FI127510B

FI127510B - System comprising alarm devices

Info

Publication number: FI127510B
Application number: FI20176169A
Authority: FI
Inventors: Pasi Karppinen; Ilmo Aronen; Knut-Olof Lerche
Original assignee: Raisioagro Oy
Priority date: 2017-12-22
Filing date: 2017-12-22
Publication date: 2018-08-15
Also published as: EA038889B1; WO2019122523A1; EA202091564A1; EP3989193A1; EP3729390B1; EP3729390A1

Abstract

According to an example aspect of the present invention, there is provided system comprising one or more alarm devices operatively connected to receiving means for acoustic signals, said system configured to cause, determining (202) an acoustic signal received by the receiving means to correspond to an aquatic vehicle approaching a fish farm, causing (204), by at least one of the alarm devices, one or more alarm operations, when the received acoustic signal comprises a stopping sound of the aquatic vehicle at the fish farm.

Description

SYSTEM COMPRISING ALARM DEVICES

FIELD

[0001] The present invention relates to fish farming.

BACKGROUND

[0002] WO 94/00007 discloses a fish farm cage security system includes sound-emitting devices attached to the cage for detecting tampering with one or more of the nets forming the cage. Detector means are provided for detecting the sound emitted by the sound-emitting devices and ambient sounds. The detectors may be responsive not only to the sounds emitted by the bells but also to other sounds generated in the area of the cages, such as those made by boats.

[0003] Fish farms can be located miles away from the shore and therefore it can take a considerable time for a farmer to reach a fish farm in case of an alert is made.

SUMMARY OF THE INVENTION

[0004] The invention is defined by the features of the independent claims. Some specific embodiments are defined in the dependent claims.

[0005] According to a first aspect of the present invention, there is provided a system comprising one or more alarm devices operatively connected to receiving means for acoustic signals, said system configured to cause: determining an acoustic signal received by the receiving means to correspond to an aquatic vehicle approaching a fish farm; causing, by at least one of the alarm devices, one or more alarm operations, when the received acoustic signal comprises a stopping sound of the aquatic vehicle at the fish farm.

[0006] According to a second aspect of the present invention, there is provided a fish farm comprising a system according to an aspect.

BRIEF DESCRIPTION OF THE DRAWINGS

[0007] FIGURE 1 illustrates a fish farm in accordance with at least some embodiments of the present invention; [0008] FIGURE 2 illustrates a method in accordance with at least some embodiments of the present invention; [0009] FIGURE 3 illustrates a system in accordance with at least some embodiments of the present invention; [0010] FIGURE 4a illustrate configuring a system for processing acoustic signals in accordance with at least some embodiments of the present invention; [0011] FIGURE 4b illustrate an example operation of a system configured for processing acoustic signals in accordance with at least some embodiments of the present invention; and [0012] FIGURE 5 illustrates a user interface in accordance with at least some embodiments of the present invention.

EMBODIMENTS

[0013] There is provided a system, comprising one or more alarm devices operatively connected to receiving means for acoustic signals. An acoustic signal received by the receiving means is determined to correspond to an aquatic vehicle approaching a fish farm. When the received acoustic signal comprises a stopping sound of the aquatic vehicle at the fish farm, one or more alarm operations are performed. In this way alarm operations of the fish farm may be controlled on the basis of the stopping sound of the aquatic vehicle, whereby security and monitoring of the fish farm may be provided.

[0014] FIGURE 1 illustrates a fish farm 106 in accordance with at least some embodiments of the present invention. The fish farm may comprise one or more floating cage structures, i.e. fish farm cages, at sea or lake. A fish farm cage 103 may comprise a floating walkway from which suspended nets form an enclosure for the fish inside the cage. Accordingly the cage structures are mostly under the water surface 110. The cage structures may extend downwards from the water surface and in some cases all the way to the bottom 112. The fish farm may be visited by an aquatic vehicle and/or aquatic vehicles may pass by the fish farm. Examples of the aquatic vehicles comprise a motorboat, a rowboat, a kayak, a canoe or a sailing boat.

[0015] The fish farm may comprise a system comprising one or more alarm devices operatively connected to receiving means for acoustic signals, said system configured to cause one or more functionalities in accordance with at least some embodiments described herein. The system may comprise receiving means 104 for acoustic signals. The receiving means may be capable of receiving acoustic signals under water or in the air, in the area of the cage and/or around the cage. In this way acoustic signals may be received for determining, whether an acoustic signal received by the receiving means 104 corresponds to an aquatic vehicle 105 approaching the fish farm 106.

