• KIISE Transactions on Computing Practices
• /
• v.21 no.7
• /
• pp.464-469
• /
• 2015

Long-term electrocardiogram data can be acquired by linking a Holter monitor to a mobile phone. However, most systems are designed to detect arrhythmia through heartbeat classification, and not just for supporting clinical decisions. In this paper, we propose an Abstracting algorithm, and introduce an analogous pateint search system using this algorithm. An analogous patient searcher summarizes each patient's typical pattern using the results of heartbeat, which can greatly simplify clinical activity. It helps to find patients with similar arrhythmia patterns, which can help in contributing to diagnostic clues. We have simulated these processes on data from the MIT-BIH arrhythmia database. As a result, the Abstracting algorithm provided a typical pattern to assist in reaching rapid clinical decisions for 64% of the patients. On an average, typical patterns and results generated by the abstracting algorithm summarized the results of heartbeat classification by 98.01%.

• Journal of Food Hygiene and Safety
• /
• v.21 no.1
• /
• pp.14-22
• /
• 2006

It is anticipated that difficulties are encountered in comparing the use levels of food additives between Korean and Codex systems because of the differences in the use level pattern and food classification method. This study was attempted to construct comparison tables between Korean and Codex standards for benzoic acid, food red No. 2, sulfur dioxide and polysorbate as well as for soybean paste, hot soybean paste and intstant noodle. Difficulties were found to be due to the food category system in use levels by additives and due to the mixed pattern of use level setting in Korea in use levels by food commodities. The comparison tables proposed in this study will be utilized momentously by regulatory authorities and food processing industry. This study showed the necessity to pay attention in comparing the use levels of food additives by country and food commodity.

• KIISE Transactions on Computing Practices
• /
• v.22 no.1
• /
• pp.50-55
• /
• 2016

To attain an understanding of customers' opinions or demands regarding a companies' products or service, it is important to consider VOC (Voice of Customer) data; however, it is difficult to understand contexts from VOC because segmented and duplicate sentences and a variety of dialog contexts. In this article, POS (part of speech) and morphemes were selected as language resources due to their semantic importance regarding documents, and based on these, we defined an LSP (Lexico-Semantic-Pattern) to understand the structure and semantics of the sentences and extracted summary by key sentences; furthermore the LSP was introduced to connect the segmented sentences and remove any contextual repetition. We also defined the LSP by categories and classified the documents based on those categories that comprise the main sentences matched by LSP. In the experiment, we classified the VOC-data documents for the creation of a summarization before comparing the result with the previous methodologies.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.3
• /
• pp.139-146
• /
• 2014

This paper proposes an efficient method for automatically distinguishing various facial expressions. To recognize the emotions from facial expressions, the facial images are obtained by digital cameras, and a number of feature points were extracted. The extracted feature points are then transformed to 49-dimensional feature vectors which are robust to scale and translational variations, and the facial emotions are recognized by statistical pattern classifiers such Naive Bayes, MLP (multi-layer perceptron), and SVM (support vector machine). Based on the experimental results with 5-fold cross validation, SVM was the best among the classifiers, whose performance was obtained by 50.8% for 6 emotion classification, and 78.0% for 3 emotions.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.5
• /
• pp.197-202
• /
• 2022

IoT (Internet of Things) devices are being attacked by malware due to many security vulnerabilities, such as the use of weak IDs/passwords and unauthenticated firmware updates. However, due to the diversity of CPU architectures, it is difficult to set up a malware analysis environment and design features. In this paper, we design time series features using the byte sequence of executable files to represent independent features of CPU architectures, and analyze them using recurrent neural networks. The proposed feature is a fixed-length time series pattern extracted from the byte sequence by calculating partial entropy and applying linear interpolation. Temporary changes in the extracted feature are analyzed by RNN and LSTM. In the experiment, the IoT malware detection showed high performance, while low performance was analyzed in the malware family classification. When the entropy patterns for each malware family were compared visually, the Tsunami and Gafgyt families showed similar patterns, resulting in low performance. LSTM is more suitable than RNN for learning temporal changes in the proposed malware features.

