Search

Aiming at the feature extraction problem of feature-based visual odometry, this paper proposed a feature selection algorithm based on mutual information and semantic segmentation uncertainty. Based on semantic and geometric information of features, the algorithm points extracted from potential static objects. It corrected the semantic uncertainty of features based on the semantic context, and selected the features based on the information entropy changes of features. Finally, this paper used the public KITTI visual odometry dataset to evaluate the algorithm and compared the experiment results with other algorithms. The results prove that the proposed algorithm has better accuracy of pose estimation, which verifies the effectiveness and feasibility of the algorithm. [ABSTRACT FROM AUTHOR]

The common spatial pattern (CSP) algorithm is efficient and accurate for channels selection and features extraction for electroencephalogram (EEG) signals classification. The CSP algorithm is usually applied on a subject-by-subject basis by measuring only intra-subject variations for selecting the most significant channels; we refer to this algorithm as CSP-based customized channels selection (CSP-CC). In practice, deploying the CSP-CC algorithm requires to set up a customized EEG device for each subject separately, which can be very costly. In this paper, we propose a new algorithm, called CSP-based unified channels (CSP-UC), for overcoming the aforementioned difficulties. The aim of the proposed algorithm is to extract unified channels that are valid for any subject; hence, one EEG device can be deployed for all subjects. Moreover, a methodology for developing both binary-class and ternary-class EEG signals classification models using either customized or unified channels is introduced. This methodology is applicable for both subject-by-subject and cross-subjects basis. In ternary-class classification models, the traditional "Max_Vote" method, used for voting the predicted class labels, has been modified to a more accurate method called "Max_Vote_then_Max_Probability." On a subject-by-subject basis, the experimental results on EEG-based driver's fatigue dataset have shown that the accuracy of the classification models that are based on the proposed CSP-UC algorithm is slightly lower than that of those based on the CSP-CC algorithm. Nevertheless, the former algorithm is more practical and cost-effective than the latter. But in cross-subjects, the classification models based on the CSP-UC algorithm outperform those based on the CSP-CC algorithm in both accuracy and the number of used channels. [ABSTRACT FROM AUTHOR]

Identifying the abnormal samples from a data set and determining their type are two key tasks of anomaly detection. However, the existing anomaly detection algorithms are generally faced with the defects of weak generalization ability and insufficient interpretation, the core reason of which is that they cannot mine specific features for different abnormal types. In this paper, a new anomaly detection algorithm aiming at feature selection for different abnormal types is developed. Inspired by self-supervised learning, we take the stationarity of variance changes of abnormal score similarity as a pretext task and combine it with wrapped search method. Then, the features and the corresponding parameters for different abnormal types can be screened to apply to the downstream task of anomaly integration detection. To verify the efficiency of the new algorithm, we conduct two sets of experiments to compare the new algorithm with 11 classical anomaly detection and 3 clustering anomaly detection algorithms on the data sets WDBC, WPBC and Wilt from DAMI database with the evaluation measures P@n , Adj- P@n , AP, Adj-AP and AUC. The experiment results show that, both in the identification and classification on abnormal samples, all performance measures of the new algorithm are explicitly better than that of the contrastive algorithms. Also, we apply the new algorithm to the Chinese auto insurance market, and find that the results can help managers to identify the main patterns of fraudulent claims and to summarize the feature combinations of fraud behaviors. In general, the new algorithm developed in this paper has the following advantages compared with traditional algorithms: 1) It can directly capture abnormal features and realize effective recognition of abnormal types, which effectively bridge the gap between abnormal judgement and feature screening. 2) Automatic screening of abnormal features can be completed under the condition of self-updating learning optimal strategy. 3) Only a few features are extracted from all features to reveal the abnormal characteristics, which significantly improves the interpretability and generalization ability of the algorithm and its results. In a word, through the novel self-supervised design method, feature screening is skillfully integrated into the anomaly detection task, which may provide a new way for anomaly detection research. [ABSTRACT FROM AUTHOR]