[0016] The system may further comprise one or more alarm devices 102. The alarm devices may be operatively connected to the receiving means 104. In this way, one or more alarm operations may be performed, when the received acoustic signal comprises a stopping sound of the aquatic vehicle 105 at the fish farm 106. Accordingly, alarm operations of the fish farm may be controlled on the basis of the stopping sound of the aquatic vehicle, whereby security and monitoring of the fish farm may be provided.

[0017] Visits of aquatic vehicles to the fish farm may comprise authorized and unauthorized visits. Typically only authorized persons are allowed to visit the fish farm. Detecting authorized and/or unauthorized visits provide that activity of the fish farming may be monitored. More particularly, detected visits may be logged to a history for later analysis. The unauthorized visits to the fish farm are a risk to fish farming for various reasons and their detection serves for supporting production yield of the fish farm. In one example, unauthorized visits may cause contamination of the fish stock, if contaminated fish farming equipment is brought into contact with the fish stock. In another example, the farming process such as the feeding times of the fish may be disturbed. In yet another example, unauthorized visitors may steal fish from the fish farm. Moreover, aquatic vehicles that approach the fish farm may be detected by the fish, whereby movement of the fish is increased, which may lead to injuries and stress of the fish.

[0018] The alarm devices 102 and the receiving means 104 may be positioned to various locations at the fish farm. Examples of the locations comprise the bottom 112 of the sea or lake, portion of the cage structure above the surface. Moreover, the alarm devices may be installed to a pole such that they are significantly above the cage structure to enable improved coverage for the alarm operations performed by the alarm devices. Similarly, the receiving means may be installed to a pole, whereby unobstructed reception of acoustic signals may be provided.

[0019] In an embodiment the alarm devices 102 may comprise one or more of a sound output device and spotlight that may be local to the fish farm. The alarm devices may alternatively or additionally comprise devices that are external to the fish farm and which can be moved to different locations. Accordingly, the alarm devices may be local to the fish farm or remote from the fish farm. Such devices may comprise computing devices for example mobile devices and handheld devices, such as smart phones. Examples of the sound output devices comprise a loudspeaker, a bullhorn and a siren.

[0020] In an embodiment, an alarm operation comprises turning on one or more spotlights directed to one or more locations at the fish farm. In this way specific locations may be enlightened by the spotlights, whereby unauthorized visitors at those locations may be detected more efficiently.

[0021] It should be appreciated that one or more video recorders may be installed at the fish farm to record video from the locations that are enlightened by the spotlights, whereby video of the unauthorized visitors may be recorded. On the other hand, the video recorders may be enabled with night vision, whereby the video recorders may record video without the spotlights being turned on. Accordingly, an alarm operation may comprise recording video by one or more video recorders installed at the fish farm.

[0022] It should be appreciated that one or more still cameras may be installed at the fish farm to take still photos from the locations that are enlightened by the spotlights, whereby photos of the unauthorized visitors may be taken. On the other hand, the still cameras may be enabled with night vision, whereby the still cameras may take still photos without the spotlights being turned on. Accordingly, an alarm operation may comprise taking still photos by one or more still cameras installed at the fish farm.

[0023] In an embodiment, an alarm operation comprises causing an alarm sound and/or audio playback by a sound output device. The alarm sound may notify the unauthorized visitor about the alarm. The audio playback may be an audio recording of speech that asks the unauthorized visitor to move away from the fish farm.

[0024] A neighbourhood of the fish farm 106 may comprise an area around the fish farm, where acoustic signals originating from locations of the neighbourhood are perceivable to the receiving means of the fish farm. The neighbourhood of the fish farm comprises preferably an area around the fish farm, where the acoustic signals originating from locations of the neighbourhood may be classified into at least one class of a plurality of classes, said plurality of classes comprising at least one class of acoustic signals, where alarm operations are not performed and at least one other class of acoustic signals, where alarm operations are performed. Examples of classes of acoustic signals, where alarm operations are not performed comprise at least one of a class indicating that an acoustic signal fails to correspond to an aquatic vehicle and a class indicating an acoustic signal that corresponds to an aquatic vehicle passing the fish farm without stopping at the fish farm 106. Examples of the classes of acoustic signals, where alarm operations are performed comprise a class indicating that an acoustic signal corresponds to a stopping sound of an aquatic vehicle at the fish farm. Preferably classes of acoustic signals are configured to the system by a machine-learning process, whereby classification of received acoustic signals may be machine-controlled.

