CN111178433A - Fishing boat operation mode identification method, device and system - Google Patents
Fishing boat operation mode identification method, device and system Download PDFInfo
- Publication number
- CN111178433A CN111178433A CN201911394714.4A CN201911394714A CN111178433A CN 111178433 A CN111178433 A CN 111178433A CN 201911394714 A CN201911394714 A CN 201911394714A CN 111178433 A CN111178433 A CN 111178433A
- Authority
- CN
- China
- Prior art keywords
- data
- fishing boat
- operation mode
- feature
- navigational speed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/254—Fusion techniques of classification results, e.g. of results related to same input data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
Abstract
The invention discloses a fishing boat operation mode identification method, device and system. The method of the invention comprises the following steps: performing fusion arrangement on the collected multi-source heterogeneous data to obtain fusion data; constructing a feature space based on the fusion data, and extracting a feature vector corresponding to each fishing boat in the fusion data according to the feature space to obtain a plurality of feature vectors; training a classification model by utilizing the characteristic vectors of the plurality of characteristics to obtain a classification model capable of identifying each fishing boat operation mode; and when the fishing boat operation mode is identified, the collected operation data of the fishing boat is input into the classification model, and the operation mode of the fishing boat is identified by using the classification model.
Description
Technical Field
The invention relates to a fishing boat operation mode identification method, device and system.
Background
At present, the offshore fishery resources in China decline seriously and the marine ecosystem is seriously damaged due to the nonstandard operation mode and illegal operation of fishing boats in the development of marine economy in China. An intelligent method capable of effectively identifying the operation mode of the fishing boat is urgently needed by a fishing boat supervision department, and the operation behavior of the fishing boat is standardized and supervised. The existing method mainly uses a method based on statistics, rules and traditional manual supervision to identify the fishing boat operation mode, and has the following problems:
1. the data source is single, the utilization rate is low, and the identification accuracy is low.
Generally, a single data source is used for analysis, so that the data utilization rate of other data sources is low, the analysis direction is single, and the recognition rate is low.
2. The recognition algorithm only utilizes structured data and does not fully utilize unstructured data for analysis.
At present, the identification algorithm only utilizes structural data provided by a fishing vessel supervision department, and does not fully utilize other valuable data with open sources to carry out comprehensive fusion analysis.
Disclosure of Invention
The invention aims to provide a fishing boat operation mode identification method, device and system, which are used for carrying out fusion analysis on multi-source, structured and unstructured data and effectively improving the identification accuracy of the fishing boat operation mode.
In a first aspect, an embodiment of the present invention provides a fishing boat operation mode identification method, including:
performing fusion arrangement on the collected multi-source heterogeneous data to obtain fusion data;
constructing a feature space based on the fusion data, and extracting a feature vector corresponding to each fishing boat in the fusion data according to the feature space to obtain a plurality of feature vectors;
training a classification model by utilizing the characteristic vectors of the plurality of characteristics to obtain a classification model capable of identifying each fishing boat operation mode;
and when the fishing boat operation mode is identified, the collected operation data of the fishing boat is input into the classification model, and the operation mode of the fishing boat is identified by using the classification model.
In a second aspect, an embodiment of the present invention provides a fishing boat operation mode identification apparatus, including:
the preprocessing unit is used for performing fusion arrangement on the collected multi-source heterogeneous data to obtain fusion data; constructing a feature space based on the fusion data, and extracting a feature vector corresponding to each fishing boat in the fusion data according to the feature space to obtain a plurality of feature vectors; training a classification model by utilizing the characteristic vectors of the plurality of characteristics to obtain a classification model capable of identifying each fishing boat operation mode;
and the identification unit is used for inputting the collected operation data of the fishing boat into the classification model when the operation mode of the fishing boat is identified, and identifying the operation mode of the fishing boat by using the classification model.
