• 한국정보과학회논문지:시스템및이론
• /
• 제30권5_6호
• /
• pp.258-264
• /
• 2003

VLIW 구조는 다량의 데이터를 처리하는 멀티미디어 애플리케이션에 매우 적합한 구조로서, 이 같은 종류의 애플리케이션에 대해 높은 수준의 병렬 처리를 가능케 한다. 이러한 병렬성을 더욱 증대 시키기 위하여 시스템을 확장하는 경우에 있어, 분산된 VLIW 구조는 그렇지 않은 구조에 비해 큰 강점을 갖는다. 하지만 여러 개의 분산된 클러스터를 하나의 구조 속에 포함하는 것은 필연적으로 적지 않은 양의 하드웨어를 요구하고, 이로 말미암아 전체 시스템에서 소모되는 전력 문제가 중요한 이슈로 대두된다. 본 논문에서는 분산된 VLIW 구조에서 전체 시스템의 성능 제한 조건을 만족시키는 동시에 최대 전력 소모량을 줄이는 효과적인 알고리즘을 제시한다. 일련의 실험을 통해 제시된 알고리즘이 최대 30.7%의 최대 전력 소모 감소 효과를 얻을 수 있음이 확인되었다.

• 한국정보통신학회논문지
• /
• 제22권5호
• /
• pp.728-733
• /
• 2018

단백질을 구성하는 아미노산의 서열 정보만으로 단백질 이차 구조를 예측하기 위하여 심층 학습이 활발히 연구되고 있다. 본 논문에서는 단백질 이차 구조를 예측하기 위하여 다양한 구조의 합성곱 신경망의 성능을 비교하였다. 단백질 이차 구조의 예측에 적합한 신경망의 층의 깊이를 알아내기 위하여 층의 개수에 따른 성능을 조사하였다. 또한 이미지 분류 분야의 많은 방법들이 기반 하는 GoogLeNet과 ResNet의 구조를 적용하였는데, 이러한 방법은 입력 자료에서 다양한 특성을 추출하거나, 깊은 층을 사용하여도 학습과정에서 그래디언트 전달을 원활하게 한다. 합성곱 신경망의 여러 구조를 단백질 자료의 특성에 적합하게 변경하여 성능을 향상시켰다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2009년도 제40회 하계학술대회
• /
• pp.1098_1099
• /
• 2009

In this paper, we present the estimation of wind turbine power generation using Cascade Architectures of Fuzzy Neural Networks(CAFNN). The proposed model uses the wind speed average, the standard deviation and the past output power as input data. The CAFNN identification process uses a 10-min average wind speed with its standard deviation. The method for rule-based fuzzy modeling uses Gaussian membership function. It has three fuzzy variables with three modifiable parameters. The CAFNN's configuration has three Logic Processors(LP) that are constructed cascade architecture and an effective optimization method uses two-level genetic algorithm. First, The CAFNN is trained with one-day average input variables. Once the CAFNN has been trained, test data are used without any update. The main advantage of using CAFNN is having simple structure of system with many input variables. Therefore, The proposed CAFNN technique is useful to predict the wind turbine(WT) power effectively and hence that information will be helpful to decide the control strategy for the WT system operation and application.

• Journal of Communications and Networks
• /
• 제2권1호
• /
• pp.46-57
• /
• 2000

Ongoing standardization effort on 3G cellular system in 3GPP (UNTS) is based on GPRS core network and promises a global standard for systems capable of offering ubiquitous access to internet for mobile users. Considered radio access systems(FDD CDMA, TDD CDMA, and EDGE) are optimized for robust mobile use. However, there are alternative relatively high-rate radio interfaces being standardized for WLAN (IEEE802.11 and HIPER-LAN/2) which are capable of delivering significantly higher data rates to static or semi-static terminals with much less overhead. Also WPANs(BLUETOOTH, IEEE802.15), which will be present in virtually every mobile handset in the near future, are offering low cast and considerable access data rate and thus are very attractive for interworking scenarios. The prospect of using these interfaces as alternative RANs inthe modular UMTS architecture is very promising. Additionally, the recent inclusion of M-IP in the UMTS R99 standard opens the way for IP-level interfacing to the core network. This article offers an overview into WLAN-Cellular interworking. A brief overview of GPRS, UMTS cellular architectures and relevant WLAN standards is given. Possible interworking architectures are presented.

• Journal of Computing Science and Engineering
• /
• 제12권1호
• /
• pp.12-23
• /
• 2018

The Internet of Things (IoT) ecosystem potentially includes heterogeneous devices with different processing mechanisms as well as very complicated network and communication models. Thus, analysis of data associated with adverse conditions is much more complicated. Moreover, mobile things in the IoT lead to dynamic alteration of environments and developments of a dynamic and ultra-large-scale (ULS) environment. Also, IoT and the services provided by that are mostly based on devices with limited resources or things that may not be capable of hosting conventional controls. Finally, the dynamic and heterogeneous and ULS environment of the IoT will lead to the emergence of new security requirements. The conventional preventive and diagnostic security controls cannot sufficiently protect it against increasing complication of threats. The counteractions provided by these methods are mostly dependent on insufficient static data that cannot sufficiently protect systems against sophisticated and dynamically evolved attacks. Accordingly, this paper investigates the current security approaches employed in the IoT architectures. Moreover, we define the dynamic security based on dynamic event analysis, dynamic engineering of new security requirements, context awareness and adaptability, clarify the need for employment of new security mechanism, and delineate further works that need to be conducted to achieve a secure IoT.

