AI and machine learning are rewriting the rules of electric vehicle battery management
A comprehensive review of 120 studies finds that hybrid AI and machine learning architectures are transforming electric vehicle battery management, ...
Tag: Machine Learning
Machine Learning Reveals Genetic Divide Between Chinese Kirghiz and Kyrgyzstan Sheep
A new genomic study combining population genetics and machine learning reveals that Chinese Kirghiz sheep are genetically differentiated from neighboring ...
Blockchain Meets Machine Learning to Guard Wireless Sensor Networks Against Attackers
A new framework fuses an unsupervised machine learning ensemble with a lightweight blockchain to detect and confirm intrusions in wireless ...
A generalized supervised contrastive learning framework for integrative multi-omics prediction models
A new machine-learning framework called MB-SupConCon extends supervised contrastive learning to continuous responses, enabling more accurate and biologically interpretable prediction ...
Graph Topology Gives IoT Intrusion Detection a Hidden Edge
A graph-augmented framework called IOTTRUST enriches conventional IoT intrusion detection with network flow topology features, achieving 99.07 percent accuracy and ...
Scientists Can Now Read Trust in the Human Brain as It Rises and Falls in Real Time
A new EEG-based non-linear state-space model continuously infers trust in autonomous systems during a space-relevant supervisory task, outperforming linear and ...
AI spots gender in how speakers move, gaze and gesture in VR — even when performance looks identical
A virtual reality experiment with 55 participants found no gender differences in public speaking anxiety or expert-rated performance, yet machine ...
Machine Learning Meets Design of Experiments to Predict Hydrochar Properties at Scale
A new review shows how combining design of experiments with machine learning can transform hydrothermal carbonization from empirical tuning into ...
Laser-Patterned Metal Freezes Three Times Faster, and an AI Model Reveals Why
A Kansas State University team used a YOLOv11 neural network to track thousands of condensing droplets on laser-patterned aluminum, revealing ...
New AI Framework Maps Drug Sensitivity Down to Individual Cells in Bulk Tumor Samples
A new two-step machine-learning framework called CLIMB and CLIFF computationally deconvolves bulk RNA-seq and drug sensitivity data into cell-type and ...
Causal AI Meets Federated Learning in a New Hybrid Intrusion Detection Framework
Researchers in India have built a hybrid intrusion detection system combining causal learning, entropy-based feature compression, adversarial calibration, and federated ...
Why There Is No Single AI for Transplantation: The Two Questions That Decode Every Algorithm
Transplantation researchers argue that AI in transplant medicine consists of many narrow, single-purpose tools rather than one monolithic system, and ...
When Numbers Meet Words: Hybrid Data Representations Push Wearable Wellness AI Forward
A new study shows that how wearable sensor data is translated into language-model inputs—raw numbers, category labels, or both—critically shapes ...
Cheetahs and Lyrebirds Inspire a Smarter Way to Keep IoT Data Private
A new hybrid optimization algorithm inspired by cheetahs and lyrebirds generates optimal encryption keys that protect sensitive IoT data while ...
How Bacteria, Archaea and Human Cells Use Different Genetic Stop Signs to End Transcription
A new review argues that transcription termination signals operate as distinct grammars across bacteria, archaea and eukaryotes, and that matching ...
New Loss Function Helps AI Learn From Flawed Labels
The practical significance of the RECE approach becomes clearer when viewed against the broader economics of dataset construction. Annotating large ...
Brain-Reading Headsets in Classrooms Demand Built-In Ethical Rules, Researchers Warn
Researchers propose a 15-safeguard governance framework to protect children as brain-computer interfaces spread from laboratories into classrooms worldwide.
Finite Element Methods Are Quietly Rewriting the Rules of Precision Manufacturing
A new editorial in Frontiers in Manufacturing Technology surveys how finite element methods are transforming precision manufacturing, from laser shock ...
Three-Layer Granular Balls Give Clustering Algorithms a New Way to See Inside Complex Data
A new clustering algorithm called 3L-GBC models dense, transitional, and sparse regions within clusters using granular balls to better handle ...
Aboriginal Women Help Shape Interpretable AI for Perinatal Mental Health Care
Researchers combined generative AI data augmentation with an intrinsically interpretable machine-learning model to predict perinatal psychological distress among Aboriginal mothers ...
