• 정보과학회 논문지
• /
• 제44권11호
• /
• pp.1125-1129
• /
• 2017

LSTM(Long Short-term Memory)은 이전 상태의 정보를 기억하여 현재 상태에 반영해 학습하는 순환신경망(Recurrent Neural Network) 모델이다. 악성코드에서 선형적 순서 정보는 각 시점에서 호출되는 함수로서 정의 가능하다. 본 논문에서는 LSTM 모델의 이전 상태를 기억하는 특성을 이용하며, 시간 순서에 따른 악성코드의 함수 호출 정보를 입력으로 사용한다. 그리고 실험으로서 우리가 제시한 방법이 악성코드 분류가 가능함을 보이고 순서 정보의 길이 변화에 따른 정확률을 측정한다.

• 제어로봇시스템학회논문지
• /
• 제21권1호
• /
• pp.59-64
• /
• 2015

In this paper, we found the usefulness of the deep belief network (DBN) in the fields of brain-computer interface (BCI), especially in relation to imagined speech. In recent years, the growth of interest in the BCI field has led to the development of a number of useful applications, such as robot control, game interfaces, exoskeleton limbs, and so on. However, while imagined speech, which could be used for communication or military purpose devices, is one of the most exciting BCI applications, there are some problems in implementing the system. In the previous paper, we already handled some of the issues of imagined speech when using the International Phonetic Alphabet (IPA), although it required complementation for multi class classification problems. In view of this point, this paper could provide a suitable solution for vowel classification for imagined speech. We used the DBN algorithm, which is known as a deep learning algorithm for multi-class vowel classification, and selected four vowel pronunciations:, /a/, /i/, /o/, /u/ from IPA. For the experiment, we obtained the required 32 channel raw electroencephalogram (EEG) data from three male subjects, and electrodes were placed on the scalp of the frontal lobe and both temporal lobes which are related to thinking and verbal function. Eigenvalues of the covariance matrix of the EEG data were used as the feature vector of each vowel. In the analysis, we provided the classification results of the back propagation artificial neural network (BP-ANN) for making a comparison with DBN. As a result, the classification results from the BP-ANN were 52.04%, and the DBN was 87.96%. This means the DBN showed 35.92% better classification results in multi class imagined speech classification. In addition, the DBN spent much less time in whole computation time. In conclusion, the DBN algorithm is efficient in BCI system implementation.

• 대한인간공학회지
• /
• 제31권2호
• /
• pp.271-279
• /
• 2012

Objective: This study classified three different emotional states(boredom, pain, and surprise) using physiological signals. Background: Emotion recognition studies have tried to recognize human emotion by using physiological signals. It is important for emotion recognition to apply on human-computer interaction system for emotion detection. Method: 122 college students participated in this experiment. Three different emotional stimuli were presented to participants and physiological signals, i.e., EDA(Electrodermal Activity), SKT(Skin Temperature), PPG(Photoplethysmogram), and ECG (Electrocardiogram) were measured for 1 minute as baseline and for 1~1.5 minutes during emotional state. The obtained signals were analyzed for 30 seconds from the baseline and the emotional state and 27 features were extracted from these signals. Statistical analysis for emotion classification were done by DFA(discriminant function analysis) (SPSS 15.0) by using the difference values subtracting baseline values from the emotional state. Results: The result showed that physiological responses during emotional states were significantly differed as compared to during baseline. Also, an accuracy rate of emotion classification was 84.7%. Conclusion: Our study have identified that emotions were classified by various physiological signals. However, future study is needed to obtain additional signals from other modalities such as facial expression, face temperature, or voice to improve classification rate and to examine the stability and reliability of this result compare with accuracy of emotion classification using other algorithms. Application: This could help emotion recognition studies lead to better chance to recognize various human emotions by using physiological signals as well as is able to be applied on human-computer interaction system for emotion recognition. Also, it can be useful in developing an emotion theory, or profiling emotion-specific physiological responses as well as establishing the basis for emotion recognition system in human-computer interaction.

• 한국통신학회논문지
• /
• 제28권7C호
• /
• pp.712-718
• /
• 2003

C.elegans 선충은 유전자 기능 연구에 주로 쓰이고 있으나, 변종들의 구분이 육안으로는 쉽지 않다. 이를 해결하기 위하여 컴퓨터 비젼을 이용하여 자동으로 분류할 수 있는 시스템이 연구 중이며, 이전 논문［1］에서 선충의 자동 분류 시스템에 사용될 영상의 전처리 과정에 대하여 서술한 바 있다. 본 논문에서는 전처리 된 영상 데이터를 이용하여 추출해 낼 수 있는 선충의 형태적 특징들을 제시한다. 선충의 크기와 관련한 특징과 자세에 관련한 특징으로 나누어, 각 특징의 추출 알고리즘을 수학적으로 표현하였다. 실험에서 제시된 형태적 특징 정보를 이용하여 직접 분류해 봄으로써 성능을 확인하였다. 분류 알고리즘은 Hierarchical Clustering을 사용하였다. 그 결과 실험에 이용된 선충의 4 종류 모두 90% 이상 옳게 분류되었다.

