DE202023107102U1 - An IoT-based water quality prediction system for aquaponics farming applications - Google Patents

Abstract

An IoT based water quality prediction system for aquaponic farming applications, the system comprising: an array of multiple IoT sensors configured to collect real-time data from the aquaponic environment; a storage unit for storing the collected real-time data using a sensor array, the storage unit using a storage device; a centralized processing unit comprising a configured processor for monitoring and predicting water quality for aquaponic farming by using the data stored in the storage unit to the processor for the prediction to train; anda user interface in communication with the central processing unit configured to display the predicted results related to cold water, warm water fish, plants and bacteria to improve the aquaponics farming business.

Description

FIELD OF THE INVENTION

The present disclosure relates to an IoT-based water quality prediction system for aquaponics farming applications, particularly to an IoT-based intelligent system that monitors water quality based on collected data and provides breeding prediction for cold-water, warm-water fish, plants, and bacteria to improve the Aquaponics farming business.

BACKGROUND OF THE INVENTION

In the ever-evolving landscape of agriculture, the integration of aquaponics has emerged as a promising approach that combines the cultivation of fish and plants in a symbiotic environment. However, the full potential of aquaponics farming remains untapped, largely due to the lack of expertise and awareness among farmers.

One of the key challenges of this innovative agricultural practice is the lack of a comprehensive system for monitoring and predicting water quality parameters. The importance of water quality in aquaponics cannot be overemphasized as it has a direct impact on the growth, health and overall productivity of the interconnected ecosystem of fish, plants and beneficial bacteria.

Traditional farming methods often fail to meet the complex requirements of aquaponics, resulting in suboptimal yields and increased susceptibility to disease. Given this knowledge and technology gap, the invention of an intelligent system to predict or monitor water quality is essential.

From the above discussion, it is clear that there is a need for an IoT based water quality prediction system for aquaponic farming applications.

SUMMARY OF THE INVENTION

The present disclosure relates to an IoT based water quality prediction system for aquaponics farming applications. To support aquaponics farming, the proposed system provides breeding predictions for warm and cold water fish, plants and microorganisms. The proposed system first uses Internet of Things sensors to collect data. Outliers and missing values are then eliminated as part of the data cleaning. Undesirable features are then eliminated and features associated with the recognized data are determined. Next, to solve the imbalanced class problem, we propose a brand new M-SMOTE approach. Finally, the proposed approach uses multi-model classification for the aquaponic ecosystem. The proposed approach evaluates the effectiveness of six classifiers using the mechanism of optimal prediction based on voting. Based on the voting concept, the proposed technique selects XGBoost and Random Forest as the best classifiers. The proposed system is evaluated for its performance, with the results indicating that the proposed system has an accuracy of 99.13%.

The disclosure relates to providing an IoT-based water quality prediction system for aquaponic farming applications. The system includes: a series of multiple IoT sensors configured to collect real-time data from the aquaponic environment; a storage unit for storing the collected real-time data using a sensor array, the storage unit using a storage device for this purpose; a centralized processing unit comprising a processor configured to monitor and predict water quality for aquaponic farming by using the data stored in the storage unit to train the processor to predict; and a user interface in conjunction with the central processing unit configured to display the predicted results related to cold water, warm water fish, plants and bacteria to improve the aquaponics farming business.

In one embodiment, the multiple IoT sensors are placed in multiple locations.

In one embodiment, the system further comprises a communication module that facilitates the communication of data from sensors to the storage unit and further to the central processing unit.

In one embodiment, the centralized processing unit, including a processor for making predictions based on the real-time collected data, is configured to: clean the collected data by replacing missing values and removing outliers; Extract the features that correlate with the collected data and develop a data set of extracted features. Address the problem of imbalanced data within the dataset by implementing an M-SMOTE algorithm on the dataset. and predicting the final outcome using multimodal classification for the aquaponic ecosystem, using a voting mechanism to evaluate the performance of classifiers.

In one embodiment, feature extraction is performed using a heatmap correlation matrix and features that contribute most to the predicted variables are selected.

In one embodiment, the data set is stored in the storage unit, which includes a storage device.

In one embodiment, implementing the M-SMOTE algorithm on the data set creates a new data set that replaces the old data set stored in the storage device, has no outlier values, and provides a noise-free data set for generating the synthetic samples for minority classes.

