Component Analysis Network Research Articles

A novel real-time multiple objects detection and tracking framework for different challenges

Recently, there was a lot of researches on real-time detection and tracking algorithms, as the frequent use of surveillance cameras and the expansion of its applications, especially in security and surveillance. However, many challenges have emerged that hinder monitoring systems' work, whether in the detection or tracking stage. We propose a robust new algorithm to detect and track objects from natural scenes captured with real-time cameras to achieve this. This work aims to create a detection and tracking algorithm that is responsive to actual and fundamental changes. This algorithm is characterized by the detection of multiple moving creatures, limited resources, and different challenges. This algorithm combines principal component analysis and deep learning networks to make the most of these two approaches' advantages to achieve an intelligent detection and tracking system that works in real-time. It is done adaptively between the two approaches to enhance performance compared to the existing detection and tracking algorithms. The experimental results showed the new algorithm's effectiveness and efficiency by comparing it with other detection and tracking systems and obtaining good detection and classification accuracy.

MMPCANet: An Improved PCANet for Occluded Face Recognition

Principal Component Analysis Network (PCANet) is a lightweight deep learning network, which is fast and effective in face recognition. However, the accuracy of faces with occlusion does not meet the optimal requirement for two reasons: 1. PCANet needs to stretch the two-dimensional images into column vectors, which causes the loss of essential image spatial information; 2. When the training samples are few, the recognition accuracy of PCANet is low. To solve the above problems, this paper proposes a multi-scale and multi-layer feature fusion-based PCANet (MMPCANet) for occluded face recognition. Firstly, a channel-wise concatenation of the original image features and the output features of the first layer is conducted, and then the concatenated result is used as the input of the second layer; therefore, more image feature information is used. In addition, to avoid the loss of image spatial information, a spatial pyramid is used as the feature pooling layer of the network. Finally, the feature vector is sent to the random forest classifier for classification. The proposed algorithm is tested on several widely used facial image databases and compared with other similar algorithms. Our experimental results show that the proposed algorithm effectively improves the efficiency of the network training and the recognition accuracy of occluded faces under the same training and testing datasets. The average accuracies are 98.78% on CelebA, 97.58% on AR, and 97.15% on FERET.

A Real-Time Framework for Human Face Detection and Recognition in CCTV Images

This paper aims to develop a machine learning and deep learning-based real-time framework for detecting and recognizing human faces in closed-circuit television (CCTV) images. The traditional CCTV system needs a human for 24/7 monitoring, which is costly and insufficient. The automatic recognition system of faces in CCTV images with minimum human intervention and reduced cost can help many organizations, such as law enforcement, identifying the suspects, missing people, and people entering a restricted territory. However, image-based recognition has many issues, such as scaling, rotation, cluttered backgrounds, and variation in light intensity. This paper aims to develop a CCTV image-based human face recognition system using different techniques for feature extraction and face recognition. The proposed system includes image acquisition from CCTV, image preprocessing, face detection, localization, extraction from the acquired images, and recognition. We use two feature extraction algorithms, principal component analysis (PCA) and convolutional neural network (CNN). We use and compare the performance of the algorithms K-nearest neighbor (KNN), decision tree, random forest, and CNN. The recognition is done by applying these techniques to the dataset with more than 40K acquired real-time images at different settings such as light level, rotation, and scaling for simulation and performance evaluation. Finally, we recognized faces with a minimum computing time and an accuracy of more than 90%.

The liquor quality recognition using magnetic resonance spectrum based on Kernel principal component analysis and convolutional neural network

In order to effectively recognize and identify liquor quality by nuclear magnetic resonance (NMR) spectrum data, we propose a hybrid data processing and recognition algorithm. In this algorithm Kernel principal component analysis (KPCA) was used to remove the correlation and reduce dimension of the NMR spectrum, and then convolutional neural network (CNN) was used for classification and identification of the processed spectrum. The compared experiment result show that the proposed KPCA+CNN method can obtain higher accuracy than CNN and PCA+CNN methods based on the NMR spectrum. The KPCA+CNN algorithm has good application prospect and reference value.

Regression and Classification of Alzheimer's Disease Diagnosis Using NMF-TDNet Features From 3D Brain MR Image.

