• 전기전자학회논문지
• /
• 제25권1호
• /
• pp.229-233
• /
• 2021

임베디드 환경에서의 NPU는 적은 하드웨어 자원으로 딥러닝 알고리즘을 수행한다. 데이터를 재사용하는 기법을 활용하면 적은 자원으로 딥러닝 알고리즘을 효율적으로 연산할 수 있다. 선행연구에서는 데이터 재사용을 위해 ScratchPad에서 shifter를 사용해 데이터를 재사용한다. 하지만 ScratchPad의 Bandwidth가 커짐에 따라 shifter 역시 많은 자원을 소모한다. 따라서 Buffer Round Robin방식을 사용한 데이터 재사용 기법을 제시한다. 본 논문에서 제시하는 Buffer Round Robin 방식을 사용하여 기존의 방식보다 약 4.7%의 Chip Area를 줄일 수 있었다.

• 센서학회지
• /
• 제30권1호
• /
• pp.20-24
• /
• 2021

The electrocardiogram (ECG) is one of the most extensively employed signals used to diagnose and predict cardiovascular diseases (CVDs). In recent years, several deep learning (DL) models have been proposed to improve detection accuracy. Among these, deep neural networks (DNNs) are the most popular, wherein the features are extracted automatically. Despite the increment in classification accuracy, DL models require exorbitant computational resources and power. This causes the mapping of DNNs to be slow; in addition, the mapping is challenging for a wearable device. Embedded systems have constrained power and memory resources. Therefore full-precision DNNs are not easily deployable on devices. To make the neural network faster and more power-efficient, spiking neural networks (SNNs) have been introduced for fewer operations and less complex hardware resources. However, the conventional SNN has low accuracy and high computational cost. Therefore, this paper proposes a new binarized SNN which modifies the synaptic weights of SNN constraining it to be binary (+1 and -1). In the simulation results, this paper compares the DL models and SNNs and evaluates which model is optimal for ECG classification. Although there is a slight compromise in accuracy, the latter proves to be energy-efficient.

• 정보관리연구
• /
• 제28권4호
• /
• pp.59-75
• /
• 1997

이 글은 전자잡지의 선정, 예산, 정책결정, 장서평가, 보존 등 전자잡지에 관한 장서관리문제를 소개 분석하고 있다. 전자잡지와 관련한 직원과 예산이 주제별 접근방식이나 형태별 접근방식에 따라, 또는 이 두 접근방식을 병행하여 조직될 수 있다고 주장하고 있다. 전자잡지는 인쇄형태 잡지와 마찬가지로 자료식별, 평가, 선정이라는 3단계과정을 거쳐 선정된다. 전자잡지는 인쇄형태잡지에 적용되는 전통적 기준뿐만 아니라 또 다른 기준이 추가로 적용된다. 이 글은 전자잡지의 구독취소와 제적을 언급하고 있지 않지만, 그 중요성은 증가할 것이다. 잡지의 소유권보다는 이용가능성과 접근가능성에 중점을 둔 새로운 이용자위주 평가 방법기법에 대한 요구가 일고 있다.

• 한국건설순환자원학회지
• /
• 제4권1호
• /
• pp.17-25
• /
• 2009

• International Journal of Computer Science & Network Security
• /
• 제22권10호
• /
• pp.17-24
• /
• 2022

The article proves that the main goal of informatization of higher education institutions in the EU countries is to improve the quality of education of future specialists by introducing digital educational resources into the education process. The main tasks of informatization of education are defined. Digital educational resources are interpreted as a set of data in digital form that is applicable for use in the learning process; it is an information source containing graphic, text, digital, speech, music, video, photo and other information aimed at implementing the goals and objectives of modern education; educational resources on the Internet, electronic textbooks, educational programs, electronic libraries, etc. The creation of digital educational resources is defined as one of the main directions of informatization of all forms and levels of Education. Types of digital educational resources by educational functions are considered. The factors that determine the effectiveness of using digital educational resources in the educational process are identified. The use of digital educational resources in the training of future specialists in the EU countries is considered in detail. European countries note that digital educational resources in professional use allow you to implement a fundamentally new approach to teaching and education, which is based on broad communication, free exchange of opinions, ideas, information of participants in a joint project, on a completely natural desire to learn new things, expand their horizons; is based on real research methods (scientific or creative laboratories), allowing you to learn the laws of nature, the basics of techniques, technology, social phenomena in their dynamics, in the process of solving vital problems, features of various types of creativity in the process of joint activities of a group of participants; promotes the acquisition by teachers of various related skills that can be very useful in their professional activities, including the skills of using computer equipment and various digital technologies.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2012년도 춘계학술대회
• /
• pp.699-702
• /
• 2012

