• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.9
• /
• pp.3583-3597
• /
• 2020

In this paper, a parallel deep learning model using a convolutional neural network and a dilated convolutional neural network is proposed to classify Alzheimer's disease with high accuracy in PET/CT images. The developed model consists of two pipelines, a conventional CNN pipeline, and a dilated convolution pipeline. An input image is sent through both pipelines, and at the end of both pipelines, extracted features are concatenated and used for classifying Alzheimer's disease. Complimentary abilities of both networks provide better overall accuracy than single conventional CNNs in the dataset. Moreover, instead of performing binary classification, the proposed model performs three-class classification being Alzheimer's disease, mild cognitive impairment, and normal control. Using the data received from Dong-a University, the model performs classification detecting Alzheimer's disease with an accuracy of up to 95.51%.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.5
• /
• pp.326-331
• /
• 2016

This paper presents a novel robust adaptive AC8B exciter system against synchronous generators for ships. A PID (proportional integral derivative) control framework, which is a part of the AC8B exciter system, is simply composed of nominal and auxiliary control configurations. For selecting these proper parameter values, the former is conventionally chosen based on the experience and knowledge of experts, and the latter is optimally estimated via a neural networks optimization procedure. Additionally, we propose an online parameter learning-based auxiliary control to practically cope with deterioration of control performance owing to uncertainty in electric generator systems. Such a control mechanism ensures the robustness and adaptability of an AC8B exciter to enhance control performance in real-time implementation. We carried out simulation experiments to test the reliability of the proposed robust adaptive AC8B exciter system and prove its superiority through a comparative study in which a conventional PID control-based AC8B exciter system is similarly applied to our simulation experiments under the same simulation scenarios.

• Smart Structures and Systems
• /
• v.7 no.5
• /
• pp.417-432
• /
• 2011

The present paper is devoted to vibration canceling and shape control of piezoelastic slender beams. Taking into account the presence of electric networks, an extended electromechanically coupled Bernoulli-Euler beam theory for passive piezoelectric composite structures is shortly introduced in the first part of our contribution. The second part of the paper deals with the concept of passive shape control of beams using shaped piezoelectric layers and tuned inductive networks. It is shown that an impedance matching and a shaping condition must be fulfilled in order to perfectly cancel vibrations due to an arbitrary harmonic load for a specific frequency. As a main result of the present paper, the correctness of the theory of passive shape control is demonstrated for a harmonically excited piezoelelastic cantilever by a finite element calculation based on one-dimensional Bernoulli-Euler beam elements, as well as by the commercial finite element code of ANSYS using three-dimensional solid elements. Finally, an outlook for the practical importance of the passive shape control concept is given: It is shown that harmonic vibrations of a beam with properly shaped layers according to the presented passive shape control theory, which are attached to an resistor-inductive circuit (RL-circuit), can be significantly reduced over a large frequency range compared to a beam with uniformly distributed piezoelectric layers.

• Progress in Superconductivity and Cryogenics
• /
• v.5 no.1
• /
• pp.56-59
• /
• 2003

As electric power systems grow to supply the increasing electric power demand short-circuit current tends to increase and impose a severe burden on circuit breakers and power system apparatuses. Thus, all electric equipment in a power system has to he designed to withstand the mechanical and thermal stresses of potential short-circuit currents. Among current limiting devices, Fault Current Limiter (FCL) is expected to reduce the short-circuit current. Especially, Superconducting Fault Current Limiters (SFCL) offer ideal performance: in normal operation the SFCL is in its superconducting state and has negligible impedance, in the event of a fault, the transition into the normal conducting state passively limits the current. The SFCL using high-temperature superconductors offers a positive resolution to controlling fault-current levels on utility distribution and transmission networks. This study contributes to the EMTDC based modeling and simulation method of DC Reactor type SFCL. Single and three phase faults in the utility system with DC reactor type SFCLs have been simulated using EMTDC in order to coordinate with other equipments, and the results are discussed in detail.

