Explore the vast range of titles available.

Due to the small size and scattered distribution of insulator defects, achieving high detection accuracy remains challenging. To overcome shortcomings in current feature extraction techniques and detection precision, this research proposes several improvements. First, DSConv is utilized to reconstruct the neck network, enhancing defect feature extraction capabilities. Second, the LSKA (Large Separable Kernel Attention) attention mechanism is introduced to strengthen key feature capture, thereby improving model robustness. Finally, an improved Inner-WIoU loss function is employed to optimize the weighting of small-object and general sample attention. Test findings show the suggested upgrades markedly boost both speed and precision in detection.

To address the limitations of current fault location technologies, this paper proposes a distribution network fault location model based on 1DCNN-BiLSTM. 1DCNN effectively extracts local features from fault data, offering unique advantages in processing one-dimensional data. BiLSTM excels at capturing long-term dependencies in sequence data, making it highly effective for time series data. By integrating 1DCNN and BiLSTM, the 1DCNN-BiLSTM model leverages the strengths of both, enabling efficient processing and analysis of distribution network fault signals. Additionally, the model incorporates an attention mechanism to focus more on critical fault features, enhancing the efficiency and accuracy of feature extraction. Furthermore, transfer learning techniques can be applied to quickly adapt the model to new fault scenarios using existing fault data and models, thereby reducing training time and data requirements.

Convolutional Networks have been demonstrated to be particularly useful for extracting high level feature in structural data. Temporal convolutional network (TCN) is a framework which employs casual convolutions and dilations so that it is adaptive for sequential data with its temporality and large receptive fields. In this paper, we apply TCN for anomaly detection in time series. We train the TCN on normal sequences and use it to predict trend in a number of time steps. Prediction errors are fitted by a multivariate Gaussian distribution and used to calculate the anomaly scores of points. In addition, a multi-scale feature mixture method is raised to promote performance. The validity of this method is confirmed on three real-world datasets.

To address the problem of image texture feature extraction, a direction measure statistic that is based on the directionality of image texture is constructed, and a new method of texture feature extraction, which is based on the direction measure and a gray level co-occurrence matrix (GLCM) fusion algorithm, is proposed in this paper. This method applies the GLCM to extract the texture feature value of an image and integrates the weight factor that is introduced by the direction measure to obtain the final texture feature of an image. A set of classification experiments for the high-resolution remote sensing images were performed by using support vector machine (SVM) classifier with the direction measure and gray level co-occurrence matrix fusion algorithm. Both qualitative and quantitative approaches were applied to assess the classification results. The experimental results demonstrated that texture feature extraction based on the fusion algorithm achieved a better image recognition, and the accuracy of classification based on this method has been significantly improved.

Accurate industrial load forecasting is essential for maintaining a balance between power supply and demand within intelligent power systems. In response to the challenges presented by the intricate, nonlinear, and temporal nature of industrial load data, a novel method integrating a Conditional Variational Autoencoder (CVAE) with a Transformer is introduced. The CVAE, conditioned on meteorological and economic data, excels in precise feature extraction from load data, effectively identifying critical patterns that influence load behavior. This specialized feature extraction is complemented by the Transformer, which refines the understanding of complex load dynamics through its temporal encoding and attention mechanisms. Experimental results using datasets from China and South Korea reveal substantial enhancements in forecasting precision compared to current models

The stethoscope is a commonly used medical device for diagnosing a patient’s condition by listening to their heartbeat. This diagnostic technique is known as auscultation, where each heart sound heard through the stethoscope has a distinct pattern that depends on the person’s heart condition. Researchers have developed computational methods that automatically analyze heart sounds to overcome the subjective nature of auscultation. In this study, we utilized the Hjorth method for feature extraction and the Long Short-Term RNN algorithm for classifying the normal and abnormal heart sounds. With 100 epochs, two layers of LSTM-RNN, and one layer of Dense, the classification accuracy for distinguishing normal and abnormal sounds reached 71.95%. This research aims to contribute to the development of an accurate system for detecting normal and abnormal heart sounds.

Feature extraction is the main core in diagnosis, classification, clustering, recognition, and detection. Many researchers may by interesting in choosing suitable features that used in the applications. In this paper, the most important features methods are collected, and explained each one. The features in this paper are divided into four groups; Geometric features, Statistical features, Texture features, and Color features. It explains the methodology of each method, its equations, and application. In this paper, we made acomparison among them by using two types of image, one type for face images (163 images divided into 113 for training and 50 for testing) and the other for plant images(130 images divided into 100 for training and 30 for testing) to test the features in geometric and textures. Each type of image group shows that each type of images may be used suitable features may differ from other types.

Stroke has a negative impact on people’s lives and is one of the leading causes of death and disability worldwide. Early detection of symptoms can significantly help predict stroke and promote a healthy lifestyle. Researchers have developed several methods to predict strokes using machine learning (ML) techniques. However, the proposed systems have suffered from the following two main problems. The first problem is that the machine learning models are biased due to the uneven distribution of classes in the dataset. Recent research has not adequately addressed this problem, and no preventive measures have been taken. Synthetic Minority Oversampling (SMOTE) has been used to remove bias and balance the training of the proposed ML model. The second problem is to solve the problem of lower classification accuracy of machine learning models. We proposed a learning system that combines an autoencoder with a linear discriminant analysis (LDA) model to increase the accuracy of the proposed ML model for stroke prediction. Relevant features are extracted from the feature space using the autoencoder, and the extracted subset is then fed into the LDA model for stroke classification. The hyperparameters of the LDA model are found using a grid search strategy. However, the conventional accuracy metric does not truly reflect the performance of ML models. Therefore, we employed several evaluation metrics to validate the efficiency of the proposed model. Consequently, we evaluated the proposed model’s accuracy, sensitivity, specificity, area under the curve (AUC), and receiver operator characteristic (ROC). The experimental results show that the proposed model achieves a sensitivity and specificity of 98.51% and 97.56%, respectively, with an accuracy of 99.24% and a balanced accuracy of 98.00%.

Conventional finger-vein recognition systems perform recognition based on the finger-vein lines extracted from the input images or image enhancement, and texture feature extraction from the finger-vein images. In these cases, however, the inaccurate detection of finger-vein lines lowers the recognition accuracy. In the case of texture feature extraction, the developer must experimentally decide on a form of the optimal filter for extraction considering the characteristics of the image database. To address this problem, this research proposes a finger-vein recognition method that is robust to various database types and environmental changes based on the convolutional neural network (CNN). In the experiments using the two finger-vein databases constructed in this research and the SDUMLA-HMT finger-vein database, which is an open database, the method proposed in this research showed a better performance compared to the conventional methods.