• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.25 no.5
• /
• pp.1001-1009
• /
• 2015

In Smart Grid, smart meter sends our electric signal data to the main server of power supply in real-time. However, the more efficient the management of power loads become, the more likely the user's pattern of usage leaks. This paper points out the threat of privacy and the need of security measures in smart device environment by showing that it's possible to identify the appliances and the specific usage patterns of users from the smart meter's data. Learning algorithm PCA is used to reduce the dimension of the feature space and k-NN Classifier to infer appliances and states of them. Accuracy is validated with 10-fold Cross Validation.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.44-45
• /
• 2019

최근 CNN 등 인공신경망은 최근 이미지 분류, 객체 인식, 자연어 처리 등 다양한 분야에서 뛰어난 성능을 보이고 있다. 그러나, 대부분의 분야에서 보다 더 높은 성능을 얻기 위해 사용한 인공신경망 모델들은 파라미터 수 및 연산량 등이 방대하여, 모바일 및 IoT 디바이스 같은 연산량이나 메모리가 제한된 환경에서 추론하기에는 제한적이다. 따라서 연산량 및 모델 파라미터 수를 압축하기 위한 딥러닝 경량화 알고리즘이 연구되고 있다. 본 논문에서는 임베디트 보드에서의 압축된 CNN 모델의 성능을 검증한다. 인공지능 지원 맞춤형 칩인 QCS605 를 내장한 임베디드 보드에서 카메라로 입력한 영상에 대해서 원 CNN 모델과 압축된 CNN 모델의 분류 성능과 동작속도 비교 분석한다. 본 논문의 실험에서는 CNN 모델로 MobileNetV2, VGG16 을 사용했으며, 주어진 모델에서 가지치기(pruning) 기법, 양자화, 행렬 분해 등의 인공신경망 압축 기술을 적용하였을 때 원래의 모델 대비 추론 시간 및 분류의 정확도 성능을 분석하고 인공신경망 압축 기술의 유용성을 확인하였다.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.41 no.10
• /
• pp.69-77
• /
• 2004

In this thesis, we created a Fuzzy rule in a Fuzzy logic that are fuzzy logic which is composed of linguistic rules and Fuzzy inference engine for effective traffic control in ATM networks. The parameters of the Fuzzy rules are adapted to minimize the given performance index in both cases. In other words, the difuzzification value controls the service rate in the server to total traffic arrival ratio and buffer occupancy ratio using fuzzy set theory for traffic connected after reasoning. Also, show experiment result about rule by MATLAB6.5 and on-line bulid-up to verify validity of created Fuzzy rule. As a result, we can verify that service ratio in server is efficiently controlled by the total traffic arrival ratio and buffer occupancy ratio.

• Journal of Korean Society of Steel Construction
• /
• v.23 no.5
• /
• pp.557-568
• /
• 2011

To effectively come up with and secure a national budget, it is very important to estimate the reasonable construction cost of each step in public construction projects. In this study, the approximate construction cost of a steel box girder bridge in the early stages of the project, on which available information is limited, was proposed using case-based reasoning. In addition, construction cost estimation models were used for existing sample design models, and the accuracy of the estimation model for the presented cost was verified. The analysis results showed that the error rate was comparatively stable. Therefore, it is expected that construction cost estimation will be effectively suggested in the country's budget preparation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.189-192
• /
• 2010

본 논문에서는 개선된 Fuzzy ART 알고리즘을 이용하여 한의학을 기반으로 증상에 대한 질병을 진단하고 민간요법을 제시하는 한방 자가 검진 시스템을 제안한다. 제안된 방법은 신체 부위를 전신, 머리, 배, 다리 등 17부위로 분류하여 사용자가 증상을 선택하도록 제시하고, 사용자가 선택한 증상과 질병에 포함된 증상 그리고 결과로 도출될 질병간의 선택증상 비율에 대한 우선순위를 개선된 Fuzzy ART 알고리즘에 적용하여 증상을 분류한 후, 퍼지 추론 규칙을 적용하여 질병을 도출한다. 도출된 질병과 그 질병에 대한 원인 및 민간요법을 결과로 제시한다. 데이터베이스에 구축되어 있는 질병 데이터는 통계청에서 정리하여 배포한 한국표준질병 사인분류(K.C.D)를 토대로 표준 질병 정보를 얻어 각 질병의 증상과 원인, 민간요법을 정리한 후, 마지막으로 한의학 전문의의 검증을 거쳐 데이터베이스를 구축하였다. 제안된 한방 자가 검진 시스템에 대한 한의학 전문의의 분석 및 검증 결과, 본 시스템의 증상에 대한 질병 도출이 높은 정확도를 보임을 확인하였다.

