36, 38) in the group (30),

-the capabilities of the nodes (34, 36, 38) in the group, and

-one or more sensing parameters for performing radio frequency based sensing.

3. The radio frequency system (100) according to claim 1 or 2, wherein the radio frequency system (100) is configured for determining radio frequency system configuration parameters that most affect the detection performance of the radio frequency based sensing based on a current context.

4. A radio frequency system (100) according to claim 3, wherein the current context comprises one or more of:

A setting of one or more of said radio frequency system configuration parameters,

the sensing application is performed in a manner that,

the delay requirement is set up in such a way that,

an expected sensing event in the sensing region (32),

the need for privacy is to be understood,

the radio power consumption requirements are that,

the radio transmission power requirements are set,

the radio beam shape requirements,

the radio reception beamforming requirements,

-a current location of the radio frequency system (100),

a current location of at least one of the at least two nodes (34, 36, 38),

-a current position of a tangible entity (26) in the sensing region (32),

the current date of the day,

a current mode of operation of at least one of the at least two nodes (34, 36, 38),

-environmental impact (50),

-bandwidth currently available in said radio frequency system (100),

current capabilities of at least one of the at least two nodes (34, 36, 38),

a current property of the sensing region (32),

-error event detection rate requirement, and

missing event detection requirements.

5. The radio frequency system (100) of at least one of claims 1 to 4, wherein the detection performance comprises one or more sensing metrics, the one or more sensing metrics comprising one or more of:

The delay time is set to be equal to the delay time,

the degree of accuracy is chosen to be,

the spatial resolution of the optical system is chosen,

a false positive detection rate of the detection of the presence of a signal,

-a rate of detection of false negatives,

confidence level for detecting a sensed event,

-sensing noise in the event detection,

-a data traffic volume to be generated,

energy consumption, and

-spatial limitation of the radio frequency signal for performing radio frequency based sensing.

6. The radio frequency system (100) according to claim 5, wherein the radio frequency system (100) is configured for determining radio frequency system configuration parameters that have the greatest influence on the detection performance of the radio frequency based sensing based on one or more sensing metrics included in the detection performance.

7. The radio frequency system (100) according to claim 5 or 6, wherein the radio frequency system (100) is configured for

-determining whether a respective current sensing level of one or more sensing metrics comprised in the detection performance is higher or lower than a respective threshold sensing level, and

-determining a radio frequency system configuration parameter having the greatest influence on the detection performance of the radio frequency based sensing based on which respective current sensing metric level of one or more sensing metrics comprised in the detection performance is above or below a respective threshold sensing metric level.

8. The radio frequency system (100) according to at least one of claims 1 to 7, wherein the radio frequency system (100) is configured for

-determining a current detection performance level of the radio frequency based sensing, and

-optimizing detection performance based on whether the current detection performance level is above or below a threshold detection performance level.

9. The radio frequency system (100) according to at least one of claims 1 to 8, wherein the radio frequency system (100) is configured for

-determining a ranking of the one or more radio frequency system configuration parameters, the one or more radio frequency system configuration parameters being ranked according to their respective degree of influence on the detection performance of the radio frequency based sensing, and

-adjusting the radio frequency system configuration parameters based on the ordering in order to optimize detection performance of radio frequency based sensing.

10. The radio frequency system (100) according to at least one of claims 1 to 9, wherein the radio frequency system (100) is configured for one or both of:

-providing radio frequency system configuration parameters that have the greatest influence on the detection performance of radio frequency based sensing, and

-providing how to adjust radio frequency system configuration parameters that have the greatest impact on the detection performance of radio frequency based sensing to optimize the detection performance.

11. The radio frequency system (100) according to claim 10, wherein the radio frequency system (100) comprises a communication interface (14) for one or both of:

-providing the user (26) with radio frequency system configuration parameters that have the greatest influence on the detection performance of the radio frequency based sensing, and

-providing the user (26) with radio frequency system configuration parameters that are to be adjusted to maximize the detection performance of the radio frequency based sensing to optimize the detection performance.

12. A method for optimizing detection performance for performing radio frequency based sensing based on radio frequency system configuration parameters, the method comprising the steps of:

performing radio frequency based sensing in a sensing area by a group of at least two nodes of a radio frequency system comprising a plurality of nodes, wherein a first node of the at least two nodes (34, 36, 38;39; 46) is configured for transmitting radio frequency signals and a second node of the at least two nodes (34, 36, 38;39; 46) is configured for receiving the transmitted radio frequency signals, and wherein radio frequency based sensing is performed by analyzing interference on the radio frequency signals caused by interactions of the radio frequency signals with one or more objects or people on a transmission path between the at least two nodes (34, 36, 38;39; 46),

-determining the radio frequency system configuration parameters of the radio frequency system configuration parameters that have the greatest influence on the detection performance of radio frequency based sensing, and

-adjusting radio frequency system configuration parameters that have the greatest influence on the detection performance of the radio frequency based sensing in order to optimize the detection performance of the radio frequency based sensing.

13. The method of claim 12, comprising one or more of the following steps:

determining a current context for performing radio frequency based sensing by a group in the sensing region,

determining radio frequency system configuration parameters affecting most detection performance of radio frequency based sensing based on the current context,

determining radio frequency system configuration parameters that have the greatest impact on the detection performance of radio frequency based sensing based on one or more sensing metrics included in the detection performance,

determining whether a respective current sensing level of one or more sensing metrics included in the detection performance is above or below a respective threshold sensing level,

determining radio frequency system configuration parameters that have the greatest impact on the detection performance of the radio frequency based sensing based on which of the respective current sensing metric levels of the one or more sensing metrics included in the detection performance is above or below the respective threshold sensing metric level,

Determining a current detection performance level of the radio frequency based sensing,

optimizing the detection performance based on whether the current detection performance level is above or below a threshold detection performance level,

determining a ranking of the one or more radio frequency system configuration parameters based on the extent to which the one or more radio frequency system configuration parameters affect the detection performance of the radio frequency based sensing, respectively,

adjusting radio frequency system configuration parameters based on the ordering in order to optimize detection performance of radio frequency based sensing,

providing radio frequency system configuration parameters that have the greatest impact on the detection performance of radio frequency based sensing,

providing how to adjust radio frequency system configuration parameters that have the greatest impact on the detection performance of radio frequency based sensing to optimize the detection performance,

-providing the user with radio frequency system configuration parameters that have the greatest influence on the detection performance of the radio frequency based sensing, and

-providing the user with how to adjust radio frequency system configuration parameters that have the greatest impact on the detection performance of the radio frequency based sensing to optimize the detection performance.

14. A computer program product for optimizing detection performance of radio frequency based sensing, wherein the computer program product comprises program code means for causing a processor (18) to carry out the method as claimed in claim 12 or 13 when the computer program product is run on the processor (18).

15. A computer readable medium (20) having stored the computer program product according to claim 14.