• Information Systems Review
• /
• v.19 no.2
• /
• pp.71-94
• /
• 2017

Recommender systems reduce information overload and enhance choice quality. This technology is used in many services and industry. Previous studies did not consider recommendation quantity and the repetitive recommendations of an item. This study is the first to examine recommender systems by considering recommendation quantity and repetitive recommendations. Only a limited number of items are displayed in offline stores because of their physical limitations. Determining the type and number of items that will be displayed is an important consideration. In this study, I suggest the use of a user-based recommender system that can recommend the most appropriate items for each store. This model is evaluated by MAE, Precision, Recall, and F1 measure, and shows higher performance than the baseline model. I also suggest a new performance evaluation measure that includes Quantity Precision, Quantity Recall, and Quantity F1 measure. This measure considers the penalty for short or excess recommendation quantity. Novelty is defined as the proportion of items in a recommendation list that consumers may not experience. I evaluate the new revenue creation effect of the suggested model using this novelty measure. Previous research focused on recommendations for customer online, but I expand the recommender system to cover stores offline.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.610-612
• /
• 2005

협동적 여과를 이용한 추천 시스템은 데이터의 희소성 문제(sparseness problem)와 초기 추천 문제 (cold-start problem)에 대해 취약점을 가지고 있다. 협동적 여과를 이용한 추천 시스템에서 사용하는 선호도 데이터에 아이템들의 전체 수량에 비해 매우 적은 양의 아이템 선호도만 존재한다면 사용자들의 유사도 측정에 문제를 발생시켜 극단적인 경우엔 협동적 추천이 불가능할 경우가 발생한다. 이와 같은 문제는 선호도 데이터에 나타난 아이템들의 총수에 비해 사용자가 선호(구매)한 아이템이 극히 적은 수량으로 존재하기 때문이며 새로운 사용자의 경우에는 아이템 선호도 정보가 전혀 없기 때문에 유사 사용자를 추출하지 못하여 아이템을 전혀 추천할 수 없는 문제가 발생한다. 본 논문에서는 희소성이 높은 선호도 데이터를 희소하지 않은 상태로 변형하는 희소 데이터 변형 기법을 제안한다. 희소 데이터 변형 기법은 희소데이터에 나타난 사용자와 아이템의 추가 속성 정보의 확률분포를 이용하여 알려지지 않은 선호도 값을 예측함으로써 희소성이 높은 선호도 데이터를 변경하고, 변경된 선호도 데이터를 협동적 추천에 적용하여 추천 성능을 향상시킨다. 이와 같은 선호도 데이터 변경 기법을 데이터 블러링(data blurring)이라 한다. 몇가지 실험 결과를 통해 제안된 기법의 효과를 확인하였다.

• Agrochemical news magazine
• /
• v.19 no.4 s.145
• /
• pp.54-55
• /
• 1998

• Korean Journal of Soil Science and Fertilizer
• /
• v.15 no.3
• /
• pp.194-198
• /
• 1982

The data from the fertilizer experiments from 1974 to 1981 were compiled and interpretation were made as to the effect of soil fertility on the quality and yield of cured tobacco supplied with conventional rate (10-15-20, 125Kg/10a). With high soil fertility, the yield of tobacco with conventional rate increased in quadratic curve, but the quality decreased. The results indicate that soil which can produce 81Kg/10a of flue-cured tobacco without fertilizer application would be optimum to the 125Kg/10a fertilizer application. On the other hand, Flue-cured tobacco yields of non-fertilizer plot are supposed to be fertility of determining the application rate which can be recommended.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.05a
• /
• pp.272-274
• /
• 2013

최근 TV 시청자들의 콘텐츠 소비량이 증가함에 따라 방송사에서 제공하는 TV 프로그램들의 수량이 방대해지고 장르 또한 다양해지고 있기 때문에 시청자가 TV 프로그램을 선택하는 것이 점점 더 어려워지고 있다. 이러한 문제를 해결하기 위해 TV 프로그램 추천이라는 연구가 활발하게 이루어지고 있다. 기존의 연구에서는 시청자를 기반으로 하는 협업 필터링 추천 방법과 아이템을 기반으로 하는 협업 필터링 추천 방법이 제안되었지만 시청자의 시청 의도를 고려하는 연구는 사례는 적다. 이에 본 논문에서는 LDA 모델링을 이용하여 사용자의 시청 의도를 고려한 TV 프로그램 추천 기법을 제안한다. 실험을 통해 시청자의 시청 의도가 반영된 TV 프로그램 추천이 가능하다는 것을 검증했다.

• Korean Journal of Soil Science and Fertilizer
• /
• v.38 no.4
• /
• pp.194-201
• /
• 2005

Silicate (Si) fertilizers are well-known for soil amendment and to improve rice productivity as well as nitrogen efficiency. In this study, we investigated the possible reduction level of nitrogen fertilization for rice cultivation by amending Si fertilizer application. Field experiments were carried out to evaluate the productivity of rice (Oryza sativa L.) on a silt loam soil, where three levels of nitrogen (0, 110 and $165kg\;ha^{-1}$) were selected and Si fertilizer as a slag type was applied at 0, 1 and 2 times of the recommendation level (available $SiO_2\;130mg\;kg^{-1}$). Application of Si fertilizer increased significantly the rice yield and nitrogen efficiency. With increasing N uptake of rice, 1 and 2 times of recommended levels of Si fertilization could decrease nitrogen application level to about 76 and $102kg\;N\;ha^{-1}$ to produce the target yield, the maximum yield in the non-Si amended treatment. Silicate fertilizer improved soil pH and significantly increased available phosphate and Si contents. Conclusively, the Si fertilizer could be a good alternative source for soil amendment, restoring the soil nutrient balance and to reduce the nitrogen application level in rice cultivation.