• The KIPS Transactions:PartB
• /
• v.17B no.2
• /
• pp.107-114
• /
• 2010

A guitar, a piano, and a violin are popular musical instruments for User Created Contents(UCC). However the patterns of audio signal generated by a guitar and a piano are too similar to differentiate. The difference between two musical instruments can be found by analyzing the frequency variation per each band near signal peaks. The distribution of probability on the existence of signal peaks based on Cumulative Histogram were applied to musical instrument recognition. Experiments with statistical models of the frequency variation per each band near signal peaks showed the 14% improvement of musical instrument recognition.

• Proceedings of the Korea Database Society Conference
• /
• 2001.06a
• /
• pp.295-302
• /
• 2001

최근 대량의 텍스트 문서로부터 의미 있는 패턴이나 연관 규칙을 발견하기 위한 텍스트마이닝 기법에 대한 연구가 활발히 전개되고 있다. 하지만 비정형 텍스트 문서로부터 추출된 용어의 수는 불규칙적이고 일반적인 용어가 많이 추출되는 관계로 기존의 연관 규칙 탐사 방법을 사용하게 되면 무의미한 연관 규칙이 대량으로 생성되어 지식 정보를 효과적으로 검색하기 어렵다. 본 논문에서는 연관 규칙 탐사 기법을 이용하여 비감독학습 기법에 의해 대량의 문서를 효율적으로 분류하기 위한 대표 색인어 추출 기법을 제안하였다. 컴퓨터 분야의 논문을 대상으로 각 분야별 대표 색인어를 추출하여 유사한 문서끼리 분류하는 실험을 통해 제안된 방법의 효율성을 보였다.

• Proceedings of the KAIS Fall Conference
• /
• 2008.05a
• /
• pp.237-240
• /
• 2008

본 논문에서는 손쉬운 방법으로 자신의 건강 정보를 제공받을 수 있는 방법을 개발하고자 한다. 이를 위한 입력 정보로는 지문 정보를 사용하며, 입력된 지문 정보를 분석하여 사상 체질을 분류하고 각 사람에 맞는 건강 정보를 제공하는 콘텐츠를 구축하고자 한다. 특히 지문유형에 따른 패턴 분석을 통해 사상체질을 분류하고 분류된 사상체질로부터 체질별 건강정보를 제공하고자 한다. 끝으로 실험을 통해 제안한 방법의 유용성을 입증하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.05a
• /
• pp.166-168
• /
• 2018

새롭게 변형되는 대규모 악성코드들을 신속하게 탐지하기 위하여 인공지능 딥러닝을 이용한 악성코드 탐지 기법을 제안한다. 대용량의 고차원 악성코드를 저차원의 이미지로 변환하고, 딥러닝 합성곱신경망(Convolution Neural Network)을 통해 이미지의 악성코드 패턴을 학습하고 분류하였다. 본 논문에서는 악성코드 분류 모델의 성능을 검증하기 위하여 악성코드 종류별 분류 실험과 악성코드와 정상코드 분류 실험을 실시하였고 각각 97.6%, 87%의 정확도로 악성코드를 구별해 내었다. 본 논문에서 제안한 악성코드 탐지 모델은 차원 축소를 통해 10,868개(200GB)의 대규모 데이터에 대하여 10분 이내의 학습시간이 소요되어 새로운 악성코드 학습 및 대용량 악성코드 탐지를 신속하게 처리 가능함을 보였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.29-30
• /
• 2024

본 논문은 Krafton의 PUBG: BATTLEGROUNDS 게임에서 플레이어 분류를 목표로 하며, 포즈 추정기술을 사용하여 일반 플레이어와 봇을 구분한다. 이는 게임에서 직접 수집한 비디오 데이터를 기반으로 하며, 다음과 같은 두 가지 접근 방식을 제안한다. 첫 번째 방법은 동작 시퀀스 분석을 통해, 사용자의 특정동작 패턴을 식별하고 로지스틱 회귀 모델을 활용해 사용자 유형을 분류한다. 두 번째 방법은 YOLO-pose 모델을 사용하여 비디오 데이터에서 키포인트를 추출하고, 이를 LSTM 모델에 적용하여 프레임별로 사용자의 유형을 분류한다. 이러한 이중 접근 방식은 게임의 공정성과 사용자 경험을 향상시키는 새로운 도구를 제공하며, 보다 안전한 게임 환경에 기여할 수 있다. 이 연구는 게임 산업뿐만 아니라 보안 및 모니터링 분야에서도 동작 분석에 대한 혁신적인 접근 방식으로 활용될 잠재력을 가지고 있다.