A method and system for optimizing and processing Internet of Things data based on deep-water cages
By using noise model and inverse filter technology in deep water cages, the noise data collected by IoT devices is solved, and the accuracy and reliability of data are improved.
Patent Information
- Application Number
- CN202411034541.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-31
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-07-31
AI Technical Summary
The accuracy of data acquisition of IoT devices in deep water cages is low, mainly due to the fact that the noise problems caused by excessive flow rates or biological aggregation have not been effectively solved.
Using a preset noise model method, acoustic waves, video and traffic data are collected through water acoustic sensors, cameras and flow monitors, noise samples are analyzed and matched, inverse filter parameters are determined, and denoising is used to optimize IoT data.
It improves the accuracy of data acquisition of IoT devices in deep water cages, reduces the impact of noise through denoising processing, and enhances the reliability of data.
Smart Images

Figure CN118568419B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of Internet of Things, and in particular to a method and system for optimizing and processing Internet of Things data based on a deep-water cage. Background Art
[0002] Deepwater cages are often used in deepwater aquaculture activities. When deepwater cages are set up, IoT devices are set up to collect data from deepwater cages so that users can understand the situation of deepwater cages. However, since the environment in which deepwater cages are located is prone to excessive flow or biological aggregation, the collected IoT data is prone to noise, which in turn leads to inaccurate IoT data for deepwater cages. Since there is no existing technology that can solve this problem, there is a problem of low accuracy in IoT device data collection in deepwater cages.
[0003] Therefore, there is an urgent need for an IoT data optimization processing strategy to solve the problem of low accuracy of IoT device data collection in deep-water cages. Summary of the invention
[0004] The embodiment of the present invention provides an Internet of Things data optimization processing method and system based on a deep-water cage to solve the problem of low accuracy of data collection of Internet of Things devices in deep-water cages.
[0005] In order to solve the above problems, an embodiment of the present invention provides an Internet of Things data optimization processing method based on a deep-water cage, comprising:
[0006] Obtain IoT data collected in the deep-water cage to be tested;
[0007] Based on a preset noise model, the noise of the Internet of Things data is estimated to obtain the noise data in the deep-water cage to be measured; wherein the noise model includes: a number of noise samples marked with a signal strength sample mean, a signal strength sample variance and a signal spectrum sample density; noise samples are analyzed based on acoustic wave data, video data and flow data; acoustic wave data is collected at the deep-water cage to be measured by a hydroacoustic sensor; video data is collected at the deep-water cage to be measured by a camera; flow data is collected at the deep-water cage to be measured by a flow monitor; the acquisition time of the acoustic wave data, video data and flow data is consistent; the hydroacoustic sensor, the camera and the flow monitor are arranged on a telescopic rod;
[0008] determining inverse filter parameters based on the noise data;
[0009] The IoT data is input into the inverse filter corresponding to the inverse filter parameters for denoising, so as to complete the noise optimization processing of the IoT data collected in the deep-water cage to be measured.
[0010] As an improvement of the above solution, the noise estimation of the IoT data based on a preset noise model to obtain the noise data in the deep-water cage to be measured includes:
[0011] Extracting the signal strength mean and signal strength variance corresponding to the IoT data;
[0012] Performing Fourier transform on the IoT data to obtain signal spectrum density;
[0013] Based on the signal strength mean, signal strength variance and signal spectrum density of the IoT data, matching is performed in a preset noise model to obtain a noise matching degree; wherein the noise model includes: a plurality of noise samples marked with a signal strength sample mean, a signal strength sample variance and a signal spectrum sample density;
[0014] Signals in the IoT data whose noise matching degree is greater than a matching degree threshold are marked as noise, and the noise data of the deep-water cage to be tested is obtained by summarizing.
