Deep Learning Applications with Practical Measured Results in Electronics IndustriesMong-Fong Horng, Hsu-Yang Kung, Chi-Hua Chen, Feng-Jang Hwang This book collects 14 articles from the Special Issue entitled “Deep Learning Applications with Practical Measured Results in Electronics Industries” of Electronics. Topics covered in this Issue include four main parts: (1) environmental information analyses and predictions, (2) unmanned aerial vehicle (UAV) and object tracking applications, (3) measurement and denoising techniques, and (4) recommendation systems and education systems. These authors used and improved deep learning techniques (e.g., ResNet (deep residual network), Faster-RCNN (faster regions with convolutional neural network), LSTM (long short term memory), ConvLSTM (convolutional LSTM), GAN (generative adversarial network), etc.) to analyze and denoise measured data in a variety of applications and services (e.g., wind speed prediction, air quality prediction, underground mine applications, neural audio caption, etc.). Several practical experiments were conducted, and the results indicate that the performance of the presented deep learning methods is improved compared with the performance of conventional machine learning methods. |
Common terms and phrases
according accuracy adaptive algorithm analysis appearance application approach authors background calculated certified China classification coefficients combined compared compensation compression Computer Conference convolutional correction point corresponding CrossRef dataset deep defined detection determined developed distribution effect Equation error error correction evaluation experiment extracted Figure fitness flight follows forecasting foreign objects frame framework function horizontal humidity IEEE Trans improved indicates initial input International layer learning machine mean measured method neural network noise obtained occlusion optimal output parameters patches Pattern performance planning positions prediction presented problem Proceedings proposed recommendation reduced regression represents residual respectively samples segmentation selected sensor sequence shown in Figure shows similarity squared structure Table target temperature template tire tracker tracking trajectory units University update variation vector vertical visual Wang wind speed Zhang