[0025] The class of acoustic signals, where alarm operations are not performed, may comprise acoustic signals that are not generated by an aquatic vehicle. It should be appreciated that the class of acoustic signals, where alarm operations are not performed, may further comprise acoustic signals generated by aquatic vehicles that bypass the fish farm. Accordingly, acoustic signals belonging to this class may first have increasing amplitude after which the amplitude begins to decrease, without any stopping sounds there between. The increasing amplitude followed by decreasing amplitude may be used to determine that the aquatic vehicle has passed the fish farm without stopping at the fish farm. Improved accuracy for classifying acoustic signals into this class may be provided, when received acoustic signals are classified into this class provided the decreasing amplitude of the acoustic signal follows within a specific time frame. If the decreasing amplitude does not follow within the specific time, the acoustic signal may be classified into another class, for example to the class where alarm operations are performed, since a lack of satisfying the condition that the decreasing amplitude would follow within the specific time may be interpreted as a stopping sound of the aquatic vehicle.

[0026] The class of acoustic signals, where alarm operations are performed, may comprise acoustic signals that are generated by an aquatic vehicle. Accordingly, acoustic signals belonging to this class may have increasing amplitude and comprise one or more stopping sounds. The stopping sounds may comprise a clutch sound, mooring sound, impact sound, sound of fixing to the fish farm and/or a lack of sound indicating the aquatic vehicle moving away from the fish farm. The lack of sound may be determined after a specific time has passed after detecting the sound of the aquatic vehicle.

[0027] FIGURE 2 illustrates a method in accordance with at least some embodiments of the present invention. The method may be performed at the fish farm described with FIGURE 1. Phase 202 comprises determining an acoustic signal received by the receiving means to correspond to an aquatic vehicle approaching a fish farm. Phase 204 comprises causing, by at least one of the alarm devices, one or more alarm operations, when the received acoustic signal comprises a stopping sound of the aquatic vehicle at the fish farm. The method provides that alarm operations of the fish farm may be controlled on the basis of the stopping sound of the aquatic vehicle, whereby security and monitoring of the fish farm may be provided.

[0028] In an embodiment, phase 202 may comprise that the received acoustic signal is classified into at least one class of a plurality of classes configured to the system by a machine-learning process, said plurality of classes comprising at least one class of acoustic signals, where alarm operations are not performed and at least one other class of acoustic signals, where alarm operations are performed. In this way the received acoustic signal may be processed by a classification determined by the machine-learning process, for example a support vector machines (SVM) process.

[0029] In an embodiment, phase 202 may comprise that the classification of the received acoustic signal may be updated based on user input for turning alarm operations on or a user input for turning alarm operations off for the received acoustic signal. In this way the operation of the system may be adapted to take into account exceptional situations and also continuous training of the system is facilitated. The user input may be obtained via a user interface on a computing device, for example.

[0030] In an embodiment, phase 204 may comprise that the alarm operation are caused, when the stopping sound indicates that the aquatic vehicle is sufficiently close for getting off the vehicle to the fish farm. In this way the, unnecessary alarm operations may be avoided. The location of the aquatic vehicle may be determined on the basis of the characteristics of the received acoustic signal. The characteristics may comprise amplitude, power and/or frequency characteristics. Alternatively or additionally, one or more changes of the characteristics may be used to determine location of the aquatic vehicle. In one example, the aquatic vehicle may be determined to be sufficiently close for getting of the vehicle, when the power of the acoustic signal is above a threshold level. When also, a change of the frequency characteristics of the acoustic signal is determined, the aquatic vehicle may be determined to be a stopping sound and to be stopped at the fish farm for getting of the vehicle. In an example, the change of the frequency characteristics may be determined, when the acoustic signal first comprises Doppler frequencies caused by the Doppler effect, when the aquatic vehicle approaches the fish farm, and thereafter the Doppler frequencies are removed.

[0031] In an example the aquatic vehicle may be sufficiently close for getting off the vehicle when the distance between the aquatic vehicle and the fish farm is less than 2m. The minimum distance is, when the aquatic vehicle has arrived at the fish farm and touches the fish farm. Typically, the aquatic vehicle that arrives at the fish farms makes an impact with the fish farm.

[0032] It should be appreciated that the alarm operations may be initiated in a sequence. Particularly, if the alarm operations may be performed by different types of devices, the alarm operations may be initiated one type of alarm devices at a time. Consequently, more than one, at least two, a part or all the alarm operations may be performed at the same time.

[0033] For example, the alarm devices may comprise a spot light, a sound output device, and a computing device such as a smart phone of the fish farmer. Then the first alarm operation may comprise turning on the spot light, the second alarm operation may comprise causing an alarm sound, the third alarm operation may comprise causing an audio playback and the fourth alarm operation may comprise displaying a notification indicating an alarm on the user interface of the computing device. The notification indicating an alarm on the user interface may be displayed in connection with any of the other alarm operations instead of being performed separately. The notification may be provided with a sound played by the computing device, to aid the user to observe the notification.

