• Journal of Intelligence and Information Systems
• /
• v.21 no.1
• /
• pp.15-28
• /
• 2015

As personal devices and pervasive technologies for interacting with networked objects continue to proliferate, there is an unprecedented world of scattered pieces of contextualized information available. However, the explosive growth and variety of information ironically lead users and service providers to make poor decision. In this situation, recommender systems may be a valuable alternative for dealing with these information overload. But they failed to utilize various types of contextual information. In this study, we suggest a methodology for context-aware recommender systems based on the concept of contextual boundary. First, as we suggest contextual boundary-based profiling which reflects contextual data with proper interpretation and structure, we attempt to solve complexity problem in context-aware recommender systems. Second, in neighbor formation with contextual information, our methodology can be expected to solve sparsity and cold-start problem in traditional recommender systems. Finally, we suggest a methodology about context support score-based recommendation generation. Consequently, our methodology can be first step for expanding application of researches on recommender systems. Moreover, as we suggest a flexible model with consideration of new technological development, it will show high performance regardless of their domains. Therefore, we expect that marketers or service providers can easily adopt according to their technical support.

• Investigative Magnetic Resonance Imaging
• /
• v.2 no.1
• /
• pp.58-66
• /
• 1998

Purpose : This paper introduces a new three dimensional magnetic Resonance Image classification which is based on Mar kov Random Field-Gibbs Random Field with a line model. Material and Methods : The performance of the Gibbs Classifier over a statistically heterogeneous image can be improved if the local stationary regions in the image are disassociated from each other through the mechanism of the interaction parameters defined at the local neighborhood level. This usually involves the construction of a line model for the image. In this paper we construct a line model for multisignature images based on the differential of the image which can provide an a priori estimate of the unobservable line field, which may lie in regions with significantly different statistics. the line model estimated from the original image data can in turn be used to alter the values of the interaction parameters of the Gibbs Classifier. Results : MRF-Gibbs classifier for volumetric MR images is developed under the condition that the domain of the image classification is $E^{3}$ space rather thatn the conventional $E^{2}$ space. Compared to context free classification, MRF-Gibbs classifier performed better in homogeneous and along boundaries since contextual information is used during the classification. Conclusion : We construct a line model for multisignature, multidimensional image and derive the interaction parameter for determining the energy function of MRF-Gibbs classifier.

• Journal of Intelligence and Information Systems
• /
• v.19 no.1
• /
• pp.57-77
• /
• 2013

