Neighborhood Component Analysis Research Articles

Hybrid Neighbourhood Component Analysis with Gradient Tree Boosting for Feature Selection in Forecasting Crime Rate

Crime forecasting is beneficial as it provides valuable information to the government and authorities in planning an efficient crime prevention measure. Most criminology studies found that influence from several factors, such as social, demographic, and economic factors, significantly affects crime occurrence. Therefore, most criminology experts and researchers study and observe the effect of factors on criminal activities as it provides relevant insight into possible future crime trends. Based on the literature review, the applications of proper analysis in identifying significant factors that influence crime are scarce and limited. Therefore, this study proposed a hybrid model that integrates Neighbourhood Component Analysis (NCA) with Gradient Tree Boosting (GTB) in modelling the United States (US) crime rate data. NCA is a feature selection technique used in this study to identify the significant factors influencing crime rate. Once the significant factors were identified, an artificial intelligence technique, i.e., GTB, was implemented in modelling the crime data, where the crime rate value was predicted. The performance of the proposed model was compared with other existing models using quantitative measurement error analysis. Based on the result, the proposed NCA-GTB model outperformed other crime models in predicting the crime rate. As proven by the experimental result, the proposed model produced the smallest quantitative measurement error in the case study.

Multi-modal feature fusion for object detection using neighbourhood component analysis and bounding box regression

Multi-modal feature fusion for object detection using neighbourhood component analysis and bounding box regression

Anomaly Detection for Industrial Internet of Things Cyberattacks

The evolution of the Internet of Things (IoT) has empowered modern industries with the capability to implement large-scale IoT ecosystems, such as the Industrial Internet of Things (IIoT). The IIoT is vulnerable to a diverse range of cyberattacks that can be exploited by intruders and cause substantial reputational and financial harm to organizations. To preserve the confidentiality, integrity, and availability of IIoT networks, an anomaly-based intrusion detection system (IDS) can be used to provide secure, reliable, and efficient IIoT ecosystems. In this paper, we propose an anomaly-based IDS for IIoT networks as an effective security solution to efficiently and effectively overcome several IIoT cyberattacks. The proposed anomaly-based IDS is divided into three phases: pre-processing, feature selection, and classification. In the pre-processing phase, data cleaning and normalization are performed. In the feature selection phase, the candidates’ feature vectors are computed using two feature reduction techniques, minimum redundancy maximum relevance and neighborhood components analysis. For the final step, the modeling phase, the following classifiers are used to perform the classification: support vector machine, decision tree, k-nearest neighbors, and linear discriminant analysis. The proposed work uses a new data-driven IIoT data set called X-IIoTID. The experimental evaluation demonstrates our proposed model achieved a high accuracy rate of 99.58%, a sensitivity rate of 99.59%, a specificity rate of 99.58%, and a low false positive rate of 0.4%.

Study of MI-BCI classification method based on the Riemannian transform of personalized EEG spatiotemporal features.

Motor imagery (MI) is a traditional paradigm of brain-computer interface (BCI) and can assist users in creating direct connections between their brains and external equipment. The common spatial patterns algorithm is the most popular spatial filtering technique for collecting EEG signal features in MI-based BCI systems. Due to the defect that it only considers the spatial information of EEG signals and is susceptible to noise interference and other issues, its performance is diminished. In this study, we developed a Riemannian transform feature extraction method based on filter bank fusion with a combination of multiple time windows. First, we proposed the multi-time window data segmentation and recombination method by combining it with a filter group to create new data samples. This approach could capture individual differences due to the variation in time-frequency patterns across different participants, thereby improving the model's generalization performance. Second, Riemannian geometry was used for feature extraction from non-Euclidean structured EEG data. Then, considering the non-Gaussian distribution of EEG signals, the neighborhood component analysis (NCA) algorithm was chosen for feature selection. Finally, to meet real-time requirements and a low complexity, we employed a Support Vector Machine (SVM) as the classification algorithm. The proposed model achieved improved accuracy and robustness. In this study, we proposed an algorithm with superior performance on the BCI Competition IV dataset 2a, achieving an accuracy of 89%, a kappa value of 0.73 and an AUC of 0.9, demonstrating advanced capabilities. Furthermore, we analyzed data collected in our laboratory, and the proposed method achieved an accuracy of 77.4%, surpassing other comparative models. This method not only significantly improved the classification accuracy of motor imagery EEG signals but also bore significant implications for applications in the fields of brain-computer interfaces and neural engineering.