In a third aspect, an embodiment of the present invention provides a fishing vessel operation mode identification system, including: a memory and a processor; a memory storing computer-executable instructions; a processor, the computer executable instructions when executed cause the processor to perform a fishing vessel operation mode identification method.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which one or more computer programs are stored, where the one or more computer programs, when executed, implement a fishing vessel operation mode identification method.
The invention at least achieves the following technical effects:
1. by fusing multi-source heterogeneous data, data information in multiple aspects is effectively integrated, so that the identification and classification results of the fishing boat operation mode are more accurate;
2. by using a big data analysis technology, government policy files and system data are subjected to fusion analysis, so that a comprehensive, rapid and accurate method is provided for relevant supervision departments;
3. the fishing boat operation mode identification method based on the multi-source heterogeneous data has the characteristic of low cost, and can save resources on the premise of ensuring the identification accuracy.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments will be briefly described below. It is appreciated that the following drawings depict only certain embodiments of the invention and are therefore not to be considered limiting of its scope. For a person skilled in the art, it is possible to derive other relevant figures from these figures without inventive effort.
FIG. 1 is a block diagram showing a hardware configuration of a fishing vessel operation manner recognition system according to an embodiment of the present invention;
FIG. 2 is a flow chart of a fishing vessel operation mode identification method according to an embodiment of the present invention;
FIG. 3 is a comparison diagram of simulation results according to an embodiment of the present invention;
FIG. 4 is a block diagram showing the structure of a fishing boat operation mode recognition device according to an embodiment of the present invention;
fig. 5 is a block diagram showing a configuration of a fishing boat operation mode recognition system according to an embodiment of the present invention.
Detailed Description
Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
< example one >
Fig. 1 is a block diagram of a hardware configuration of a fishing vessel operation manner recognition system 100 according to an embodiment of the present invention.
As shown in fig. 1, the fishing vessel operation manner recognition system 100 includes a data collection device 1000 and a fishing vessel operation manner recognition device 2000.
The data collecting device 1000 is used to collect fishing boat operation data and provide the collected fishing boat operation data to the product defect detecting device 2000.
The fishing boat operation mode recognition device 2000 may be any electronic device, such as a PC, a notebook computer, a server, or the like.
In this embodiment, referring to fig. 1, the fishing boat work pattern recognition apparatus 2000 may include a processor 2100, a memory 2200, an interface apparatus 2300, a communication apparatus 2400, a display apparatus 2500, an input apparatus 2600, a speaker 2700, a microphone 2800, and the like.
The processor 2100 may be a mobile version processor. The memory 2200 includes, for example, a ROM (read only memory), a RAM (random access memory), a nonvolatile memory such as a hard disk, and the like. The interface device 2300 includes, for example, a USB interface, a headphone interface, and the like. The communication device 2400 can perform wired or wireless communication, for example, the communication device 2400 may include a short-range communication device, such as any device that performs short-range wireless communication based on a short-range wireless communication protocol, such as a Hilink protocol, WiFi (IEEE 802.11 protocol), Mesh, bluetooth, ZigBee, Thread, Z-Wave, NFC, UWB, LiFi, and the like, and the communication device 2400 may also include a remote communication device, such as any device that performs WLAN, GPRS, 2G/3G/4G/5G remote communication. The display device 2500 is, for example, a liquid crystal display, a touch panel, or the like, and the display device 2500 is used to display data collected by the data collection device 1000. The input device 2600 may include, for example, a touch screen, a keyboard, and the like. A user can input/output voice information through the speaker 2700 and the microphone 2800.
In this embodiment, the memory 2200 of the fishing vessel operation pattern recognition apparatus 2000 is configured to store instructions for controlling the processor 2100 to operate to perform at least the fishing vessel operation pattern recognition method according to any embodiment of the present invention. The skilled person can design the instructions according to the disclosed solution. How the instructions control the operation of the processor is well known in the art and will not be described in detail herein.
Although a plurality of means of the fishing vessel operation pattern recognition means 2000 are shown in fig. 1, the present invention may relate only to some of them, for example, the fishing vessel operation pattern recognition means 2000 relates only to the memory 2200 and the processor 2100.
