WO2022122141A1

WO2022122141A1 - Sensor node, sensing system, and methods of sensing a component of a gas

Info

Publication number: WO2022122141A1
Application number: PCT/EP2020/085180
Authority: WO
Inventors: Sidharta Andalam; Nahong ZHAO
Original assignee: Robert Bosch Gmbh
Priority date: 2020-12-09
Filing date: 2020-12-09
Publication date: 2022-06-16

Abstract

A sensor node for detection of fungus including a sensor to detect at least one component in a gas by a change of an electrical property, and a control circuit to control a temperature and to measure a transient of the electrical property during an application of a thermal pulse on the sensor. Another aspect concerns a sensing system including one or more sensor nodes, and a server for receiving data from the sensor nodes. Another aspect concerns a method for sensing, including generating a thermal pulse by a control circuit so that information is generated based on a measurement of a transient of an electrical property of a sensor based on the detection of at least one component in a gas, recording the transient, calculating and processing a plurality of parameters into principal components, and processing the principal components to determine a likelihood of a colonization by fungus.

Description

SENSOR NODE, SENSING SYSTEM, AND METHODS OF SENSING A COMPONENT OF A GAS

TECHNICAL FIELD

[0001 ] Various aspects of this disclosure relate to a sensor node and a sensing system. Various aspects of this disclosure relate to a method of sensing.

BACKGROUND

[0002] Ganoderma fungus grows at the roots, stems, and at the base of the plant, and causes a mortality rate of approximately 75% to 85% of infected plants, leading to major long-term crop losses.

[0003] As such, there is huge demand for disease detection methods that allow for the early detection of the Ganoderma fungus. Specifically, there is demand for efficient and cost effective sensors for the early detection of the Ganoderma fungus and basal stem rot disease.

SUMMARY

[0004] Various embodiments may provide a sensor node for detection of fungus. The sensor node may include a sensor configured to detect at least one component in a gas, such as air, by a change of an electrical property of the sensor. The sensor node may further include a control circuit configured to control a temperature of the sensor and to measure a transient of the electrical property during an application of a thermal pulse on the sensor.

[0005] Various embodiments may provide a sensing system. The sensing system may include one or more sensor nodes. The sensing system may include a server for receiving data from the sensor nodes. The server may be configured to determine server-side principal components based on the plurality of parameters. Alternatively, the server may be configured to determine server-side plurality of parameters based on the transient, and may be further configured to determine server-side principal components based on the server-side plurality of parameters. According to various embodiments, the parameters may be selected or calculated from one or more of resistance, humidity, temperature.

[0006] Various embodiments may provide a method of sensing. The method may include generating a thermal pulse by a control circuit. Information may be generated based on a measurement of a transient of an electrical property of a sensor. The transient may be based on the detection of at least one component in a gas, such as air. The method may further include recording the transient in the control circuit, and calculating a plurality of parameters based on the transient. The method may further include processing the plurality of parameters into principal components based on the plurality of parameters. The method may further include processing the principal components to determine a likelihood of a colonization of crop by fungus.

BRIEF DESCRIPTION OF THE DRAWINGS

[0007] The invention will be better understood with reference to the detailed description when considered in conjunction with the non-limiting examples and the accompanying drawings, in which:

- FIG. 1 shows a general schematic of a sensor node 100 according to one embodiment, including a sensor 110 and a control circuit 120;

- FIG. 2 shows a graph 200 illustrating a transient 220 of an electrical property during an application of a thermal pulse 210 on the sensor 110, in accordance with various embodiments;

- FIG. 3 shows a table of the major volatile organic components that may be detected by the sensor node 100, in accordance with various embodiments;

- FIG. 4 shows a general schematic of a sensor node 100 according to another embodiment, including a sensor 110, a control circuit 120, and a communication circuit 126;

- FIG. 5A shows a sensing system 500A according to one embodiment;

- FIG. 5B shows a sensing system 500B according to another embodiment;

- FIG. 6 illustrates a method of sensing 600 according to various embodiments;

- FIG. 7 shows a graph 700 onto which PCA components may be plotted;

- FIG. 8 shows a graph 800 illustrating a thermal pulse 810 and 820, and a transient 812 and 822 based on a change of an electrical property of a sensor generated under a pulsed heating and cooling program, in accordance with various embodiments; and

- FIG. 9 shows a plot 900 of a primary pattern classification based on a principal component analysis method, in accordance with various embodiments.

DETAILED DESCRIPTION

[0008] The following detailed description refers to the accompanying drawings that show, by way of illustration, specific details and embodiments in which the disclosure may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the disclosure. Other embodiments may be utilized and structural, and logical changes may be made without departing from the scope of the disclosure. The various embodiments are not necessarily mutually exclusive, as some embodiments can be combined with one or more other embodiments to form new embodiments.

[0009] Features that are described in the context of an embodiment may correspondingly be applicable to the same or similar features in the other embodiments. Features that are described in the context of an embodiment may correspondingly be applicable to the other embodiments, even if not explicitly described in these other embodiments. Furthermore, additions and/or combinations and/or alternatives as described for a feature in the context of an embodiment may correspondingly be applicable to the same or similar feature in the other embodiments.

[0010] The disclosure illustratively described herein may suitably be practiced in the absence of any element or elements, limitation or limitations, not specifically disclosed herein. Thus, for example, the terms “comprising”, “including,” containing”, etc. shall be read expansively and without limitation. The word "comprise" or variations such as "comprises" or "comprising" will accordingly be understood to imply the inclusion of a stated integer or groups of integers but not the exclusion of any other integer or group of integers. Additionally, the terms and expressions employed herein have been used as terms of description and not of limitation, and there is no intention in the use of such terms and expressions of excluding any equivalents of the features shown and described or portions thereof, but it is recognized that various modifications are possible within the scope of the disclosure. Thus, it should be understood that although the present disclosure has been specifically disclosed by exemplary embodiments and optional features, modification and variation of the disclosure embodied herein may be resorted to by those skilled in the art.

