• The Journal of the Acoustical Society of Korea
• /
• v.25 no.6
• /
• pp.269-276
• /
• 2006

In this paper, we propose an emotion recognition system that can discriminate human emotional state into neutral or anger from the speech captured by a cellular-phone in real time. In general. the speech through the mobile network contains environment noise and network noise, thus it can causes serious System performance degradation due to the distortion in emotional features of the query speech. In order to minimize the effect of these noise and so improve the system performance, we adopt a simple MA (Moving Average) filter which has relatively simple structure and low computational complexity, to alleviate the distortion in the emotional feature vector. Then a SFS (Sequential Forward Selection) feature optimization method is implemented to further improve and stabilize the system performance. Two pattern recognition method such as k-NN and SVM is compared for emotional state classification. The experimental results indicate that the proposed method provides very stable and successful emotional classification performance such as 86.5%. so that it will be very useful in application areas such as customer call-center.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.05a
• /
• pp.165-170
• /
• 2003

This paper presents an integrated approach to unconstrained face recognition in arbitrary scenes. The front end of the system comprises of a scale and pose tolerant face detector. Scale normalization is achieved through novel combination of a skin color segmentation and log-polar mapping procedure. Principal component analysis is used with the multi-view approach proposed in[10] to handle the pose variations. For a given color input image, the detector encloses a face in a complex scene within a circular boundary and indicates the position of the nose. Next, for recognition, a radial grid mapping centered on the nose yields a feature vector within the circular boundary. As the width of the color segmented region provides an estimated size for the face, the extracted feature vector is scale normalized by the estimated size. The feature vector is input to a trained neural network classifier for face identification. The system was evaluated using a database of 20 person's faces with varying scale and pose obtained on different complex backgrounds. The performance of the face recognizer was also quite good except for sensitivity to small scale face images. The integrated system achieved average recognition rates of 87% to 92%.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.1
• /
• pp.25-31
• /
• 2009

The anti-vibration tables that use air suspensions as dampers have been widely used due to their high anti-vibration performance in wide frequency band. However, they face a problem of easily accelerating the vibration when triggered by external force because their air suspensions have low rigidity and dampness. In response, there has been a study on active/semi-active dampers that use only the passive components like air suspensions to complement the passive-control format. Thus, we have dynamically analyzed the active/semi-active control of such passive anti-vibration tables. To demonstrate the anti-vibration table's control system, we have also constructed a kinetic model based on the physical characteristics of an anti-vibration table with 6 degrees of freedom and verified its applicability through analysis and experiments.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.6
• /
• pp.1312-1317
• /
• 2003

This paper presents an integrated approach to unconstrained face recognition in arbitrary scenes. The front end of the system comprises of a scale and pose tolerant face detector. Scale normalization is achieved through novel combination of a skin color segmentation and log-polar mapping procedure. Principal component analysis is used with the multi-view approach proposed in[10] to handle the pose variations. For a given color input image, the detector encloses a face in a complex scene within a circular boundary and indicates the position of the nose. Next, for recognition, a radial grid mapping centered on the nose yields a feature vector within the circular boundary. As the width of the color segmented region provides an estimated size for the face, the extracted feature vector is scale normalized by the estimated size. The feature vector is input to a trained neural network classifier for face identification. The system was evaluated using a database of 20 person's faces with varying scale and pose obtained on different complex backgrounds. The performance of the face recognizer was also quite good except for sensitivity to small scale face images. The integrated system achieved average recognition rates of 87% to 92%.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.4
• /
• pp.281-285
• /
• 2013

In this paper, a design scheme of a cruise control system for an electric vehicle using piece-wised PD control is proposed. Cruise control of electric vehicles is one of the major performance elements. Drive motors having linear characteristics ideally is required in order to achieve the cruise driving. But practical motors have nonlinear characteristics and the performance of the motors can be improved by the closed-loop control to compensate it. In this paper, we improved the performance of by applying piece-wised PD control because the driving motors having nonlinear characteristics are difficult to obtain adequate performance only using closed-loop control. In order to test the proposed method, the experiments were carried out by applying the proposed method after setting up an electric vehicle equiped with a driving motors having large nonlinear characteristics. The experiment results of the proposed piece-wised PD control shows better performance than that of closed-loop control.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.7C
• /
• pp.712-722
• /
• 2002

We have investigated a novel optical decoder for a fiber-optic code division multiple access(CDMA) communication systems. The conventional optical encoder and decoder have the advantage of simple structure. However the number of users in the system is limited by the auto- and cross-correlation properties generated in decoding process. In previous studies, to improve the system performance, although they used an optical code that minimize the sidelobe and cross-correlation, could not yet find a novel methods for performance improvement in fiber-optic CDMA system. Thus, it is necessary to investigate the novel optical decode in order to improve the performance of system. In this paper, we schematize the AND gate logic element(AGLE) composed with 1$\times$2 or 1$\times$3 coupler and the optical thyristor and propose the novel optical decoder using K(weight) AGLE. The optical thyristor only passes the overlapped signal and clips other signals. Such a novel concept means that the optical thyristor can operate as a hard-limiter. We analyze the fiber-optic CDMA system using the novel optical decoder with simulation and is found that the novel optical decoder using the AGLE and optical thyristor excludes the sidelobe and cross-correlation intensity between any two sequences.

