Vector Quantization Neural Network Research Articles

Fault Diagnosis for PEMFC Water Management Subsystem Based on Learning Vector Quantization Neural Network and Kernel Principal Component Analysis

To solve the problem of water management subsystem fault diagnosis in a proton exchange membrane fuel cell (PEMFC) system, a novel approach based on learning vector quantization neural network (LVQNN) and kernel principal component analysis (KPCA) is proposed. In the proposed approach, the KPCA method is used for processing strongly coupled fault data with a high dimension to reduce the data dimension and to extract new low-dimensional fault feature data. The LVQNN method is used to carry out fault recognition using the fault feature data. The effectiveness of the proposed fault detection method is validated using the experimental data of the PEMFC power system. Results show that the proposed method can quickly and accurately diagnose the three health states: normal state, water flooding failure and membrane dry failure, and the recognition accuracy can reach 96.93%. Therefore, the method proposed in this paper is suitable for processing the fault data with a high dimension and abundant quantities, and provides a reference for the application of water management subsystem fault diagnosis of PEMFC.

Overview of Algorithms for Using Particle Morphology in Pre-Detonation Nuclear Forensics

A major goal in pre-detonation nuclear forensics is to infer the processing conditions and/or facility type that produced radiological material. This review paper focuses on analyses of particle size, shape, texture (“morphology”) signatures that could provide information on the provenance of interdicted materials. For example, uranium ore concentrates (UOC or yellowcake) include ammonium diuranate (ADU), ammonium uranyl carbonate (AUC), sodium diuranate (SDU), magnesium diuranate (MDU), and others, each prepared using different salts to precipitate U from solution. Once precipitated, UOCs are often dried and calcined to remove adsorbed water. The products can be allowed to react further, forming uranium oxides UO3, U3O8, or UO2 powders, whose surface morphology can be indicative of precipitation and/or calcination conditions used in their production. This review paper describes statistical issues and approaches in using quantitative analyses of measurements such as particle size and shape to infer production conditions. Statistical topics include multivariate t tests (Hotelling’s T2), design of experiments, and several machine learning (ML) options including decision trees, learning vector quantization neural networks, mixture discriminant analysis, and approximate Bayesian computation (ABC). ABC is emphasized as an attractive option to include the effects of model uncertainty in the selected and fitted forward model used for inferring processing conditions.

An online driver behavior adaptive shift strategy for two-speed AMT electric vehicle based on dynamic corrected factor

The performance of the shift strategy can reduce the energy consumption of two automatic manual transmissions (AMT) electric vehicles while meeting the needs of various drivers. Hence, the adjustment of the shift strategy is complicated due to the uncertain driver behavior. To address the above issue, an online driver behavior adaptive shift strategy based on dynamic corrected factors is proposed. Firstly, the simplified models of the power system and conventional shift strategies are constructed for electric vehicles. Secondly, principal component analysis and k-means algorithms are implemented to classify driver styles. Next, Learning Vector Quantization neural network and Fuzzy neural network are applied to identifying driving style and driving intention in real-time. Then, according to the driver behavior, a dynamic corrected factor is introduced. The dynamic corrected factors of different driver styles are modified to adjust the proportion of power and economy in the shifting process. As a result, the proposed shift strategy based on dynamic corrected factors achieves a compromise between power and economy for two-speed AMT electric vehicles. The numerical validation results demonstrate that the proposed shift strategy is energy-saving compared with the conventional shift strategy and can satisfy the requirements of various driver styles.

