• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1741-1744
• /
• 2005

In this paper, we proposed an adaptive skill element based on error signal. We assume that human progress their skills of actions based on errors, then an inverse dynamic of human motion have to changes. Human controller consists from feedback element (FB) and feed forward element (FF) and their elements cooperate to control actions. Under the assumption, we vary the connection of FF and FB by error signal. We propose the index function for change of a skill parameter. From results of the numerical simulations for the varying skill parameter with index function, we consider that the position error given by our vision changes the skill element and we confirm that the position error is the one of the estimate function for the improvement in our skill.

• Proceedings of the KIEE Conference
• /
• 1992.07a
• /
• pp.476-479
• /
• 1992

This paper presents a neural network method for tuning PlD controller of a time-varying process. Three gains of PlD controller are tuned for a certain desirable response pattern by back-propagation neural network. The neural network is trained using changes of output features vs. changes of PlD gains. But sometimes it needs longer training time and larger structure to train the correlation between the process and controller on entire region of the process. The difficulty in system identification is that the inverse function of the system can not be clearly stated. To cope with the problem, we do not train the neural network to respond correctly for the entire regions but train for only local region where the system is heading toward by training the neural network and tuning of the PlD controller. It may be trained for fine-tuning itself. Simulation results show that the adaptive PID controller using neural network trained in the local area performs remarkably for time-varying second order process.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.34S no.10
• /
• pp.141-150
• /
• 1997

In this paepr, we propose an intelligent double talk detector that can enhance the performance of the acoustic echo cancellation system. The conventional double talk detection methods often misunderstand the echo path changes as double talk. Although there exist several detection methods that can distinguish the echo path changes from the double-talks, they show poor tracking performance because of the excessive decision delay for the discrimination and can only be used after the adaptive digital filter converges. A new and more effective ditetion algorithm has been proposed, where the detection mechanism is performed by observing the change rate of the reflection coefficients of the two lattice predictors that re placed on the near-end and far-end terminals. The excellence of the proposed method is verified by extensive computer simulations using real speech signals.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.19 no.7
• /
• pp.112-120
• /
• 2020

During the past decades, dramatic technology changes affected the life of billions of people around the globe. Although these changes resulted to economic benefits, mostly for the developed countries, the undiscerning development also resulted to many side effects, such as environment pollution, scarce natural resources, global warming, and an increase of the gap between "those who have" and "those who have not", among others. Also, since these developments were based on high technologies, they were not suitable for 90% of the underdeveloped countries. In this review, the possible ways of increasing the quality of life in underdeveloped countries are described, by providing adaptive solutions using appropriate technologies. Some successful applications of appropriate and intermediate technology are introduced, and the need for a new undergraduate education course of engineering design based on appropriate technology is proposed for Korea.

• Proceedings of the KSME Conference
• /
• 2001.06b
• /
• pp.105-109
• /
• 2001

This paper discuss the real-time self-tuning learning control based on evolutionary computation, which proves its the superiority in the finding of the optimal solution at the off-line learning method. The individuals are reduced in order to learn the evolutionary strategy in real-time, and new method that guarantee the convergence of evolutionary mutations are proposed. It possible to control the control object varied as time changes. As the state value of the control object is generated, applied evolutionary strategy each sampling time because the learning process of an estimation, selection, mutation in real-time. These algorithms can be applied, the people who do not have knowledge about the technical tuning of dynamic systems could design the controller or problems in which the characteristics of the system dynamics are slightly varied as time changes.

• Computers and Concrete
• /
• v.24 no.3
• /
• pp.271-282
• /
• 2019

Concrete undergoes a series of thermo-based physio-chemical changes once exposed to elevated temperatures. Such changes adversely alter the composition of concrete and oftentimes lead to fire-induced explosive spalling. Spalling is a multidimensional, complex and most of all sophisticated phenomenon with the potential to cause significant damage to fire-exposed concrete structures. Despite past and recent research efforts, we continue to be short of a systematic methodology that is able of accurately assessing the tendency of concrete to spall under fire conditions. In order to bridge this knowledge gap, this study explores integrating novel artificial intelligence (AI) techniques; namely, artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS) and genetic algorithm (GA), together with traditional statistical analysis (multilinear regression (MLR)), to arrive at state-of-the-art procedures to predict occurrence of fire-induced spalling. Through a comprehensive datadriven examination of actual fire tests, this study demonstrates that AI techniques provide attractive tools capable of predicting fire-induced spalling phenomenon with high precision.