[0034] In an embodiment a stopping sound comprises a clutch sound, a mooring sound, an impact sound, a sound of fixing to the fish farm and/or a lack of sound indicating the aquatic vehicle moving away from the fish farm. The lack of sound may be determined after a specific time has passed after detecting the sound of the aquatic vehicle.

[0035] In the foregoing examples, the acoustic signals are determined using increasing amplitude and decreasing amplitude of the acoustic signals, however, alternatively or additionally other properties of the received acoustic signal may be utilized, for example properties derivable based on the Doppler effect.

[0036] In an example a clutch sound may be generated by a clutch of the aquatic vehicle. The aquatic vehicle may be a motorized aquatic vehicle comprising an engine. The engine may be a diesel engine or a petrol engine. Accordingly, when an acoustic signal generated by the aquatic vehicle is received and the aquatic vehicle is approaching the fish farm and the acoustic signal comprises a clutch sound, it may be determined that the aquatic vehicle is stopping at the fish farm. Examples of characteristics of the clutch sound comprise a series of tapping sounds for e.g. 0,1 seconds, re-occurrence of the tapping sounds and duration of the received acoustic signal. In an example, re-occurrence of the tapping sounds within a specific time period may be used to determine that the clutch is used repeatedly, when the aquatic vehicle is stopping at the fish cage.

[0037] In an example, a mooring sound may be caused by mooring operations performed at the aquatic vehicle. Examples of the mooring operations comprise an impact sound between the aquatic vehicle and the fish farm and fixing the aquatic vehicle to the fish farm. The aquatic vehicle may be fixed to the fish farm by ropes and/or chains. Accordingly, fixing the aquatic vehicle may cause acoustic signals originating from the chains and/or ropes, when the chains and/or ropes touch the fish farm and/or the aquatic vehicle.

[0038] FIGETRE 3 illustrates a system in accordance with at least some embodiments of the present invention. The system is described with reference to examples of units illustrated in the FIGETRE 3. However, it should be appreciated that also other implementations of the system may be viable. The system may comprise one or more alarm devices 302 and one or more receiving means 304 for acoustic signals. The alarm devices may be operatively connected to the receiving means to cause a method described with FIGETRE 2. In this way alarm operations of the fish farm may be controlled on the basis of the stopping sound of the aquatic vehicle, whereby security and monitoring of the fish farm may be provided. The system may be installed to the fish farm described with FIGETRE 1. Examples of the alarm device comprise a spot light, a sound output device, and a computing device such as a smart phone of the fish farmer.

[0039] In an embodiment the system may comprise a data connection unit (DCU) 310 configured to communicate information indicating an alarm over a data connection to a remote system (RS) 312. In this way the remote system may obtain data, e.g. information indicating an alarm, and perform one or more operations for supporting security and/or monitoring of the fish farm. Accordingly, the remote system and/or devices connected to the remote system may serve for an alarm device for example for alarming users that are remote from the fish farm.

[0040] The remote system may be in a fixed location ashore or the remote system may be a mobile system, mobile device or handheld device. In scenarios, where the fish farm is located out, for example several kilometres, in the sea, wireless connections between the system and the remote system may be preferred. However, wired connections may be preferred, if wireless connections are not available and a wired connection would be available.

[0041] An example of the system comprises a controller (CNTL) 306 and a memory (M) 308 that are connected to the alarm device, receiving means and the data connection unit by wired or wireless connections. The data connection unit may be connected to the remote system by wired or wireless connection to provide the remote system information indicating an alarm to enable the remote system to perform one or more operations for supporting security and/or monitoring of the fish farm. The connections may be capable of communications of data between at least part of the units of the system. The data may comprise one or more of acoustic signals, video, still images, data indicating one or more acoustic signals, information indicating an alarm and information indicating an alarm operation. In an example, the data indicating an acoustic signal may comprise an acoustic signal received by the receiving means and which has been digitized and/or classified.

[0042] In an example, the information indicating an alarm may indicate that a received acoustic signal comprises a stopping sound of the aquatic vehicle at the fish farm. The information indicating the alarm may further indicate one or more alarm operations caused or to be caused, when the received acoustic signal comprises a stopping sound of the aquatic vehicle at the fish farm.