[0015] As an improvement of the above solution, the generation of the noise model includes:
[0016] Receiving the acoustic wave data, video data and flow data collected at the deep-water cage to be measured; wherein, based on the characteristics of the telescopic rod moving up and down, data collection is performed at different depths outside the deep-water cage to be measured;
[0017] Making a judgment on the video data and the traffic data;
[0018] If the video data meets the first noise environment condition, or the traffic data meets the second noise environment condition, the target acquisition time is recorded, the sound wave data corresponding to the target acquisition time is retrieved and signal preprocessing is performed to obtain a number of noise samples;
[0019] Extracting a signal strength sample mean and a signal strength sample variance of each of the noise samples;
[0020] Performing Fourier transform on each of the noise samples to obtain signal spectrum sample density;
[0021] Each noise sample and the signal strength sample mean, signal strength sample variance and signal spectrum sample density corresponding to each noise sample are stored in a database to obtain a noise model.
[0022] As an improvement of the above solution, the judging of the video data and the traffic data further includes:
[0023] If the video data does not meet the first noise environment condition, and the traffic data does not meet the second noise environment condition, the current sound wave data is selected as normal sound wave data;
[0024] After determining that the sound wave data is normal, the telescopic rod is rotated in the deep-water cage, so that the flow monitor of the telescopic rod collects the flow data in the deep-water cage to be measured;
[0025] Retrieving the surface wind data of the area where the deep-water cage to be measured is located;
[0026] Based on the water depth where the flow monitor on the telescopic rod is located, the preset flow rate calculation formula and the wind data, the basic flow rate of the water body at the water depth where the flow monitor is located is calculated; wherein the flow rate calculation formula is specifically:
[0027] ;
[0028] In the formula, V is the basic velocity of the water body, U is the surface wind data, is the surface Ekman drift coefficient, D is the water depth, and H is the attenuation depth parameter;
[0029] Based on the flow data currently collected by the flow monitor and the current basic flow velocity of the water body, the target water depth is marked so that the user can determine the water depth position of the aquaculture based on the target water depth; wherein, when the difference between the flow data currently collected by the flow monitor and the current basic flow velocity of the water body is greater than the flow velocity difference threshold, the water depth at which the flow monitor is located at this time is marked as the target water depth.
[0030] As an improvement of the above solution, the video data satisfies the first noise environment condition, including:
[0031] Identify every two frames of video data;
[0032] If the area of the pixel change region between every two frames is greater than the area change threshold, and the RGB difference of the pixel change region is greater than the RGB change threshold, the video data corresponding to the current two frames meet the first noise environment condition, and the acquisition time of the current two frames is selected as the target acquisition time;
[0033] Otherwise, do nothing.
[0034] As an improvement of the above solution, the traffic data satisfies the second noise environment condition, including:
[0035] In the flow data, the flow rate with the largest time proportion is selected as the flow rate threshold;
[0036] Identify the flow rate of flow data;
[0037] If the flow rate is greater than or equal to the flow rate threshold, the flow data with a flow rate greater than the flow rate threshold meets the second noise environment condition, and the collection time of the current flow data is selected as the target collection time.
[0038] As an improvement of the above solution, the inverse filter parameters include: a stopband range of a band-stop filter and a passband width of a bandpass filter; and determining the inverse filter parameters based on the noise data includes:
[0039] Extracting a first signal frequency range corresponding to the noise data, and determining a stopband range of the band-stop filter based on the first signal frequency range;
[0040] Summarize normal sound wave data to obtain a normal sound wave data set;
[0041] A second signal frequency range corresponding to the normal sound wave data set is extracted, and a passband width of the bandpass filter is determined based on the second signal frequency range.
[0042] Accordingly, an embodiment of the present invention further provides an IoT data optimization processing system based on deepwater cages, comprising: a data acquisition module, a noise estimation module, a data determination module and a denoising module;
[0043] The data acquisition module is used to acquire the IoT data collected in the deep-water cage to be tested;
[0044] The noise estimation module is used to perform noise estimation on the IoT data based on a preset noise model to obtain the noise data in the deep-water cage to be measured; wherein the noise model includes: a number of noise samples marked with a signal strength sample mean, a signal strength sample variance and a signal spectrum sample density; noise samples are analyzed based on acoustic wave data, video data and flow data; acoustic wave data is collected at the deep-water cage to be measured by a hydroacoustic sensor; video data is collected at the deep-water cage to be measured by a camera; flow data is collected at the deep-water cage to be measured by a flow monitor; the acquisition time of the acoustic wave data, video data and flow data is consistent; the hydroacoustic sensor, the camera and the flow monitor are arranged on a telescopic rod;
[0045] The data determination module is used to determine the inverse filter parameters based on the noise data;
[0046] The denoising module is used to input the IoT data into the inverse filter corresponding to the inverse filter parameters for denoising, so as to complete the noise optimization processing of the IoT data collected in the deep-water cage to be measured.