Social media has become one of the most popular media in web and mobile application. In 2011, social networks and blogs are still the top destination of online users, according to a study from Nielsen Company. In their studies, nearly 4 in 5active users visit social network and blog. Social Networks and Blogs sites rule Americans' Internet time, accounting to 23 percent of time spent online. Facebook is the main social network that the U.S internet users spend time more than the other social network services such as Yahoo, Google, AOL Media Network, Twitter, Linked In and so on. In recent trend, most of the companies promote their products in the Facebook by creating the "Facebook Page" that refers to specific product. The "Like" option allows user to subscribed and received updates their interested on from the page. The film makers which produce a lot of films around the world also take part to market and promote their films by exploiting the advantages of using the "Facebook Page". In addition, a great number of streaming service providers allows users to subscribe their service to watch and enjoy movies and TV program. They can instantly watch movies and TV program over the internet to PCs, Macs and TVs. Netflix alone as the world's leading subscription service have more than 30 million streaming members in the United States, Latin America, the United Kingdom and the Nordics. As the matter of facts, a million of movies and TV program with different of genres are offered to the subscriber. In contrast, users need spend a lot time to find the right movies which are related to their interest genre. Recent years there are many researchers who have been propose a method to improve prediction the rating or preference that would give the most related items such as books, music or movies to the garget user or the group of users that have the same interest in the particular items. One of the most popular methods to build recommendation system is traditional Collaborative Filtering (CF). The method compute the similarity of the target user and other users, which then are cluster in the same interest on items according which items that users have been rated. The method then predicts other items from the same group of users to recommend to a group of users. Moreover, There are many items that need to study for suggesting to users such as books, music, movies, news, videos and so on. However, in this paper we only focus on movie as item to recommend to users. In addition, there are many challenges for CF task. Firstly, the "sparsity problem"; it occurs when user information preference is not enough. The recommendation accuracies result is lower compared to the neighbor who composed with a large amount of ratings. The second problem is "cold-start problem"; it occurs whenever new users or items are added into the system, which each has norating or a few rating. For instance, no personalized predictions can be made for a new user without any ratings on the record. In this research we propose a clustering method according to the users' genre interest extracted from social network service (SNS) and user's movies rating information system to solve the "cold-start problem." Our proposed method will clusters the target user together with the other users by combining the user genre interest and the rating information. It is important to realize a huge amount of interesting and useful user's information from Facebook Graph, we can extract information from the "Facebook Page" which "Like" by them. Moreover, we use the Internet Movie Database(IMDb) as the main dataset. The IMDbis online databases that consist of a large amount of information related to movies, TV programs and including actors. This dataset not only used to provide movie information in our Movie Rating Systems, but also as resources to provide movie genre information which extracted from the "Facebook Page". Formerly, the user must login with their Facebook account to login to the Movie Rating System, at the same time our system will collect the genre interest from the "Facebook Page". We conduct many experiments with other methods to see how our method performs and we also compare to the other methods. First, we compared our proposed method in the case of the normal recommendation to see how our system improves the recommendation result. Then we experiment method in case of cold-start problem. Our experiment show that our method is outperform than the other methods. In these two cases of our experimentation, we see that our proposed method produces better result in case both cases.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.7 s.349
• /
• pp.24-31
• /
• 2006

Traditional security mechanisms do not work well in the sensor network area due to the sensor's resource constraints. Therefore security issues are challenging problems on realization of the sensor network. Among them, the key establishment is one of the most important and challenging security primitives which establish initial associations between two nodes for secure communications. Recently, R. Anderson et al. proposed one of the promising key establishment schemes for commodity sensor network called Key Infection. However, key infection has an intrinsic vulnerability that there are some areas where adversaries can eavesdrop on the transferred key information at initial key establishment time. Therefore, in this paper, we propose a security-enhanced key establishment scheme for key infection by suggesting a mechanism which effectively reduces the vulnerable areas. The proposed security mechanism uses other neighbor nodes' additional key information to establish pair-wise key at the initial key establishment time. By using the additional key information, we can establish security-enhanced key establishment, since the vulnerable area is decreased than the key infection's. We also evaluate our scheme by comparing it with key infection using logical and mathematical analysis.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.4
• /
• pp.189-198
• /
• 2024

Lipreading is one of the important parts of speech recognition, and several studies have been conducted to improve the performance of lipreading in lipreading systems for speech recognition. Recent studies have used method to modify the model architecture of lipreading system to improve recognition performance. Unlike previous research that improve recognition performance by modifying model architecture, we aim to improve recognition performance without any change in model architecture. In order to improve the recognition performance without modifying the model architecture, we refer to the cues used in human lipreading and set other regions such as chin and cheeks as regions of interest along with the lip region, which is the existing region of interest of lipreading systems, and compare the recognition rate of each region of interest to propose the highest performing region of interest In addition, assuming that the difference in normalization results caused by the difference in interpolation method during the process of normalizing the size of the region of interest affects the recognition performance, we interpolate the same region of interest using nearest neighbor interpolation, bilinear interpolation, and bicubic interpolation, and compare the recognition rate of each interpolation method to propose the best performing interpolation method. Each region of interest was detected by training an object detection neural network, and dynamic time warping templates were generated by normalizing each region of interest, extracting and combining features, and mapping the dimensionality reduction of the combined features into a low-dimensional space. The recognition rate was evaluated by comparing the distance between the generated dynamic time warping templates and the data mapped to the low-dimensional space. In the comparison of regions of interest, the result of the region of interest containing only the lip region showed an average recognition rate of 97.36%, which is 3.44% higher than the average recognition rate of 93.92% in the previous study, and in the comparison of interpolation methods, the bilinear interpolation method performed 97.36%, which is 14.65% higher than the nearest neighbor interpolation method and 5.55% higher than the bicubic interpolation method. The code used in this study can be found a https://github.com/haraisi2/Lipreading-Systems.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.1
• /
• pp.35-40
• /
• 2019

