Machine learning
STMicroelectronics, a global semiconductor leader, has revealed an inertial measurement unit (IMU) that combines sensors tuned for activity tracking and high-g impact measurement in a single, space-saving package. This innovative device, the LSM6DSV320X, is designed to provide accurate and personalized user experiences, and is expected to have a significant impact
Machine learning
Artificial intelligence (AI), particularly Large Language Models (LLMs) such as GPT-4, Gemini, and LLaMA, have revolutionized the field of computational biology and bioinformatics. Scientists have developed a novel framework called BioLLMBench to evaluate the performance of these LLMs in various bioinformatics tasks. The study assessed the performance of GPT-4, Gemini,
Machine learning
Researchers from Tokyo University of Marine Science and Technology have developed a system combining fluorescence spectroscopy and machine learning to identify the origins of Japanese green teas with high accuracy. The study aims to address the priority of accurate identification in the food industry due to the emergence of problems
Machine learning
Researchers from Imam Abdulrahman Bin Faisal University in Dammam, Saudi Arabia, have made significant strides in the field of sensor and actuator networks by employing deep learning methods to enhance human activity recognition. By utilizing three deep learning architectures - Convolutional Neural Networks (CNN), CNN-based autoencoders, and Long Short-Term Memory
Machine learning
Researchers at King Abdulaziz University have developed an Emotional Artificial Neural Network (EANN) model to predict ship fuel consumption with remarkable accuracy, addressing the challenges posed by complex environmental conditions and operational variability. The study examines the impact of climate change on maritime operations and fuel efficiency by analyzing climatic
Machine learning
Researchers at the University of California, San Diego (UCSD) have proposed a novel algorithm called Recursive Feature Machines (RFMs) that can explicitly perform feature learning, a process crucial for understanding how neural networks make accurate predictions. Recent work posited that common training algorithms for neural networks implicitly perform dimensionality reduction,
Machine learning
Researchers from Clemson University have made significant strides in utilizing Artificial Intelligence (AI) and Machine Learning (ML) to improve flood prediction models. According to a recent study, the application of Recurrent Neural Networks (RNNs) has led to notable enhancements in capturing the intensity and timing of flood events, particularly for
Machine learning
Scientists at the University of Zurich have embarked on an innovative study to investigate the capabilities of artificial intelligence (AI) in classifying legal interpretations. Utilizing a unique dataset and Large Language Models (LLMs), the research aims to determine how AI can be employed to identify complex features relevant to the
Machine learning
Researchers from Newcastle University have created an artificial intelligence-powered underwater vehicle designed to monitor marine mammals with minimal intrusion. The system, called SWiMM, uses a Unity simulation model and a Deep Reinforcement Learning backend to navigate and track targets underwater. This innovative approach aims to replace traditional tagging methods, which
Machine learning
The convergence of robotics and frontier artificial intelligence (AI) systems has significant implications for national security, according to a recent working paper. The paper assesses the potential risks associated with the proliferation of robotic embodiments of artificial general intelligence (AGI) and highlights the challenges policymakers face in balancing safety and
Machine learning
Researchers at Fudan University in Shanghai, China have developed a novel non-contact, bed-based micro-movement sensing system designed for accurate heart rate variability (HRV) monitoring. The system uses a polyvinylidene fluoride (PVDF) piezoelectric film sensor to detect ballistocardiogram (BCG) signals through a 10 cm thick mattress, ensuring both comfort and practicality
Machine learning
Researchers at Liaocheng University in Shandong, People's Republic of China, have employed four machine learning algorithms to analyze the sensitivity of parameters in the numerical simulation of particle flow code (PFC2D). By using support vector machine (SVM), random forest (RF), gradient boosting decision tree (GBDT), and xtreme gradient