[0047] Correspondingly, an embodiment of the present invention further provides a computer terminal device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements a method for optimizing and processing Internet of Things data based on deep-water cages as described in the present invention.
[0048] Correspondingly, an embodiment of the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute a method for optimizing and processing Internet of Things data based on deep-water cages as described in the present invention.
[0049] As can be seen from the above, the present invention has the following beneficial effects:
[0050] The present invention provides an optimization processing method for Internet of Things data based on deep-water cages, which obtains Internet of Things data collected in a deep-water cage to be tested; estimates the noise of the Internet of Things data based on a preset noise model to obtain the noise data in the deep-water cage to be tested; determines the inverse filter parameters based on the noise data; and inputs the Internet of Things data into an inverse filter corresponding to the inverse filter parameters for denoising, so as to complete the noise optimization processing of the Internet of Things data collected in the deep-water cage to be tested. The present invention estimates the noise of the Internet of Things data collected by the deep-water cage to be tested based on a preset noise model, thereby confirming the noise data, and setting the inverse filter based on the noise data, thereby realizing denoising of the Internet of Things data of the deep-water cage and improving the collection accuracy of the Internet of Things device data in the deep-water cage. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] Figure 1 It is a flow chart of a method for optimizing and processing Internet of Things data based on deep-water cages provided by one embodiment of the present invention;
[0052] Figure 2 It is a structural schematic diagram of an Internet of Things data optimization processing system based on a deep-water cage provided by an embodiment of the present invention;
[0053] Figure 3 It is a schematic diagram of the structure of a terminal device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0055] Embodiment 1
[0056] See also Figure 1 , Figure 1 : is a flow chart of a method for optimizing and processing Internet of Things data based on deep-water cages provided by an embodiment of the present invention, such as Figure 1As shown, this embodiment includes steps 101 to 104, and each step is specifically as follows:
[0057] Step 101: Obtain IoT data collected in the deep-water cage to be tested.
[0058] In this embodiment, the IoT data of the deepwater cage to be tested is collected through the IoT device, and the corresponding IoT device is selected according to the water quality, depth, temperature and water pressure of the deepwater cage to ensure the stability and waterproof performance of the IoT device. The IoT device transmits data in a wired manner, thereby transmitting the IoT data to the device / equipment for executing the IoT data optimization processing method based on the deepwater cage.
[0059] Step 102: Estimating the noise of the IoT data based on a preset noise model to obtain the noise data in the deep-water cage to be measured; wherein the noise model includes: a number of noise samples marked with a signal strength sample mean, a signal strength sample variance and a signal spectrum sample density; analyzing the noise samples based on the acoustic wave data, the video data and the flow data; collecting the acoustic wave data at the deep-water cage to be measured by a hydroacoustic sensor; collecting the video data at the deep-water cage to be measured by a camera; collecting the flow data at the deep-water cage to be measured by a flow monitor; the collection time of the acoustic wave data, the video data and the flow data is kept consistent; the hydroacoustic sensor, the camera and the flow monitor are arranged on a telescopic rod.
[0060] It should be noted that an inwardly concave groove is provided on the outer surface of the deep-water cage to be measured so that the telescopic rod can move up and down and rotate left and right in the groove.
[0061] In this embodiment, the noise estimation of the IoT data based on a preset noise model to obtain the noise data in the deep-water cage to be measured includes:
[0062] Extracting the signal strength mean and signal strength variance corresponding to the IoT data;
[0063] Performing Fourier transform on the IoT data to obtain signal spectrum density;
[0064] Based on the signal strength mean, signal strength variance and signal spectrum density of the IoT data, matching is performed in a preset noise model to obtain a noise matching degree; wherein the noise model includes: a plurality of noise samples marked with a signal strength sample mean, a signal strength sample variance and a signal spectrum sample density;
[0065] Signals in the IoT data whose noise matching degree is greater than a matching degree threshold are marked as noise, and the noise data of the deep-water cage to be tested is obtained by summarizing.
