• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권9호
• /
• 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%.

• 제어로봇시스템학회논문지
• /
• 제22권5호
• /
• 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
• /
• 제7권5호
• /
• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권10호
• /
• pp.3810-3830
• /
• 2015

In this paper, we investigate the differential game theoretic approach for distributed dynamic cooperative power control in cognitive radio ad hoc networks (CRANETs). First, a payoff function is defined by taking into consideration the tradeoff between the stock of accumulated power interference to the primary networks and the dynamic regulation of the transmit power of secondary users (SUs). Specifically, the payoff function not only reflects the tradeoff between the requirement for quickly finding the stable available spectrum opportunities and the need for better channel conditions, but also reveals the impact of the differentiated types of data traffic on the demand of transmission quality. Then the dynamic power control problem is modeled as a differential game model. Moreover, we convert the differential game model into a dynamic programming problem to obtain a set of optimal strategies of SUs under the condition of the grand coalition. A distributed dynamic cooperative power control algorithm is developed to dynamically adjust the transmit power of SUs under grand coalition. Finally, numerical results are presented to demonstrate the effectiveness of the proposed algorithm for efficient power control in CRANETs.

• 대한전자공학회논문지TC
• /
• 제49권5호
• /
• pp.99-106
• /
• 2012

함정의 운용 효율성을 높이기 위해서 한국 해군은 음성통신위주의 함내외 통합통신체계(ICS:Integrated Communication System)을 운용해 오고 있으며, 최근에는 음성, 영상, 문자 등이 포함된 멀티미디어 통합통신망에 대한 적용을 고려하고 있다. 본 논문은 함정용 멀티미디어 통합통신망을 구축하기 위한 기초연구로써 한국 해군의 함정 내 여러 통신망 중에서 통합통신망에 적용할 통신망을 구분하고, 구분된 통신망에서 운용중인 멀티미디어 트래픽의 종류 및 특성들을 고찰한다. 아울러 ICS 통신교환기에서의 트래픽 입력소스 수에 따른 링크용량을 예측하기 위해서 트래픽 다중화 모델을 제안하고, 한국 해군의 주요 함정 별 트래픽의 링크용량 산출 및 통합 트래픽을 분석한다.

• 전자공학회논문지SC
• /
• 제39권1호
• /
• pp.24-32
• /
• 2002

본 논문은 다중 컴퓨터 시스템(multicomputer system)에서 사용되는 상호연결망(interconnection network)의 일종인 다단계 상호연결망(multistage interconnection network)에서의 고착고장(stuck-at fault)과 관련된 고장진단(fault diagnosis)에 대해 고찰한다. 지금까지 연구된 바에 의하면 다단계 상호연결망의 고장을 검출하고 위치를 찾기 위채서는 각 고장의 유형에 따라 서로 다른 다수의 과정을 거치거나 몇 번의 테스트를 통한 진단기법을 필요로 한다. 이에 본 논문에서는 단일과정을 통해 대표적인 고착고장의 유형을 검출하고 위치를 찾아내는 고장진단 알고리즘을 제안한다. 즉, 고착고장이 존재하는 임의의 다단계상호연결망에 대하여 고장 스위치 소자의 행과 열의 위치정보 및 고착고장의 유형진단 알고리즘을 제시한다. 마지막으로 다단계 상호연결망의 일종인 16×16 베이스라인 망(baseline network)에서 고착고장이 발생한 스위치의 위치와 유형을 찾는 과정을 통해 제안하는 알고리즘의 효용성을 검증한다.