In one embodiment, six different classifiers are used, which are trained and whose performance is evaluated, and the best performing classifier is selected as a prediction model that predicts the outcome based on the input processed data.

An objective of the present disclosure is to provide an IoT-based water quality prediction system for aquaponic farming applications.

Another objective of the present disclosure is to provide a system that provides agricultural prediction for cold water and warm water fish, plants and bacteria to improve the aquaponics farming business.

Another objective of the present disclosure is to predict cold water fish, warm water fish, plants and beneficial bacteria suitable for fresh water.

Another objective of the present disclosure is to provide strategies and remedies for efficient fish farming taking into account other aquatic organisms such as bacteria and plants to create a balanced ecosystem.

In order to further illustrate the advantages and features of the present disclosure, a more detailed description of the invention will be made with reference to specific embodiments thereof shown in the accompanying drawings. It is understood that these drawings represent only typical embodiments of the invention and are therefore not to be viewed as limiting its scope. The invention is described and explained in more detail and in greater detail with reference to the accompanying drawings.

BRIEF DESCRIPTION OF THE FIGURES

• 1 veranschaulicht ein Blockdiagramm eines IoT- basierten Wasserqualitätsvorhersagesystems für Aquaponik-Landwirtschaftsanwendungen gemäß einer Ausführungsform der vorliegenden Offenbarung; Und
• 2 zeigt ein Diagramm, das den Rahmen des vorgeschlagenen Systems zur Vorhersage der Wasserqualität für die Aquaponik-Landwirtschaft gemäß einer Ausführungsform der vorliegenden Offenbarung zeigt.

These and other features, aspects and advantages of the present disclosure will be better understood when the following detailed description is read with reference to the accompanying drawings, in which like reference numerals represent like parts throughout the drawings, in which:

• 1 illustrates a block diagram of an IoT-based water quality prediction system for aquaponics farming applications according to an embodiment of the present disclosure; And
• 2 Fig. 12 is a diagram showing the framework of the proposed water quality prediction system for aquaponic farming according to an embodiment of the present disclosure.

Additionally, experienced craftsmen will recognize that elements in the drawings are presented for convenience and may not necessarily have been drawn to scale. For example, the flowcharts illustrate the method through key steps that help improve understanding of aspects of the present disclosure. Additionally, in view of the construction of the device, one or more components of the device may have been represented in the drawings by conventional symbols, and the drawings may show only the specific details relevant to understanding the embodiments of the present disclosure around the drawings not to be obscured by details that would be readily apparent to one of ordinary skill in the art using the description herein.

DETAILED DESCRIPTION:

In order to promote understanding of the principles of the invention, reference will now be made to the embodiment shown in the drawings and specific language will be used to describe the same. It is to be understood, however, that this is not intended to limit the scope of the invention, since changes and further modifications to the system illustrated and further applications of the principles of the invention set forth therein are contemplated as would normally occur to one skilled in the art Technology to which the invention relates.

It will be understood by those skilled in the art that the foregoing general description and the following detailed description are exemplary and illustrative of the invention and are not intended to limit the same.

References in this specification to “an aspect,” “another aspect,” or similar language mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure is included. Therefore, the phrases “in one embodiment,” “in another embodiment,” and similar phrases in this specification may, but not necessarily, refer to the same embodiment.

The terms “includes,” “comprising,” or other variations thereof are intended to cover non-exclusive inclusion, such that a process or method that includes a list of steps not only includes those steps, but may include other steps not specifically listed or following this inherent in the process or method. Likewise, one or more devices or subsystems or elements or structures or components prefixed with "comprises...a" do not exclude, without further limitation, the existence of other devices or other subsystems or other elements or other structures from other components or additional devices or additional subsystems or additional elements or additional structures or additional components.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as generally understood by one of ordinary skill in the art to which this invention pertains. The system, methods and examples provided herein are for illustrative purposes only and are not intended to be limiting.

Embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

The functional units described in this specification are identified as devices. A device may be implemented in programmable hardware devices such as processors, digital signal processors, central processing units, field programmable gate arrays, programmable array logic, programmable logic devices, cloud processing systems, or the like. The devices can also be implemented in software for execution by different types of processors. An identified device may contain executable code and, for example, include one or more physical or logical blocks of computer instructions, which may be organized, for example, as an object, procedure, function, or other construct. However, the executable file of an identified device does not have to be physically located together, but may consist of different files stored in different locations Instructions exist which, when logically put together, form the device and fulfill the stated purpose of the device.