It is important to constantly provide service in real-time multimedia applications using multicast. Transmission path reconstruction occurs in hybrid multicast using Internet Protocol (IP) multicast and ALM in order to adapt the network status to things like congestion. So, there is a problem in which real-time QoS is reduced, caused by an increase in end-to-end delay. In this paper, we want to solve this problem through multi-layer transmission path construction. In the proposed method, we deploy the control server and application layer overlay host (ALOH) in each multicast domain (MD) for hybrid multicast construction. After the control server receives the control information from an ALOH that joins the MD, it makes a group based on the hop count and sends it to the ALOH in each MD. The ALOH in the MD performs the role of sending the packet to another ALOH and constructs the multi-layered transmission path in order of priority by using control information that is received from the control server and based on the delay between neighboring ALOHs. When congestion occurs in, or is absent from, the ALOH in the upper MD, the ALOH selects the path with the highest priority in order to reduce end-to-end delay. Simulation results show that the proposed method could reduce the end-to-end delay to less than 289 ms, on average, under congestion status.

• The KIPS Transactions:PartC
• /
• v.12C no.4 s.100
• /
• pp.473-480
• /
• 2005

We can obtain useful information by deploying large scale sensor networks in various situations. Security is also a major concern in sensor networks, and we need to establish pairwise keys between sensor nodes for secure communication. In this paper, we propose new pairwise key establishment mechanism based on clustering and polynomial sharing. In the mechanism, we divide the network field into clusters, and based on the polynomial-based key distribution mechanism we create bivariate Polynomials and assign unique polynomial to each cluster. Each pair of sensor nodes located in the same cluster can compute their own pairwise keys through assigned polynomial shares from the same polynomial. Also, in our proposed scheme, sensors, which are in each other's transmission range and located in different clusters, can establish path key through their clusterheads. However, path key establishment can increase the network overhead. The number of the path keys and tine for path key establishment of our scheme depend on the number of sensors, cluster size, sensor density and sensor transmission range. The simulation result indicates that these schemes can achieve better performance if suitable conditions are met.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.8 no.6 s.40
• /
• pp.55-66
• /
• 2004

Recently, many high-rise apartment buildings using the box system, composed of only reinforced concrete walls and slabs, have been constructed. In residential buildings such as apartments, vibrations occur from various sources and these vibrations transfer to neighboring residential units through walls and slabs. It is necessary to use a refined finite element model for an accurate vibration analysis of shear wall building structures. But it would take significant amount of computational time and memory if the entire building structure were subdivided into a finer mesh. Therefore, an efficient analytical method, which has only translational DOFs perpendicular to walls or slabs by the matrix condensation technique, is proposed in this study to obtain accurate results in significantly reduced computational time. If all of the DOFs except those perpendicular to walls or slabs in the shear wall structure eliminated using the matrix condensation technique at a time, the computational time for the matrix condensation would be significant. Thus, the modeling technique using super elements and substructuring technique is proposed to reduce the computational time for the matrix condensation. Dynamic analysis of 3-story and 5-story shear wall example structures were performed to verify the efficiency and accuracy of the proposed method. It was confirmed that the proposed method can provide the results with outstanding accuracy requiring significantly reduced computational time and memory.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.10
• /
• pp.6036-6045
• /
• 2014