Pathological voice classification based on multi-domain features and deep hierarchical extreme learning machine

The intelligent data-driven screening of pathological voice signals is a non-invasive and real-time tool for computer-aided diagnosis that has attracted increasing attention from researchers and clinicians. In this paper, the authors propose multi-domain features and the hierarchical extreme learning machine (H-ELM) for the automatic identification of voice disorders. A sufficient number of sensitive features are first extracted from the original voice signal through multi-domain feature extraction (i.e., features of the time domain and the sample entropy based on ensemble empirical mode decomposition and gammatone frequency cepstral coefficients). To eliminate redundancy in high-dimensional features, neighborhood component analysis is then applied to filter out sensitive features from the high-dimensional feature vectors to improve the efficiency of network training and reduce overfitting. The sensitive features thus obtained are then used to train the H-ELM for pathological voice classification. The results of the experiments showed that the sensitivity, specificity, F1 score, and accuracy of the H-ELM were 99.37%, 98.61%, 99.37%, and 98.99%, respectively. Therefore, the proposed method is feasible for the initial classification of pathological voice signals.

Fusion of EEG and Eye Blink Analysis for Detection of Driver Fatigue.

The driver fatigue detection using multi-channel electroencephalography (EEG) has been extensively addressed in the literature. However, the employment of a single prefrontal EEG channel should be prioritized as it provides users with more comfort. Furthermore, eye blinks from such channel can be analyzed as the complementary information. Here, we present a new driver fatigue detection method based on simultaneous EEG and eye blinks analysis using an Fp1 EEG channel. First, the moving standard deviation algorithm identifies eye blink intervals (EBIs) to extract blink-related features. Second, the discrete wavelet transform filters the EBIs from the EEG signal. Third, the filtered EEG signal is decomposed into sub-bands, and various linear and nonlinear features are extracted. Finally, the prominent features are selected by the neighbourhood components analysis and fed to a classifier to discriminate between fatigue and alert driving. In this paper, two different databases are investigated. The first one is used for parameters' tuning of proposed method for the eye blink detection and filtering, nonlinear EEG measures, and feature selection. The second one is solely used for testing the robustness of the tuned parameters. The comparison between the obtained results from both databases by the AdaBoost classifier in terms of sensitivity (90.2% vs. 87.4%), specificity (87.7% vs. 85.5%), and accuracy (88.4% vs. 86.8%) indicates the reliability of the proposed method for the driver fatigue detection. Considering the existence of commercial single prefrontal channel EEG headbands, the proposed method can be used to detect the driver fatigue in real-world scenarios.

Hybrid Feature Selection based on BTLBO and RNCA to Diagnose the Breast Cancer

Feature selection is a feasible solution to improve the speed and performance of machine learning models. Optimization algorithms are doing a significant job in searching for optimal variables from feature space. Recent feature selection methods are purely depending on various meta heuristic algorithms for searching a good combination of features without considering the importance of individual features, which makes classification models to suffer from local optima or overfitting problems. In this paper, a novel hybrid feature subset selection technique is introduced based on Regularized Neighborhood Component Analysis (RNCA) and Binary Teaching Learning Based Optimization (BTLBO) algorithms to overcome the above problems. RNCA algorithm assigns weights to the attributes based on their contribution in building the learning models for classification. BTLBO algorithm computes the fitness of individuals with respect to the weights of features and selects the best ones. The results of similar feature selection methods are matched with the proposed hybrid model and proved better performance in terms of classification accuracy, recall and AUC measures over breast cancer datasets.