In fact, a device or module's executable code could be a single instruction or multiple instructions, and even distributed across several different code segments, between different applications and across multiple storage devices. Similarly, operational data may be identified and represented herein within the device and may be embodied in any suitable form and organized into any suitable type of data structure. The operational data may be collected as a single data set or distributed across various locations, including various storage devices, and may exist, at least in part, as electronic signals in a system or network.

References in this specification to “a selected embodiment,” “an embodiment,” or “an embodiment” mean that a particular feature, structure, or feature described in connection with the embodiment is disclosed in at least one embodiment of the Item is included. Therefore, the expressions “a selected embodiment,” “in one embodiment,” or “in one embodiment” used elsewhere in this specification do not necessarily refer to the same embodiment.

Additionally, the features, structures, or properties described may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to provide a thorough understanding of embodiments of the disclosed subject matter. However, one skilled in the art will recognize that the disclosed subject matter may be practiced without one or more of the specific details or with other methods, components, materials, etc. In other cases, well-known structures, materials, or processes may not be shown or described in detail so as not to obscure aspects of the subject matter disclosed.

According to exemplary embodiments, the disclosed computer programs or modules may be executed in many exemplary ways, for example, as an application residing in a device's memory or as a hosted application executing on and communicating with a server via a device application or browser Set of standard protocols such as TCP/IP, HTTP, XML, SOAP, REST, JSON and other sufficient protocols. The disclosed computer programs may be written in exemplary programming languages that are executed from the device's memory or from a hosted server, such as BASIC, COBOL, C, C++, Java, Pascal, or scripting languages such as JavaScript, Python, Ruby, PHP, Perl or other suitable programming languages.

Some of the disclosed embodiments involve or otherwise involve data transmission over a network, such as the transmission of various inputs or files over the network. The network may include, for example, one or more of the following: Internet, Wide Area Networks (WANs), Local Area Networks (LANs), analog or digital wired and wireless telephone networks, e.g. B. a PSTN, Integrated Services Digital Network (ISDN), a cellular network and Digital Subscriber Line (xDSL), radio, television, cable, satellite and / or other transmission or tunneling mechanisms for data transmission. The network may include multiple networks or subnetworks, each of which may include, for example, a wired or wireless data path. The network may include a circuit-switched voice network, a packet-switched data network, or any other network capable of transmitting electronic communications. The network may include, for example, networks based on Internet Protocol (IP) or Asynchronous Transfer Mode (ATM), and may support voice using, for example, VoIP, Voice over ATM, or other comparable protocols used for voice data communications. In one implementation, the network includes a cellular network configured to enable the exchange of text or SMS messages.

Examples of the network include a Personal Area Network (PAN), a Storage Area Network (SAN), a Home Area Network (HAN), a Campus Area Network (CAN) and a Local Area Network (LAN), a Wide Area Network (WAN), a Metropolitan Area Network (MAN), a Virtual Private Network (VPN), an Enterprise Private Network (EPN), Internet, a Global Area Network (GAN) and so on.

1 shows a block diagram of an IoT-based water quality prediction system (100) for aquaponics farming applications according to an embodiment of the present disclosure. The System (100) includes an array of multiple IoT sensors (102) configured to collect real-time data from the aquaponics environment.

In one embodiment, a storage unit (104) for storing the collected real-time data using a sensor array, the storage unit using a storage device (104a) for this purpose.

In one embodiment, a centralized processing unit (106) includes a processor (106a) configured to monitor and predict water quality for aquaponics farming by using the data stored in the storage unit (104) to train the processor (106a) to predict .

In one embodiment, a user interface (108) in conjunction with the central processing unit (106) is configured to display the predicted results related to cold water, warm water fish, plants and bacteria to improve the aquaponics farming business.

In one embodiment, the multiple IoT sensors (102) are placed at multiple locations.

In one embodiment, the system (100) also comprises a communication module (110) that enables data from sensors (102) to be communicated to the storage unit (104) and further to the central processing unit (106).