[0011] In the context of various embodiments, the articles “a”, “an” and “the” as used with regard to a feature or element include a reference to one or more of the features or elements. As used herein, the term “and/or” includes any and all combinations of one or more of the associated listed items.

[0012] The reference signs included in parenthesis in the claims are for ease of understanding of the invention and have no limiting effect on the scope of the claims. [0013] According to various embodiments, the term “crop” may refer to a plant or animal product, which may be harvested for example, for subsistence, and may be cultivated in agriculture or aquaculture. For example, the crop may refer to a plant product, and may include, for example plants of the genus Elaeis (palm oil) which are used in commercial agriculture for the production of palm oil. Within the context of the present disclosure, the plant product of genus Elaeis may be the Elaeis guineensis species which may be a species of palm oil plant. Elaeis guineensis is a principal source of palm oil and may be found in countries accounting for a large proportion of palm oil production, for example in Malaysia and Indonesia.

[0014] According to various embodiments, the term “fungus” (or “fungi”) may define an eukaryotic microorganism which survives by decomposing and absorbing the organic material in which they grow in. Fungus may include molds, yeasts, mushrooms, and may further include fungus of the Ganoderma genus. Within the context of the present disclosure, fungus of the Ganoderma genus may be the Ganoderma boninense (Ganoderma orbiforme) species, a polypore fungus that is widespread across Southeast Asia. Ganoderma boninense is the plant pathogen that causes basal stem rot disease in the palm oil plant. According to various embodiments, “fungus” (or “fungi”) may refer to an eukaryotic microorganism which survives on the crop. [0015] According to various embodiments, the term “mycelium” may refer to the vegetative part of the fungus and is mainly characterized by a mass of branching, thread-like hyphae. Mycelia are vital in ecosystems for their role in the decomposition of plant material. For example, fungus may absorb nutrients from its environment through the mycelium. Within the context of the present disclosure, the Ganoderma boninense fungus may include different proportions of mycelium, which may be an indicator of the presence of the basal stem rot disease and its progression.

[0016] According to various embodiments, the term “at least one component in a gas” may refer to one or more different components or species in gas form, vapor form, suspended in the gas, or a mixture thereof. For example, components of a gas may include gases such as carbon dioxide, oxygen, and volatile organic compounds (VOCs). The term VOC may include one (single) species of VOC, and may include a composition of VOCs with more than one species of VOCs (a mixture of different species of VOCs). The component may include an aerosol suspended in the gas. [0017] According to various embodiments, “gas” may refer to air. “Air” as used herein may be ambient air, for example from the crop planation, soil air, for example air in soil of the crop plantation, or a combination including ambient air and soil air.

[0018] According to various embodiments, the term “electrical property” may refer to an electrical property of a sensor. For example, the electrical property of a sensor may include an electrical impedance of the sensor or a component thereof, such as an electrical resistance of the sensor. The electrical property may depend on the temperature of the sensor. Accordingly, the term “a change in an electrical property” may refer to a change in the impedance, e.g., the resistance of the sensor. Such a change may be measured, for example, by measuring voltage drop over the sensor using a constant probe current, or, for example, by measuring a current passing through the sensor when applying a constant voltage.

[0019] According to various embodiments, the term “thermal pulse” may refer to the application of a signal, for example, a pulse wave which may be a non-sinusoidal periodic waveform in which the amplitude alternates between fixed maximum and minimum values. Within the context of the present disclosure, the thermal pulse may be a square pulse. [0020] According to various embodiments, the term “transient” may be measured as the evolution of the electrical property over time upon application of a square thermal signal, such as the rising edge of the thermal pulse. The transient may end when a pre-defined level, e.g., a predefined steady state is achieved. According to various embodiments, a pre-defined time period, for example, a transient duration may be used for measuring the transient. Other parameters which may characterize the transient may include the transient height, transient slope time and/or the transient gradient.

[0021] According to various embodiments, a circuit may include analog circuits or components, digital circuits or components, or hybrid circuits or components. Any other kind of implementation of the respective functions which will be described in more detail below may also be understood as a "circuit" in accordance with an alternative embodiment. A digital circuit may be understood as any kind of a logic implementing entity, which may be special purpose circuitry or a processor executing software stored in a memory, firmware, or any combination thereof. Thus, in various embodiments, a "digital circuit" may be a hard-wired logic circuit or a programmable logic circuit such as a programmable processor, e.g. a microprocessor (e.g. a Complex Instruction Set Computer (CISC) processor or a Reduced Instruction Set Computer (RISC) processor). A "digital circuit" may also be a processor executing software, e.g. any kind of computer program, e.g. a computer program using a virtual machine code such as e.g. C-language and Python.

[0022] FIG. 1 provides a schematic illustration of a sensor node 100 for detection of fungus, according to various embodiments. The sensor node 100 may include a sensor 110 and a control circuit 120. The control circuit 120 may be in electrical connection with the sensor 110. The sensor 110 may include a sensing element 112, a heater 114 and a gas exchange opening 116. The sensing element 112 may be a transducer. The gas exchange opening 116 allows at least one component in a gas to come into contact with the sensing element 112. The sensing element 112 may refer to a device that may be configured to measure a physical property of a target gas, and may produce a signal which conveys information about the target gas. The sensing element 112 may be configured to detect the target gas upon the application of a thermal pulse 210 on the sensor 110. [0023] The application of the thermal pulse 210 may be controlled by the control circuit 120, since the control circuit 120 may be configured to control a temperature of the sensor 110. For example, the sensor 110 may include a heater 114 configured to control the temperature of the sensor 110. The heater 114 may be switched on or off in the various phases of heating and cooling of the sensor 110. The heater 114 may produce heat for the application of a thermal pulse 210 by the control circuit 120. Therefore, the control circuit 120 may control the temperature of the sensor 110 by controlling the heater 114 for the application of the thermal pulse 210 on the sensor 110. Upon application of the thermal pulse 210, the sensing element 112 may detect at least one component of a gas through a change in the electrical property of the sensor 110, for example, a change in the resistance of current flow through the sensing element 112. After detection, the sensing element 112 in the sensor 110 may transmit the information to the control circuit 120. The information may include data on the at least one component in a gas, for example, the current flowing through the sensing layer 112.