[0066] In a specific embodiment, the signal strength mean and signal strength variance of IoT data are extracted: the signal strength mean and variance are extracted from IoT data. For example, each data point of IoT data contains time, location, and signal strength. The signal strength mean and variance of all data points are calculated to obtain the signal strength mean (Mean) and signal strength variance (Variance);
[0067] Performing Fourier transform on IoT data will yield a spectrum representation of the signal, showing the energy distribution of the signal at different frequencies.
[0068] It can be understood that the noise matching degree is calculated by comparing the signal strength mean, variance and spectral density of the IoT data with the values of the corresponding samples in the noise model. The matching degree can be evaluated by using a certain distance metric or similarity index, such as the Euclidean distance or correlation coefficient; and the matching degree threshold can be a value adaptively set based on different water depth environments.
[0069] In this embodiment, the generation of the noise model includes:
[0070] Receiving the acoustic wave data, video data and flow data collected at the deep-water cage to be measured; wherein, based on the characteristics of the telescopic rod moving up and down, data collection is performed at different depths outside the deep-water cage to be measured;
[0071] Making a judgment on the video data and the traffic data;
[0072] If the video data meets the first noise environment condition, or the traffic data meets the second noise environment condition, the target acquisition time is recorded, the sound wave data corresponding to the target acquisition time is retrieved and signal preprocessing is performed to obtain a number of noise samples;
[0073] Extracting a signal strength sample mean and a signal strength sample variance of each of the noise samples;
[0074] Performing Fourier transform on each of the noise samples to obtain signal spectrum sample density;
[0075] Each noise sample and the signal strength sample mean, signal strength sample variance and signal spectrum sample density corresponding to each noise sample are stored in a database to obtain a noise model.
[0076] In a specific embodiment, by initially installing a hydroacoustic sensor, a camera and a flow monitor in the deep-water cage to be tested, the water flow conditions and biological dynamics of the deep-water cage to be tested can be recorded, which is beneficial for users to understand the impact between the sound wave data collected by the hydroacoustic sensor and the water flow conditions and biological dynamics.
[0077] It can be understood that the present invention uses the signal strength mean, signal strength variance and signal spectrum density as the characteristics of noise, so that the signal of the Internet of Things data can be judged based on three dimensions when matching the noise, thereby improving the accuracy of the Internet of Things data noise estimation.
[0078] In this embodiment, the judging of the video data and the traffic data further includes:
[0079] If the video data does not meet the first noise environment condition, and the traffic data does not meet the second noise environment condition, the current sound wave data is selected as normal sound wave data;
[0080] After determining that the sound wave data is normal, controlling the telescopic rod to rotate in the deep-water cage, so that the flow monitor of the telescopic rod collects the flow data in the deep-water cage to be measured;
[0081] Retrieving the surface wind data of the area where the deep-water cage to be measured is located;
[0082] Based on the water depth where the flow monitor on the telescopic rod is located, the preset flow rate calculation formula and the wind data, the basic flow rate of the water body at the water depth where the flow monitor is located is calculated; wherein the flow rate calculation formula is specifically:
[0083] ;
[0084] In the formula, V is the basic velocity of the water body, U is the surface wind data, is the surface Ekman drift coefficient, D is the water depth, and H is the attenuation depth parameter;
[0085] Based on the flow data currently collected by the flow monitor and the current basic flow velocity of the water body, the target water depth is marked so that the user can determine the water depth position of the aquaculture based on the target water depth; wherein, when the difference between the flow data currently collected by the flow monitor and the current basic flow velocity of the water body is greater than the flow velocity difference threshold, the water depth at which the flow monitor is located at this time is marked as the target water depth.
[0086] After determining the target water depth for aquaculture, since there is no noise influence, the data collected at this time are all relevant data of the aquaculture. Users can carry out targeted feed delivery or other aquaculture activities at the target water depth, which is conducive to saving aquaculture costs.
