Explore the vast range of titles available.

Gait is a vital biometric process for human identification in the domain of machine learning. In this article, a new method is implemented for human gait recognition based on accurate segmentation and multi-level features extraction. Four major steps are performed including: a) enhancement of motion region in frame by the implementation of linear transformation with HSI color space; b) Region of Interest (ROI) detection based on parallel implementation of optical flow and background subtraction; c) shape and geometric features extraction and parallel fusion; d) Multi-class support vector machine (MSVM) utilization for recognition. The presented approach reduces error rate and increases the CCR. Extensive experiments are done on three data sets namely CASIA-A, CASIA-B and CASIA-C which present different variations in clothing and carrying conditions. The proposed method achieved maximum recognition results of 98.6% on CASIA-A, 93.5% on CASIA-B and 97.3% on CASIA-C, respectively.

This study proposes a robust method for the face recognition from low‐resolution red, green, and blue‐depth (RGB‐D) cameras acquired images which have a wide range of variations in head pose, illumination, facial expression, and occlusion in some cases. The local binary pattern (LBP) of the RGB‐D images with the suitable feature dimension of Depth image is employed to extract the facial features. On the basis of error correcting output codes, they are fed to multiclass support vector machines (MSVMs) for the off‐line training and validation, and then the online classification. The proposed method is called as the LBP‐RGB‐D‐MSVM with the suitable feature dimension of the depth image. The effectiveness of the proposed method is evaluated by the four databases: Indraprastha Institute of Information Technology, Delhi (IIIT‐D) RGB‐D, visual analysis of people (VAP) RGB‐D‐T, EURECOM, and the authors. In addition, an extended database merged by the first three databases is employed to compare among the proposed method and some existing two‐dimensional (2D) and 3D face recognition algorithms. The proposed method possesses satisfactory performance (as high as 99.10 ± 0.52% for Rank 5 recognition rate in their database) with low computation (62 ms for feature extraction) which is desirable for real‐time applications.

Acute lymphocytic leukemia (ALL) is a common serious cancer in white blood cells (WBC) that advances quickly and produces abnormal cells in the bone marrow. Cancerous cells associated with ALL lead to impairment of body systems. Microscopic examination of ALL in a blood sample is applied manually by hematologists with many defects. Computer-aided leukemia image detection is used to avoid human visual recognition and to provide a more accurate diagnosis. This paper employs the ensemble strategy to detect ALL cells versus normal WBCs using three stages automatically. Firstly, image pre-processing is applied to handle the unbalanced database through the oversampling process. Secondly, deep spatial features are generated using a convolution neural network (CNN). At the same time, the gated recurrent unit (GRU)-bidirectional long short-term memory (BiLSTM) architecture is utilized to extract long-distance dependent information features or temporal features to obtain active feature learning. Thirdly, a softmax function and the multiclass support vector machine (MSVM) classifier are used for the classification mission. The proposed strategy has the resilience to classify the C-NMC 2019 database into two categories by using splitting the entire dataset into 90% as training and 10% as testing datasets. The main motivation of this paper is the novelty of the proposed framework for the purposeful and accurate diagnosis of ALL images. The proposed CNN-GRU-BiLSTM-MSVM is simply stacked by existing tools. However, the empirical results on C-NMC 2019 database show that the proposed framework is useful to the ALL image recognition problem compared to previous works. The DenseNet-201 model yielded an F1-score of 96.23% and an accuracy of 96.29% using the MSVM classifier in the test dataset. The findings exhibited that the proposed strategy can be employed as a complementary diagnostic tool for ALL cells. Further, this proposed strategy will encourage researchers to augment the rare database, such as blood microscopic images by creating powerful applications in terms of combining machine learning with deep learning algorithms.

In order to accurately identify a bearing fault on a wind turbine, a novel fault diagnosis method based on stochastic subspace identification (SSI) and multi-kernel support vector machine (MSVM) is proposed. First, the collected vibration signal of the wind turbine bearing is processed by the SSI method to extract fault feature vectors. Then, the MSVM is constructed based on Gauss kernel support vector machine (SVM) and polynomial kernel SVM. Finally, fault feature vectors which indicate the condition of the wind turbine bearing are inputted to the MSVM for fault pattern recognition. The results indicate that the SSI-MSVM method is effective in fault diagnosis for a wind turbine bearing and can successfully identify fault types of bearing and achieve higher diagnostic accuracy than that of K -means clustering, fuzzy means clustering and traditional SVM.

Breast tumors are the major malignancy in females and diagnostic systems using artificial intelligence algorithms for breast imaging have shown promising results. Among many algorithms, a deep convolutional neural network (DCNN) using K-means clustering and a multiclass support vector machine model enhance the precision of categorizing breast tumors from mammogram images. Nonetheless, effective breast tumor identification is still difficult without partitioning the pectoral muscle (PM) boundary from the remaining breast area. Therefore, this article proposes an Ensemble-Net model by ensembling the transfer learning model with different pre-trained CNN structures for partitioning the PM boundary from the remaining breast area in the mammographic scans. The segmentation process has 2 phases. In the initial phase, different region-of-interests are generated that include the object according to the input images. In the secondary phase, the object class is predicted after the areas of bounding boxes are refined and a pixel-range mask is created for the entity. These 2 different phases are associated with the backbone structure which creates the pyramid hierarchy of DCNN to acquire the features from the raw images. Moreover, it employs global average pooling followed by the softmax classification to recognize the normal, benign and malignant cases. Finally, the experimental outcomes demonstrate that the Ensemble-Net achieves 96.72% accuracy than the other classical classifiers.

