Machine Learning in Sensors and Imaging

• Format: eBook
• Language: English
• Published: Basel MDPI - Multidisciplinary Digital Publishing Institute 2022
• Subjects: History of engineering & technology; Technology: general issues; activity recognition; artificial neural network; BLDC; BP artificial neural network; burr formation; capacitive; chaotic system; color prior model; compressive sensing; computer vision; coniferous plantations; convex optimization; convolutional neural network; cut interruption; deep learning; display; electric machine protection; explainable artificial intelligence; extrinsic camera calibration; fiber laser; forest growing stem volume; fuzzy; image classification; image denoising; image encryption; imbalanced activities; intelligent vehicles; laser cutting; machine learning; machine learning-based classification; marine; maximum likelihood estimation; mixed Poisson-Gaussian likelihood; modulation transfer function; Naïve bayes; neural network; noisy; non-uniform foundation; object detection; obstacle avoidance; on-shelf availability; path planning; piston error detection; plaintext related; plankton; Q-learning; quality monitoring; random forest; real-world; red-edge band; reinforcement learning; risk assessment; robot arm; sampling methods; segmented telescope; semi-supervised; semi-supervised learning; SNR; star image; stochastic analysis; structure from motion; stylus; target reaching; temperature estimation; texture feature; touchscreen; transmission-line corridors; variable selection; vehicle-pavement-foundation interaction; wearable sensors; wildfire; YOLO algorithm
• Online Access: Open Access: DOAB: description of the publication; Open Access: DOAB, download the publication

 Machine learning is extending its applications in various fields, such as image processing, the Internet of Things, user interface, big data, manufacturing, management, etc. As data are required to build machine learning networks, sensors are one of the most important technologies. In addition, machine learning networks can contribute to the improvement in sensor performance and the creation of new sensor applications. This Special Issue addresses all types of machine learning applications related to sensors and imaging. It covers computer vision-based control, activity recognition, fuzzy label classification, failure classification, motor temperature estimation, the camera calibration of intelligent vehicles, error detection, color prior model, compressive sensing, wildfire risk assessment, shelf auditing, forest-growing stem volume estimation, road management, image denoising, and touchscreens.