• 한국정보처리학회논문지
• /
• 제4권2호
• /
• pp.616-627
• /
• 1997

본 논문에서는 동영상 처리에서 사용되는 움직임 추정을 위한 삼단 검색 알고리 즘의 구조에서는 규칙적인 데이타 입력이 가능하게 되고 입력된 데이타는 그 데이타를 사용하는 모든 연산과정을 거치게 되어 데이타 입력 대역폭이 최소화 된다. 기존의 구조 들 보다 적은 자원으로 최대 계산 속도에 접근하는 성능을 가진다. 제안된 구조의 성능 분석과 다른 구조들과의 비교가 제시된다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 하계학술대회 논문집 D
• /
• pp.2762-2764
• /
• 2001

In this study, we introduce and investigate a class of dynamic perceptron architectures, discuss a comprehensive design methodology and carry out a series of numeric experiments. The proposed dynamic perceptron architectures are called as Polynomial Neural Networks(PNN). PNN is a flexible neural architecture whose topology is developed through learning. In particular, the number of layers of the PNN is not fixed in advance but is generated on the fly. In this sense, PNN is a self-organizing network. PNN has two kinds of networks, Polynomial Neuron(FPN)-based and Fuzzy Polynomial Neuron(FPN)-based networks, according to a polynomial structure. The essence of the design procedure of PN-based Self-organizing Polynomial Neural Networks(SOPNN) dwells on the Group Method of Data Handling (GMDH) [1]. Each node of the SOPNN exhibits a high level of flexibility and realizes a polynomial type of mapping (linear, quadratic, and cubic) between input and output variables. FPN-based SOPNN dwells on the ideas of fuzzy rule-based computing and neural networks. Simulations involve a series of synthetic as well as experimental data used across various neurofuzzy systems. A detailed comparative analysis is included as well.

• ETRI Journal
• /
• 제44권2호
• /
• pp.286-299
• /
• 2022

Human activity recognition in real time is a challenging task. Recently, a plethora of studies has been proposed using deep learning architectures. The implementation of these architectures requires the high computing power of the machine and a massive database. However, handcrafted features-based machine learning models need less computing power and very accurate where features are effectively extracted. In this study, we propose a handcrafted model based on three-dimensional sequential skeleton data. The human body skeleton movement over a frame is computed through joint positions in a frame. The joints of these skeletal frames are projected into two-dimensional space, forming a "movement polygon." These polygons are further transformed into a one-dimensional space by computing amplitudes at different angles from the centroid of polygons. The feature vector is formed by the sampling of these amplitudes at different angles. The performance of the algorithm is evaluated using a support vector machine on four public datasets: MSR Action3D, Berkeley MHAD, TST Fall Detection, and NTU-RGB+D, and the highest accuracies achieved on these datasets are 94.13%, 93.34%, 95.7%, and 86.8%, respectively. These accuracies are compared with similar state-of-the-art and show superior performance.

• 한국의학물리학회지:의학물리
• /
• 제30권2호
• /
• pp.49-58
• /
• 2019

Purpose: Automated analytical systems have begun to emerge as a database system that enables the scanning of medical images to be performed on computers and the construction of big data. Deep-learning artificial intelligence (AI) architectures have been developed and applied to medical images, making high-precision diagnosis possible. Materials and Methods: For diagnosis, the medical images need to be labeled and standardized. After pre-processing the data and entering them into the deep-learning architecture, the final diagnosis results can be obtained quickly and accurately. To solve the problem of overfitting because of an insufficient amount of labeled data, data augmentation is performed through rotation, using left and right flips to artificially increase the amount of data. Because various deep-learning architectures have been developed and publicized over the past few years, the results of the diagnosis can be obtained by entering a medical image. Results: Classification and regression are performed by a supervised machine-learning method and clustering and generation are performed by an unsupervised machine-learning method. When the convolutional neural network (CNN) method is applied to the deep-learning layer, feature extraction can be used to classify diseases very efficiently and thus to diagnose various diseases. Conclusions: AI, using a deep-learning architecture, has expertise in medical image analysis of the nerves, retina, lungs, digital pathology, breast, heart, abdomen, and musculo-skeletal system.

• 디지털융복합연구
• /
• 제14권6호
• /
• pp.405-413
• /
• 2016

인터넷의 여러 문제들을 해결하고, 데이터 전송 성능을 개선하기 위하여 제안된 다양한 미래 인터넷 아키텍처들은 네트워크 노드나 프락시 서버에 캐싱된 데이터를 활용하고 있다. 미래 인터넷 기술 중 하나인 데이터 이름 기반 네트워킹 (NDN)은 네트워크 노드에 데이터 캐싱 기능을 구현하고, 네트워크 노드가 데이터 요청 메시지에 응답함으로써 인터넷의 성능을 개선한다. 그러나 네트워크 노드에 데이터가 캐싱 된 이후에는 해당 데이터의 소유자가 데이터 배포 및 사용에 관여할 수 없기 때문에 사용자 프라이버시에 심각한 위협이 될 수 있다. 이를 해결하기 위해, NDN은 데이터 암호화 및 그룹 기반 키 관리 기술을 사용하여 데이터 접근 제어 기능을 제안하고 있다. 그러나 제안된 기술은 접근 통제 리스트와 복호화 키를 획득하기 위하여 추가적인 메시지 교환이 필요하기 때문에 성능 저하 요인이 될 수 있다. 본 논문은 NDN의 접근 통제 기능을 살펴보고, 성능 향상을 위한 개선된 방안을 제안한다.