This paper addresses the problem of feature selection for Multi-class Support Vector Machines. Two models involving the ℓ 0 (the zero norm) and the ℓ 2 – ℓ 0 regularizations are considered for which two continuous approaches based on DC (Difference of Convex functions) programming and DCA (DC Algorithms) are investigated. The first is DC approximation via several sparse inducing functions and the second is an exact reformulation approach using penalty techniques. Twelve versions of DCA based algorithms are developed on which empirical computational experiments are fully performed. Numerical results on real-world datasets show the efficiency and the superiority of our methods versus one of the best standard algorithms on both feature selection and classification.

The human digestive system's electrical activity may be recorded noninvasively by Electrogastrography (EGG). Electrogastrograms are recordings of the electrical activity produced by the stomach muscles. EGG Several gastrointestinal disorders may be diagnosed and their severity measured using EGG signal properties. The literature has several contributions to the categorization of EGG signals. The majority of them make use of either the EGG's frequency or time data. The wide variety of EGG signals is a challenge for current automated categorization methods. Therefore, this study's objective is to develop a lightweight classifier that achieves high classification accuracy while using little processing resources. To acquire normal and abnormal EGG signals at a reasonable cost, a three-electrode measuring device is created here, with classification performed by a hybrid of Linear Vector Quantization and the African Buffalo Search Algorithm (HLVQ-ASO). The results show that the information richness of recorded EGG signals from healthy persons is greater for EGG signals captured using a surface electrode with a contact diameter of 19 mm as compared to 16 mm. To demonstrate their validity and degree of classification accuracy, the results computed using the suggested classifiers are compared with the current classifiers like Artificial Neural Network, Multimodal Support Vector Machine (MSVM), and Improved Convolutional Neural Network (CNN). Additionally, the HLVQ-ASO-based classification method is effective in differentiating between normal and diabetic EGG signals, found a sensitivity of 97% and a specificity of 98.8%. For a dataset of 500 samples, the classification accuracy is 97%.

Fluctuation on the assembly quality of the linear axis of machine tools (LA-MT) at the same batch is urgent problem need to be solved in assembly of machine tools. In this paper, a new concept of assembly consistency degree was introduced for defining the fluctuation degree of assembly quality. Based on assembly consistency degree, a hybrid machine learning method, genetic algorithm optimized multi-class support vector machine and improved Kuhn–Munkres (GA-MSVM-I-KM) was proposed for improving assembly consistency of LA-MT. The assembly of linear axis of a three-axis vertical machining center was regarded as an example, and the assembly consistency influence factors on straightness error of Y-axis (SE-YA) were analyzed through the Kruskal–Wallis statistical method. The main factors affected on the assembly consistency of SE-YA turned out to be the machining errors of bed and the assembly team technical levels. Based on this, the assembly consistency improvement model was established. Then, the prediction model of SE-YA based on assembly experiment data and genetic algorithm optimized multi-class support vector machine (GA-MSVM) was constructed, and I-KM method was applied for improving assembly consistency of SE-YA. The results show that the GA-MSVM-I-KM method can effectively enhance the assembly consistency of SE-YA, and the assembly consistency degree is reduced from 0.19 to 0.08.

Emotion recognition has been of great interest in psychology, machine intelligence, human–machine interaction and biomedical fields. This paper proposes a novel soft computing technique for facial emotion recognition by introducing edge- enhanced bidimensional empirical mode decomposition (EEBEMD) as a feature extraction tool for facial emotion recognition. Facial images are subjected to optimized cost function-based self-guided edge enhancement algorithm. BEMD has been applied on the edge- enhanced facial images, and the first four intrinsic mode functions (IMFs) and the residue have been calculated. On the basis of an empirical analysis, the first IMF is selected for further analysis. A proposed fusion model that consists of selected features from the gray-level co-occurrence matrix, the histogram of oriented gradients and the local ternary pattern of the IMF response is fed to a recursive feature elimination-based algorithm to select the appropriate feature subsets for classification. These feature vectors have been trained in three machine learning algorithms namely multi-class SVM, ELM with RBF kernel and k-NN classifier independently. The IMFs have been subjected to principal component analysis and linear discriminant analysis (LDA) algorithm successively for dimensionality reduction, and the facial images with different emotions have been clustered in different zones in the LDA subspace. The proposed method demonstrates promising accuracy when tested on the JAFFE database, Cohn–Kanade database and the eNTERFACE database.

[...]the crop changes from one farm to another on the basis of the planting dates, diversity, soil environment and the crop organization. [...]a large chunk of the soil properties are protracted and expensive to estimate, in addition to habitual variations over a period of time. [...]the swift and precise forecast of soil properties has become the need of the hour so as to successfully deal with the deficiency of the estimated soil property data [11]. [...]there has been a zooming necessity for the superior estimates of output yield and overall biomass production.