Search

Objectives: To develop a robust algorithm for estimating ultrasonic axial transmission velocity from neonatal tibial bone, and to investigate the relationships between ultrasound velocity and neonatal anthropometric measurements as well as clinical biochemical markers of skeletal health. Methods: This study presents an unsupervised learning approach for the automatic detection of first arrival time and estimation of ultrasonic velocity from axial transmission waveforms, which potentially indicates bone quality. The proposed method combines the ReliefF algorithm and fuzzy C‐means clustering. It was first validated using an in vitro dataset measured from a Sawbones phantom. It was subsequently applied on in vivo signals collected from 40 infants, comprising 21 males and 19 females. The extracted neonatal ultrasonic velocity was subjected to statistical analysis to explore correlations with the infants' anthropometric features and biochemical indicators. Results: The results of in vivo data analysis revealed significant correlations between the extracted ultrasonic velocity and the neonatal anthropometric measurements and biochemical markers. The velocity of first arrival signals showed good associations with body weight (ρ = 0.583, P value <.001), body length (ρ = 0.583, P value <.001), and gestational age (ρ = 0.557, P value <.001). Conclusion: These findings suggest that fuzzy C‐means clustering is highly effective in extracting ultrasonic propagating velocity in bone and reliably applicable in in vivo measurement. This work is a preliminary study that holds promise in advancing the development of a standardized ultrasonic tool for assessing neonatal bone health. Such advancements are crucial in the accurate diagnosis of bone growth disorders. [ABSTRACT FROM AUTHOR]

The high commercial value of camellia oil entails the development of a rapid and accurate method for identifying camellia oil adulteration. In this study, the feasibility of using low-field nuclear magnetic resonance (LF-NMR) relaxation characteristics and support vector machine (SVM) to detect adulteration in camellia oil was investigated. The LF-NMR relaxation characteristics of raw and oxidized oils of camellia and three other species and their binary blends were compared. Furthermore, principal component analysis was carried out and then an SVM multi-classifier with a binary tree structure was designed. After feature screening by the ReliefF algorithm, an SVM model for identifying adulteration in camellia oil was established and evaluated. The results showed that the LF-NMR relaxation characteristics of oil samples were affected by oil type, oxidation degree and blending ratio. The SVM multi-classification model with 9 features exhibited the best performance, with an accuracy of 90.77%. Additionally, the average recall, precision and F1 score for camellia oil, blending type and ratio were 90.87%, 90.83% and 0.90, respectively. This study indicated that the SVM model based on LF-NMR relaxation characteristics could be employed for identifying adulteration in camellia oil.

Copyright of Shipin Kexue/ Food Science is the property of Food Science Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The current of the residential series arc fault is affected by the load type, and the fault feature change is not obvious and contains noise. Therefore, the extraction of fault features will affect the arc fault detection results. To solve this problem, an improved salp swarm optimization algorithm combined with variational mode decomposition is proposed to extract the characteristics of current signal, improve the decomposition effect of current signal, and construct a dataset that can fully reflect the characteristics of arc fault. The ReliefF algorithm is designed to combine minimum redundancy maximum relevance to reduce the feature dimension and eliminate redundancy. Finally, the random forest model is used to diagnose the fault, which can quickly detect the fault and does not cause overfitting. Experiments based on the self–built sample set prove that the arc fault can be quickly detected under different acquisition frequencies and noise environments, and the detection rate is more than 95%.

Bridges are a critical component of transportation infrastructure, playing a vital role in connectivity. The safe operation of bridges demands significant resource and capital investment, particularly as the operation phase is the most extended period in a bridge's life cycle. Therefore, the efficient allocation of resources and funds is crucial for the maintenance and repair of bridges. This study addresses the need to predict changes in bridge condition over time. The commonly used state-based Markov chain method for bridge condition rating prediction is straightforward but limited by its assumptions of homogeneity and memorylessness. To improve upon this, we propose a novel method that integrates an Elman neural network with a Markov chain to predict the bridge condition rating. Initially, the ReliefF algorithm conducts a sensitivity analysis on bridge features to obtain the importance ranking of these features that affect the bridge condition. Next, six significant features are selected for data classification: bridge age, average daily truck traffic volume, material type, skew angle between bridges and roads, bridge deck structure type, and bridge type. The Elman neural network is then trained to train a prediction model for bridge condition ratings using the classified data, which can predict the condition levels of bridges. The Markov chain's transition probability matrix is derived using a genetic algorithm to match the deterioration curve predicted by the Elman neural network. This proposed method, when applied to actual bridge data, demonstrates its effectiveness as evidenced by the condition rating of an actual bridge. [ABSTRACT FROM AUTHOR]