With the development of deep learning and medical imaging technology, many researchers use convolutional neural network(CNN) to obtain deep-level features of medical image in order to better classify Alzheimer's disease (AD) and predict clinical scores. The principal component analysis network (PCANet) is a lightweight deep-learning network that mainly uses principal component analysis (PCA) to generate multilevel filter banks for the centralized learning of samples and then performs binarization and generates blockwise histograms to obtain image features. However, the dimensions of the extracted PCANet features reaching tens of thousands or even hundreds of thousands, and the formation of the multilevel filter banks is sample data dependent, reducing the flexibility of PCANet. In order to solve these problems, in this paper, we propose a data-independent network based on the idea of PCANet, called the nonnegative matrix factorization tensor decomposition network (NMF-TDNet). Specifically, we use nonnegative matrix factorization (NMF) instead of PCA to create multilevel filter banks for sample learning, then uses the learning results to build a higher-order tensor and perform tensor decomposition (TD) to achieve data dimensionality reduction, producing the final image features. Finally, our method use these features as the input of the support vector machine (SVM) for AD classification diagnosis and clinical score prediction. The performance of our method is extensively evaluated on the ADNI-1, ADNI-2 and OASIS datasets. The experimental results show that NMF-TDNet can achieve data dimensionality reduction and the NMF-TDNet features as input achieved superior performance than using PCANet features as input.

Intelligent Combined Neural Network and Kernel Principal Component Analysis Tool for Engine Health Monitoring Purposes

An efficient maintenance plan is an important aspect for aeronautical companies to increase flight safety and decrease costs. Modern technologies are widely used in the Engine Health Monitoring (EHM) discipline to develop intelligent tools capable of monitoring the health status of engines. In this work, Artificial Neural Networks (ANNs) and in-detail Feed-Forward Neural Networks (FFNNs) were exploited in addition to a Kernel Principal Component Analysis (KPCA) to design an intelligent diagnostic tool capable of predicting the Performance Parameters (PPs) of the main components used as their health index. For this purpose, appropriate datasets containing information about degraded engines were generated using the Gas Turbine Simulation Program (GSP). Finally, the original datasets and the reduced datasets obtained after the application of KPCA to the original datasets were both used in the training and testing process of neural networks, and results were compared. The goal was to obtain a reliable intelligent tool useful for diagnostic purposes. The study showed that the degraded component detection and estimation of its performance achieved by using the hybrid KPCA–FFNNs were predicted with accurate and reliable performance, as demonstrated through detailed quantitative confusion matrix analysis.

Similarity‐based clustering and data aggregation with independent component analysis in wireless sensor networks

AbstractWireless sensor networks are consisted of group of sensor nodes, which are scattered in inaccessible areas with limited resources. Data aggregation and clustering methods minimize sensor network's energy usage by reducing the quantity of data transmission. Machine learning techniques like reinforcement learning, neural networks, and swarm intelligence significantly cut down the transmission of data and make use of network's distributive features. Quantity of aggregated data can be reduced if the measured data are similar. Based on this concept, a similarity based clustering method is proposed in which sensor node with similar data are grouped as a cluster for data aggregation. Then an algorithm is proposed that aggregates the data using independent component analysis which is performed on cluster head sensor nodes. Data aggregation process is executed on clusters which are having higher data similarity. Implementation shows that proposed method is performing better in terms of computational overhead, aggregation ratio, and energy consumption.

Development of a combined Artificial Neural Network and Principal Component Analysis technique for Engine Health Monitoring

In aerospace sector, reliability is a crucial point. Modern technologies widely use Artificial Intelligence (AI) algorithms together with detections by sensors in order to design a health-based maintenance plan which stops an aircraft only when needed. In this work, an Engine Health Monitoring (EHM) system was developed by exploiting AI algorithms as Artificial Neural Networks (ANNs) trained to estimate a series of Performance Parameters (PPs) used as index of the health status of the main components constituting an engine. A neural network called Feed-Forward Neural Network (FFNN) in combination with a Principal Component Analysis (PCA) for feature reduction was used in this paper. The software Gas turbine Simulation Program (GSP) was used to generate a series of data containing information about engine performance under different flight conditions and compressor degradation levels. The datasets were subsequently used to train the neural networks to estimate the PPs of the degraded component. The final purpose of the present work is to develop an efficient diagnostic system useful to increase flight safety and decrease maintenance costs and fuel consumption.

Motor imagery EEG signal classification using long short-term memory deep network and neighbourhood component analysis

Motor imagery EEG signal classification using long short-term memory deep network and neighbourhood component analysis

Risk assessment of coal mine water inrush based on PCA-DBN

To provide an effective risk assessment of water inrush for coal mine safety production, a BP neural network prediction method for water inrush based on principal component analysis and deep confidence network optimization was proposed. Because deep belief network (DBN) is disadvantaged by a long training time when establishing a high-dimensional data classification model, the principal component analysis (PCA) method is used to reduce the dimensionality of many factors affecting the water inrush of the coal seam floor, thus reducing the number of variables of the research object, redundancy and the difficulty of feature extraction and shortening the training time of the model. Then, a DBN network was used to extract secondary features from the processed nonlinear data, and a more abstract high-level representation was formed by combining low-level features to find the expression of the nonlinear relationship between the characteristics of water in bursts. Finally, a prediction model was established to predict the water inrush in coal mines. The superiority of this method was verified by comparing the prediction of the actual working face with the actual situation in typical mining areas of North China. The prediction accuracy of coal mine water inrush obtained by this algorithm is 94%, while the prediction accuracy of traditional BP algorithm is 70%, and the prediction accuracy of SVM algorithm is 88%.

