• Annual Conference on Human and Language Technology
• /
• 2013.10a
• /
• pp.64-69
• /
• 2013

스마트폰의 대중화로 인하여 앱 마켓 시장이 급속도로 성장하였다. 이로 인하여 하루에도 수십개의 새로운 앱들이 출시되고 있다. 이러한 앱 마켓 시장의 급격한 성장으로 인해 사용자들은 자신이 흥미를 가질만한 앱들을 선택하는데 큰 어려움을 겪고 있어 앱 추천 방법에 대한 연구에 많은 관심이 집중되고 있다. 기존 연구에서 협력 필터링 기반의 추천 방법들을 제안하였으나 이는 콜드 스타트 문제를 지니고 있다. 이와는 달리 컨텐츠 기반 필터링 방식은 콜드 스타트 문제를 효율적으로 해소할 수 있는 방법이지만 앱설명에는 광고, 공지사항등 실질적으로 앱의 특징과는 무관한 노이즈들이 다수 존재하고 이들은 앱 사이의 유사관계를 파악하는데 방해가 된다. 본 논문에서는 이런 문제를 해결하기 위하여 앱 설명에서 노이즈에 해당하는 설명들을 자동으로 제거할 수 있는 모델을 제안한다. 제안하는 모델은 모바일 앱 설명을 구성하고 있는 각 문단을 LDA로 학습된 토픽들의 비율로 나타내고 이들을 분류문제에서 우수한 성능을 보이는 SVM을 이용하여 분류한다. 실험 결과에 따르면 본 논문에서 제안한 방법은 기존에 문서 분류에 많이 사용되는 Bag-of-Word 표현법에 기반한 문서 표현 방식보다 더 나은 분류 성능을 보였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.577-578
• /
• 2016

QR 코드를 이용한 접촉 매체를 이용해 본 경험자 중 대부분은 스마트폰을 사용한 것으로 나타났으며, 해당 접촉 매체 중 가장 높은 이용 비율을 나타낸 매체는 홍보용 전단지나 브로슈어 등 이다. 이와 같이 스마트폰의 보급에 따른 QR 코드의 이용 범위가 마케팅 분야에 집중되면서 효율적인 이용 방법에 대한 연구가 증가하고 있는 추세이다. 본 연구에서는 QR 코드에 저장된 음식에 대한 상세 정보를 활용한 모바일 웹 기반의 음식 추천을 위한 개인화 서비스 시스템을 제안한다.

• The Journal of the Korea Contents Association
• /
• v.19 no.8
• /
• pp.106-114
• /
• 2019

The study was conducted to investigate the effect of whole-wheat ratio and nutrition information provision on purchasing behavior and consumer intention among individuals in their twenties who lack calcium intake. In the end, this study aims to provide basic data on the development and marketing strategy of customized nutrition-reinforced snacks. Regarding whole wheat ratios, the acceptance of taste of whole wheat flour was highest in ZF but didn't seem significant difference with HF's. The familiarity of taste and flavor (P <0.001), purchase intention (p <0.001) and recommendation intention (p <0.001) were higher in order of ZF, HF and TF. Regarding information provision, familiarity of taste and flavor (P <0.05), purchase intention (p <0.05) and recommendation intention (p <0.05) were higher in order of detailed information group, non - information group and simple information group. Therefore, developing calcium-fortified biscuit, mixing whole wheat flour with normal flour might reduce consumer's resistance, Also, providing detailed information on the degree of fortification of calcium and dietary fiber might cause a synergistic effect on consumption.

• The KIPS Transactions:PartB
• /
• v.16B no.1
• /
• pp.55-62
• /
• 2009

Collaborative filtering is a popular technique that recommends items based on the opinions of other people in recommender systems. Memory-based collaborative filtering which uses user database can be divided in user-based approaches and item-based approaches. User-based collaborative filtering predicts a user's preference of an item using the preferences of similar neighborhood, while item-based collaborative filtering predicts the preference of an item based on the similarity of items. This paper proposes a combined forecast scheme that predicts the preference of a user to an item by combining user-based prediction and item-based prediction using the ratio of the number of similar users and the number of similar items. Experimental results using MovieLens data set and the BookCrossing data set show that the proposed scheme improves the accuracy of prediction for movies and books compared with the user-based scheme and item-based scheme.

• Journal of Navigation and Port Research
• /
• v.41 no.6
• /
• pp.445-450
• /
• 2017

It is necessary to set a route to reflect the traffic flow for the safety of the traffic vessels. This ongoing analysis is needed to ensure that the vessels comply with a route. The purpose of this study is to discover the problems of the recommended route vicinity for Wando Harbor and suggest an improvement plan. We used a support vector machine based on the ship's trajectory to establish an efficient route center line. Since the vessels should navigate to the starboard side, with reference to the center line of the recommended route, the trajectories of the vessels were divided into two clusters. The support vector machine is being used in many fields such as pattern recognition, and it is effective for this binary classification. As a result of this study, about 79.5 % of the merchant eastbound ships in a 2.4 NM distance to Jangjuk Sudo did not observe the recommended route, so the risk of collision always existed. The contraflow traffic rate of the route of the eastbound ships decreased from 79.5 % to 30.9 % when the recommended route was reset about 300 meters to the north, from its present position. The support vector machine applied in this study is expected to be applicable, to effectively set the route center line because the ship trajectories can be classified into two clusters.

