Deep Learning Model Flags Early Signs of Problematic Digital Habits in Older Adults
A hybrid CNN-LSTM-attention model predicts risky digital usage patterns in adults aged 60 and older with 0.947 accuracy and 0.93 ...
Tag: LSTM
Research report: Automated phase recognition in the cardiac catheterization laboratory with deep learning
Deep learning models trained on video, equipment logs and clinical data from 222 real coronary angiograms recognized catheterization lab workflow ...
Butterfly-Inspired AI Sharpens Relay Baton Handover Analysis in Speed Skating
A study in Discover Artificial Intelligence reports that a BOA-CNN-LSTM-enhanced SIMI-Motion system cut relay handover feature extraction errors from 13.2 ...
Explainable AI models track EV battery health over 6G networks
A new study combines LSTM-based deep learning with LIME and SHAP explainability to estimate EV battery state of health across ...
AI and IoT Transform Poultry Farming with Predictive Microclimate Control
A systematic review of IoT and AI-enabled microclimate regulation in poultry farming demonstrates that predictive climate management can achieve thermal ...
AI Learns to Water Greenhouse Tomatoes Even When Its Sensors Lie
Researchers coupled the AquaCrop crop model with a disturbance-trained deep reinforcement learning agent that cut simulated greenhouse tomato irrigation by ...
Physics-guided neural networks outperform data-only models on fractional LCR circuit
A comparative study in Scientific Reports reports that a fractional physics-informed network reached a test RMSE of about 2×10⁻⁴ on ...
Chicago taxi-demand model reports higher spatial equity with modest accuracy cost
A Chicago study combining missing-data reconstruction, LSTM forecasting and RHP-based regularization reported up to 50% better spatial equity with an ...
Federated Edge AI Keeps Dairy Cow Health Data on the Farm While Predicting Disease
A simulation-based study reports that a federated Edge-AI framework combining smart neck collars and a hybrid GBoost-LSTM model predicted dairy ...
Physics Meets Machine Learning to Predict the Full Seismic Response of Steel–Concrete Composite Structures
A new physics-informed machine learning framework embeds hysteretic mechanical laws into neural network training, reproducing full seismic load–deformation and energy ...
Reported Echinococcosis in Xinjiang Peaked in 2017 and Fell to a 2022 Low, but the Best Forecast Model Depends on the Test
A 15-year analysis of 20,302 reported echinococcosis cases in Xinjiang found cases peaked in 2017 and fell to a low ...
Seeing and Listening at Once: Dual-View AI Spots Malware That Single Detectors Miss
A new dynamic malware detection method fuses sandbox-captured API call sequences with color images converted from out-of-VM memory dumps, reaching ...
ZAPP reduces percentage errors in near-zero solar power forecasts
A two-dataset study found that ZAPP reduced the hybrid model’s photovoltaic forecasting sMAPE from 60.57% to 11.07% and from 63.30% ...
KG-LSTM model diagnoses English learning behavior patterns with 92% accuracy in junior high school study
A study of junior high school students’ online English-learning logs found that a knowledge-map and LSTM model classified three behavioral ...
Hybrid deep-learning model shows favorable hourly PM2.5 prediction performance in modeling study
A Scientific Reports abstract describes a hybrid decomposition and deep-learning model that reported favorable accuracy and generalization performance for hourly ...
Cluster-aware deep learning framework for bus arrival time prediction in Indian cities
A study in Delhi, Mysore and Surat found that clustering road segments before training deep-learning models improved bus arrival-time predictions ...
AI Models Forecast Leishmaniasis Decline in Ethiopia but Warn WHO 2030 Target Will Be Missed
A new deep learning study projects that leishmaniasis incidence in Ethiopia will fall to about 84 cases per 100,000 by ...
Hand-crafted features beat raw sequences when battery protocols shift
Every lithium-ion cell in an electric vehicle carries a hidden countdown. Long before capacity visibly fades, subtle electrochemical fingerprints in ...
Lightweight AI Spots Violence in Surveillance Video at 130 Frames Per Second
A new deep learning framework detects violent incidents in real surveillance footage with 90 percent accuracy while running fast enough ...
AI Watches the Wind and Sun: Transformer Model Learns to Spot Grid Anomalies
Researchers in India built a transformer-based deep learning system to detect anomalies in solar-wind power plants, achieving strong reconstruction accuracy ...
POPULAR NEWS
-
Spinal cord lesions stretching three segments or more: Spanish cohort maps the causes and the MRI clues that tell them apart
-
Preservative-free 0.02% tacrolimus eye drops eased vernal keratoconjunctivitis in children
-
MicroRNAs May Steer Male and Female Development in Gnetum montanum
-
Erectile dysfunction may precede rare genetic brain disease by years, case series suggests