[0087] In a specific embodiment, the attenuation depth parameter H represents the Ekman drift coefficient along the vertical direction. The depth required to decay to 1 / e (the base of the natural logarithm) of the original value. The specific value of H depends on the characteristics of the sea / water area and environmental conditions, and is generally between tens and hundreds of meters. Determining the surface Ekman drift coefficient requires a large amount of observation data and research work, as well as a full understanding of the sea / water environment and characteristics. Users need to set it adaptively based on actual conditions. The velocity difference threshold needs to be set adaptively by the user based on the habits of the aquaculture.
[0088] In this embodiment, the video data satisfies the first noise environment condition, including:
[0089] Identify every two frames of video data;
[0090] If the area of the pixel change region between every two frames is greater than the area change threshold, and the RGB difference of the pixel change region is greater than the RGB change threshold, the video data corresponding to the current two frames meet the first noise environment condition, and the acquisition time of the current two frames is selected as the target acquisition time;
[0091] Otherwise, do nothing.
[0092] In a specific embodiment, biological aggregation or movement may cause biological noise in deep-water cages, and the biological noise generation situation of deep-water cages is identified by the area of pixel change region and the RGB difference of pixel change region as the first noise environment condition.
[0093] It should be noted that the area of the pixel change region can identify environmental changes, but the pixel change region may appear due to meteorological problems, but this is not caused by biological noise; the pixel change regions caused by meteorological problems are all changes in light in water, and the RGB difference is not large. Identification through the RGB difference of the pixel change region can eliminate the influence of meteorological conditions and accurately identify the biological noise caused by biological movement.
[0094] In this embodiment, the traffic data satisfies the second noise environment condition, including:
[0095] In the flow data, the flow rate with the largest time proportion is selected as the flow rate threshold;
[0096] Identify the flow rate of flow data;
[0097] If the flow rate is greater than or equal to the flow rate threshold, the flow data with a flow rate greater than the flow rate threshold meets the second noise environment condition, and the collection time of the current flow data is selected as the target collection time.
[0098] In a specific embodiment, when the water flow is too large due to meteorological conditions or hydrological influences, water flow noise will also be generated. Since the water flow velocities in different areas are different, the present invention can adapt to the water flow noise detection in different areas by selecting the flow rate with the largest time proportion as the flow rate threshold, and judge the water flow noise by identifying the Internet of Things data when it is greater than the flow rate threshold.
[0099] Preferably, the noise model needs to be updated in a timely manner to meet the changes in flow velocity in different regions and seasons, thereby avoiding the problem of inaccurate noise model due to large differences in meteorological environment.
[0100] It can be understood that the flow rate threshold may be a range formed by the top three flow rate maximums and flow rate minimums in terms of time proportion.
[0101] Step 103: Determine inverse filter parameters based on the noise data.
[0102] In this embodiment, the inverse filter parameters include: a stopband range of a band-stop filter and a passband width of a bandpass filter; and determining the inverse filter parameters based on the noise data includes:
[0103] Extracting a first signal frequency range corresponding to the noise data, and determining a stopband range of the band-stop filter based on the first signal frequency range;
[0104] Summarize normal sound wave data to obtain a normal sound wave data set;
[0105] A second signal frequency range corresponding to the normal sound wave data set is extracted, and a passband width of the bandpass filter is determined based on the second signal frequency range.
[0106] In a specific embodiment, the frequency components of the normal sound wave signal are retained and noise is suppressed by setting the passband width of the filter (eg, if the normal sound wave frequency in IoT data is 100 Hz to 10 kHz, then the passband width is 100 Hz to 10 kHz).
[0107] It can be understood that in order to better illustrate the setting of the stopband range of the band-stop filter, the following example is given: a spectrum analysis of the high-frequency noise of the deep-water cage to be measured shows that it is mainly concentrated in the frequency range above 10kHz and may have a higher power spectral density. In order to attenuate the high-frequency noise, we can set the stopband range of the band-stop filter to above 10kHz and adjust the stopband range of the filter based on the estimate of the noise power spectral density.
[0108] Using these adjusted inverse filters, we can pass the original signal through the filter to reduce the noise component as much as possible and retain the frequency components of the music signal. By adjusting the frequency range and noise characteristics, we can better adapt to the characteristics of the signal and noise and achieve a more effective inverse wave denoising effect. It should be noted that the specific adjustment parameters need to be adjusted and optimized according to actual conditions and needs.
