Search Results (6,953)

Aiming to address the problems of difficulty in selecting characteristic quantities and the reliance on manual experience in the diagnosis of transformer core loosening faults, a diagnosis method for transformer core looseness based on the Gram angle field (GAF), residual network (ResNet), and multi-head attention mechanism (MA) is proposed. This method automatically learns effective fault features directly from GAF images without the need for manual feature extraction. Firstly, the vibration signal is denoised using ensemble empirical mode decomposition (EEMD), and the one-dimensional temporal signal is converted into a two-dimensional image using Gram angle field to generate an image dataset. Subsequently, the image set is input into ResNet to train the model, and the output of ResNet is weighted and summed using a multi-head attention module to obtain the deep feature representation of the image signal. Finally, the classification probabilities of different iron-core loosening states of the transformer are output through fully connected layers and Softmax layers. The experimental results show that the diagnostic model proposed in this paper has an accuracy of 99.52% in identifying loose iron cores in transformers, and can effectively identify loose iron cores in different positions. It is suitable for the identification and diagnosis of loose iron cores in transformers. Compared with traditional methods, this method has better fault classification performance and noise resistance. Full article

Emotion recognition is critical to understanding students’ emotional states. However, problems such as crowded classroom environments, changing light, and occlusion often affect the accuracy of recognition. This study proposes an emotion recognition algorithm specifically for classroom environments. Firstly, the study adds the self-made MCC module and the Wise-IoU loss function to make object detection in the YOLOv8 model more accurate and efficient. Compared with the native YOL0v8x, it reduces the parameters by 16% and accelerates the inference speed by 20%. Secondly, in order to address the intricacies of the classroom setting and the specific requirements of the emotion recognition task, a multi-channel emotion recognition network (MultiEmoNet) has been developed. This network fuses skeletal, environmental, and facial information, and introduces a central loss function and an attention module AAM to enhance the feature extraction capability. The experimental results show that MultiEmoNet achieves a classification accuracy of 91.4% on a homemade classroom student emotion dataset, which is a 10% improvement over the single-channel classification algorithm. In addition, this study also demonstrates the dynamic changes in students’ emotions in the classroom through visual analysis, which helps teachers grasp students’ emotional states in real time. This paper validates the potential of multi-channel information-fusion deep learning techniques for classroom teaching analysis and provides new ideas and tools for future improvements to emotion recognition techniques. Full article

Aiming at the problem that the vibration signals of rolling bearings in high-speed rail traction motors are often affected by noise when they are in a fault state, which makes it very difficult to extract the fault features during fault diagnosis and causes obstruction in fault classification. The article proposes a rolling bearing fault diagnosis based on optimized variational mode decomposition (VMD) combined with signal features and an improved convolutional neural network (CNN). The golden jackal optimization (GJO) algorithm is employed to optimize the key parameters of the VMD, enabling effective signal decomposition. The decomposed signals are then filtered and reconstructed using criteria based on kurtosis and interrelationship measures. The time-domain features of the reconstructed signals are computed, and the feature vectors are constructed, which are used as inputs to the deep learning network; the CNN combined with the support vector machine (SVM) network model is used for the extraction of the features and the classification of the faults. The experimental results show that the method can effectively extract fault features in noise-covered signals, and the accuracy is also significantly improved compared with traditional methods. Full article

Background/Objectives: Dermatological complaints are commonly seen in the emergency department (ED) setting and may be attributed to infectious, inflammatory, allergic, hypersensitivity, or traumatic processes, yet few studies have been carried out in Saudi Arabia addressing this topic. This study, therefore, aimed to explore this issue by investigating the most common dermatology-related ED encounters in a large tertiary care center in Riyadh, Saudi Arabia, and estimating the incidence of these encounters. Methods: This was a retrospective cohort study conducted in the ED of King Abdulaziz Medical City, a tertiary care center in Riyadh, Saudi Arabia. Data included all patients with dermatology-related ED visits during the period of 2022–2023. Demographic information including, for example, age and sex was collected. The International Classification of Diseases, 10th Revision (ICD-10) was used for the classification of diagnoses. Results: A total of 11,443 patients were included in the study, with male patients making up the majority (54.9%). The mean age upon diagnosis was 22.4 ± 23.2 years. More than half of the patients (55.3%) were diagnosed during childhood (<18), while proportions of older ages declined gradually. Average monthly presentations ranged from 400 to 560. Rash and non-specific skin eruptions (16%), cellulitis (13.6%), and urticaria (12.2%) were the most frequent dermatological emergencies. Conclusions: This study examined the dermatological conditions commonly seen in the emergency department. The findings highlighted a range of dermatology diseases that are typically seen in the ED. Addressing these prevalent disorders in the future will enhance ER physicians’ understanding and management of such common dermatological problems. Full article

