• Journal of the Korea Society of Computer and Information
• /
• v.21 no.7
• /
• pp.9-16
• /
• 2016

Collaborative filtering(CF) uses the purchase or item rating history of other users, but does not need additional properties or attributes of users and items. Hence CF is known th be the most successful recommendation technology. But conventional CF approach has some significant weakness, such as the new user problem. In this paper, we propose a approach using word embedding with skip-gram for learning distributed item representations. In particular, we show that this approach can be used to capture precise item for solving the "new user problem." The proposed approach has been tested on the Movielens databases. We compare the performance of the user based CF, item based CF and our approach by observing the change of recommendation results according to the different number of item rating information. The experimental results shows the improvement in our approach in measuring the precision applied to new user problem situations.

• Physical Therapy Korea
• /
• v.11 no.2
• /
• pp.9-16
• /
• 2004

The purpose of this study was to validate the Korean version of the Gross Motor Function Measure (GMFM) using Rasch analysis. The data was obtained from the assessments of 59 children with cerebral palsy in Korea and were applied to Rasch's rating scale model to estimate the difficulty and goodness-of-fit of each item. Rasch modeling helped us to identify 76 items from the original 88-item GMFM that form an unidimensional hierarchical scale to rearrange 76 items in order of difficulty. Reliability coefficients of the 88-item and 76-item GMFM were .99 and .99, respectively. In this preliminary report, the Korean version of GMFM seems to have significant validity and reliability. These results may be useful in assessment of gross motor functions in children with cerebral palsy.

• International Commerce and Information Review
• /
• v.10 no.2
• /
• pp.265-282
• /
• 2008

This article is a study on the A Study on the Export and Import Public Notification System for Efficiency of Trade Item Management. The purpose of this article shall be studies to the trade control regulation in korea foreign law. this article are two most important elements in strategic item and rule of origin. that is, economic profit and nation industries protect have been obtain trade control system. The trade public notification system achieve efficiency of trade item control and nation industry development and domestic customer protect and trade order for trade system and control scheme. Therefor, The Result of the article is review to protection of domestic.

• Speech Sciences
• /
• v.13 no.2
• /
• pp.7-18
• /
• 2006

An aphasia screening test can serve a main purpose of differentiating aphasics from non-aphasic patients in a quick as well as efficient manner. As a preliminary study for developing a standardized aphasia screening test for Korean patients, we constructed an aphasia screening test constituting items from the Paradise' Korean version-the Western Aphasia Battery(P K-WAB). All test items were analyzed in order to extract items with optimal item discrimination and adequate item difficulty indices. From the results, we were able to select some items from each subtest with optimal results of discriminant function analysis for aphasic and normal control groups. It is expected, thus, that information on the item analysis could be utilized in developing a Korean aphasia screening test.

• Journal of Information Technology Applications and Management
• /
• v.16 no.1
• /
• pp.97-113
• /
• 2009

Collaborative filtering(CF) has been a very successful approach for building recommender system, but its widespread use has exposed to some well-known problems including sparsity and scalability problems. In order to mitigate these problems, we propose two novel models for improving the typical CF algorithm, whose names are ISCF(Item-Selected CF) and USCF(User-Selected CF). The modified models of the conventional CF method that condense the original dataset by reducing a dimension of items or users in the user-item matrix may improve the prediction accuracy as well as the efficiency of the conventional CF algorithm. As a tool to optimize the reduction of a user-item matrix, our study proposes genetic algorithms. We believe that our approach may relieve the sparsity and scalability problems. To validate the applicability of ISCF and USCF, we applied them to the MovieLens dataset. Experimental results showed that both the efficiency and the accuracy were enhanced in our proposed models.