Deep learning-based target detection for optical remote sensing images is a significant research direction in the field of image processing. Different from natural images, remote sensing images are characterized by complex backgrounds, similarity of characteristics between various classes and diverse target scales. In this paper, we propose an adaptive multi-feature fusion YOLOv3 remote sensing small target detection algorithm to cope with these features. In the proposed algorithm, the shallow semantic information is extracted by the accessory feature extraction network, and fused with the deep features extracted by Darknet-53 down-sampling to enrich the semantic and spatial information of the feature layers on the auxiliary network. In addition, the shallow features are filtered using the adaptive feature selection module to refine the effective feature information. A cross-layer feature fusion module is proposed to fuse different feature layers to enhance the connection between the semantic information of feature contexts to obtain more information about the characteristics of small targets. To test the effectiveness of the proposed algorithm, it is validated on the Pascal voc2007 dataset. The experimental results show that the detection accuracy of the proposed algorithm could achieve 88.3%, and evidently superior to the original YOLOv3 algorithm. Finally, the proposed algorithm is applied to detect the small target in remote sensing images. The detection results show that compared with the original YOLOv3 algorithm, the mean average precision(mAP) of the proposed algorithm is improved by 2.6%, which can effectively detect more small targets and significantly improve the detection accuracy of small targets than other classical algorithms. [ABSTRACT FROM AUTHOR]

The main intention of this paper is to develop a new intelligent framework for web page classification and re-ranking. The two main phases of the proposed model are (a) classification, and (b) re-ranking-based retrieval. In the classification phase, pre-processing is initially performed, which follows the steps like HTML (Hyper Text Markup Language) tag removal, punctuation marks removal, stop words removal, and stemming. After pre-processing, word to vector formation is done and then, feature extraction is performed by Principle Component Analysis (PCA). From this, optimal feature selection is accomplished, which is the important process for the accurate classification of web pages. Web pages contain several features, which reduces the classification accuracy. Here, the adoption of a new meta-heuristic algorithm termed Opposition based-Tunicate Swarm Algorithm (O-TSA) is employed to perform the optimal feature selection. Finally, the selected features are subjected to the Enhanced Convolutional-Recurrent Neural Network (E-CRNN) for accurate web page classification with enhancement based on O-TSA. The outcome of this phase is the categorization of different web page classes. In the second phase, the re-ranking is involved utilizing the O-TSA, which derives the objective function based on similarity function (correlation) for URL matching, which results in optimal re-ranking of web pages for retrieval. Thus, the proposed method yields better classification and re-ranking performance and reduce space requirements and search time in the web documents compared with the existing methods. [ABSTRACT FROM AUTHOR]

Degradation state identification for hydraulic pumps is crucial to ensure system performance. As an important step, feature extraction has always been challenging. The non-stationary and non-Gaussian characteristics of the vibration signal are likely to weaken the performance of traditional features. In this paper, an efficient feature extraction algorithm named multi-scale ternary dynamic analysis (MTDA) is proposed. MTDA reconstructs the phase space based on the given signal and converts each embedding vector into a ternary pattern independently, which enhances its capacity of describing the details of non-stationary signals. State entropy (SE) and state transition entropy (STE) are calculated to estimate the dynamical changes and complexity of each signal sample. The excellent performance of SE and STE in detecting frequency changes, amplitude changes, and the development process of fault is verified with the use of four simulated signals. The proposed multi-scale analysis enables them to provide a more precise estimation of entropy. Furthermore, support vector machine (SVM) and nondominated sorting genetic algorithm II (NSGA-II) are introduced to conduct feature selection and state identification. NSGA-II and SVM can conduct the joint optimization of these two goals. The details of the method proposed in this paper are tested using simulated signals and experimental data, and some studies related to the fault diagnosis of rotating machinery are compared with our method. All the results show that our proposed method has better performance, which obtains higher recognition accuracy and lower feature set dimension. [ABSTRACT FROM AUTHOR]

