“…Other applications of deep learning include a real-time maskless-face detector using deep residual networks [356], topology optimization with embedded physical law and physical constraints [357], prediction of stress-strain relations in granular materials from triaxial test results [358], surrogate model for flight-load analysis [359], classification of domestic refuse in medical institutions based on transfer learning and convolutional neural network [360], convolutional neural network for arrhythmia diagnosis [361], e-commerce dynamic pricing by deep reinforcement learning [362], network intrusion detection [363], road pavement distress detection for smart maintenance [364], traffic flow statistics [365], multi-view gait recognition using deep CNN and channel attention mechanism [366], mortality risk assessment of ICU patients [367], stereo matching method based on space-aware network model to reduce the limitation of GPU RAM [368], air quality forecasting in Internet of Things [369], analysis of cardiac disease abnormal ECG signals [370], detection of mechanical parts (nuts, bolts, gaskets, etc.) by machine vision [371], asphalt road crack detection [372], steel commondity selection using bidirectional encoder representations from transformers (BERT) [373], short-term traffic flow prediction using LSTM-XGBoost combination model [374], emotion analysis based on multi-channel CNN in social networks [375].…”