In this embodiment, the data collecting device 1000 is used to collect fishing boat operation data and provide the fishing boat operation mode identifying device 2000 with the fishing boat operation mode identifying device 2000, and the fishing boat operation mode identifying device 2000 implements the fishing boat operation mode identifying method according to any embodiment of the present invention based on the fishing boat operation data.
It should be understood that although fig. 1 shows only one data collection device 1000 and one fishing vessel operation manner identification device 2000, it is not meant to limit the number of each, and a plurality of data collection devices 1000 and/or fishing vessel operation manner identification devices 2000 may be included in the fishing vessel operation manner identification system 100.
< example two >
With the development of the field of big data application analysis, data analysis presents the characteristics of multiple sources, multiple structures and large quantity, and the multi-source heterogeneous data fusion technology is increasingly applied to various fields as the development trend of a big data processing analysis technology. The multi-source and heterogeneous data fusion technology can perform fusion mining analysis on multi-source, structured and unstructured data, and is more comprehensive and accurate than the analysis only depending on a single data source.
The embodiment also provides a fishing boat operation mode identification method. Fig. 2 is a flowchart of a fishing vessel operation mode identification method according to an embodiment of the present invention, and as shown in fig. 2, the method of the embodiment includes:
and S2100, performing fusion and arrangement on the collected multi-source heterogeneous data to obtain fusion data.
S2200, constructing a feature space based on the fusion data, and extracting a feature vector corresponding to each fishing boat in the fusion data according to the feature space to obtain a plurality of feature vectors.
And S2300, training the classification model by utilizing the plurality of features to the feature vector to obtain the classification model capable of identifying each fishing boat operation mode.
And S2400, when the fishing boat operation mode is identified, inputting the collected operation data of the fishing boat into the classification model, and identifying the operation mode of the fishing boat by using the classification model.
On one hand, the multi-source heterogeneous data are fused, so that data information in multiple aspects is effectively integrated, and the identification and classification results of the fishing boat operation mode are more accurate; on the other hand, by using a big data analysis technology, the government policy files and the system data are subjected to fusion analysis, so that a comprehensive, rapid and accurate method is provided for relevant supervision departments; moreover, the fishing boat operation mode identification method based on the multi-source heterogeneous data has the characteristic of low cost, and resources can be saved on the premise of ensuring the identification accuracy.
In this embodiment, the multi-source heterogeneous data may be collected by the following method:
setting data acquisition tools in advance according to data formats provided by each data source, wherein each data acquisition tool is suitable for acquiring data in one data format; and calling a corresponding data acquisition tool according to a data format provided by the data source, and storing the acquired data into a preset file system by using the data acquisition tool. The data format includes one or more of txt (text) format, CSV (Comma-Separated Values, CSV, character separation value) format, xls (table) format, and database data format (e.g., MySQL database data format).
For text data, such as data files in txt and csv formats, a function can be designed and implemented, and the data can be stored in a file system from the text file or directly stored in the file system. And for table data, such as data files in xls and xlsx formats, the data is stored in a file system from an Excel file through designing a function of realizing the function, or the Excel file is directly stored in the file system. For database data, such as data in MySQL database, the data is read from the database by using the database access interface and stored in the file system.
In some embodiments, the step S2100 performs fusion and sorting on the collected multi-source heterogeneous data, and obtaining the fusion data further includes:
removing repeated data in the multi-source heterogeneous data to obtain processed multi-source heterogeneous data; eliminating noise data in the processed multi-source heterogeneous data to obtain noiseless multi-source heterogeneous data; and carrying out format conversion processing on the noiseless multi-source heterogeneous data to obtain fusion data in the same format.
In one example, processing is performed on multi-source heterogeneous data, including processing of cleaning of repeated data and noise data, conversion of data format, and the like.
Due to the variety of data sources, duplicated data may exist, and the duplicated data is deduplicated by using a deduplication function or designing the deduplication function.