The tool condition during the shearing process of iron-based nanocrystalline alloy strips was critical to ensure the processing quality. To address the problem of tool wear monitoring during shear processing of iron-based nanocrystalline alloy strips, a shear tool wear online monitoring method based on acoustic emission signal was proposed. First, the acoustic emission monitoring equipment was built to determine the corresponding parameters, and the raw acoustic emission signal was collected for pre-processing to obtain the signal of shear processing stage for subsequent processing. Then, the relationship between shear tool wear and strip quality changes during the shear processing was studied, and according to the acoustic emission signal obtained during the shear processing, the time domain, frequency domain and time-frequency domain features were extracted, and the relationship between the obtained features and tool wear was analyzed. The features with good correlation were obtained by using ReliefF and principal component analysis (PCA) algorithms for feature selection and dimensionality reduction. Finally, based on the selected features, a support vector machines (SVM) artificial intelligence model was constructed to identify the shear tool wear stages. The results show that: with the increase of tool wear, the strip quality decreases, and there is a correspondence between the acoustic emission signal feature values and tool wear. Using ReliefF-PCA-SVM model can achieve 95.56% classification accuracy, which can effectively monitor tool wear during shear processing online. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Drainage & Irrigation Machinery Engineering / Paiguan Jixie Gongcheng Xuebao is the property of Editorial Department of Drainage & Irrigation Machinery Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

One of the most dangerous diseases in the world is a brain tumor. A brain tumor destroys healthy tissue in the brain and then multiplies abnormally, causing increased internal pressure in the skull. This can lead to death if not diagnosed early. Magnetic Resonance Imaging (MRI) is a diagnostic method that is frequently used in soft tissues and gives successful results. In this study, a brain tumor was automatically detected from MR images. For feature extraction, a pre-trained Convolutional Neural Network (CNN) model named MobilenetV2 was used. Then, the ReliefF algorithm was used for feature selection. The features extracted with MobileNetV2 and the features selected with the ReliefF algorithm are given separately to the classifiers and the system performance is tested. As a result of experimental studies, it was seen that the highest performance was obtained with the combination of MobileNetV2 feature extraction, ReliefF algorithm feature selection, and KNN classifier.

Bridges are a critical component of transportation infrastructure, playing a vital role in connectivity. The safe operation of bridges demands significant resource and capital investment, particularly as the operation phase is the most extended period in a bridge’s life cycle. Therefore, the efficient allocation of resources and funds is crucial for the maintenance and repair of bridges. This study addresses the need to predict changes in bridge condition over time. The commonly used state-based Markov chain method for bridge condition rating prediction is straightforward but limited by its assumptions of homogeneity and memorylessness. To improve upon this, we propose a novel method that integrates an Elman neural network with a Markov chain to predict the bridge condition rating. Initially, the ReliefF algorithm conducts a sensitivity analysis on bridge features to obtain the importance ranking of these features that affect the bridge condition. Next, six significant features are selected for data classification: bridge age, average daily truck traffic volume, material type, skew angle between bridges and roads, bridge deck structure type, and bridge type. The Elman neural network is then trained to train a prediction model for bridge condition ratings using the classified data, which can predict the condition levels of bridges. The Markov chain’s transition probability matrix is derived using a genetic algorithm to match the deterioration curve predicted by the Elman neural network. This proposed method, when applied to actual bridge data, demonstrates its effectiveness as evidenced by the condition rating of an actual bridge.

As a reflection of the scholar's mastery of basic theories and professional knowledge, the dissertation is an important yardstick for measuring the level of scientific research. At present, the problem of academic misconduct is becoming increasingly prominent, which is not only related to personal academic ethics, but also related to the overall development of the national academic and scientific research field. In the traditional method of evaluating the quality of papers, it is mainly based on the evaluation experts' comments and scores. However, there are cases that the evaluation experts' comments and scores are inconsistent in practice. To address this problem, we proposed a paper quality consistency detection model based on the nearest neighbor analysis dimensionality reduction algorithm. Compared with other traditional models, the experimental results show that the detection accuracy of XGBoost model after dimensionality reduction using nearest neighbor analysis algorithm reaches 85.81%.

Schizophrenia is a chronic mental disorder that impairs a person's thinking capacity, feelings and emotions, behavioural traits, etc., Emotional distortions, delusions, hallucinations, and incoherent speech are all some of the symptoms of schizophrenia, and cause disruption of routine activities. Computer-assisted diagnosis of schizophrenia is significantly needed to give its patients a higher quality of life. Hence, an improved adaptive neuro-fuzzy inference system based on the Hybrid Grey Wolf-Bat Algorithm for accurate prediction of schizophrenia from multi-channel EEG signals is presented in this study. The EEG signals are pre-processed using a Butterworth band pass filter and wICA initially, from which statistical, time-domain, frequency-domain, and spectral features are extracted. Discriminating features are selected using the ReliefF algorithm and are then forwarded to ANFIS for classification into either schizophrenic or normal. ANFIS is optimized by the Hybrid Grey Wolf-Bat Algorithm (HWBO) for better efficiency. The method is experimented on two separate EEG datasets-1 and 2, demonstrating an accuracy of 99.54% and 99.35%, respectively, with appreciable F1-score and MCC. Further experiments reveal the efficiency of the Hybrid Wolf-Bat algorithm in optimizing the ANFIS parameters when compared with traditional ANFIS model and other proven algorithms like genetic algorithm-ANFIS, particle optimization-ANFIS, crow search optimization algorithm-ANFIS and ant colony optimization algorithm-ANFIS, showing high R2 value and low RSME value. To provide a bias free classification, tenfold cross validation is performed which produced an accuracy of 97.8% and 98.5% on the two datasets respectively. Experimental outcomes demonstrate the superiority of the Hybrid Grey Wolf-Bat Algorithm over the similar techniques in predicting schizophrenia. [ABSTRACT FROM AUTHOR]