Short Term Electric Power Load Forecasting Using Principal Component Analysis and Recurrent Neural Networks

Electrical load forecasting study is required in electric power systems for different applications with respect to the specific time horizon, such as optimal operations, grid stability, Demand Side Management (DSM) and long-term strategic planning. In this context, machine learning and data analytics models represent a valuable tool to cope with the intrinsic complexity and especially design future demand-side advanced services. The main novelty in this paper is that the combination of a Recurrent Neural Network (RNN) and Principal Component Analysis (PCA) techniques is proposed to improve the forecasting capability of the hourly load on an electric power substation. A historical dataset of measured loads related to a 33/11 kV MV substation is considered in India as a case study, in order to properly validate the designed method. Based on the presented numerical results, the proposed approach proved itself to accurately predict loads with a reduced dimensionality of input data, thus minimizing the overall computational effort.

Electronic tongue as innovative instrument for detection of crocin concentration in saffron (Crocus sativus L.).

Electronic tongue is a new approach for simple and fast detection, classification, and quantification of the solved compounds. Crocin is the main source of color of saffron(Crocus sativus L.). An electronic tongue system was used to predict the concentration of saffron crocin in the present study. The measurement system included an electrochemical sensor array based on voltammetry electrodes, a three-electrode cell, a potentiostat, a personal computer. Aqueous analyte were provided by blending pure crocin and different saffron samples from Iran and Spain with distilled water. Output signals of the electronic tongue system were analyzed by principal component analysis and artificial neural networks. Based on principal component analysis, the total variance among pure crocin was 99% and that of saffron samples was 100%. The accuracy of artificial neural network model was 98.80%. The results indicated that the developed electronic tongue system and artificial neural network model can successfully predict crocin concentration in saffron.

Intelligent decision method of sludge bulking using recursive kernel principal component analysis and Bayesian network

Efficient and accurate decision is essential to avoid sludge bulking and ensure the stable operation of wastewater treatment process (WWTP). However, due to the strong nonlinear characteristic, time-varying characteristic and changeable triggering causes of sludge bulking, the decision performance is not optimistic. In this paper, an intelligent decision method combining recursive kernel principal component analysis (RKPCA) and Bayesian network (BN) is proposed to accurately detect the occurrence, identify the root causes and severity level, and provide the restraining measures for sludge bulking. The proposed intelligent decision method consists of three main parts. First, a RKPCA model based on the sliding window mechanism is proposed to extract the nonlinear and time-varying characteristics of WWTP. Then, the proposed RKPCA can assist the decision method to detect the sludge bulking with high accuracy. Second, a mean reconstruction contribution of RKPCA (MRC-RKPCA) method is designed to preliminarily isolate all candidate faulty relevant variables of sludge bulking. Then, the MRC-RKPCA method is able to provide the relationship between the sludge bulking and the corresponding faulty variables for the decision method. Third, a decision model using BN is developed to determine the root causes and the severity of sludge bulking through reverse and forward inference, and provide corresponding restraining measures. Then, the proposed decision method can obtain accurate strategies to suppress the sludge bulking. Finally, the proposed intelligent decision method was applied for a real WWTP. The results demonstrate the proposed intelligent decision method can obtain better decision performance than some existing methods.

Real-estate price prediction with deep neural network and principal component analysis

Abstract Despite the wide application of deep neural networks (DNN) models, their application over small-sized real-estate price prediction is limited due to the reduced prediction accuracy and the high-dimensionality of the dataset. This study motivates small-sized real-estate agencies to take DNN-driven decisions using the available local dataset. To improve the high-dimensionality of real-estate price datasets and thus enhance the price-prediction accuracy of a DNN model, this paper adopts principal component analysis (PCA). The PCA benefits in improving the prediction accuracy of a DNN model are threefold: dimensionality reduction, dataset transformation and localisation of influential price features. The results indicate that, through the PCA-DNN model, the transformed dataset achieves higher accuracy (90%–95%) and better generalisation ability compared with other benchmark price predictors. The spatial and building age proved to have the most impact in determining the overall real-estate price. The application of PCA not only reduces the high-dimensionality of the dataset but also enhances the quality of the encoded feature attributes. The model is beneficial in real-estate and construction applications, where the absence of medium and big datasets decreases the price-prediction accuracy.

