ReliefF Algorithm Research Articles

Research on rotor system fault diagnosis method based on vibration signal feature vector transfer learning

Aiming at the common fault diagnosis problems of rotors in industrial applications. A rotor system fault diagnosis method based on vibration signal feature vector transfer learning is proposed. First, Statistical methods and wavelet packet decomposition are used for vibration signal feature extraction. Then, the ReliefF algorithm is used to evaluate the fault features and screen out the sensitive fault features set. Next, the training data and real time test data are mapped to the kernel Hilbert space using the transfer component analysis method. Finally, the weighted k-nearest neighbor method is used as the fault feature classifier for fault pattern recognition. Model training and validation using typical failure datasets of different equipment and different operating conditions. Compared with other related methods, the results indicate that the proposed method has better generalization and diagnostic accuracy. This research will promote the engineering application of intelligent fault diagnosis of rotor system.

Identification of vegetation under natural gas leakage by spectral index based on feature selection

ABSTRACT The leakage of natural gas storage has a significant impact on economy, personal safety and natural environment. When the leakage is slight, the effect of direct detection is not ideal. Hyperspectral remote sensing can detect it indirectly through the spectral changes of surface vegetation. In this study, wheat, bean and grass were used as surface experimental objects to analyse the variation characteristics of canopy spectrum and physiological and biochemical parameters of vegetation under natural gas leakage. The results showed that with the increase of natural gas concentration in the soil, the spectral reflectance of vegetation increased significantly in the visible region, and decreased significantly in the near infrared region. The natural gas identification index (NGII) was constructed according the optimal weight index screened by Relief-F algorithm. The quantitative test by Jeffries-Matusita (JM) distance showed that NGII can identify (JM > 1.8) stressed vegetation under natural gas leakage in a short time. This study can provide technical reference for detecting leakage of underground natural gas storage.

Utilization of UV-visible and FTIR spectroscopy coupled with chemometrics for differentiation of Indonesian tea: an exploratory study

Ultraviolet (UV)-visible and Fourier-transformed infrared (FTIR) spectroscopy are two of the most popular and readily available laboratory instruments. Fingerprinting analysis of the UV-visible and FTIR spectra has been applied for food classification and authentication studies. In this study, the UV-visible and FTIR spectra of brewed tea, and their data fusion data sets, were used to build models for the classification of tea based on tea types and origins. The study included black and green tea samples from several provinces in Sumatra and Java Islands (Indonesia). Chemometric models of principal component analysis (PCA), k-nearest neighbor (kNN), and logistic regression were developed for classification purposes. All PCA models were able to well-separate the tea groups. kNN and logistic regression models based on UV-visible spectra successfully classified green and black tea with >0.8 classification accuracy. The kNN model of FTIR spectra had good accuracy (0.903) for classifying tea based on its origin. ReliefF algorithm was employed to select the best features among the data fusion data sets of UV-visible and FTIR spectra. The data fusion data sets of UV-visible and FTIR spectra demonstrated good separation of tea types and origins with a high area under the ROC curve (>0.8) and moderate accuracy (0.548). Therefore, UV-visible and FTIR spectroscopy may provide complementary information for tea classification based on tea types and origins.

Recognition of Human Inner Emotion Based on Two-Stage FCA-ReliefF Feature Optimization

Currently, there is a growing interesting in emotion recognition. Representation of emotional states is a very challenging issue. Considering the calculation cost and generalization capability for practical application, a series of features which contain common time and frequency domain are extracted from physiological signals to represent different emotional states. To reduce feature dimensionality and improve the emotion recognition accuracy, a two-stage feature optimization method based on feature correlation analysis (FCA) and ReliefF algorithm is proposed to select critical features. Firstly, FCA is employed to analyze the redundancy between features, then ReliefF is adopted to analyze the correlation between features and categories, and the optimal feature subset is obtained using the two-stage FCA-ReliefF feature optimization method. Support vector machine is employed as the classifier to evaluate classification performance in this investigation. The effectiveness of the method which is proposed is validated by testing on two publicly available multimodal emotion datasets, Augsburg Biosignal Toolbox (AuBT) and Database for Emotion Analysis Using Physiological Signals (DEAP). Compared with recent similar reported studies, the method developed in this research for emotion recognition is stable and competitive, and its accuracy reaches to 98.40% (AuBT) and 92.34% (DEAP).