Feature selection has become popular in data mining tasks currently for its ability of improving the performance of the algorithm and gaining more information about the dataset. Although the firefly algorithm is a well-performed heuristic algorithm, there is still much room for improvement as to the feature selection problem. In this research, an improved firefly algorithm designed for feature selection with the ReliefF-based initialization method and the weighted voting mechanism is proposed. First of all, a feature grouping initialization method that combines the results of the ReliefF algorithm and the cosine similarity is designed to take place of random initialization. Then, the direction of the firefly is modified to move toward the optimal solution. Finally, inspired by the ensemble algorithm, a weighted voter is proposed to build recommended positions for fireflies, which is also integrated with the elite crossover operator and the mutation operator to improve the diversity of the population. Selected from the mixed swarm, a new population is constructed to replace the original population in the next stage. To verify the effectiveness of the algorithm proposed in this paper, 18 datasets are utilized and 9 comparison algorithms (e.g., Black Hole Algorithm, Grey Wolf Optimizer and Pigeon Inspired Optimizer) from state-of-the-art related works are selected for the simulating experiments. The experimental results demonstrate the superiority of the proposed algorithm applied to the feature selection problem. [ABSTRACT FROM AUTHOR]

In order to improve the recall and precision of image retrieval, a visual retrieval method of digital media image features based on active noise is proposed. In this paper, Canny algorithm is used to detect the edge of the image to get the feature information of the edge of the image. The RGB color space model is used to decompose the color information of the image, and the color characteristic information of the image is obtained. Extracting image features to retain the useful information contained in the image as much as possible; In order to facilitate the visual retrieval of image features, reduce the retrieval complexity and further fuse image features, FPCA and ReliefF algorithms are used to reduce the dimensionality of image features, and the active noise control method is used to sharpen the image. After processing the results, a digital media image feature visual retrieval platform is established to realize the visual retrieval of digital media image features. Experimental results show that the proposed method has a high accuracy of over 80% and a high recall rate of 95.2%. [ABSTRACT FROM AUTHOR]

As a reflection of the scholar's mastery of basic theories and professional knowledge, the dissertation is an important yardstick for measuring the level of scientific research. At present, the problem of academic misconduct is becoming increasingly prominent, which is not only related to personal academic ethics, but also related to the overall development of the national academic and scientific research field. In the traditional method of evaluating the quality of papers, it is mainly based on the evaluation experts' comments and scores. However, there are cases that the evaluation experts' comments and scores are inconsistent in practice. To address this problem, we proposed a paper quality consistency detection model based on the nearest neighbor analysis dimensionality reduction algorithm. Compared with other traditional models, the experimental results show that the detection accuracy of XGBoost model after dimensionality reduction using nearest neighbor analysis algorithm reaches 85.81%. [ABSTRACT FROM AUTHOR]

The automated magnetic resonance imaging (MRI) processing techniques are gaining more importance in Alzheimer disease (AD) recognition, because it effectively diagnosis the pathology of the brain. Currently, computer aided diagnosis based on image analysis is an emerging tool to support AD diagnosis. In this research study, a new system is developed for enhancing the performance of AD recognition. Initially, the brain images were acquired from three online datasets and one real-time dataset such as AD Neuroimaging Initiative (ADNI), Minimal Interval Resonance Imaging in AD (MIRIAD), and Open Access Series of Imaging Studies (OASIS) and National Institute of Mental Health and Neuro Sciences (NIMHANS). Then, adaptive histogram equalization (AHE) and grey wolf optimization based clustering algorithm (GWOCA) were applied for denoising and segmenting the brain tissues; grey matter (GM), cerebro-spinal fluid (CSF), and white matter (WM) from the acquired images. After segmentation, the feature extraction was performed by utilizing dual tree complex wavelet transform (DTCWT), local ternary pattern (LTP) and Tamura features to extract the feature vectors from the segmented brain tissues. Then, ReliefF methodology was used to select the active features from the extracted feature vectors. Finally, the selected active feature values were classified into three classes [AD, normal and mild cognitive impairment (MCI)] utilizing deep neural network (DNN) classifier. From the simulation result, it is clear that the proposed framework achieved good performance in disease classification and almost showed 2.2–6% enhancement in accuracy of all four datasets. [ABSTRACT FROM AUTHOR]

