Advance driver assistance systems (ADAS) swiftly and effectively detect oncoming cars’ lanes-changing intentions in intelligent transportation, supporting decision support and safety. Current techniques fail to account for vehicle interactions and trajectory data temporal dependencies; hence this research proposes a multi-model fusion-based lane-changing intention recognition framework for intelligent transportation. Using actual vehicle trajectory data from a dataset, the suggested model is verified and contrasted with several well used baseline models. According to the experimental findings, the lane change intention detection technique can greatly increase prediction accuracy by fusing attention processes, reinforcement learning-based CRF, and vehicle interaction data. The system’s main components are input processing and lane-changing intention recognition. Vehicle trajectory data is cleaned, labelled, sliced, and one-hot encoded during input processing BiLSTM-F model detects driver lane-change intent, enhanced by incorporating attention mechanism to the Bidirectional Long Short-Term Memory (BiLSTM) network, the model may give changing weights to input processing section output. This lets the model focus on lane-changing intention-affecting factors. Finally, a Reinforcement Learning-based Conditional Random Field (CRF) efficiently determines the globally optimal lane-changing intention. This field fully represents input data temporal interdependence. The model was trained and tested on the public NGSIM dataset. Validation results show it can achieve up to 97.19% accuracy and predict a vehicle’s lane change intention with 94.16% accuracy, two seconds before the actual maneuver occurs. The suggested model outperforms baseline lane-changing intention recognition models in terms of accuracy, loss performance, F1 score, and stability.

Generative Artificial Intelligence (GAI) is emerging as a transformative force that empowers transnational education (TNE) in engineering. Recent trends indicate a significant shift in the application of generative AI in engineering policies, academic research, business practices, and educational settings throughout TNE. Governments and organizations are transitioning from restrictive stances to developing guiding frameworks for its application, enabling cross-border collaboration in TNE. Numerous universities have permitted and even promoted the utilization of GAI. Furthermore, academic research around the world is looking into the pros and cons of GAI in engineering education, focusing on how it can help teachers and keep students interested. Industrial applications are diversifying, extending across disciplines, and TNE is occurring in engineering contexts, including cross-border programs. GAI possesses the capacity to transform TNE by revolutionizing talent development, reformulating engineering models, and facilitating scientific assessment across multinational frameworks. However, problems like the generative illusion, ethical and ideological risks, lack of trust between teachers and students, and new threats to TNE in engineering equity in global settings require substantial focus. This study examines these concerns and outlines potential strategies to leverage GAI for transnational education in engineering, offering stakeholders the opportunity to prioritize AI literacy among educators and learners. This work emphasizes that cross-disciplinary and collaborative R&D, following national and international standards, should tackle application hurdles while guaranteeing safety and inclusion. This study also addresses several future directions that can contribute to creating a unified framework and cost-effective solutions. These solutions, integrated with platforms like the National Smart Education Platform, can bridge digital divides, ensuring equitable access and enabling global TNE stakeholders to capitalize on the GAI revolution. We also provide several statistics and case studies to show the effectiveness of GAI over TNE in engineering and provide practical solutions for the incorporation of GAI into TNE within engineering frameworks, guaranteeing inclusivity and equity.

The interactive attention graph convolution network (IAGCN), a novel model proposed in this article, will revolutionize aspect-level sentiment analysis (SA). IAGCN effectively addresses these key features, in contrast to prior research that ignored the meaning of aspect terms and their relationship with context. The model combines a modified dynamic weighting layer with bidirectional long short-term memory (BiLSTM) to accurately acquire context. It takes use of graph convolutional networks (GCNs) to encrypt syntactic information from the syntactic dependency tree. Furthermore, a method for interactive attention is employed to discover the intricate relationships between context and aspect terms, which results in the reconstruction of those terms’ representations. Comparing the proposed IAGCN model to baseline models, impressive gains are made. Across five datasets, the model beats previous methods with an amazing improvement in F1 scores that ranges from 1.34% to 4.04% and an impressive improvement in accuracy that ranges from 0.56% to 1.75%. Additionally, the IAGCN model outperforms the global vectors (GloVe)-based strategy when the potent pretrained model bidirectional encoder representations from transformers (BERT) is included in the challenge, resulting in even greater improvements. The F1 score considerably increases from 2.59% to 7.55%, and accuracy increases from 1.47% to 3.95%, making the IAGCN model a standout performer in aspect-level SA.