• Proceedings of the Korean Society for Bio-Environment Control Conference
• /
• 1997.05a
• /
• pp.11-16
• /
• 1997

본 연구는 양액재배에서 영양진단에 기초한 배양액관리를 하기 위해 유효한 수단으로 이용되고 있는 신속하고 간편하며 정확한 즙액분석 방법(질산태질소의 정량방법, 인산정량방법, 즙액추출법, 추출비율, 마쇄시간 및 샘플채취 부위 등)들에 관한 비교검토를 하였다. 'Earl's Favorite 춘계 F$_1$호'를 1993년 1월 11일에 파종하여 본엽 3~4매의 묘를 스티로폼베드내 암면슬라브에 정식하여 비순환방식으로 재배했다. 즙액분석법은 결핍이나 과잉증상이 외관적으로 나타나기 전에 신속하고 간이한 즙액분석법에 의해 작물체의 영양상태를 진단하여 대응이 가능하다고 판단되었다. 즙액분석시 질산태질소의 분석에는 자외부흡광도법, 인산분석에는 바나드몰리브덴산법이 추천되었고, 추출비율은 1:4로, 엽병의 마쇄시간은 60초, 그리고 채취 부위는 일정부위로 하는 것이 바람직하다고 판단되었다. 그러나 샘플채취시간에 대해서는 채취시간에 따른 차이가 크기 때문에 앞으로 보다 상세한 검토가 요청되었다.

• Journal of KIISE:Software and Applications
• /
• v.32 no.8
• /
• pp.693-703
• /
• 2005

Given the local traders with pattern-based multi-predictors of stock prices, we study a method of dynamic asset allocation to maximize the trading performance. To optimize the proportion of asset allocated to each recommendation of the predictors, we design an asset allocation strategy called meta policy in the reinforcement teaming framework. We utilize both the information of each predictor's recommendations and the ratio of the stock fund over the total asset to efficiently describe the state space. The experimental results on Korean stock market show that the trading system with the proposed meta policy outperforms other systems with fixed asset allocation methods. This means that reinforcement learning can bring synergy effects to the decision making problem through exploiting supervised-learned predictors.

• Journal of Gifted/Talented Education
• /
• v.16 no.2
• /
• pp.101-122
• /
• 2006

In this study, selecting process for scientifically gifted students was investigated and analyzed to science education institute for the gifted in university and was compared with foreign education institute for the gifted. The number of science education institute for the gifted was unequality located to the regions, comparing with the ratio of students. Therefore it is necessary for balancing location of science education institute for the gifted according to the ratio of students to let various students have the gifted education. Comparing with the ratio of gifted students between elementary school students and middle school students, the shape of ratios seems to be a inversed-pyramid. It is necessary to select students with the shape of the pyramid, supporting them to be educated, systematically and officially. The gifted students were selected through the procedures of creative test, intelligent test and individual interview in science education institute

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.4
• /
• pp.504-510
• /
• 2009

Recently, personalized-adaptive services became the center of interest in the world. However the services about music are not widely diffused out. That is because the analyzing of music information is more difficult than analyzing of text information. In this paper, we propose a music recommendation system which provides personalized services. The system keeps a user's listening list and analyzes it to select pieces of music similar to the user's preference. For analysis, the system extracts properties from the sound wave of music and the time when the user listens to music. Based on the properties, a piece of music is mapped into a point in the property space and the time is converted into the weight of the point. At this time, if we select and analyze the group which is selected by user frequently, we can understand user's taste. However, it is not easy to predict how many groups are formed. To solve this problem, we apply the K-means clustering algorithm to the weighted points. We modified the K-means algorithm so that the number of clusters is dynamically changed. This manner limits a diameter so that we can apply this algorithm effectively when we know the range of data. By this algorithm we can find the center of each group and recommend the similar music with the group. We also consider the time when music is released. When recommending, the system selects pieces of music which is close to and released contemporarily with the user's preference. We perform experiments with one hundred pieces of music. The result shows that our proposed algorithm is effective.

• The Korean Journal of Quaternary Research
• /
• v.25 no.2
• /
• pp.25-37
• /
• 2011

The purpose of this study is to assume the particular area of hills where it is highly possible for historical site to be buried in the viewpoint of geomorphology and based on this to suggest excavation-recommended area. Namely, this writer is to understand the dwelling site type of ancient people who had resided there at that time for the object of 'Ohnju region urban development business site' (referred as investigation area hereinafter) and considering the characteristics of micro-landform of hills which are distributed in investigation area and is to recommend the area where it is highly possible for historical site to be buried. The result of analysis is like the following. (1) Dwelling site types of ancient people who might have resided in the whole area of investigation region are discovered to be largely 'low hills+wetland' of Type-I and 'alluvial fan(or river terrace+wetland' of Type-II. (2) In investigation area if the area which has high possibility of distribution of historical site namely, excavation-recommended area is looked as based on micro-landform unit of hills, they are Crest slope and Crest flat. Individual area ratios which Crest slope and Crest flat occupies in investigation area are 12.9% and 10.2% respectively and the rankings are 3 and 6 each. And excavation-recommended areas in valley plain(or bottomland) of investigation area are in the vicinity of 'distal end' or 'buried distal end'of small scale alluvial fan.