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. HIGHLIGHT By comparing the prediction results of PSO-BP neural network and AdaBoost-BP neural network, it is found that the AdaBoost-BP evaluation model has higher accuracy, better stability and better application value.;

Abstract Background Chronic obstructive pulmonary disease (COPD) is a chronic respiratory disease that seriously threatens people’s health, with high morbidity and mortality worldwide. At present, the clinical diagnosis methods of COPD are time-consuming, invasive, and radioactive. Therefore, it is urgent to develop a non-invasive and rapid COPD severity diagnosis technique suitable for daily screening in clinical practice. Results This study established an effective model for the preliminary diagnosis of COPD severity using lung sounds with few channels. Firstly, the time-frequency-energy features of 12 channels lung sounds were extracted by Hilbert–Huang transform. And then, channels and features were screened by the reliefF algorithm. Finally, the feature sets were input into a support vector machine to diagnose COPD severity, and the performance with Bayes, decision tree, and deep belief network was compared. Experimental results show that high classification performance using only 4-channel lung sounds of L1, L2, L3, and L4 channels can be achieved by the proposed model. The accuracy, sensitivity, and specificity of mild COPD and moderate + severe COPD were 89.13%, 87.72%, and 91.01%, respectively. The classification performance rates of moderate COPD and severe COPD were 94.26%, 97.32%, and 89.93% for accuracy, sensitivity, and specificity, respectively. Conclusion This model provides a standardized evaluation with high classification performance rates, which can assist doctors to complete the preliminary diagnosis of COPD severity immediately, and has important clinical significance.

The frequent outbreak of algal bloom in inland lakes has seriously affected the safety of surface water environment,and has brought great obstacles to the construction of ecological civilization in China.Taking full advantage of SAR(Synthetic Aperture Radar) remote sensing technologies,large-scale and periodic algal bloom discrimination and monitoring can be realized.It is of great practical significance for the protection and supervision of water environment.Based on the research and application of SAR remote sensing target recognition technology,this paper proposes an algal bloom discrimination method with feature optimization.After the in-depth analysis and extraction of algal bloom image features,the ReliefF algorithm is used to obtain the optimal feature set,which consists of 10 features from all 22 algal bloom features.And then,the BP (Back Propagation) neural network is as the classifier of this discrimination method to carry out a number of comparative experiments.The overall accuracy of the proposed method is 81.39%,which is 19.38% higher than that before optimization.The experimental results show that the optimal feature set can not only greatly reduce the algorithm complexity,but also effectively improve the discrimination accuracy of algal bloom,which has practical value for further promotion.

This study proposes a novel glaucoma identification system from fundus images through the deep belief network (DBN) optimized by the elephant-herding optimization (EHO) algorithm. Initially, the input image undergoes the preprocessing steps of noise removal and enhancement processes, followed by optical disc (OD) and optical cup (OC) segmentation and extraction of structural, intensity, and textural features. Most discriminative features are then selected using the ReliefF algorithm and passed to the DBN for classification into glaucomatous or normal. To enhance the classification rate of the DBN, the DBN parameters are fine-tuned by the EHO algorithm. The model has experimented on public and private datasets with 7280 images, which attained a maximum classification rate of 99.4%, 100% specificity, and 99.89% sensitivity. The 10-fold cross validation reduced the misclassification and attained 98.5% accuracy. Investigations proved the efficacy of the proposed method in avoiding bias, dataset variability, and reducing false positives compared to similar works of glaucoma classification. The proposed system can be tested on diverse datasets, aiding in the improved glaucoma diagnosis. [ABSTRACT FROM AUTHOR]

Machine learning (ML) techniques have been used to solve real-world problems for decades. In the field of medical sciences, these approaches have been found to be useful in the diagnosis and prognosis of a variety of medical disorders. However, when dealing with voluminous, inconsistent, and higher-dimensional data, conventional ML approaches have failed to deliver the expected results. Researchers have suggested hybrid solutions to resolve these problems, which have been found to be more effective than conventional methods because these systems integrate their merits while reducing their drawbacks. In the current research article, hybrid model has been presented by coupling feature optimization with prediction approach. The proposed hybrid model has two stages: the first involves implementing the ReliefF Algorithm for optimum feature selection in erythemato-squamous diseases, and the second involves implementing k-nearest neighbor (KNN) for prediction of those selected optimum features. The experimentation was carried out on bench mark dataset for erythemato-squamous diseases. The presented hybrid model was also assessed with conventional KNN approach based on various metrics such as classification accuracy, kappa coefficient, recall, precision, and f-score. [ABSTRACT FROM AUTHOR]

