Machine learning
Research from the Technical University of Denmark (DTU) has uncovered trends and challenges in machine learning-based intrusion detection in Internet of Things (IoT) networks. The study, which analyzed datasets and machine learning techniques used from 2019 to 2024, found that certain datasets, such as BoT-IoT and TON_IoT, combined with
Machine learning
Researchers from Mediterranea University of Reggio Calabria have developed an artificial intelligence-based monitoring system to support the care of elderly individuals. The system, which combines Internet of Things (IoT) technologies with machine learning algorithms, is designed to recognize human movements and activities, allowing healthcare staff to assess the motor skills
Machine learning
Artificial intelligence and machine learning techniques can significantly reduce the environmental impact of Internet of Things (IoT) networks. Researchers from the Department of Information and Communication Technologies, Universidad Politécnica de Madrid, have developed an optimization framework leveraging machine learning to minimize the carbon footprint associated with IoT multi-hop network deployments.
Machine learning
Researchers at Edge University have made a significant contribution to the field of engineering by detailing new data on the privacy concerns associated with the rapid proliferation of Internet of Things (IoT) devices. According to the study, the increase in network packet traffic due to IoT devices has raised significant
Machine learning
Researchers at the Indian Institutes of Technology Kharagpur have developed a novel approach to generating legal questions using large language models (LLMs). The team created a dataset of 2023 pairs of context and keywords, covering multiple countries and languages, to benchmark the performance of several LLMs. The study also explored
Machine learning
Researchers from Bournemouth University have raised alarm bells regarding the addictive nature of ChatGPT, a transformative tool that enhances productivity, communication, and task automation across industries. The study, led by Ala Yankouskaya, highlights concerns that ChatGPT's personalized responses, emotional validation, and continuous engagement may lead to over-reliance, reducing
Machine learning
Researchers from the Qingdao University of Science and Technology have proposed a novel spatial multi-scale graph convolutional network (SGTB) that effectively captures complex spatial dependencies and global features in gene expression analysis. This advancement has significant implications for tasks such as cell type classification and gene regulatory network construction. By
Machine learning
Researchers from Hangzhou Normal University have made a significant contribution to the field of image restoration with the proposal of a novel network architecture, Multi-Stage progressive image restoration Network (MSTNet). This innovative model has the potential to improve the quality of endoscopic images, aiding doctors in making more accurate diagnoses
Machine learning
Researchers at Zhejiang University of Technology have made a significant breakthrough in the field of intelligent systems, developing a novel multiscale linear transformer forecaster called VTformer. This innovative model is designed to mine global variate correlation and long-term temporal dependence in time series data, providing multifaceted dynamics for downstream self-attention
Machine learning
Researchers at the Jiangsu Vocational Institute of Commerce have proposed a novel approach for transformer fault diagnosis using machine learning techniques. The study combines the Shapley Additive Explanations (SHAP) method for feature importance evaluation, the bald eagle search (BES) intelligent optimization algorithm for hyperparameter optimization, and the light gradient boosting
Algorithms
Researchers from Xi'an Jiaotong University have made significant contributions to the field of computational intelligence by proposing a novel approach to tuning the hyper-parameters of adaptive evolutionary algorithms. The team's variational reinforcement learning framework, named Reinforcement EM (REM), combines the expectation-maximization (EM) algorithm and a reinforcement
Machine learning
Researchers from Nanyang Technological University have developed a novel approach to reinforcement learning that utilizes a discrete-time reward for decision-making in complex systems. This innovative method, described in a recent study published in the National Science Open journal, enables the extraction of a unique continuous-time decision law and improves computational
