LVQ Neural Network Research Articles

Research on Edge Detection of Agricultural Pest and Disease Leaf Image Based on LVQ Neural Network

Background: Roberts, Sobel, Prewitt and other operators are commonly used in image edge detection, but because of the complex background of agricultural pests and diseases, the efficiency of using these operators to detect is not ideal. Objective: To improve the accuracy of crop disease image edge detection, the method of using LVQ neural network to detect crop disease image edge was studied. Methods: It is proposed to use LVQ1 neural network to detect the edge of the image. The commonly used median feature quantity, directional information feature quantity and Krisch operator direction feature quantity are used as the input signal of LVQ1 neural network for network training. On the basis of simulation, an image feature vector that solves the image pixel neighborhood consistency is added, and an algorithm for edge detection using LVQ2 neural network is proposed. Computer simulations show that the improved algorithm significantly improved the edge image continuity of the output. Results: LVQ2 neural network can complete the edge detection of gray-scale image better, the output edge image has good continuity, clear contour and keeps most of the original image information. Compared with the LVQ1 neural network detection results, the edge image detected by LVQ2 neural network has obvious improvement in the processing of small edge, and the contour is clearer. It shows that the training method can converge the network better and obtain more ideal output results. Conclusion: The simulation comparison is carried out under the Matlab platform. The results show that based on the LVQ2 neural network, the four image feature quantities are used as the input signal detection algorithm, which significantly improved the output edge image continuity, compared with the traditional Sobel algorithm and LVQ1 nerve. The network is more superior, robust and generalized.

Research on Building Height Extraction Method from High-resolution Image

In recent years, there are many researches on calculating the height of buildings by extracting the shadow of buildings, but this method is difficult to be realized in the case of dense buildings or complex ground. To solve this problem, we can use the side information of the building to retrieve the height of the building. In this paper, Otsu Algorithm and LVQ neural network are used to extract the side information of buildings from high-resolution remote sensing images, calculate its length, and then calculate the height of the building according to the physical model of imaging. Compared with the measured building height, the calculation results of this method can meet the accuracy requirements of building height calculation, and this method can complement the results of shadow extraction method. Finally, the height information of most buildings in the area can be obtained.

Face detection algorithm based on LVQ neural network model

Face detection algorithm based on LVQ neural network 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.

ARABIC SPEECH RECOGNITION BASED ON KNN, J48, AND LVQ

Abstract Most systems of speaker recognition work on speech feature primarily classified of being a low level which considerably relies on speaker physical characteristics and, to the lower extent, the acquired speaking habits. In this paper present a system to recognition and identification in Arabic speaker. It includes two phases (training phase and testing phase) each phase includes the using of audio features (Mean, Standard Division, Zero Crossing, Amplitude). after get the feature, the recognition step is using (J48, KNN, LVQ),) where the Nearest Neighbor (KNN) applied o get the similarity of the data training and data testing , LVQ neural network used for Speech Recognition and Arabic language Identification. This sentence contains words especially kidnappings and kidnappers are ten sentences and pronounce these sentences by 10 people, five men and five women of different ages and each of the ten pronunciation of all sentences, so a total of 100 samples and the samples were recorded on audio and wave. The results of the sentences pronounced by women are higher than the results of the same sentences pronounced by men. They achieved better recognition rate 85, 93, 96.4%

Bimodal biometric pattern recognition system based on fusion of iris and palmprint using multi-resolution approach

A biometric pattern recognition system is a pattern recognition system which uses the biological traits to recognize individuals. Single biometric systems may not possess the required characteristics like permanence, acceptability and circumvention. In general, the performance of the unimodal biometrics systems is degraded due to noisy data acquisition from sensor, intra-class and inter-class similarities. Several such restrictions are removed when multiple sources of information are used. In this paper, a bimodal biometric system designed from iris pattern and palmprint pattern is described. The feature extractor is created from the wavelet packet analysis, and classifier is created based on neural network. Using wavelet packets and gray-level spatial dependence matrix, the iris code vector is constructed. With the help of Gabor wavelets and gray-level spatial dependence matrix, the palmprint code vector is computed. The features extracted from iris pattern and palmprint pattern are fused by feature-level fusion into a multimodal pattern vector of size 1408 bits. The recognition rate achieved by the LVQ neural network is 94.50%. This system can complete recognition in 15.25 microseconds so that it can be made use for implementing real-time recognition tasks.