[0043] In an example, information indicating an alarm operation may indicate an alarm operation to be performed, an alarm operation that has been performed and/or an alarm operation that is being performed. The alarm operation may comprise transmitting information indicating an alarm to a computing device, turning on one or more spotlights, recording video, taking still photos, causing an alarm sound by a sound output device and/or causing audio playback by a sound output device. The information indicating an alarm operation may serve for information indicating an alarm.

[0044] The controller 306 may be a processor capable of executing computer program code and/or instructions to cause one or more functionalities described herein in various embodiments. The computer program code and/or instructions may be stored in the memory 308 and the computer program code and/or instructions may be accessed by the processor to retrieve the computer program code and/or instructions for executing the computer program code and/or instructions. The alarm devices, receiving means, data connection unit and remote system may include one or more similar processors and memory for execution of functionalities described herein.

[0045] Examples of connections between units devices and apparatuses comprise wired connections for data transfer such as computer buses. Alternatively or additionally the units may be connected by wireless connections of which examples comprise data connections provided by wireless communications networks. Examples of wireless communications networks comprise mobile communications networks based on GSM, IS-95, UMTS, CDMA2000 or LTE technology, and IoT networks based on NB-IoT, SIGFOX, LoRaWAN.

[0046] The receiving means 304 may comprise means for receiving acoustic signals carried by the air and/or water from a source of the acoustic signal to the fish farm. Examples of the receiving means may comprise one or more video cameras, still cameras, microphones and/or hydrophones. Preferably, the receiving means is at least configured to receive acoustic signals from an aquatic vehicle. Further receiving means such as video cameras and still camera may provide that the source of the acoustic signal may be verified by a user on the basis of video and/or still images.

[0047] The remote system 312 may be a network service provided by one or more network elements located in a communications network. The remote system may be accessible to computing devices and/or the system over data connections. The network service may be a single server computer or a cloud computing service. On the other hand the remote system may be a computing device connected to the communications network. In one example the system may send a message to the remote system. Examples of messages comprise Short Message Service and Internet Protocol-based messaging services such as Facebook Messenger, WhatsApp, Viber, WeChat and Line, available on smart phones with data connections. The message may serve for a notification indicating the alarm on a user interface of the remote system. It should be appreciated that the system and the remote system may essentially operate as terminals of a mobile communications network. Terminals of the mobile communications network may be smartphones that are capable or executing third-party applications and have touch screen displays for providing graphical user interfaces.

[0048] In an embodiment, the receiving means 304 may be an acoustic positioning system capable of positioning aquatic vehicles approaching the fish farm. The acoustic positioning system may be an underwater positioning system or a surface positioning system. The acoustic positioning system may perform tracking and positioning of the aquatic vehicle by means of acoustic distance and/or direction measurements, and subsequent position triangulation. The underwater positioning system may comprise hydrophones that receive underwater acoustic signals for tracking and positioning of the aquatic vehicle. The surface positioning system may comprise microphones that receive acoustic signals in the air for tracking and positioning of the aquatic vehicle.

[0049] In an embodiment, at least one alarm operation may be caused, when a stopping sound is determined from an aquatic vehicle located at at least one location at the fish farm. Accordingly, the stopping sound from the location may be used to trigger one or more alarm operations. The location may be determined for example by the receiving means that is an acoustic positioning system as described above. According to one aspect, when acoustic signals are received from one or more predefined locations and the received acoustic signals comprise a stopping sound, one or more alarm operations may be caused. In this way reception sensitivity of the acoustics signals may be tuned to the predefined locations. Moreover, if the acoustic signals are received in a predefined order from the predefined locations, the path taken by the aquatic vehicle may be tracked by the acoustic positioning system to ascertain it is approaching the fish farm, whereby unnecessary alarm operations after reception of the stopping sound may be avoided.

[0050] FIGURE 4a illustrates configuring a system for processing acoustic signals in accordance with at least some embodiments of the present invention. The system may be the system described with FIGURE 3, which is now referred together with FIGURE 4a.

The system may have a training mode and a production mode, whereby the system may be first configured in the training mode before the mode is switched to the production mode after configuration of the system is performed. It should be appreciated that functionalities of the training mode may be performed also after an initial configuration of the system for improving the processing capabilities of the acoustic signals. Configuring the system may comprise receiving 402 input data. The input data may be received from the receiving means 304. The input data may be processed by a machine-learning process to determine parameters for classifying input data. The machine-learning process may be a support vector machines (SVM) process for example. Features may be extracted 406 from the received input data and the extracted features may be fed to a learning model 408. The extracted features may comprise characteristics of the received acoustic signal, e.g. amplitude, power and/or frequency characteristics of the acoustic signal. Alternatively or additionally the characteristics may comprise changes of the amplitude, power and/or frequency. In an example the extracted features may define a stopping sound comprising a clutch sound, a mooring sound, impact sound, sound of fixing to the fish farm and/or a lack of sound indicating the aquatic vehicle moving away from the fish farm. A clutch sound may comprise a series of tapping sounds for e.g. 0,1 seconds, re-occurrence of the tapping sounds and duration of the received acoustic signal. In an example, re-occurrence of the tapping sounds within a specific time period may be used to determine that the clutch is used repeatedly, when the aquatic vehicle is stopping at the fish cage.