By using the rule-based method, the noise data in the data is cleaned and reduced, and the loss of effective information is avoided in the denoising process. For example, based on the rule that the operating speed of the fishing boat does not exceed 12 knots, if the data shows that the speed of the fishing boat is 50 knots, the data is considered as noise data and is eliminated.
In the data collection and storage process, a disordered data format may exist, which is not beneficial to the post data processing, and the disordered data format is uniformly converted and then stored in a file system.
In some embodiments, the feature vectors include one or more of the following feature vectors:
a feature vector representing time features of the fallowing period, wherein the time features include but are not limited to the characteristics of the beginning and the end of the fallowing period in the time of the month and the day;
the characteristic vector represents the proportion characteristic of the operating navigational speed of the fishing boat in a preset navigational speed interval, and the preset navigational speed interval comprises but is not limited to navigational speed intervals (0, 0.5), navigational speed intervals (0.5, 4.5), navigational speed intervals (4.5, 5.5) and navigational speed intervals (5.5, 12);
the characteristic vector represents the statistical characteristics of the operation navigational speed of the fishing boat in a preset navigational speed interval, the preset navigational speed interval comprises three navigational speed intervals, namely a navigational speed interval (0, 0.5), a navigational speed interval (0.5, 4.5) and a navigational speed interval (4.5, 5.5), and the statistical characteristics comprise but are not limited to a mean value, a median and a standard deviation;
the characteristic vector represents the statistical characteristics of the operation navigational speed of the fishing boat in a preset navigational speed interval based on the preset position information, the preset navigational speed interval comprises three navigational speed intervals including but not limited to a navigational speed interval (0, 0.5), a navigational speed interval (0.5, 4.5) and a navigational speed interval (4.5, 5.5), the statistical characteristics based on the preset position information comprise but not limited to the characteristics of the mean value and the median based on the longitude information of the position of the fishing boat, and/or the characteristics of the mean value and the median based on the latitude information of the position of the fishing boat;
the characteristic vector represents the heading-based statistical characteristic of the operation speed of the fishing boat in a preset speed interval, the preset speed interval comprises three speed intervals including but not limited to a speed interval (0, 0.5), a speed interval (0.5, 4.5) and a speed interval (4.5, 5.5), and the heading-based statistical characteristic comprises but not limited to the standard deviation characteristic of the fishing boat heading;
the characteristic vector of the proportion characteristic recorded in all the records of the navigational speed interval of the fishing vessel at the operational navigational speed of the preset navigational speed interval comprises but is not limited to the proportion characteristic recorded in all the records of the navigational speed interval (0.5, 4.5);
and recording the navigational speed of the operation fishing boat in a preset navigational speed interval in all the navigational speed records in a preset navigational speed range of characteristic vectors of the proportion characteristics, wherein the preset navigational speed range comprises but is not limited to time ranges of 0:00-5:00, 5:00-7:00, 5:00-8:00, 6:00-11:00, 6:00-17:00, 12:00-14:00, 12:00-17:00, 18:00-23:00 and 18:00-5:00, and the preset navigational speed interval comprises but is not limited to navigational speed intervals (0.5, 4.5).
An example, the feature vector representing the time feature of the fallowing period is represented by f1-f6Is shown in which f1-f3Respectively representing the characteristics of the month, day and hour at the beginning of the fallowing period specified by the national policy f3-f6Respectively representing the month, day and time of the end of the fishery period specified by the national policy.
The feature vector representing the proportion feature of the operating speed of the fishing boat in the preset speed interval can be represented by f7-f10Is represented by f7-f10The occupation characteristics of the navigational speed in navigational speed intervals (0, 0.5), navigational speed intervals (0.5, 4.5), navigational speed intervals (4.5, 5.5) and navigational speed intervals (5.5, 12) are shown.
F is a feature vector representing the statistical characteristics of the operating speed of the fishing vessel in a preset speed range11-f19And (4) showing. Wherein f is11-f13Respectively representing the characteristics of mean value, median and standard deviation of the navigational speed in the range of navigational speed interval (0, 0.5), f14-f16Respectively representing the characteristics of mean value, median and standard deviation of the navigational speed in the range of navigational speed interval (0.5, 4.5), f17-f19Respectively represents the characteristics of mean value, median and standard deviation of the navigational speed in the range of navigational speed intervals (4.5, 5.5).