Effective multi-class lungdisease classification using the hybridfeature engineering mechanism.

The utilization of computational models in the field of medical image classification is an ongoing and unstoppable trend, driven by the pursuit of aiding medical professionals in achieving swift and precise diagnoses. Post COVID-19, many researchers are studying better classification and diagnosis of lung diseases particularly, as it was reported that one of the very few diseases greatly affecting human beings was related to lungs. This research study, as presented in the paper, introduces an advanced computer-assisted model that is specifically tailored for the classification of 13 lung diseases using deep learning techniques, with a focus on analyzing chest radiograph images. The work flows from data collection, image quality enhancement, feature extraction to a comparative classification performance analysis. For data collection, an open-source data set consisting of 112,000 chest X-Ray images was used. Since, the quality of the pictures was significant for the work, enhanced image quality is achieved through preprocessing techniques such as Otsu-based binary conversion, contrast limited adaptive histogram equalization-driven noise reduction, and Canny edge detection. Feature extraction incorporates connected regions, histogram of oriented gradients, gray-level co-occurrence matrix and Haar wavelet transformation, complemented by feature selection via regularized neighbourhood component analysis. The paper proposes an optimized hybrid model, improved Aquila optimization convolutional neural networks (CNN), which is a combination of optimized CNN and DENSENET121 with applied batch equalization, which provides novelty for the model compared with other similar works. The comparative evaluation of classification performance among CNN, DENSENET121 and the proposed hybrid model is also done to find the results. The findings highlight the proposed hybrid model's supremacy, boasting 97.00% accuracy, 94.00% precision, 96.00% sensitivity, 96.00% specificity and 95.00% F1-score. In the future, potential avenues encompass exploring explainable machine learning for discerning model decisions and optimizing performance through strategic model restructuring.

Swin-textural: A novel textural features-based image classification model for COVID-19 detection on chest computed tomography

BackgroundChest computed tomography (CT) has a high sensitivity for detecting COVID-19 lung involvement and is widely used for diagnosis and disease monitoring. We proposed a new image classification model, swin-textural, that combined swin-based patch division with textual feature extraction for automated diagnosis of COVID-19 on chest CT images. The main objective of this work is to evaluate the performance of the swin architecture in feature engineering. Material and methodWe used a public dataset comprising 2167, 1247, and 757 (total 4171) transverse chest CT images belonging to 80, 80, and 50 (total 210) subjects with COVID-19, other non-COVID lung conditions, and normal lung findings. In our model, resized 420 × 420 input images were divided using uniform square patches of incremental dimensions, which yielded ten feature extraction layers. At each layer, local binary pattern and local phase quantization operations extracted textural features from individual patches as well as the undivided input image. Iterative neighborhood component analysis was used to select the most informative set of features to form ten selected feature vectors and also used to select the 11th vector from among the top selected feature vectors with accuracy >97.5%. The downstream kNN classifier calculated 11 prediction vectors. From these, iterative hard majority voting generated another nine voted prediction vectors. Finally, the best result among the twenty was determined using a greedy algorithm. ResultsSwin-textural attained 98.71% three-class classification accuracy, outperforming published deep learning models trained on the same dataset. The model has linear time complexity. ConclusionsOur handcrafted computationally lightweight swin-textural model can detect COVID-19 accurately on chest CT images with low misclassification rates. The model can be implemented in hospitals for efficient automated screening of COVID-19 on chest CT images. Moreover, findings demonstrate that our presented swin-textural is a self-organized, highly accurate, and lightweight image classification model and is better than the compared deep learning models for this dataset.

