• Korean Journal of Agricultural Science
• /
• v.42 no.4
• /
• pp.319-324
• /
• 2015

An estimation of the requirement of minerals based on growth stage and cropping pattern is very important for greenhouse zucchini. This study was performed at farmer's field which was applied with a fertigation system and a semi-forcing cultivation from Feb. to July in 2014, and nitrogen levels were set up with x0.5, x0.75, x1.0 and x1.5 of the NO3-N-based soil-testing recommendation for zucchini cultivation. Top dressing of nitrogen (basal : top = 4 : 6) and potassium (basal : top = 3 : 7) was applied with an interval of every two weeks from two and six weeks after transplanting, respectively, and phosphorus was totally supplied with basal dressing. The nitrogen uptake was the order of x1.0, x0.75, x1.5 and x0.5, phosphorus, x1.0, x0.75, x0.5 and x1.5, and potassium, x0.75, x1.0, x1.5 and x0.5. From these results, it was suggested that highest mineral uptake could be reached between x0.75 and x1.0 of the NO3-N-based soil-testing recommendation. In conclusion, nutrient management based on the growth stage was proven to be better method for favorable growth and yield of zucchini.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2005.11a
• /
• pp.415-424
• /
• 2005

The rapid growth of blog has caused information overload where bloggers in the virtual community space are no longer able to effectively choose the blogs they are exposed to. Recommender systems have been widely advocated as a way of coping with the problem of information overload in e-business environment. Collaborative Filtering (CF) is the most successful recommendation method to date and used in many of the recommender systems. Therefore, we propose a CF-based recommender system for bloggers in the virtual community space. Our proposed methodology consists of three main phases: In the first phase, we apply the "Interest Value" to a recommender system. The Interest Value is a quantity value about user preference in virtual community, and can measure the opinion of users accurately. Next phase, we generate the neighborhood group based on the Interest Value. In the final phase, we use the Community Likeness Score (CLS) to generate the top-n recommendation list. The methodology is explained step by step with an illustrative example and is verified with real data of a blog service provider.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.406-409
• /
• 2023

With the explosion of information, recommendation algorithms are becoming increasingly important in providing people with appropriate content, enhancing their online experience. In this paper, we propose a recommender system using advanced deep reinforcement learning(DRL) techniques. This method is more adaptive and integrative than traditional methods. We selected the MovieLens dataset and employed the precision metric to assess the effectiveness of our algorithm. The result of our implementation outperforms other baseline techniques, delivering better results for Top-N item recommendations.

• Journal of information and communication convergence engineering
• /
• v.21 no.2
• /
• pp.117-129
• /
• 2023

High-utility itemset mining (HIUM) has emerged as a key data-mining paradigm for object-of-interest identification and recommendation systems that serve as frequent itemset identification tools, product or service recommendation systems, etc. Recently, it has gained widespread attention owing to its increasing role in business intelligence, top-N recommendation, and other enterprise solutions. Despite the increasing significance and the inability to provide swift and more accurate predictions, most at-hand solutions, including frequent itemset mining, HUIM, and high average- and fast high-utility itemset mining, are limited to coping with real-time enterprise demands. Moreover, complex computations and high memory exhaustion limit their scalability as enterprise solutions. To address these limitations, this study proposes a model to extract high-utility frequent closed itemsets based on an improved cumulative summary list structure (CSLFC-HUIM) to reduce an optimal set of candidate items in the search space. Moreover, it employs the lift score as the minimum threshold, called the cumulative utility threshold, to prune the search space optimal set of itemsets in a nested-list structure that improves computational time, costs, and memory exhaustion. Simulations over different datasets revealed that the proposed CSLFC-HUIM model outperforms other existing methods, such as closed- and frequent closed-HUIM variants, in terms of execution time and memory consumption, making it suitable for different mined items and allied intelligence of business goals.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.23 no.1
• /
• pp.83-86
• /
• 2014

Many have been performed to decrease the thickness of polyethylene terephthalate (PET) bottles to reduce the manufacturing cost. However, it is difficult to guarantee the mechanical strength under top-loading after decreasing the thickness. This paper investigates the large deformation characteristics of a PET bottle under a compressive load using experimental and finite element analysis (FEA) data. A round 1.65-L bottle is analyzed under a compressive velocity of 5 mm/min with a maximum load of 9,800 N in experiments. The arc length method is used in a nonlinear FEA to understand the buckling phenomenon of the PET bottle. From the analyzed results, a recommendation is made to restrict the top loading to less than 1,208 N, because the first buckling phenomenon occurred at a load of 1,208 N.