F is a characteristic vector of statistical characteristics based on preset positions and representing the operation speed of the fishing boat in a preset speed interval20-f31And (4) showing. Wherein f is20-f21Respectively representing the average and median characteristics of the longitude in the range of the navigational speed interval (0, 0.5), f22-f23Respectively representing the average value and the median characteristic of the longitude in the range of the navigational speed interval (0.5, 4.5), f24-f25Respectively representing the average and median characteristics of the longitude in the range of the navigational speed interval (4.5, 5.5), f26-f27Respectively representing the characteristics of mean value and median of latitude in the range of navigational speed interval (0, 0.5), f28-f29Respectively representing the characteristics of mean value and median of latitude in the range of navigational speed interval (0.5, 4.5), f30-f31Respectively representing the mean and median characteristics of the latitude in the range of the navigational speed interval (4.5, 5.5).
F is the characteristic vector of the statistical characteristic based on the course of the operation speed of the fishing vessel in the preset speed interval32-f34And (4) showing. f. of32-f34Respectively represents the standard deviation characteristics of the course directions in the range of the navigational speed interval (0, 0.5), (0.5, 4.5) and (4.5, 5.5).
The feature vector f representing the ratio feature of the record of the operation speed of the fishing boat in the preset speed interval in the records of all the speed intervals35-f58Is represented by f35-f58The proportion of the hourly navigational speed in all records is represented by the ratio features of the records in the range of navigational speed interval (0.5, 4.5).
The characteristic vector of the proportion characteristic of the navigational speed record of the operation fishing vessel in the preset navigational speed interval in all navigational speed records can be used as f59-f67Is represented by f59-f67Respectively represent the occupation characteristics of all records of the navigational speed in the range of 0:00-5:00, 5:00-7:00, 5:00-8:00, 6:00-11:00, 6:00-17:00, 12:00-14:00, 12:00-17:00, 18:00-23:00 and 18:00-5:00 in the navigational speed interval (0.5, 4.5).
The dimension of the feature space can be constructed according to the feature quantity of the fishing boat operation mode included in the fusion data, and the dimension of the feature space is the feature quantity of the fishing boat operation mode. For example, with the above 67 feature quantities, a feature space with 67 dimensions can be formed, and each fishing boat can form a feature vector with 67 dimensions as the largest dimension in the feature space.
The classification model in this embodiment is a decision tree model, such as an XGBOOST model. When the model is trained, sample data and the specified feature dimension are input, and the XGB OST model is constructed.
And splitting the root node to obtain two child nodes, enumerating all unselected features when the nodes are split, and calculating loss function increments after all the features are split.
Comparing the model performance before and after splitting, if the model performance can be improved after the feature splitting, the feature is reserved, and if the model performance cannot be improved after the feature splitting, the feature is not reserved.
And selecting the feature which improves the model performance to the highest as the node to be split from the reserved features which can improve the model performance by splitting. When node splitting is performed each time, only the situations before and after the node splitting are considered, and the situations of other nodes are not considered.
And continuously splitting according to the mode, traversing all the training data to form a decision tree, and obtaining a trained classification model.
As shown in fig. 3, the recognition accuracy of the fishing boat operation method using the classification network trained based on the fusion data provided by the present embodiment is higher than that based on the conventional recognition method.
< example three >
The embodiment also provides a fishing boat operation mode identification device. Fig. 4 is a block diagram showing a configuration of a fishing boat operation mode recognition apparatus according to an embodiment of the present invention, and as shown in fig. 4, the apparatus of the present embodiment includes:
the preprocessing unit 4100 is configured to perform fusion arrangement on the collected multi-source heterogeneous data to obtain fusion data; constructing a feature space based on the fusion data, and extracting a feature vector corresponding to each fishing boat in the fusion data according to the feature space to obtain a plurality of feature vectors; training a classification model by utilizing the characteristic vectors of the plurality of characteristics to obtain a classification model capable of identifying each fishing boat operation mode;
an identifying unit 4200, configured to input the collected operation data of the fishing vessel into the classification model when identifying the operation mode of the fishing vessel, and identify the operation mode of the fishing vessel using the classification model.