Detection of communicable and non-communicable diseases using hyperparameter optimization with Bi-LSTM model in pathology images

PurposeThe present research work is carried out for determining haemoprotozoan diseases in cattle and breast cancer diseases in humans at early stage. The combination of LeNet and bidirectional long short-term memory (Bi-LSTM) model is used for the classification of heamoprotazoan samples into three classes such as theileriosis, babesiosis and anaplasmosis. Also, BreaKHis dataset image samples are classified into two major classes as malignant and benign. The hyperparameter optimization is used for selecting the prominent features. The main objective of this approach is to overcome the manual identification and classification of samples into different haemoprotozoan diseases in cattle. The traditional laboratory approach of identification is time-consuming and requires human expertise. The proposed methodology will help to identify and classify the heamoprotozoan disease in early stage without much of human involvement.Design/methodology/approachLeNet-based Bi-LSTM model is used for the classification of pathology images into babesiosis, anaplasmosis, theileriosis and breast images classified into malignant or benign. An optimization-based super pixel clustering algorithm is used for segmentation once the normalization of histopathology images is conducted. The edge information in the normalized images is considered for identifying the irregular shape regions of images, which are structurally meaningful. Also, it is compared with another segmentation approach circular Hough Transform (CHT). The CHT is used to separate the nuclei from non-nuclei. The Canny edge detection and gaussian filter is used for extracting the edges before sending to CHT.FindingsThe existing methods such as artificial neural network (ANN), convolution neural network (CNN), recurrent neural network (RNN), LSTM and Bi-LSTM model have been compared with the proposed hyperparameter optimization approach with LeNET and Bi-LSTM. The results obtained by the proposed hyperparameter optimization-Bi-LSTM model showed the accuracy of 98.99% when compared to existing models like Ensemble of Deep Learning Models of 95.29% and Modified ReliefF Algorithm of 95.94%.Originality/valueIn contrast to earlier research done using Modified ReliefF, the suggested LeNet with Bi-LSTM model, there is an improvement in accuracy, precision and F-score significantly. The real time data set is used for the heamoprotozoan disease samples. Also, for anaplasmosis and babesiosis, the second set of datasets were used which are coloured datasets obtained by adding a chemical acetone and stain.

Rapid odor recognition based on reliefF algorithm using electronic nose and its application in fruit identification and classification

Rapid odor recognition based on reliefF algorithm using electronic nose and its application in fruit identification and classification

A Hybrid Convolutional Neural Network and Relief-F Algorithm for Fault Power Line Recognition in Internet of Things-Based Smart Grids

Today, energy management based on the digitalization of smart grids by the Internet of Things (IoT) is an emerging paradigm for power line systems. There are several environmental hazards to break down high-voltage power cables such as lightning, severe voltage fluctuations, and incorrect design of electric field distribution. So, identifying faulty high-voltage power lines is one of the most emerging challenges in smart grids to avoid disruption of the power distribution networks. This paper presents a new hybrid Convolutional Neural Network and Relief-F (CNN-RF) algorithm for an energy-aware collaborative learning approach to detect power line systems in smart grids. This hybrid approach ensures the stability and reliability of the defective power line system and improves the energy efficiency of the smart grids. This approach can detect the defective power line recognition using damaged power line images concerning automatic monitoring using Unmanned Aerial Vehicle (UAV) control system and IoT communications. By applying UAV control system and IoT communications on gathering damaged power line images, human faults and environmental hazards for extra data transmission are avoided. Experimental results show that the proposed CNN-RF model represents a high accuracy rate of 92.2% for recognizing damaged power lines. Also, the precision of damaged line detection ratio is higher than other prediction methods by the rate of 92.5%. Finally, the performance of the damaged line prediction approach in the CNN-RF method has a daily minimum cost in the IoT-based smart grids.