Improving branch prediction by combining perceptron with learning vector quantization neural network in embedded processor

Improving branch prediction by combining perceptron with learning vector quantization neural network in embedded processor

Sediment recognition by warp tension monitoring of bottom otter trawling and applying the self-organizing map algorithm

Model towing experiments of a bottom trawl net with hyper-lift trawl door were conducted to investigate the effect of the bottom sediment (concrete, sand, gravel, and rock) on the warp tension of the overall trawl system. The towing speed was from 50 cm/s to 70 cm/s and the ratio of warp length relative to the water depth was within the range of 4–6. Through the signal analysis of time-series warp tension, results reveal that there is a significant dependence of the warp tension on the type of bottom sediment, and the oscillation of warp tension in a frequency range of 1–10 Hz increases in the order of concrete, sand, gravel, and rock. Based on these characterizations, the time-series warp tension is thus represented by the feature vector for the input data of the self-organizing map (SOM) and learning vector quantization (LVQ) neural networks. A clustering method with an unsupervised SOM neural network acting as an updating tool for the bottom sediment database was successfully built using the validation of the prepared sediments. In combination with the output vector of labeled bottom sediment, the supervised LVQ neural network for sediment recognition performed excellently with a high classification accuracy of over 80%.

Energy active adjustment and bidirectional transfer management strategy of the electro-hydrostatic hydraulic hybrid powertrain for battery bus

The electro-hydrostatic hydraulic hybrid (EH3) powertrain has unique advantages in efficient recovery and utilization of energy. However, it also faces severe challenges in the decision-making of active adjustment and bidirectional transfer between multiple energy sources under the influence of driving pattern. Taking battery buses as the object, the power and energy-saving characteristics of EH3 powertrain under the control of driving pattern recognition (DPR) and fuzzy logic rules (FLR) are studied in this paper. The control ideas of active adjustment and bidirectional transfer of electric power and hydraulic power guided by the results of DPR are proposed. Firstly, the driving patterns and velocity in the actual driving scene is tested, and the data is divided into multiple short driving cycles through a rolling time window. Secondly, the K-means clustering algorithm is used to classify the obtained short driving cycles. The classification results are used as samples to train and test the Learning Vector Quantization neural network (LVQ-NN) to realize online recognition and prediction of driving patterns. Finally, the FLR controller is introduced to process multiple input variables, and the results of DPR and FLR are integrated to realize the active adjustment and bidirectional transfer of electric motor (EM) and variable pump/motor. The simulation results show that compared with the traditional control strategies, energy management strategy (EMS) based on DPR and FLR can effectively realize the intelligent adjustment and transfer of energy between composite power sources, and significantly improve the driving range and service life of the battery.

Identification Method of Coal and Coal Gangue Based on Dielectric Characteristics

To solve the problems of the difficult feature extraction, poor feature credibility and low recognition accuracy of coal and gangue, this paper utilizes the difference in the dielectric properties of coal and gangue and in combination with a support vector machine (SVM) to propose a recognition method based on the dielectric characteristics of coal and gangue. The influence rule of the edge effect of the electrode plate on the capacitance value is analyzed when the thickness of the electrode plate changes. By changing the frequency and voltage of the excitation source, curves of the dielectric constant of coal and gangue versus frequency and voltage are obtained. Combined with the Kalman filter, the adaptive noise complete set empirical mode decomposition (CEEMDAN) denoising method is improved, which results in a signal with a higher signal-to-noise ratio and lower root mean square error after denoising. The effective value and frequency of the denoised response signal are extracted to construct the feature vector set to form the training set and test set. The data of the training set are input into the SVM to train the intelligent classification model, the test set is used to test the SVM classification effect, and the classification accuracy is 100%. Unlike these of the probabilistic neural network (PNN) intelligent classification model and the learning vector quantization (LVQ) neural network classification model, the recognition and classification accuracies of the three can reach 100%, but the classification speed of SVM is the fastest, only taking 0.007916 s, which fully reflects the feasibility and efficiency of the capacitance method in identifying coal gangue. In this paper, the capacitance method and SVM are applied to identify coal and gangue, and accurate and efficient identification results are obtained, providing a new feasible solution for research on coal gangue identification.