In some embodiments, the pre-processing unit 4100 comprises: the device comprises a data cleaning module and a format conversion module;
the data cleaning module is used for removing repeated data in the multi-source heterogeneous data to obtain processed multi-source heterogeneous data; eliminating noise data in the processed multi-source heterogeneous data to obtain noiseless multi-source heterogeneous data;
and the format conversion module is used for carrying out format conversion processing on the noiseless multi-source heterogeneous data to obtain fusion data in the same format.
The preprocessing unit 4100 further includes: the data acquisition module calls corresponding data acquisition tools according to data formats provided by the data sources, and stores the acquired data into a preset file system by using the data acquisition tools, wherein the data acquisition tools are preset according to the data formats provided by the data sources, and each data acquisition tool is suitable for acquiring data in one data format.
The preprocessing unit 4100 is further configured to construct a dimension of a feature space according to the feature quantity of the fishing boat operation manner included in the fusion data, where the dimension of the feature space is the feature quantity of the fishing boat operation manner.
The specific implementation manner of each module in the apparatus embodiment of the present invention may refer to the related content in the method embodiment of the present invention, and is not described herein again.
< example six >
Fig. 5 is a block diagram of a fishing vessel operation mode identification system according to an embodiment of the present invention, and as shown in fig. 5, the virtual reality system includes a processor, and optionally further includes an internal bus, a network interface, and a memory, in a hardware level. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory, such as at least one disk Memory.
The processor, the network interface, and the memory may be connected to each other via an internal bus, which may be an ISA (Industry Standard Architecture) bus, a PCI (peripheral component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 5, but this does not indicate only one bus or one type of bus.
And the memory is used for storing programs. In particular, the program may comprise program code comprising computer executable instructions. The memory may include both memory and non-volatile storage and provides instructions and data to the processor.
The processor reads the corresponding computer program from the nonvolatile memory into the memory and then runs the computer program to form the fishing boat operation mode recognition device on the logic level. And the processor executes the program stored in the memory to realize the fishing boat operation mode identification method.
The method executed by the fishing boat operation mode identification device disclosed by the embodiment shown in fig. 5 in the specification can be applied to or realized by a processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above-described fishing boat operation mode identification method can be implemented by integrated logic circuits of hardware in a processor or instructions in the form of software. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present specification may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present specification may be embodied directly in a hardware decoding processor, or in a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is positioned in the memory, and the processor reads the information in the memory and combines the hardware to complete the steps of the fishing boat operation mode identification method.
The invention also provides a computer readable storage medium.
The computer readable storage medium stores one or more computer programs, the one or more computer programs comprising instructions, which when executed by a processor, are capable of implementing the fishing vessel operation mode identification method described above.
For the convenience of clearly describing the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, the words "first", "second", and the like are used to distinguish the same items or similar items with basically the same functions and actions, and those skilled in the art can understand that the words "first", "second", and the like do not limit the quantity and execution order.
While the foregoing is directed to embodiments of the present invention, other modifications and variations of the present invention may be devised by those skilled in the art in light of the above teachings. It should be understood by those skilled in the art that the foregoing detailed description is for the purpose of better explaining the present invention, and the scope of the present invention should be determined by the scope of the appended claims.
Claims (10)
1. A fishing boat operation mode identification method is characterized by comprising the following steps:
performing fusion arrangement on the collected multi-source heterogeneous data to obtain fusion data;
constructing a feature space based on the fusion data, and extracting a feature vector corresponding to each fishing boat in the fusion data according to the feature space to obtain a plurality of feature vectors;
training a classification model by utilizing the characteristic vectors of the plurality of characteristics to obtain a classification model capable of identifying each fishing boat operation mode;
and when the fishing boat operation mode is identified, the collected operation data of the fishing boat is input into the classification model, and the operation mode of the fishing boat is identified by using the classification model.
