• 대한임베디드공학회논문지
• /
• 제2권2호
• /
• pp.95-100
• /
• 2007

Recently ubiquitous application services are developed plentifully using RFID techniques in the field of distribution and security industries. However, except these field the applications using RFID are not mature yet. In this study, we proposed a real-time context service model of the u-conference based on the real-time contextual information acquired from conference and exposition. With collection of real-time contextual information for u-conference, the model can provide a lot of information services on the state of session attendee, doorway control, affairs, user certification, presentation progress etc. For the verification of proposed real-time context service model of u-conference, we design and implement the conference progress state service included the state of session attendee, user certification and presentation progress etc. This service provides the presentation state information included the current presenter, the paper list, the number of session attendee, the schedule and place of each session using the collecting RFID tag and the related information.

• 인지과학
• /
• 제33권2호
• /
• pp.109-133
• /
• 2022

일화기억은 핵심 이벤트와 그에 연합된 맥락으로 구성된다. 해마와 해마 주변 영역이 일화기억의 부호화에서 맥락을 표상하는 역할에 관해 연구되어왔지만, 시공간적 맥락 외에 다양한 맥락-특이적 정보들에 대한 표상에 관한 연구는 많지 않다. 본 연구에서는 고해상도 자기기능공명기법을 이용하여 여러 맥락정보(예, 육하원칙 - 누가, 왜, 무엇을 언제, 어디서, 어떻게)의 부호화에 관여하는 내측두엽 및 대뇌피질 신경연결성의 특징을 탐색하였다. 참가자들은 두 명의 얼굴과 하나의 사물로 구성된 실험 이벤트를 보면서 여섯가지 맥락 부호화 과제를 수행하였다. 휴지기 기능적 자기공명영상 정보를 활용해 내측두엽의 세부 영역을 기능적으로 구분하였고 맥락 기억 과제별 기능적 신경연결성 네트워크를 탐색하였다. 일반선형화 모델 분석을 통해 시공간적 맥락정보를 처리할 때보다 사회적, 행동적, 의도 맥락을 연합할 때 내측두엽의 세부영역, 전전두엽, 하부두정엽 영역이 유의미하게 증가한 활성화를 보이며 관여함을 확인하였다. 나아가 이 영역들과 내측두엽 영역이 맥락조건간 차이에 관여하는 기능적 연결성 특징을 탐색하기 위하여 맥락부호화 과제를 수행하는 동안의 해마세부영역들과 전전두엽, 하부두정엽 등 간의 과제기반 기능적 연결성 정보들을 다변량 패턴분석의 주요입력변수로 선정하였고, 기계학습을 통해 맥락 조건 간 연결성 패턴분류를 시도하였다. 네트워크 패턴분류에서도 시공간 맥락 조건과 각 사회적, 행동적, 의도 맥락처리 조건 간에는 기능적 연결성의 차이가 두드러졌다. 본 연구결과를 통해 일화기억에서 특정 맥락을 처리하는 신경학적 기제의 특성과 맥락 조건 간 차이를 제시하였다.

• 한국컴퓨터정보학회논문지
• /
• 제22권10호
• /
• pp.121-128
• /
• 2017

In this paper, we propose a multi-label classification method in which multi-label classification estimation techniques are applied to resolving location prediction problem. Most of previous studies related to location prediction have focused on the use of single-label classification by using contextual information such as user's movement paths, demographic information, etc. However, in this paper, we focused on the case where users are free to visit multiple locations, forcing decision-makers to use multi-labeled dataset. By using 2373 contextual dataset which was compiled from college students, we have obtained the best results with classifiers such as bagging, random subspace, and decision tree with the multi-label classification estimation methods like binary relevance(BR), binary pairwise classification (PW).

