A Semi-Supervised Relief Based Feature Extraction Algorithm

Android, the most widely used mobile operating system, is also the most vulnerable to malware due to its high popularity. This has significantly focused on Android malware detection in mobile security. While extensive research has been conducted using various methods, new malware’s emergence underscores this field’s dynamic nature and the need for continuous research. The motivation that drives malware developers to create Android malware constantly is the potential to access Android devices, thereby gaining access to sensitive user information. This study, which is a complex and in-depth exploration, aims to detect Android malware using a meta-classifier that combines the single-classifier light gradient boosting machine, support vector machine, and random forest. The process involves converting disassembled malware codes into grey images for global and local feature extraction. The classification accuracy is 97% at best on a malware dataset of 3,963 samples. The main contribution of this paper is to produce an Android APK malware detector model that works by combining multiple machine learning algorithms trained using the dataset resulting from local and global feature extraction algorithms.

A novel local texture feature extraction algorithm is proposed based on histogram of oriented gradient domain texture tendency (HOGTT). Classical HOG descriptor proves to be sensitive to rotation transformation, though it is insensitive to illumination and scale changes. The intrinsic texture tendency of tyre tread image has obvious consistency and is robust to different types of images transformation. This paper mainly makes two contributions: First, the scale and circular region constraint on tyre pattern in local feature extraction highly improves the representation precision of the extracted HOG feature. Second, the HOG feature matrix is modified by texture tendency to obtain the rotation invariance property. Experimental results on tyre tread dataset demonstrate the effectiveness of HOGTT in tyre pattern retrieval.

In recent years, the target of local feature extraction and recognition technology is a hot research topic in digital image processing and computer vision field.In target recognition, pest undetected phenomenon often happens due to occlusion, once the conditions are favorable, pests quickly multiply and spread, causing great harm to the stored product.we established a common stored product pests image database, proposed feature extraction and matching algorithms, based on the combination of improved SURF and multi-resolution histogram.Pests specified in the database for target identification, especially when the pest is partially obscured, or the shape and size changes,by finding matching number of feature points the description of the target for accurate identification .This method is efficient, time-saving,provides an important scientific basis for the entry-exit inspection and quarantine in rapid identification of stored product pests.It is more conducive to the subsequent classification.

Active Learning is a machine learning and data mining technique that selects the most informative samples for labeling and uses them as training data; it is especially useful when there are large amount of unlabeled data and labeling them is expensive. Recently, batch-mode active learning, where a set of samples are selected concurrently for labeling, based on their collective merit, has attracted a lot of attention. The objective of batch-mode active learning is to select a set of informative samples so that a classifier learned on these samples has good generalization performance on the unlabeled data. Most of the existing batch-mode active learning methodologies try to achieve this by selecting samples based on certain criteria. In this article we propose a novel criterion which achieves good generalization performance of a classifier by specifically selecting a set of query samples that minimize the difference in distribution between the labeled and the unlabeled data, after annotation. We explicitly measure this difference based on all candidate subsets of the unlabeled data and select the best subset. The proposed objective is an NP-hard integer programming optimization problem. We provide two optimization techniques to solve this problem. In the first one, the problem is transformed into a convex quadratic programming problem and in the second method the problem is transformed into a linear programming problem. Our empirical studies using publicly available UCI datasets and two biomedical image databases demonstrate the effectiveness of the proposed approach in comparison with the state-of-the-art batch-mode active learning methods. We also present two extensions of the proposed approach, which incorporate uncertainty of the predicted labels of the unlabeled data and transfer learning in the proposed formulation. In addition, we present a joint optimization framework for performing both transfer and active learning simultaneously unlike the existing approaches of learning in two separate stages, that is, typically, transfer learning followed by active learning. We specifically minimize a common objective of reducing distribution difference between the domain adapted source, the queried and labeled samples and the rest of the unlabeled target domain data. Our empirical studies on two biomedical image databases and on a publicly available 20 Newsgroups dataset show that incorporation of uncertainty information and transfer learning further improves the performance of the proposed active learning based classifier. Our empirical studies also show that the proposed transfer-active method based on the joint optimization framework performs significantly better than a framework which implements transfer and active learning in two separate stages.