• Journal of Electrical Engineering and Technology
• /
• v.1 no.1
• /
• pp.23-27
• /
• 2006

In this paper a Hybrid Real Time HVDC Simulator fur both operator Training and Researching in the Cheju-Haenam HVDC System is proposed and its performance is studied by means of RTDS (Real Time Digital Simulator), EMTDC (Electro-Magnetic Transients system for DC), PSS/E (Power System Simulator for Engineering), and experienced scenarios. The objective of this paper is to represent the strategy in development for KEPCO's hybrid HVDC simulator for the Cheju-Haenam HVDC system. This simulator consists of two DC stations, DC cables, external digital/analog controllers, monitoring systems and control desk for education, and AC networks. Its suitability for operator's education is tested during startup/shutdown and normal state operations. Dynamic performances of it are also verified.

• Proceedings of the KIEE Conference
• /
• 2001.11c
• /
• pp.61-64
• /
• 2001

The electric power load during the peak time in summer is strongly affected by cooling load. which decreases the preparation ratio of electricity and brings about the failure in the supply of electricity in the electric power system. The ice-storage system and heat pump system etc are used to settle this problem. In this study, the method of estimating temperature and humidity to forecast the cooling load of ice-storage system is suggested. And also the method of forecasting the cooling load using neural network is suggested. For the simulation, the cooling load is calculated using actual temperature and humidity. The forecast of the temperature, humidity and cooling load are simulated. As a result of the simulation, the forecasted data approached to the actual data.

• Journal of the Korean Society for Precision Engineering
• /
• v.15 no.2
• /
• pp.7-13
• /
• 1998

This paper presents a methodology for determining machining conditions in Electric Discharge Wire-Cut. Unification of two phase neural network approach with an automatic generation of machining parameters is designed. The first phase neural network, which is 1 to M backward-mapping neural net, produces approximate machining conditions. Using approximate conditions, all possible conditions are newly created by the proposed automatic generation procedure. The second phase neural net, which is a M to 1 forward-mapping neural net, determines the best one among the generated candidates. Simulation results with ANN are given to verify that the presenting methodology could apply for determining machining parameters in Electric Discharge Wire-Cut.

• Journal of IKEEE
• /
• v.11 no.4
• /
• pp.279-282
• /
• 2007

In this paper, we introduce the general way for producing context information to support context-aware applications. It can fetch raw data from the service environments, translate it to reasonable context information, and provide to multiple applications. It is designed originally for the ubiquitous computing middleware and based on the ontology processing model. Automated service applications can use this system as the form of libraries or of web services for deciding its semantic cause of action.

• Proceedings of the KIEE Conference
• /
• 2015.07a
• /
• pp.55-56
• /
• 2015

A smart meter is a kind of electronic meters that measures and records consumption of electric energy in intervals of an hour or less and transmits that information to the remote places. AMI provides two-way communication path between utilities and consumers and should be able to support smart grid's new functionalities such as demand-response actions and real time pricing. The main objective of this paper is to provide a new diagnosis method and system for testing of smart meters in AMI neighborhood area network.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06c
• /
• pp.292-294
• /
• 2011

전기자동차에 대한 연구가 진행됨에 따라 동력원으로 사용되는 대용량 리튬-폴리머 배터리의 운용과 관리에 대한 관심이 증가하고 있다. 다중 셀로 구성된 대용량 리튬-폴리머 배터리는 물리적 화학적 특성에 따라 충전시 셀간 전압 격차가 발생하게 된다. 셀간 전압차는 배터리 용량, 수명, 안정성에 부정적 영향을 주게 된다. 기존 연구들은 각 셀의 특성을 고려하지 않고 충전 결과를 바탕으로 동일한 밸런싱 방법을 적용시킴으로 효율성을 떨어트린다. 본 논문에서는 진화 신경망 기반의 지능형 셀 밸런싱 시스템을 제안한다. 배터리의 특성을 진화 신경망을 통해 학습시킴으로 각 셀 충전시 저항의 크기를 결정한다. 이를 통해 각 셀 특성을 고려한 사전 셀 밸런싱을 수행하였다. 제안하는 방법의 유용성을 입증하기 위해 카이스트 온라인 전기자동차에 장착 예정인 배터리 관리 시스템 기반 시뮬레이션을 수행하여 효과적인 셀 밸런싱이 가능함을 보였다.