Current Issue : July - September Volume : 2017 Issue Number : 3 Articles : 5 Articles
Thehybrid brain computer interface (BCI) based onmotor imagery (MI) and P300 has been a preferred strategy aiming to improve\nthe detection performance through combining the features of each. However, current methods used for combining these two\nmodalities optimize them separately, which does not result in optimal performance. Here, we present an efficient framework to\noptimize them together by concatenating the features of MI and P300 in a block diagonal form. Then a linear classifier under a\ndual spectral norm regularizer is applied to the combined features. Under this framework, the hybrid features of MI and P300 can\nbe learned, selected, and combined together directly. Experimental results on the data set of hybrid BCI based on MI and P300\nare provided to illustrate competitive performance of the proposed method against other conventional methods. This provides an\nevidence that the method used here contributes to the discrimination performance of the brain state in hybrid BCI....
The ability to develop Brain-Computer Interfaces (BCI) to Intelligent Systems would\noffer new perspectives in terms of human supervision of complex Artificial Intelligence\n(AI) systems, as well as supporting new types of applications. In this article, we\nintroduce a basic mechanism for the control of heuristic search through fNIRS-based\nBCI. The rationale is that heuristic search is not only a basic AI mechanism but\nalso one still at the heart of many different AI systems. We investigate how usersââ?¬â?¢\nmental disposition can be harnessed to influence the performance of heuristic search\nalgorithm through a mechanism of precision-complexity exchange. From a system\nperspective, we use weighted variants of the AâË?â?? algorithm which have an ability to\nprovide faster, albeit suboptimal solutions. We use recent results in affective BCI\nto capture a BCI signal, which is indicative of a compatible mental disposition in\nthe user. It has been established that Prefrontal Cortex (PFC) asymmetry is strongly\ncorrelated to motivational dispositions and results anticipation, such as approach or\neven risk-taking, and that this asymmetry is amenable to Neurofeedback (NF) control.\nSince PFC asymmetry is accessible through fNIRS, we designed a BCI paradigm\nin which users vary their PFC asymmetry through NF during heuristic search tasks,\nresulting in faster solutions. This is achieved through mapping the PFC asymmetry\nvalue onto the dynamic weighting parameter of the weighted AâË?â?? (WAâË?â??) algorithm.\nWe illustrate this approach through two different experiments, one based on solving\n8-puzzle configurations, and the other on path planning. In both experiments, subjects\nwere able to speed up the computation of a solution through a reduction of search\nspace in WAâË?â??. Our results establish the ability of subjects to intervene in heuristic search\nprogression, with effects which are commensurate to their control of PFC asymmetry:\nthis opens the way to new mechanisms for the implementation of hybrid cognitive\nsystems....
To offer a functionality that could not be found in traditional rigid robots, compliant\nactuators are in development worldwide for a variety of applications and especially for humanââ?¬â??robot\ninteraction. Pneumatic bending actuators are a special kind of such actuators. Due to the absence\nof fixed mechanical axes and their soft behavior, these actuators generally possess a polycentric\nmotion ability. This can be very useful to provide an implicit self-alignment to human joint axes in\nexoskeleton-like rehabilitation devices. As a possible realization, a novel bending actuator (BA) was\ndeveloped using patented pneumatic skewed rotary elastic chambers (sREC). To analyze the actuator\nself-alignment properties, knowledge about the motion of this bending actuator type, the so-called\nskewed rotary elastic chambers bending actuator (sRECBA), is of high interest and this paper presents\nexperimental and simulation-based kinematic investigations. First, to describe actuator motion, the\nfinite helical axes (FHA) of basic actuator elements are determined using a three-dimensional (3D)\ncamera system. Afterwards, a simplified two-dimensional (2D) kinematic simulation model based\non a four-bar linkage was developed and the motion was compared to the experimental data by\ncalculating the instantaneous center of rotation (ICR). The equivalent kinematic model of the sRECBA\nwas realized using a series of four-bar linkages and the resulting ICR was analyzed in simulation.\nFinally, the FHA of the sRECBA were determined and analyzed for three different specific motions.\nThe results show that the actuatorââ?¬â?¢s FHA adapt to different motions performed and it can be assumed\nthat implicit self-alignment to the polycentric motion of the human joint axis will be provided....
Research on robots that accompany humans is being continuously studied. The Pet-Bot\nprovides walking-assistance and object-carrying services without any specific controls through\ninteraction between the robot and the human in real time. However, with Pet-Bot, there is a limit to\nthe number of robots a user can use. If this limit is overcome, the Pet-Bot can provide services in more\nareas. Therefore, in this study, we propose a swarm-driving middleware design adopting the concept\nof a swarm, which provides effective parallel movement to allow multiple human-accompanying\nrobots to accomplish a common purpose. The functions of middleware divide into three parts:\na sequence manager for swarm process, a messaging manager, and a relative-location identification\nmanager. This middleware processes the sequence of swarm-process of robots in the swarm through\nmessage exchanging using radio frequency (RF) communication of an IEEE 802.15.4 MAC protocol\nand manages an infrared (IR) communication module identifying relative location with IR signal\nstrength. The swarm in this study is composed of the master interacting with the user and the slaves\nhaving no interaction with the user. This composition is intended to control the overall swarm in\nsynchronization with the user activity, which is difficult to predict. We evaluate the accuracy of the\nrelative-location estimation using IR communication, the response time of the slaves to a change in\nuser activity, and the time to organize a network according to the number of slaves....
We present a robust algorithm for complex human activity recognition for natural human-robot interaction. The algorithm is\nbased on tracking the position of selected joints in human skeleton. For any given activity, only a few skeleton joints are involved\nin performing the activity, so a subset of joints contributing the most towards the activity is selected. Our approach of tracking\na subset of skeleton joints (instead of tracking the whole skeleton) is computationally efficient and provides better recognition\naccuracy. We have developed both manual and automatic approaches for the selection of these joints.The position of the selected\njoints is tracked for the duration of the activity and is used to construct feature vectors for each activity. Once the feature vectors\nhave been constructed, we use a Support Vector Machines (SVM) multiclass classifier for training and testing the algorithm. The\nalgorithm has been tested on a purposely built dataset of depth videos recorded using Kinect camera. The dataset consists of 250\nvideos of 10 different activities being performed by different users. Experimental results show classification accuracy of 83% when\ntracking all skeleton joints, 95% when using manual selection of subset joints, and 89% when using automatic selection of subset\njoints....
Loading....