• Spatial Information Research
• /
• 제5권2호
• /
• pp.177-183
• /
• 1997

토지이용 분류 체계상에서의 종류라는 개념은 토지이용 변화의 분류 체계성에 그대로 적용시킬 수가 있다. 본 연구에서는 선형 판별 함수를 원용하는 최우법(Maximum likelihood method)으로 산출되는 토지이용분류의 공간적 결과와 Markov 전이 행렬 방법으로 산출되는 정량적 결과가 상호 보완하는 의미에서 합성모형으로 통합되었다. 본 연구에서는 다변수 판별 함수의 계산법과 Markov 연쇄행렬 계산법에 관하여 토의되고 그 합성 모형을 대상 지역에 실제 적용하여 그 결과 '90년, '95년 토지이용도가 예측 작성되었다. 모형화의 문제 및 예측의 정확도 역시 더욱 토의 되어야 하며 추후 개선의 여지를 남긴다.

• 한국도로학회논문집
• /
• 제12권4호
• /
• pp.47-51
• /
• 2010

도로를 주행하는 차량들을 구분하는 차종자료는 도로 및 포장의 설계와 관리 등 여러 분야에서 기초자료로 활용되고 있다. 본 연구에서는 차종구분에 차량높이라는 분류기준을 적용하기 위해 주행하는 차량의 높이를 계측할 수 있는 방법을 고안하고 현장에 장비를 설치한 후 실험을 통해서 차량길이와 차량최고높이 자료를 획득하였다. 차량높이 측정과 동시에 동영상을 촬영하여 국토해양부 12종 차종분류에 의거하여 차종분류 기준값을 작성하였다. 영상을 통해 작성된 차종자료 기준값과 측정된 차량길이와 차량높이를 토대로 판별함수를 이용한 차종분류값을 서로 비교한 결과 88.6%의 차종정확도를 확인하였다. 이를 통해 차량높이라는 분류기준을 적용하여 차종분류에 활용할 수 있는 방안을 제시하였다.

• 한국데이타베이스학회:학술대회논문집
• /
• 한국데이타베이스학회 1999년도 춘계공동학술대회: 지식경영과 지식공학
• /
• pp.187-194
• /
• 1999

Case-Based Reasoning(CBR) systems support ill structured decision-making. The measure of the success of a CBR system depends on its ability to retrieve the most relevant previous cases in support of the solution of a new case. One of the methodologies widely used in existing CBR systems to retrieve previous cases is that of the Nearest Neighbor(NN) matching function. The NN matching function is based on assumptions of the independence of attributes in previous case and the availability of rules and procedures for matching.(omitted)

• 간호행정학회지
• /
• 제14권3호
• /
• pp.229-240
• /
• 2008

Purpose: To develop the patient classification system based on the resource utilization for reimbursement of long-term care hospitals in Korea. Method: Health Insurance Review & Assessment Service (HIRA) conducted a survey in July 2006 that included 2,899 patients from 35 long-term care hospitals. To calculate resource utilization, we measured care time of direct care staff (physicians, nursing personnel, physical and occupational therapists, social workers). The survey of patient characteristics included ADL, cognitive and behavioral status, diseases and treatments. Major category criteria was developed by modified delphi method from 9 experts. Each category was divided into 2-3 groups by ADL using tree regression. Relative resource use was expressed as a case mix index (CMI) calculated as a proportion of mean resource use. Result: This patient classification system composed of 6 major categories (ultra high medical care, high medical care, medium medical care, behavioral problem, impaired cognition and reduced physical function) and 11 subgroups by ADL score. The differences of CMI between groups were statistically significant (p<.0001). Homogeneity of groups was examined by total coefficient of variation (CV) of CMI. The range of CV was 29.68-40.77%. Conclusions: This patient classification system is feasible for reimbursement of long-term care hospitals.

• 한국인터넷방송통신학회논문지
• /
• 제9권2호
• /
• pp.1-6
• /
• 2009

많은 양의 데이터로부터 유용성있는 정보의 추출, 진단 및 예후에 대한 결정, 질병 치료의 응용 등은 바이오 인포머틱스(Bioinformatics)분야에서 매우 중요한 문제들이다. 본 논문에서는 암진단시스템에 적용하기위해 support vector machine을 위한 weogjted lernel fuction과 빠른 수렴성과 좋은 분류성능을 갖는 학습방법을 제안하였다. 제안된 kernel function에서 기본적인 kernel fuction의 weights는 암진단 학습단계에서 결정되고 분류단계에서 파리미터로 사용된다. 대장암 데이터와 같은 임상 데이터에 대한 실험결과에서 제안된 방법은 기존의 다른 kernel fuction들 보다 더 우수하고 안정적인 분류성능을 보여주었다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.354-354
• /
• 2000

In this paper, we would study the applicability of neural networks to the recognition process of Korean stenographic character image, applying the classification function, which is the greatest merit of those of neural networks applied to the various pans so far, to the stenographic character recognition, relatively simple classification work. Korean stenographic recognition algorithms, which recognize the characters by using some methods, have a quantitative problem that despite the simplicity of the structure, a lot of basic characters are impossible to classify into a type. They also have qualitative one that it is not easy to classify characters for the delicacy of the character forms. Even though this is the result of experiment under the limited environment of the basic characters, this shows the possibility that the stenographic characters can be recognized effectively by neural network system. In this system, we got 90.86% recognition rate as an average.