[0024] The control circuit 120 may also be configured to measure a transient 220 of the electrical property during the application of a thermal pulse 210 on the sensor 110. After receiving the information from the sensor 110, the control circuit 120 may measure the transient 220 based on the information. The transient 220 may convey information on the type(s) and amount(s) of gas component(s) detected. After measuring the transient 220, the control circuit 120 may be configured to determine a plurality of parameters based on the transient 220. The plurality of parameters may be correlated and may include information on the transient 220 such as a transient height, a transient slope time, and a transient gradient. The control circuit 120 may be further configured to determine principal components based on the plurality of parameters. The control circuit 120 may determine the principal components using a principal component analysis (PCA) statistical procedure. For example, principal components may be determined using orthogonal transformation to convert the correlated plurality of parameters into a set of values of linearly uncorrelated variables. PCA may be used to make predictive models and may be used to visualize genetic distance and relatedness between data. [0025] PCA allows to efficiently identify the dominating and/or influential parameters. It was found that using PCA is advantageous in the present application, e.g., when the sensor node is deployed in an open and/or uncontrolled environment. [0026] The control circuit 120 may store a reference table, which may include reference data. The reference data may be a composition or profile of data on the different type(s) and amount(s) of gas component(s) associated with different conditions. For example, the reference data may include a VOC profile for that of a healthy crop, and a VOC profile for that of a crop colonized by fungus. The reference data may also include a VOC profile which indicates the severity or degree of crop colonization by the fungus. For example, the reference data may include a VOC profile which enables the early detection of the fungus, and a VOC profile which indicates severe crop colonization by the fungus. For example, a colonization may indicate that it is too late to save the sick crop. Reference data, for example for healthy crop, colonized crop, or different degrees of colonization of crop, may be obtained in the field. The reference data may be verified by comparing to results from an analytical method, for example a method that separates and detects individual components of the gas. Currently, gas chromatography-mass spectrometry (GC-MS) is the main method for detecting fungal VOCs due to its powerful separation and highly sensitive detection capabilities. GC-MS may be used to identify different VOC components, for example, different type(s) and amount(s) of VOCs within a test sample. The VOC components may be identified using a library of database of mass spectra, or by comparison of retention times and spectra with those of known standards.

[0027] The control circuit 120 may be configured to determine principal components based on the plurality of parameters. The principal components may be determined through a PCA operation, for example, by determining the eigenvectors and eigenvalues of the data, for example, the data including or based on the plurality of parameters. Based on the correlation between the principal components with the reference data, the control circuit 120 may generate information, such as a primary pattern classification plot which provides an indication on the health of the crop, specifically on the likelihood of colonization of a crop by fungus, and/or the degree of colonization of a crop by fungus. [0028] According to various embodiments, one or more of the following parameters may be determined from the resistance measurement (e.g., the resistance of current flow through the sensing element 112) as part of the plurality of parameters and used for PCA (LIST 1 ): o R - resistance; o Diff(Rj, Rj) - difference in resistance between two samples; o Norm(R) - normalized value for resistance R; o Diff(Normj,Norrrij) - difference in normalized resistance between two samples; o 1/R - reciprocal of R; o Norm(1/R) - normalized reciprocal of R; o Diff(1/Rj,1/Rj) - difference reciprocal of R between two samples; wherein the indices i, j are used to indicate that there are two different samples. The plurality of parameters may further include one or more of: temperature, moisture.

[0029] According to various embodiments, resistivity may be used instead of resistance.

[0030] In Examples, Diff(1/Ri,1/Rj) was found, via PCA, to be the most dominating component, amongst the parameters of the LIST 1 .

[0031] According to some embodiments, the control circuit 120 may further be configured to carry out a calibration by determining the correlation between one or more principal components with the reference data. For example, the control circuit 120 may compare the principal components with the reference data to identify the types(s) detected and amount(s) of gas detected.

[0032] According to some embodiments, the calibration may be made completely or partially by a circuit other than the control circuit, e.g., by a server.

[0033] According to various embodiments, the sensor may be micro- electromechanical systems (MEMS) based multi-pixel gas sensor.

[0034] According to various embodiments, the sensor may be a metal oxide semiconductor sensor. A metal oxide semiconductor sensor may include a substrate, a heating layer (also referred to as “heater”) on the substrate and a sensing layer (also referred to as “sensing element”) on the seed layer. Other arrangements are also possible. A first electrode and a second electrode may be in contact with respective ends of the sensing layer. The sensing layer may be formed from materials such as tin dioxide (SnC ), tungsten trioxide (WO3), and zinc oxide (ZnO). During operation, a voltage is applied to the heater, which heats up the sensing layer. It may also be envisioned that the sensing layer may include other materials such as organic materials. A potential difference is then applied between the first electrode and the second electrode so that a current flows through the electrodes and the sensing layer. In the presence of a gas such as a VOC, the gas components may bind to the grain boundaries of the sensing layer via adsorption, thus changing (i.e. increasing or reducing) the current flowing through the sensor. The change of the current depends on the type and/or amount of gas component. The metal-oxide sensor may thus be able to detect the presence of different types and amounts of gas components.