• Journal of Korea Multimedia Society
• /
• v.25 no.8
• /
• pp.1242-1250
• /
• 2022

When recommending cold items that do not have user-item interactions to users, even we adopt state-of-the-arts algorithms, the predicted information of cold items tends to have lower accuracy compared to warm items which have enough user-item interactions. The lack of information makes for recommender systems to recommend monotonic items which have a few top popular contents matched to user preferences. As a result, under-diversified items have a negative impact on not only recommendation diversity but also on recommendation accuracy when recommending cold items. To address the problem, we adopt a diversification algorithm which tries to make distributions of accumulated contents embedding of the two items groups, recommended items and the items in the target user's already interacted items, similar. Evaluation on a real world data set CiteULike shows that the proposed method improves not only the diversity but also the accuracy of cold item recommendation.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.145-146
• /
• 2023

본 논문에서는 최대 규모의 게임 플랫폼인 Steam에서 수집한 유저 정보 데이터 셋에 Item2vec과 LSTM을 사용하여 추천 시스템을 구현한다. 수집한 유저 정보 데이터 셋에 Item2vec을 적용하여 각각의 유저들이 보유하고 있는 고유한 Appid들을 200차원의 벡터로 변환한다. 그 후 데이터 셋을 기간에 따라 4단계의 시퀀스로 나눈 후 LSTM을 사용하여 유저별로 최대 5가지의 추천 리스트를 생성한다. 유저 정보 데이터 셋은 액티브한 유저 정보를 얻기 위해 Steam 게임 리뷰 항목에서 리뷰를 남긴 유저들의 데이터를 api를 사용해 수집했으며 LSTM을 사용한 실험의 성능 평가 지표는 RMSE를 사용했고 이때의 성능은 0.1357을 얻을 수 있었다.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.23 no.5
• /
• pp.774-783
• /
• 1994

New food item numbers for each food included in Food Composition Table in Korea (4th ed) and other Food Composition Table. New Food item numbers classified to base 5-basic food groups and its classification was as follows. 1 As for the 1569 food items , they were classified as 20 food sub-groups(82 food sorts) for 5-basic food groups. 2. As for the 82 food sorts, they were individually classified with raw prepared , fat sugar content and arranged in order, ㄱ , ㄴ and ㄷ and made the item number. 3. The data set of nutritive value of food with new item numbers was accessed on computer files. 4. The Food & Description Table was drafted as 1572 food items were arranged in order, ㄱ, ㄴand ㄷ. 5. The Food Table arranged in the order or each nutrient content (energy, carbohydrate, protein , etc....) was drafted. Clipper program for computing nutritive values and tabulation of nutrients of daily diet were coded by applying new food item numbers. It is expected that should utilized as a basic data of computer program for calculating the nutritive value of diet, evaluating the nutrition and counseling the nutrition.

• School Mathematics
• /
• v.14 no.4
• /
• pp.517-529
• /
• 2012

Assessment in the school should be done consistently in accordance with the national curriculum. This study analyzed the process that preservice teachers developed the question items. The preservice teachers already equipped with the knowledge about the curriculum, didn't reflect it to items at first. However, in the review and modification process with colleague discussions, they get the curriculum coherence faithfully. And the item completeness gets higher such as to conform to the item intent, to help the students easily understand the item and to have the consistency between items.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.30 no.6 s.154
• /
• pp.992-1000
• /
• 2006

The main purpose of this research is to develop the methodology of objective evaluation of clothing appearance by eye movement analysis. The visual clothing items used in this study were skirt, one-piece, pants and shirt with the style variation of silhouette and details. By observing eye movement during visual evaluation of clothing, we can achieve the basic fixation data of eye movement. Moreover, we developed the Matlab program to extract the fixation coordinate and number of eye fixation on each part of the clothing item. As results, there were differences in the duration of fixation time for each item and the fixation time was not different by styles within a clothing item. However, we could find differences in the fixation time within a style, in other words, we could select the important parts of the clothing by observing the fixation time in a certain clothing item. It is also noted that time required in visual information processing differs depending on the item, and there was a region which contain more information independent with styles in the same item. By developing the objective method of visual evaluation that correspond to human's visual information processing, the results are expected to be applied in the retrieval program in internet shopping mall or in the development of contents for advertisement of clothing.