Learning Vector Quantization Research Articles

A twin delayed deep deterministic policy gradient-based energy management strategy for a battery-ultracapacitor electric vehicle considering driving condition recognition with learning vector quantization neural network

Deep reinforcement learning algorithms have been widely applied in the energy management of hybrid energy storage systems. However, these deep reinforcement learning algorithms, such as DQN and DDPG, have the problem of discontinuous action space and consistently overestimated Q values. To address this issue, a novel energy management strategy based on a twin delayed deep deterministic policy gradient (TD3) algorithm is proposed for the battery-ultracapacitor electric vehicles in this study. In addition, the driving condition recognition method is integrated into the energy management strategy framework to reduce the training time of the TD3 agent. The detailed implementation steps are as follows. At first, dynamic experiments were performed to establish high-precision models of the battery and ultracapacitor. Secondly, learning vector quantization neural networks are applied to classify driving conditions, namely, urban, suburban and highway conditions. Furthermore, three parallel TD3 agents are trained for urban, suburban and highway conditions, respectively. Finally, the proposed strategy is evaluated under standard driving cycles. The simulation results indicate that compared with the TD3-based strategy, the proposed strategy improves the economy by 1 % and reduces the training time by 34 %, and the economic gap with the dynamic programming-based energy management strategy is narrowed down to 3 %.

A dynamic programming-optimized two-layer adaptive energy management strategy for electric vehicles considering driving pattern recognition

To achieve optimal real-time power allocation in electric vehicles, a two-layer adaptive dynamic programming (DP) optimization energy management strategy (EMS) has been proposed. The upper layer uses learning vector quantization (LVQ) to produce real-time driving pattern recognition (DPR) results. The method determines 10 characteristic parameters for training the recognition network and the length of the sampling window is 120 s. The typical driving cycles are divided into different levels of blocks to identify the real-time DPR level. The lower layer adopts the optimization strategy of DP extraction to adjust the power distribution between the battery pack and the supercapacitor pack according to the recognition results. DP is used to define a cost function to minimize the energy loss of the hybrid energy storage system (HESS) and optimize the battery usage range in the system. The near-optimal real-time EMS is extracted by analyzing the DP control behavior of the battery under the layered state of charge (SOC). The simulation results indicate that the proposed new rule control based on DP optimization (NRB) EMS improves the system efficiency by 10 % compared with the original rule-based (RB) EMS under different temperatures and DPR levels. In addition, the system efficiency gap is controlled at 3 % compared with DP.

#6868 MACHINE LEARNING-BASED HYPERTENSION DISEASE RISK CLASSIFICATION USING LEARNING VECTOR QUANTIZATION ALGORITHM

Abstract Background and Aims According to the World Health Organization, the disease dubbed as the silent killer of death is the number one cause of death in the world. Hypertension is a disease that does not show certain symptoms. There are about 95% of hypertension cases have no known cause, while the rest are caused by other diseases. Therefore, an early detection system for hypertension is needed. In this research, the Learning Vector Quantization (LVQ) algorithm is used to perform the classification process. Method In this research, the LVQ machine learning algorithm is used. LVQ is an algorithm that is a type of artificial neural network and uses neural computation. The data in this study is hypertension patient data from Sultan Daeng Radja Hospital which is divided into four classes. In the system design stage using the LVQ algorithm, the process in this system is by entering input data in the form of medical records consisting of 12 attributes based on their weights which will then be carried out by the LVQ process to produce classification results. If the classification results have been obtained, the system will stop. After the classification testing process is carried out, the accuracy calculation process is carried out. Results Based on six test scenarios that have been carried out, the system produces recommendations for a value of 0.1 for the learning rate, a value of 0.2 for the learning rate multiplier, the amount of training data of as much as 50%, the maximum epoch value of six, the minimum value of alpha 0.001. From these values, the average accuracy result obtained is 94%. Conclusion Based on the value of accuracy results obtained exceeding 90%, the system can be done quite successfully in detecting hypertension. However, further research is needed to further develop the system.