[0109] Step 104: input the IoT data into the inverse filter corresponding to the inverse filter parameters for denoising, so as to complete the noise optimization processing of the IoT data collected in the deep-water cage to be measured.
[0110] In a specific embodiment, the IoT data is input into MATLAB and denoised using the MATLAB inverse filter function. The denoising accuracy of the inverse filter is improved by setting the stopband range of the band-stop filter and the passband width of the bandpass filter.
[0111] See also Figure 2 , Figure 2 It is a structural diagram of an Internet of Things data optimization processing system based on a deep-water cage provided by an embodiment of the present invention, comprising: a data acquisition module 201, a noise estimation module 202, a data determination module 203 and a denoising module 204;
[0112] The data acquisition module is used to acquire the IoT data collected in the deep-water cage to be tested;
[0113] The noise estimation module is used to perform noise estimation on the IoT data based on a preset noise model to obtain the noise data in the deep-water cage to be measured; wherein the noise model includes: a number of noise samples marked with a signal strength sample mean, a signal strength sample variance and a signal spectrum sample density; noise samples are analyzed based on acoustic wave data, video data and flow data; acoustic wave data is collected at the deep-water cage to be measured by a hydroacoustic sensor; video data is collected at the deep-water cage to be measured by a camera; flow data is collected at the deep-water cage to be measured by a flow monitor; the acquisition time of the acoustic wave data, video data and flow data is consistent; the hydroacoustic sensor, the camera and the flow monitor are arranged on a telescopic rod;
[0114] The data determination module is used to determine the inverse filter parameters based on the noise data;
[0115] The denoising module is used to input the IoT data into the inverse filter corresponding to the inverse filter parameters for denoising, so as to complete the noise optimization processing of the IoT data collected in the deep-water cage to be measured.
[0116] It can be understood that the above-mentioned system item embodiments correspond to the method item embodiments of the present invention, which can implement the Internet of Things data optimization processing method based on deep-water cages provided by any one of the above-mentioned method item embodiments of the present invention.
[0117] This embodiment obtains the IoT data collected in the deep-water cage to be measured; estimates the noise of the IoT data based on a preset noise model to obtain the noise data in the deep-water cage to be measured; determines the inverse filter parameters based on the noise data; and inputs the IoT data into the inverse filter corresponding to the inverse filter parameters for denoising, so as to complete the noise optimization processing of the IoT data collected in the deep-water cage to be measured. Based on a preset noise model, the present invention estimates the noise of the IoT data collected from the deep-water cage to be measured, thereby confirming the noise data, and setting the inverse filter based on the noise data, thereby achieving denoising of the IoT data of the deep-water cage and improving the accuracy of data collection of IoT devices in the deep-water cage.
[0118] Embodiment 2
[0119] See also Figure 3 , Figure 3 It is a schematic diagram of the structure of a terminal device provided in one embodiment of the present invention.
[0120] A terminal device of this embodiment includes: a processor 301, a memory 302, and a computer program stored in the memory 302 and executable on the processor 301. When the processor 301 executes the computer program, the steps of the above-mentioned method for optimizing the processing of IoT data based on deep-water cages in the embodiment are implemented, for example: Figure 1 All steps of the method for optimizing and processing Internet of Things data based on deep-water cages are shown. Alternatively, when the processor executes the computer program, the functions of each module in the above-mentioned system embodiments are realized, for example: Figure 2 All modules of the IoT data optimization processing system based on deep-water cages are shown.
[0121] In addition, an embodiment of the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the Internet of Things data optimization processing method based on deep-water cages as described in any of the above embodiments.
[0122] Those skilled in the art will understand that the schematic diagram is merely an example of a terminal device and does not constitute a limitation on the terminal device. The terminal device may include more or fewer components than shown in the diagram, or a combination of certain components, or different components. For example, the terminal device may also include input and output devices, network access devices, buses, etc.
[0123] The processor 301 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor 301 is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.
[0124] The memory 302 can be used to store the computer program and / or module. The processor 301 implements various functions of the terminal device by running or executing the computer program and / or module stored in the memory and calling the data stored in the memory 302. The memory 302 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.). In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.
[0125] Wherein, if the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.