This survey research was performed to determine the social capital that public officials generate within the relationship of the community at the individual level by performing their public office work as an administrative duty. To this end, a survey was conducted on 500 civil servants in Jeju province. The survey period was May 19-23, 2014. 476 subjects were analyzed using a T-test, One way ANOVA, and multiple regression analysis to on SPSS 19.0Win software. As a result of the analysis, 1. The norms of the community cultural, male staff participation and cooperation, and social capital level of civil servants, showed a significantly higher association than female civil servants. There was a difference between the populations of registration to an association to the work location type. In addition, the social capital increases generally as the level of the officers increases. 2. The sub-category in the social capital of a personal level on civil servants family & associates trust, participation & cooperation and neighbor trust had a positive impact on the efficiency of public services. On the other hand, community cultural associations (network) did not have an influence on efficiency.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.97-117
• /
• 2020

Product evaluation criteria is an indicator describing attributes or values of products, which enable users or manufacturers measure and understand the products. When companies analyze their products or compare them with competitors, appropriate criteria must be selected for objective evaluation. The criteria should show the features of products that consumers considered when they purchased, used and evaluated the products. However, current evaluation criteria do not reflect different consumers' opinion from product to product. Previous studies tried to used online reviews from e-commerce sites that reflect consumer opinions to extract the features and topics of products and use them as evaluation criteria. However, there is still a limit that they produce irrelevant criteria to products due to extracted or improper words are not refined. To overcome this limitation, this research suggests LDA-k-NN model which extracts possible criteria words from online reviews by using LDA and refines them with k-nearest neighbor. Proposed approach starts with preparation phase, which is constructed with 6 steps. At first, it collects review data from e-commerce websites. Most e-commerce websites classify their selling items by high-level, middle-level, and low-level categories. Review data for preparation phase are gathered from each middle-level category and collapsed later, which is to present single high-level category. Next, nouns, adjectives, adverbs, and verbs are extracted from reviews by getting part of speech information using morpheme analysis module. After preprocessing, words per each topic from review are shown with LDA and only nouns in topic words are chosen as potential words for criteria. Then, words are tagged based on possibility of criteria for each middle-level category. Next, every tagged word is vectorized by pre-trained word embedding model. Finally, k-nearest neighbor case-based approach is used to classify each word with tags. After setting up preparation phase, criteria extraction phase is conducted with low-level categories. This phase starts with crawling reviews in the corresponding low-level category. Same preprocessing as preparation phase is conducted using morpheme analysis module and LDA. Possible criteria words are extracted by getting nouns from the data and vectorized by pre-trained word embedding model. Finally, evaluation criteria are extracted by refining possible criteria words using k-nearest neighbor approach and reference proportion of each word in the words set. To evaluate the performance of the proposed model, an experiment was conducted with review on '11st', one of the biggest e-commerce companies in Korea. Review data were from 'Electronics/Digital' section, one of high-level categories in 11st. For performance evaluation of suggested model, three other models were used for comparing with the suggested model; actual criteria of 11st, a model that extracts nouns by morpheme analysis module and refines them according to word frequency, and a model that extracts nouns from LDA topics and refines them by word frequency. The performance evaluation was set to predict evaluation criteria of 10 low-level categories with the suggested model and 3 models above. Criteria words extracted from each model were combined into a single words set and it was used for survey questionnaires. In the survey, respondents chose every item they consider as appropriate criteria for each category. Each model got its score when chosen words were extracted from that model. The suggested model had higher scores than other models in 8 out of 10 low-level categories. By conducting paired t-tests on scores of each model, we confirmed that the suggested model shows better performance in 26 tests out of 30. In addition, the suggested model was the best model in terms of accuracy. This research proposes evaluation criteria extracting method that combines topic extraction using LDA and refinement with k-nearest neighbor approach. This method overcomes the limits of previous dictionary-based models and frequency-based refinement models. This study can contribute to improve review analysis for deriving business insights in e-commerce market.