Poststroke Grasp Ability Assessment Using an Intelligent Data Glove Based on Action Research Arm Test: Development, Algorithms, and Experiments.

Growing impact of poststroke upper extremity (UE) functional limitations entails newer dimensions in assessment methodologies. This has compelled researchers to think way beyond traditional stroke assessment scales during the out-patient rehabilitation phase. In concurrence with this, sensor-driven quantitative evaluation of poststroke UE functional limitations has become a fertile field of research. Here, we have emphasized an instrumented wearable for systematic monitoring of stroke patients with right-hemiparesis for evaluating their grasp abilities deploying intelligent algorithms. An instrumented glove housing 6 flex sensors, 3 force sensors, and a motion processing unit was developed to administer 19 activities of Action Research Arm Test (ARAT) while experimenting on 20 voluntarily participating subjects. After necessary signal conditioning, meaningful features were extracted, and subsequently the most appropriate ones were selected using the ReliefF algorithm. An optimally tuned support vector classifier was employed to classify patients with different degrees of disability and an accuracy of 92% was achieved supported by a high area under the receiver operating characteristic score. Furthermore, selected features could provide additional information that revealed the causes of grasp limitations. This would assist physicians in planning more effective poststroke rehabilitation strategies. Results of the one-way ANOVA test conducted on actual and predicted ARAT scores of the subjects indicated remarkable prospects of the proposed glove-based method in poststroke grasp ability assessment and rehabilitation.

Modeling the effects of biodiesel chemical composition on iodine value using novel machine learning algorithm

Biodiesel is a promising renewable energy the use of which facilitates the goals of carbon neutrality and timely carbon peak. The iodine value (IV), one of the major properties of biodiesel, denotes the degree of unsaturation and correlates with the chemical composition of biodiesel. In this work, a novel approach based on random forest (RF) and least squares support vector machine (LSSVM) algorithms optimized by whale optimization algorithm (WOA) is proposed for estimating the IV of biodiesel as a function of fatty acid methyl ester profiles. In doing so, the compositions and IVs of 52 biodiesel/binary biodiesel blends were determined by gas chromatography mass spectrometry and EN14111 standard. Then, LSSVM algorithm was assessed as the most appropriate predictive method compared to the adaptive neuro fuzzy inference system, multi-layer perceptron neural network, and decision tree algorithms. Continuously, four feature selection approaches (Pearson’s correlation coefficient, principal component analysis, ReliefF algorithm, and RF) were utilized to choose the most influencing fatty acid methyl ester combination as input. The RF-LSSVM model was found to be superior to other Ⅰ hybrid models. Then, WOA was incorporated into the modeling process and the RF-WOA-LSSVM model achieved a high performance with a root mean square error and correlation coefficient of 1.1893 and 0.9977, respectively. The accuracy and error of the RF-WOA-LSSVM model have been validated. Comparison with previous biodiesel IV machine learning models and application of other new experimental datasets from the literature prove the feasibility of the proposed hybrid RF-WOA-LSSVM model for estimating the IV of different biodiesels types.

Comparative analysis of proficiencies of various textures and geometric features in breast mass classification using k-nearest neighbor

This paper introduces a comparative analysis of the proficiencies of various textures and geometric features in the diagnosis of breast masses on mammograms. An improved machine learning-based framework was developed for this study. The proposed system was tested using 106 full field digital mammography images from the INbreast dataset, containing a total of 115 breast mass lesions. The proficiencies of individual and various combinations of computed textures and geometric features were investigated by evaluating their contributions towards attaining higher classification accuracies. Four state-of-the-art filter-based feature selection algorithms (Relief-F, Pearson correlation coefficient, neighborhood component analysis, and term variance) were employed to select the top 20 most discriminative features. The Relief-F algorithm outperformed other feature selection algorithms in terms of classification results by reporting 85.2% accuracy, 82.0% sensitivity, and 88.0% specificity. A set of nine most discriminative features were then selected, out of the earlier mentioned 20 features obtained using Relief-F, as a result of further simulations. The classification performances of six state-of-the-art machine learning classifiers, namely k-nearest neighbor (k-NN), support vector machine, decision tree, Naive Bayes, random forest, and ensemble tree, were investigated, and the obtained results revealed that the best classification results (accuracy = 90.4%, sensitivity = 92.0%, specificity = 88.0%) were obtained for the k-NN classifier with the number of neighbors having k = 5 and squared inverse distance weight. The key findings include the identification of the nine most discriminative features, that is, FD26 (Fourier Descriptor), Euler number, solidity, mean, FD14, FD13, periodicity, skewness, and contrast out of a pool of 125 texture and geometric features. The proposed results revealed that the selected nine features can be used for the classification of breast masses in mammograms.