• 한국컴퓨터정보학회논문지
• /
• 제14권12호
• /
• pp.169-180
• /
• 2009

홈 네트워크는 유무선 네트워크를 기반으로 언제, 어디서나 정보가전 및 기기제어와 양방향 멀티미디어 서비스를 이용할 수 있는 주거환경을 일컫는다. 홈 네트워크가 점차 활성화되고 있는 현시점에서 댁내망은 PC 뿐만 아니라 홈오토메이션, 백색가전 등 다양한 기기들로 구축되기 때문에 외부의 공격 형태 및 피해 양상 역시 다양하게 나타날 수 있다. 그래서 본 논문에서 홈 네트워크에 대한 침입에 대응할 수 있는 SIP 기반 홈 네트워킹인 SSIP(Secure Session Initiate Protocol) 모델을 제안한다. 본 논문에서 제안하는 SIP기반 홈네트워킹인 SSIP(Secure Session Initiate Protocol) 모델은 홈 게이트웨이에서 수행하는 Cluster-to-Cluster환경에 SIP의 인증기능을 추기하여 효과적인 인증과 세션 재설정시에 세션 시간 및 셋업 시간을 줄여 주는 효율적이고 신뢰성 있는 시스템이다.

• 한국컴퓨터정보학회논문지
• /
• 제16권4호
• /
• pp.101-110
• /
• 2011

스마트 그리드 네트워크(Smart Grid Networks)는 기존의 전력망에 정보기술(IT)을 접목하여 전력 공급자와 소비자가 양방향으로 정보를 교환함으로써 에너지 효율을 최적화하는 차세대 지능형 전력망이다. 고압 전력망과 IT 영역에서 응용되고 있는 스마트 그리드 네트워크(Smart Grid Networks)는 정보의 도청이나, 비정상적 패킷의 유통, 메시지의 재사용등 데이터의 위 변조와같은외부의공격에쉽게노출되는환경에서동작함으로보안은필수적으로갖추어져야 하는 중요한 기능이다. 저전력, 초소형 저비용 장점을 갖는 Zigbee는 스마트 그리드 네트워크를 구현하는 최적의 기술로 주목 받고 있다. 그러나 Zigbee 보안 시스템에는 심각한 문제점들을 가지고 있다. 본 논문에서는 스마트 그리드의 Zigbee 보안 시스템이 가지고 있는 문제점들을 자세히 분석하고, 이를 해결하여 스마트 그리드에 적합한 보안 프로토콜을 새롭게 제안하고 그 효율성을 비교 분석한다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 학술대회 논문집 정보 및 제어부문
• /
• pp.264-266
• /
• 2005

Recently, on-line diagnosis methods through wired and wireless networks are widely adopted in the diagnosis of industrial Electric Facilities, such as generators, transformers and motors. Also smart sensors which includes sensors, signal conditioning circuits and micro-controller in one board are widely studied in the field of condition monitoring. This paper suggests an self-powered system suitable for condition-monitoring smart sensors, which uses parasitic vibrations of the facilities as energy source. First, vibration-driven noise patterns of the electric facilities are presented. And then, an electromagnetic generator which uses mechanical mass-spring vibration resonance are suggested and designed. Finally energy consumption of the presented smart sensor, which consists of MEMS vibration sensors, signal conditioning circuits, a low-power consumption micro-controller, and a ZIGBEE wireless tranceiver, are presented. The usefulness and limits of the presented electromagnetic generators in the field of electric facility monitoring are also suggested.

• 한국전기전자재료학회논문지
• /
• 제33권3호
• /
• pp.239-244
• /
• 2020

This study examines the feasibility of the image deep learning method using convolution neural networks (CNNs) to maintain a porcelain insulator. Data augmentation is performed to prevent over-fitting, and the classification performance is evaluated by training the age, material, region, and pollution level of the insulator using image data in which the background and labelling are removed. Based on the results, it was difficult to predict the age, but it was possible to classify 76% of the materials, 60% of the pollution level, and more than 90% of the regions. From the results of this study, we identified the potential and limitations of the CNN classification for the four groups currently classified. However, it was possible to detect discoloration of the porcelain insulator resulting from physical, chemical, and climatic factors. Based on this, it will be possible to estimate the corrosion of the cap and discoloration of the porcelain caused by environmental deterioration, abnormal voltage, and lightning.