Brain-computer interface (BCI) controlled wheelchair robots can serve as powerful aids for severely disabled people in their daily life, especially to help them move voluntarily. In order to better understand human “...
详细信息
Brain-computer interface (BCI) controlled wheelchair robots can serve as powerful aids for severely disabled people in their daily life, especially to help them move voluntarily. In order to better understand human “thought”, owing to the development of the hybrid brain/muscle interface technique, in this paper, we present a real-time hybrid brain/muscle interface to control a wheelchair directly to keep the disables recovering several motion capabilities by using noninvasive motor imagery Electroencephalography (EEG) and Electromyography (EMG). The EMG and EEG signals from the users are extracted to control the motion of an intelligent wheelchair. Both signals processing consists of off-line training, online control evaluation, and real-time control. An algorithm called the common spatial patterns (CSP) is used in this human-robot system to extract the most discriminative spatial patterns pairs as features. The extensive experiments were conducted on the developed human-wheelchair systems to verify the proposed approaches.
A lot of work have been carried out to find the efficient algorithms for QoS-aware dynamic web service composition. The multi-objective multi-choice problem as an evolutive multi-dimension multi-objective 0-1 knapsack...
详细信息
ISBN:
(纸本)9780769547923
A lot of work have been carried out to find the efficient algorithms for QoS-aware dynamic web service composition. The multi-objective multi-choice problem as an evolutive multi-dimension multi-objective 0-1 knapsack problem (MMKP) can be reduced into the web service composition with multiple QoS constraints, while many approaches based on ant colony optimization (AOC) have been introduced in order for solving MMKP. This paper presents a novel QoS-aware dynamic web service composition optimization algorithm with improved AOC. The essence of the algorithm is that the problem of dynamic web service selection with QoS global optimality is transformed into a multi-objective multi-choice QoS-aware web services composition optimization (an evolutive MMKP), for the final purpose of our algorithm is to achieve Pareto Optimality.
A multiple anti-windup loops under multiple dynamic activations strategy is proposed to enlarge the domain of attraction. This work is parallel to the multiple activation case with static *** traditional anti-windup c...
详细信息
ISBN:
(纸本)9781479900305
A multiple anti-windup loops under multiple dynamic activations strategy is proposed to enlarge the domain of attraction. This work is parallel to the multiple activation case with static *** traditional anti-windup compensator is activated immediately as the saturation *** was shown recently that,by delaying the activation of the anti-windup mechanism to a certain level,the performance can be improved for the closed-loop *** was further shown that better performance can be obtained by activating an anti-windup mechanism in anticipation of actuator saturation,in comparison with the delayed activation *** paper considers the anti-windup design problem of enlarging domain of attraction under a dynamic multiple activation *** this multiple activation scheme,the anticipatory,delayed and immediate activation mechanism is incorporated in the same framework simultaneously.A furthermore significant performance improvements over both the immediate and delayed activation schemes can be *** proposed dynamic multiple activation scheme established a unified anti-windup framework and can be readily extended to the traditional immediate,delayed and anticipatory activation anti-windup mechanisms.
Anti-windup design is an intuitive and efficient way to deal with input saturation *** the classic antiwindup design,the compensator is set to be activated immediately as the control signal saturates the *** important...
详细信息
ISBN:
(纸本)9781479900305
Anti-windup design is an intuitive and efficient way to deal with input saturation *** the classic antiwindup design,the compensator is set to be activated immediately as the control signal saturates the *** important innovation in the anti-windup activation mechanism is to delay the activation of the anti-windup mechanism until the saturation reaches to a certain severity which led to a performance improvement of the resulting closed-loop *** recently,it was shown that by activating a static anti-windup mechanism in anticipation of actuator saturation,significant further performance improvements can be achieved in comparison with the delayed activation *** addition,we have combined both the delayed and anticipatory activation mechanisms,to develop the multiple activation strategy,in terms of(?) gain *** paper furthermore considers the problem of enlarging domain of attraction and demonstrates that the multiple activation of a static multiple feedback anti-windup mechanism would also lead to significant performance improvements over both the immediate and delayed activation schemes.
A novel networked data-fusion method is developed for the target tracking in wireless sensor networks (WSNs). Specifically, this paper investigates data fusion scheme under the communication constraint between the fus...
详细信息
A novel networked data-fusion method is developed for the target tracking in wireless sensor networks (WSNs). Specifically, this paper investigates data fusion scheme under the communication constraint between the fusion center and each sensor. Such a message constraint is motivated by the bandwidth limitation of the communication links, fusion center, and by the limited power budget of local sensors. In the proposed scheme, each sensor collects one noise-corrupted sample, performs a quantizing operation, and transmits quantized message to the fusion center. Then the fusion center combines the received quantized messages to produce a final estimate. The novel data-fusion method is based on the quantized measurement innovations and decentralized Kalman filtering (DKF) with feedback. For the proposed algorithm, the performance analysis of the estimation precision is provided. Finally, Monte Carlo simulations show the effectiveness of the proposed scheme.
This paper focuses on macro prediction of corporate equipment maintenance expenditure, adopts ARMA to establish the model for historical data of corporate equipment maintenance expenditure and makes demand analysis an...
详细信息
With the development of SOA based on web services, there are more and more web services with same interface and similar function. How to find and choose the best web service is an important problem that all SOA enterp...
详细信息
ISBN:
(纸本)9780769547923
With the development of SOA based on web services, there are more and more web services with same interface and similar function. How to find and choose the best web service is an important problem that all SOA enterprises face. QoS is used to describe the quality criteria of a web service. In this paper, a new algorithm of web service hierarchy base on QoS similarity has been proposed, which is concerned with meeting requirements of service consumers and the satisfaction with load requirement.
Recently, object tracking has been widely studied as a binary classification problem. Semi-supervised learning is particularly suitable for improving classification accuracy when large quantities of unlabeled samples ...
详细信息
This paper focuses on intervention of collective behavior of multi-agent systems. Distinct from the classical leader-follower method that guides group based on the inclination of convergence, here by virtue of collisi...
详细信息
This paper focuses on intervention of collective behavior of multi-agent systems. Distinct from the classical leader-follower method that guides group based on the inclination of convergence, here by virtue of collision avoidance in flocking behavior, we intervene in collective behavior by adding some obstacles and designing their moving strategies. A model which can be treat as a shepherding process is developed, where the sheep moves according to Boid model, and the shepherd aims to drive all sheep to a desired place. Two strategies with both global and only local information are designed for the shepherd to fulfill the intervention task. Based on Netlogo, we vividly show the shepherding process and prove the efficiency of the obstacle-avoidance method.
The aim of this paper is to improve voltage quality at the terminals of distributed generators (DGs) in an islanded microgrid. To achieve this goal, it is proposed to include separate voltage and current control loops...
详细信息
暂无评论