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

With the continuous development and wide application of artificial intelligence technology, artificial neural network technology has begun to be used in the field of fraud identification. Among them, learning vector quantization (LVQ) neural network is the most widely used in the field of fraud identification, and the fraud identification rate is relatively high. In this context, this paper explores this neural network technology in depth, uses the same fraud sample to test the fraud recognition rate of these two models, and proposes an optimized LVQ-based combined neural network fraud risk recognition model on this basis. This paper selects 550 listed companies that have committed fraud from 2015 to 2019 as the fraud samples, determines 550 nonfraud matching sample companies in accordance with the Beasley principle one-to-one, and uses this as the research sample. The fraud risk identification indicators with better identification effects combed out according to the literature were used as the initial indicator system. After the collinearity problem was eliminated through the paired sample T test and principal component analysis, the five indicators with the best identification effects were finally selected. Finally, based on the above theoretical analysis and empirical research summarizing the full text, it analyzes the shortcomings of this research and puts forward prospects for the future development of fraud risk identification models.

Velocity prediction using Markov Chain combined with driving pattern recognition and applied to Dual-Motor Electric Vehicle energy consumption evaluation

Vehicle velocity prediction is of great significance in electric vehicle (EV) energy consumption evaluation. However, vehicle velocity prediction is complicated due to the uncertainty of vehicle velocity and driving pattern. To address the challenges, a vehicle velocity prediction model based on driving pattern recognition (DPR) and Markov Chain (MC) is proposed. Firstly, three typical driving cycles are adopted to constructed sample driving cycle. K-means algorithm is used for clustering the constructed driving cycle segments. And Learning Vector Quantization (LVQ) neural network (NN) is applied to recognizing the driving pattern in real-time, then the Markov Transition Matrix (MTM) corresponding to three clustered driving patterns are adopted to predict vehicle velocity. Finally, the velocity prediction results are applied to dual-motor EV energy consumption evaluation model which is established by Multiple Linear Regression (MLR). Velocity prediction results show that the Root Mean Square Error (RMSE) value of velocity prediction based on DPR and MC decreased by 24.1% compared with MC prediction without DPR. The velocity prediction is applied to energy consumption evaluation, the results shows that the error is 2.33%, which is sufficient to demonstrate the accuracy of the velocity prediction model and the energy consumption evaluation model.

Fault diagnosis of flexible production line machining center based on PCA and ABC-LVQ

A fault diagnosis method of flexible production line machining center based on principal component analysis (PCA) and artificial bee colony based learning vector quantization (ABC-LVQ) neural network is proposed to target the issue of key vulnerable parts of the flexible production line machining center. Along with that, a general scheme of fault diagnosis is designed according to the characteristics of flexible production line which includes multiple machining centers. Firstly, the acceleration sensor is used to collect the vibration signals of the key and critical components of the flexible production line machining center, to analyze and pick up the multi-information characteristics, the time domain, the frequency domain and the time-frequency domain of the signals. Then, in order to reduce the dimension of the eigenvector, PCA is adopted to realize such reduction. Finally, aiming at the problem that LVQ neural network is sensitive to the initial value weights, an ABC algorithm is proposed to quickly obtain excellent initial weights vector of LVQ neural network, which can accurately classify all kinds of faults. The experimental results show that the scheme can diagnose and monitor several key components of horizontal machining center of flexible production line in a quick and accurate manner.

Metaheuristic-based vector quantization approach: a new paradigm for neural network-based video compression

