• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.04a
• /
• pp.257-260
• /
• 2007

인간의 행위에는 외부환경으로부터 감각정보가 입력되어 반응되는 무의식적인 행동과 뇌에 의한 추론과 인지에 의한 행동으로 분류할 수 있다. 동일한 환경 조건하에서의 인간 행위분류의 통해 활용 적합한 응용프로그램을 개발하여 적용하여 본다. 본 논문에서는 인간의 몸에 부착하여 움직임을 데이터로 분석할 수 있도록 행동인식 시스템을 개발하였다. 인간행동의 인식패턴을 분류하기 위해 Soft-Computing Algorithm을 행위 추출센서에 적용시킨 단독 시스템을 개발하여 센서모듈로부터 인간의 행동 패턴을 분류할 수 있도록 한다. 이러한 센서모듈은 3축 각속도 및 가속도 센서를 부착시킨 모듈로 Micro-Processor를 사용하여 모듈을 구성하였으며, 구축된 모듈은 인간의 몸에 착용하여 인간의 움직임을 디지털 데이터로 변환된다. 변환된 데이터를 무선통신을 통해 워크스테이션에 전달되어 인간행위에 대한 패턴분류 알고리즘 처리가 가능하며, 추출된 데이터를 기반으로 인간의 행동분석과 교정이 이루어 질 수 있도록 한다. 본 논문에서의 최종 시나리오는 운전자의 행동패턴을 이용한 행동 감지 및 서비스 시스템을 구성하는 데에 목적을 둔다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.423-425
• /
• 1998

An optical system which can autonomously form and display an impression of a picture made up by many figures has been developed. This system consists of optical fuzzy-neurons which calculate the correlation between the input picture and the reference image by incoherent optics. The calculated signal is applied to an amplifier whereby the output signal increases, then decreases according to increase of the input signal . These outputs are synthesized, and are used for changing the position where the system gaze on a part of the input picture by light beam. In this system, the light intensity used for gazing changes chaotically, The attractor drawn from the change of light intensity corresponds to the impression of the picture. This paper shows the results that are calculated by the numerical simulation. The system has been simulated to express the impression for a picture formed by 4figures.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.12a
• /
• pp.225-228
• /
• 2001

DNA computing has been applied to the problem of getting an optimal solution since Adleman's experiment. DNA computing uses strings with various length and four-type bases that makes more useful for finding a global optimal solutions of the complex multi-modal problems. This paper presents DNA coding method for finding optimal solution of the multi-modal function and compares the efficiency of this method with the genetic algorithms (GA). GA searches effectively an optimal solution via the artificial evolution of individual group of binary string and DNA coding method uses a tool of calculation or Information store with DNA molecules and four-type bases denoted by the symbols of A(Ademine), C(Cytosine), G(Guanine) and T(Thymine). The same operators, selection, crossover, mutation, are applied to the both DNA coding algorithm and genetic algorithms. The results show that the DNA based algorithm performs better than GA.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.05a
• /
• pp.381-384
• /
• 2006

Self Organizing Map(SOM) is a powerful neural network model for unsupervised loaming. In many clustering works with exploratory data analysis, it has been popularly used. But it has a weakness which is the poorly theoretical base. A lot more researches for settling the problem have been published. Also, our paper proposes a method to overcome the drawback of SOM. As compared with the presented researches, our method has a different approach to solve the problem. So, a hybrid SOM is proposed in this paper. Using Monte Carlo computing, a hybrid SOM improves the performance of clustering. We verify the improved performance of a hybrid SOM according to the experimental results using UCI machine loaming repository. In addition to, the number of clusters is determined by our hybrid SOM.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.05a
• /
• pp.3-6
• /
• 2006