Background: Chronic obstructive pulmonary disease (COPD) is a chronic respiratory disease that seriously threatens people's health, with high morbidity and mortality worldwide. At present, the clinical diagnosis methods of COPD are time-consuming, invasive, and radioactive. Therefore, it is urgent to develop a non-invasive and rapid COPD severity diagnosis technique suitable for daily screening in clinical practice.Results: This study established an effective model for the preliminary diagnosis of COPD severity using lung sounds with few channels. Firstly, the time-frequency-energy features of 12 channels lung sounds were extracted by Hilbert-Huang transform. And then, channels and features were screened by the reliefF algorithm. Finally, the feature sets were input into a support vector machine to diagnose COPD severity, and the performance with Bayes, decision tree, and deep belief network was compared. Experimental results show that high classification performance using only 4-channel lung sounds of L1, L2, L3, and L4 channels can be achieved by the proposed model. The accuracy, sensitivity, and specificity of mild COPD and moderate + severe COPD were 89.13%, 87.72%, and 91.01%, respectively. The classification performance rates of moderate COPD and severe COPD were 94.26%, 97.32%, and 89.93% for accuracy, sensitivity, and specificity, respectively.Conclusion: This model provides a standardized evaluation with high classification performance rates, which can assist doctors to complete the preliminary diagnosis of COPD severity immediately, and has important clinical significance. [ABSTRACT FROM AUTHOR]

Aiming at the high dimensional problem of pathological image morphometric features and the small amount of applied samples in medical field, this paper presents the ReliefF-HEPSO head and neck cancer pathological image feature selection algorithm. The algorithm constructs a framework of multi-level dimensionality reduction. Firstly, according to the correlation of features and categories, the ReliefF algorithm is used to determine different feature weights to achieve initial dimensionality reduction. Secondly, the evolutionary neural strategy (ENS) is used to enrich the particle populations diversity of the binary particle swarm optimization (BPSO). A hybrid binary evolutionary particle swarm optimization (HEPSO) algorithm is proposed to automatically search for the best feature subsets of candidate feature subsets. Compared with 7 feature selection algorithms, the experiment proves that the algorithm can effectively screen out the morphological features of high correlation pathology images, achieve rapid dimensionality reduction, and obtain higher classification performance with fewer features.

This paper proposes a condition monitoring method based on Dynamic Related ReliefF-SFA (DRRSFA), which solves the problem of huge variable dimensions and strong autocorrelation in process monitoring. First, the samples are mapped into a new space, and the slow projection components (SPCs) of the samples are calculated. The SPCs not only considers the autocorrelation between the variables, but also characterizes the inherent properties of the whole system. Second, the feature selection algorithm ReliefF is used to select the more weighted features, which is called the principal components(PCs) to achieve dimensionality reduction. Then the corresponding statistics and control limits are calculated based on the obtained PCs. Finally, the process monitoring using the proposed algorithm is performed by testing a numerical example and the actual production process data, and the results show the effectiveness of the proposed method.

Micro-expressions are deliberate or unconscious movements of people's psychological activities, reflecting the transient facial true expressions. Previous works focus on the whole face for micro-expressions recognition. These methods can extract a number of feature vectors which are relevant or irrelevant to the micro-expressions recognition. Besides, the high-dimension feature vectors can result in longer computational time and increased computational complexity. In order to address these problems, we propose a new framework which combines the local-region division and the feature selection. Based on the proposed framework, the original images can retain more efficient regions and filter out the invalid components of feature vectors. Specifically, with the joint efforts of the facial deformation identification model and facial action coding system, the global region is divided into seven local regions with their corresponding actions units. The ReliefF algorithm is used to select effective components of feature vectors and reduce the dimension. To evaluate the proposed framework, we conduct experiments on both the Chinese Academy of Sciences Micro-expression II Database and Spontaneous Micro-expression Database with Leave-One-Subject-Out Cross Validation method. The results show that the performance in local combined regions outperforms its counterpart in the global region, and the recognition accuracy is further improved with the combination of feature selection.

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Real-time explosive detectors must be developed to facilitate the rapid implementation of appropriate protective measures against terrorism. We report a simple yet efficient methodology to classify three explosives and three non-explosives by using laser-induced breakdown spectroscopy. However, the similarity existing among the spectral emissions collected from the explosives resulted in the difficulty of separating samples. We calculated the weights of lines by using the ReliefF algorithm and then selected six line regions that could be identified from the arrangement of weights to calculate the area of each line region. A multivariate statistical method involving support vector machines was followed for the construction of the classification model. Several models were constructed using full spectra, 13 lines, and 100 lines selected by the arrangement of weights and areas of the selected line regions. The highest correct classification rate of the model reached 100% by using the six line regions.