2. The method of claim 1, wherein the feature vectors comprise one or more of the following feature vectors:
a feature vector representing the time feature of the fallowing period;
the characteristic vector represents the proportion characteristic of the operation navigational speed of the fishing boat in a preset navigational speed interval;
the characteristic vector represents the statistical characteristics of the operation navigational speed of the fishing boat in a preset navigational speed interval;
the characteristic vector represents the statistical characteristics of the operation speed of the fishing boat in a preset speed interval based on a preset position;
the characteristic vector represents the statistical characteristic of the operation speed of the fishing boat in a preset speed interval based on the course;
the characteristic vector represents the proportion characteristic of the record of the operation navigational speed of the fishing boat in the preset navigational speed interval in the records of all navigational speed intervals;
and recording the navigational speed of the operation fishing vessel in the preset navigational speed interval in all the navigational speed records in the characteristic vector of the ratio characteristic in the preset navigational speed record.
3. The method of claim 1, wherein the fusing and sorting the collected multi-source heterogeneous data to obtain fused data comprises:
removing repeated data in the multi-source heterogeneous data to obtain processed multi-source heterogeneous data;
eliminating noise data in the processed multi-source heterogeneous data to obtain noiseless multi-source heterogeneous data;
and carrying out format conversion processing on the noiseless multi-source heterogeneous data to obtain fusion data in the same format.
4. The method of claim 1, wherein the method for collecting multi-source heterogeneous data comprises:
setting data acquisition tools in advance according to data formats provided by each data source, wherein each data acquisition tool is suitable for acquiring data in one data format;
and calling a corresponding data acquisition tool according to a data format provided by the data source, and storing the acquired data into a preset file system by using the data acquisition tool.
5. The method of claim 4, wherein the data format comprises one or more of txt format, csv format, xls format, database data format.
6. The method of claim 1, wherein constructing a feature space based on the fused data comprises:
and constructing the dimension of a feature space according to the feature quantity of the fishing boat operation mode included in the fusion data, wherein the dimension of the feature space is the feature quantity of the fishing boat operation mode.
7. The method of claim 1, wherein the classification model is a decision tree model.
8. A fishing boat operation mode recognition device includes:
the preprocessing unit is used for performing fusion arrangement on the collected multi-source heterogeneous data to obtain fusion data; constructing a feature space based on the fusion data, and extracting a feature vector corresponding to each fishing boat in the fusion data according to the feature space to obtain a plurality of feature vectors; training a classification model by utilizing the characteristic vectors of the plurality of characteristics to obtain a classification model capable of identifying each fishing boat operation mode;
and the identification unit is used for inputting the collected operation data of the fishing boat into the classification model when the operation mode of the fishing boat is identified, and identifying the operation mode of the fishing boat by using the classification model.
9. A fishing boat operation mode identification system is characterized by comprising: a memory and a processor;
the memory storing computer-executable instructions;
the processor, which when executed, causes the processor to perform the fishing vessel operation pattern identification method of any of claims 1-7.
