Real driving environment EEG-based detection of driving fatigue using the wavelet scattering network

With the continuous influx of application software onto the application software market, achieving accurate software recommendations for users in the huge software application market is urgent. To address this issue, each application software market currently provides its own classification tags. However, several problems still exist, such as the lack of objectivity, hierarchy, and standardization in these classifications, which in turn affects the accuracy of precise software recommendations. Accordingly, a customized BERTopic model is proposed to cluster the software description texts of the application software and the automatic tagging and updating of the application software tags are realized according to the clusters obtained by topic clustering and the extracted subject words. At the same time, a data enhancement method based on the c-TF-IDF algorithm is proposed to solve the problem of imbalance of datasets, and then the classification model based on the BERT-BiLSTM model is trained on the labeled datasets to classify the software in the dimension of the application function, so as to realize the accurate software recommendation for users. Based on the experimental verification of two datasets, 21 categories in the SourceForge dataset and 19 categories in the Chinese App Store dataset are subclassed by the clustering results of the customized BERTopic model, and the tags of 138 subclasses and 262 subclasses are formed, respectively. In addition, a complete tagged software description text dataset is constructed and the software tags are updated automatically. In the first stage of the classification experiment, the weighted average accuracy, recall rate, and F1 value can reach 0.92, 0.91, and 0.92, respectively. In the second stage, the weighted average accuracy, recall rate, and F1 value can all reach 0.96. After data enhancement, the weighted average F1 value of the classification model can be increased by up to two percentage points.

The advances in biomedical imaging equipment have produced a massive amount of medical images that are generated by the different modalities. Consequently, a huge volume of data has been produced and caused a complex and time-consuming retrieving process of the relevant cases. To resolve this issue, the Content-Based Biomedical Image Retrieval (CBMIR) system is applied to retrieve the related images from the earlier patients’ databases. However, the previous handcrafted features methods that applied the CBMIR model have shown poor performance in many multimodal databases. In this paper, we focus on designing CBMIR technique using Deep Learning (DL) models. We present a new Multimodal Biomedical Image Retrieval and Classification (M-BMIRC) technique for retrieving and classifying the biomedical images from huge databases. The proposed M-BMIRC model involves three dissimilar processes as following: feature extraction, similarity measurement, and classification. It uses an ensemble of handcrafted features from Zernike Moments (ZM) and deep features from Deep Convolutional Neural Networks (DCNN) for feature extraction process. Additionally, the Hausdorff Distance based similarity measure is employed to identify the resemblance between the queried image and the images that exist in the database. Moreover, the classification process gets executed on the retrieval images using the Probabilistic Neural Network (PNN) model, which allocates the class labels of the tested images. Finally, the experimental studies are conducted using two benchmark medical datasets and the results ensure the superior performance of the proposed model in terms of different measures include Average Precision Rate (APR), Average Recall Rate (ARR), F-score, accuracy, and Computation Time (CT).

Fast and accurate acquisition of the outline of rural buildings on remote sensing images is an efficient method to monitor illegal rural buildings. The traditional object detection method produces useless background information when detecting rural buildings; the semantic segmentation method cannot accurately segment the contours between buildings; the instance segmentation method cannot obtain regular building contours. The rotated object detection methods can effectively solve the problem that the traditional artificial intelligence method cannot accurately extract the outline of buildings. However, the rotated object detection methods are easy to lose location information of small objects in advanced feature maps and are sensitive to noise. To resolve these problems, this paper proposes a two-stage rotated object detection network for rural buildings (TRDet) by using a deep feature fusion network (DFF-Net) and a pixel attention module (PAM). Specifically, TRDet first fuses low-level location and high-level semantic information through the DFF-Net and then reduces the interference of noise information to the network through the PAM. The experimental results show that the mean average precession (mAP), precision, recall rate, and F1 score of the proposed TRDet are 83.57%, 91.11%, 86.5%, and 88.74%, respectively, which outperform the R2CNN model by 15%, 15.54%, 4.01%, and 9.87%. The results demonstrate that the TRDet can achieve better detection in small rural buildings and dense rural buildings.