• Korean Journal of Soil Science and Fertilizer
• /
• v.49 no.5
• /
• pp.598-607
• /
• 2016

This study was conducted to evaluate the amount of nitrogen (N) top dressing based on the normalized difference vegetation indices (NDVI) by ground based sensors for leaf perilla under the polyethylene house. Experimental design was the randomized complete block design for five N fertilization levels and conventional fertilization with 3 and 4 replications in Gumsan-gun and Milyang-si field, respectively. Dry weight (DW), concentration of N, and amount of N uptake by leaf perilla as well as NDVIs from sensors were measured monthly. Difference of growth characteristics among treatments in Gumsan field was wider than Milyang. SPAD-502 chlorophyll meter reading explained 43.4% of the variability in N content of leaves in Gumsan field at $150^{th}$ day after seedling (DAS) and 45.9% in Milyang at $239^{th}$ DAS. Indexes of red sensor (RNDVI) and amber sensor (ANDVI) at $172^{th}$ day after seedling (DAS) in Gumsan explained 50% and 57% of the variability in N content of leaves. RNDVI and ANDVI at $31^{th}$ DAS in Milyang explained 60% and 65% of the variability in DW of leaves. Based on the relationship between ANDVI and N application rate, ANDVI at $172^{th}$ DAS in Gumsan explained 57% of the variability in N application rate but non significant relationship in Milyang field. Average sufficiency index (SI) calculated from ratio of each measurement index per maximum index of ANDVI at $172^{th}$ DAS in Gumsan explained 73% of the variability in N application rate. Although the relationship between NDVIs and growth characteristics was various upon growing season, SI by NDVIs of ground based remote sensors at top dressing season was thought to be useful index for recommendation of N top dressing rate of leaf perilla.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.5
• /
• pp.495-507
• /
• 2019

Data sparsity is one of the main challenges for the recommender system. The recommender system contains massive data in which only a small part is the observed data and the others are missing data. Most studies assume that missing data is randomly missing from the dataset. Therefore, they only use observed data to train recommendation model, then recommend items to users. In actual case, however, missing data do not lost randomly. In our research, treat these missing data as negative examples of users' interest. Three sample methods are seamlessly integrated into SVD++ algorithm and then propose SVD++_W, SVD++_R and SVD++_KNN algorithm. Experimental results show that proposed sample methods effectively improve the precision in Top-N recommendation over the baseline algorithms. Among the three improved algorithms, SVD++_KNN has the best performance, which shows that the KNN sample method is a more effective way to extract the negative examples of the users' interest.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.85-109
• /
• 2018