[0126] It should be noted that the system embodiment described above is merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the system embodiment provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.
[0127] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.
Claims
1. A method for optimizing and processing Internet of Things data based on deep-water cages, characterized in that: include: Obtain IoT data collected in the deep-water cage to be tested; Based on a preset noise model, the noise of the Internet of Things data is estimated to obtain the noise data in the deep-water cage to be measured; wherein the noise model includes: a number of noise samples marked with a signal strength sample mean, a signal strength sample variance and a signal spectrum sample density; noise samples are analyzed based on acoustic wave data, video data and flow data; acoustic wave data is collected at the deep-water cage to be measured by a hydroacoustic sensor; video data is collected at the deep-water cage to be measured by a camera; flow data is collected at the deep-water cage to be measured by a flow monitor; the acquisition time of the acoustic wave data, video data and flow data is consistent; the hydroacoustic sensor, the camera and the flow monitor are arranged on a telescopic rod; determining inverse filter parameters based on the noise data; Inputting the IoT data into the inverse filter corresponding to the inverse filter parameter for denoising, so as to complete the noise optimization processing of the IoT data collected in the deep-water cage to be measured; Wherein, the noise estimation of the IoT data based on the preset noise model to obtain the noise data in the deep-water cage to be measured includes: extracting the signal strength mean and signal strength variance corresponding to the IoT data; performing Fourier transform on the IoT data to obtain signal spectrum density; matching the signal strength mean, signal strength variance and signal spectrum density of the IoT data in the preset noise model to obtain noise matching degree; marking the signal in the IoT data whose noise matching degree is greater than the matching degree threshold as noise, and summarizing to obtain the noise data of the deep-water cage to be measured; The generation of the noise model includes: receiving the sound wave data, video data and flow data collected outside the deep-water cage to be measured; based on the characteristics of the telescopic rod moving up and down, data is collected at different depths outside the deep-water cage to be measured; the video data and the flow data are judged; if the video data meets the first noise environment condition, or the flow data meets the second noise environment condition, the target collection time is recorded, the sound wave data corresponding to the target collection time is retrieved and the signal preprocessing is performed to obtain a number of noise samples; the signal strength sample mean and the signal strength sample variance of each noise sample are extracted; each noise sample is Fourier transformed to obtain the signal spectrum sample density; each noise sample and the signal strength sample mean, signal strength sample variance and signal spectrum sample density corresponding to each noise sample are stored in a database to obtain the noise model.
2. The method for optimizing and processing Internet of Things data based on deep-water cages according to claim 1 is characterized in that: The judging of the video data and the traffic data further includes: If the video data does not meet the first noise environment condition, and the traffic data does not meet the second noise environment condition, the current sound wave data is selected as normal sound wave data; After determining that the sound wave data is normal, controlling the telescopic rod to rotate in the deep-water cage, so that the flow monitor of the telescopic rod collects the flow data in the deep-water cage to be measured; Retrieving the surface wind data of the area where the deep-water cage to be measured is located; Based on the water depth where the flow monitor on the telescopic rod is located, the preset flow rate calculation formula and the wind data, the basic flow rate of the water body at the water depth where the flow monitor is located is calculated; wherein the flow rate calculation formula is specifically: ; In the formula, V is the basic velocity of the water body, U is the surface wind data, is the surface Ekman drift coefficient, D is the water depth, and H is the attenuation depth parameter; Based on the flow data currently collected by the flow monitor and the current basic flow velocity of the water body, the target water depth is marked so that the user can determine the water depth position of the aquaculture based on the target water depth; wherein, when the difference between the flow data currently collected by the flow monitor and the current basic flow velocity of the water body is greater than the flow velocity difference threshold, the water depth at which the flow monitor is located at this time is marked as the target water depth.
3. The method for optimizing and processing Internet of Things data based on deep-water cages according to claim 2 is characterized in that: The video data meets a first noise environment condition, including: Identify every two frames of video data; If the area of the pixel change region between every two frames is greater than the area change threshold, and the RGB difference of the pixel change region is greater than the RGB change threshold, the video data corresponding to the current two frames meet the first noise environment condition, and the acquisition time of the current two frames is selected as the target acquisition time; Otherwise, do nothing.
