Graph-Based Framework Detects IoT Anomalies Without Labels
A new self-supervised graph neural network framework, GraphContrast-IoT, improves anomaly detection in industrial IoT sensor networks by combining physical topology ...
Tag: temporal convolutional network
Wavelet Framework Achieves 72.85 Percent Accuracy Predicting Continuous Stock Trends
A framework combining discrete wavelet transforms and temporal convolutional networks predicted continuous stock trends with 72.85 percent accuracy across 400 ...
New Model Improves Common-Rail Pressure Anomaly Detection in Aircraft Piston Engines
A condition-adaptive framework combining sequence-history modelling and conditional quantile regression accurately detects aircraft piston engine pressure anomalies while reducing false ...
Continuous low-cost monitoring and early warning of particulate excursions in a hot-dip galvanizing plant: A three-month field case study
A three-month field deployment in a working hot-dip galvanizing plant shows a roughly USD 150 sensor node can forecast particulate ...
Self-Learning Controller Keeps EV Batteries Healthier During Grid Service
An online Gaussian-process controller that tightens its own safety limits based on prediction uncertainty retained 4.3 percentage points more battery ...
Dual-Stream AI Network Predicts Battery Heat and Health to Warn of Thermal Risks Early
A dual-stream AI network that jointly predicts lithium-ion battery temperature and state of health achieved a 92.6 percent timely warning ...
AI Model Reads Solar Magnetic Fields to Predict Flares 24 Hours Ahead
A hybrid ConvNeXV2 and Transformer–TCN deep learning model forecasts C-class and M-class solar flares 24 hours ahead with True Skill ...
Four sensors predict lower-limb joint moments with subject-specific calibration
A four-sensor deep-learning system estimated five lower-limb joint moments during walking and stair tasks, with 10 seconds of unlabeled walking ...
Mahabad Dam modeling study reports 80% lower mean absolute error for total nitrogen predictions
A Mahabad Dam modeling study reported an 80% reduction in mean absolute error and a rise in Willmott’s index from ...
Solar Spectrum Forecasts Power Ultra-Short-Term Photovoltaic Predictions With Deep Learning
Researchers in Kazakhstan have developed a two-stage deep learning method that forecasts the solar spectrum itself and uses it to ...
-
Mothers who receive childcare support from maternal grandparents show more parental warmth, finds NTU Singapore study
-
University of Seville Breaks 120-Year-Old Mystery, Revises a Key Einstein Concept
-
Bee body mass, pathogens and local climate influence heat tolerance
-
Researchers record first-ever images and data of a shark experiencing a boat strike
-
Groundbreaking Clinical Trial Reveals Lubiprostone Enhances Kidney Function
Embark on a thrilling journey of discovery with Scienmag.com—your ultimate source for cutting-edge breakthroughs. Immerse yourself in a world where curiosity knows no limits and tomorrow’s possibilities become today’s reality!