Recommender system recommends the items expected to be purchased by a customer in the future according to his or her previous purchase behaviors. It has been served as a tool for realizing one-to-one personalization for an e-commerce service company. Traditional recommender systems, especially the recommender systems based on collaborative filtering (CF), which is the most popular recommendation algorithm in both academy and industry, are designed to generate the items list for recommendation by using 'overall rating' - a single criterion. However, it has critical limitations in understanding the customers' preferences in detail. Recently, to mitigate these limitations, some leading e-commerce companies have begun to get feedback from their customers in a form of 'multicritera ratings'. Multicriteria ratings enable the companies to understand their customers' preferences from the multidimensional viewpoints. Moreover, it is easy to handle and analyze the multidimensional ratings because they are quantitative. But, the recommendation using multicritera ratings also has limitation that it may omit detail information on a user's preference because it only considers three-to-five predetermined criteria in most cases. Under this background, this study proposes a novel hybrid recommendation system, which selectively uses the results from 'traditional CF' and 'CF using multicriteria ratings'. Our proposed system is based on the premise that some people have holistic preference scheme, whereas others have composite preference scheme. Thus, our system is designed to use traditional CF using overall rating for the users with holistic preference, and to use CF using multicriteria ratings for the users with composite preference. To validate the usefulness of the proposed system, we applied it to a real-world dataset regarding the recommendation for POI (point-of-interests). Providing personalized POI recommendation is getting more attentions as the popularity of the location-based services such as Yelp and Foursquare increases. The dataset was collected from university students via a Web-based online survey system. Using the survey system, we collected the overall ratings as well as the ratings for each criterion for 48 POIs that are located near K university in Seoul, South Korea. The criteria include 'food or taste', 'price' and 'service or mood'. As a result, we obtain 2,878 valid ratings from 112 users. Among 48 items, 38 items (80%) are used as training dataset, and the remaining 10 items (20%) are used as validation dataset. To examine the effectiveness of the proposed system (i.e. hybrid selective model), we compared its performance to the performances of two comparison models - the traditional CF and the CF with multicriteria ratings. The performances of recommender systems were evaluated by using two metrics - average MAE(mean absolute error) and precision-in-top-N. Precision-in-top-N represents the percentage of truly high overall ratings among those that the model predicted would be the N most relevant items for each user. The experimental system was developed using Microsoft Visual Basic for Applications (VBA). The experimental results showed that our proposed system (avg. MAE = 0.584) outperformed traditional CF (avg. MAE = 0.591) as well as multicriteria CF (avg. AVE = 0.608). We also found that multicriteria CF showed worse performance compared to traditional CF in our data set, which is contradictory to the results in the most previous studies. This result supports the premise of our study that people have two different types of preference schemes - holistic and composite. Besides MAE, the proposed system outperformed all the comparison models in precision-in-top-3, precision-in-top-5, and precision-in-top-7. The results from the paired samples t-test presented that our proposed system outperformed traditional CF with 10% statistical significance level, and multicriteria CF with 1% statistical significance level from the perspective of average MAE. The proposed system sheds light on how to understand and utilize user's preference schemes in recommender systems domain.

• Korean Journal of Soil Science and Fertilizer
• /
• v.44 no.6
• /
• pp.1112-1117
• /
• 2011

This study was conducted to recommend nitrogen (N) top dressing based on soil nitrate content for leaf perilla under forcing culture in Gumsan-gun and Milyang-si. Experimental design was the randomized complete block design for five N fertilization levels and conventional fertilization. Dry weight, nitrogen uptake, and the node number of leaf perilla were measured and soil nitrate contents were analyzed monthly. The amount of nitrogen uptake for growth of a node with two leaves was $2.2kg\;10a^{-1}$ for Gumsan site and $3.5kg\;10a^{-1}$ for Milyang site. Lower level of soil nitrate N concentration for standard N fertilization was determined as $10mg\;kg^{-1}$ for both sites. Soil depth, bulk density, utilization rate of soil nitrate N, and the amount of N uptake for growth of a node with two leaves were considered for calculation of upper level of soil nitrate N concentration. The upper levels of soil nitrate N concentration for no N fertilization were determined as $30mg\;kg^{-1}$ for Gumsan site and as $40mg\;kg^{-1}$ for Milyang site. Consequently the recommendation equations for the N top dressing were Y=-0.157X+4.71 for Gumsan site and Y=-0.1667X+6.6667 for Milyang site.

• Journal of the Korea Convergence Society
• /
• v.11 no.3
• /
• pp.181-186
• /
• 2020

The purpose of this study is to empirically examine the factors affecting the binge-watching behaviors of OTT service users by using a multi-layer perceptron (MLP) artificial neural network. All samples (n=1,000) were collected from 'A survey on user awareness in OTT service' published by a Media Research Center of the Korea Press Foundation in 2018. Our research model includes one dependent variable which is binge-watching behaviors on OTT service and five independent variables such as gender, age, frequency of service usage, users' satisfaction with content recommendation algorithm, and content types mainly consumed. Our findings demonstrate that age, frequency of service usage, users' satisfaction with content recommendation algorithms, and certain types of contents (e.g., Korean dramas, Korean films, and foreign dramas) were found to be highly related to binge-watching behavior on OTT services.