본 논문에서는 WCDMA(Wide Code Division Multiple Access) 시스템 사양을 만족시키는 주파수 합성기 블록 중 위상잡음 및 전력소모의 최적 설계가 필요한 LC-VCO(voltage controlled oscillator)의 설계를 제안 하였다. 최적 설계를 위한 핵심내용은 LC-tank의 손실성분을 보상하는 MOS트랜지스터의 전달컨덕턴스와 인덕턴스 평면에 여유이득라인과 튜닝 범위 라인을 그어 설계 가능한 영역 내에서 위상잡음이 최소가 되는 인덕턴스 값을 구하고 선택하는 것이다. 제안한 최적 설계방법에 의해 진행된 LC-VCO의 시뮬레이션 결과 위상잡음 특성은 1MHz옵셋에서 -113dBc/Hz였다.

• 한국멀티미디어학회논문지
• /
• 제23권9호
• /
• pp.1201-1209
• /
• 2020

Based on the risk factor evaluation for the file format, this paper defines the procedures for presenting the long-term preservation plan for that format and the technical information registry necessary for building the system. This is a procedure to perform a risk assessment for the format, evaluate the risk, and select a long-term preservation strategy based on the information registered in the registry and information on the external signature and internal signature of the electronic record. We also reviewed the criteria for selecting appropriate long-term preservation strategies in the process and provided the criteria for adopting each detailed strategy of migration and emulation, which are long-term preservation strategies. And we implemented this process as a long-term preservation decision support system. This system can be used to provide guidelines for the maintenance, management, service and long-term preservation of information resources of electronic records in public institutions such as National Archives of Korea and Libraries.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제15권1호
• /
• pp.60-67
• /
• 2015

This paper proposes an image-dependent color image enhancement method that uses adaptive luminance enhancement and color emphasis. It effectively enhances details of low-light regions while maintaining well-balanced luminance and color information. To compare the structure similarity and naturalness, we used the tone mapped image quality index (TMQI). The proposed method maintained better structure similarity in the enhanced image than did the space-variant luminance map (SVLM) method or the adaptive and integrated neighborhood dependent approach for nonlinear enhancement (AINDANE). The proposed method required the smallest computation time among the three algorithms. The proposed method can be easily implemented using the field-programmable gate array (FPGA), with low hardware resources and with better performance in terms of similarity.

• 전력전자학회:학술대회논문집
• /
• 전력전자학회 2001년도 추계학술대회 논문집
• /
• pp.71-75
• /
• 2001

Currently there are very limited amounts of resources and serious amounts pollution. Wind power generation system have an advantage of unlimited and unpolluted amount of energy resource. In this paper, for the application of these characteristic and for the generation to be achieved regard of districts and geographical features the energy continuously. The operation characteristics of system were analyzed through experiments for a trial product.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제13권1호
• /
• pp.34-42
• /
• 2013

Human faces have been broadly studied in digital image and video processing fields. An appearance-based method, the adaptive boosting learning algorithm using integral image representations has been successfully employed for face detection, taking advantage of the feature extraction's low computational complexity. In this paper, we propose a face-detection postprocessing method that equalizes instantaneous facial regions in an efficient hardware architecture for use in real-time multimedia applications. The proposed system requires low hardware resources and exhibits robust performance in terms of the movements, zooming, and classification of faces. A series of experimental results obtained using video sequences collected under dynamic conditions are discussed.