A robust fleet-based anomaly detection framework applied to wind turbine vibration data

Representation learning with deep sparse auto-encoder for multi-task learning

Understanding human emotions is one of the necessary skills for the computer to interact intelligently with human users. The most expressive way humans display emotions is through facial expressions. In this paper, we report on several advances we have made in building a system for classification of facial expressions from continuous video input. We use Bayesian network classifiers for classifying expressions from video. One of the motivating factor in using the Bayesian network classifiers is their ability to handle missing data, both during inference and training. In particular, we are interested in the problem of learning with both labeled and unlabeled data. We show that when using unlabeled data to learn classifiers, using correct modeling assumptions is critical for achieving improved classification performance. Motivated by this, we introduce a classification driven stochastic structure search algorithm for learning the structure of Bayesian network classifiers. We show that with moderate size labeled training sets and large amount of unlabeled data, our method can utilize unlabeled data to improve classification performance. We also provide results using the Naive Bayes (NB) and the Tree-Augmented Naive Bayes (TAN) classifiers, showing that the two can achieve good performance with labeled training sets, but perform poorly when unlabeled data are added to the training set.

LocalFace: Learning significant local features for deep face recognition

Medical image classification is essential for contemporary clinical diagnosis and decision support systems. However, medical images generally have similar inter-class features and complex structure patterns, making it a challenging task. While both local and global features are critical for noise reduction and discriminative pattern extraction in medical images, conventional approaches exhibit limitations. Specifically, convolutional neural networks (CNNs) focus on local features extraction but lack a comprehensive understanding of global semantic. Conversely, vision transformers (ViTs) can model long-range feature dependencies but may cause disruption to local features. To address these limitations, we propose Hierarchical Enhanced Multi-attention Feature (HEMF), an adaptive hierarchical enhanced multi-attention feature fusion framework to synergistically extract and fuse multi-scale local and global features. It comprises two core components: (1) the enhanced local and global feature extraction modules to extract multi-scale local and global features in parallel; (2) the hierarchical enhanced feature fusion module integrating a novel attention mechanism named Mixed Attention (MA) and a novel inverted residual block named Squeezed Inverted Residual Multi-Layer Perceptron (SIRMLP) to effectively fuse multi-scale features. Experimental results demonstrate that with nearly minimal model parameters compared to other advanced models, HEMF achieves the accuracy and F1-score of 87.34% and 78.89% on the ISIC2018 dataset, 87.03% and 87.02% on the Kvasir dataset, and 82.26% and 82.20% on the COVID-19 CT dataset, which are the state-of-the-art performance. Our code is open source and available from https://github.com/Esgjgd/HEMF.

In the object recognition based on the bag of visual words, we focus on several main feature extraction algorithms. The Scale Invariant Feature Transform (SIFT) that based on local features with good significance and robustness has became a popular feature extraction method. But we take into consideration that the SIFT will generate a large number of high-dimensional feature vectors, which will increase the computational cost. In this paper, a novel feature extraction algorithm by means of SIFT to fuse region information entropy (SIFT-entropy) is proposed. The algorithm can improve the quality of the feature extracted from the image by cluster similar key points to removing the noisy key points. So a more discriminative high quality “visual word” codebook could be generated. We made a comprehensive comparison between the proposed method and the original SIFT method on Caltech-101 database. The experimental results show that this improvement can reduce the dimension of the feature space, and has higher classification accuracy.

The partial area under a receiver operating characteristic curve (pAUC) is a performance measurement for binary classification problems that summarizes the true positive rate with the specific range of the false positive rate. Obtaining classifiers that achieve high pAUC is important in a wide variety of applications, such as cancer screening and spam filtering. Although many methods have been proposed for maximizing the pAUC, existing methods require many labeled data for training. In this paper, we propose a semi-supervised learning method for maximizing the pAUC, which trains a classifier with a small amount of labeled data and a large amount of unlabeled data. To exploit the unlabeled data, we derive two approximations of the pAUC: the first is calculated from positive and unlabeled data, and the second is calculated from negative and unlabeled data. A classifier is trained by maximizing the weighted sum of the two approximations of the pAUC and the pAUC that is calculated from positive and negative data. With experiments using various datasets, we demonstrate that the proposed method achieves higher test pAUCs than existing methods.

