• Journal of the Korea Society of Computer and Information
• /
• v.26 no.6
• /
• pp.19-28
• /
• 2021

Nowadays, interest in health care is increasing due to Coronavirus (COVID-19), and a lot of people are doing home training as there are more difficulties in using fitness centers and public facilities that are used together. In this paper, we propose a personalized exercise recommendation algorithm using personalized propensity information to provide more accurate and meaningful exercise recommendation to home training users. Thus, we classify the data according to the criteria for obesity with a k-nearest neighbor algorithm using personal information that can represent individuals, such as eating habits information and physical conditions. Furthermore, we differentiate the exercise dataset by the level of exercise activities. Based on the neighborhood information of each dataset, we provide personalized exercise recommendations to users through a dimensionality reduction algorithm (SVD) among model-based collaborative filtering methods. Therefore, we can solve the problem of data sparsity and scalability of memory-based collaborative filtering recommendation techniques and we verify the accuracy and performance of the proposed algorithms.

• The Journal of the Korea Contents Association
• /
• v.7 no.12
• /
• pp.292-302
• /
• 2007

Thousands of studies on predicting information and products that are suitable for customers' preference have been actively proceeding. In massive information, unnecessary information should be removed to satisfy customers' needs. This Information filtering has been proceeding with several methods such as content-based and collaborative filtering etc. These conventional filtering methods have scarcity and scalability problems. Thus, this paper proposes a recommendation system using BPN to solve them. Data obtained by survey questionnaire are used as training data of neural network. The recommendation system using neural network is expected to recommend suitable products because it creates optimal network. Finally, the prototype for recommendation system based on neural network is proposed to collect data and recommend appropriate methods through survey questionnaire. As a result, this research improved the problems of conventional information filtering.

• Journal of Information Technology Applications and Management
• /
• v.23 no.1
• /
• pp.97-117
• /
• 2016

Drawing on the theoretical framework of customer value-satisfaction-loyalty, this study examines how scarcity message influences customers' value, satisfaction, and loyalty in the context of group-buying social commerce. Previous studies have argued that scarcity message limiting the avilability of products and service is a source of enhancing customer value. In this regard, this study posits scarcity message as a predictor of customer value. Furthermore, this study classifies customer value into two forms (i.e., utilitarian value and hedonic value) and verfies how scarcity message is associated with them. To test the proposed research model and hypotheses, this study performed structural equation modeling (SEM) analyses, using a total of 292 data collected on users who have experience in purchasing products and service through group-buying social commerce sites such as Coupang, Timon, and WeMakePrice. The key results are as follows : First, scarcity message increases utilitarian and hedonic values and further customer satisfaction. Second, utilitarian value increases customer satisfaction and repurchase intention while hedonic value has nothing to do with them. The findings imply that customers seek to maximize utilitarian value through group-buying social commerce. Finally, this study indicates that repuchase intention depends greatly on customer satisfaction.

• The Journal of Korean Association of Computer Education
• /
• v.19 no.1
• /
• pp.111-118
• /
• 2016

Measuring similarity in collaborative filtering-based recommender systems greatly affects system performance. This is because items are recommended from other similar users. In order to overcome the biggest problem of traditional similarity measures, i.e., data sparsity problem, this study suggests a new similarity measure that is the optimal combination of previous similarity and the value reflecting the number of co-rated items. We conducted experiments with various conditions to evaluate performance of the proposed measure. As a result, the proposed measure yielded much better performance than previous ones in terms of prediction qualities, specifically the maximum of about 7% improvement over the traditional Pearson correlation and about 4% over the cosine similarity.

• Journal of Creative Information Culture
• /
• v.4 no.3
• /
• pp.221-230
• /
• 2018

Collaborative filtering technique is a major method of recommender systems and has been successfully implemented and serviced in real commercial online systems. However, this technique has several inherent drawbacks, such as data sparsity, cold-start, and scalability problem. Clustering-based collaborative filtering has been studied in order to handle scalability problem. This study suggests a collaborative filtering system which utilizes genetic algorithms to improve shortcomings of K-means algorithm, one of the widely used clustering techniques. Moreover, different from the previous studies that have targeted for optimized clustering results, the proposed method targets the optimization of performance of the collaborative filtering system using the clustering results, which practically can enhance the system performance.