With the advancement in Tiny Machine Learning (ML) technologies, their application in enhancing unmanned aerial vehicles (UAVs) for hydraulic engineering surveying and mapping has become increasingly significant. TinyML’s integration offers a leap in processing efficiency and capabilities, particularly in addressing challenges such as UAV search and monitoring due to loss of contact or forced landings. The usage of medical cyber-physical systems in healthcare can revolutionize existing service delivery methods. The study focuses into the spatial grid mapping technique for three-dimensional information, the PTZ camera spatial grid target locking algorithm, and the UAV detection and image correction algorithm. The UAV target is processed using the surveying UAV target tracking method. TinyML techniques are essential for processing and analyzing these photos quickly. Precise UAV identification and tracking are made possible by the combination of image recognition and radar data, which are then processed using TinyML algorithms. This study explores the complexities of algorithms designed specifically for TinyML, such as tracking, UAV detection, grid mapping, and 3D grid space division. Experimental results validate the enhanced capability of this. The results show how well the proposed technique maps and surveys water conservation regions while promptly catching, locking onto, and tracking drones. The algorithm in this study betters than the YOLO, SSD, and RetinaNet algorithms in the recognition and detection of image-oriented surveying and mapping drones.

With the advancement of intelligent transportation cyber-physical systems (TCPS), significant opportunities for Vehicular Ad-hoc transportation cyber-physical systems (VTCPS) have been evolved, yet they also encounter several security challenges. A distributed intelligent trust management strategy (ITMS), is presented to mitigate potential internal attackers and false messages in VTCPS. Given the attributes of VTCPS, the system assesses the trustworthiness of vehicle nodes within the network with an enhanced subjective logic model that integrates both direct and indirect trust, thereby building trust connections among nodes based on their contact histories. The reliability of communications is assessed based on node trust and inter-node distance, while deceptive messages and malevolent nodes inside the network are detected according to the trust evaluation outcomes. To assess the efficacy of the proposed method, four distinct assault scenarios were devised, and comparative experiments were executed on the Veins vehicular network simulation platform to evaluate the performance of the ITMS scheme under diverse attack conditions. The experimental findings indicate that the ITMS scheme can proficiently counteract diverse attacks in VTCPS and can still detect the majority of fraudulent messages and malevolent nodes, even with a 40% ratio of malicious nodes. Furthermore, the efficacy of the ITMS scheme markedly surpasses that of the baseline scheme, which consists of a subjective logic model and a distance-based weighted voting mechanism.

Social media networking platforms connect people living in every corner of the world. Twitter has now become a popular microblogging service, allowing users to express themselves and keep up with current events. Twitter has attracted spammers because to its popularity and ease of use. As a result, spam identification (ID) has become one of the most pressing issues. It is vital to detect and filter spam tweets as well as their owners in order to provide a spam-free environment. In this article, a spam detection method is proposed using a swarm optimization approach on a tweet-by-tweet basis. A spam tweet detection dataset is used to train the machine learning (ML) model. Metaheuristic features are created based on the input features in the dataset. Whale swam optimization algorithm (WOA) is used to select the important features before classification. The conventional objective function of WOA is modified into stochastic gradient descent (SGD) to perform feature selection. The selected subset of features is used to train the Adaboost (AB) classifier to detect the spam in the tweets. The AB classifier produced the best results in combination with WOA and SGD. The obtained accuracy is 99.85% in testing with a minimum subset of seven features and in the least possible minimum time of 17.9 s.