Cardiac Arrhythmia, CHF, and NSR Classification With NCA-Based Feature Fusion and SVM Classifier

An arrhythmia is an irregular heartbeat that causes abnormal heart rhythms. Manual analysis of electrocardiogram (ECG) signals is not sufficient to quickly detect cardiac arrhythmias. This study proposes a deep learning approach based on a convolutional neural network (CNN) architecture for the classification of cardiac arrhythmias (ARR), congestive heart failure (CHF), and normal sinus rhythm (NSR). First, the ECG signal is converted into a 2D image using time-frequency conversion. The scalogram is constructed using a continuous wavelet transform to extract dynamic features. With CNN, each ECG signal is broken down into heartbeats, and then each heartbeat is converted into a 2D grayscale image of the heartbeat. Morphological feature extraction was performed by segmenting the QRS complex and detecting P and T waves. A third approach to feature extraction is dual-tree complex wavelet transform (DT-CWT). In addition, all extracted features are combined using neighborhood component analysis (NCA), and features are selected to classify using a support vector machine (SVM) classifier.

Evaluation of the performance of different feature selection techniques for identification of NPPs transients using deep learning

Accidents that occur at NPPs must be correctly identified so quickly that mitigation actions can be taken in a timely manner. Depending on the type of transient, the operating parameters follow different patterns and it might be possible to identify the transient by monitoring these parameters. Due to the large number of parameters of an NPP, it is necessary to determine the parameters that play a vital role in transient identification. Data-driven methods have shown effective performance for NPP transient identification. To determine the most important input parameters for NPP transient identification, the present paper has utilized a hybrid feature selection method, in which feature subsets are created using several filter methods and then the best feature subset is determined by comparing the training results of a deep Long Short-Term Memory network. According to the results, the Neighbourhood Components Analysis method has selected the best subset of features.

A new one-dimensional testosterone pattern-based EEG sentence classification method

Electroencephalography (EEG) signals are crucial data to understand brain activities. Thus, many papers have been proposed about EEG signals. In particular, machine learning techniques have been used/presented to extract information from EEG signals. However, there are limited works on sentence classification using this data. To fill this gap, we propose an automated EEG signal classification model. In this model, we have presented a new molecular-based feature extractor, which utilizes a graph of the testosterone molecular structure. The proposed testosterone graph-based pattern is a nature-inspired pattern. The motivation is to show the feature extraction capability of the chemical-based graphs. Hence, we presented a hand-modeled EEG classification architecture. Our architecture uses wavelet packet decomposition (WPD) to generate wavelet bands to extract low and high-level features. The statistical feature extraction function has been used to generate statistical features, and our proposed testosterone pattern (TesPat) generates textural features. A feature selector has been used to choose the most informative features (neighborhood component analysis). Channel-wise results have been calculated by deploying a shallow classifier (k nearest neighbors). Majority voting has been conducted to create general results, and our proposed model selects the best-resulted predicted labels vector. Our proposed model attained a classification accuracy of >97% with 10-fold cross-validation (CV) and >91% with leave-one subject out (LOSO) CV. Our high classification results demonstrate that our presented system is an accurate and robust sentence classification model. The novelty of this work is the development of an accurate testosterone-based learning model using three EEG sentence datasets.

Automated accurate detection of depression using twin Pascal’s triangles lattice pattern with EEG Signals

Electroencephalogram (EEG)-based major depressive disorder (MDD) machine learning detection models can objectively differentiate MDD from healthy controls but are limited by high complexities or low accuracies. This work presents a self-organized computationally lightweight handcrafted classification model for accurate MDD detection using a reference subject-based validation strategy. We used the public Multimodal Open Dataset for Mental Disorder Analysis (MODMA) comprising 128-channel EEG signals from 24 MDD and 29 healthy control (HC) subjects. The input EEG was decomposed using multilevel discrete wavelet transform with Daubechies 4 mother wavelet function into eight low- and high-level wavelet bands. We used a novel Twin Pascal’s Triangles Lattice Pattern(TPTLP) comprising an array of 25 values to extract local textural features from the raw EEG signal and subbands. For each overlapping signal block of length 25, two walking paths that traced the maximum and minimum L1-norm distances from v1 to v25 of the TPTLP were dynamically generated to extract features. Forty statistical features were also extracted in parallel per run. We employed neighborhood component analysis for feature selection, a k-nearest neighbor classifier to obtain 128 channel-wise prediction vectors, iterative hard majority voting to generate 126 voted vectors, and a greedy algorithm to determine the best overall model result. Our generated model attained the best channel-wise and overall model accuracies. The generated system attained an accuracy of 76.08% (for Channel 1) and 83.96% (voted from the top 13 channels) using leave-one-subject-out(LOSO) cross-validation (CV) and 100% using 10-fold CV strategies, which outperformed other published models developed using same (MODMA) dataset.