4. The method for optimizing and processing Internet of Things data based on deep-water cages according to claim 2 is characterized in that: The flow data meets the second noise environment condition, including: In the flow data, the flow rate with the largest time proportion is selected as the flow rate threshold; Identify the flow rate of flow data; If the flow rate is greater than or equal to the flow rate threshold, the flow data with a flow rate greater than the flow rate threshold meets the second noise environment condition, and the collection time of the current flow data is selected as the target collection time.
5. The method for optimizing and processing Internet of Things data based on deep-water cages according to claim 4 is characterized in that: The inverse filter parameters include: a stopband range of a band-stop filter and a passband width of a bandpass filter; and determining the inverse filter parameters based on the noise data includes: Extracting a first signal frequency range corresponding to the noise data, and determining a stopband range of the band-stop filter based on the first signal frequency range; Summarize normal sound wave data to obtain a normal sound wave data set; A second signal frequency range corresponding to the normal sound wave data set is extracted, and a passband width of the bandpass filter is determined based on the second signal frequency range.
6. An Internet of Things data optimization processing system based on deep-water cages, characterized in that: include: Data acquisition module, noise estimation module, data determination module and denoising module; The data acquisition module is used to acquire the IoT data collected in the deep-water cage to be tested; The noise estimation module is used to perform noise estimation on the IoT data based on a preset noise model to obtain the noise data in the deep-water cage to be measured; wherein the noise model includes: a number of noise samples marked with a signal strength sample mean, a signal strength sample variance and a signal spectrum sample density; noise samples are analyzed based on acoustic wave data, video data and flow data; acoustic wave data is collected at the deep-water cage to be measured by a hydroacoustic sensor; video data is collected at the deep-water cage to be measured by a camera; flow data is collected at the deep-water cage to be measured by a flow monitor; the acquisition time of the acoustic wave data, video data and flow data is consistent; the hydroacoustic sensor, the camera and the flow monitor are arranged on a telescopic rod; The data determination module is used to determine the inverse filter parameters based on the noise data; The denoising module is used to input the IoT data into the inverse filter corresponding to the inverse filter parameter for denoising, so as to complete the noise optimization processing of the IoT data collected in the deep-water cage to be measured; Wherein, the noise estimation of the IoT data based on the preset noise model to obtain the noise data in the deep-water cage to be measured includes: extracting the signal strength mean and signal strength variance corresponding to the IoT data; performing Fourier transform on the IoT data to obtain signal spectrum density; matching the signal strength mean, signal strength variance and signal spectrum density of the IoT data in the preset noise model to obtain noise matching degree; marking the signal in the IoT data whose noise matching degree is greater than the matching degree threshold as noise, and summarizing to obtain the noise data of the deep-water cage to be measured; The generation of the noise model includes: receiving the sound wave data, video data and flow data collected outside the deep-water cage to be measured; based on the characteristics of the telescopic rod moving up and down, data is collected at different depths outside the deep-water cage to be measured; the video data and the flow data are judged; if the video data meets the first noise environment condition, or the flow data meets the second noise environment condition, the target collection time is recorded, the sound wave data corresponding to the target collection time is retrieved and the signal preprocessing is performed to obtain a number of noise samples; the signal strength sample mean and the signal strength sample variance of each noise sample are extracted; each noise sample is Fourier transformed to obtain the signal spectrum sample density; each noise sample and the signal strength sample mean, signal strength sample variance and signal spectrum sample density corresponding to each noise sample are stored in a database to obtain the noise model.
7. A computer terminal device, characterized in that: It comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements a method for optimizing and processing Internet of Things data based on deep-water cages as described in any one of claims 1 to 5.
8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the Internet of Things data optimization processing method based on deep-water cages as described in any one of claims 1 to 5.
Citation Information
Patent Citations
Underwater-acoustic-channel discrete noise source suppression method of multi-sensor array
CN105022050A
Offshore rainfall noise characteristic in-situ measurement device and method
CN111879293A
Underwater fish school motion mode analysis method
CN112712548A
Underwater sound audio denoising method
CN116612735A
Image processing apparatus, image processing method, and imaging apparatus
US20100188535A1
