• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2004년도 학술대회지
• /
• pp.842-845
• /
• 2004

The aim of this study is to compare the classification results for choosing the fuzzy membership function within fuzzy rules. There are various methods of extracting rules from training data in the process of fuzzy rules generation. Pattern distribution characteristics are considered to produce fuzzy rules. The accuracy of classification results are depended on not only considering the characteristics of fuzzy subspaces but also choosing the fuzzy membership functions. This paper shows how to produce various type of fuzzy rules from the partitioning the pattern spaces and results of land cover classification in satellite remote sensing images by adopting various fuzzy membership functions. The experiments of this study is applied to Landsat TM image and the results of classification are compared by fuzzy membership functions.

• 한국멀티미디어학회논문지
• /
• 제19권5호
• /
• pp.874-880
• /
• 2016

The gesture classification has been applied to many fields. But it is not efficient in the environment for game interface with low specification devices such as mobile and tablet, In this paper, we propose a effective way for realistic game interface using k-nearest neighbors algorithm for gesture classification. It is time consuming by realtime rendering process in game interface. To reduce the process time while preserving the accuracy, a reconstruction method to minimize error between training and test data sets is also proposed. The experimental results show that the proposed method is better than the conventional methods in both accuracy and time.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2002년도 봄 학술발표논문집 Vol.29 No.1 (B)
• /
• pp.703-705
• /
• 2002

최근 컴퓨터 해킹이 커다란 사회적 문제로 대두되고 있다. 물론 시스템 보호를 위한 많은 상용 제품들이 존재하지만, 침입피해 상황에서는 대부분의 경우, 시스템 관리자의 현장 경험에 의존하는 실정이다. 따라서 시스템 관리자는 기존의 침입에 관한 해결방법 뿐만 아니라, 새로운 위협들에 대한 대처방안을 항상 준비 하여야 한다. 이러한 침입상황을 시스템 관리자들에게 교육하기 위하여, 본 논문에서는 모의 훈련환경을 설계하고 구현하였다. 본 시스템의 특징은 우선, 지식베이스로부터 동적으로 생성되는 학습 주제들로 이루어진 교과 과정을 학습자에게 제시한다. 학습자에 의해 선택된 학습 주제는 학습목표로 간주되고, 이 주제는 교수 계획에 의해 다수의 임무(mission)들을 생성한다. 학습자는 각 임무에서 주어진 상황을 가상의 UNIX명령어들을 직접 사용하여 모의 실험해 봄으로써 임무 완수에 필요한 지식을 숙지할 수 있게 된다. 시스템은 임무 완수에 요구되는 해 경로(solution paths)를 유지함으로써, 학습자의 문제 해결 과정을 감독할 수 있고, 도움을 요구하거나 실수를 할 때 적절한 힌트를 제공한다. 시스템은 웹 기반의 클라이언트/서버 구조로 설계되어, 학습자는 브라우저만으로도 학습이 가능하고, 자바 애플릿으로 이루어진 가상 운영체제 하에서 직접 침입대처 상황을 학습 할 수 있다.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2018년도 제30회 한글 및 한국어 정보처리 학술대회
• /
• pp.61-66
• /
• 2018

인과관계 추출이란 어떠한 문장에서 인과관계가 존재하는지, 인과관계가 존재한다면 원인과 결과의 위치까지 분석하는 것을 말한다. 하지만 인과관계 관련 연구는 그 수가 적기 때문에 말뭉치의 수 또한 적으며, 기존의 말뭉치가 존재하더라도 인과관계의 특성상 새로운 도메인에 적용할 때마다 데이터를 다시 구축해야 하는 문제가 있다. 따라서 본 논문에서는 도메인 특화에 따른 데이터 구축비용 문제를 최소화하면서 새로운 도메인에서 인과관계 모델을 잘 구축할 수 있는 통계 기반 모델을 이용한 인과관계 데이터 확장 방법과 도메인에 특화되지 않은 일반적인 언어자질과 인과관계에 특화된 자질을 심층 학습 기반 모델에 적용함으로써 성능 향상을 보인다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.484-484
• /
• 2000

