• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2001년도 The Pacific Aisan Confrence On Intelligent Systems 2001
• /
• pp.164-168
• /
• 2001

This paper introduces an agent system that assists in user's work on the Internet. First, the agent receives requests from the user or other agents. Since there are various kinds of requests, it is difficult to describe a completes set of request -handling rules in advance. Therefore, the agent makes a plan referring to old cases. The agent executes the plane which is a sequence of basic operation. If the agent fails to execute basic operation or to create a plan. then it makes a new plan by interacting with the user or other agent. Finally the agent stores this new case with user's evaluation score into the case base.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권6호
• /
• pp.2464-2479
• /
• 2020

This paper presents a detailed subjective quality assessment for the ultra-high definition (UHD) videos having frame rates of 30fps and 60 fps. The subjective assessment is based on the ITU-R BT-500 recommendations, where double stimulus continuous quality scale (DSCQS-type II) test is performed for the evaluation of the perceived quality of the user's in terms of differential mean opinion score (DMOS). Encoding of the UHD videos by opting encoders i.e. H.264/AVC, H.265/HEVC, and VP9 at five different quantization parameter (QP) levels is done to investigate the perceived user's quality of experience (QoE) given as DMOS. Moreover, the encoding efficiency as the encoding time for each encoder and qualitative performance by employing full-reference (FR) quality metrics are presented in this work.

• 한국임상약학회지
• /
• 제33권1호
• /
• pp.51-61
• /
• 2023

Background: Mobile applications (apps) on dietary supplements can increase consumers' access to information. However, it can lead to indiscriminate use of dietary supplements. This study aims to systematically review dietary supplement apps released in English and Korean and evaluate the quality of those apps. Methods: Through the app stores, apps on dietary supplements were systemically searched and examined. Two independent evaluators evaluated the apps and presented a mean score using the Mobile App Rating Scale (MARS). The correlation between MARS scores, user and evaluator ratings, and the number of secondary features of the apps were analyzed. Results: Of the 2,772 dietary supplement apps identified, 17 apps were included according to the selection criteria. The mean MARS score was 3.28 (standard deviation: 0.29) out of 5. Apps had higher scores in aesthetics and functionality dimensions, while engagement and information dimensions had lower scores. There was a positive correlation between the number of app downloads and information among MARS dimensions. The subjective evaluation also correlated with the information dimension. There was a positive correlation between the secondary features of the apps and MARS total score as well as the engagement dimension. Conclusion: The dietary supplement apps need to be managed at a higher level of quality to provide safe and reliable information to consumers. Especially, quality on information and engagement dimensions can be improved. Involvement of healthcare professionals in the app development, management with adequate referencing of information, and use of secondary features for enhanced user engagement can be helpful.

• 융합정보논문지
• /
• 제12권5호
• /
• pp.150-158
• /
• 2022

본 연구의 목적은 이용자의 관점에서 노인장기요양보험 방문요양서비스 기관 평가의 효과성을 확인하는 것이다. 이를 위해, 전라북도 내 지역별(14개 시·군) 할당표집을 통해 수집한 이용자(266명) 설문자료와 기관(47개) 자료를 결합하여 다층모형으로 분석하였다. 주요 연구결과는 다음과 같다. 첫째, 5개 평가영역 중 이용자에게 권리의식을 갖게하고, 이용자를 존중하는지에 대한 '권리·책임' 영역의 점수가 높을수록 서비스 품질과 만족도도 높게 나타났다. 둘째, 5개 평가영역 중 '권리·책임' 영역과 '급여제공결과' 영역이 충성도에 영향을 미치는 것으로 나타났다. 셋째, '기관운영', '환경·안전', '급여제공과정' 영역은 서비스 품질, 만족도, 충성도에 영향을 미치지 않는 것으로 나타났다. 이러한 결과를 바탕으로 형식적이고 정량적인 평가지표보다는 이용자가 인식할 수 있고, 방문요양서비스의 기본 목적에 충실한 내용으로 평가지표를 재구성할 것 등을 제안하였다.

• 지능정보연구
• /
• 제25권1호
• /
• pp.219-239
• /
• 2019

개인에게 맞춤형 서비스를 제공하는 것이 중요해지면서 개인화 추천 시스템 관련 연구들이 끊임없이 이루어지고 있다. 추천 시스템 중 협업 필터링은 학계 및 산업계에서 가장 많이 사용되고 있다. 다만 사용자들의 평점 혹은 사용 여부와 같은 정량적인 정보에 국한하여 추천이 이루어져 정확도가 떨어진다는 문제가 제기되고 있다. 이와 같은 문제를 해결하기 위해 현재까지 많은 연구에서 정량적 정보 외에 다른 정보들을 활용하여 추천 시스템의 성능을 개선하려는 시도가 활발하게 이루어지고 있다. 리뷰를 이용한 감성 분석이 대표적이지만, 기존의 연구에서는 감성 분석의 결과를 추천 시스템에 직접적으로 반영하지 못한다는 한계가 있다. 이에 본 연구는 리뷰에 나타난 감성을 수치화하여 평점에 반영하는 것을 목표로 한다. 즉, 사용자가 직접 작성한 리뷰를 감성 수치화하여 정량적인 정보로 변환해 추천 시스템에 직접 반영할 수 있는 새로운 알고리즘을 제안한다. 이를 위해서는 정성적인 정보인 사용자들의 리뷰를 정량화 시켜야 하므로, 본 연구에서는 텍스트 마이닝의 감성 분석 기법을 통해 감성 수치를 산출하였다. 데이터는 영화 리뷰를 대상으로 하여 도메인 맞춤형 감성 사전을 구축하고, 이를 기반으로 리뷰의 감성점수를 산출한다. 본 논문에서 사용자 리뷰의 감성 수치를 반영한 협업 필터링이 평점만을 고려하는 전통적인 방식의 협업 필터링과 비교하여 우수한 정확도를 나타내는 것을 확인하였다. 이후 제안된 모델이 더 개선된 방식이라고 할 근거를 확보하기 위해 paired t-test 검증을 시도했고, 제안된 모델이 더 우수하다는 결론을 도출하였다. 본 연구에서는 평점만으로 사용자의 감성을 판단한 기존의 선행연구들이 가지는 한계를 극복하고자 리뷰를 수치화하여 기존의 평점 시스템보다 사용자의 의견을 더 정교하게 추천 시스템에 반영시켜 정확도를 향상시켰다. 이를 기반으로 추가적으로 다양한 분석을 시행한다면 추천의 정확도가 더 높아질 것으로 기대된다.

• Journal of Information Processing Systems
• /
• 제17권4호
• /
• pp.707-720
• /
• 2021

To improve the accuracy of the recommendation system, multi-criteria recommendation systems have been widely researched. However, it is highly complicated to extract the preferred features of users and items from the data. To this end, subjective indicators, which indicate a user's priorities for personalized recommendations, should be derived. In this study, we propose a method for generating recommendation candidates by predicting multi-criteria ratings from reviews and using them to derive user priorities. Using a deep learning model based on convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM), multi-criteria prediction ratings were derived from reviews. These ratings were then aggregated to form a linear regression model to predict the overall rating. This model not only predicts the overall rating but also uses the training weights from the layers of the model as the user's priority. Based on this, a new score matrix for recommendation is derived by calculating the similarity between the user and the item according to the criteria, and an item suitable for the user is proposed. The experiment was conducted by collecting the actual "TripAdvisor" dataset. For performance evaluation, the proposed method was compared with a general recommendation system based on singular value decomposition. The results of the experiments demonstrate the high performance of the proposed method.

• 대한물리치료과학회지
• /
• 제27권3호
• /
• pp.35-44
• /
• 2020

Background: This study was to confirm the effect and feasibility of knee extension assist orthosis (KEAO) on balance and gait in subacute stroke patients. Design: Case study. Methods: The subjects of the study were 4 subacute stroke patients, who had an onset period of less than 6 months. The limit of stability (LOS) and berg balance scale (BBS), timed up and go test (TUG) were used to verify the dynamic balance ability, static balance ability, and gait ability pre and post and after wearing the knee extension assist orthosis (KEAO). In addition, the satisfaction survey was to confirm the feasibility of the knee extension assist orthosis (KEAO) through the to Korean quebec user evaluation of satisfaction assistive technology 2.0 (K-QUEST 2.0). Results: After the wearing on KEAO, the distance for the limit of stability decreased by mean 541.25±240.46 mm2, and the score on the berg balance scale improved by mean 5±2.71 point, and the time for the timed up and go test deceased by mean 3.75±1.71 second. The stability and durability were found to be full score, and the control, ease, effectiveness were some high score, and the size, weight, comfort were some low score in the satisfaction and feasibility. Conclusion: The knee extension assist orthosis (KEAO) produce in this study was improved the static balance ability, dynamic balance ability and gait ability of subacute stroke patients, and the satisfaction and feasibility were high in the stability, durability and effectiveness of the user.

• 디지털융복합연구
• /
• 제11권5호
• /
• pp.31-39
• /
• 2013

스마트TV는 컴퓨팅 능력, 방송 및 인터넷 서비스가 가능한 상호작용을 높인 텔레비전이다. 사용성은 스마트TV의 평가요소로 그 중요성이 있다. 사용성 관점에서 스마트TV를 평가하기 위해서는 사용성에 영향을 미치는 요인을 중심으로 한 측정 모델의 개발이 필요하다. 본 논문에서는 스마트TV의 사용성 측정을 위한 AHP(계층적분석과정) 모델과 측정 데이터를 획득하는 방법을 제안한다. 선행연구로부터 사용성에 영향을 미치는 요인을 도출한 후 사용성 점수를 계산하는 수치적 예제를 보인다.

• 디지털산업정보학회논문지
• /
• 제19권3호
• /
• pp.221-232
• /
• 2023

In this paper, we propose a recommendation system based on the latent factor model using matrix factorization, which is one of the most commonly used collaborative filtering algorithms for recommendation systems. In particular, by introducing the concept of creating a list of recommended content and a list of non-preferred recommended content, and removing the non-preferred recommended content from the list of recommended content, we propose a method to ultimately increase the satisfaction. The experiment confirmed that using a separate list of non-preferred content to find non-preferred content increased precision by 135%, accuracy by 149%, and F1 score by 72% compared to using the existing recommendation list. In addition, assuming that users do not view non-preferred content through the proposed algorithm, the average evaluation score of a specific user used in the experiment increased by about 35%, from 2.55 to 3.44, thereby increasing user satisfaction. It has been confirmed that this algorithm is more effective than the algorithms used in existing recommendation systems.

• 대한안전경영과학회지
• /
• 제14권2호
• /
• pp.123-136
• /
• 2012

The validity of the results from observational methods such as RULA, REBA, OWAS has been one of major concerns due to their subjective characteristics in determining the posture of interests. There have been many studies regarding validity of the results from each checklist. However, most studies provided only fragmentary rather than comprehensive results in nature. This study specifically tried to analyze consistency of novice user based on intra-observer consistency and sensitivity of industrial types during MSDs(Musculoskekltal Disorders) evaluation with major checklists. In this study, twenty two novice subjects were participated to conduct MSDs evaluation for the forty five jobs from three types of industries(automobile, electronics, hospital). The main results for this study were summarized as follows; 1) The action level based on RULA was always higher than that from REBA and OWAS for all three types of industries., 2) The order of consistency from novice users was OWAS(72.7%(kappa=0.57)) RULA(54.3%(kappa=0.41)), REBA(41.0%(kappa=0.34))., 3) The percentage of agreement between 2nd and 3rd trials was higher than those between 1st and 2nd trials and between 1st and 3rd trials irrespective of industrial types during using RULA and REBA., 4) The average score of automobile industry was higher than those of hospital and electronics industries., 5) The types of jobs associated with five body parts(A1(Front), A2(Interior), A3(Rear), A4(Lower), A5(Door)) in automobile industry showed statistically significant differences in terms of MSDs scores for the body parts considered in each checklists.