• 한국컴퓨터정보학회논문지
• /
• 제22권11호
• /
• pp.97-104
• /
• 2017

Location prediction has been successfully utilized to provide high quality of location-based services to customers in many applications. In its usual form, the conventional type of location prediction is to predict future locations based on user's past movement history. However, as location prediction needs are expanded into much complicated cases, it becomes necessary quite frequently to make inference on the locations that target user visited in the past. Typical cases include the identification of locations that infectious disease carriers may have visited before, and crime suspects may have dropped by on a certain day at a specific time-band. Therefore, primary goal of this study is to predict locations that users visited in the past. Information used for this purpose include user's demographic information and movement histories. Data mining classifiers such as Bayesian network, neural network, support vector machine, decision tree were adopted to analyze 6868 contextual dataset and compare classifiers' performance. Results show that general Bayesian network is the most robust classifier.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2005년도 춘계종합학술대회
• /
• pp.1145-1148
• /
• 2005

본 논문에서는 다양한 시각적 정보와 일정한 관련 정보를 통합하여 인간의 피로도를 추론하기 위하여 베이지안 네트워크를 기반으로 한 확률 모델을 제안하고자 한다. 먼저 눈꺼풀의 움직임, 시선, 머리의 움직임, 그리고 얼굴 표정 같은 개인의 상태를 특성 지을 수 있는 시각적 매개변수를 측정하였다. 그러나 각각의 시각적 정보와 일정한 관련 정보만으로 인간의 피로도를 결정하기에는 충분하지 않으므로, 본 논문에서는 인간의 피로도를 모니터링 하기 위하여 가능한 많은 관련 정보와 시각 정보를 융합하여 베이지안 네트워크 모델을 개발하였다. 실험 결과, 피로 예측과 모델링을 위해 제안된 베이지안 네트워크의 유용함을 확인 할 수 있었다.

• 한국컴퓨터정보학회논문지
• /
• 제28권9호
• /
• pp.35-46
• /
• 2023

본 연구에서는 문서 분류기의 정확도를 높이기 위해 문맥 정보와 키워드 정보를 모두 사용하는 이중 접근(Dual Approach) 방법론을 제안한다. 우선 문맥 정보는 다양한 자연어 이해 작업(Task)에서 뛰어난 성능을 나타내고 있는 사전학습언어모델인 Google의 BERT를 사용하여 추출한다. 구체적으로 한국어 말뭉치를 사전학습한 KoBERT를 사용하여 문맥 정보를 CLS 토큰 형태로 추출한다. 다음으로 키워드 정보는 문서별 키워드 집합을 Autoencoder의 잠재 벡터를 통해 하나의 벡터 값으로 생성하여 사용한다. 제안 방법을 국가과학기술정보서비스(NTIS)의 국가 R&D 과제 문서 중 보건 의료에 해당하는 40,130건의 문서에 적용하여 실험을 수행한 결과, 제안 방법이 문서 정보 또는 단어 정보만을 활용하여 문서 분류를 진행하는 기존 방법들에 비해 정확도 측면에서 우수한 성능을 나타냄을 확인하였다.

• 한국산학기술학회논문지
• /
• 제13권2호
• /
• pp.628-635
• /
• 2012

스마트폰 애플리케이션(스마트폰 앱) 시장이 급속히 성장하고 있다. 본 연구는 스마트폰 앱에 대한 사용의도와 충성도의 변수인 정보품질(상호작용, 내용, 정황성)에 개인적인 태도(혁신성, 친숙성)가 미치는 영향을 실증적으로 평가하였다. 연구 결과 혁신성, 콘텐츠품질, 정황성품질은 사용의도에 긍정적인 영향을 주는 것으로 나타났다. 반면에 친숙성과 상호작용품질은 사용의도에 긍정적인 영향을 주지 않는 것으로 나타났다. 그리고 사용의도 역시 충성도에 긍정적인 영향을 주지 않는 것으로 나타났다.