Autoimmune diseases represent a severe personal and healthcare problem that seeks novel therapeutic solutions. Mesenchymal stem cells (MSCs) are multipotent cells with interesting cell biology and promising therapeutic potential. The immunoregulatory effects of secretory factors produced by umbilical cord mesenchymal stem cells (UC-MSCs) were assessed on B lymphocytes from 17 patients with systemic lupus erythematosus (SLE), as defined by the 2019 European Alliance of Associations for Rheumatology (EULAR)/American College of Rheumatology (ACR) classification criteria for SLE, and 10 healthy volunteers (HVs). Peripheral blood mononuclear cells (PBMCs) from patients and HVs were cultured in a UC-MSC-conditioned medium (UC-MSCcm) and a control medium. Flow cytometry was used to detect the surface expression of CD80, CD86, BR3, CD40, PD-1, and HLA-DR on CD19+ B cells and assess the percentage of B cells in early and late apoptosis. An enzyme-linked immunosorbent assay (ELISA) quantified the production of BAFF, IDO, and PGE2 in PBMCs and UC-MSCs. Under UC-MSCcm influence, the percentage and mean fluorescence intensity (MFI) of CD19+BR3+ cells were reduced in both SLE patients and HVs. Regarding the effects of the MSC secretome on B cells in lupus patients, we observed a decrease in CD40 MFI and a reduced percentage of CD19+PD-1+ and CD19+HLA-DR+ cells. In contrast, in the B cells of healthy participants, we found an increased percentage of CD19+CD80+ cells and decreased CD80 MFI, along with a decrease in CD40 MFI and the percentage of CD19+PD-1+ cells. The UC-MSCcm had a minimal effect on B-cell apoptosis. The incubation of patients’ PBMCs with the UC-MSCcm increased PGE2 levels compared to the control medium. This study provides new insights into the impact of the MSC secretome on the key molecules involved in B-cell activation and antigen presentation and survival, potentially guiding the development of future SLE treatments. Full article

Cancer-related diseases are some of the major health hazards affecting individuals globally, especially breast cancer. Cases of breast cancer among women persist, and the early indicators of the diseases go unnoticed in many cases. Breast cancer can therefore be treated effectively if the detection is correctly conducted, and the cancer is classified at the preliminary stages. Yet, direct mammogram and ultrasound image diagnosis is a very intricate, time-consuming process, which can be best accomplished with the help of a professional. Manual diagnosis based on mammogram images can be cumbersome, and this often requires the input of professionals. Despite various AI-based strategies in the literature, similarity in cancer and non-cancer regions, irrelevant feature extraction, and poorly trained models are persistent problems. This paper presents a new Multi-Feature Attention Network (MFAN) for breast cancer classification that works well for small lesions and similar contexts. MFAN has two important modules: the McSCAM and the GLAM for Feature Fusion. During channel fusion, McSCAM can preserve the spatial characteristics and extract high-order statistical information, while the GLAM helps reduce the scale differences among the fused features. The global and local attention branches also help the network to effectively identify small lesion regions by obtaining global and local information. Based on the experimental results, the proposed MFAN is a powerful classification model that can classify breast cancer subtypes while providing a solution to the current problems in breast cancer diagnosis on two public datasets. Full article

This study proposes a system for analyzing non-face-to-face counseling data using text-mining techniques to assess psychological states and automatically classify them into predefined categories. The system addresses the challenge of understanding internal issues that may be difficult to express in traditional face-to-face counseling. To solve this problem, a counseling management system based on text mining was developed. In the experiment, we combined TF-IDF and Word Embedding techniques to process and classify client counseling data into five major categories: school, friends, personality, appearance, and family. The classification performance achieved high accuracy and F1-Score, demonstrating the system’s effectiveness in understanding and categorizing clients’ emotions and psychological states. This system offers a structured approach to analyzing counseling data, providing counselors with a foundation for recommending personalized counseling treatments. The findings of this study suggest that in-depth analysis and classification of counseling data can enhance the quality of counseling, even in non-face-to-face environments, offering more efficient and tailored solutions. Full article