Video compression has great significance in the communication of motion pictures. Video compression techniques try to remove the different types of redundancy within or between video sequences. In the temporal domain, the video compression techniques remove the redundancies between the highly correlated consequence frames of the video. In the spatial domain, the video compression techniques remove the redundancies between the highly correlated consequence pixels (samples) in the same frame. Evolving neural-networks based video coding research efforts are focused on improving existing video codecs by performing better predictions that are incorporated within the same codec framework or holistic methods of end-to-end video compression schemes. Current neural network-based video compression adapts static codebook to achieve compression that leads to learning inability from new samples. This paper proposes a modified video compression model that adapts the genetic algorithm to build an optimal codebook for adaptive vector quantization that is used as an activation function inside the neural network’s hidden layer. Background subtraction algorithm is employed to extract motion objects within frames to generate the context-based initial codebook. Furthermore, Differential Pulse Code Modulation (DPCM) is utilized for lossless compression of significant wavelet coefficients; whereas low energy coefficients are lossy compressed using Learning Vector Quantization (LVQ) neural networks. Finally, Run Length Encoding (RLE) is engaged to encode the quantized coefficients to achieve a higher compression ratio. Experiments have proven the system’s ability to achieve higher compression ratio with acceptable efficiency measured by PSNR.

Identification of epilepsy from intracranial EEG signals by using different neural network models

In this work, a framework is provided for identifying intracranial electroencephalography (iEEG) seizures based on discrete wavelet transform (DWT) analysis of iEEG signals using forward propagation and feedback neural networks. The performance of 5 different data sets combination classifications is studied using the probabilistic neural network (PNN), learning vector quantization neural network (LVQ) and Elman neural network (ENN). Different feature combinations serve as the input vectors of the classifiers to obtain the best outcomes. It has been found that PNN has less running time and provides better classification accuracy (CA) than ENN and LVQ classifiers for all 5 classification problems. It is worth noticing that the CA for the C-D classification task, which shows the status of pre-ictal versus post-ictal, has been greatly improved, and reached 83.13%. Hence, the epilepsy iEEG signals pattern recognition based on DWT statistical features using the PNN classifier is more suitable for forming a reliable, automatic classification system in order to assist doctors in diagnosis.

Application of Unconventional Seismic Attributes and Unsupervised Machine Learning for the Identification of Fault and Fracture Network

The identification of small scale faults (SSFs) and fractures provides an improved understanding of geologic structural features and can be exploited for future drilling prospects. Conventional SSF and fracture characterization are challenging and time-consuming. Thus, the current study was conducted with the following aims: (a) to provide an effective way of utilizing the seismic data in the absence of image logs and cores for characterizing SSFs and fractures; (b) to present an unconventional way of data conditioning using geostatistical and structural filtering; (c) to provide an advanced workflow through multi-attributes, neural networks, and ant-colony optimization (ACO) for the recognition of fracture networks; and (d) to identify the fault and fracture orientation parameters within the study area. Initially, a steering cube was generated, and a dip-steered median filter (DSMF), a dip-steered diffusion filter (DSDF), and a fault enhancement filter (FEF) were applied to sharpen the discontinuities. Multiple structural attributes were applied and shortlisted, including dip and curvature attributes, filtered and unfiltered similarity attributes, thinned fault likelihood (TFL), fracture density, and fracture proximity. These shortlisted attributes were computed through unsupervised vector quantization (UVQ) neural networks. The results of the UVQ revealed the orientations, locations, and extensions of fractures in the study area. The ACO proved helpful in identifying the fracture parameters such as fracture length, dip angle, azimuth, and surface area. The adopted workflow also revealed a small scale fault which had an NNW–SSE orientation with minor heave and throw. The implemented workflow of structural interpretation is helpful for the field development of the study area and can be applied worldwide in carbonate, sand, coal, and shale gas fields.

The study of multiple diagnosis models of human prostate cancer based on Taylor database by artificial neural networks.