Research on application of ReliefF and improved RVM in water quality grade evaluation.

ReliefF algorithm was used to analyze the weight of each water quality evaluation factor, and then based on the Relevance Vector Machine (RVM), Particle Swarm Optimization (PSO) was used to optimize the kernel width factor and hyperparameters of RVM to build a water quality evaluation model, and the experimental results of RVM, PSO-RVM, ReliefF-RVM and PSO-ReliefF-RVM were compared. The results show that ReliefF algorithm, combined with threshold value, selects 5 evaluation factors with significant weight from eight evaluation factors, which reduces the amount of data used in the model, CSI index is used to calculate the separability of each evaluation factor combination. The results show that the overall separability of the combination is best when the evaluation factor with significant weight is reserved. When different water quality evaluation factors were included, the evaluation accuracy of PSO-ReliefF-RVM model reached 95.74%, 14.23% higher than that of RVM model, which verified the effectiveness of PSO algorithm and ReliefF algorithm, and had a higher guiding significance for the study of water quality grade evaluation. It has good practical application value.

A Simple and Effective Approach Based on a Multi-Level Feature Selection for Automated Parkinson's Disease Detection.

Parkinson’s disease (PD), which is a slowly progressing neurodegenerative disorder, negatively affects people’s daily lives. Early diagnosis is of great importance to minimize the effects of PD. One of the most important symptoms in the early diagnosis of PD disease is the monotony and distortion of speech. Artificial intelligence-based approaches can help specialists and physicians to automatically detect these disorders. In this study, a new and powerful approach based on multi-level feature selection was proposed to detect PD from features containing voice recordings of already-diagnosed cases. At the first level, feature selection was performed with the Chi-square and L1-Norm SVM algorithms (CLS). Then, the features that were extracted from these algorithms were combined to increase the representation power of the samples. At the last level, those samples that were highly distinctive from the combined feature set were selected with feature importance weights using the ReliefF algorithm. In the classification stage, popular classifiers such as KNN, SVM, and DT were used for machine learning, and the best performance was achieved with the KNN classifier. Moreover, the hyperparameters of the KNN classifier were selected with the Bayesian optimization algorithm, and the performance of the proposed approach was further improved. The proposed approach was evaluated using a 10-fold cross-validation technique on a dataset containing PD and normal classes, and a classification accuracy of 95.4% was achieved.

Power Quality Disturbance Recognition Using Empirical Wavelet Transform and Feature Selection

With the growth of nonlinear electrical equipment, power quality disturbances (PQDs) often appear in electrical systems. To solve this, a practical heuristic methodology for PQD detection and classification based on empirical wavelet transform has been proposed. By using a multiresolution analysis tool, empirical wavelet transform, the voltage waveform signal is decomposed into several sub-signals, and some potential features are extracted in the statistical method. To reduce the feature vector dimensions, the ReliefF algorithm is used for feature selection and optimized for dimensionality reduction, which reduces the complexity of system calculation while ensuring accuracy. Finally, a classifier based on support vector machines (SVM) was built, and with the ranked feature vectors’ input, the PQD can be recognized. The experimental results verify that the classification results achieved high accuracy, which confirms the properties and robustness of the proposed approach in noisy environments.

