Description
Book SynopsisVolume 35 first provides a classification scheme of assembly line balancing problems according to characteristic practical settings, highlighting relevant model extensions which are required to reflect real-world problems. Additionally, an assembly line balancing problem is introduced through designing an integrated assembly line and addressing the number of workstations and simultaneous assignments of skilled and unskilled workers. The authors describe an analogy between the methods of adaptive control used in classical control theory and practice on the one hand, and the methods of self-learning used in artificial intelligence systems on the other hand. In one study, a long short-term memory (LSTM) and a Bi-LSTM are proposed to use for classifying the activities of daily living. The accuracy of the proposed approach is evaluated against the current state-of-the-art methods. Two questions regarding very large-scale integration (VSLI) implementation of the X11 algorithm are addressed: how such algorithms are efficiently implemented at once, as well as whether it is possible to use the methods applied in such a VLSI in the implementation of more powerful VLSIs. The concluding study illustrates the azimuth concept in synthetic aperture radar through an analytical description of basic state of the art azimuth signal processing performed to generate synthetic aperture radar images.
Table of ContentsPreface; Assembly Line Balancing Problems: Classification and Solution Approaches; Integrated Assembly Line Balancing with Collaboration; Classical Control Theory and Methods of Artificial Intelligence: Machine Self-Learning; Long Short-Term Memory Network for Human Activity Classification; Structures of Specialized Computational ASICs of China; Azimuth in Synthetic Aperture Radars; Index.