Prostate cancer (PCa) is the most common malignancy seen in men and the second leading cause of cancer-related death in males. The incidence and mortality associated with PCa has been rapidly increasing in China recently. Multiple diagnostic models of human PCa were developed based on Taylor database by combining the artificial neural networks (ANNs) to enhance the ability of PCa diagnosis. Genetic algorithm (GA) is used to select feature genes as numerical encoded parameters that reflect cancer, metastatic, or normal samples. Back propagation (BP) neural network and learning vector quantization (LVQ) neural network were used to build different Cancer/Normal, Primary/Metastatic, and Gleason Grade diagnostic models. The performance of these modeling approaches was evaluated by predictive accuracy (ACC) and area under the receiver operating characteristic curve (AUC). By observing the statistically significant parameters of the three training sets, our Cancer/Normal, Primary/Metastatic, and Gleason Grade models' with ACC and AUC can be drawn (97.33%, 0.9832), (99.17%, 0.9952), and (90.48%, 0.8742), respectively. These results indicated that our diagnostic models of human PCa based on Taylor database combining the feature gene expression profiling data and artificial intelligence algorithms might act as a powerful tool for diagnosing PCa. Gleason Grade diagnostic models were used as novel prognostic diagnosis models for biochemical recurrence-free survival and overall survival, which might be helpful in the prognostic diagnosis of PCa in patients.

Detection and classification of matrix cracking in laminated composites using guided wave propagation and artificial neural networks

The guided wave propagation and artificial intelligence (AI) approaches were used to propose an intelligent model for automatic detection and classification of the matrix cracking in composites. Glass/epoxy cross-ply laminated composites were fabricated and the matrix cracking with several densities was induced in 90° layers. A non-destructive testing procedure using the fundamental antisymmetric Lamb wave propagation was performed on the intact specimens and those with 0.05, 0.15, and 0.25 matrix cracking density. The velocity of propagated Lamb wave, wave amplitudes in four different distances from the actuator, and the ratio of these amplitudes to the first received wave amplitude, in three frequencies of 100, 200, and 330 kHz were extracted from the acquired signals. The extracted sensory features were used to train three types of supervised machine learning models for the crack density classification. The linear discriminant analysis (LDA) was performed for dimensional reduction to find a linear combination of features that can better discriminate the classes. Support vector machines (SVM), linear vector quantization (LVQ) neural network (NN), and multilayer perceptron (MLP) NN were used for the classification. It was shown that SVM accounted for the highest classification accuracy (91.7%) followed by LVQ NN (88.9%) and MLP NN (77.8%), respectively.

Forecasting rupiah exchange rate with learning vector quantization neural network

<p>The classification technique and data forecasting will probably be one of the techniques that will often be needed in handling or managing big data. So, from that the author analyzes the possible development of the existing algorithms. The purpose is to find possibilities in the use of reliable algorithms in a particular field, then can be adopted and implemented to develop forecasting techniques in the future. Based on these considerations, the authors conducted experiments by applying LVQNN to conduct shortterm forecasting on daily period of the Rupiah exchange rate. The literature that is used as a reference is the discovery of architectural data classification processes that resemble forecasting techniques. So, when there is a combination of Rupiah exchange histories, it is possible to find these combinations into certain classes based on predetermined parameters and historical data combination data and forecast values in the past. In this research the factors chosen as indicators that affect the Rupiah exchange rate are the amount of exports, the amount of imports, the inflation rate and also the world oil price. In this research the highest accuracy value in the testing process for the population reached 99.0991%. The increase in the percentage value of forecasting accuracy is influenced by the composition of the data. In this study the formation of data composition is influenced by distinct data. The selection of parameters which become distinct claused determines how the composition of the data will be formed. If the composition of the data is not correct, the test results will not be good. If the number of weights vector is smaller than the input data, the forecasting accuracy will decrease. Because the weight vector cannot represent data combinations that used during training or testing.</p>

Learning vector quantization neural network for surface water extraction from Landsat OLI images