ViVGG19: Novel exemplar deep feature extraction-based shoulder rotator cuff tear and biceps tendinosis detection using magnetic resonance images.

Rotator cuff tear (RCT) and biceps tendinosis (BT) are the two most common shoulder disorders worldwide. These disorders can be diagnosed using magnetic resonance imaging (MRI), but the expert interpretation is manual, time-consuming, and subjected to human errors. Therefore, a fixed-size feature extraction model was created to objectively and accurately perform automated binary classification of RCT vs. normal and BT vs. normal on MRI images. We have developed an exemplar deep feature extraction model to diagnose RCT and BT disorders. The model was tested on a new MR image dataset comprising transverse, sagittal, and coronal MRI images of the shoulder that had been organized into three cases. BT was studied on transverse MRI images (Case 1), while RCT was studied on sagittal (Case 2) and coronal MRI images (Case 3). Our model comprised deep feature generation using a pre-trained VGG19, feature selection using iterative neighborhood component analysis (INCA), and classification using shallow standard classifiers k-nearest neighbors (KNN), support vector machine (SVM), and artificial neural network (ANN). In the feature extraction phase, two fully connected layers were used to extract deep features from the original image, and sixteen fixed-size patches obtained by the division of the original image. This model was named Vision VGG19 (ViVGG), analogous to vision transformers (ViT). The feature vector is extracted from the raw image dataset, and 16 feature vectors are extracted from each fixed-size patch. Seventeen feature vectors obtained from each image are obtained from fc6 and fc7 layers of the pre-trained VGG19, are merged to obtain final feature vector. INCA was used to choose the top features from the created features, and the chosen features were classified using shallow classifiers. We defined three cases to evaluate the proposed ViVGG19 to diagnose RT and BCT disorders. Our proposed ViVGG19 model achieved more than 99% accuracy using the KNN classifier. ViVGG19 is a very effective model for detecting RCT and BT disorders on shoulder MRI images. The developed automated system is ready to be tested with a bigger diverse database obtained from different medical centers.

Hybrid Deep Model for Automated Detection of Tomato Leaf Diseases

Tomatoes are preferred by farmers because of their high productivity. This fruit has a fibrous structure and contains plenty of vitamins. Tomato diseases are generally observed on stem, fruit, and leaves. Early diagnosis of the disease in plants is of vital importance for the plant. This is very important for farmers who expect economic gain from that plant. Because if the disease is not treated early, these tomatoes should be destroyed. For these reasons, systems to diagnose the disease early are very important. In this study, a tomato leaf diseases classification model developed with deep learning methods, which is one of the most popular artificial intelligence techniques, is proposed in order to eliminate the possibility of the human eye being mistaken. In this study, 6 different Convolutional Neural Network (CNN) architectures were used. In the first stage of this study, which consists of two stages, the classification process was carried out with the Alexnet, Googlenet, Shufflenet, Efficientb0, Resnet50, and Inceptionv3 architectures that were previously trained. In the second stage, feature maps of tomato leaf images in the dataset were obtained using the six pre-trained deep learning architectures. In the hybrid model proposed in this study, the feature maps extracted using the best two of the six deep learning models are concatenated. Then, the Neighborhood Component Analysis (NCA) method was applied to the extracted features in order to speed up the system, unnecessary features were removed and optimized. The optimized feature map is classified by traditional intelligent classification models. As a result of experimental studies, the average accuracy rate of the proposed model is 99.50 percent.

Multilevel hybrid accurate handcrafted model for myocardial infarction classification using ECG signals.