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Currently, hand gesture recognition becomes a promising system for the digital entertainment field due to the recent development of sensor innovations and machine learning. However, hand gesture recognition is a challenging task in most of the existing models, due to background clutter, motion blur, illumination variations, and occlusions. In this research, a dynamic hand gesture recognition system is proposed to improve the performance of hand gesture recognition. At first, the normalization method is used to enhance the visibility level of the gesture images which are collected from the Indian sign language dataset. Then, semi vectorial multilevel segmentation method is employed to segment the exact gesture regions from the normalized images. Further, improved reliefF algorithm and K-nearest neighbour classifiers are used to select the optimal features and to classify the 16 gesture classes or symbols. In the experimental phase, the proposed improved reliefF- K-nearest neighbour model performance is analysed in light of Matthew’s correlation coefficient, accuracy, sensitivity, specificity, and f-score. For overall 16 distinct alphabets; A, B, D, E, F, G, H, K, P, R, T, U, W, X, Y, Z, the proposed improved reliefF-K-nearest neighbour model achieves average accuracy of 98.95%. Hence, the proposed improved reliefF-K-nearest neighbour model showed maximum of 7.97% and minimum of 0.15% improvement in recognition accuracy compared to k means-neural network model, and discriminant correlation analysis based unimodal feature-level fusion model. [ABSTRACT FROM AUTHOR]

Data mining is one of the most important applications of machine learning. In machine learning algorithms, the fusion kernel principle component analysis (KPCA) and support vector machine (SVM) algorithm is used in complex data classification. To solve the problem that the fusion KPCA and SVM algorithm does not have promising classification performance, the SVM based on a feature selection algorithm for differential space fusion (DSF-FS) is proposed. First, the original data is processed to obtain differential space data by principle component analysis (PCA), and the KPCA algorithm is performed respectively on the original data and differential space data to get the differential space fusion features. Second, the ReliefF algorithm is used to get the weight of features, and the optimal feature combination is selected by a preliminary classification evaluation metric. Third, the SVM algorithm is used to classify the dimensionality reduction data. Finally, some experimental results on the five UCI datasets show that the proposed DSF-FS algorithm can not only improve the classification accuracy, but it can also reduce the computational complexity of the classification process. Moreover, the DSF-FS algorithm can be successfully applied in diabetic fundus image classification, and the encouraging results further demonstrate its strong feasibility and applicability.

The decentralized weighted ReliefF-PCA (DWRPCA) method is proposed to improve the performance of principal component analysis (PCA) for fault detection. The improved ReliefF-PCA algorithm is used to select the principal components instead of the traditional cumulative percent variance (CPV) criterion, so that the important information contained in the small variance is considered. The sub-models for different types of faults which are being considered the influence weights of process variables and faults are established respectively to obtain the decentralized weighted model. The Bayesian Information Criterion is adopted to integrate different types of faults for a unified monitoring index. The case study of a numerical example and the Tennessee Eastman process illustrate the effectiveness of the proposed method.

The cuffless blood pressure (BP) measurement allows for frequent measurement without discomfort to the patient compared to the cuff inflation measurement. With the availability of a large dataset containing physiological waveforms, now it is possible to use them through different learning algorithms to produce a relationship with changes in BP. In this paper, a novel cuffless noninvasive blood pressure measurement technique has been proposed using optimized features from electrocardiogram and photoplethysmography based on multivariate symmetric uncertainty (MSU). The technique is an improvement over other contemporary methods due to the inclusion of feature optimization depending on both linear and nonlinear relationships with the change of blood pressure. MSU has been used as a selection criterion with algorithms such as the fast correlation and ReliefF algorithms followed by the penalty-based regression technique to make sure the features have maximum relevance as well as minimum redundancy. The result from the technique was compared with the performance of similar techniques using the MIMIC-II dataset. After training and testing, the root mean square error (RMSE) comes as 5.28 mmHg for systolic BP and 5.98 mmHg for diastolic BP. In addition, in terms of mean absolute error, the result improved to 4.27 mmHg for SBP and 5.01 for DBP compared to recent cuffless BP measurement techniques which have used substantially large datasets and feature optimization. According to the British Hypertension Society Standard (BHS), our proposed technique achieved at least grade B in all cumulative criteria for cuffless BP measurement.

Convolutional neural networks (CNNs) have recently emerged as a popular topic for machine learning in various academic and industrial fields. It is often an important problem to obtain a dataset with an appropriate size for CNN training. However, the lack of training data in the case of remote image research leads to poor performance due to the overfitting problem. In addition, the back-propagation algorithm used in CNN training is usually very slow and thus requires tuning different hyper-parameters. In order to overcome these drawbacks, a new approach fully based on machine learning algorithm to learn useful CNN features from Alexnet, VGG16, VGG19, GoogleNet, ResNet and SqueezeNet CNN architectures is proposed in the present study. This method performs a fast and accurate classification suitable for recognition systems. Alexnet, VGG16, VGG19, GoogleNet, ResNet and SqueezeNet pretrained architectures were used as feature extractors. The proposed method obtains features from the last fully connected layers of each architecture and applies the ReliefF feature selection algorithm to obtain efficient features. Then, selected features are given to the support vector machine classifier with the CNN-learned features instead of the FC layers of CNN to obtain excellent results. The effectiveness of the proposed method was tested on the UC-Merced dataset. Experimental results demonstrate that the proposed classification method achieved an accuracy rate of 98.76% and 99.29% in 50% and 80% training experiment, respectively. [ABSTRACT FROM AUTHOR]