[0051] The input data may be evaluated 404 also by a user and the user may provide a result of the evaluation as input to the learning model 408. The input of the user may be provided via a user interface provide on a computing device, for example. The learning model may determine 410 parameters for classifying input data on the basis of the evaluation result from the user and the extracted features. The parameters may be used for classifying input data to at least one class of more than one, for example two, three, four or more classes. Examples of the classes are given below with FIGURE 4b. After the parameters have been determined the system has been configured and the system may be switched to the production mode.

[0052] In configuring the system, the input data or at least part of the input data may be transmitted by the data connection unit 310 to a remote system 312, for example a computing device operated by the user. The computing device may comprise a user interface via which the user may evaluate the input data and provide his/her evaluation result. The evaluation result of the user may be transmitted from the computing device to the data connection unit of the apparatus to be used as input to the learning model 408.

[0053] It should be appreciated that the input data may comprise one or more video, still images, acoustic signals and/or data indicating one or more acoustic signals, whereby the system may be configured to cause one or more alarm operations, when the received acoustic signal comprises a stopping sound of the aquatic vehicle at the fish farm. The input data evaluated 404 by the user may be different than the input data fed to feature extraction 406. In one example the input data to the feature extraction may comprise acoustic signals and/or data indicating one or more acoustic signals, and the input data evaluated 404 by the user may comprise video and/or still images. Additionally, the user may also evaluate a representation of the acoustic signals and/or data indicating one or more acoustic signals. In this way the capabilities of the user may facilitate interpretation of the input data, when the result of the evaluation of the user is fed as input to the learning model 408.

[0054] FIGURE 4b illustrate an example operation of an system configured for processing acoustic signals in accordance with at least some embodiments of the present invention. The system may be the system described with FIGURE 3. The system may have a training mode and a production mode, whereby the system may be first configured in the training mode, for example in accordance with FIGURE 4a, and the mode may be switched to the production mode, after the system is configured. Next the FIGURE 4b is explained with reference to FIGURE 4a and FIGURE 3.

[0055] In the example operation of the system in accordance with at least some embodiments, input data and feature extraction may be performed similar to described with FIGURE 4a. The extracted features may be classified 412 on the basis of parameters 410 for classifying input data. The extracted features may comprise characteristics of the received acoustic signal, e.g. amplitude, power and/or frequency characteristics of the acoustic signal. Alternatively or additionally the characteristics may comprise changes of the amplitude, power and/or frequency. In an example the extracted features may define a stopping sound comprising a clutch sound, a mooring sound, impact sound, sound of fixing to the fish farm and/or a lack of sound indicating the aquatic vehicle moving away from the fish farm. A clutch sound may comprise a series of tapping sounds for e.g. 0,1 seconds, reoccurrence of the tapping sounds and duration of the received acoustic signal. In an example, re-occurrence of the tapping sounds within a specific time period may be used to determine that the clutch is used repeatedly, when the aquatic vehicle is stopping at the fish cage.

[0056] The classification 412 may output a result indicating at least one class 414, 416, 418 of more than one, for example two, three, four or more classes. The classes may comprise at least one class indicating that the input data comprises an acoustic signal that fails to correspond to an aquatic vehicle. The classes may further comprise at least one class indicating that the input data comprises an acoustic signal that corresponds to a stopping sound of an aquatic vehicle at the fish farm. The classes may further comprise at least one class indicating that the input data comprises an acoustic signal that corresponds to an aquatic vehicle passing the fish farm.

[0057] FIGURE 5 illustrates a user interface for alarm operations in accordance with at least some embodiments of the present invention. The user interface 500 may be provided on a computing device. The user interface may be caused to display a notification 506 indicating an alarm on the user interface in response to the computing device receiving information indicating an alarm operation. The notification may be provided with a sound to aid the user to observe the notification. Examples of the notification comprise a graphical element on the user interface, video and/or still image. The alarm operation may be caused in response to a received wave at the fish cage corresponding to at least one type of waves, for example as described with FIGURE 2. The user interface may be provided on a remote system 312 described with FIGURE 3.