• 한국정보시스템학회지:정보시스템연구
• /
• 제16권4호
• /
• pp.51-73
• /
• 2007

Ubiquitous computing is enhancing computer use by making many computers available throughout the physical environment, but making them effectively invisible to the user. To facilitate the successful adoption and diffusion of ubiquitous computing, it is necessary to figure out the factors affecting the use of U-service. Though the research related to ubiquitous computing has been vigorously conducted from the aspect of system and service provider, there have been very few studies that focus on the user's perspective. Therefore, this study attempts to figure out major factors which are dedicated to the development of ubiquitous computing and u-service, and that ultimately influence the u-business outcome. This study derived the factors that characterize u-service, such as ubiquity, contextual offer, reliability, invisibility, and confidentiality, which are then combined in the TAM model and carry out the path analysis. The research findings indicate that ubiquity affects both the perceived usefulness and perceived ease of use. The reliability and confidentiality were found to affect the perceived usefulness, whereas the contextual offer and invisibility turned out to influence the perceived ease of use. Finally, the relationship among the perceived usefulness, perceived ease of use, and the attitude toward using are identical with the previous research findings related to the technology acceptance model(TAM).

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1990년도 하계학술대회 논문집
• /
• pp.535-538
• /
• 1990

The main problem in speech recognition is the enormous variability in acoustic signals due to complex but predictable contextual effects. Especially in plosive consonants it is very difficult to find invariant cue due to various contextual effects, but humans use these contextual effects as helpful information in plosive consonant recognition. In this paper we experimented on three artificial neural net models for the recognition of plosive consonants. Neural Net Model I used "Multi-layer Perceptron ". Model II used a variation of the "Self-organizing Feature Map Model". And Model III used "Interactive and Competitive Model" to experiment contextual effects. The recognition experiment was performed on 9 Korean plosive consonants. We used VCV speech chains for the experiment on contextual effects. The speech chain consists of Korean plosive consonants /g, d, b, K, T, P, k, t, p/ (/ㄱ, ㄷ, ㅂ, ㄲ, ㄸ, ㅃ, ㅋ, ㅌ, ㅍ/) and eight Korean monothongs. The inputs to Neural Net Models were several temporal cues - duration of the silence, transition and vot -, and the extent of the VC formant transitions to the presence of voicing energy during closure, burst intensity, presence of asperation, amount of low frequency energy present at voicing onset, and CV formant transition extent from the acoustic signals. Model I showed about 55 - 67 %, Model II showed about 60%, and Model III showed about 67% recognition rate.

• 인터넷정보학회논문지
• /
• 제25권4호
• /
• pp.7-21
• /
• 2024

There are various machine learning techniques such as Reinforcement Learning, Deep Learning, Neural Network Learning, and so on. In recent, Large Language Models (LLMs) are popularly used for Generative AI based on Reinforcement Learning. It makes decisions with the most optimal rewards through the fine tuning process in a particular situation. Unfortunately, LLMs can not provide any explanation for how they reach the goal because the training is based on learning of black-box AI. Reinforcement Learning as black-box AI is based on graph-evolving structure for deriving enhanced solution through adjustment by human feedback or reinforced data. In this research, for mutually exclusive decision-making, Mutually Exclusive Learning (MEL) is proposed to provide explanations of the chosen goals that are achieved by a decision on both ends with specified conditions. In MEL, decision-making process is based on the tree-based structure that can provide processes of pruning branches that are used as explanations of how to achieve the goals. The goal can be reached by trade-off among mutually exclusive alternatives according to the specific contextual conditions. Therefore, the tree-based structure is adopted to provide feasible solutions with the explanations based on the pruning branches. The sequence of pruning processes can be used to provide the explanations of the inferences and ways to reach the goals, as Explainable AI (XAI). The learning process is based on the pruning branches according to the multi-dimensional contextual conditions. To deep-dive the search, they are composed of time window to determine the temporal perspective, depth of phases for lookahead and decision criteria to prune branches. The goal depends on the policy of the pruning branches, which can be dynamically changed by configured situation with the specific multi-dimensional contextual conditions at a particular moment. The explanation is represented by the chosen episode among the decision alternatives according to configured situations. In this research, MEL adopts the tree-based learning model to provide explanation for the goal derived with specific conditions. Therefore, as an example of mutually exclusive problems, employment process is proposed to demonstrate the decision-making process of how to reach the goal and explanation by the pruning branches. Finally, further study is discussed to verify the effectiveness of MEL with experiments.