There is a growing concern over surface water dynamics due to an increased understanding of water availability and management with current climate trends. Remote sensing has now become an effective means of water extraction due to the availability of an enormous amount of data with diverse spatial, spectral, and temporal resolutions. However, water extraction from optical remote sensing data is associated with several major difficulties, such as the applicability of the extraction method over large areas and complex environments; shadow contamination from clouds, buildings, and mountains; and disclosure of shadowed water and exclusion of floating and submerged plants. To address these difficulties, a learning vector quantization (LVQ) neural network-based method was proposed and implemented to extract water using Landsat 8 imageries. This method is capable of separating water from clouds, build-up areas, shadows, and shadowed water by the ideal input of bands 1 to 7 and normalized difference vegetation index. This model learns water across Sri Lanka. Eight OLI scenes were tested, and the performance was compared with five widely used machine learning algorithms: support vector machine, K-nearest neighbor, discriminant analysis, combination of modified normalized difference water index and modified fuzzy clustering method, and K-means clustering methods. This method performed the best, achieving overall accuracies and the kappa coefficients between 97.8% and 99.7% and between 0.96 and 0.99, respectively. Results have demonstrated robustness, consistency, and preciseness in various dark surfaces, noisiest water environments, and highly water scarce scenes. LVQ revealed a good generalizing ability to detect all types of water with less amount of training samples. This method can be easily adaptable for other sensors and global water to support water resource studies.

Application of Quantum Genetic Optimization of LVQ Neural Network in Smart City Traffic Network Prediction

Accurate prediction of traffic flow in urban networks is of great significance for smart city management. A short-term traffic flow prediction algorithm of Quantum Genetic Algorithm - Learning Vector Quantization (QGA-LVQ) neural network is proposed to forecast the changes of traffic flow. Different from BP neural network, Learning Vector Quantization (LVQ) neural network is of simple structure, easy implementation and better clustering effect. Utilizing the global optimization ability of Quantum Genetic Algorithm (QGA), it is combined with LVQ neural network to overcome some shortcomings of LVQ neural network, including sensitive to initial weights and prone to local minima. In order to test the convergence ability and the timeliness of QGA-LVQ neural network in short-term traffic flow, some contrast experiments are performed. Experimental simulation results show that, QGA-LVQ neural network obtains excellent prediction results in prediction accuracy and convergence speed. Besides, compared with GA-BP neural network and wavelet neural network, QGA-LVQ neural network performs better in short-term traffic flow prediction.

Digital Image Processing for Detecting Industrial Machine Work Failure with Quantization Vector Learning Method

Todays, digital image processing is widely used in various fields to facilitate humans in doing work by analyzing videos or images for use in decision making in the industrial world. The use of industrial machine technology is one of the most important factors in efforts to facilitate human work, but an industrial machine is inseparable from work failure that can hinder the production process and cause harm to the industry. This study aims to detect a failure in industrial machinery by using video data of industrial machine movements recorded using a webcam camera. For the preprocessing stage, the image is resized then converted to grayscale imagery and segmented using the thresholding method, then morphological operations are performed with an opening operation, feature extraction is done by changing the binary image into a vector data that is used as input data in the classification process using the Learning Vector Quantization Neural Network Algorithm (LVQ NN) version 1. The results showed the results of the detection of machine working errors can be done well with an accuracy value of 94.24% in training and 92.38% in the testing phase.

Simulation and Experimental Investigation on Active Thermography Test of the Solder Balls

The miniaturized electronic products require not only high density, but also high reliability. Defect inspection for the high-density package becomes challenging gradually. In this article, active thermography technology is used to detect the solder balls in flip-chip (FC) packages. A single-layer FC model is constructed and heat conduction in the FC package is simulated by using the finite-element analysis code of COMSOL. Experimental investigation is also carried out to inspect the solder defects by using the laser excitation thermography test system. Infrared images of the SFA1 package are captured, and the spatial adaptive filtering algorithm is used to remove the thermal noise. The hot spots of the solder balls are segmented from the filtered infrared image, and the representative features are extracted for each hot spot. The modified learning vector quantization (LVQ) neural network is used for the classification of the solder balls. The missing solder balls are identified accurately. The simulation and experimental results prove that the proposed approach using active thermography and LVQ algorithm is effective for defect inspection in high-density electronic devices.