• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.5
• /
• pp.2122-2140
• /
• 2020

Proper and precise embedding of commercial ads within Webpages requires Ad-hoc analysis and understanding of their content. By the successful implementation of this step, both publishers and advertisers gain mutual benefits through increasing their revenues on the one hand, and improving user experience on the other. In this research work, we propose a novel multi-level context-based ads serving approach through which ads will be served at generic publisher websites based on their contextual relevance. In the proposed approach, knowledge encoded in domain-specific and generic semantic repositories is exploited in order to analyze and segment Webpages into sets of contextually-relevant segments. Semantically-enhanced indexes are also constructed to index ads based on their textual descriptions provided by advertisers. A modified cosine similarity matching algorithm is employed to embed each ad from the Ads repository into one or more contextually-relevant segments. In order to validate our proposal, we have implemented a prototype of an ad serving system with two datasets that consist of (11429 ads and 93 documents) and (11000 documents and 15 ads), respectively. To demonstrate the effectiveness of the proposed techniques, we experimentally tested the proposed method and compared the produced results against five baseline metrics that can be used in the context of ad serving systems. In addition, we compared the results produced by our system with other state-of-the-art models. Findings demonstrate that the accuracy of conventional ad matching techniques has improved by exploiting the proposed semantically-enhanced context-based ad serving model.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.8
• /
• pp.83-93
• /
• 2014

Research into recommendation systems for wellness content has focused on representative research on the convergence of wellness and information technology, as interest in wellness has recently increased. But existing research is not suitable because it uses only one or two of the five wellness areas: physical, emotional, social, intellectual, and spiritual. And It cause decline of reliability and satisfaction for recommendation. Thus, a wellness areal feature analysis and integration management technique is needed. In this paper, suggest meta-data configuration and feature analysis technique of content. Also Cosine similarity of wellness areal features of the content was analyzed by applying a wellness areal score calculated in this way and by suggested wellness areal detailed properties and a measurement system to verify the efficiency of this research. This allows the wellness features of contents analyzed, and even will be able to personalized recommendations service for wellness.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.11
• /
• pp.201-210
• /
• 2020

Navy submarines are developed into complex weapons systems with various equipment, which directly leads to difficulties in submarine maintenance. In addition, the method of establishing a maintenance plan for submarines is limited in efficient maintenance because it relies on statistical access to the number of people, number of target ships, and consumption time. For efficient maintenance, it is necessary to derive and maintain major maintenance factors based on an understanding of the target. In this paper, the maintenance loads rate is defined as a key maintenance factor. the submarine maintenance data is analyzed using the SNA scheme to identify phenomena by focusing on the relationship between the analysis targets. Through this, maintenance loads characteristics that have not been previously revealed in quantitative analysis are derived to identify areas that the maintenance manager should focus on.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.27 no.4
• /
• pp.125-145
• /
• 2016

This study aimed at finding theological trends of Calvin Theological Journal by analyzing Library of Congress Subject Headings (LCSH). The study performed the time-series analysis and the analysis of distinctive terms by examining the main authors and the subject headings of the articles published in Calvin Theological Journal during 45 years. We also proposed a new method of dividing the analysis period with the change of authors and subject headings. In the analysis results, the 18 main authors had the three clusters and shared Calvin and the Reformed Theology, the Bible. The reformed characteristics were shown in the first and second period, but the reformed theology was at the margins. The frequency of Calvin became small in the third period, the frequency of the reformed theology became bigger than before, but it was at the perimeters. Literary criticism was clustered independently. There were lots of the terms of the reformed theology in the analysis of the distinctive terms in all three periods and especially in the 2-1 period science and religion were included as the distinctive terms. Therefore, the theological tendency of the Calvin Theological Journal seemed the reformed theology and Old Testament.

• Journal of the Institute of Convergence Signal Processing
• /
• v.13 no.3
• /
• pp.142-149
• /
• 2012

Various image transformations can be used to compress images, to reduce noises in images and to extract useful features. Watermarking techniques using DCT and DWT have been a lot of research interest in the spread of multimedia contents. In this paper, Gabor cosine and sine transform considered as human visual filter is applied to embedding and extraction of watermarks for digital images. The proposed transform is used for watermarking with fifteen attacks. Randomly normal distributed noises are used as an embedded watermark. To measure the similarity between the embedded watermark and extracted one, a correlation value is computed and furthermore is compared with that of existing DCT method. Correlation values of extracted watermark are computed with randomly normal distributed noise sequences, and the sequence with the largest correlation value is declared as the embedded watermark. Frequency components are divided into various bands. Experimental results for low frequency and mid-frequency bands have shown that the proposed GCST provides a good watermarking algorithm and its performance is better than DCT.