Automatic clothes pattern recognition is important to assist visually impaired people and for real-world applications such as e-commerce or personal fashion recommendation systems, and it has attracted increased interest from researchers. It is a challenging texture classification problem in that even images of the same texture class expose a high degree of intraclass variations. Moreover, images of clothes patterns may be taken in an unconstrained illumination environment. Machine learning methods proposed for this problem mostly rely on handcrafted features and traditional classification methods. The research works that utilize the deep learning approach result in poor recognition performance. We propose a deep learning method based on an ensemble of convolutional neural networks where feature engineering is not required while extracting robust local and global features of clothes patterns. The ensemble classifier employs a pre-trained ResNet50 with a non-local (NL) block, a squeeze-and-excitation (SE) block, and a coordinate attention (CA) block as base learners. To fuse the individual decisions of the base learners, we introduce a simple and effective fusing technique based on entropy voting, which incorporates the uncertainties in the decisions of base learners. We validate the proposed method on benchmark datasets for clothes patterns that have six categories: solid, striped, checkered, dotted, zigzag, and floral. The proposed method achieves promising results for limited computational and data resources. In terms of accuracy, it achieves 98.18% for the GoogleClothingDataset and 96.03% for the CCYN dataset. Full article

Sida mottle virus (SiMoV) and Sida micrantha mosaic virus (SiMMV) are major Brazilian begomoviruses (Geminiviridae). However, the range of DNA–A identity of isolates of these viruses (81–100%) is not in agreement with the current criteria for Begomovirus species demarcation (<91%). To clarify this putative classification problem, we performed a comprehensive set of molecular analyses with all 53 publicly available isolates (with complete DNA–A genomes) designated as either SiMoV or SiMMV (including novel isolates obtained herein from nationwide metagenomics-based studies). Two well-defined phylogenetic clusters were identified. The SiMMV complex (n = 47) comprises a wide range of strains (with a continuum variation of 88.8–100% identity) infecting members of five botanical families (Malvaceae, Solanaceae, Fabaceae, Oxalidaceae, and Passifloraceae). The SiMoV group now comprises eight isolates (90–100% identity) restricted to Malvaceae hosts, including one former reference SiMMV isolate (gb|NC_077711) and SP77 (gb|FN557522; erroneously named as “true SiMMV”). Iteron analyses of metagenomics-derived information allowed for the discovery of the missing DNA–B cognate of SiMoV (93.5% intergenic region identity), confirming its bipartite nature. Henceforth, the correct identification of SiMoV and SiMMV isolates will be a crucial element for effective classical and biotech resistance breeding of the viral host species. Full article

In order to improve the accuracy and efficiency of flow pattern recognition and to solve the problem of the real-time monitoring of flow patterns, which is difficult to achieve with traditional visual recognition methods, this study introduced a flow pattern recognition method based on a convolutional neural network (CNN), which can recognize the flow pattern under different pressure and flow conditions. Firstly, the complex gas–liquid distribution and its velocity field in the annulus were investigated using a computational fluid dynamics (CFDs) simulation, and the gas–liquid distribution and velocity vectors in the annulus were obtained to clarify the complexity of the flow patterns in the annulus. Subsequently, a sequence model containing three convolutional layers and two fully connected layers was developed, which employed a CNN architecture, and the model was compiled using the Adam optimizer and the sparse classification cross entropy as a loss function. A total of 450 images of different flow patterns were utilized for training, and the trained model recognized slug and annular flows with probabilities of 0.93 and 0.99, respectively, confirming the high accuracy of the model in recognizing annulus flow patterns, and providing an effective method for flow pattern recognition. Full article

Due to increasing traffic congestion, travel modeling has gained importance in the development of transportion mode detection (TMD) strategies over the past decade. Nowadays, recent smartphones, equipped with integrated inertial measurement units (IMUs) and embedded algorithms, can play a crucial role in such development. In particular, obtaining much more information on the transportation modes used by users through smartphones is very challenging due to the variety of the data (accelerometers, magnetometers, gyroscopes, proximity sensors, etc.), the standardization issue of datasets and the pertinence of learning methods for that purpose. Reviewing the latest progress on TMD systems is important to inform readers about recent datasets used in detection, best practices for classification issues and the remaining challenges that still impact the detection performances. Existing TMD review papers until now offer overviews of applications and algorithms without tackling the specific issues faced with real-world data collection and classification. Compared to these works, the proposed review provides some novelties such as an in-depth analysis of the current state-of-the-art techniques in TMD systems, relying on recent references and focusing particularly on the major existing problems, and an evaluation of existing methodologies for detecting travel modes using smartphone IMUs (including dataset structures, sensor data types, feature extraction, etc.). This review paper can help researchers to focus their efforts on the main problems and challenges identified. Full article