Methods for risk engineering is a bundle of engineering tools including fundamental concepts and approaches of soft computing with application to real issues of risk management. In this talk fundamental concepts and soft computing approaches of risk engineering will be introduced. As the term of risk implies both advantageous and hazardous uncertainty in its origins, a fundamental theory to describe uncertainties is introduced that includes traditional probability and statistical models, fuzzy systems, as well as less popular modal logic. In particular, modal logic capabilities to express various kinds of uncertainties are emphasized and relations with rough sets and evidence theory are described. Another topic is data mining related to problems in risk management. Some risk mining techniques including fuzzy clustering are introduced and a recently developed algorithm is overviewed. A numerical example is shown.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.13-16
• /
• 2000

In fuzzy expert systems or database systems that have huge volumes of fuzzy data or large fuzzy rules, the inference time is much increased. Therefore, a high performance parallel fuzzy computing environment is needed. In this paper, we propose a parallel fuzzy inference mechanism in parallel computing environment. In this, fuzzy rules are distributed and executed simultaneously. The ONE_TO_ALL algorithm is used to broadcast the fuzzy input vector to the all nodes. The results of the MIN/MAX operations are transferred to the output processor by the ALL_TO_ONE algorithm. By parallel processing of fuzzy rules or data, the parallel fuzzy inference algorithm extracts effective parallel ism and achieves a good speed factor.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.13 no.4
• /
• pp.245-253
• /
• 2013

Knowledge representation realized by information granules is one of the essential facets of granular computing and an area of intensive research. Fuzzy clustering and clustering are general vehicles to realize formation of information granules. Granulation - degranulation paradigm is one of the schemes determining and quantifying functionality and knowledge representation capabilities of information granules. In this study, we augment this paradigm by forming and optimizing a collection of associations among original and transformed information granules. We discuss several transformation schemes and analyze their properties. A series of numeric experiments is provided using which we quantify the improvement of the degranulation mechanisms offered by the optimized transformation of information granules.

• ETRI Journal
• /
• v.44 no.2
• /
• pp.194-207
• /
• 2022

In the last decade, substantial progress has been achieved in intelligent traffic control technologies to overcome consistent difficulties of traffic congestion and its adverse effect on smart cities. Edge computing is one such advanced progress facilitating real-time data transmission among vehicles and roadside units to mitigate congestion. An edge computing-based deep reinforcement learning system is demonstrated in this study that appropriately designs a multiobjective reward function for optimizing different objectives. The system seeks to overcome the challenge of evaluating actions with a simple numerical reward. The selection of reward functions has a significant impact on agents' ability to acquire the ideal behavior for managing multiple traffic signals in a large-scale road network. To ascertain effective reward functions, the agent is trained withusing the proximal policy optimization method in several deep neural network models, including the state-of-the-art transformer network. The system is verified using both hypothetical scenarios and real-world traffic maps. The comprehensive simulation outcomes demonstrate the potency of the suggested reward functions.

• Journal of KIISE:Software and Applications
• /
• v.33 no.12
• /
• pp.1062-1072
• /
• 2006

Recently, new intelligent service frameworks, such as ubiquitous computing are proposed. So, the necessity of adaptive agent system has been increased. In this paper, we propose an intelligent service agent to help that ubiquitous computing system offer user suitable service in ubiquitous computing environment. In order to offer user suitable uT-service, an intelligent service agent mediates the gap between the context information in uT-service system, and user preference is reflected in it. Therefore, we focus on following three components; the first is suitable multi agent framework-agent communication analysis and applicable method of inference engine, the second is uT-ontologies to describe various context information-context information sharing between agents and context information understanding between agents, the third is learning method of user profile to apply in uT-service system. This approach enables us to build adaptive uT-service system to offer suitable service according to user preference.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.50.3-50
• /
• 2002

Our living spaces are becoming increasingly populated with infinite numbers of intelligent embedded agents we are interacting with. in ubiquitous computing environments the aim is to support the occupants during their everyday lives and enhance their living conditions. In this paper we introduce such an environment, the iDorm, which has arisen from our work in careAgents, a project supported by the UK-Korean S&T collaboration fund and the EU's Disappearing Computer Initiative eGadgets project We discuss the research challenges involved, particularly those relating to intelligently associating and configuring large numbers of embedded agents. The paper presents an intelligent association sys...