[0058] In an embodiment, the user interface 500 may comprise one or more elements capable of receiving a user input from the user of the computing device. The elements may comprise an element 502 for turning alarm operations on and/or an element 504 for turning alarm operations off.

[0059] In an example, the notification 506 may be an in-app notification or a push notification. An in-app notification may be also referred to as in-app messages. The in-app notifications may be displayed on the user interface during use of a specific app, i.e. application. Accordingly, the in-app notification may be displayed directly within the app itself executed in the computing device.

[0060] In an example, the notification 506 may be a push notification. The push notification may be displayed on the user interface even if a specific application is not being displayed. Accordingly, the push notification may be a notification by one application being executed in the computing device in the background and the push notification may be displayed on top of a home screen of the computing device or on top of a user interface view of another application. In this way the push notification may serve for alerting the user of the device even if the application is executed in the background.

[0061] In an embodiment, the notification 506 may comprise one or more video and/or still image. The video and/or still image may be received from a receiving means, e.g. video camera and alarm device, of the system described with FIGURE 3. In this way the user may evaluate the video and/or still images for determining whether the alarm indicated by the notification should be turned on or off. After the user has evaluated the still images and/or video the user may select the element 502 for turning alarm operations on or the element 504 for turning alarm operations off in accordance with the result of the user’s evaluation of the video and/or still images. The evaluation of the user may be utilized in configuring the system in accordance with FIGURE 4a. Accordingly, selection of the user to turn the alarm on or off on the basis of the video and/or still images may be fed to the learning model 408 for determining 410 new or updated parameters for classifying acoustic signals. In this way the system may be configured to classify received acoustic signals based on notifications indicating alarm operations particularly after an initial configuration of the system. The new or updated parameters may be applied in accordance with the operation described with FIGURE 4b. Configuration of the system after initial configuration provides that the system may achieve a relatively high accuracy for causing alarm operations, whereby the system may be adapted to provide reliable monitoring for a specific fish farm and user.

[0062] It should be appreciated that examples of the notification may comprise messages of Short Message Service and Internet Protocol-based messaging services such as Facebook Messenger, WhatsApp, Viher, WeChat and Line, available on smart phones with data connections. A computing device may be configured for communications of messages according to one or more of the above messaging services.

[0063] In an example, a received acoustic signal may be classified to a class, where an alarm operation is performed. The alarm operation may comprise displaying a notification 506 indicating the alarm on the user interface. A user input received in response to the alarm operation may be used for configuring a system for processing acoustic signals, for example as described with FIGURE 4a. The user input may be received by an element 504 for turning alarm operations off. Accordingly, the received acoustic signal may be received 402 as input data in the process of FIGURE 4a and the user input received in response to the alarm operation may be fed to the learning model 408 for determining 410 new or updated parameters for classifying acoustic signals. When the user input has been received by the element 504 for turning alarm operations off, the new or updated parameters are determined such that the received acoustic signal does not cause an alarm operation. The determined 410 parameters may be applied in classifying the acoustic signals in accordance with the operation described with FIGURE 4b. Accordingly, the updated parameters may cause that the received acoustic signal is classified into a class, where alarm operations are not performed. In this way the system may be configured to turn off alarm operations for specific received acoustic signals.

[0064] On the other hand, if a received acoustic signal is classified to a class, where an alarm operation is not performed, a notification 506 indicating the acoustic signal may be displayed on the user interface. Then a user input received in response the notification may be used for configuring a system for processing acoustic signals. The user input received by an element 502 for turning alarm operations on. Accordingly, the received acoustic signal may be received 402 as input data in the process of FIGURE 4a and the user input received in response to the notification may be fed to the learning model 408 for determining 410 new or updated parameters for classifying acoustic signals. When the user input has been received by the element 502 for turning alarm operations on, the new or updated parameters are determined 410 such that the received acoustic signal causes an alarm operation. The determined parameters may be applied in classifying the acoustic signals in accordance with the operation described with FIGURE 4b. Accordingly, the updated parameters may cause that the received acoustic signal is classified into a class, where alarm operations are performed. In this way the system may be configured to turn on alarm operations for received acoustic signals. It should be appreciated that, the user input may be received by the user operating the user interface 500. The user interface may comprise various forms of possibilities to receive user input, comprising, a button, a user interface element or a location on a touch screen. The user input may cause that classification of the acoustic signals is updated such that alarm operations for specific received acoustic signals are turned on or off.

[0065] In an example, the notification may be an in-app notification or a push notification. An in-app notification may be also referred to as in-app messages. The in-app notifications may be displayed on the user interface during use of a specific app, i.e. application. Accordingly, the in-app notification may be displayed directly within the app itself executed in the computing device.