Leaf Disease Detection in Android

Abstract: In agriculture, early disease identification is crucial for a productive crop product. Ails similar as bacterial spot, late scar, Septoria splint spot, and unheroic twisted splint the quality of the tomato crop. Automatic bracket ways of factory conditions also help in taking action once they're discovered diseased splint symptoms Presented below is a Convolutional Learning Vector Quantization and Neural Network( CNN) model system for detecting tomato splint dis- ease grounded on the( LVQ) algorithm and categorization. There are 500 tomato prints in the dataset. leaves that display four complaint symptoms. We created a model of CNN for point birth and categorization automatically. Color Research on factory splint conditions laboriously uses information. In our model, three channels grounded on RGB are subordinated to pollutants

Leaf Disease Detection

Abstract: Early disease identification is crucial for productive crop production in agriculture. illnesses such as bacterial spot, late blight, Septoria leaf spot, and yellow curved leaf the quality of the tomato harvest. Automatic classification techniques of plant diseases also assist in taking action once they are discovered diseased leaf symptoms Presented below is a Convolutional Learning Vector Quantization and Neural Network (CNN) model Method for detecting tomato leaf disease based on the (LVQ) algorithm and categorization. There are 500 tomato photos in the dataset. leaves that display four disease symptoms. We created a model of CNN for feature extraction and categorization automatically. Color Research on plant leaf diseases actively uses information. In our model, three channels based on RGB are subjected to filters.

Artificial Neural Networks for Diagnosis of Kidney Stones Disease

The foundation of medical care for children with renal stone disease is the assessment of metabolic risk factors, which aims to stop the growth of preexisting calculi and subsequent stone occurrences. In this retrospective analysis, 90 children with kidney stone disease who had been sent to our institution and had undergone clinical testing in accordance with a defined procedure had their metabolic risk factors, clinical histories, and family histories assessed. Our pediatric patients were 10.7 years old on average, with a male to female ratio of 1.14:1.0. In 84.4% of the instances, biochemical abnormalities were discovered. Of the patients, 52.2% (n = 47) had only one urine metabolic risk factor, whereas the remaining 31.1% (n = 28) had several risk factors. Adrenal hypercalciuria. The aim of this work is to compare the performance of all three neural networks on the basis of its accuracy, time taken to build model, and training data set size. We will use Learning vector quantization (LVQ), two layers feed forward perceptron trained with back propagation training algorithm and Radial basis function (RBF) networks for diagnosis of kidney stone disease. In this work we used Waikato Environment for Knowledge Analysis (WEKA) version 3.7.5 as simulation tool which is an open source tool

A novel coal-rock cutting state identification model based on the Internet of Things

The sudden change in the interface between coal-rock mass can lead to the increased abrasion of picks and the failure rate of mining machinery. The safe and efficient coal-rock identification technology is the key to realize the intelligent control of coal mining machinery. To realize the real-time perception and accurate recognition of coal-rock cutting state information, a novel coal-rock cutting state identification model based on the Internet of Things (IoT) is explored. Specifically, by using the virtual prototype technology, multi-source heterogeneous data from acquisition, processing and identification of coal-rock cutting state information are fused and analyzed. First, the paper analyzes the physical and mechanical characteristics of coal-rock mass, and takes the cutting drum of bolter miner as the research object to theoretically analyze its load, which provides a foundation for the research on coal-rock cutting state identification. Second, a rigid-flexible coupling virtual prototype model of the cutting drum and coal-rock models under different cutting conditions are established. The simulation process is implemented by employing the discrete element method (DEM) to ensure the real-time transmission of motion information and state characteristic signals. Ultimately, the dynamic information of drum load during the coal-rock cutting process is obtained. Finally, LVQ (Learning Vector Quantization) and PSO-BP (Particle Swarm Optimization-Back Propagation) neural networks are created, and the variation coefficient, waveform factor, and peak factor of load curves of cutting drums in the coal-rock mass with different firmness coefficients are input into the neural networks as feature vectors for state recognition. The experimental results show that LVQ and PSO-BP neural networks can be used for coal-rock cutting state identification, and PSO-BP network has faster convergence speed and higher recognition efficiency, which provides a new scheme for coal-rock cutting state identification to improve the safety and efficiency of coal mining machinery.

