Jin Quan Liu

Learn More
A hybrid system for automated EEG sleep staging is presented in this article. By combining a self-organizing feature map (SOFM) with a fuzzy reasoning-based classifier (FRBC) and utilizing both temporal and spectrum features of the EEG signal, the system provides a reliable tool for automatic EEG sleep staging. Conceptually, the system is divided into four(More)
Gravity gradient measurement makes use of the difference between the outputs of pairs of linear accelerometers, which results in cancelling out the common mode accelerations caused by mounting platform and external environment. One of the key technologies is to match the acceleration-to-voltage or acceleration-to-current transfer functions of the pairs of(More)
1-Bromopropane (1-BP) has been widely used as a substitute for chlorofluorocarbon that destroys the ozone layer. Although the central neurotoxicity of 1-BP has been recently reported, a molecular mechanism is not clear. In particular, the effects on cells in brain have not been fully analyzed. Here, we studied the effects of 1-BP on the activation of(More)
Patients with minor psychiatric disorders, including neuroses, situational adjustment reaction or acute emotional reaction, were investigated using symptom questionnaires at five research sites in Asia including: Chiang-Mai, Thailand; Bali, Indonesia; Kao-Hsiung, Taiwan, China; Shanghai, China; and Tokyo, Japan. The results revealed that the symptom(More)
This paper presents an in-plane sandwich nano-g microelectromechanical systems (MEMS) accelerometer. The proof-mass fabrication is based on silicon etching through technology using inductive coupled plasma (ICP) etching. The capacitive detection system, which employs the area-changing sensing method, combines elementary capacitive pickup electrodes with(More)
So far, the accurate modeling and control of blast furnace iron-making process (BFIP) is still an open problem due to its excessive complexity. Aiming at the issue of long time-delay and strong cross-coupling characteristics of BFIP, the random forests (RF) algorithm is introduced for predicting the silicon content in hot metal, which is the most key(More)
  • 1