Analisis Perbandingan Metode LVQ Dan Backpropagation dalam Penentuan Keaslian Uang Kertas Rupiah Berbasis Parameter HSV

The high demand of the community for money that causes crime is the circulation of fake paper money. Counterfeit money if shared has the same physical as the original money issued by Bank Indonesia. To avoid the public accidentally transacting using counterfeit money, the government has actually socialized the 3D method (Seen, Diraba, and Diterawang). However, along with technological developments, the technique of making counterfeit money will also require the development of alternative techniques that can be used to help save fake money. Determining the authenticity of Rupiah banknotes can be done using pattern classification methods, one of which can be accommodated by artificial neural networks. LVQ neural network (Learning Vector Quantization) and Backpropagation are two types of artificial neural networks that do supervised learning. Extraction of features that show the authenticity of banknotes can be done using the HSV color space. This color space consists of components H (Hue), S (Saturation), and V (Value). This is the background of the topic chosen for analysis choosing the LVQ and Backpropagation methods in determining the authenticity of Rupiah banknotes based on HSV parameters. Evaluation analysis taken from the level assessment The evaluation results using the composition of the test data consisting of 10 original money images and 8 original money images obtained results both LVQ and Backpropagation networks were able to classify real and fake money images with 100% acquisition rates. However, when viewed from the MSE value, the LVQ network has a better performance with the supporting MSE value being 0. The test results from the preparation time, the Backpropagation network requires a shorter time compared to the LVQ network.

A Comparative Sensor Based Multi-Classes Neural Network Classifications for Human Activity Recognition

Human activity recognition with the smartphone could be important for many applications, especially since most of the people use this device in their daily life. A smartphone is a portable gadget with internal sensors and enough hardware power to accommodate this problem. In this paper, three neural network algorithms were compared to detect six major activities. The data are collected by a smartphone in real life and simulated on the remote server. The results show that MLP and GMDH neural network have better accuracy and performance compared with the LVQ neural network algorithm.

Digital Image Based Identification of Rice Variety Using Image Processing and Neural Network

The increased of consumer concern on the originality of rice variety and the quality of rice leads to originality certification of rice by existing institutions. Technology helps human to perform evaluations of food grains using images of objects. This study developed a system used as a tool to identify rice varieties. Identification process was performed by analyzing rice images using image processing. The analyzed features for identification consisted of six color features, four morphological features, and two texture features. Classifier used LVQ neural network algorithm. Identification results using a combination of all features gave average accuracy of 70,3% with the highest classification accuracy level of 96,6% for Mentik Wangi and the lowest classification accuracy of 30% for Cilosari.

Digital Image Based Identification of Rice Variety Using Image Processing and Neural Network

The increased of consumer concern on the originality of rice variety and the quality of rice leads to originality certification of rice by existing institutions. Technology helps human to perform evaluations of food grains using images of objects. This study developed a system used as a tool to identify rice varieties. Identification process was performed by analyzing rice images using image processing. The analyzed features for identification consisted of six color features, four morphological features, and two texture features. Classifier used LVQ neural network algorithm. Identification results using a combination of all features gave average accuracy of 70,3% with the highest classification accuracy level of 96,6% for Mentik Wangi and the lowest classification accuracy of 30% for Cilosari.

Detection and Identification of Defects in Transparent Film

Biaxially oriented polyester film (BOPET) defect is an important factor affecting the quality of the film. In view of identification of defects in the conventional film production process, this mathod resulted in the identification of defects inaccurate. and low labor efficiency and machine vision recognition on identification of specific defect. This paper presents a LVQ neural network-based BOPET film of defects detection and identification methods. In this algorithm, the film images were processed and the outlines of the membrane defects were obtained. Through extracting the aspect ration, circularity, complexity and elongation , projection histogram central moment and so on, the characteristic values of membrane defects, which from the image of film images after image processing, and then input to the defects recognition system based on LVQ neural network that had been trained, in order to achieve the film defects identification, classification and localization. Through the study of features of the defects in BOPET and extracted some quantities as character input of the LVQ neural network, then input some characteristic values as training value into the LVQ neural network to achieve the learning and prediction purpose, and the LVQ neural network was designed. The experiments show that, the proposed method can meet the requirements analysis of air defects in transparent film.

Faults Diagnosis of Railway Bearing Based on FIR-wavelet Packet and LVQ Neural Network

In this paper, we present an way for railway bearing fault diagnosis with the use of FIR-wavelet packet and LVQ neural network, First, the original vibration signal of trains' rolling bearing is denoised based on FIR. Then, the sig- nals after de-noised are preprocessed by wavelet packet and the wavelet packet energy eigenvector is reconstructed, those kinds of wavelet packet energy eigenvectors are used to train LVQ neural network. Finally, the intelligent fault diagnosis is realized. The result shows that this approach is effective to distinguish this kind of rolling bearing faults. This method has important practical value.