Myocardial infarction (MI) is detected using electrocardiography (ECG) signals. Machine learning (ML) models have been used for automated MI detection on ECG signals. Deep learning models generally yield high classification performance but are computationally intensive. We have developed a novel multilevel hybrid feature extraction-based classification model with low time complexity for MI classification. The study dataset comprising 12-lead ECGs belonging to one healthy and 10 MI classes were downloaded from a public ECG signal databank. The model architecture comprised multilevel hybrid feature extraction, iterative feature selection, classification, and iterative majority voting (IMV). In the hybrid handcrafted feature (HHF) generation phase, both textural and statistical feature extraction functions were used to extract features from ECG beats but only at a low level. A new pooling-based multilevel decomposition model was presented to enable them to create features at a high level. This model used average and maximum pooling to create decomposed signals. Using these pooling functions, an unbalanced tree was obtained. Therefore, this model was named multilevel unbalanced pooling tree transformation (MUPTT). On the feature extraction side, two extractors (functions) were used to generate both statistical and textural features. To generate statistical features, 20 commonly used moments were used. A new, improved symmetric binary pattern function was proposed to generate textural features. Both feature extractors were applied to the original MI signal and the decomposed signals generated by the MUPTT. The most valuable features from among the extracted feature vectors were selected using iterative neighborhood component analysis (INCA). In the classification phase, a one-dimensional nearest neighbor classifier with ten-fold cross-validation was used to obtain lead-wise results. The computed lead-wise results derived from all 12 leads of the same beat were input to the IMV algorithm to generate ten voted results. The most representative was chosen using a greedy technique to calculate the overall classification performance of the model. The HHF-MUPTT-based ECG beat classification model attained excellent performance, with the best lead-wise accuracy of 99.85% observed in Lead III and 99.94% classification accuracy using the IMV algorithm. The results confirmed the high MI classification ability of the presented computationally lightweight HHF-MUPTT-based model.

Developing bearing capacity model for geogrid-reinforced stone columns improved soft clay utilizing MARS-EBS hybrid method

Because of the complicated geometry and a lack of knowledge about the parameters that impact it, estimating the ultimate bearing capacity (qrs) of a geogrid-reinforced sandy bed on vertical stone columns in soft clay is challenging. In practical applications, developing an accurate prediction model can be beneficial due to the difficulty and expense of estimating qrs. The objective of this study is to develop a model for predicting the bearing capacity of geogrid-reinforced stone columns using Multivariate Adaptive Regression Splines (MARS) and Escaping Bird Search optimization algorithm (EBS). In order to accomplish this, 219 constructed experimental samples were used. Feature selection based on the Neighborhood Component Analysis (NCA) method showed that due to the strong correlation between undrained shear strength of unreinforced clay (qu) and the ratio of stone columns distance to foundation diameter (s/D) variables, only qu should be included in the modeling. A developed model for estimating the bearing capacity was found to have coefficients of determination (R2) of 0.997 for training, 0.993 for testing, and 0.995 for total data. This study confirms that the undrained shear strength of unreinforced clay (qu) is the most essential input parameter for assessing bearing capacity, while the the ratio of sandy bed thickness to foundation diameter (t/D) is the least essential input parameter. In addition, the parametric analysis shows that increasing all input parameters increases bearing capacity.

Novel favipiravir pattern-based learning model for automated detection of specific language impairment disorder using vowels.