• Journal of Sensor Science and Technology
• /
• v.22 no.2
• /
• pp.162-173
• /
• 2013

The purpose of this paper is to classify VOC gases by emulating the characteristics found in biological olfaction. For this purpose, we propose new signal processing method based a polymeric chemical sensor array consisting of 4096 sensors which is created by NEUROCHEM project. To remove unstable sensors generated in the manufacturing process of very large scaled chemical sensor array, we used discrete wavelet transformation and cosine similarity. And, to remove the supernumerary redundancy, we proposed the method of selecting candidates of representative sensor representing sensors with similar features by Fuzzy c-means algorithm. In addition, we proposed an improved algorithm for selecting representative sensors among candidates of representative sensors to better enhance classification ability. However, Classification for very large scaled sensor array has a great deal of time in process of learning because many sensors are used for learning though a redundancy is removed. Throughout experimental trials for classification, we confirmed the proposed method have an outstanding classification ability, at transient state as well as steady state.

• Journal of Digital Convergence
• /
• v.14 no.11
• /
• pp.101-106
• /
• 2016

A number of non-structured data associated with lectures in the field of university education have been generated and it is an important consideration of the students's written comments lecture evaluation. The purpose of this study is to find student interaction factors associated with the student evaluation of teaching at universities, and to provide some insights into improving the student evaluation program based on the results. So, this study consists of three steps that create interaction score, collect student's written comments satisfaction, and analyze an individual professor score. There are a number of limitations to this study. The limitation is that the study was conducted on a narrow sample of the overall student population.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.1
• /
• pp.22-27
• /
• 2014

Blocking and ringing artifacts continue to be the most serious defects that occur in images and video streams compressed to low bit rates using block-based discrete cosine transform(DCT) compression standards. These artifacts contain the high frequency components near the block and the edge boundaries. Usually the lowpass filter can remove them. However, simple lowpass filter results into blur by removing important information such as edges at the same time. To overcome these problems, we propose a novel postfiltering algorithm that calculate the weight value based on the intensity similarity in the neighboring pixels and multiply this weight to the Gaussian lowpass filter coefficient. Experimental results show that the proposed technique provides satisfactory performance in both objective and subjective image quality.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.40 no.4
• /
• pp.154-163
• /
• 2017

Collaborative filtering, one of the most widely used techniques to build recommender systems, is based on the idea that users with similar preferences can help one another find useful items. Credit card user behavior analytics show that most customers hold three or less credit cards without duplicates. This behavior is one of the most influential factors to data sparsity. The 'cold-start' problem caused by data sparsity prevents recommender system from providing recommendation properly in the personalized credit card recommendation scenario. We propose a personalized credit card recommender system to address the cold-start problem, using multiple user profiles. The proposed system consists of a training process and an application process using five user profiles. In the training process, the five user profiles are transformed to five user networks based on the cosine similarity, and an integrated user network is derived by weighted sum of each user network. The application process selects k-nearest neighbors (users) from the integrated user network derived in the training process, and recommends three of the most frequently used credit card by the k-nearest neighbors. In order to demonstrate the performance of the proposed system, we conducted experiments with real credit card user data and calculated the F1 Values. The F1 value of the proposed system was compared with that of the existing recommendation techniques. The results show that the proposed system provides better recommendation than the existing techniques. This paper not only contributes to solving the cold start problem that may occur in the personalized credit card recommendation scenario, but also is expected for financial companies to improve customer satisfactions and increase corporate profits by providing recommendation properly.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.9B
• /
• pp.1259-1265
• /
• 2010

Recently, on-line social network has been increasing according to development of internet. The most representative service is blog. A Blog is a type of personal web site, usually maintained by an individual with regular entries of commentary. These blogs are related to each other, and it is called Blog Network in this paper. In a blog network, posts in a blog can be diffused to other blogs. Analyzing information diffusion in a blog world is a very useful research issue, which can be used for predicting information diffusion, abnormally detection, marketing, and revitalizing the blog world. Existing studies on network analysis have no consideration for the passage of time and these approaches can only measure network activity for a node by the number of direct connections that a given node has. As one solution, this paper suggests the new method of measuring the blog network activity using logistic curve model and Cosine-similarity in key words by the Map/Reduce programming model.