• Journal of Internet Computing and Services
• /
• v.18 no.5
• /
• pp.133-141
• /
• 2017

Recently, the regulation issues for the zero-rating began to be proliferated. The corresponding regulators in charge of Internet services of all the countries of the world illustrated the various spectrums, rather than the similar policy line. In contrast, the oversee regulators not only recognized that zero-rating might be somethings to do with the net neutrality regulation, and but also actively debated regarding the validity for the regulation. However, any domestic study examining the issue has not endeavored yet. Therefore, the purpose of the study is to identify the validity of net neutrality regulation of zero-rating. Specifically, the study provided the features of zero-rating, the relationship with this new regulation and traditional regulations, and the various arguments and policies in major countries. The results of the study would be utilized as a reference in planning the regulation and countermeasure, from the corresponding policy makers and business operators.

• The Journal of the Korea Contents Association
• /
• v.13 no.7
• /
• pp.379-385
• /
• 2013

On the internet, the rating scores assigned by customers are considered as the preference information of themselves and thus, these can be used efficiently in the customer profile generation process of recommender system. However, since anyone is free to assign a score that has a biased rating, using this without any filtering can exhibit a reliability problem. In this study, we suggest the methodology that measures the reliability of rating scores and then applies them to the customer profile creation process. Unlikely to some related studies which measure the reliability on the user level, we measure the reliability on the individual rating score level. Experimental results show that prediction accuracy of recommender system can be enhanced when ratings with higher reliability are selectively used for the customer profile configuration.

• Journal of Intelligence and Information Systems
• /
• v.17 no.3
• /
• pp.79-98
• /
• 2011

This paper proposes a semantic recommendation technique for a personalized e-commerce portal. Semantic recommendation is achieved by utilizing the attributes of products. The semantic similarity of the products is merged with the rating information of the products to provide an accurate recommendation. The recommendation technique also analyzes various attitudes of the customer to evaluate the implicit rating of products. Attitudes are classifies into three types such as "purchasing product", "adding product to shopping cart", and "viewing the product information." We implicitly track customer attitude to estimate the rating of products for recommending products. Also we implement a session validation process to identify the valid sessions that are highly important for giving an accurate recommendation. Our recommendation technique shows a high degree of accuracy as we use age groupings of customers with similar preferences. The experimental section shows that our proposed recommendation method outperforms well known collaborative filtering methods not only for the existing customer, but also for the new user with no previous purchase record.

• Information Systems Review
• /
• v.1 no.1
• /
• pp.51-61
• /
• 1999

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.1
• /
• pp.17-24
• /
• 2020

In this paper, we present a movie rating prediction architecture based on a convolutional neural network (CNN). Our prediction architecture extends TextCNN, a popular CNN-based architecture for sentence classification, in three aspects. First, character embeddings are utilized to cover many variants of words since reviews are short and not well-written linguistically. Second, the attention mechanism (i.e., squeeze-and-excitation) is adopted to focus on important features. Third, a scoring function is proposed to convert the output of an activation function to a review score in a certain range (1-10). We evaluated our prediction architecture on a movie review dataset and achieved a low MSE (e.g., 3.3841) compared with an existing method. It showed the superiority of our movie rating prediction architecture.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.25 no.2
• /
• pp.49-54
• /
• 2013

In field of apartment housing currently, insulation technology is the most effective way because it is common to improve the thermal performance, therefore, it is contributed to energy saving as several regional insulation standards and legal mandate method. In addition, by applying of building energy efficiency rating certification system, it has inspired voluntary energy conservation commitment for the building owner or facility manager by making a plan to evaluate and verify building energy performance. However, these circumstances are not enough to acquire a grade 2 of higher information. Therefore, in this study, we analyzed the impact of building energy efficiency rating and confirmed reduction ratio compared to the standard housing on the basis of recent our nation building law when we had changed the shape of windows and wall insulation performance and shapes of housing.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.26 no.3
• /
• pp.227-232
• /
• 2020

This paper develops a risk index based on an indicator of risk assessment in terms of coastal activity location and accident type. The risk index is derived from a formula which adds the consequence of failure to a vulnerability value, then subtracts the mitigation value. Specifically, the consequence of failure is the number of casualties in coastal activity locations. An indicator of vulnerability refers to coastal environment elements and social elements. A pointer of mitigation includes managerial and organizational elements that indicate the capabilities of coastal activities. A risk rating of coastal activity location is found from a risk matrix consisting of the accident location and type. The purpose of this study is to prevent accidents at coastal activity locations by allowing the Coastal police guard to monitor effectively and inform visitors of potential risks.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.463-466
• /
• 2003

Fuzzy set expressing category in fuzzy rating, which is a kind of psychological scaling, is dependent on situations. This paper assumes that a mapping exists between fuzzy sets expressing categories in some situation and those expressing same categories in another situation. fuzzy sets expressing categories in some situation are obtained by fuzzy sets expressing categories in another situation and the mapping between them. The usefulness of the present method is confirmed by the experiments comparing fuzzy sets obtained by the presented method with those identified directly by fuzzy rating. The normalized distance is used to compare both fuzzy sets and the experimental results show that the normalized distances between both fuzzy sets are enough small and that the presented method is useful for psychological scaling.

• Journal of Multimedia Information System
• /
• v.3 no.4
• /
• pp.155-160
• /
• 2016

The Pulse Coupled Neural Network (PCNN) is a kind of neural network models that consists of spiking neurons and local connections. The PCNN was originally proposed as a model that can reproduce the synchronous phenomena of the neurons in the cat visual cortex. Recently, the PCNN has been applied to the various image processing applications, e.g., image segmentation, edge detection, pattern recognition, and so on. The method for the image matching using the PCNN had been proposed as one of the valuable applications of the PCNN. In this method, the Genetic Algorithm is applied to the PCNN parameter learning for the image matching. In this study, we propose the method of the similar image rating using the PCNN. In our method, the Genetic Algorithm based method is applied to the parameter learning of the PCNN. We show the performance of our method by simulations. From the simulation results, we evaluate the efficiency and the general versatility of our parameter learning method.

• Journal of Construction Engineering and Project Management
• /
• v.5 no.1
• /
• pp.40-46
• /
• 2015

This study presents the results of our analysis and recommendations for process and productivity improvements. The project studied consists of a 5-story research building, with a structure of steel frames supporting concrete slabs. The observations focused on the analysis of the overall erection and framing process. The methods used for the analysis consisted in intensive visits on site, where construction processes were observed in term of resources, activities, durations, materials' handling procedures, and technology used. Back to the office, authors used the information captured to model the different trades' activities, using work sampling and 5-minute rating technique. The work sampling provides insight into the activity, hence allowing for process improvements. The productivity of various trades is strongly dependent on the organization of the work process and work site conditions. Improving the productivity of the entire project or company is not possible until everyone is committed to improvement.