Collaboration consists mainly of two tasks; one is each partner's task which is done by the individual, the other is communication with each other. Both of them are very important for the smooth collaboration. Fro...
详细信息
Collaboration consists mainly of two tasks; one is each partner's task which is done by the individual, the other is communication with each other. Both of them are very important for the smooth collaboration. From the viewpoint, the collaboration support system should be a coalition between the operation support and the communication support. We have developed the 3D shape evaluation support system in virtual space and the embodied virtual communication system for the analysis by synthesis. The fusion of two system is necessary for the collaboration support system for 3D shape evaluation in virtual space. From the viewpoint of communication, the talkers tend to prefer the situation in which they can share embodied interaction by observing their interaction of avatars including themselves in the same virtual space. However, the motion images including themselves would discourage them from the shape evaluation. In this paper, the influence of difference of the point of view on the shape evaluation in virtual space is investigated using the proposed system by the sensory evaluation of paired comparison and the questionnaire analysis. It is found that the subjects prefer the point of view from which they can see only their forearms' motion for the shape evaluation in virtual space.
Transforming knowledge between connectionist and symbolic machine learning approaches is not a uniform task and there is no general recipe for performing it. Irrespective of the way the transformation of knowledge, th...
详细信息
Transforming knowledge between connectionist and symbolic machine learning approaches is not a uniform task and there is no general recipe for performing it. Irrespective of the way the transformation of knowledge, the developed methods usually fall into two classes: methods with high rate of transformed knowledge is done, but with a lot of restrictions concerning the type of data in the training sets, training methods, and the size of data sets; and methods with moderate rate of transformed knowledge, but with less restrictions. Our main interest was to find or develop a technique that would possess the knowledge acquisition power of neural networks and explanation power of decision trees. That is why we developed a NN-DT Cascade method, an embedded hybrid of neural networks and decision trees, which is capable of transforming a part of knowledge from the neural network into a decision tree.
In this paper, a simulation of neural network controller for a three links robot arm is presented. The network is based on modified Kohonen's self-organizing map. In the proposed model, recurrent network and modif...
详细信息
In this paper, a simulation of neural network controller for a three links robot arm is presented. The network is based on modified Kohonen's self-organizing map. In the proposed model, recurrent network and modified SOM network are interconnected.
Proposes an energy based control law for swinging up the Acrobot. The control law is designed and the convergence analysis is carried out based on Lyapunov stability theory. The conditions on the parameters in the con...
详细信息
Proposes an energy based control law for swinging up the Acrobot. The control law is designed and the convergence analysis is carried out based on Lyapunov stability theory. The conditions on the parameters in the control law such that the total energy of the Acrobot converges to the potential energy of its top upright position are given. Under such convergence of the energy, the angle between two links converges to zero and the motion of two links converges to a homoclinic orbit containing the top upright position. The characteristics of the solution of the closed-loop system with the energy based control law for swinging up the Acrobot is illustrated clearly in the paper.
Agents have been touted as a very promising technology that have inspired many researchers around the world to develop prototype systems that seem to change the way software works. With major organizations involved in...
详细信息
Agents have been touted as a very promising technology that have inspired many researchers around the world to develop prototype systems that seem to change the way software works. With major organizations involved in projects that utilize agents as solutions, it is believed that agents may have the potential to be part of everyday life in the future. This paper briefly discusses the implementation of multi-agents in university timetabling where agents have to communicate with each other in order to produce a good timetable.
A cortical neuron generates irregular spike sequences including highly variable intervals. This seems to suggest that the neuron receives highly fluctuating synaptic inputs. The simple leaky integrate-and-fire(LIF) mo...
详细信息
A cortical neuron generates irregular spike sequences including highly variable intervals. This seems to suggest that the neuron receives highly fluctuating synaptic inputs. The simple leaky integrate-and-fire(LIF) model driven by fluctuating inputs exhibits high variability in their spike sequences. The variability of inter-spike intervals(ISIs) becomes larger as the input fluctuation becomes larger. But the Hodgkin-Huxley (HH) model is found to exhibit inverse relationships. The ISI variability becomes smaller as the input fluctuation becomes larger, although the effective strength of inputs is kept to be constant. We report the strange responses of the Hodgkin-Huxley model to highly fluctuating inputs.
A speech-driven embodied interactive actor called InterActor with both functions of speaker and listener is developed for activating human interaction and communication by generating expressive actions and motions coh...
详细信息
A speech-driven embodied interactive actor called InterActor with both functions of speaker and listener is developed for activating human interaction and communication by generating expressive actions and motions coherently related to speech input. InterActor is the electronic media version of physical interaction robot called InterRobot for robot-mediated communication support, which sets free from the hardware restriction. By using InterActor, the concept of speech driven embodied interaction system is proposed for human interaction sharing by the entrainment between human speech and InterActor's motions in remote communication. The prototype of the system is developed, and the sensory evaluation and behavioral analysis in human communication through InterActor demonstrate the effectiveness of the system. Actual applications of InterActor to human interface are also demonstrated.
Searching for new rules and new knowledge in problem areas, where very little or almost none previous knowledge is present, can be a very long and demanding process. In our research we addressed the problem of finding...
详细信息
Searching for new rules and new knowledge in problem areas, where very little or almost none previous knowledge is present, can be a very long and demanding process. In our research we addressed the problem of finding new knowledge in the form of rules in the diabetes database using a combination of decision trees and association rules. The first question we wanted to answer was, if there are significant differences in sets of rules both approaches produce, and how rules, produced by decision trees behave, after being a subject of filtering and reduction, normally used in association rule approaches. In order to accomplish that, we had to make some modifications to both the decision tree approach and association rule approach. From the first results we can conclude, that the sets of rules, built by decision trees are much smaller than the sets created by association rules. We could also establish, that filtering and reduction did not effect the rules derived from decision trees in the same scale as association rules.
We propose a pipelined architecture for an equalizer based on the multilevel modified constant modulus algorithm (MMCMA). We also provide the correction factor that mathematically converts the adaptive equalizer havin...
详细信息
We propose a pipelined architecture for an equalizer based on the multilevel modified constant modulus algorithm (MMCMA). We also provide the correction factor that mathematically converts the adaptive equalizer having the proposed architecture into an equivalent non-pipelined conventional MMCMA based equalizer. The proposed architecture uses modules with 6 filter coefficients, resulting in an overall latency of a single sampling period, along the main transmission line. The basic concepts of the proposed architecture is to implement the finite impulse response (FIR) filter and the algorithm portion of the equalizer, such that the critical path of all circuits has three complex multipliers and three adders.
In this paper, we propose a new controller design method, where the identification technique, which directly acquires any order of reduced model, is applied to the feedforward controller design composed of time delays...
详细信息
In this paper, we propose a new controller design method, where the identification technique, which directly acquires any order of reduced model, is applied to the feedforward controller design composed of time delays and inverse dynamics of a controlled object. By applying the proposed controller, the tracking error with reference signal of the N-th power of t becomes zero when the future reference signal is available. The resulting system has neither deterioration in the feedback characteristics nor increase in the tuning man-hour because feedforward controllers do not affect the feedback characteristics and the feedback controller can be designed with the accumulated know-how.
暂无评论