A Physical Layer Key Generation Scheme Based on Deep Learning Compensation and Balanced Vector Quantization

Channel reciprocity is the foundation for physical layer key generation, which is influenced by noise, hardware impairments, and synchronization offsets. Weak channel reciprocity will result in a high key disagreement rate (KDR). The existing solutions for improving channel reciprocity cannot achieve satisfactory performance improvements. Furthermore, the existing quantization algorithms generally use one-dimensional channel features to quantize and generate secret keys, which cannot fully utilize channel information. The multidimensional vector quantization technique also needs to improve in terms of randomness and time complexity. This paper proposes a physical layer key generation scheme based on deep learning and balanced vector quantization. Specifically, we build a channel reciprocity compensation network (CRCNet) to learn the mapping relationship between Alice and Bob’s channel measurements. Alice compensates for channel measurements via a trained CRCNet to reduce channel measurement errors between legitimate users and enhance channel reciprocity. We also propose a balanced vector quantization algorithm based on integer linear programming (ILP-BVQ). ILP-BVQ reduces the time complexity of quantization on the basis of ensuring key randomness and a low KDR. Simulation results showed that the proposed CRCNet performs better in terms of channel reciprocity and KDR, while the proposed ILP-BVQ algorithm improves time consumption and key randomness.

Electroencephalography (EEG) eye state classification using learning vector quantization and bagged trees

The analysis of Electroencephalography (EEG) signals has been an effective way of eye state identification. Its significance is highlighted by studies that examined the classification of eye states using machine learning techniques. In previous studies, supervised learning techniques have been widely used in EEG signals analysis for eye state classification. Their main goal has been the improvement of classification accuracy through the use of novel algorithms. The trade-off between classification accuracy and computation complexity is an important task in EEG signals analysis. In this paper, a hybrid method that can handle multivariate signals and non-linear is proposed with supervised and un-supervised learning to achieve a fast EEG eye state classification with high prediction accuracy to provide real-time decision-making applicability. We use the Learning Vector Quantization (LVQ) technique and bagged tree techniques. The method was evaluated on a real-world EEG dataset which included 14976 instances after the removal of outlier instances. Using LVQ, 8 clusters were generated from the data. The bagged tree was applied on 8 clusters and compared with other classifiers. Our experiments revealed that LVQ combined with the bagged tree provides the best results (Accuracy = 0.9431) compared with the bagged tree, CART (Classification And Regression Tree) (Accuracy = 0.8200), LDA (Linear Discriminant Analysis) (Accuracy = 0.7931), Random Trees (Accuracy = 0.8311), Naïve Bayes (Accuracy = 0.8331) and Multilayer Perceptron (Accuracy = 0.7718), which demonstrates the effectiveness of incorporating ensemble learning and clustering approaches in the analysis of EEG signals. We also provided the time complexity of the methods for prediction speed (Observation/Second). The result showed that LVQ + Bagged Tree provides the best result for prediction speed (58942 Obs/Sec) in relation to Bagged Tree (28453 Obs/Sec), CART (27784 Obs/Sec), LDA (26435 Obs/Sec), Random Trees (27921), Naïve Bayes (27217) and Multilayer Perceptron (24163).

Learning Vector Quantization, Hebbian Learning, and Self-Organizing Map for Classification

Deep Learning has been rapidly developed. Almost all proposed methods already have very high accuracy. Most of these methods still use techniques from the past with some modifications to adapt to existing modules. Sometimes it is necessary to understand past methods to produce new methods. Therefore, this research examines past models that have the potential to improve the performance of existing deep learning models. The methods to be examined include Learning Vector Quantization (LVQ), Hebbian learning, and Self-Organizing Map (SOM). The iris dataset available on Scikit-learn (SKlearn) is used here for testing in cases of supervised learning and unsupervised learning (especially SOM). The results show that LVQ has a good accuracy of 93%, while Hebbian learning has an accuracy of 56%. SOM fluctuates between 88% and 93%. Although the accuracy of SOM does not exceed LVQ, this model does not require labels in its training process.