A novel ensemble machine learning and time series approach for oil palm yield prediction using Landsat time series imagery based on NDVI

Accurate oil palm yield prediction is necessary to sustain oil palm production for food security and economic return. However, there are limited studies on comprehensive mapping and accurate oil palm yield prediction using advanced machine learning algorithms. Using multi-temporal remote sensing data, this paper proposed a new approach to predict oil palm yield based on the normalized difference vegetation index (NDVI) and ensemble machine learning algorithm. ReliefF algorithm with linear projection was employed to select the best combination of spectral indices in oil palm discrimination. Oil palm land cover was classified using random forest (RF) and modified AdaBoost algorithms. A time-series approach known as walk-forward validation was firstly introduced to train the model using the 2016-2019 data and the one-step prediction was performed for 2020 using RF and AdaBoost. Result of the study revealed that the RF model (RMSE = 0.384; MSE = 0.148; MAE = 0.147) outperformed the AdaBoost model (RMSE = 0.410; MSE = 0.168; MAE = 0.176). Our research has demonstrated the value of detailed mapping and subsequent yield prediction by developing a novel approach utilising time-series satellite imagery, ensemble machine learning, and NDVI, which will assist decision-makers in managing their practices related to oil palm.

Efficient Intrusion Detection System for IoT Environment

These days, the Internet is subjected to a variety of attacks that can harm network devices or allow attackers to steal the most sensitive data from these devices. IoT environment provides new perspective and requirements for Intrusion detection due to its heterogeneity. This paper proposes a newly developed Intrusion Detection System (IDS) that relies on machine learning and deep learning techniques to identify new attacks that existed systems fail to detect in such an IoT environment. The paper experiments consider the benchmark dataset ToN_IoT that includes IoT services telemetry, Windows, Linux operating system, and network traffic. Feature selection is an important process that plays a key role in building an efficient IDS. A new feature selection module has been introduced to the IDS; it is based on the ReliefF algorithm which outputs the most essential features. These extracted features are fed into some selected machine learning and deep learning models. The proposed ReliefF-based IDSs are compared to the existed IDSs based correlation function. The proposed ReliefF-based IDSs model outperforms the previous IDSs based correlation function models. The Medium Neural Network model, Weighted KNN model, and Fine Gaussian SVM model have an accuracy of 98.39 %, 98.22 %, and 97.97 %, respectively.

A Novel Convolutional Neural Networks-Fused Shallow Classifier for Breast Cancer Detection

This paper proposes a fused methodology based upon convolutional neural networks and a shallow classifier to diagnose and differentiate breast cancer between malignant lesions and benign lesions. First, various pre-trained convolutional neural networks are used to calculate the features of breast ultrasonography (BU) images. Then, the computed features are used to train the different shallow classifiers like the tree, naïve Bayes, support vector machine (SVM), k-nearest neighbors, ensemble, and neural network. After extensive training and testing, the DenseNet-201, MobileNet-v2, and ResNet-101 trained SVM show high accuracy. Furthermore, the best BU features are merged to increase the classification accuracy at the cost of high computational time. Finally, the feature dimension reduction ReliefF algorithm is applied to address the computational complexity issue. An online publicly available dataset of 780 BU images is utilized to validate the proposed approach. The dataset was further divided into 80 and 20 percent ratios for training and testing the models. After extensive testing and comprehensive analysis, it is found that the DenseNet-201 and MobileNet-v2 trained SVM has an accuracy of 90.39% and 94.57% for the original and augmented BU images online dataset, respectively. This study concluded that the proposed framework is efficient and can easily be implemented to help and reduce the workload of radiologists/doctors to diagnose breast cancer in female patients.