[0035] Alternatively, the sensor may be an electro-chemical sensor. An electrochemical sensor may, for instance, have a membrane (sensing layer or sensing element) that absorbs the gas component (e.g., VOCs). The membrane is in contact with a first electrode and a second electrode. The absorbed gas component may have an electrochemical, reduction/oxidation reaction with the first electrode upon application of a potential difference between the first electrode and the second electrode, thus affecting the current flowing through the membrane, the first electrode and the second electrode. The change in current indicates the type and/or amount of gas.

[0036] Within the context of the present disclosure, the sensor may, for instance, be a multi-pixel gas sensor, such as BME680 or its future generations, or any other suitable sensor from Bosch SensorTec. The temperature of the BME680 may be controlled by the user for the application of the thermal pulse. The BME680 may be able to distinguish between the different VOC species such as ketones, aldehydes and aliphatic compounds (including eight carbon atoms). In addition, the BME680 sensor may be able to detect pressure, humidity, temperature and sugar level of the crop. Alternatively, the BME680 may include other sensors configured to detect pressure, humidity, temperature and sugar levels of the crop.

[0037] The sensor node 100 depicted in FIG. 1 is provided for illustration purposes and the disclosure is not limited thereto. In accordance with various embodiments, the sensor node 100 may be placed within a crop planation, for example, a palm oil planation. As a further example, the sensor node 100 may be embedded in the soil of the crop planation. As such, the sensor node 100 may detect the gas component(s) (e.g., VOC) levels originating from the roots of the crop, for example, the roots of the palm oil plant.

[0038] FIG. 2 provides a graph 200 illustrating an example of a transient 220 (dotted line) of the electrical property that may be generated in response to an application of an exemplary thermal pulse 210 (dashed line) on the sensor 110, in accordance with various embodiments. The graph 200 depicted in FIG. 2 is provided for illustration purposes and the disclosure is not limited thereto. The horizontal axis (x-axis) represents time, the vertical axis (y-axis) on the left-hand side represents the temperature change during the application of the thermal pulse 210. The vertical axis (y-axis) on the right-hand side represents a change in the resistance of the transient 220 of the electrical property. According to various embodiments, the control circuit 120 may be configured to control the temperature of the sensor 110 by controlling the heater 114 for the application of the thermal pulse 210, and may further be configured to measure the transient 220 of the electrical property generated in response to the thermal pulse 210.

[0039] The thermal pulse 210 may be a square pulse, and may have a thermal pulse height defined by the difference between a base temperature TBASE and a high temperature TH (TH - TBASE). The base temperature TBASE may be an ambient or environmental temperature, which may refer to the temperature of the air surrounding the sensor node 100. For example, the base temperature TBASE may be approximately 3°C to 15°C higher than a standard room temperature Tpyof 25°C, e.g., selected from 28°C to 40 °C. Within the context of the present disclosure, the base temperature TBASE may be more than or equal to 35°C, which may represent the ambient temperature or the temperature of the soil within an exemplary palm oil plantation. The high temperature TH may be the temperature of the sensor 110 during the application of the thermal pulse 210 (by the heater 114) on the sensor 110. The high temperature TH may be, e.g., selected from a temperature equal or less than 80 °C and higher than the selected base temperature TBASE. Accordingly, the thermal pulse height may represent a temperature change between the base temperature TBASE and the high temperature TH when the thermal pulse 210 is applied.

[0040] The transient 220 may be measured by a pre-determined time period, for example, a transient duration ATP. The transient duration ATP may refer to the time interval from a time ti that the transient 220 is generated upon the application of the thermal pulse 210, to the time when the transient 220 reaches a pre-defined steady state at time ts (ts- ti). For example, the transient duration ATP may refer to the pulse width of the transient 220. The transient duration ATP may be equal to or more than 10 milliseconds. For example, the transient duration ATP may be range from 10 milliseconds to 100 seconds. Alternatively the transient duration ATP may be taken as the duration of the thermal pulse, which is pre-defined.

[0041] The transient 220 may be characterized by the transient height defined by the difference between the resistance Ri of the sensor 110 before the application of the thermal pulse 210, and the resistance R2 of the sensor 110 attained upon the application of the thermal pulse 210 (R2 - R1). The difference may be an absolute difference. The resistance R2 may be the peak resistance attained after the rising edge of the thermal pulse 210, and may be attained at time t2. The resistance R2 may be higher than the resistance R1 since the resistance of the sensor 110 may change due to the application of the thermal pulse 210. In other words, the transient height may represent a resistance change between an initial resistance of the sensor 110 and the peak resistance of the sensor 110 in response to the rising edge of the thermal pulse 210.

[0042] The transient 220 may also be characterized by a transient slope time ATs, which may refer to the time taken for the transient 220 to change from the initial resistance R1 at time ti to the peak resistance R2 obtained at time t2, in response to the application of the rising edge of the thermal pulse 210 (transient pulse height). The transient slope time ATs may be less than or equal to 1 second, or preferably, may be less than or equal to 100 milliseconds.

[0043] The transient 220 may also be characterized by a transient gradient 224 of the transient 220 as it changes from a peak resistance R2 at time t2 to a pre-defined steady-state resistance R3 at time ts, obtained in response to the rising edge of the thermal pulse 210. The transient gradient 224 may be a measure of the steepness of the transient 220, and may be a function of the thermal capacity of the sensor 110, which may be defined as the amount of heat to be supplied to a given mass of the heater to produce a unit change in its temperature. For example, the transient gradient 224 of the transient 220 may be a straight line, and the gradient 224 may be calculated as a ratio of the change in the peak resistance R2 at time t2 and the steady state resistance R3 at time ts over the time interval ts - 12. Alternatively, the gradient 224 may be a curve, and the gradient 224 may be calculated as the tangent to the transient 220 at a particular point along the curve.

[0044] Fungi, for example the Ganoderma boninense fungus may give off different types of VOCs, and different amounts or proportions of VOCs during the various stages of growth. VOCs may include, e.g., ketones, alcohols, aldehydes, aliphatic compounds with eight carbon atoms, such as octanol-based organic compounds, for example, 1-octen-3-ol, 3-octanone, 1 -octanol, and (E)-2-octenal etc.