Detection of the Use of Masks as an Effort to Prevent Covid-19 Using Gray Level Co-Occurrence Matrix (GLCM) Based on Learning Vector Quantization (LVQ)

Covid-19 is a disease caused by the SARS-CoV-2 virus. Transmission of Covid-19 can be through the flow of air (aerosol), splashes of liquid (droplets). One of the prevention efforts to break the chain of transmission is to use a mask when interacting with other people. Monitoring and controlling the use of masks will be safer and more efficient when implementing a mask detection system. This study will analyze GLCM for extraction method and LVQ for classification method. The results of GLCM successfully provide statistical features that represent image characteristics well. While the LVQ can provide classification results with a good percentage of accuracy. The results of the best percentage accuracy for the first rank are 83.15% in the composition ratio of 90: 10. Furthermore, the percentage of accuracy for the second rank is 76.03% at the composition ratio of 70: 30 and the third rank is 72.47% at the composition ratio of 80: 20. This indicates that the composition more training data does not guarantee the level of achievement of a higher percentage of accuracy. There is an optimal maximum number of epochs where the number of epochs that exceeds the optimal number of epochs will not experience a change in the percentage of accuracy. For each value the learning rate (alpha) can give the results of the percentage of accuracy with different graphic patterns and will stop at the optimal maximum number of epochs.

Data sampling approach using heuristic Learning Vector Quantization (LVQ) classifier for software defect prediction

On the basis of quality estimate, early prediction and identification of software flaws is crucial in the software area. Prediction of Software Defects SDP is defined as the process of exposing software to flaws through the use of prediction models and defect datasets. This study recommended a method for dealing with the class imbalance problem based on Improved Random Synthetic Minority Oversampling Technique (SMOTE), followed by Linear Pearson Correlation Technique to perform feature selection to predict software failure. On the basis of the SMOTE data sampling approach, a strategy for software defect prediction is given in this paper. To address the class imbalance, the defect datasets were initially processed using the Improved Random-SMOTE Oversampling technique. Then, using the Linear Pearson Correlation approach, the features were chosen, and using the k-fold cross validation process, the samples were split into training and testing datasets. Finally, Heuristic Learning Vector Quantization is used to classify data in order to predict software problems. Based on measures like sensitivity, specificity, FPR, and accuracy rate for two separate datasets, the performance of the proposed strategy is contrasted with the approaches to classification that presently exist.

Digital Twin Evolution for Hard-to-Follow Aeronautical Ad-Hoc Networks in Beyond 5G

The aircrafts were top of the places that disrupted the seamless connectivity requirement of 5G and beyond. The Aeronautical Ad-hoc Networks (AANETs) take the attention of both industry and academia to satisfy this connectivity requirement with the low cost, easy deployment, and continuous coverage features. On the other hand, the ultra-dynamic characteristics of AANET with unstructured topology make its environment hard-to-follow. Here, Artificial Intelligence (AI)-based methodologies have an essential role in handling the management complexity of this hard-to-follow environment. However, these methodologies increase the computational complexity of aircraft due to the continuous update, convergence time, and scalability issues. At that point, we propose the utilization of the Digital Twin (DT) technology to handle the management complexity of AANET while solving the main issues of AI-based methodologies on it. The DT can virtually replicate the physical AANET components through closed-loop feedback in real-time. Therefore, this work introduces the utilization of DT technology for the AANET orchestration and, accordingly, proposes a DT-enabled AANET (DT-AANET) topology management framework. This framework consists of the Physical AANET Twin and Controller, including Digital AANET Twin with Operational Module. Here, the Digital AANET Twin virtually represents the physical environment while the operational module executes the AI-based computations on them through unsupervised learning-based training or supervised learning-based prediction. Finally, we present a case study based on Learning Vector Quantization (LVQ) to show the usability of the proposed framework and support this through evaluation results.

Sensor fusion and the application of artificial intelligence to identify tool wear in turning operations

This paper aims to develop an effective sensor fusion model for turning processes for the detection of tool wear. Fusion of sensors’ data combined with novelty detection algorithm and learning vector quantisation (LVQ) neural networks is used to detect tool wear and present diagnostic and prognostic information. To reduce the number of sensors required in the monitoring system and support sensor fusion, the ASPS approach (Automated Sensor and Signal Processing Selection System) is used to select the most appropriate sensors and signal processing methods for the design of the condition monitoring system. The experimental results show that the proposed approach has demonstrated its efficacy in the implementation of an effective solution for the monitoring tool wear in turning. The results prove that the fusion of sensitive sensory characteristic features and the use of AI methods have been successful for the detection and prediction of the tool wear in turning processes and show the capability of the proposed approach to reduce the complexity of the design of condition monitoring systems and the development of a sensor fusion system using a self-learning method.