Research on Recognition of Fertilized Egg Based on Optimized LVQ by Genetic Algorithm

In order to detect fertilized eggs nondestructively to improve hatching rate, this paper uses the method of image processing and Learning Vector Quantization neural network to identify fertilized eggs. Firstly, we use image collection device to collect images of the unfertilized and fertilized eggs and extract the feature of egg image, and then determine 5 principal component characteristics of the egg shape. Learning vector quantization neural networkis 5 dimensional input and 1 dimensional outputs.Finally,we use Genetic Algorithm to optimize the weights and threshold of neural network, which can be used to predict the condition of fertilization. The experiment shows that, compared with the traditional LVQ neural network, it is more accurate to recognize the fertilized eggs when using optimized LVQ neural network by genetic algorithm. The rate can reach 98.21%, which meets therequirements of recognizing fertilized eggs.

Research on Image Technology with Image Recognition of Wheat Diseases Based on Multi-Fractal and LVQ Neural Network

As for different shape features for different wheat diseases, it can make use of multi-fractal analysis to extract 7 Multi-fractal spectrum value of wheat diseases image as the parameters of the wheat disease characteristics. Eight feature parameters can be applied to index the image database as a learning vector quantization neural network input. According, Sample training, classification and recognition is to be carried out. Experimental results show that the wheat disease recognition rate of the algorithm can reach more than 90%.

Identification of Pesticide Residues of Lettuce Leaves Based on LVQ Neural Network

In order to ensure the healthy safety of edible lettuce, an identification way of pesticide residues of lettuce leaves is studied. Soilless cultivation of lettuce sample was adopted. At tillering stage, various levels of fenvalerate were sprayed to different groups of lettuce, lettuce leaves accompanied by a collection of pesticide residues and lettuce leaves not sprayed pesticide residues were collected, Hyperspectral Information of each blade leaf were collected and lettuce leaves sample spectral library was set up. Randomly 90 samples were selected as training samples, and the classification models based on BP neural network and LVQ neural network were set up. The remaining samples were taken to forecast classification test. Results showed that, the prediction identification correct rate of LVQ neural network model is 98.3607%. The algorithm is suitable for pesticide residues diagnosis of lettuce leaves.

Analysis on Children Custody Decision Making Model

Children custody disputes are complicated for many judges owing to so many dynamic factors should to be considered. This paper proposes a novel model for legal expert system Based on LVQ Neural Network. Firstly, all clauses and discretionary factors, extracted from theories and judicial practice, involved with custody disputes in divorce were quantified to obtain related set elements. Then the LVQ neural network was applied to construct a model for children custody disputes weight vector analysis on the set elements. Ultimately, the weight vector close to decision boundaries between classes could promote the classification performance. Accordingly, the performance of the LVQ by generating weight vectors close to decision boundaries is higher. By testing, custody disputes legal expert system could consider all relevant circumstances from a good all-around point of view and effectively.

Fault Diagnosis for Temperature Signal of Turbine Blade Based on LS-SVM

This document discusses the support vector machine (SVM) algorithm, then discusses least squares support vector machine (LS-SVM) algorithm, at the same time, the applications of SVM in the fault diagnosis of temperature signal of turbine blade being discussed, the least squares support vector machine algorithm being used in the research of fault diagnosis, being compared with LVQ neural network, experiments result show the operation speed of the least squares support vector machine algorithm is fast, its generalization ability is stronger, SVM can solve small sample learning problems as well as no-linear, high dimension and local minimization problems in the fault diagnosis of temperature signal of turbine blade.

Research of Improved LVQ Neural Network by AdaBoost Algorithm

Research of Improved LVQ Neural Network by AdaBoost Algorithm

An optimization Algorithm of LVQ Neural Network Classification by GA

This paper describes a dimension reduction method of input vector to improve classification efficiency of LVQ neural network, where GA is used to decrease the redundancy of input data. And in order to solve the initial weight vector sensitivity, GA is also employed to optimize the initial vector. The experimental results on the UCI data sets demonstrate that the efficiency and accuracy of our LVQ network by GA is higher than general LVQ neural network classification algorithm.

LVQ Neural Network Based Driving Cycles Recognition for Hybrid Electric Vehicles

In order to establish a real-time hybrid electric vehicle energy management strategy, a LVQ neural network based driving cycles recognizer is established. Selecting 6 typical driving cycles, and the characteristic parameters of the typical driving cycles are extracted and is used to train the LVＱ neural network by LVQ2 algorithm. The trained LVＱ neural network is employed to recognize the other driving cycle. The result shows that the recognition result reflects the character of the real driving cycle very well.