• Journal of KIISE:Computer Systems and Theory
• /
• v.28 no.11
• /
• pp.561-572
• /
• 2001

Since energy consumption of CMOS circuits has a quadratic dependency on the supply voltage, lowering the supply voltage is the most effective way of reducing energy consumption. We propose an intra-task voltage scheduling algorithm for low-energy hard real-time applications. Based on a static timing analysis technique, the proposed algorithm controls the supply voltage within an individual task boundary. By fully exploiting all the slack times, as scheduled program by the proposed algorithm always complete its execution near the deadline, thus achieving a high energy reduction ratio. In order to validate the effectiveness of the proposed algorithm, we built a software tool that automatically converts a DVS-unaware program into an equivalent low-energy program. Experimental results show that the low-energy version of an MPEG-4 encoder/decoder (converted by the software tool) consumes less than 7~25% of the original program running on a fixed-voltage system with a power-down mode.

• Journal of the Korean Institute of Gas
• /
• v.27 no.3
• /
• pp.27-34
• /
• 2023

Using ammonia as fuel for solid oxide fuel (SOFC) cells has become an attractive topic nowadays due to its high efficiency, environmental friendliness, and ease of storage and transportation. Several configurations of ammonia-fed SOFC systems have been proposed and investigated, demonstrating high electrical efficiency. However, to further enhance efficiency, it is crucial to understand the inefficient components of the system. The exergy concept is well-suited for this purpose, making exergetic analysis essential for ammonia-fed SOFC systems. This study conducts an exergetic analysis for three selected systems: a simple fuel cell system (FC), an anode off-gas recirculation system (RC-FC), and a recirculation system with water removal (RC-WR-FC). The results reveal that the exergetic efficiencies of the FC, RC-FC, and RC-WR-FC are 48.7%, 51.6%, and 58.4%, respectively. In all three systems, the SOFC stack is the main source of exergy destruction. However, other components with relatively low exergetic efficiency, such as the burner, air heat exchanger, and cooler/condenser, offer greater opportunities for improvement.

• Proceedings of the KIEE Conference
• /
• 2008.04a
• /
• pp.244-245
• /
• 2008

본 논문은 관성센서를 이용한 무인 항공체의 자세 제어에 관한 연구를 다루었다. 항공계의 종류는 크게 고정익기와 회선익기로 나뉘는데 본 연구에서는 회전익기의 형태를 가진 Quarter Vehicle을 사통하였다. Quarter Vehicle은 4개의 프로펠러에 의한 양력과 회전 반발력으로 비행을 한다. 이때의 양력은 수평면에 대해 수직으로 추력을 발생시키므로 다른 비행체보다 불안정하며 이를 안정하게 제어하기 위해 관성 센서를 적용하여 균형을 유지한다. 본 연구에서는 관성센서를 이용하여 UAV의 자세와 균형을 안정적으로 유지하여 안정적인 비행이 가능하도록 하였다. 또한 상호 의존적인 항법 시스템으로 환경변화에 영향을 받지 않으며, 정확한 위치정보를 제공하는 GPS를 사용하여 3개 이상의 위성으로부터 정보를 받아 좌표를 계산하고 위치, 속도 및 방향을 결정하여 자율 비행이 가능하도록 설계하였다. 본 논문에서는 Quarter Vehicle의 구조와 이론적 배경을 통한 설계, 그리고 관성센서와 GPS의 적용을 위한 방법을 제시 한다.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.1
• /
• pp.1-10
• /
• 1997

In this paper, for useful administration of the data which have ambiguities meaningfully and hard to treat, a new relation database model using an integrated fuzzy sets and rough sets relational database one. After proposing Fuzzy-rough relational database model on the base of integrated Fuzzy and Rough sets, Application of the examples of arithmetic is analyzed through the Access DBMS and the visual basic by composing and representing database based on fuzzy and rough sets which are characterized as fuzzy sets and rough sets on Pentium computer(166Mhz). This paper was induced to reduce the data incompleteness.