In context to high-dimensional clustering, the concept of feature weighting has gained considerable importance over the years to capture the relative degrees of importance of different features in revealing the cluster structure of the dataset. However, the popular techniques in this area either fail to perform feature selection or do not preserve the simplicity of Lloyd’s heuristic to solve the $k$ k -means problem and the like. In this paper, we propose a Lasso Weighted $k$ k -means ($LW$ L W - $k$ k -means) algorithm, as a simple yet efficient sparse clustering procedure for high-dimensional data where the number of features ($p$ p ) can be much higher than the number of observations ($n$ n ). The $LW$ L W - $k$ k -means method imposes an $\ell _1$ ℓ 1 regularization term involving the feature weights directly to induce feature selection in a sparse clustering framework. We develop a simple block-coordinate descent type algorithm with time-complexity resembling that of Lloyd’s method, to optimize the proposed objective. In addition, we establish the strong consistency of the $LW$ L W - $k$ k -means procedure. Such an analysis of the large sample properties is not available for the conventional sparse $k$ k -means algorithms, in general. $LW$ L W - $k$ k -means is tested on a number of synthetic and real-life datasets and through a detailed experimental analysis, we find that the performance of the method is highly competitive against the baselines as well as the state-of-the-art procedures for center-based high-dimensional clustering, not only in terms of clustering accuracy but also with respect to computational time. [ABSTRACT FROM AUTHOR]

It is well known that we, as human beings, are prone to a variety of undesirable emotions such as excitement, boredom, and fear, all of which are induced by varying degrees of negative states. In this paper, we designed an emotion-evoking experiment to induce calm, excited, bored, and fearful emotions, as well as low, moderate, and high levels of tension. Based on the six physiological signals such as heart rate and respiration rate of the subjects in these emotion states, feature extraction was performed after removing the baseline preprocessing, combined with particle swarm optimisation algorithm for feature selection, and the k-nearest neighbour algorithm was used to classify the different emotion and tension levels in the undesirable states. By comparing the results of several sets of experiments, we found that with baseline removal and particle swarm feature selection optimisation, our experimental results using k-nearest neighbour classification showed a significant improvement in recognition accuracy compared to the traditional k-nearest neighbour algorithm, which indicates that the proposed method has better recognition results. [ABSTRACT FROM AUTHOR]

Spike trains (STs) induced by external stimuli are complex and challenging to decode the embedded spatiotemporal information. Although various methods have been developed to characterize STs, few applications have been reported in tactile discrimination applications. In this paper, a neurocomputing method based on reference spike train (RST) is proposed to establish a neural computation scheme, on which existing ST metrics could be fed into various traditional models directly. Moreover, existing metrics in the field of statistics and vector measurement are introduced together to extract more discriminative features. With the binning technique and feature selection algorithm applied, the neural computation scheme is aimed at taking advantage of as maximal as possible information contained in tactile signals. Based on our designed artificial fingertip, the effect is validated by improving the recognition accuracy from 77.6% to 83.4% when it is applied to the discrimination of eight roughness surfaces. Furthermore, properties of RST, such as spike intervals and distributions, are evaluated and it is found that RSTs with uniform distribution perform the best for tactile discrimination. [ABSTRACT FROM AUTHOR]

Motor imagery (MI) based brain–computer interfaces help patients with movement disorders to regain the ability to control external devices. Common spatial pattern (CSP) is a popular algorithm for feature extraction in decoding MI tasks. However, due to noise and nonstationarity in electroencephalography (EEG), it is not optimal to combine the corresponding features obtained from the traditional CSP algorithm. In this paper, we designed a novel CSP feature selection framework that combines the filter method and the wrapper method. We first evaluated the importance of every CSP feature by the infinite latent feature selection method. Meanwhile, we calculated Wasserstein distance between feature distributions of the same feature under different tasks. Then, we redefined the importance of every CSP feature based on two indicators mentioned above, which eliminates half of CSP features to create a new CSP feature subspace according to the new importance indicator. At last, we designed the improved binary gravitational search algorithm (IBGSA) by rebuilding its transfer function and applied IBGSA on the new CSP feature subspace to find the optimal feature set. To validate the proposed method, we conducted experiments on three public BCI datasets and performed a numerical analysis of the proposed algorithm for MI classification. The accuracies were comparable to those reported in related studies and the presented model outperformed other methods in literature on the same underlying data. [ABSTRACT FROM AUTHOR]