Specific language impairment (SLI) is one of the most common diseases in children, and early diagnosis can help to obtain better timely therapy economically. It is difficult and time-consuming for clinicians to accurately detect SLI through standard clinical assessments. Hence, machine learning algorithms have been developed to assist in the accurate diagnosis of SLI. This work aims to investigate the graph of the favipiravir molecule-based feature extraction function and propose an accurate SLI detection model using vowels. We proposed a novel handcrafted machine learning framework. This architecture comprises the favipiravir molecular structure pattern, statistical feature extractor, wavelet packet decomposition (WPD), iterative neighborhood component analysis (INCA), and support vector machine (SVM) classifier. Two feature extraction models, statistical and textural, are employed in the handcrafted feature generation methodology. A new nature-inspired graph-based feature extractor that uses the chemical depiction of the favipiravir (favipiravir became popular with the COVID-19 pandemic) is employed for feature extraction. Finally, the proposed favipiravir pattern, statistical feature extractor, and wavelet packet decomposition are used to create a feature vector. Moreover, a statistical feature extractor is used in this work. The WPD generates multilevel features, and the most meaningful features are selected using the NCA feature selector. Finally, these chosen features are fed to SVM classifier for automated classification. Two validation methods, (i) leave one subject out (LOSO) and (ii) tenfold cross-validations (CV), are used to obtain robust classification results. Our proposed favipiravir pattern-based model developed using a vowel dataset can detect SLI children with an accuracy of 99.87% and 98.86% using tenfold and LOSO CV strategies, respectively. These results demonstrated the high vowel classification ability of the proposed favipiravir pattern-based model.

Deep autoencoder based hybrid dimensionality reduction approach for classification of SERS for melanoma cancer diagnostics

Melanoma, a kind of fatal skin cancer, originates in melanin secreting cells of the dermis. Disease identification in the early stages assures a high survival rate for the patient. Most of the existing techniques retard the cancer detection phase. Surface-Enhanced Raman Spectroscopy (SERS) can capture fine details from the specimens that machine learning models can utilize to discriminate between healthy and diseased individuals rapidly. Our research work proposes a deep autoencoder based hybrid dimensionality reduction approach with a machine learning model on SERS spectrums of human skin fibroblast for melanoma cancer diagnostics. SERS measurements of 307 samples in total, belonging to two different classes, such as normal (157 samples) and malignant melanoma (150 samples), are used in this study. The SERS spectra measurements for both the samples lie between 100cm-1 and 4278cm-1. The variations in the intensity of Raman bands between both classes are intrinsically subtle. Neighborhood Component Analysis (NCA) technique has been exerted to transform 2090 dimensional spectral features into 2090 dimensional vectors and then the Deep Autoencoder (DAE) model is used to handle the nonlinearity in the data and produce the latent space, while Linear Discriminant Analysis (LDA) classifier have been employed for discriminating the normal and cancer cells. The k-fold cross-validation technique with a k value of 10 is implemented to assess the metrics of the model. The stated hybrid (NCA and DAE) model with 10-dimension latent space achieves an accuracy of 98%, the sensitivity of 99% and specificity of 97%, respectively. Due to the high-intensity nature of the SERS spectrum, the existing linear dimensionality reduction based discriminating model fails if the class label (Normal or Cancer) gets distributed on the low variance side. The proposed methodology captures both linear and nonlinear underlying structures present in the spectrums, resulting in better classification compared to the standard dimensionality reduction techniques.

Residual-Electrical-Endurance Prediction of AC Contactor Based on CNN-GRU

AC contactors are used frequently in various low-voltage control lines, so remaining-life prediction for them can significantly improve the operational reliability of power control systems. To address the problem that the existing AC contactor remaining-life prediction methods do not make full use of the correlation between previous and later states in the degradation process, a CNN-GRU (convolutional neural network-gated recurrent unit) method for AC-contactor remaining-life prediction is proposed. Firstly, the entire cycle of an AC contactor’s degradation data is obtained through a whole-life test, from which the characteristic parameters that effectively reflect the operating states of the contactor are extracted; secondly, neighborhood component analysis (NCA) and maximal information coefficient (MIC) are used to eliminate the redundant information of multidimensional parameters in order to select the optimal feature subset; and then, CNN is used to compress the feature dimension and mine the regular information between the features, so as to extract the effective feature vectors; finally, taking the AC contactor remaining electrical life as a long time sequence issue, time-series accurate prediction is performed using GRU. It is verified that this model is better than RNN (recurrent neural network), LSTM (long short-term memory) and GRU models in prediction, with an effective accuracy of 96.63%, which effectively supports the feasibility of time-series prediction in the field of the remaining-life prediction of electrical devices.