[0066] In an example, the notification may be a push notification. The push notification may be displayed don the user interface even if a specific application is not being displayed. Accordingly, the push notification may be a notification by one application being executed in the computing device in in the background and the push notification may be displayed on top of a home screen of the computing device or on top of a user interface view of another application. In this way the push notification may serve for alerting the user of the device even if the application is executed in the background.

[0001] It is to be understood that the embodiments of the invention disclosed are not limited to the particular structures or process steps disclosed herein, but are extended to equivalents thereof as would be recognized by those ordinarily skilled in the relevant arts. It should also be understood that terminology employed herein is used for the purpose of describing particular embodiments only and is not intended to be limiting.

[0002] Reference throughout this specification to “one embodiment” or “an embodiment” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, appearances of the phrases “in one embodiment” or “in an embodiment” in various places throughout this specification are not necessarily all referring to the same embodiment.

[0003] As used herein, a plurality of items and/or structural elements may be presented in a common list for convenience. However, these lists should be construed as though each member of the list is individually identified as a separate and unique member. Thus, no individual member of such list should be construed as a de facto equivalent of any other member of the same list solely based on their presentation in a common group without indications to the contrary. In addition, various embodiments and example of the present invention may be referred to herein along with alternatives for the various components thereof. It is understood that such embodiments, examples, and alternatives are not to be construed as de facto equivalents of one another, but are to be considered as separate and autonomous representations of the present invention.

[0004] Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0005] While the forgoing examples are illustrative of the principles of the present invention in one or more particular applications, it will be apparent to those of ordinary skill in the art that numerous modifications in form, usage and details of implementation can be made without the exercise of inventive faculty, and without departing from the principles and concepts of the invention. Accordingly, it is not intended that the invention be limited, except as by the claims set forth below.

[0006] The verbs “to comprise” and “to include” are used in this document as open limitations that neither exclude nor require the existence of also un-recited features. The features recited in depending claims are mutually freely combinable unless otherwise explicitly stated. Furthermore, it is to be understood that the use of "a" or "an", i.e. a singular form, throughout this document does not exclude a plurality.

INDUSTRIAL APPLICABILITY

[0007] The present invention can be applied in monitoring a fish farm.

Claims

A system comprising one or more alarm devices operatively coupled to acoustic signal receiving means, characterized in that said system is configured to provide: (202) an acoustic signal received by the receiving means corresponding to a water craft approaching a fish farm; providing (204), at least one of the alarm devices, one or more alarm functions when the received acoustic signal comprises a water craft stop sound for a fish farm.

The waste system of claim 1, wherein the received acoustic signal is classified into at least one of a plurality of classes configured for the waste system by machine learning process, said plurality of classes comprising at least one class of acoustic signals where no action is performed and operations are performed.

The waste system according to claim 2, wherein the classification is updated based on user time to turn on alarm functions or user time on to turn off alarm functions.

The system according to any one of claims 1, 2 or 3, wherein the stop sound comprises a switching sound, anchoring sound, sound of anchoring and / or no sound indicating movement of the craft away from the fish farm.

The system of any one of claims 1, 2, 3 or 4, wherein the alarm function is provided when the stop sound indicates that the water vehicle is close enough to exit the vehicle to the fish farm.

The system of any one of claims 1 to 5, wherein the receiving means comprises one or more video cameras, still cameras, microphones and / or hydrophones.

The system of any one of claims 1 to 6, wherein the receiving means is an acoustic positioning system capable of locating water craft approaching a fish farm.

The system of any one of claims 1 to 7, wherein alarm functions are provided when the stop sound is determined from a water craft located at at least one location in the fish farm.

The system of any one of claims 1 to 8, wherein the classification of the received acoustic signals is machine controlled and the machine controlled classification is updated based on a user request.

A system according to any one of claims 1 to 9, comprising a data connection unit configured to communicate alarm indicating information over the data connection to the remote system.

The system of any one of claims 1 to 10, wherein the alarm functions comprise transmitting an alarm indication information to a data processing device comprising a user interface, wherein the alarm indication information causes the alarm indication to be displayed by the user interface.

The system according to any one of claims 1 to 11, wherein the alarm functions comprise switching on one or more of the target lights at the fish farm.

The system of any one of claims 1 to 12, wherein the alarm functions comprise providing an alarm sound and / or audio output by an audio output device.

The system of any one of claims 1 to 13, wherein the water vehicle is a motor boat, a rowing boat, a kayak, a canoe or a launch boat.

A fish farm, characterized in that the fish farm comprises a system according to any one of claims 1 to 14.