Fusing clinical and image data for detecting the severity level of hospitalized symptomatic COVID-19 patients using hierarchical model

Based on medical reports, it is hard to find levels of different hospitalized symptomatic COVID-19 patients according to their features in a short time. Besides, there are common and special features for COVID-19 patients at different levels based on physicians’ knowledge that make diagnosis difficult. For this purpose, a hierarchical model is proposed in this paper based on experts’ knowledge, fuzzy C-mean (FCM) clustering, and adaptive neuro-fuzzy inference system (ANFIS) classifier. Experts considered a special set of features for different groups of COVID-19 patients to find their treatment plans. Accordingly, the structure of the proposed hierarchical model is designed based on experts’ knowledge. In the proposed model, we applied clustering methods to patients’ data to determine some clusters. Then, we learn classifiers for each cluster in a hierarchical model. Regarding different common and special features of patients, FCM is considered for the clustering method. Besides, ANFIS had better performances than other classification methods. Therefore, FCM and ANFIS were considered to design the proposed hierarchical model. FCM finds the membership degree of each patient’s data based on common and special features of different clusters to reinforce the ANFIS classifier. Next, ANFIS identifies the need of hospitalized symptomatic COVID-19 patients to ICU and to find whether or not they are in the end-stage (mortality target class). Two real datasets about COVID-19 patients are analyzed in this paper using the proposed model. One of these datasets had only clinical features and another dataset had both clinical and image features. Therefore, some appropriate features are extracted using some image processing and deep learning methods. According to the results and statistical test, the proposed model has the best performance among other utilized classifiers. Its accuracies based on clinical features of the first and second datasets are 92% and 90% to find the ICU target class. Extracted features of image data increase the accuracy by 94%. The accuracy of this model is even better for detecting the mortality target class among different classifiers in this paper and the literature review. Besides, this model is compatible with utilized datasets about COVID-19 patients based on clinical data and both clinical and image data, as well. • A new hierarchical model is proposed using ANFIS classifiers and FCM clustering method in this paper. Its structure is designed based on experts’ knowledge and real medical process. FCM reinforces the ANFIS classification learning phase based on the features of COVID-19 patients. • Two real datasets about COVID-19 patients are studied in this paper. One of these datasets has both clinical and image data. Therefore, appropriate features are extracted based on its image data and considered with available meaningful clinical data. Different levels of hospitalized symptomatic COVID-19 patients are considered in this paper including the need of patients to ICU and whether or not they are in end-stage. • Well-known classification methods including case-based reasoning (CBR), decision tree, convolutional neural networks (CNN), K-nearest neighbors (KNN), learning vector quantization (LVQ), multi-layer perceptron (MLP), Naive Bayes (NB), radial basis function network (RBF), support vector machine (SVM), recurrent neural networks (RNN), fuzzy type-I inference system (FIS), and adaptive neuro-fuzzy inference system (ANFIS) are designed for these datasets and their results are analyzed for different random groups of the train and test data; • According to unbalanced utilized datasets, different performances of classifiers including accuracy, sensitivity, specificity, precision, F-score, and G-mean are compared to find the best classifier. ANFIS classifiers have the best results for both datasets. • To reduce the computational time, the effects of the Principal Component Analysis (PCA) feature reduction method are studied on the performances of the proposed model and classifiers. According to the results and statistical test, the proposed hierarchical model has the best performances among other utilized classifiers.

Leakage detection in water distribution networks using machine-learning strategies

Abstract This work proposes a reliable leakage detection methodology for water distribution networks (WDNs) using machine-learning strategies. Our solution aims at detecting leakage in WDNs using efficient machine-learning strategies. We analyze pressure measurements from pumps in district metered areas (DMAs) in Stockholm, Sweden, where we consider a residential DMA of the water distribution network. Our proposed methodology uses learning strategies from unsupervised learning (K-means and cluster validation techniques), and supervised learning (learning vector quantization algorithms). The learning strategies we propose have low complexity, and the numerical experiments show the potential of using machine-learning strategies in leakage detection for monitored WDNs. Specifically, our experiments show that the proposed learning strategies are able to obtain correct classification rates up to 93.98%.