[0045] During the early stages of spore germination and mycelial growth in a crop, for example, the palm oil plant, the fungus may emit different type(s) and/or amount(s) of VOCs as compared to that of a healthy crop. The correlation of the different type(s) and/or amount(s) of VOC species, may provide information on the presence and progression of the basal stem rot disease and the overall health of the plant. It is crucial for a user, for example, farmers to detect the Ganoderma fungus and basal stem rot disease as early as possible, as this may allow the farmer to intervene and treat the diseased crop, especially since basal stem rot disease results in the high mortality rate of the crop. In addition, the farmers may also collect information on the moisture and nutrient levels of the crop, photos of the plant state, e.g., either remotely via a satellite or via a mobile phone on land, and such information may also serve as an indicator of the overall health of the plant.

[0046] Existing basal stem rot disease detection methods include (i) manual and visual confirmation of basal stem rot disease - which is often too late for the farmers to intervene, treat and save the infected crop; (ii) protein analysis of the bark and roots to detect basal stem rot disease - which require specialized laboratory equipment such as microscopes, cultures facilities and molecular diagnostic tools. Protein analysis of the samples is also labor intensive and costly; (iii) laser-based airborne fungal spore testing; and/or (iv) hyperspectral imaging. These approaches (especially approaches (iii) and (iv)) are costly as they require the use of highly specialized equipment and may not be applicable for analyzing the disease at the roots of the crop where the fungus may first start growing. Analysis at the roots of the crop may be required for the early detection of basal stem rot disease. In contrast, the information generated by the sensor node 100 may provide an indication of the presence and progression of basal stem rot disease without the use of expensive equipment, additional labor required to conduct laboratory analysis on samples of the crop, and/or physically checking on each crop within the plantation. Therefore, the sensor node 100 may have lower cost per than existing solutions, and may also enjoy low latency of real time monitoring due to the short response time. The sensor node 100 may also be portable and may be placed near the crop. For example, the sensor node 100 may be embedded in the soil and may therefore detect VOCs emitted from the roots of the crop, thus increasing accuracy of detection and enabling early detection of basal stem rot disease.

[0047] FIG. 3 provides a table of the exemplary major VOCs that may be detected by the sensor node 100, in accordance with various embodiments. The sensor node 100 may be configured to determine the presence of a first gas composition A, the presence of a second gas composition B, and/or the presence of a third gas composition C. The first gas composition A, the second gas composition B and the third gas composition C may include one or more chemical compounds S, which may refer to a species of VOCs. For example, the first gas composition A, the second gas composition B, and the third gas composition C may include at least one species of the VOCs, and may differ to each other.

[0048] The first gas composition A may include a first composition of first compounds from a healthy crop, for example, a crop free of colonization by the fungus. The first gas composition A may include VOCs of a first species Si released by a crop free of the Ganoderma fungus. Within the context of the present disclosure, species Si may be furfural. The first gas composition A may optionally, include other VOC species, for example, species S2, which may be hexanal. Therefore, the first gas composition A may include furfural (Si) and hexanal (S2), originating from a healthy crop, for example, a palm oil plant free of colonization by the Ganoderma fungus. [0049] The second gas composition B may include a composition of compounds which may be indicative of the presence of fungus, for example, the Ganoderma or Ganoderma boninense fungus. As a further example, the second gas composition B may be indicative of the presence of the Ganoderma fungus comprising mycelium. The second gas composition B may include a second composition of second compounds originating from the Ganoderma fungus. For example, the second composition of second compounds B may include VOCs including species S3, which may be aliphatic compound(s). The aliphatic compound(s) (S3) may include compounds which include 8 carbon atoms such as 1-octen-3-ol, 3-octanone, 1- octanol, and (E)-2-octenal. In addition, a third gas composition C may include a modified first composition C(A,B), which may include compounds originating from a crop colonized by the Ganoderma fungus. For example, the third composition C(A,B) may be include at least one VOC species from the first gas composition A, for example, species S2, and may include at least one compound from the second composition B comprising second compounds, for example, species S3. In other words, the third composition C(A,B) may include hexanal (S2) released by the partially healthy or healthy crop, and aliphatic compounds (S3) released by the fungus. The second gas composition B may be substantially free of furfural (Si). In other words, furfural (Si), which is present within the first gas composition A and indicative of a healthy crop may be substantially absent from the third gas composition C. The third gas composition is classified as free from furfural, if furfural gas levels are undetectable or completely absent.

[0050] With reference FIGS. 1 and 3, the sensor 110 may include different sensing elements to detect the first gas composition A, the second gas composition B and/or the third gas composition C. For example, the sensor 110 may include different sensors to detect different species of VOCs. For example, the sensor 110 may include a first sensor to detect species Si (furfural), a second sensor to detect species S2 (hexanal), and a third sensor to detect species S3 (aliphatic compounds). The sensor 110 may also include additional sensors to detect other gas species, and/or other parameters such as temperature, humidity and sugar levels of the crop. For example, the sensor 110 may include other sensors to detect other gas species, and other sensors such as temperature sensors, moisture or humidity sensors, and sugar sensors.

[0051 ] Alternatively, the sensor 110 may include one sensing element configured to detect different species of gas components or a combination of gas components. For example, the sensor 110 may include a single sensing element configured to detect the different species of VOCs, furfural (Si), hexanal (S2) and aliphatic compounds (S3), or the electric property may be based on a combination thereof. Different species of the VOCs may be detected via different operation modes or algorithms on the single sensing element. According to various embodiments, the sensor may also be configured to detect other parameters such as temperature, humidity or moisture and sugar levels.