• Journal of the Korean earth science society
• /
• v.24 no.6
• /
• pp.524-532
• /
• 2003

The purpose of the present study was to test the hypothesis that student's abductive reasoning skills play an important role in the generation of hypotheses on pendulum motion tasks. To test the hypothesis, a hypothesis-generating test on the pendulum motion and a prior knowledge test about the length of the pendulum motion were developed and administered to a sample of 5th grade children. A significant number of subjects who have the prior knowledge about the length of the pendulum motion failed to apply that prior knowledge to generate a hypothesis on a swing task. These results showed that students' failure in hypothesis-generating was related to their deficiency in abductive reasoning ability, rather than the simple lack of prior knowledge. Furthermore, children's successful generating hypothesis should be required their abductive reasoning skills as well as prior knowledge. Therefore, this study supports the notion that abductive reasoning ability beyond prior knowledge plays an important role in the process of hypothesis-generation. This study suggests that science education should provide teaching about abdctive reasoning as well as scientific declarative knowledge for developing children's hypothesis-generating skills.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.13 no.1
• /
• pp.115-129
• /
• 2003

This paper presents a semi-automated formal verification method based on the famous SVO logic, and discusses its experimental results. We discuss several problems on automating the SVO logic and design its derivative, ASVO logic for automation. Also the proposed method is implemented by the Isabelle/Isar system. As a result, we verified the well-known weakness of the NSSK protocol that is vulnerable to the Denning-Sacco attack, using our Isabelle/ASVO system. Finally, we refined the protocol by following the logical consequence of the ASVO verification.

• School Mathematics
• /
• v.14 no.1
• /
• pp.85-107
• /
• 2012

Problem solving is important in school mathematics as the means and end of mathematics education. In elementary school, inductive reasoning is closely linked to problem solving. The purpose of this study was to examine ways of improving problem solving ability through analysis of inductive reasoning process. After the process of inductive reasoning in problem solving was analyzed, five different stages of inductive reasoning were selected. It's assumed that the flow of inductive reasoning would begin with stage 0 and then go on to the higher stages step by step, and diverse sorts of additional inductive reasoning flow were selected depending on what students would do in case of finding counter examples to a regulation found by them or to their inference. And then a case study was implemented after four elementary school students who were in their sixth grade were selected in order to check the appropriateness of the stages and flows of inductive reasoning selected in this study, and how to teach inductive reasoning and what to teach to improve problem solving ability in terms of questioning and advising, the creation of student-centered class culture and representation were discussed to map out lesson plans. The conclusion of the study and the implications of the conclusion were as follows: First, a change of teacher roles is required in problem-solving education. Teachers should provide students with a wide variety of problem-solving strategies, serve as facilitators of their thinking and give many chances for them ide splore the given problems on their own. And they should be careful entegieto take considerations on the level of each student's understanding, the changes of their thinking during problem-solving process and their response. Second, elementary schools also should provide more intensive education on justification, and one of the best teaching methods will be by taking generic examples. Third, a student-centered classroom should be created to further the class participation of students and encourage them to explore without any restrictions. Fourth, inductive reasoning should be viewed as a crucial means to boost mathematical creativity.

• Proceedings of the Korea Database Society Conference
• /
• 1999.06a
• /
• pp.105-113
• /
• 1999

최근 데이터와 데이터베이스의 폭발적 증가에 따라 무한한 데이터 속에서 정보나 지식을 찾고자하는 지식채굴과정 (knowledge discovery process)에 대한 관심이 높아지고 있다. 특히 기업 내외부 데이터베이스 뿐만 아니라 데이터웨어하우스 (data warehouse)를 기반으로 하는 OLAP환경에서의 데이터와 인터넷을 통한 웹 (web)에서의 정보 등 정보원의 다양화와 첨단화에 따라 다양한 환경 하에서의 지식채굴과정이 요구되고 있다. 본 연구에서는 인터넷 상의 지식을 효과적으로 채굴하기 위한 지식채굴과정을 제안한다. 제안된 지식채굴과정은 명시지 (explicit knowledge)외에 암묵지 (tacit knowledge)를 지식채굴과정에 반영하기 위해 선행지식베이스 (prior knowledge base)와 선행지식관리시스템 (prior knowledge management system)을 이용한다. 선행지식관리시스템은 퍼지인식도(fuzzy cognitive map)를 이용하여 선행지식베이스를 구축하여 이를 통해 웹에서 찾고자 하는 유용한 정보를 정의하고 추출된 정보를 지식변환시스템 (knowledge transformation system)을 통해 통합적인 추론과정에 사용할 수 있는 형태로 변환한다. 제안된 연구모형의 유용성을 검증하기 위하여 재무자료에 선행지식을 제외한 자료와 선행지식을 포함한 자료를 사례기반추론 (case-based reasoning)을 이용하여 실험한 결과, 제안된 지식채굴과정이 유용한 것으로 나타났다.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.4
• /
• pp.5-11
• /
• 1994

In this paper, the ciassification of Korean character type using multi neural network and fuzzy inference based on block partition is studied. For the effective classification of a consonant and a vowel, block partition method which devide the region of a consonant and a vowel for each type in the character is proposed. And the partitioned block can be changed according to the each type adaptively. For the improvement of classification rate, the multi neural network with a whole and a part neural network is consisted, and the character type by using fuzzy inference is decided. To verify the validity of the proposed method, computer simulation is accomplished, and from the classification rate $92.6\%$, the effectivity of the method is confirmed.