The optical fiber distributed strain sensor based on the optical frequency domain reflectometer (OFDR) preserves its dominant position in short-distance measurement fields with high spatial resolution, such as biomedical treatment, soft robot, etc. However, owing to the weak intensity of the Rayleigh backscattered signal (RBS) in the single-mode fiber (SMF) and complex computation, the large strain changes cannot be precisely and rapidly demodulated by the traditional cross-correlation method. In this work, the OFDR with backscattering enhanced optical fiber (BEOF) is proposed and demonstrated for fast and large strain measurement. By enhancing the RBS amplitude, the signal-to-noise ratio (SNR) is improved, resulting in a higher similarity between the reference signal and test signal, which is beneficial for the expansion of the strain measurement range. Moreover, the adaptive local feature extraction and matching (ALFEM) algorithm is presented and demonstrated, which replaces the traditional cross-correlation method for strain demodulation and fast measurement. On account of the enhancement ratio of BEOF, the dominant characteristic data segment can be extracted from whole wavelength data. In the experiments, the enhancing ratio of BEOF is designed as 10, resulting in the spatial resolution reaches 400µm and the strain measurement range is greatly increased to 4800µɛ. Further, the effectiveness of the ALFEM algorithm has been verified, in which the strain demodulation time is approximately 25% of that of the traditional method. This scheme fully exploits the enhancement characteristic of the BEOF and is also applicable to the systems based on other types of BEOF, different strain changes and sensing distances.

We organized a data mining challenge on “active learning” for IJCNN/WCCI 2010, addressing machine learning problems where labeling data is expensive, but large amounts of unlabeled data are available at low cost. Examples include handwriting and speech recognition, document classification, vision tasks, drug design using recombinant molecules and protein engineering. Such problems might be tackled from different angles: learning from unlabeled data or active learning. In the former case, the algorithms must satisfy themselves with the limited amount of labeled data and capitalize on the unlabeled data with semi-supervised learning methods. Several challenges have addressed this problem in the past. In the latter case, the algorithms may place a limited number of queries to get new sample labels. The goal in that case is to optimize the queries and the problem is referred to as active learning. While the problem of active learning is of great importance, organizing a challenge in that area is non trivial. This is the problem we have addressed, and we describe our approach in this paper. The “active learning” challenge is part of the WCCI 2010 competition program (http://www.wcci2010. org/competition-program). The website of the challenge remains open for submission of new methods beyond the termination of the challenge as a resource for students and researchers (http://clopinet.com/al).

Face Recognition is a prototype with stirring functions in the direction of facial features for consent and validation. In this approach, a particular type of face recognition systems is bond different feature extraction approaches to conquer the image entity configuration. To solve face recognition under unreliable pose is rigorous pose invariant features with effective approach. In this work, an algorithm is implemented in MATLAB and performance evaluation of achievement rate with existing techniques is proposed. Also, the performance of the face recognition system is based on feature extractions using wavelet transform and demonstrates the improved quality image. This work provides Artificial Neural Network (ANN) for face recognition and using a combination of Discrete Wavelet Transform (DWT) and Principal Component Analysis (PCA) algorithm for feature extraction and acquires a transformed face image to raise the features. The results demonstrated that the proposed system has higher accuracy, precision and sensitivity than face recognition using different feature extractors.

Feature extraction is recognized as a critical stage in bearing fault diagnosis. Pattern spectrum (PS) and pattern spectrum entropy (PSE) in recent years have been smoothly applied in feature extraction, whereas they easily ignore the partial impulse signatures hidden in bearing vibration data. In this paper, the pattern gradient spectrum (PGS) and pattern gradient spectrum entropy (PGSE) are firstly presented to improve the performance of fault feature extraction of two approaches (PS and PSE). Nonetheless, PSE and PGSE are only able to evaluate dynamic behavior of the time series on a single scale, which implies there is no consideration of feature information at other scales. To address this problem, a novel approach entitled multiscale pattern gradient spectrum entropy (MPGSE) is further implemented to extract fault features across multiple scales, where its key parameters are determined adaptively by grey wolf optimization (GWO). Meanwhile, a Laplacian score- (LS-) based feature selection strategy is employed to choose the sensitive features and establish a new feature set. Finally, the selected new feature set is imported into extreme learning machine (ELM) to identify different health conditions of rolling bearing. Performance of our designed algorithm is tested on two experimental cases. Results confirm the availability of our proposed algorithm in feature extraction and show that our method can recognize effectively different bearing fault categories and severities. More importantly, the designed approach can achieve higher recognition accuracies and provide better stability by comparing with other entropy-based methods involved in this paper.