Drilling Medium Types Determination Based on Acoustic Signals Using Principal Component Analysis and Artificial Neural Network Techniques

Drilling Medium Types Determination Based on Acoustic Signals Using Principal Component Analysis and Artificial Neural Network Techniques

A prediction model for stock market based on the integration of independent component analysis and Multi-LSTM

<abstract><p>In this paper, we investigate the statistical behaviors of the stock market complex network. A hybrid model is proposed to predict the variations of five stock prices in the securities plate sub-network. This model integrates independent component analysis (ICA) and multivariate long short-term memory (Multi-LSTM) neural network to analyze the trading noise and improve the prediction accuracy of stock prices in the sub-network. Firstly, we apply ICA to deconstruct the original dataset and remove the independent components that represent the trading noise. Secondly, the rest of the independent components are given to Multi-LSTM neural network. Finally, prediction results are reconstructed from the outputs of the Multi-LSTM neural network and the corresponding mixing matrix. The experiment results indicate that the hybrid model outperforms the benchmark approaches, especially in terms of the stock market complex network.</p></abstract>

Traffic Anomaly Detection in Wireless Sensor Networks Based on Principal Component Analysis and Deep Convolution Neural Network

With the popularity of wireless networks, wireless sensor networks (WSNs) have advanced rapidly, and their flexibility and ease of deployment have resulted in more security concerns, making it critical to research network intrusion prevention for WSNs. Denial of service (DoS) is a common network attack, achieving its goal by bringing down the target network. A DoS attack on WSNs devices with limited resources would be fatal. This paper proposes a method based on principal component analysis (PCA) and a deep convolution neural network (DCNN) for DoS traffic anomaly detection in WSNs, based on the vulnerability of WSNs to attacks and the limited storage space of their devices. Compared with the conventional deep learning structure, the proposed model has a lightweight structure and more effective feature extraction capability, which can effectively detect network abnormal traffic in WSNs devices with limited storage capacity. To assure the effectiveness of the proposed model, receiver operating characteristic (ROC) curves, various classification metrics, and confusion matrices are used to verify the classification results of the model. Through experimental comparison, the proposed model, with small model size, outperforms other mainstream abnormal traffic detection models in terms of classification effect.

A new method to predict brittleness index for shale gas reservoirs: Insights from well logging data

Brittleness is a significant mechanical property which determines the degree of fracturing difficulty in shale gas exploitation and hence, the brittleness index (BI) is a key parameter for the selection of suitable hydraulic fracturing intervals in shale gas reservoirs. However, at present there are no universal and convenient methods for the prediction of BI. Therefore, this study proposes a well logging data-driven BI prediction method based on principal component analysis (PCA) and back-propagation neural networks (BPNN), which can interpret nonlinear and complex relationships between predictors (input variables) and predicted values (target variables). Specifically, 63 samples and their corresponding well logging data were collected from the Wufeng-Longmaxi and Baota formations at the periphery of Sichuan Basin. Experimentally measured brittleness index (BIcore) values (from 0.18 to 0.88) derived from compression test stress-strain curves, were considered as the target parameter. Based on the results of linear regression and sensitivity analysis, five types of well logging, including gamma ray (GR), density (DEN), compressional wave slowness (DT), neutron porosity (CNL) and spontaneous potential (SP), were selected as appropriate well logging techniques. Three principal components were extracted from the five well logging datasets using PCA. Following PCA, the back-propagation neural network (PCA-BPNN) model exhibited excellent prediction accuracy according to statistical and graphical error analysis. The established PCA-BPNN model was then applied to forecast the BI profiles of the intervals of interest in well Y1 in the study area and the predicted BI values were found to be in agreement with the laboratory measured BIcore values. Therefore, the established PCA-BPNN BI prediction method can be applied to accurately locate suitable hydraulic fracturing intervals for economic and technical practicality.

A Deep Unfolded Prior-Aided RPCA Network for Cloud Removal

Clouds, together with their shadows, usually occlude ground-cover features in optical remote sensing images. This hinders the utilization of these images for a range of applications such as earth observation, land-cover classification and urban planning. In this work, we propose a deep unfolded and prior-aided robust principal component analysis (DUPA-RPCA) network for removing clouds and recovering ground-cover information in multi-temporal satellite images. We model these cloud-contaminated images as a sum of low rank and sparse elements and then unfold an iterative RPCA algorithm that has been designed for reweighted <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\ell _{1}$</tex-math></inline-formula> minimization. As a result, the activation function in DUPA-RPCA adapts for every input at each layer of the network. Our experimental results on both Landsat and Sentinel images indicate that our method gives better accuracy and efficiency when compared with existing state of the art methods.

Combustion Regime Identification in Turbulent Non-Premixed Flames with Principal Component Analysis, Clustering and Back-Propagation Neural Network

Combustion Regime Identification in Turbulent Non-Premixed Flames with Principal Component Analysis, Clustering and Back-Propagation Neural Network