• 3 layer neural networks outperform other ML algorithms in automated assessments. • In subjective assignments, deep neural networks can improve score prediction. • Word embeddings and linguistic feature results in more precise text mining models. • Extraction and selection of appropriate features can improve results. Machine learning (ML) has recently gained popularity in a variety of domains for automating tasks. This has also been used in the evaluation of student responses/ assignments. This paper presents a qualitatively enhanced methodology for automated score prediction of subjective assignments. To consider all the major aspects of a human grader, 21 linguistic features related to syntactical, grammatical, sentimental, and readability are analyzed from the assignments. This study makes use of the ASAP competition dataset from Kaggle. The evaluation metric used is Quadratic Weighted Kappa (QWK), which measures the agreement between the human graded score and the predicted score. The effect of appropriate feature selection has been observed using Mutual Information Regression. Four ML algorithms are investigated on identified linguistic features. 3 Layer Neural Network with feature selection performed well among all chosen ML algorithms with average QWK of 0.678. To include the benefits of deep learning, a new hybrid model (LF-BiLSTM-att-FS) is proposed that combines a higher level deep neural network (DNN) with the selected features. Pre-trained Glove embedding is used to include contextual information of the text. The proposed model results demonstrated an improvement in overall accuracy, with an average QWK value of 0.768. [ABSTRACT FROM AUTHOR]

A motor imagery (MI) based brain computer interface (BCI) is a challenging nonmuscular connection system used to independently perform movement-related tasks. It is gaining increasing prominence in helping paralyzed individuals communicate with the real world. Achieving better classification accuracy is the major concern in the field of motor imagery-based BCI. To upgrade the classification performance, relevant features play a vital role. The relevant features can be selected by the extreme gradient Bayesian optimization (XGBO) method. In this paper, a combination of time-, frequency-, and spatial-related MI features are extracted to design a reliable MI-BCI system. The proposed method incorporates the XGBO algorithm for feature selection and the random forest for the classification of EEG signals. The potency of the proposed system was investigated using two public EEG datasets (BCI Competition III dataset IIIa and dataset IVa). A novel XGBO algorithm increases the accuracy and reduces the time consumption by reducing the dimensionality of features. The proposed algorithm selects the minimum number of features that increase the computational efficacy for MI-based BCI systems. The proposed method is compared with ANOVA, sequential forward selection, recursive feature elimination, and LASSO methods and the accuracy rate is increased with the lowest computation time. The proposed method achieves mean accuracies of 94.44% and 88.72% and classification errors of 5.56% and 11.28% for Datasets IIIa and IVa, respectively. It outperforms four state-of-art methods with 0.87% and 0.59% increases in the accuracy for Datasets IIIa and IVa, respectively. • A novel feature selection method enhances the classification of EEG signals. • The time, spatial and frequency domain of EEG motor imagery features are extracted. • Predominant EEG Features are selected using the proposed XGBO method. • XGBO method is compared with existing feature selection methods. • The proposed method increases accuracy and reduces the computation time. [ABSTRACT FROM AUTHOR]

Snoring is an important characteristic of obstructive sleep apnea-hypopnea syndrome (OSAHS). Snoring sound can be used to develop a non-invasive approach for automatically screening OSAHS. In this paper, a snoring detection algorithm based on acoustic features and the XGBoost was proposed. The Fisher Ratio (FR) method was used for feature selection and the 23-dimensional feature set was extracted from the original 58-dimensional feature to reduce computational complexity. A variety of training and test data split methods were used to evaluate the performance of the proposed model. In addition, the proposed method was compared with the deep learning method on the independent subjects training set and test set. The accuracy of the reduced feature set by the proposed model was 87.22% and the deep learning model 87.26% on independent subjects training set and test set, the prediction time of the deep learning model on the test set was around 238 ms, the prediction time of XGBoost was around 58 ms, and the computing efficiency of XGBoost is higher than that of the deep learning model. The results show that the proposed method achieves a good balance between computational cost and performance. These results provide an important method for fast and real-time classification and evaluation of snoring for OSAHS. [ABSTRACT FROM AUTHOR]