[0052] FIG. 4 shows a general schematic of a sensor node 100 according to another embodiment, including the sensor 110, the control circuit 120, and a communication circuit 126. The sensor node 100 may be based on the sensor node 100 as described in relation to FIG. 1 , and repeated descriptions will be omitted. The control circuit 120 may also include a microprocessor 122 and a local memory 124. The microprocessor 122 may be the central processing unit and may control the operations of the sensor node 100. For example, the microprocessor 122 may measure and generate information on the transient or a plurality of transients 220 (herein referred to as the transients 220). The local memory 124 may be configured to store data. For example, the local memory 124 may store data on the reference table, data on historical measurements of the transients 220, and may also store data on the trained classifiers used for PCA. The transients 220 may be recorded for a given time frame. For example, the sensor node 100 may record data of, or processed from a plurality of transients 220 per day, and may store the data in the local memory 124. The local memory 124 may further be configured to send the data to a server at time intervals. For example, the local memory 124 may send the data to the server at regular time intervals. Alternatively, the memory 124 may send the data to the server upon a request by the server, or upon request by the user controlling the server.

[0053] According to various embodiments, the local memory may include a device used to store information. The memory may include a primary storage, for example, a random-access memory. For example, the memory may include volatile and nonvolatile memory devices. In addition, secondary storage devices such as hard disk drives and/or solid-state drives may be used to store information.

[0054] In addition, the sensor node 100 may include a communication circuit 126. The communication circuit 126 may be in electrical connection with the control circuit 120, and the communication circuit 126 may be configured to transmit information (for example, the transient, a plurality of parameters, or principal components) to an external device. For example, the data may be sent from the local memory 124 to the external device using the communication circuit 126. The communication circuit 126 may be a wireless communicator, and may be configured to transmit the information to the external device, such as a computer or a server of a cloud network, via wireless communications. Alternatively, it may also be envisioned that the communication circuit 126 may be configured to transmit information to the external device via wired communications.

[0055] According to various embodiments, wireless communications may, for instance, be any one selected from a group consisting of Bluetooth, Wi-Fi, Zigbee, and Low-Power Wide-Area Network (LPWAN) communications (e.g. LoRa).

[0056] FIG. 5A shows a sensing system 500A according to one embodiment. The system 500A may include at least one sensor node 100 as described herein. For example, the system 500A may include a first sensor node 100A, a second sensor node 100B and a third sensor node 100C. Three sensor nodes are depicted for illustration purposes and the disclosure is not limited thereto. Several sensor nodes 100 may be deployed in the crop plantation to allow for spatially precise and accurate monitoring. The system 500A may further include a monitoring platform, such as a server 400, configured to manage and receive the information generated by the microprocessor 122 of the sensor nodes 100. The information generated by the sensor nodes 100 may be sent to a cloud network through a local gateway computer. The cloud network may include one or more computers. The information generated by the sensor nodes 100 may also be transmitted to the server 400 through a network connection 405. The network connection 405 may include a local network connection, a direct network, a broadband network, a virtual private networks and/or a wireless network. It is envisioned that the network connection 405 may transmit information via wireless or wired communications. The network connection 405 may be implemented with wireless communication as previously explained. The system 500A may be deployed in a crop plantation, for example, a palm oil plantation to monitor the VOC, sugar and moisture levels of the crop for the early detection of the Ganoderma fungus.

[0057] FIG. 5B shows a sensing system 500B according to another embodiment. Similar to the sensing system of FIG. 5A, the sensing system 500B may further include a base station 300 which may be connected to the at least one sensor node 100. The base station 300 may be connected to the at least one sensor node 100 through a local network connection 310. The base station 300 may be a short-range transceiver configured to receive information from the sensor node(s) 100 within a limited geographic area, for example, within the crop plantation. For example, the base station may be a router than communicates with devices, for example, the sensor node 100 and/or the server 400 via wireless or wired communications. The local network connection 310 may be implemented with wireless communication as previously explained. The local network connection 310 may be a computer network that interconnects and transmits information from the individual sensor node 100 to the base station 300 within the crop plantation. The base station 300 may further be connected to the server 400 through a network connection 410. For example, the network connection 410 may be a wide area network that extends over a large geographical area, for example, an area outside the crop plantation. This allows the user to analyze information sent to the server 400 regardless of location. Therefore, the user does not need to be physically located within the crop plantation and yet may still access the information on the server 400.

[0058] As shown in FIGS. 5A and 5B, the server 400, which includes at least one computer, retrieves or downloads the information from the sensor nodes 100 or the base station 300. Analysis of the information may be carried out on the server 400. For example, the server 400 may be configured to determine the principal components as a server-side principal components based on the plurality of parameters. The plurality of parameters may be based on the transients 220 generated by the control circuit 120. Alternatively, the server 400 may be configured to determine the plurality of parameters as a server-side plurality of parameters based on the transients 220. The server 400 may be further configured to determine the principal components as server-side principal components based on the serverside plurality of parameters. The server-side principal components may be determined using the PCA method. The server may then carry out a server-side calibration by determining the correlation between one or more of the server-side principal components with the reference data.

[0059] According to various embodiments, the sensing system may be configured to provide the information to a user, such as the farmer, by displaying the correlation between one or more of the server-side principal components with the reference data. Additionally, the sensing system may be configured to provide an audio and/or visual alert upon when a sensor node 100 provides information of abnormal VOC, moisture and/or humidity levels, suggesting the detection of the Ganoderma fungus. With proper placement of the sensor nodes 100 within the plantation and connected to the server 400 via wired or wireless communications, the Ganoderma fungus may be detected at an early stage. Further, the overall health of the crops within the plantation may be monitored with greater efficiency.