Optical Character Recognition (OCR) is crucial for identifying and extracting information from scientific documents. However, recognizing online handwritten physics expressions remains a relatively unexplored area of research. In the existing literature, most of the researchers worked on CNN classification to identify mathematical expressions. The traditional Convolution Neural Network (CNN) has limitations for extracting sequential data. This study proposes a CRNN (Convolution Recurrent Neural Network)-LSTM (Long Short-Term Memory) model that uses sequence a to-sequence approach for recognition of online handwritten physics expressions to enhance the feature extraction process for the sequential data which overcomes the limitations of CNN. A dataset was constructed from 100 users using a Java-based interface, covering five commonly used types of physics expressions: (1) Electric flux; (2) Maxwell’s equations; (3) Inductance; (4) Pointing vector, and (5) Moment of inertia. This dataset identifies 25 unique Physics symbols. The Online Handwritten Physics Expression (OHPE) dataset comprises a total of 500 physics expressions, including operators, special symbols, alphabets, and numbers. The proposed architecture of CRNN-LSTM architecture consists of convolution layers followed by LSTM layers for sequence processing. CTC (Connectionist Temporal Classification) loss function is used to train the model, which is particularly used to predict the sequence of symbols within the physics expressions. The performance evaluation has been carried out and the accuracy of symbol level and expression level prediction is reported. In the final stage the trained model is evaluated to make the predictions on the unseen test set images with the recognition accuracy of 96.36% at the expression level and 98.10% at the symbol level.

Different deep convolution neural network (DCNN) models have been proposed for wafer map pattern identification and classification tasks in previous studies. However, factors such as the effect of input image resolution on the classification performance of the proposed models and class imbalance in the training set after splitting the data into training and test sets have not been considered in the previous studies. This study proposes a DCNN model with residual blocks, called Opt-ResDCNN model, for wafer map defect pattern identification and classification by considering 26 * 26 input image resolutions and class imbalance issues during the model training. The proposed model is compared with the previously published defect pattern recognition and classification models in terms of accuracy, precision, recall, and F1 score for 26 * 26 input image size. Using a publicly available wafer map dataset (WM-811K), the proposed method can obtain an average accuracy, precision, recall, and F1 score results of 99.672%, 99.664%, 99.695%, 99.692%, respectively for the 26 * 26 input image resolution.

In unconventional oil and gas resources, especially shale oil and gas resources with extremely low permeability and porosity, in order to develop effectively, it is necessary to establish perforation and multi-stage fracturing. The machine learning algorithm k-means clustering was used to cluster the five features selected to describe reservoir properties: shale content, porosity, total organic carbon content and those reflecting rock mechanical properties: Young’s modulus and Poisson’s ratio. The data were classified in a high-dimensional space to determine different perforation fracture stages. The classification algorithm XGboost was then used to predict different perforation stages using four conventional logging curves GR, NPRL, VP and DEN. The K-means clustering algorithm based on Euclidean distance can well classify the selected features in the high-dimensional space. The Hopkins statistics of clustering trend is 0.94, showing a good clustering trend. When the classification algorithm is used for prediction, the average accuracy is 0.92, the average recall rate is 0.90, and the average F1 score is 0.90, which can predict different perforated fracture stages well and optimize the design of the perforated fracture stage.

This paper represents automatic facial expression analysis method named Local Directional Stigma Mean Patterns (LDSMP) for automatic facial expression analysis and image retrieval using content based facial expression image retrieval and CNN. The traditional local patterns such as Local Binary Patterns (LBP) and Local Ternary Patterns (LTP) are applied for face recognition and expression analysis, calculated using relationship between the center pixel and neighboring pixels. The proposed method calculates the eight directional difference values then divided into the three ranges based on threshold values. Thus, the values are substituted with basic three positive values (+3, +2, +1) and three negative values (-3, -2, -1) to get more sensitive information from an image rather than aforementioned methods. The threshold can be select either static which is selected by user or dynamic is evaluated from image itself and supports to improve the efficiency. The performance of the proposed method is further improved by giving this patterns as input to the Convolutional Neural Networks (CNN) and compared with the existing methods LBP, LTP, and Directional Binary Code (DBC) in terms of Average Precision (AP), Average Recall (AR), and Average Retrieval Rate (ARR) using standard databases COREL 10K (DB1) and JAFFE (The Japanese Female Facial Expression) (DB2) and Extended Cohn-Kanade (CK +) (DB3) dataset.