Feature selection in real-world data mining problems is essential to make the learning task efficient and more accurate. Identifying the best feature selection algorithm, among the many available, is a complex activity that still relies heavily on human experts or some random trial-and-error procedure. Thus, the automated machine learning community has taken some steps towards the automation of this process. In this paper, we address the metalearning challenge of recommending feature selection algorithms by proposing a novel meta-feature engineering model. Our model considers a broad collection of meta-features that enable the study of the relationship between the dataset properties and the feature selection algorithm performance in terms of several criteria. We arrange the input meta-features into eight categories: (i) simple, (ii) statistical, (iii) information-theoretical, (iv) complexity, (v) landmarking, (vi) based on symbolic models, (vii) based on images, and (viii) based on complex networks (graphs). The target meta-features emerge from a multi-criteria performance measure, based on five individual performance indexes, that assesses feature selection methods grounded in information, distance, dependence, consistency, and precision measures. We evaluate our proposal using a recently developed framework that extracts the input meta-features from 213 benchmark datasets, and ranks the assessed feature selection algorithms, to fill in the target meta-features in meta-bases. This evaluation uses five state-of-the-art classification methods to induce recommendation models from meta-bases: C4.5, Random Forest, XGBoost, ANN, and SVM. The results showed that it is possible to reach an average accuracy of up to 90% applying our meta-feature engineering model. This work is the first to use an extensive empirical evaluation to provide a careful discussion of the strengths and limitations of more than 160 meta-features. These meta-features, while designed to aid the task of feature selection algorithm recommendation, can readily be employed in other metalearning scenarios. Therefore, we believe our findings are a valuable contribution to the fields of automated machine learning and data mining, as well as to the feature extraction and pattern recognition communities. • A novel meta-feature engineering model recommends feature selection algorithms. • The proposal obtains promising results from 213 datasets with hit rates of up to 90%. • Some simple, landmarking, image, and graph-based input meta-features highlighted. • A multi-criteria performance measure rigorously assesses candidate algorithms. • Chains of binary or multiclass classifiers can efficiently rank candidate algorithms. [ABSTRACT FROM AUTHOR]

Currently, the world is still facing a COVID-19 (coronavirus disease 2019) classified as a highly infectious disease due to its rapid spreading. The shortage of X-ray machines may lead to critical situations and delay the diagnosis results, increasing the number of deaths. Therefore, the exploitation of deep learning (DL) and optimization algorithms can be advantageous in early diagnosis and COVID-19 detection. In this paper, we propose a framework for COVID-19 images classification using hybridization of DL and swarm-based algorithms. The MobileNetV3 is used as a backbone feature extraction to learn and extract relevant image representations as a DL model. As a swarm-based algorithm, the Aquila Optimizer (Aqu) is used as a feature selector to reduce the dimensionality of the image representations and improve the classification accuracy using only the most essential selected features. To validate the proposed framework, two datasets with X-ray and CT COVID-19 images are used. The obtained results from the experiments show a good performance of the proposed framework in terms of classification accuracy and dimensionality reduction during the feature extraction and selection phases. The Aqu feature selection algorithm achieves accuracy better than other methods in terms of performance metrics. [ABSTRACT FROM AUTHOR]

Enhancers are regulatory elements involved in gene expression.It is a part of DNA, which can enhance the transcription rate of gene. However, the identification of enhancer by biological experimental methods is time-consuming and expensive. Therefore, there is an urgent need for more efficient methods to identify them.In this study, we propose a new feature extraction method RKPK, which combines three feature methods and uses the recursive feature elimination algorithm for feature selection, and apply deep neural network as classifier to construct the iEnhancer-RD calculation method for enhancer identification. It is a two-layer classification architecture in which the first layer(layer I) identifies enhancers from a set of DNA sequences, and the second layer(layer II) divides the identified enhancers into two subgroups, namely strong and weak enhancers. Independent dataset test indicates that the proposed method is significantly better than most existing methods, and attains the accuracy of 78.8% and 70.5% in the two layers, respectively. Our iEnhancer-RD architecture is implemented in Python and is available at https://github.com/YangHuan639/iEnhancer-RD. [Display omitted] • In this paper, we propose iEnhancer-RD, a method to identify enhancers and their strength. • We propose new feature methods KPCV and RKPK, and compare and analyze these two representations. • Deep neural network (DNN) is used as our classififier. • Optimize several feature methods and the parameters of the constructed deep neural network. • Compared with other work, this method has signifificant improvement in most performance indicators. [ABSTRACT FROM AUTHOR]

The reliable and cost-effective condition monitoring of the bearings installed in water pumps is a real challenge in the industry. This paper presents a novel strong feature selection and extraction algorithm (SFSEA) to extract fault-related features from the instantaneous power spectrum (IPS). The three features extracted from the IPS using the SFSEA are fed to an extreme gradient boosting (XBG) classifier to reliably detect and classify the minor bearing faults. The experiments performed on a lab-scale test setup demonstrated classification accuracy up to 100%, which is better than the previously reported fault classification accuracies and indicates the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]