[0060] According to the various embodiments, the sensor system may further include a microprocessor and a memory. The microprocessor may be configured to carry out instructions of a trained classifier, wherein the information on the trained classifier may be stored at least partially in the memory. The trained classifier may be an algorithm that maps the input data, for example, information from the transients to a specific category which may include for example, crops which may or may not be colonized by the fungus. The trained classifier may include artificial neural networks or deep learning, logistic regression, decision tree, naive bayes, support vector machines, or a combination thereof. As a further example, the trained classifier may include at least one class in the output layer having a value, which, once determined based on the transients and/or on information obtained from the transients, may correspond to a prediction of colonization of crop by the fungus. The trained classifier may be trained by the parameters, or server-side parameters generated by the server.

[0061] FIG. 6 illustrates a method of sensing according to various embodiments. The method may include, in 610, generating a thermal pulse by a control circuit such that information is generated based on a measurement of a transient of an electrical property of a sensor. The transient may be generated in response to the detection of at least one component in a gas, for example, at least one gas component, for example a VOC in a gas. The transient may convey information on the different type(s) and/or amount(s) of components (e.g. VOC) in the gas. The method may also include, in 620, the recording of the transients in the control circuit. For example, the transients may be recorded in a local memory of the control circuit. In 620, the method may further include calculating a plurality of parameters based on the transients. Alternatively, the information on the transients may be transmitted to a server which may be configured to determine server-side plurality of parameters. The method may include, in 630, the processing of the plurality of parameters into principal components based on the plurality of parameters. For example, the microprocessor within the control circuit may be configured to determine the principal components based on the plurality of parameters. Where the information is being transmitted to the server, a microprocessor within the server may be configured to determine server-side principal components based on the server-side plurality of parameters. Lastly, in 640, the method may include processing the principal components by the control circuit or processing of the server-side principal components by the server to determine a likelihood of a colonization of crop by the fungus. For example, the processing of the principal components or server-side principal components may include determining the correlation between one or more principal components and the reference data.

[0062] FIG. 7 provides agraph 700 onto which a principal component analysis pattern may be plotted, such as a principal component PC2 plotted as function of a principal component PC1 . Said plot may be obtained based on measuring a transient of the electrical property during an application of a thermal pulse on the sensor, and further processing of the information from the transient based method described in FIG. 6 wherein the principal components may be correlated with reference data obtained using GC-MS. Said plot onto graph 700 may show clusters of samples based on their similarity which may be located in one of the quadrants I-IV. For example, a cluster in quadrant II may represent samples which include aliphatic compounds (S3) and have a higher concentration of such VOCs, suggesting late- stage colonization by the Ganoderma fungus. A cluster in quadrant III may represent samples which may have VOCs including both furfural (Si) and aliphatic compounds (S3) but with lower levels of VOCs, and may represent crop colonized by the Ganoderma fungus at an early stage, a A cluster in quadrant IV may represent healthy crop which may emit VOCs including furfural (Si) and hexanal (S2). As shown in FIG. 7, graph 700 provides a visual representation (based on a large set of data and variables) that easily allows the user to identify different clusters. As such, the user may easily identify clusters with that has been colonized by the Ganoderma fungus, which may aid in the early detection of the Ganoderma fungus.

[0063] FIG. 8 provides an exemplary graph 800 illustrating a signal of the transient 810 and 820 of an electrical property of a sensor generated under a pulsed heating and cooling program, in accordance with various embodiments. The x-axis may represent time (in seconds), and the y-axis may represent resistance (in ohms). As shown in FIG. 8, plot 800 may include signal 810 measuring the change in resistance of the sensor upon detection of VOCs emitted from a healthy crop (without the Ganoderma fungus), and may include signal 820 measuring the change in the resistance of the sensor upon detection of VOCs emitted from a crop colonized by the Ganoderma fungus. Signals 810 and 820 may be generated by first warming the sensor up with a slow heating I cooling process and applying a pulsed heating I cooling program. For example, at time intervals T1 , the sensor may be slowly heated to 100°C for a duration of approximately 10 seconds. At time intervals T2, the sensor may be rapidly heated to 300°C in a slope time of less than or equal to 1 second, for example, less than or equal to 100 millisecond. The control circuit may then apply a thermal pulse (signals 810 and 820) on the sensor, and may measure the transients 812 and 822 of the change in the resistance of the sensor. The pulse durations may be more than or equal to 100 milliseconds, for example, selected from 100 milliseconds to 100 seconds. As may be seen in FIG. 8, the slope of transient 822 may be steeper than the slope of transient 812. Therefore, transients 812 and 822 may each convey information of the different type(s) and/or amount(s) of VOCs that may be detected by the sensor, for example, information on the likelihood and/or degree of crop colonization by the Ganoderma fungus. [0064] FIG. 9 provides an exemplary plot 900 of a primary pattern classification after application of a principal component analysis method on the VOC response, in accordance with various embodiments, showing a first component PC1 On the horizontal axis and a second component PC2 on the vertical axis. Plot 900 may be based on the VOC response obtained in FIG. 8, specifically, on the transients 812 and 822 of signals 810 and 820, respectively. Seven parameters may be derived from the transients 812 and 822, namely, the resistance (R), the differential of the resistance (dR/dt), the normalized resistance (NR), the differential of the normalized resistance (dNR/dt), the inverse of the resistance (1/R), the normalized inverse of the resistance (dN(1/R)), and the differential of the normalized inverse of the resistance (dN(1/R)/dt). Principal component analysis may then be applied on each of the parameters to realize the primary pattern classification plot 900. Plot 900 may include cluster 910, indicating a cluster of a crop free of colonization by the Ganoderma fungus, and cluster 920, indicating a cluster of a crop colonized by the Ganoderma fungus. In that manner, the user may easily identify crop that has been colonized by the Ganoderma fungus (cluster 920), and may treat the diseased crop accordingly.

[0065] In accordance with various embodiments, a sensor node and a method of sensing for the early detection of fungus may be provided. Further, a sensing system including one or more sensor nodes may also be provided.