Online leakage current classification using convolutional neural network long short-term memory for high voltage insulators on web-based service

ABSTRACTIn recent years, object-based segmentation methods and shallow-model classification algorithms have been widely integrated for remote sensing image supervised classification. However, as the image resolution increases, remote sensing images contain increasingly complex characteristics, leading to higher intraclass heterogeneity and interclass homogeneity and thus posing substantial challenges for the application of segmentation methods and shallow-model classification algorithms. As important methods of deep learning technology, convolutional neural networks (CNNs) can hierarchically extract higher-level spatial features from images, providing CNNs with a more powerful recognition ability for target detection and scene classification in high-resolution remote sensing images. However, the input of the traditional CNN is an image patch, the shape of which is scarcely consistent with a given segment. This inconsistency may lead to errors when directly using CNNs in object-based remote sensing classification: jagged errors may appear along the land cover boundaries, and some land cover areas may overexpand or shrink, leading to many obvious classification errors in the resulting image. To address the above problem, this paper proposes an object-based and heterogeneous segment filter convolutional neural network (OHSF-CNN) for high-resolution remote sensing image classification. Before the CNN processes an image patch, the OHSF-CNN includes a heterogeneous segment filter (HSF) to process the input image. For the segments in the image patch that are obviously different from the segment to be classified, the HSF can differentiate them and reduce their negative influence on the CNN training and decision-making processes. Experimental results show that the OHSF-CNN not only can take full advantage of the recognition capabilities of deep learning methods but also can effectively avoid the jagged errors along land cover boundaries and the expansion/shrinkage of land cover areas originating from traditional CNN structures. Moreover, compared with the traditional methods, the proposed OHSF-CNN can achieve higher classification accuracy. Furthermore, the OHSF-CNN algorithm can serve as a bridge between deep learning technology and object-based segmentation algorithms thereby enabling the application of object-based segmentation methods to more complex high-resolution remote sensing images.

Aiming at the problem that traditional convolutional neural networks cannot fully capture text features during feature extraction, and a single model cannot effectively extract deep text features, this paper proposes a text sentiment classification method based on the attention mechanism of LSTM-TCN hybrid model. First, use the Word2vec word vector model to transform words into the form of word vectors. Secondly, with Long Short-Term Memory (LSTM) to obtain the serialized feature information of the text, and then combined with the Temporal Convolutional Network (TCN) to sample and calculate the text features to extract more comprehensive feature information of the text. Then, combined with the attention mechanism, the influence of important information on the sentiment of the text is considered, and the effect of text sentiment classification is optimized. Finally, use softmax function to classify sentiment in the text classification layer. Multiple sets of comparative experiments were conducted on two sets of Chinese data sets, and the accuracy of the text model reached 93.06% and 91.08%, respectively, proving that the proposed model performs better than the traditional single convolutional neural network.

Tool wear is an inevitable and critical problem in manufacturing systems. Accurate prediction of tool wear under varying operation conditions is a hot and challenging problem. In this paper, temporal convolutional network (TCN) is employed to predict tool wear using raw sensor signals. Dilated causal convolution and residual connections are used in TCN to form a more flexible structure with stable training gradients for sequential modeling. In addition, auxiliary learning is used in this paper to enhance model performance under varying operation conditions. An auxiliary task of recognizing operating conditions is designed to support the tool wear prediction task. Experiment on a real milling wear dataset illustrates the superiority of TCN for tool wear prediction compared with traditional convolutional neural network (CNN) and long short-term memory (LSTM) network. Experimental results also demonstrate the effectiveness of the proposed auxiliary learning.