• Economic and Environmental Geology
• /
• v.55 no.4
• /
• pp.353-366
• /
• 2022

Spatial estimation of geoscience data (geo-data) is challenging due to spatial heterogeneity, data scarcity, and high dimensionality. A novel spatial estimation method is needed to consider the characteristics of geo-data. In this study, we proposed the application of Gaussian Mixture Model (GMM) among machine learning algorithms with multivariate data for robust spatial predictions. The performance of the proposed approach was tested through soil chemical concentration data from a former smelting area. The concentrations of As and Pb determined by ex-situ ICP-AES were the primary variables to be interpolated, while the other metal concentrations by ICP-AES and all data determined by in-situ portable X-ray fluorescence (PXRF) were used as auxiliary variables in GMM and ordinary cokriging (OCK). Among the multidimensional auxiliary variables, important variables were selected using a variable selection method based on the random forest. The results of GMM with important multivariate auxiliary data decreased the root mean-squared error (RMSE) down to 0.11 for As and 0.33 for Pb and increased the correlations (r) up to 0.31 for As and 0.46 for Pb compared to those from ordinary kriging and OCK using univariate or bivariate data. The use of GMM improved the performance of spatial interpretation of anthropogenic metals in soil. The multivariate spatial approach can be applied to understand complex and heterogeneous geological and geochemical features.

• Ecology and Resilient Infrastructure
• /
• v.7 no.3
• /
• pp.171-180
• /
• 2020

With the increase in industrialization and urbanization, scarcity of space for leisure life has become an important issue. Opportunities such as natural scenery and ecological experiences provided by waterfront spaces around streams are fundamental factors in the development of the community and creation of a hydrophilic park. In the past, on-site surveys have been conducted using human resources to quantify the number of river visitors, but the accuracy of the results was not sufficient owing to limitations in expenses, manpower, space, and time. In this study, to overcome this problem, we estimated the number of visitors using the location information related to hydrophilic parks. The study areas were Samrak Ecological Park and Daejeo Ecological Park located downstream of the Nakdong River. We compared and analyzed the pattern of the visitors by using the large communication data and the visiting pattern based on GPS location information. The GPS location information is based on Google Popular Times and Kakao visitor data. When the GPS location data were used, the pattern for weekday and weekend visitors was clearer than when the large communication data were used. Therefore, it is expected to be similar to the result of GPS location information if the number of visitors is extracted under the condition of precision of pCELL size and residence time of 30 minutes or more when using future communication big data. In addition, if revisions such as the Personal Information Protection Act are made to extract more accurate data, by estimating the number of visitors based on GPS data, more accurate indicators of the number of visitors can be derived.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.4
• /
• pp.433-438
• /
• 2003

Recently, some studies of a web-based information recommendation technique which provides users with the most necessary information through websites like a web-based shopping mall have been conducted vigorously. In most cases of web information recommendation techniques which rely on a user profile and a specific feedback from users, they require accurate and diverse profile information of users. However, in reality, it is quite difficult to acquire this related information. This paper is aimed to suggest an information prediction technique for a web information service without depending on the users'specific feedback and profile. To achieve this goal, this study is to design and implement a Dynamic Web Information Prediction System which can recommend the most useful and necessary information to users from a large volume of web data by designing and embodying Ensemble Support Vector Machine and hybrid SOM algorithm and eliminating the scarcity problem of web log data.

• Journal of Digital Contents Society
• /
• v.18 no.4
• /
• pp.707-712
• /
• 2017

As the amount of data increases exponentially, the recommender system is attracting interest in various industries such as movies, books, and music, and is being studied. The recommendation system aims to propose an appropriate item to the user based on the user's past preference and click stream. Typical examples include Netflix's movie recommendation system and Amazon's book recommendation system. Previous studies can be categorized into three types: collaborative filtering, content-based recommendation, and hybrid recommendation. However, existing recommendation systems have disadvantages such as sparsity, cold start, and scalability problems. To improve these shortcomings and to develop a more accurate recommendation system, we have designed a recommendation system as a factorization machine using actual online product purchase data.

• The Journal of Bigdata
• /
• v.5 no.1
• /
• pp.41-54
• /
• 2020

With the recent expansion of Internet channels and the development of financial technology and information and communication technology, direct overseas purchases have expanded. Although direct overseas purchases dominate consumers in terms of price and scarcity by providing relatively low-priced products and products that are difficult to obtain in Korea, there is a higher chance of consumer dissatisfaction in terms of delivery, product, A/S and refund than domestic purchases. Therefore, this study analyzed consumer dissatisfaction caused by active overseas direct purchase and studied ways to improve problems with overseas direct purchase. As a research method, Several statistical data were collected from the Korea Consumer Agency(KCA), the Korea Customs Service(KCS) and the Korea International Trade Association(KITA) and analyzed using the Exploratory Data Analysis Technique (EDA). The analysis confirmed that consumers were not well aware of information about direct overseas purchases and that the type or degree of consumer complaints varied depending on the type of purchase. Therefore, this study suggests a direction for the revitalization of overseas direct purchases by using EDA to identify the overall status of overseas direct purchases and consumer dissatisfaction and to improve them.