The diagnosis of the degree of differentiation of tumor cells can help physicians to make timely detection and take appropriate treatment for the patient's condition. In this study, the original dataset is clustered into two independent types by the Kohonen clustering algorithm. One type is used as the development sets to find correlation indicators and establish predictive models of differentiation, while the other type is used as the validation sets to test the correlation indicators and models. In the development sets, thirteen indicators significantly associated with the degree of differentiation of esophageal squamous cell carcinoma are found by the Kohonen clustering algorithm. Thirteen relevant indicators are used as input features and the degree of tumor differentiations is used as output. Ten classification algorithms are used to predict the differentiation of esophageal squamous cell carcinoma. Artificial bee colony-support vector machine (ABC-SVM) predicts better than the other nine algorithms, with an average accuracy of 81.5% for the 10-fold cross-validation. Based on logistic regression and ReliefF algorithm, five models with the greater merit for the degree of differentiation are found in the development sets. The AUC values of the five models are 0.672, 0.628, 0.630, 0.628, and 0.608 (P < 0.05). The AUC values of the five models in the validation sets are 0.753, 0.728, 0.744, 0.776, and 0.868 (P < 0.0001). The predicted values of the five models are constructed as the input features of ABC-SVM. The accuracy of the 10-fold cross-validation reached 82.0 and 86.5% in the development sets and the validation sets, respectively. [ABSTRACT FROM AUTHOR]

The quick and accurate picking of the first arrival on microseismic signals is one of the critical processing steps of microseismic monitoring. This study proposed a first arrival picking method for application to microseismic data with a low signal-to-noise ratio (SNR). This approach consisted of two steps: feature selection and clustering. First of all, the optimal feature was searched automatically using the ReliefF algorithm according to the weight distribution of the signal features, and without manual design. On that basis, a k-means clustering method was adopted to classify the microseismic data with symmetry (0–1), and the first arrival times were accurately picked. The proposed method was validated using the synthetic data with different noise levels and real microseismic data. The comparative study results indicated that the proposed method had obviously outperformed the classical STA/LTA and the k-means without feature selection. Finally, the microseismic localization of the first arrivals picked using the various methods were compared. The positioning errors were analyzed using box plots with symmetric effect, and those of the proposed method were the smallest, and stable (all of which were less than 0.5 m), which further verified the superiority of this study’s proposed method and its potential in processing complicated microseismic datasets.

Highlights • Aggregate acoustic and visual features for acoustic scene classification. • Investigate three feature selection methods for acoustic scene classification. • Compare time-frequency representations for visual feature extraction. Abstract Acoustic scene classification has gained great interests in recent years due to its diverse applications. Various acoustic and visual features have been proposed and evaluated. However, few studies have investigated acoustic and visual feature aggregation for acoustic scene classification. In this paper, we investigated various feature sets based on the fusion of acoustic and visual features. Specifically, acoustic features are directly extracted from the waveform: spectral centroid, spectral entropy, spectral flux, spectral roll-off, short-time energy, zero-crossing rate, and Mel-frequency Cepstral coefficients. For visual features, we calculate local binary pattern, histogram of gradients, and moments based on the audio scene time-frequency representation. Then, three feature selection algorithms are applied to various feature sets to reduce feature dimensionality: correlation-based feature selection, principal component analysis, and ReliefF. Experimental results show that our proposed system was able to achieve an accuracy improvement of 15.43% compared to the baseline system with the development set. When all development sets are used for training, the performance based on the evaluation set provided by the TUT Acoustic scene 2016 challenge is 87.44%, which is the fourth best among all non-neural network systems. [ABSTRACT FROM AUTHOR]

Abstract With the exponential growth of global photovoltaic (PV) power capacity, it is essential to monitor, detect and diagnose the faults in PV arrays for optimal operation. This paper presents an improved rotation forest (RoF) algorithm classifiers ensemble hybridized with extreme learning machine (ELM) for fault diagnosis of PV arrays, which mainly consists of feature selection and classification. In the feature selection step, all the attributes are ranked by the ReliefF algorithm and the top-ranked attributes are chosen to create the new training data subset. In the classification step, the base classifier decision tree of the RoF is replaced by the extreme learning machine to form a new hybrid RoF-ELM ensemble classifier. In the RoF-ELM algorithm, the feature space is first split into several subspaces and the best number of feature subsets is found through the traversal search method. Then, the bootstrap algorithm is employed to carry out bootstrap resampling for each feature subspace, and the principal component analysis (PCA) is then used to transform the resampled samples. Finally, the ELM base classifier is exploited to build each classification model and the final decision is determined by the simple voting approach. By combining the RoF ensemble method with the ELM classifier, the proposed RoF-ELM algorithm not only overcomes the overfitting problem of the basic RoF algorithm, but also improves the generalization ability of the basic ELM. In order to experimentally verify the proposed approach, different types and levels of faults have been created in a laboratory small scale grid-connected PV power system to obtain the fault data samples. Experimental results demonstrate that the RoF-ELM can achieve higher diagnosis accuracy and reliability compared to the basic RoF and ELM algorithms. [ABSTRACT FROM AUTHOR]