In one embodiment, the centralized processing unit (106), including a processor (106a) for making predictions based on the real-time collected data, is configured to: clean the collected data by replacing missing values and removing outliers; Extract the features that correlate with the collected data and develop a data set of extracted features. Address the problem of imbalanced data within the dataset by implementing an M-SMOTE algorithm on the dataset. and predicting the final outcome using multimodal classification for the aquaponic ecosystem, using a voting mechanism to evaluate the performance of classifiers.

In one embodiment, feature extraction is performed using a heatmap correlation matrix and features that contribute most to the predicted variables are selected.

In one embodiment, the data set is stored in the storage unit (104), which includes a storage device (104a).

In one embodiment, implementing the M-SMOTE algorithm on the data set creates a new data set that replaces the old data set stored in the storage unit (104), has no outlier values, and provides a noise-free data set for generating the synthetic samples for minority classes .

In one embodiment, six different classifiers are used, which are trained and whose performance is evaluated, and the best performing classifier is selected as a prediction model that predicts the results based on the input processed data.

In one embodiment, the centralized processing unit (106) may be implemented in programmable hardware devices such as processors, digital signal processors, central processing units, field programmable gate arrays, programmable array logic, programmable logic devices, cloud processing systems, or the like.

In one embodiment, the system (100) further includes a feature extraction unit to extract features using a heatmap correlation matrix, and features that contribute most to the predicted variables are selected from the data.

In one embodiment, the centralized processing unit (106) is configured to remove missing values and outliers and remove unwanted features when correlated with the acquired data.

In one embodiment, the centralized processing unit (106) is configured to implement the M-SMOTE technique algorithm on the data set collected from sensors and create a new data set that replaces the old data set stored in the storage unit.

2 Fig. 12 is a diagram showing the framework of the proposed water quality prediction system for aquaponic farming according to an embodiment of the present disclosure.

Aquaponics farming has not yet reached its full potential because farmers lack understanding and skills in this area. Farmers need to use modern technologies for breed selection, selection of disease-free seeds and species, and monitoring of water quality parameters to improve aquaponic farming.

The system predicts plants and beneficial bacteria suitable for freshwater, coldwater and warmwater fish. To create a balanced ecosystem, the proposed system also provides techniques and solutions for effective fish farming that take into account other aquatic organisms such as bacteria and plants.

Referring to The proposed system includes: Real-time data collection, data cleaning, feature extraction, handling biased data, preferred classifiers and optimal prediction based on voting form the six components of the proposed system.

First, sensor devices are used to collect captured data. Data cleaning is about eliminating outliers and missing numbers. Unwanted features are eliminated, features associated with the detected data are extracted, and a data set is created. Imbalanced datasets are taken into account by the M-SMOTE approach. Multi-model categorization is used by the proposed system to make predictions.

Each phase of the proposed system is described in detail below.

Real-time data collection: IOT sensor devices are used to initially collect the water quality parameters from multiple nodes at different locations. The information collected is presented numerically as follows. $$D_s=\left\{D_1,{\mathrm{<figure-callout\; id="2"\; label="D"\; filenames="DE202023107102U1\_0006.png"\; state="\{\{state\}\}">D</figure-callout>}}_2,D_3,\dots \dots \dots \dots ,D_m\right\}$$

Where D _s denotes the data set and D _n implies the m number of sensor data D.

Data Cleansing: The proposed system replaces missing values and eliminates outliers from the data through a data cleaning procedure. The missing value is replaced by the average of the two numbers before and after. For example, to replace the missing 20th value, the average of the 18th, 19th, 21st and 22nd values is calculated. The median formula is used to adjust the data set containing the outliers. If there are multiple missing values, the average of the two values before or next to the position of the missing value is used.

Feature selection: Using a correlation matrix and a heatmap, this step selects the essential features and the features that have the greatest influence on the predictor variable.

Unbalanced Data Processing: The dataset is divided into nine classes by the proposed system. First, it is found that these classes are unevenly distributed throughout the dataset. The ratio of the nine classes (NS: P: C: B: BW: BP: BPW: BC: BCP) in percent is determined in the classification problem with 6: 4: 6: 7: 17: 13: 25: 10: 13 with 7338 instances (rows). Due to the uneven distribution of classes for multi-class classification, the dataset of the proposed system is unbalanced.