For changing semantics, ontological and information presentation, as well as computational linguistics for Asian social networks, are one of the most essential platforms for offering enhanced and real-time data mapping, as well as huge data access across diverse big data sources on the web architecture, information extraction mining, statistical modeling and data modeling, database control, and so on. The concept of opinion or sentiment analysis is often used to predict or classify the textual data, sentiment, affect, subjectivity, and other emotional states in online text. Recognizing the message's positive and negative thoughts or opinions by examining the author's goals will aid in a better understanding of the text's content in terms of the stock market. An intelligent ontology and knowledge Asian social network solution can improve the effectiveness of a company's decision making support procedures by deriving important information about users from a wide variety of web sources. However, ontology is concerned primarily with problem-solving knowledge discovery. The utilization of Internet-based modernizations welcomed a significant effect on the Indian stock exchange. News related to the stock market in the most recent decade plays a vital role for the brokers or users. This article focuses on predicting stock market news sentiments based on their polarity and textual information using the concept of ontological knowledge-based Convolution Neural Network (CNN) as a machine learning approach. Optimal features are essential for the sentiment classification model to predict the stock's textual reviews' exact sentiment. Therefore, the swarm-based Artificial Bee Colony (ABC) algorithm is utilized with the Lexicon feature extraction approach using a novel fitness function. The main motivation for combining ABC and CNN is to accelerate model training, which is why the suggested approach is effective in predicting emotions from stock news.

Diabetic retinopathy (DR) is on the increase nowadays due to the high sugar level in the blood, and it is the reason for blindness that mainly occurs in middle-aged people. Furthermore, the Internet of Medical Things (IoMT) enabled computer-aided diagnostic (CAD) systems record DR-related data online and give patients with reassuring information. The internet allows for the interconnection of a variety of smart devices, enabling remote healthcare systems based on the IoMT to link patients with medical professionals. The proper diagnosis of diabetic patients and detection of DR severity in earlier stages help in preventing blindness. Therefore, the basic aim of this study is to prevent the diabetic patient from losing vision by detecting and classifying the severity of DR fundus images using the IoMT-enabled CAD system. This article designed a novel diabetic retinopathy classification (DRC) system by hybridizing the DL model with optimization algorithms to classify the DR images based on severity. This system begins with preprocessing phase for removing the noise from edges. Next, the proposed K-mean cluster-based growing region segmentation is employed to extract the useful region from the images. Then, pretrained convolutional neural network (CNN) model, i.e., RESnet with the proposed hybrid genetic and ant colony optimization (HGACO) algorithm, is applied to extract the features from the region of interest (ROI) and classify them into four severity levels. Performance indices such as AUC,$F$-measure, accuracy, sensitivity, and specificity are analyzed to evaluate the performance on MESSIDOR dataset. The performance of the proposed DRC system is compared with state-of-the-art classification systems. The proposed HGACO algorithm is also compared with Adam and gradient descent (GD) optimizers. The system is also evaluated by employing different parameters of CNN and HGACO. Additionally, for the determination of the classification accuracy of the DRC system, the confidence interval statistical test is implemented considering various parameters and configurations of the neural network. The results revealed that the proposed DR system provides higher classification results by achieving 95.78%, 91.98%, 97.7%, and 94.56% AUC, sensitivity, accuracy, and specificity rate, respectively. CNN alleviates the difficulty of developing image features, whereas the HGACO algorithm-based technique automates CNN hyperparameter design.

Traditional classification algorithms struggle to categorize hypertensive retinopathy (HR) lesions correctly because they lack obvious characteristics. A regional IoT-enabled federated learning-based HR categorization approach (IoT-FHR) incorporating global and local attributes is suggested as a solution to this issue. The local feature arterial and venous nicking (AVN) classification model is fused with the overall IoT-FHR classification model to enhance the effect of the classification of IoT-FHR. The AVN classification model’s local lesion characteristics and the IoT-FHR classification model’s global lesion characteristics were combined using feature mean. After that, the results of the global IoT-FHR classification model are averaged with the results of the local AVN classification model. An easy neural network receives its input from the final outcome. The probability value of IoT-FHR in the fundus image is output by the sigmoid classifier after the neural network’s two fully connected and one dropout layer. The AVN classification makes a new kind of intersection detection algorithm suggestion. To determine the intersection points, the algorithm applies a logical AND operation to the classified arteries and veins. It takes HR fundus pictures and extracts AVN image blocks using the region of interest extraction approach. The accuracy, sensitivity, and specificity of the suggested fusion model are 93.50%, 69.83%, and 98.33%, respectively, when tested on a private dataset. It is clear from the experiments and results that the suggested model leads the currently used methods when the single-stage classification model is compared with them.