• Journal of Korea Society of Industrial Information Systems
• /
• v.11 no.4
• /
• pp.32-39
• /
• 2006

MANET is a dynamically reconfigurable wireless network with no fixed infrastructure (base station, or AP). In order to provide the data service in MANET, we need an efficient routing protocol to deliver the data to the wanted destination at a mobile node. A method of routing protocols called reactive routing protocol has recently got attention because of their low routing overhead. But a method of flooding broadcasts the packet to all of its neighbors. For this reason, each of the node has high routing overhead to route and keep path discovery. Accordingly in this paper, I propose an adaptive flooding scheme using N-hop look-ahead in MANET, md an optimal N value of doing flooding the packet to limited area. Because of being basically ignorant about topological changes, each of the node did not spontaneously cope with path alteration. But an efficient flooding scheme applying N-hop look-ahead is more resilient to topology changes than traditional algorithms. And also with this efficient flooding scheme, the simulation results demonstrate excellent reduction of routing overhead.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.20 no.6
• /
• pp.107-115
• /
• 2017

This study illustrated the process of bar structure and vegetation coverage to understand historical changes of riverbed and suppose adaptive management in Tan-chun ecological landscape reserve. The study site that lower reach of the Tan-chun are known as habitats of migratory bird and aquatic species with dynamic riverbed. Aerial photos from 2006 to 2016 and surveyed vegetation data in 2006 and 2016 were used by analysis of landscape changes and comparison of vegetation coverage. Study area is classified into 3 sites (A: straight site, B: meandering site, C: meandering and junction with Yangjae-cheon). The result showed that bar area of A and C sites gradually increased, B site decreased during 10 years. Also, ratio of bar area to vegetation coverage and level of vegetation coverage increased in all sites during 10 years. All sites seem to have experienced the terrestrialization with time. On the other hand, ratio of annual vegetation increased and ratio of perennial vegetation decreased in C site in 2016 compare to 2006. Because area of Japanese Hops (Humulus japonicas) as one type of annual vegetation increased, other vegetation could not grow up by its powerful expandability. It is time to make active adaptive management based on not only continuos monitoring but also revaluation of river conditions in order to enhance habitat quality and quantity in Tan-chun ecological landscape reserve.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.48 no.7
• /
• pp.1-8
• /
• 2011

Vehicular Ad-hoc Network (VANET) is a special form of Mobile Ad-hoc Network designed to provide communications among nearby vehicles without communications infrastructure. Some characteristics in VANET environment such as high mobility, dynamic topology and selfishness of nodes can cause degradation of network quality. In this paper, we propose an adaptive incentive/topology control scheme to improve network quality in VANET by stimulating real time data forwarding and reporting changes of network topology. In the proposed scheme, an incentive suggested by the source node is updated in real time simultaneously with data transmission to stimulate real time data forwarding. In addition, when the order of the nodes in the path is changed, nodes which report the changes of network topology will get an additional incentive. By computer simulation, it is shown that the proposed incentive/topology control scheme outperforms the conventional schemes with respect to data delivery time and data delivery ratio.

• Journal of IKEEE
• /
• v.28 no.3
• /
• pp.296-302
• /
• 2024

In this paper, we propose a driver condition monitoring system using FMCW in-cabin radar, which is free from wearing inconvenience and privacy issues. Using 77GHz high-precision radar, the system detects changes in eye blinking patterns according to changes in the driving environment and the driver's condition using an adaptive multiple filtering algorithm, and accurately determines drowsy driving by measuring the number of eye blinks and the time it takes to open and close the eyes through the detected data. With the emergence of high-performance radars that are becoming more and more miniaturized, it is possible to embed them in the instrument panel or rearview mirror of the vehicle, and if the driver is judged to be drowsy, it can wake up the driver through an alarm or interlock with the vehicle's driving system to slow down and make an emergency stop to prevent accidents and promote driver safety.