[0066] Advantageously, the sensor node according to the various embodiments may provide a multi-functional, low-cost, highly-sensitive sensor node. The sensor node may primarily be configured to detect the different types and amounts of VOCs, and may be integrated with other sensors, such as a moisture and sugar sensor. Further, information generated by the sensor note may be collected and sent to a cloud server for historical tracing, analysis and mapping. The pattern classification derived from the data of specific VOC signals and abnormal water and/or sugar levels may provide information on the overall health of the crop, in particular, on the presence of the Ganoderma fungus so as to allow for the early detection basal stem rot disease. The information generated by the sensor node may therefore allow the farmer to intervene at an earlier stage, treat the diseased crop and minimize crop loss and damage. [0067] It may be further envisioned that the node, system and/or method described herein may be used in other areas or applications, such as the detection of early stage fungus growth in other crops, and in pollution monitoring and control. [0068] While the disclosure has been particularly shown and described with reference to specific embodiments, it should be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. The scope of the invention is thus indicated by the appended claims and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced.

Claims

24 CLAIMS

1 . A sensor node (100) for detection of fungus, comprising: a sensor (110) configured to detect at least one component in a gas by a change of an electrical property of the sensor (110); and a control circuit (120) being configured to control a temperature of the sensor and to measure a transient (220) of the electrical property during an application of a thermal pulse (210) on the sensor (110).

2. The sensor node (100) of claim 1 , wherein the sensor (110) comprises a heater (114) and the control circuit (120) is configured to control a temperature of the sensor (110) by controlling the heater (114) for the application of the thermal pulse (210), wherein the thermal pulse (210) has a pulse height determined as the difference between a high temperature (TH) and a base temperature (TBASE), and has a rising time of less than or equal to 1 second, for example less than or equal to 100 milliseconds.

3. The sensor node (100) of claim 1 or claim 2, wherein the transient (220) has a transient duration (ATP) of equal to or more than 100 milliseconds, for example, selected from 100 milliseconds to 100 seconds.

4. The sensor node (100) of any one of claims 1 to 3, wherein the sensor node (100) is configured to determine the presence of a first gas composition (A), the presence of a second gas composition (B), and/or a third gas composition (C), wherein the first gas composition (A) is different from the second gas composition (B), and the third gas composition (C), and wherein the first gas composition (A) includes a first composition of first compounds originated from a crop free of colonization by the fungus, and

RECTIFIED SHEET (RULE 91) ISA/EP wherein the second gas composition (B) and/or the third gas composition (C) is an indicative of the presence of the fungus, optionally an indicative of the presence of the fungus of genus Ganoderma, for example Ganoderma boninense.

5. The sensor node (100) of claim 4, wherein the second gas composition (B) or the third gas composition (C) is an indicative of the presence of fungus comprising mycelium.

6. The sensor node (100) of claim 4 or claim 5, wherein the second gas composition (B) comprises a second composition comprising second compounds originating from the fungus; and wherein the third gas composition (C) comprises a modified first composition (C(A,B)) different from the second composition (B), the modified first composition (C(A,B)) comprising compounds originated from the crop colonized by the fungus.

7. The sensor node (100) of any one of claims 4 to 6, wherein the first gas composition (A) comprises furfural (Si).

8. The sensor node (100) of any one of claims 4 to 7, wherein the second gas composition (B) and/or the third gas composition (C) is substantially free of furfural (Si) and comprises aliphatic compounds (S3), for example, with 8 carbons.

9. The sensor node (100) of any one of claims 1 to 8, wherein the control circuit (120) is configured to determine a plurality of parameters based on the transient (220); and wherein the control circuit (120) is further configured to determine principal components based on the plurality of parameters.

10. The sensor node (100) of claim 9, wherein the control circuit (120) is further configured to carry out a calibration by determining the correlation between one or more of the principal components with reference data,

RECTIFIED SHEET (RULE 91) ISA/EP wherein the reference data is obtained from gas chromatography and mass spectrometry.

11 . The sensor node (100) of any of claims 1 to 10, wherein the crop is a plant, and wherein the plant is of the genus Elaeis, for example Elaeis guineensis.

12. The sensor node (100) of any one of claims 1 to 11 , further comprising a local memory (124) and a communication circuit (126), wherein the sensor node (100) is configured to record data of, or processed from, a plurality of transients (220) per day, store the data in the local memory (124) and send the data to a server (400) at time intervals using the communication circuit (126), wherein the local memory (124) may be part of the control circuit (120).

13. A sensor system (500) comprising: one or more sensor nodes (100) in accordance to claim 12; the server (400) for receiving the data from the sensor nodes (100);

14. The sensor system (500) of claim 13, wherein

(i) the server (400) is configured to determine server-side principal components based on the plurality of parameters, or wherein

(ii) the server (400) is configured to determine a server-side plurality of parameters based on the transient, and is further configured to determine server-side principal components based on the server-side plurality of parameters.

15. The sensor system (500) of claim 13 or claim 14, wherein the server (400) is further configured to carry out a server-side calibration by determining the correlation between one or more of the server-side principal components with reference data.

16. The sensor system (500) of any one of claims 1 to 15, further comprising

RECTIFIED SHEET (RULE 91) ISA/EP 27 a microprocessor and a memory and being configured to carry out, with the microprocessor, instructions of a trained classifier, stored at least partially in the memory, wherein: the trained classifier comprises at least one class in the output layer having a value, which, once determined based on the transients and/or on information obtained from the transients, corresponds to a prediction of colonization of crop by fungus, the trained classifier was trained with/by [].

17. A method of sensing, the method comprising: generating a thermal pulse (210) by a control circuit (120) so that information is generated based on a measurement of a transient (220) of an electrical property of a sensor (110) based on the detection of at least one component in a gas; recording the transient (220) in the control circuit (120); calculating a plurality of parameters based on the transient (220); processing the plurality of parameters into principal components based on the plurality of parameters; and processing the principal components to determine a likelihood of a colonization of crop by fungus.

RECTIFIED SHEET (RULE 91) ISA/EP