• Journal of Digital Contents Society
• /
• v.13 no.4
• /
• pp.559-565
• /
• 2012

The remarkable development of IT is contributed to popularization of smart phones, which in turn creates a new domain called app store. Smartphone apps have grown fast because they can be easily purchased through an app store. As the volume of apps traded in app stores is so huge that it is extremely hard for users to find the exact app they want. In general, an app store recommends an app to users based on the search words they entered. In terms of recommendation of app, this kind of content-based method is not effective. To increase accuracy in recommending app, this paper proposes a characteristic similarity-based app recommendation method. This method creates attributes on the app based on the related information such as genre, functionality and number of downloads and then compares them with the propensity to use the app. According to diverse simulations, the method proposed in this paper improved the performance of app recommendation by 33% in average, compared to the conventional method.

• Korean Journal of Environmental Agriculture
• /
• v.27 no.2
• /
• pp.171-177
• /
• 2008

The application in agricultural fields of pig slurry composting biofiltraton amending smell and nutrient unevenness, it is important for the appropriate nitrogen nutrient management to promote the availability of the crops and to minimize the risk of adversely environmental effects. The objective of this study was to determine the application rates of the preplant pig slurry composting biofiltration for red pepper(Capsicum annuum L.) by considering the yield response and the fruit quality such as sugar, capsaicinoid content. Red peppers were grown on plastic film ground under five different pig slurry(PS) application rates and mineral fertilizer(MF 100%) as a control. The effects of a single application of five different doses of PS: PS 0%(no kg N $ha^{-1}$), PS 50%(51.5 kg N $ha^{-1}$), PS 75%(77.3 kg N $ha^{-1}$), PS 100%(103 kg N $ha^{-1}$) and PS 125%(129 kg N $ha^{-1}$) were compared with the recommended mineral treatment(103 kg N $ha^{-1}$) in the pre-planting. The sidedressing N application(87 kg N $ha^{-1}$) was applied to the mineral fertilizer in all treatments. Red peppers were harvested at the mature red stage through five times from 72 days after transplanting(DAT) to 133 DAT. The results indicated that the yield of red pepper was increased with the increase of the N application rates from PS 0% to PS 100%. The highest yield was obtained in PS 100% by 20,843 kg $ha^{-1}$, although there were no significant differences in yield among PS 100, PS 125% and MF 100%. In addition, The contents of soluble sugar and capsaicinoids were not significantly different in all treatments. Accordingly, fertilization recommendations of red pepper to substitute PS for the mineral fertilizer were considered to PS 100%.

• Korean Journal of Soil Science and Fertilizer
• /
• v.34 no.1
• /
• pp.64-70
• /
• 2001

To verify the newly developed decision assisting expert system for nitrogen fertilizer application NES to Illinois cornfields, a couple of N rate studies from Dr. Howard and five Illinois Agricultural Experiment Stations were applied. Four types of recommendations including the current Illinois recommendation, Hoeft recommendation, NES, and maximum economic recommendation were compared with each other for the crop yields, profits, recovery rate, and N losses to cornfields. The N rate of NES recommendation, considering productivity index (PI), soil organic matter content (SOM), and pre-sidedressing nitrate concentration (PSNT) level, was the lowest in comparison to those of other recommendations. However, N recovery rate in NES was generally higher and the resulting N loss was lower than others. But, adherence to the recommendations may also reduce farmers income if environmental expense did not considered. Therefore, NES will be more effective by adding the factors including environmental expense, tillage systems, crop rotation, and other agricultural management parameters.

• Korean Journal of Soil Science and Fertilizer
• /
• v.36 no.5
• /
• pp.280-289
• /
• 2003

The purpose of this study was to establish a model for recommendable application level of nitrogen fertilizer based on soil testing for summer chinese cabbage in highland. A field experiment was carried out with various nitrogen application levels in sand loamy soil with and without poultry manure compost. The application level of N in poultry manure compost plot was found to be $291kg\;ha^{-1}$ for maximum yield of chinese cabbage, and it was 87% of the required N application level, $335kg\;ha^{-1}$, for maximum yield of chinese cabbage in nonmanure plot. In the treatment of poultry manure, approximately $174kg\;ha^{-1}$ of N was required to obtain the same yield of chinese cabbage as the maximum yield obtained in the treatments without poultry manure application. Therefore, with poultry manure application, N application level can be reduced by 40%. Using these results, a new equation for N recommendation for chinese cabbage in highland soil was proposed. With the average organic matter content of $33g\;kg^{-1}$ in highland field, the application levels of N for chinese cabbage were in the range of $215-129kg\;ha^{-1}$, which means that 32.8-59.7% of current application amount of N fertilizer can be reduced.