Special issue on broadband and wireless computing, communication and applications

Abstract

Ambient intelligence is an important cross-discipline research field. In order to let the background system sense humans in the environment and provide proper services to the humans, it needs sensing, networking, intelligent computing and innovative interface technologies. Various kinds of sensors can sense the movements of the human in the environment. With wired or wireless networking technologies, these sensed signals/data are then transmitted to the background computing system for analysis. Furthermore, intelligent technologies are used to understand the intention of the human from the sensed signals/data. Finally, the results are presented in the human–machine interface to interact with the human. On the other hand, the all-IP networking technology has changed the ways of living for the people around the world. The progress of electronic integration and wireless communications is going to pave the way to offer people the access to the wireless networks on the fly, based on which all electronic devices will be able to exchange the information with each other whenever necessary. The aim of this special issue is to present innovative researches, technologies and development in broadband and wireless computing, communication and applications, related to ambient intelligence. This special issue invited selected papers from the Fifth International Conference on broadband and wireless computing, communication and applications (BWCCA-2010), held on 4–6 November 2010 in Fukuoka, Japan. The authors had put a great effort to extend and enhance their work to the journal standard. All the submitted papers were strictly reviewed by three experts in the field. Totally six papers of high quality were accepted. The first two papers are related to pattern recognition and human–machine interface. The rest four are about data networking and communications. The first paper by Lee and Li proposes fingertip handwriting alphanumeric character recognition system based on the hidden conditional random field (HCRF) model. It aims to provide an alternative way for human computer interaction. A combination of fingertip and camera provides a flexible and convenient input device. The proposed system combines fingertip detection, trajectory feature extraction, and character recognition. It also presents possible applications for camera input devices. In the second paper, Li et al. use general cross-correlation (GCC) of frequency spectrum to classify various faults with fine grit. The acoustic data remotely measured by microphones are widely used to investigate monitoring and diagnose integrity of ball bearing in rotational machines. Early fault diagnosis is very difficult for acoustic emission. Principal component analysis (PCA) is used to separate the primary frequency spectrum into main frequency and residual frequency. Multi-classification strategy based on binary-tree support vector machine (SVM) is F. Tang (&) Department of Computer Science and Engineering, Shanghai Jiao Tong University, 800 Dongchuan Road, Minhang District, Shanghai 200240, China e-mail: feilongtang8@gmail.com