VIKOR uses the idea of overall utility maximization and individual regret minimization to afford a compromise result for multi-attribute decision-making problems with conflicting attributes. Many researchers have proposed corresponding improvements and expansions to make it more suitable for sorting optimization in their respective research fields. However, these improvements and extensions only rank the alternatives without classifying them. For this purpose, this text introduces the three-way sequential decisions method and combines it with the VIKOR method to design a three-way VIKOR method that can deal with both ranking and classification. By using the final negative ideal solution (NIS) and the final positive ideal solution (PIS) for all alternatives, the individual regret value and group utility value of each alternative were calculated. Different three-way VIKOR models were obtained by four different combinations of individual regret value and group utility value. In the ranking process, the characteristics of VIKOR method are introduced, and the subjective preference of decision makers is considered by using individual regret, group utility, and decision index values. In the classification process, the corresponding alternatives are divided into the corresponding decision domains by sequential three-way decisions, and the risk of direct acceptance or rejection is avoided by putting the uncertain alternatives into the boundary region to delay the decision. The alternative is divided into decision domains through sequential three-way decisions, sorted according to the collation rules in the same decision domain, and the final sorting results are obtained according to the collation rules in different decision domains. Finally, the effectiveness and correctness of the proposed method are verified by a project investment example, and the results are compared and evaluated. The experimental results show that the proposed method has a significant correlation with the results of other methods, ad is effective and feasible, and is simpler and more effective in dealing with some problems. Errors caused by misclassification is reduced by sequential three-way decisions. Full article

Deep learning methods have shown significant advantages in polarimetric synthetic aperture radar (PolSAR) image classification. However, their performances rely on a large number of labeled data. To alleviate this problem, this paper proposes a PolSAR image classification method with a Masked Autoencoder based on Position prediction and Memory tokens (MAPM). First, MAPM designs a Masked Autoencoder (MAE) based on the transformer for pre-training, which can boost feature learning and improve classification results based on the number of labeled samples. Secondly, since the transformer is relatively insensitive to the order of the input tokens, a position prediction strategy is introduced in the encoder part of the MAE. It can effectively capture subtle differences and discriminate complex, blurry boundaries in PolSAR images. In the fine-tuning stage, the addition of learnable memory tokens can improve classification performance. In addition, ${\mathit{L}}_1$ loss is used for MAE optimization to enhance the robustness of the model to outliers in PolSAR data. Experimental results show the effectiveness and advantages of the proposed MAPM in PolSAR image classification. Specifically, MAPM achieves performance gains of about 1% in classification accuracy compared with existing methods. Full article

Individual physiotherapy is crucial in treating patients with various pain and health issues, and significantly impacts abdominal surgical outcomes and further medical problems. Recent technological and artificial intelligent advancements have equipped healthcare professionals with innovative tools, such as sensor systems and telemedicine equipment, offering groundbreaking opportunities to monitor and analyze patients’ physical activity. This paper investigates the potential applications of mobile accelerometers in evaluating the symmetry of specific rehabilitation exercises using a dataset of 1280 tests on 16 individuals in the age range between 8 and 75 years. A comprehensive computational methodology is introduced, incorporating traditional digital signal processing, feature extraction in both time and transform domains, and advanced classification techniques. The study employs a range of machine learning methods, including support vector machines, Bayesian analysis, and neural networks, to evaluate the balance of various physical activities. The proposed approach achieved a high classification accuracy of 90.6% in distinguishing between left- and right-side motion patterns by employing features from both the time and frequency domains using a two-layer neural network. These findings demonstrate promising applications of precise monitoring of rehabilitation exercises to increase the probability of successful surgical recovery, highlighting the potential to significantly enhance patient care and treatment outcomes. Full article

Prediction tasks over pixels in hyperspectral images (HSI) require careful effort to engineer the features used for learning a classifier. However, the generated classification map may suffer from an over-smoothing problem, which is manifested in significant differences from the original image in terms of object boundaries and details. To address this over-smoothing problem, we designed a method for extracting spectral–spatial-band-correlation (SSBC) features. In SSBC features, joint spectral–spatial feature extraction is considered a discrete cosine transform-based information compression, where a flattening operation is used to avoid the high computational cost induced by the requirement of distillation from 3D images for joint spectral–spatial information. However, this process can yield extracted features with lost spectral information. We argue that increasing the spectral information in the extracted features is the key to addressing the over-smoothing problem in the classification map. Consequently, the normalized difference vegetation index and iron oxide are improved for HSI data in extracting band-correlation features as added spectral information because their calculations, involving two spectral bands, are not appropriate for the abundant spectral bands of HSI. Experimental results on four real HSI datasets show that the proposed features can significantly mitigate the over-smoothing problem, and the classification performance is comparable to that of state-of-the-art deep features. Full article