The proposed system proposes several approaches to address the data imbalance issues. This includes using multiple performance measures (accuracy is not recommended for the imbalance data set), such as: B. Recall, F1 score, ROC curves and precision. Using techniques to oversample and undersample the data set can help solve the problem of an unbalanced data set. Random rows (instances) from the minority class are added to the training data set through the oversampling method using replacement. Rows with more copies of an instance are removed from the class by the undersampling method. A difficult optimization problem is selecting instances from the minority class, sampling attribute, sampling types, sampling rate, and sampling distribution technique from the minority class.

SMOTE uses samples from multiple classes instead of examining neighboring samples to generate new examples of minority classes, resulting in more noise and class overlap. Since SMOTE is unable to process high-dimensional data, multiple samples are created for minority classes. Therefore, the dataset may contain a large number of duplicate samples after applying SMOTE, which affects the accuracy of the model. These represent a major disadvantage of SMOTE technology.

A unique modified synthetic minority oversampling technique called M-SMOTE is proposed as a solution to imbalanced class problems. Without causing class overlap, the proposed M-SMOTE handles oversampling for minority classes. Two input parameters such as Dataset and Dy (the name of the dependent variable) are passed to M-SMOTE. Outlier detection and remediation form the initial phase of the M-SMOTE approach. The RemoveOutlier function, which uses the Z-score approach to identify and remove outliers, is used by M-SMOTE.

M-SMOTE algorithm:

This is done repeatedly until the dataset contains the unique samples within the allowed range of the attribute.

In the above algorithm, Equation 2 calculates the Z-score using Equations 3 and 4. The mean and standard deviation are calculated by Equations 3 and 4, respectively. Equations 5 and 6 are used to obtain the upper and lower bounds. respectively. The outliers are determined by Equation 7. To create a data set without noise and outliers, use Equation 8 to eliminate the outliers. Equation 9 is used to split the data set into the independent (Dx) and dependent (Dy) variables. A data set containing both Dx and Dy is then returned to the M-SMOTE function. Equation 10, where CMJ is the name of the majority class, is used to determine the length of the majority class. Equation 11, attributed to CMN, is used in computing the minority class list. Equation 12 is used to find the total number of minority classes (M). Equation 13 is used to calculate the ratio of the minority classes to the dominant class. The class is considered unbalanced if the ratio is less than 0.8. Equation 1 is used to calculate the total number of synthetic G samples produced for minority classes. Equations 15 and 16 are used to create G samples which are then added to the data set. By creating a new data set with no outlier values, this technique provides a noise-free data set that can be used to create synthetic samples for minority classes.

Aquaponics Farming Prediction: Based on performance metrics such as accuracy, time (sec), precision and recall, the classification method is selected. To increase the prediction performance, the proposed system includes six classifiers, each of which is evaluated based on performance metrics. Using the validation dataset, the proposed methods train and evaluate each classifier to select better classifiers. The CatBoost, Gradient Boosting, XGBoost, Decision Tree, Random Forest, and KNN classifiers have all been included in the recommended classifier configuration. For a given set of water quality metrics, different models using different techniques will have different characteristics. Using the preferred classifier, the proposed system selects the best prediction model for new input data and then uses this prediction model to achieve the expected result.

The experimental results of the proposed IoT -based efficient prediction system are analyzed to determine whether water is suitable for warm-water fish, cold-water fish, plants and microorganisms. Python is used to implement the proposed approach. For performance evaluation, the proposed approach uses a water quality dataset from the Water Quality Information Sheet (WBPCBWQIS) of the West Bengal Pollution Control Board. The dataset consists of 7338 records collected for freshwater from various rivers and lakes in 27 Indian states. The proposed approach exploits the properties of the dataset including temperature, ammonia, dissolved oxygen, nitrite and nitrate. 15% is used for validation, 15% is used for testing, and 70% of the dataset is used for training.

The categorization algorithms are selected according to the various performance metrics. The model is trained using different classifiers and the performance of each classifier is evaluated using different performance metrics including accuracy, precision, recall, F1 measure, Kappa, ROC curve, MCC and execution time depending on the validation dataset. Voting is used by the proposed system to determine which forecast is the best. Be here Execution time, kappa, precision and F1 measure used as performance metrics for tuning in this proposed system.

