Artificial Neural Network Classification Technique Research Articles

Image Security Performance Analysis for SVM and ANN Classification Techniques

Image Security has been talked about the classification extemporized in numerous structures and utilizing distinctive systems just as innovations. The upgrades continue including the quickest security refreshing the system framework. This proposes a representation for verifying the video framework alongside the system and upgrades it more by relate AI methods SVM (support vector machine) and ANN (Artificial Neural Network). Both the methods are utilized together training and testing classification to produce results which are fitting for investigation reason and subsequently, turn out to be the achievement for security.

Studying the effect of lossy compression and image fusion on image classification

Nowadays, the remotely sensed images are of huge sizes that require the implementation of compression technique to be easily stored on the internet. In addition, image fusion which is the merging of panchromatic and multispectral images to generate a single image with high spatial and spectral resolutions is required to increase the information in the resulted image. The purpose of this paper is to study the effect of image compression and fusion techniques on the classification accuracy. In this study, two pan and mul Geo-eye images covering an area of Cape Town, South Africa were registered and fused using different fusion techniques. The fused image with the superior accuracy was then compressed with various compression ratios ranging from 1:10 to 1:100. Then, the compressed fused images were classified using Maximum Likelihood Classification and Artificial Neural Network Classification techniques. Finally, the confusion matrices of the classified images were generated and evaluated to determine the effect of compression and fusion techniques on the accuracy of the classification process.

Artificial Neural Network Classification for Fatigue Feature Extraction Parameters Based on Road Surface Response

The aim of this paper is for classification for fatigue feature extraction parameters based on road surface response using the artificial neural network (ANN) technique. It is important for classification of the fatigue damage of automotive suspension as it is considers the random strain loading from the road surface contributed from complex variable amplitude loadings. In this study, the proposed method captured that strain signal collected from the car coil spring during the road test. Hence, the prediction of fatigue life need to assess based on actual loading to ensure the prediction results are accurate. The high amplitude segments were extracted from the strain signals using the discrete wavelet transform. This approach provides an advantage in assessing the signals containing random loads for both discontinuities and smooth components for the areas that contain high fatigue damage in the strain signal. From this, three significant fatigue features extraction parameters such as kurtosis, wavelet energy coefficients and fatigue damage were classified based on the similarities using ANN classification technique. This is important in analysing the clustering and classification were used in detection of fatigue damage according to the response of the various road surface condition. The results show the classifications using ANN give the accuracy based on the coefficient of determinant, R= 0.85 for all data. From on the accuracy of the ANN, it can be concluded that the discrete wavelet transform as a pre-processing method to extract the features from the signal for classification level of fatigue damage for the coil spring according to the response of loading based on road surface.

HYBRID CLASSIFICATION SCHEMES FOR HEART MURMUR DETECTION TO ASSIST PHONOCARDIOGRAM BASED SIGNAL ACQUISITION

The main contribution of this paper has been to introduce nonlinear classification techniques to extract more information from the PCG signal. Especially, Artificial Neural Network classification techniques have been used to reconstruct the underlying system’s state space based on the measured PCG signal. This processing step provides a geometrical interpretation of the dynamics of the signal, whose structure can be utilized for both system characterization and classification as well as for signal processing tasks such as detection and prediction.

Solving time series classification problems using support vector machine and neural network

The major aim of classification is to extract categories of inputs according to their characteristics. The literature contains several methods that aim to solve the time series classification problem, such as the artificial neural network (ANN) and the support vector machine (SVM). Time series classification is a supervised learning method that maps the input to the output using historical data. The primary objective is to discover interesting patterns hidden in the data. In this study, we use a new method called SVNN which combines the SVM and ANN classification techniques to solve the time series data classification problem. The proposed SVNN is applied to six benchmark UCR time series datasets. The results show that the proposed method outperforms the ANN and SVM on all datasets. Further comparison with other approaches in the literature also shows that the SVNN is able to maximise accuracy. It is believed that combining classification techniques can give better results in terms of accuracy and better solutions for time series classification.

Fuzzy Neural Network-Based Health Monitoring for HVAC System Variable-Air-Volume Unit

For indoor smart grids, the proper operation of building environmental systems is essential to energy efficiency, so automatic detection and classification of abnormal conditions are important. The application of computational intelligence tools to a building’s environmental systems that include the building automation system (BAS) and heating ventilating and air conditioning (HVAC) loads is used to develop automatic building diagnostic tools for health monitoring, fault detection, and diagnostics. A novel health monitoring system (HMS) for a variable air volume (VAV) unit is developed using fuzzy logic (FL) to detect abnormal operating conditions and to generate fault signatures for various fault types. Artificial neural network classification technique is applied to fault signatures to classify the fault type. The HMS is tested with simulated data and actual BAS data. The system created was demonstrated to recognize faults and to accurately classify the various fault signatures for test faults of interest.

Classification of Electron Gun Operation Modes Using Artificial Neural Networks

In electron collision experiments, the seven-element electron gun is commonly used to accelerate and focus an electron beam. The main operation modes of this experimental device are afocal, zoom and broad beam-modes. Each of these operation modes can be used for producing electron beam with desired diameter. In this study, the artificial neural network classification technique (ANN) is used for classification of electron gun operation modes depending on electrostatic lens voltages. For this purpose, we investigate the focusing condition for the first three-element lens. Other ANN is employed for the second four-element lens voltages to find the electron gun operation modes. A comprehensive training data is obtained from SIMION software which uses traditional ray-tracing method. ANNs are trained with this dataset. Moreover, performance evaluations are carried out to determine the classification power of ANNs. High performance values show that the ANN can easily categorize the operation mode of the electron gun as a function of lens voltages. The proposed approach may help to adjust electron gun voltages before collision experiments. It is believed that this study will be a model for the future research in electron collision systems. Network can be trained with experimental data for practical applications.