The problem of determining the proper size of an neural network is recognized to be crucial, especially for its practical implications in such important issues as learning and generalization. Unfortunately, it usually is not obvious what size is best: a system that is too snail will not be able to learn the data while one that is just big enough may learn the slowly and be very sensitive to initial conditions and learning parameters. One popular technique is commonly known as pruning and consists of training a larger than necessary network and then removing unnecessary weights/nodes. In this paper, a new pruning method is developed, based on the penalty-term methods. This method makes the neural network good for the generalization and reduces the retraining time after pruning weights/nodes.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2012년도 한국컴퓨터종합학술대회논문집 Vol.39 No.1(B)
• /
• pp.112-113
• /
• 2012

본 논문에서는 실전적인 전투 훈련을 체험할 수 있는 육군 과학화 전투 훈련단의 시스템을 상용 이동통신망(LTE)을 기반으로 한 MTC(장비 또는 기계간의 통신)에 적용하여, 저비용이면서도 신뢰성있는 체계 모델을 제안하며 이를 통해 공군의 각 기지/부대 별 특성에 맞는 실전적 기지방호 훈련이 가능하게 되어 실질적인 전투 능력을 향상시킬 수 있을 것으로 기대한다.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2019년도 제60차 하계학술대회논문집 27권2호
• /
• pp.381-382
• /
• 2019

Recently, various search techniques using artificial intelligence techniques have been introduced. It is also possible to use the artificial intelligence to grasp customer propensity. Analyzing the clothes that customers usually wear, it is possible to analyze various colors such as favorite colors, patterns, and fashion styles. In this study, we use artificial intelligence technology to create an application that distinguish between adults and children by combining various factors such as shape, type, color and size of human clothes. Through this, it will be possible to utilize it in a living area where children can be protected in advance by grasping the intrusion of unauthorized adults in the living area where children live mainly. In addition, in the future, we can obtain good results to detect stranger adult person if we apply this experimental result to the detection system using clothing information.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2019년도 하계학술대회
• /
• pp.98-101
• /
• 2019

At present, deep convolutional neural networks have made a very important contribution in single-image super-resolution. Through the learning of the neural networks, the features of input images are transformed and combined to establish a nonlinear mapping of low-resolution images to high-resolution images. Some previous methods are difficult to train and take up a lot of memory. In this paper, we proposed a simple and compact deep recursive residual network learning the features for single image super resolution. Global residual learning and local residual learning are used to reduce the problems of training deep neural networks. And the recursive structure controls the number of parameters to save memory. Experimental results show that the proposed method improved image qualities that occur in previous methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권3호
• /
• pp.853-873
• /
• 2021

In recent years, deep reinforcement learning (DRL) models are enjoying great interest as their success in a variety of challenging tasks. Deep Q-Network (DQN) is a widely used deep reinforcement learning model, which trains an intelligent agent that executes optimal actions while interacting with an environment. This model is well known for its ability to surpass skilled human players across many Atari 2600 games. Although DQN has achieved excellent performance in practice, there lacks a clear understanding of why the model works. In this paper, we present a visual analytics system for understanding deep Q-network in a non-blind matter. Based on the stored data generated from the training and testing process, four coordinated views are designed to expose the internal execution mechanism of DQN from different perspectives. We report the system performance and demonstrate its effectiveness through two case studies. By using our system, users can learn the relationship between states and Q-values, the function of convolutional layers, the strategies learned by DQN and the rationality of decisions made by the agent.

• International Journal of Computer Science & Network Security
• /
• 제22권10호
• /
• pp.282-290
• /
• 2022

A huge budget is spent on technological solutions to protect Information Systems from cyberattacks by organizations. However, it is not enough to invest alone in technology-based protection and to keep humans out of the cyber loop. Humans are considered the weakest link in cybersecurity chain and most of the time unaware that their actions and behaviors have consequences in cyber space. Therefore, humans' aspects cannot be neglected in cyber security field. In this work we carry out a systematic literature review to identify human factors in cybersecurity. A total of 27 papers were selected to be included in the review, which focuses on the human factors in cyber security. The results show that in total of 14 identified human factors, risk perception, lack of awareness, IT skills and gender are considered critical for organization as for as cyber security is concern. Our results presented a further step in understanding human factors that may cause issues for organizations in cyber space and focusing on the need of a customized and inclusive training and awareness programs.