10. A computer-readable storage medium, wherein one or more computer programs are stored on the computer-readable storage medium, which when executed perform the fishing vessel work pattern recognition method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911394714.4A CN111178433A (en) | 2019-12-30 | 2019-12-30 | Fishing boat operation mode identification method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911394714.4A CN111178433A (en) | 2019-12-30 | 2019-12-30 | Fishing boat operation mode identification method, device and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111178433A true CN111178433A (en) | 2020-05-19 |
Family
ID=70652203
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911394714.4A Pending CN111178433A (en) | 2019-12-30 | 2019-12-30 | Fishing boat operation mode identification method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111178433A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116150618A (en) * | 2023-02-02 | 2023-05-23 | 中国水产科学研究院东海水产研究所 | Fishing boat operation type identification method based on deep learning neural network |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109117864A (en) * | 2018-07-13 | 2019-01-01 | 华南理工大学 | Coronary heart disease risk prediction technique, model and system based on heterogeneous characteristic fusion |
| CN109685086A (en) * | 2017-10-18 | 2019-04-26 | 中电科海洋信息技术研究院有限公司 | The recognition methods of marine ships job state, device, equipment and storage medium |
| CN110033051A (en) * | 2019-04-18 | 2019-07-19 | 杭州电子科技大学 | A kind of trawler behavior method of discrimination based on multistep cluster |
| CN110175633A (en) * | 2019-04-29 | 2019-08-27 | 杭州电子科技大学 | A kind of fishing boat track method for detecting abnormality based on Beidou satellite transmission data |
-
2019
- 2019-12-30 CN CN201911394714.4A patent/CN111178433A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109685086A (en) * | 2017-10-18 | 2019-04-26 | 中电科海洋信息技术研究院有限公司 | The recognition methods of marine ships job state, device, equipment and storage medium |
| CN109117864A (en) * | 2018-07-13 | 2019-01-01 | 华南理工大学 | Coronary heart disease risk prediction technique, model and system based on heterogeneous characteristic fusion |
| CN110033051A (en) * | 2019-04-18 | 2019-07-19 | 杭州电子科技大学 | A kind of trawler behavior method of discrimination based on multistep cluster |
| CN110175633A (en) * | 2019-04-29 | 2019-08-27 | 杭州电子科技大学 | A kind of fishing boat track method for detecting abnormality based on Beidou satellite transmission data |
Non-Patent Citations (1)
| Title |
|---|
| 郑巧玲: "基于神经网络和VMS的渔船捕捞类型辨别" * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116150618A (en) * | 2023-02-02 | 2023-05-23 | 中国水产科学研究院东海水产研究所 | Fishing boat operation type identification method based on deep learning neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020147488A1 (en) | Method and device for identifying irregular group | |
| JP6229046B2 (en) | Speech data recognition method, device and server for distinguishing local rounds | |
| TW201913522A (en) | Risk feature screening, description message generation method, device and electronic device | |
| CN106484915B (en) | A kind of cleaning method and system of mass data | |
| CN108063768B (en) | Network malicious behavior identification method and device based on network gene technology | |
| TW202009741A (en) | Feature relationship recommendation method and apparatus, computing device and storage medium | |
| WO2018188539A1 (en) | Data processing method, terminal, device, and storage medium | |
| CN111339248A (en) | Data attribute filling method, device, equipment and computer readable storage medium | |
| CN108234452B (en) | System and method for identifying network data packet multilayer protocol | |
| US11216512B2 (en) | Accessible machine learning backends | |
| CN111259212B (en) | Telemetering data interpretation method, device, equipment and storage medium | |
| CN106649344B (en) | Weblog compression method and device | |
| CN112765150A (en) | Big data heterogeneous fusion extraction method and device | |
| CN111178433A (en) | Fishing boat operation mode identification method, device and system | |
| CN109582774A (en) | Natural language classification method, device, equipment and storage medium | |
| WO2020140620A1 (en) | Intelligent decision based text classification method and device, server and storage medium | |
| WO2019096176A1 (en) | Method and system for learning data processing, and electronic device | |
| WO2014109040A1 (en) | Control method, control program, and control device | |
| EP3200098A1 (en) | Methods and apparatus for comparing different types of data | |
| CN107798101A (en) | The webpage data acquiring method and system of user's free point arrangement | |
| CN115567371B (en) | Abnormity detection method, device, equipment and readable storage medium | |
| CN110543426A (en) | software performance risk detection method and device | |
| CN103186672B (en) | file ordering method and device thereof | |
| CN115080745A (en) | Multi-scene text classification method, device, equipment and medium based on artificial intelligence | |
| CN115470279A (en) | Data source conversion method, device, equipment and medium based on enterprise data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |