• 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.

• 응용통계연구
• /
• 제33권6호
• /
• pp.833-842
• /
• 2020

넷플릭스, 아마존, 유튜브 등 대형 플랫폼에서는 고객의 다양한 정보를 활용하여 정밀한 추천시스템을 마련하고 여기서 추천된 상당수의 아이템이 실제 구매로 이어지고 있다. 본 논문에서는 추천 컨텐츠의 속성에 따라 사용자의 선호도에 차이가 있을 것이라고 예상하고 콘텐츠의 속성에 따라 군집분석을 실시하였다. 속성의 형태와 관계없이 사용할 수 있도록 Gower 거리를 사용했다. 본 논문에서는 영화 평점 사이트인 'The Movie Dataset'의 자료를 이용하여 영화의 기본정보인 장르, 감독 및 배우 변수를 바탕으로 사용자를 계층적으로 분류하고 영화를 추천하였다. 본 논문에서 제안한 추천 시스템을 평가하기 위하여 각 사용자 그룹별로 훈련자료와 검증자료로 나누어 정밀도를 살펴보았다. 그 결과 UBCF보다 월등히 높은 정밀도를 갖는 것으로 나타났다.

• 한국강구조학회 논문집
• /
• 제14권4호
• /
• pp.549-556
• /
• 2002

바닥구조의 진동을 평가하는데 있어 기존의 고유진동수 예측식에 의한 방법이 사용되어지고 있다. 그러나, 이러한 예측식들은 재료에 따른 구분이 없기 때문에 실제와느나 다른 결과를 보이게 된다. 또한, 합성데크 플레이트 슬래브의 경우, 고유진동수를 예측하기 위해 슬래브의 단면을 환산해야 하는데, 각 데크 플레이트의 특성상 그 형태가 상이함으로 인하여 많은 어려움을 느끼게 된다. 따라서, 본 논문에서는 슬래브의 단면을 환산하기 위한 새로운 단순화된 방법을 제시하였다. 그리고, 실제 측정값과 가장 오차율이 적은 "LRFD"에 제안된 고유진동수 산출식을 보정하여 기존 예측시에 비해 약 14.3%의 오차율을 개선하는 새로운 예측보정식을 제안하고, 이에 대한 일반적인 적용가능성을 검증하였다.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2005년도 춘계학술대회 논문집
• /
• pp.223-227
• /
• 2005

여수해만 특정해역 밖의 인근해역은 섬들이 매우 많고 수심이 낮은 해역으로서 한반도의 동 ${\cdot}$ 서해안을 운항하는 선박들이 섬 사이의 협소한 해역을 통항하고 있어 잦은 교행이 이루어지고 있으며, 이들 선박은 소리도 남단과 욕지도 부근 해역에서 원유 운반선, 광석운반선 및 컨테이너선과 같은 대형선과 만나면서 교통 혼잡도를 가중시키고 있다. 따라서 본 연구에서는 교통의 흐름을 단순화하고, 교차 및 집중 상황을 완화시키기 위한 통항분리대의 도입 및 추천항로의 설정한다.

• 한국간호교육학회지
• /
• 제20권4호
• /
• pp.596-605
• /
• 2014

Purpose: This study aims to understand the influence of college entrance system-related factors and scores of college scholastic ability test on a first year nursing student's academic achievement. Method: Data collected include both a descriptive survey designed to assess college entrance system-related factors with respect to 182 nursing students attending a 4-year nursing college program and their test scores in the first year. The data were analyzed via descriptive statistics, Mann-Whitney U test, Kruskal-Wallis test with Bonferroni's correction, and Spearman's rank correlation coefficient through an SPSS 18.0 program. Results: Student academic achievement with regard to college entrance system-related factors exhibited significant divergence from first year grade point averages (hereafter GPA) and natural science grades. Conclusion: This study confirmed the existence of significant differences, depending on the factors regarding the college entrance system. As a result, conducting assessment to evaluate the level of basic knowledge before college entrance is highly recommended. Also recommended is the development of a support program for students projected to have difficulties with respect to their academic achievement.

• 한국멀티미디어학회논문지
• /
• 제22권9호
• /
• pp.1108-1121
• /
• 2019

As the quality and level of life rise, many people are doing search for various pieces of information about tourism. In addition, users prefer the search methods reflecting individual opinions such as SNS and blogs to the official websites of tourist destination. Many of previous studies focused on a recommendation system for tourist courses based on the GPS information and past travel records of users, but such a system was not capable of recommending the latest tourist trends. This study thus set out to collect and analyze the latest SNS data to recommend tourist destination of high interest among users. It also aimed to propose an altered TSP algorithm to recommend the optimal routes to the recommended destination within an area and a system to recommend the optimal tourist courses by applying the Elasticsearch engine. The altered TSP algorithm proposed in the study used the location information of users instead of Dijkstra's algorithm technique used in previous studies to select a certain tourist destination and allowed users to check the recommended courses for the entire tourist destination within an area, thus offering more diverse tourist destination recommendations than previous studies.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 A
• /
• pp.61-65
• /
• 2000

This paper presents the load shedding case studies and recommendations of load shedding scheme For improving the reliability to suit the requirements of LG-Caltex refinery plant power sγstem. It is recommended for LG-Caltex to decrease the total generation for the economic dispatch. When the LG-Caltex refinery is isolated from KEPCO utility system, the proper load shedding scheme should be implemented since total generation in LG-Caltex refinery plant is less than the load demand. According to the studies carried out the logic-based load shedding is recommended as the main protection scheme, with the combination of the under-frequency relay load shedding.

• 대한안전경영과학회지
• /
• 제16권1호
• /
• pp.231-237
• /
• 2014

In order to improve participation and quick decision-making in an emergency, the Voluntary Participation Program was recommended in this study for effective management of Civil Defense. The problems in the Law and Administration group and Forced Education by Mobilization system were analyzed through actual conditions of Civil Defense management and participation. In order to improve these problems, cases such as "Extension of Participation Methods", "Cooperation Activities with Civil Groups", "Usage of Community Information" were studied. Based on the investigation results, domestic applicability was recommended.

• 수산해양기술연구
• /
• 제57권1호
• /
• pp.69-77
• /
• 2021

The noise environment was evaluated using the ISO recommended NR evaluation curve and PSIL (Preferred Sound Interference Level) in order to investigate the onboard educational environment according to the noise in the Motor Vessel Saehaerim, a fishing training ship under making way. As a result, NRNs were measured at 37-61 dB in accommodation areas, 44-56 dB in work areas, 37-57 dB in educational and conference areas, 83-103 dB in engine areas and 65.3 dB and 51.2 dB in the work and education areas respectively based on PSIL. The NRNs, which evaluated the cabin of the experimental ship according to the purpose, exceeded all of the indoor standard noise recommended by the ISO, and the PSIL had a generally short conversational distance within 0.25-2.3 m and 0.75-1.3 m for teaching and work areas.

• 한국IT서비스학회지
• /
• 제20권4호
• /
• pp.129-140
• /
• 2021

Recently, interest in AI tutors is rising as a way to bridge the educational gap in school settings. However, research confirming the effectiveness of AI tutors is lacking. The purpose of this study is to explore how effective learner characteristics and recommended item learning activities are in predicting learner's academic performance in an adaptive online learning environment. This study proposed the hypothesis that learner characteristics (prior knowledge, midterm evaluation) and recommended item learning activities (learning time, correct answer check, incorrect answer correction, satisfaction, correct answer rate) predict academic achievement. In order to verify the hypothesis, the data of 362 learners were analyzed by collecting data from the learning management system (LMS) from the perspective of learning analytics. For data analysis, regression analysis was performed using the regsubset function provided by the leaps package of the R program. The results of analyses showed that prior knowledge, midterm evaluation, correct answer confirmation, incorrect answer correction, and satisfaction had a positive effect on academic performance, but learning time had a negative effect on academic performance. On the other hand, the percentage of correct answers did not have a significant effect on academic performance. The results of this study suggest that recommended item learning activities, which mean behavioral indicators of interaction with AI tutors, are important in the learning process stage to increase academic performance in an adaptive online learning environment.