Aiming at the multi-classification problem of DNA microarray data with the characteristic of high dimension and small sample, this paper proposed a feature gene selection algorithm based on ReliefF and ant colony optimization( ReFACO). The method adopted ReliefF algorithm to evaluate the feature weights,and selected the irrelevant genes based on the threshold, introduced an improved ant colony algorithm to find the optimal subset of genes in the process of iteration and improvement, used classical classification algorithms to classify and identify the data set, dimensions of which had been reduced. Experimental results show that the method can eliminate irrelevant and redundant genes effectively, and achieve a higher classification performance with less characteristic genes. [ABSTRACT FROM AUTHOR]

Chronic liver diseases are fifth leading cause of fatality in developing countries. Early diagnosis is important for timely treatment and to salvage life. Ultrasound imaging is frequently used to examine abnormalities of liver. However, ambiguity lies in visual interpretation of liver stages on ultrasound images. This difficult visualization problem can be solved by analysing extracted textural features from images. Grey-level difference matrix, a texture feature extraction method, can provide information about roughness of liver surface, sharpness of liver borders and echotexture of liver parenchyma. In this article, the behaviour of variants of grey-level difference matrix in characterizing liver stages is investigated. The texture feature sets are extracted by using variants of grey-level difference matrix based on two, three, five and seven neighbouring pixels. Thereafter, to take the advantage of complementary information from extracted feature sets, feature fusion schemes are implemented. In addition, hybrid feature selection (combination of ReliefF filter method and sequential forward selection wrapper method) is used to obtain optimal feature set in characterizing liver stages. Finally, a computer-aided system is designed with the optimal feature set to classify liver health in terms of normal, chronic liver, cirrhosis and hepatocellular carcinoma evolved over cirrhosis. In the proposed work, experiments are performed to (1) identify the best approximation of derivative (forward, central or backward); (2) analyse the performance of individual feature sets of variants of grey-level difference matrix; (3) obtain optimal feature set by exploiting the complementary information from variants of grey-level difference matrix and (4) analyse the performance of proposed method in comparison with existing feature extraction methods. These experiments are carried out on database of 754 segmented regions of interest formed by clinically acquired ultrasound images. The results show that classification accuracy of 94.5% is obtained by optimal feature set having complementary information from variants of grey-level difference matrix. [ABSTRACT FROM AUTHOR]

This in-depth paper studies the issue of energy-related CO2 emissions of China using sample data from 1980 to 2015. Due to the lack of official data, CO2 emissions are first calculated by the recommended IPCC method. It shows that CO2 emissions in China present an "S" type in shape. Then the Tapio decoupling index is applied to investigate the relationship between CO2 emissions and economic growth. This suggests that weak decoupling is the main state during the study period and the decoupling trend is M-shaped. Moreover, the study years are divided into decoupling years and re-link years according to the decoupling relationship, and the ReliefF algorithm is proposed to verify the feasibility of the classification and judge the influencing weights of different driving factors. The ascending order is: actual GDP, urbanization rate, industrial structure, population, energy structure, and electricity consumption. Finally, a hybrid model of grey neural network model (GNNM) based on grey model (GM) and BP neural network (BPNN) is established to forecast CO2 emissions. This demonstrates that the GNNM model has a better capacity for forecasting CO2 emissions and capturing the non-linear and non-stationary characteristics of CO2 emissions. [ABSTRACT FROM AUTHOR]

The pulse signal at the wrist communicates a range of cardiovascular information and reflects a person's state of health. In recent years pulse signals have been used extensively in the field of disease identification. As a typical quasi-cyclic physiological signal, many researchers have simply used single-cycle pulse signals for disease diagnosis, ignoring the influence of inter-cycle differences on the diagnosis. In this paper, we propose a disease identification method based on graph features between pulse cycles, to focus on the differences in pulse cycles brought about by the disease. The pulse was pre-processing using a Sliding Window, followed by the construction of the correlation coefficient matrix, the setting of a threshold and the construction of the connection graph to obtain the graph features; the Multiscale Permutation Entropy method was used to extract the pulse's entropy features. The ReliefF algorithm is then used to select a total of 18 features and a classification algorithm is used to distinguish between patients and healthy people. Both the self-constructed dataset and the open dataset from the PLA 211 Hospital had high recognition rates for the experiments. The accuracy of identifying hypertension was 94.16% with a precision of 90.41%; the accuracy of identifying chronic diseases was 97.23% with a precision of 97.81%. The experimental results from the two datasets demonstrate both the validity of the difference between cycles for disease classification and the applicability of the method proposed in this paper. • Proposed disease identification method based on graph features between pulse cycles. • The correlation matrix of pulses was constructed to obtain graph features. • Feature optimization was performed using the ReliefF algorithm. • Experiments demonstrate the validity of cycle differences in disease classification. [ABSTRACT FROM AUTHOR]

Copyright of Econometrics / Ekonometria is the property of Sciendo and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)