introduction: evoked potentials arisen by stimulating the brain can be utilized as a communication tool  between humans and machines. most brain-computer interface (bci) systems use the p300 component,  which is an evoked potential. in this paper, we evaluate the use of the hidden markov model (hmm) for  detection of p300.  materials and methods: the wavelet transforms, wavelet-enhanced indepen...

PURPOSE To compare a three-dimensional Fourier transform (3DFT) gradient-echo pulse sequence with magnetization transfer at a short echo time against standard 3DFT gradient-echo technique in the evaluation of cervical spondylosis, specifically addressing the effects of motion and susceptibility artifacts on the dimensions of the neural foramina and contrast at the cerebrospinal fluid (CSF)-spin...

The digital instrument interface designers in industrial circle must face the typical nonlinear and uncertainty of the relationship between Kansei images (KIs) and product attributes (PAs), and the shortage of the statistical sample. It is conducted thorough research to the problem of nonlinear processing method, pointed out a new way that using combinatorial methods to solve the complex proble...

Mechanisms to motivate user participation became a necessary strategy for the evolution and sustainability of many online systems. Nowadays, most of these mechanisms are based on user activity displays, which take, for example, the form of badges or ranking scores. In this paper we discuss the current use of activity displays as incentives for user participation, and present IntroText, an alter...

On-chip neural interface devices based on CMOS image sensor technology are proposed and demonstrated. The devices were designed with target applications to optogenetics in bioscience. Multifunctional CMOS image sensors equipped with an addressable on-chip electrode array were integrated with a functional interface chip that contained embedded GaInN light emitting diodes (LEDs) and electrodes to...

Emerging nano-scale programmable Resistive-RAM (RRAM) has been identified as a promising technology for implementing brain-inspired computing hardware. Several neural network architectures, that essentially involve computation of scalar-products between input data vectors and stored network ‘weights’ can be efficiently implemented using high density cross-bar arrays of RRAM, integrated with CMO...

In this paper we present a system for accelerating special kinds of neural networks. It is a hardware supported system consisting of diierent parts. A special-purpose neural coprocessor is connected to a personal computer (PC) by a special, asynchronous interface. Two diierent neural coprocessors are available, KO-KOS, a coprocessor for Kohonen's selforganizing map, and KOBOLD, accelerating bac...

This paper presents a review of our neural prosthesis research program and provides a brief introduction to the field. We focus on four key problems: sensing, neural encoding, neural decoding, and interface design. We explore these problems and present our current solutions which have led to the direct cortical control of unconstrained 2D cursor movement.

-the-fly approaches that learn and formulate rules from interface, widget reconfiguration, neural network, rules

The article presents a fast portable system to provide health professionals with solutions for pre-operative surgical planning and decision making in real time. The system employs an effective computational environment for solving partial and ordinary differential equations based on neural networks. This approach is implemented partially on a specialized hardware board to exploit the fact that ...