A Hybrid Deep Features PSO-ReliefF Based Classification of Brain Tumor

With technological advancements, deep machine learning can assist doctors in identifying the brain mass or tumor using magnetic resonance imaging (MRI). This work extracts the deep features from 18-pre-trained convolutional neural networks (CNNs) to train the classical classifiers to categorize the brain MRI images. As a result, DenseNet-201, EfficientNet-b0, and DarkNet-53 deep features trained support vector machine (SVM) model shows the best accuracy. Furthermore, the ReliefF method is applied to extract the best features. Then, the fitness function is defined to select the number of nearest neighbors of ReliefF algorithm and feature vector size. Finally, the particle swarm optimization algorithm minimizes the fitness function to determine the optimal feature vector for model training. The proposed approach is validated by using the available online dataset. The proposed approach enhances the classification accuracy to 97.1% using the optimal concatenated deep features of DenseNet-201and DarkNet-53. Therefore, owing to the high accuracy of the proposed approach, it can be helpful to use real-time applications in the future.

Feature Selection and Deep Learning for Deterioration Prediction of the Bridges

Bridge deterioration is inevitable in service, and the inspection and maintenance of bridges are needed to ensure structural integrity. To make cost-effective inspection plans, bridge management departments need degradation models to predict future condition ratings of bridges. Although there have been studies on bridge degradation, the input features of models are selected mostly based on engineering experience, and no effective method has been proposed. Meanwhile, most models based on machine learning (ML) and deep learning (DL) only predict the degradation of bridges in a single year and cannot cover a complete inspection cycle (usually 2 years), providing limited decision support for the transportation departments. Besides, more accurate models are needed to predict the degradation trend of bridges. In response to these problems, an improved ReliefF algorithm is proposed to select features of bridges in the paper. Meanwhile, a new degradation model combining recurrent neural network (RNN) and convolutional neural network (CNN) is established. Historical data of bridges in the US state of Texas from 1992 to 2019 are employed to verify the proposed methods. The result shows that the improved ReliefF algorithm selects the appropriate feature set as the input of the prediction model, and the model accurately predicts the future condition ratings of bridges in the next 3–4 years. The research is beneficial to infrastructure management departments in allocating bridge inspection and maintenance resources reasonably.

Intelligent algorithm for detection of dengue using mobilenetv2‐based deep features with lymphocyte nucleus

AbstractDengue is a vector‐borne disease that is highly endemic in countries located in tropical regions. It can cause severe complications and can even lead to death in the case of delayed diagnosis. Detection of dengue is done by manually examining the platelets and lymphocytes in Leishman's stained peripheral blood smear (PBS) images. PBS examination is considered the gold standard for diagnosing various haematological disorders. However, manual analysis of the PBS is labour‐intensive, tedious, and time‐consuming, requiring a skilled and experienced haematologist. Today, soft computing methods and artificial intelligence have made their way into every science and technology branch. One such area which has adopted this approach is digital pathology, for automatically identifying and diagnosing various diseases. The main objective of this work was to design an intelligent algorithm to classify normal and dengue patients with the help of digital microscopic blood smear images. A total of 94 normal and dengue‐infected PBSs were acquired at a magnification of 100×. Grey‐level segmentation based on Otsu's thresholding was used for the segmentation of the nucleus of lymphocytes. Distinct features from the nucleus that differentiated infected cells from normal were extracted using a pre‐trained MobileNetV2 network and local binary pattern. Significant features were selected using the ReliefF algorithm. Subsequently, these features were fed to the support vector machine (SVM) classifier. Our proposed system gave an accuracy, sensitivity, and specificity of 95.74%, 98.14%, and 92.50%, respectively. Hence, the developed intelligent model with deep and hand‐crafted features can be valuable for dengue diagnosis.

EEG Electrode Selection for a Two-Class Motor Imagery Task in a BCI Using fNIRS Prior Data.

This study investigated the possibility of using functional near infrared spectroscopy (fNIRS) during right- and left-hand motor imagery tasks to select an optimum set of electroencephalography (EEG) electrodes for a brain computer interface. fNIRS has better spatial resolution allowing areas of brain activity to more readily be identified. The ReliefF algorithm was used to identify the most reliable fNIRS channels. Then, EEG electrodes adjacent to those channels were selected for classification. This study used three different classifiers of linear and quadratic discriminant analyses, and support vector machine to examine the proposed method.Clinical Relevance- Reducing the number of sensors in a BCI makes the system more usable for patients with severe disabilities.