Handwritten digit recognition, a task in computer vision, is critical for applications such as postal automation, banking, and digitization of forms. Traditional approaches have leveraged statistical models, but the rise of deep learning, particularly Convolutional Neural Networks (CNN) and Long-Short Term Memory (LSTM), has revolutionized the field. However, a comprehensive performance comparison of CNN and LSTM architectures in the context of handwritten digit classification remains underexplored. This study aimed to address this gap by evaluating and comparing CNN and LSTM models for the classification of handwritten digits. Two machine learning models – Convolutional Neural Network (CNN) and Long-Short Term Memory (LSTM) were trained with the preprocessed handwritten digit dataset. The CNN model was designed with multiple convolutional and pooling layers, along with dropout for regularization. The LSTM model was designed with LSTM layers to capture sequential patterns in the data, followed by a dense layer for classification. The models were implemented in python, evaluated and compared based on accuracy, precision, recall and F1-score. The evaluation and comparison results indicate that CNN achieved 99.31% accuracy, 99.0% precision, 99.0% recall, and a 99.0% F1-score, while LSTM achieved 98.90% accuracy, 99.0% precision, 99.0% recall, and a 99.0% F1-score. The results demonstrated that CNN outperformed LSTM in terms of accuracy and misclassification errors, making it the optimal choice for image-based handwritten digit recognition. This finding underscores the efficiency of CNN in addressing challenges related to digit recognition, contributing to the advancement of automated digit classification systems and improving the accuracy of image-based classification tasks.

According to the problem of overfitting in the traditional Convolutional Neural Networks(CNN) with large samples, an improved sparse DropConnect algorithm is put forward. With proposed algorithm, the CNN is improved and optimized. The performance of the network in image recognition is verified. Experiments of weld image recognition and classification indicate that the selective ability of the CNN on the sparse feature is improved. High recognition accuracy and classification accuracy of test sample are achieved. Over-fitting in the traditional network model can be avoided. More important, the feature sparsity and discriminative ability of the CNN are increased.

Driver drowsiness is a major cause of road accidents worldwide, leading to thousands of injuries and fatalities each year. Detecting early signs of fatigue remains a critical challenge in road safety and intelligent transportation systems. This paper proposes a novel deep learning-based framework named SAFE-DRIVE-AI, designed to detect drowsiness in real-time by analyzing visual cues from the driver's eyes. The proposed framework integrates three components: A Convolutional Neural Network (CNN) to extract spatial features from eye images, a Long Short-Term Memory (LSTM) layer for capturing temporal patterns such as blink duration and frequency, and an Attention mechanism to enhance the model’s focus on the most relevant time steps. To validate the effectiveness of Deep Learning (DL) techniques, a comparative analysis was conducted using both traditional Machine Learning (ML) models (Logistic Regression, Decision Trees, Random Forest, and Support Vector Machines) and DL models (CNN, LSTM). The experimental results showed that the DL models significantly outperformed the ML ones in all metrics. The hybrid CNN+LSTM model achieved an accuracy of 97.3% and an F1-score of 96.8%, being the most accurate approach. SAFE-DRIVE-AI is designed for real-world deployment, with potential integration into edge devices, 5G-enabled systems, and real-time alert mechanisms. The proposed method offers a practical and intelligent solution for enhancing driver safety through proactive fatigue monitoring.

This research aims to implement deep learning techniques to determine fact and fake news in Indonesian language. The methods used are Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM). The stages of the research consisted of collecting data, labeling data, preprocessing data, word embedding, splitting data, forming CNN and LSTM models, evaluating, testing new input data and comparing evaluations of the established CNN and LSTM models. The Data are collected from a fact and fake news provider site that is valid, namely TurnbackHoax.id. There are 1786 news used in this study, with 802 fact and 984 fake news. The results indicate that the CNN and LSTM methods were successfully applied to determine fact and fake news in Indonesian language properly. CNN has an accuracy test, precision and recall value of 0.88, while the LSTM model has an accuracy test and precision value of 0.84 and a recall of 0.83. In testing the new data input, all of the predictions obtained by CNN are correct, while the prediction results obtained by LSTM have 1 wrong prediction. Based on the evaluation results and the results of testing the new data input, the model produced by the CNN method is better than the model produced by the LSTM method.