Transfer Deep Reinforcement Learning-Based Energy Management Strategy for Plug-In Hybrid Electric Heavy-Duty Trucks under Segmented Usage Scenarios

Energy management strategy (EMS) is a way to reduce the energy consumption of hybrid power systems. This article proposes a unique deep reinforcement learning- (DRL-) based EMS for plug-in hybrid electric heavy-duty trucks (PHETs), combining driving cycle pattern recognition (DPR) and deep transfer learning (DTL). The proposed EMS can cope well with the complex usage scenarios of PHETs and the difficulty of generating EMS. While ensuring the minimum overall driving cost, the strategy can improve the convergence speed of the DRL method and the generalizability under segmented usage scenarios. Firstly, representative driving cycles that reflect different usage scenarios are constructed based on a naturalistic data-driven method. Secondly, a plug-in hybrid electric heavy-duty truck (PHET) driving pattern recognizer based on a learning vector quantization neural network (LVQ) is built. Thirdly, the deep deterministic policy gradient (DDPG) algorithm is innovatively combined with the DTL algorithm. The pretrained neural network in the corresponding usage scenarios is transferred to the natural driving cycles based on DTL. Moreover, the proposed EMS gives an emphasized consciousness on the battery degradation cost. Finally, the strategy is tested under natural driving cycles in different usage scenarios and proven through comparison with the current state-of-the-art techniques, deep reinforcement learning-based strategy, and dynamic programming (DP). The results show that the proposed strategy outperforms existing cutting-edge deep reinforcement learning techniques in terms of convergence speed, battery life extension, fuel consumption, and overall driving cost reduction. The proposed control strategy can improve the convergence speed by nearly 50%, while effectively extending the battery life and reducing the overall driving cost compared to the existing state-of-the-art strategies. The battery degradation rate is reduced by 48.46%, 57.95%, and 36.99%, and the driving cost is reduced by 17.76%, 8.51%, and 7.12%, respectively, under each usage scenario.

A Novel Energy Management Strategy Integrating Deep Reinforcement Learning and Rule Based on Condition Identification

In order to reduce the driving cost of plug-in hybrid electric vehicles, a novel energy management strategy integrating deep reinforcement learning and rule based on condition identification is proposed. Firstly, principal component analysis is used to reduce the dimension of kinematic sequences features, and fuzzy clustering is used to classify the kinematics sequences, and then the working conditions are reorganized according to the classification results to obtain the three kinds of training conditions, and learning vector quantization neural network is used to train and identify the type of working conditions. Then, the rule taking engine torque, state of charge, and motor torque as control variables and driving mode as output is designed, which is integrated into the agent of deep reinforcement learning. Combined with the designed energy management strategy trained under three working conditions, the numerical simulation is carried out under the verification working condition based on condition identification, the simulation results are systematically analyzed to show the effectiveness of the designed energy management strategy.

LVQ Treatment for Zero-Shot Learning

In image classification, there are no labeled training instances for some classes, which are therefore called unseen classes or test classes. To classify these classes, zero-shot learning (ZSL) was developed, which typically attempts to learn a mapping from the (visual) feature space to the semantic space in which the classes are represented by a list of semantically meaningful attributes. However, the fact that this mapping is learned without using instances of the test classes affects the performance of ZSL, which is known as the domain shift problem. In this study, we propose to apply the learning vector quantization (LVQ) algorithm in the semantic space once the mapping is determined. First and foremost, this allows us to refine the prototypes of the test classes with respect to the learned mapping, which reduces the effects of the domain shift problem. Secondly, the LVQ algorithm increases the margin of the 1-NN classifier used in ZSL, resulting in better classification. Moreover, for this work, we consider a range of LVQ algorithms, from initial to advanced variants, and applied them to a number of state-of-the-art ZSL methods, then obtained their LVQ extensions. The experiments based on five ZSL benchmark datasets showed that the LVQ-empowered extensions of the ZSL methods are superior to their original counterparts in almost all settings.

Retracted: Using an Optimized Learning Vector Quantization- (LVQ-) Based Neural Network in Accounting Fraud Recognition.

[This retracts the article DOI: 10.1155/2021/4113237.].