Byung-Tae Chun

An effective method for combining multiple features of image retrieval

We propose an image retrieval system using the Borda count method in combining multiple experts (CME). It combines color-, shape- and texture-based retrieval systems. CME method can complementarily combine results of each retrieval system, which uses different features. There are some problems when the Borda count method in pattern recognition is applied to image retrieval. Thus, we propose a modified Borda count method to solve these problems. In the experiment our method reduces false positive errors and produces better results than that of each retrieval module that uses only one feature.

Recognition of walking intention using multiple bio/kinesthetic sensors for lower limb exoskeletons

In order to assist the lower limb disabled people to walk, walking-support exoskeletons with bio/kinesthetic sensors such as EMG (Electromyography), gyroscope, and FSR (Force Sensing Resistor) have been developed. It is important to implicitly recognize the walking intention and control the walking-support mechanism. The objective of this work is to examine the walking intention while a person is walking with Lofstrand crutches by analyzing multiple bio/kinesthetic sensor signals. We developed watch/glove and shoe-insoles sensor modules using FSR sensors to recognize the users walking states as well as intention to walk. The FSR signals measuring force at the palm and Gyro sensor signals reflecting the pose of the upper limb were used as clues for recognizing walking intention. While seventeen normal subjects walked for five gate cycles based on the triped walking (i.e., placing crutches in forward and then moving one step) with crutches, the FSR and Gyro signals were acquired from their palms and area of vertebrae lumbales. The result showed that the combination of FSR and Gyro signals could recognize users implicit intention to walk - start walking, keep walking, and stop walking.

Similarity between real faces and facial videos from a display device: a face recognition perspective

Face recognition technology is more direct, user friendly, and convenient compared to other biometric methods. Recently, it has become a widely applied intelligent service robots. However, the performance of facial recognition engines does not always satisfy the expectations of users. This can affect the reliability of robots, for example, that implement a face recognition function. A majority of facial recognition performance test methods use static images that cannot reflect dynamic factors. Consequently, there is a disparity between the performance of the algorithms and performance in real service environments. Moreover, the performance of a face recognition engine cannot guarantee the performance of a robot. Although user demand for performance is increasing, it is difficult to evaluate owing to a lack of test methods and testing environments. In this paper, we demonstrate the similarity between real faces and facial videos from the perspective of face recognition and prove the effectiveness of the evaluation method using a display device.

An Efficient Workload Redistribution Algorithm in Grid Computing Systems Using Genetic Information

There are various machines in grid system which was performed programs for multiple applications. In grid systems, some machines have a low utilization. But other machines have high utilization. For applications that are grid enabled, the grid can offer a resource balancing effect by scheduling grid jobs on machines with low utilization. A scheduling policy is used to manage many resources efficiently. When jobs communicate with each other, the internet, with storage resources, an advanced scheduler could schedule them to minimize communication traffic or minimize the distance of the communications for turnaround time improvement. Therefore, we propose a workload redistribution algorithm to improve the performance of grid scheduler using genetic information.