The performance of the proposed system is evaluated without using the M-SMOTE approach. The effectiveness of several classifiers, including CatBoost, Gradient Boosting, XGBoost, Decision Tree, Random Forest and KNN, is evaluated using performance metrics such as accuracy, AUC curve, recall, precision, F1 score, Kappa and MCC. Except for KNN, all classifiers have a prediction performance of over 93% using the proposed method.

The M-SMOTE approach is used to evaluate the performance of the proposed system. Classifiers such as CatBoost, Gradient Boosting, Except for ANN, all classifiers in the proposed system have a prediction performance of more than 97%. The Random Forest and XGBoost classifiers were found to have accuracy percentages of 99.13% and 98.97%, respectively.

Without M-SMOTE, CatBoost takes 15.9 seconds, while with M-SMOTE it takes 11,899 seconds. Gradient Boosting takes 1.34 seconds when M-SMOTE is used and 2.87 seconds when not used. Likewise, XGBoost takes 1.505 and 0.701 seconds, in that order. In both scenarios, Decision Tree, Random Forest and KNN take less than a second. In terms of execution time, Random Forest and Decision Tree deliver the best results in terms of accuracy. The random forest classifier and decision tree take less than 0.5 seconds. After evaluating the performance of each classifier, the proposed system uses the best prediction determined by voting. Voting-based prediction evaluates the effectiveness of the different classifiers using benchmark criteria such as prediction score, accuracy, time, recall and kappa score. The proposed system selects XGBoost and Random Forest as the best classifiers based on the voting principle.

The drawings and the description above provide examples of embodiments. Those skilled in the art will recognize that one or more of the elements described can certainly be combined into a single functional element. Alternatively, certain elements can be divided into several functional elements. Elements of one embodiment may be added to another embodiment. For example, the orders of the processes described herein may be changed and are not limited to the manner described herein. Additionally, the actions of a flowchart do not have to be implemented in the order shown; Not all actions necessarily have to be carried out. Even those actions that are not dependent on other actions can be carried out in parallel with the other actions. The scope of the embodiments is in no way limited by these specific examples. Numerous variations, whether explicitly stated in the specification or not, such as: B. Differences in structure, dimensions and material use are possible. The scope of the embodiments is at least as broad as indicated by the following claims.

Advantages, other benefits, and solutions to problems have been described above with respect to specific embodiments. However, the advantages, benefits, solutions to problems and any components that may cause a benefit, advantage or solution to occur or become more pronounced should not be construed as a critical, necessary or essential function or component of any or all of the claims.

CREDENTIALS

100

An IoT-Based Water Quality Prediction System for Aquaponics Agriculture.

102

Array Of Multiple IoT Sensors

104

Storage unit

104a

storage device

106

Central processing unit

106a

Configured processor

108

user interface

110

Communication module

202

Measured Water Quality Data

202a

Data cleaning

202b

Feature selection

202c

M-SMOTE

204

Preferred classifier

204a

Catboost classifier

204b

Slope gain classifier

204c

Xgboost classifier

204d

Decision tree classifier

204e

Random forest classifier

204f

Data cleaning

206

Optimal Prediction Based On Select

Claims (6)

An IoT based water quality prediction system for aquaponic farming applications, the system comprising: a series of multiple IoT sensors configured to collect real-time data from the aquaponic environment; a storage unit for storing the collected real-time data using a sensor array, the storage unit using a storage device for this purpose; a centralized processing unit comprising a processor configured to monitor and predict water quality for aquaponic farming by using the data stored in the storage unit to train the processor to predict; and a user interface in conjunction with the central processing unit configured to display the predicted results related to cold water, warm water fish, plants and bacteria to improve the aquaponics farming business. System after Claim 1 , where the multiple IoT sensors are placed in multiple locations. System after Claim 1 , which also includes a communication module that enables communication of data from sensors to the storage unit and further to the central processing unit. System after Claim 1 , further comprising a feature extraction unit for extracting features using a heatmap correlation matrix, and features that contribute most to the predicted variables are selected from the data. System after Claim 1 , wherein the centralized processing unit is configured to remove missing values and outliers and remove unwanted features when correlating with the acquired data. System after Claim 1 , wherein the centralized processing unit is configured to implement the M-SMOTE technique algorithm on the data set acquired by sensors and create a new data set that replaces the old data set stored in the storage unit.

Images