• Journal of the Korea Society of Computer and Information
• /
• v.17 no.4
• /
• pp.83-90
• /
• 2012

In e-commerce systems that deal with a large number of items, the function of personalized recommendation is essential. Collaborative filtering that is a successful recommendation algorithm, suffers from the sparsity, cold-start, and scalability restrictions. Additionally, this work raises a new flaw of the algorithm, inconsistent performance of recommendation. This is also not measurable by the current MAE-based evaluation that does not consider the deviation of prediction error, and furthermore is performed independently of precision and recall measurement. To evaluate the collaborative filtering comprehensively, this work proposes an extended evaluation model that includes the current criteria such as MAE, Precision, Recall, deviation, and applies it to cluster-based combined collaborative filtering.

• Journal of Korea Society of Industrial Information Systems
• /
• v.21 no.4
• /
• pp.1-11
• /
• 2016

Recently numerous studies are conducted to estimate the human personality from the online social activities. This paper develops a comprehensive model for political attitude estimation leveraging the Facebook Like information of the users. We designed a Facebook Crawler that efficiently collects data overcoming the difficulties in crawling Ajax enabled Facebook pages. We show that the category level selection can reduce the data analysis complexity utilizing the sparsity of the huge like-attitude matrix. In the Korean Facebook users' context, only 28 criteria (3% of the total) can estimate the political polarity of the user with high accuracy (AUC of 0.82).

• Journal of Biomedical Engineering Research
• /
• v.35 no.3
• /
• pp.68-74
• /
• 2014

Recent research on mild cognitive impairment (MCI) has shown that cognitive and memory decline in this disease is accompanied by disruptive changes in the brain functional network. However, there have been no graph-theoretical studies using $^{11}C$-PIB PET data of the Alzheimer's Disease or mild cognitive impairment. In this study, we acquired $^{18}F$-FDG PET and $^{11}C$-PIB PET images of twenty-four normal aging control participants and thirty individuals with MCI from ADNI (Alzheimer's Disease Neuroimaging Initiative) database. Brain networks were constructed by thresholding binary correlation matrices using graph theoretical approaches. Both normal control and MCI group showed small-world property in $^{11}C$-PIB PET images as well as $^{18}F$-FDG PET images. $^{11}C$-PIB PET images showed significant difference between NC (normal control) and MCI over large range of sparsity values. This result will enable us to further analyze the brain using established graph-theoretical approaches for $^{11}C$-PIB PET images.

• International Journal of Contents
• /
• v.11 no.3
• /
• pp.47-53
• /
• 2015

Visual object tracking is a fundamental problem in the field of computer vision, as it needs a proper model to account for drastic appearance changes that are caused by shape, textural, and illumination variations. In this paper, we propose a feature-based visual-object-tracking method with a sparse representation. Generally, most appearance-based models use the gray-scale pixel values of the input image, but this might be insufficient for a description of the target object under a variety of conditions. To obtain the proper information regarding the target object, the following combination of features has been exploited as a corresponding representation: First, the features of the target templates are extracted by using the HOG (histogram of gradient) and LBPs (local binary patterns); secondly, a feature-based sparsity is attained by solving the minimization problems, whereby the target object is represented by the selection of the minimum reconstruction error. The strengths of both features are exploited to enhance the overall performance of the tracker; furthermore, the proposed method is integrated with the particle-filter framework and achieves a promising result in terms of challenging tracking videos.

• 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 the Korean Institute of Landscape Architecture
• /
• v.29 no.2
• /
• pp.14-21
• /
• 2001

This study aims to analyze visual structure by evaluating the view from five building sites around An-ap pond, and attempt to determine which site commands the best view and will provide the most active use. The results of this study can be summarized as follows: According to the questionnaire survey of experts on the relations of dominancy-subordination(´chu-jong´), vacancy-solidness(´heo-sil´), sparsity-density(´so-mil´) based on ancient oriental Yin-Yang theory and analysis of visual structure on angle of elevation, depression, and the landscape-component ratio to be seen through five building sites around the west of An-ap pond, building site three was selected as the building site which has the best landscape. Therefore, it is estimated that building site three played the role of core-building site. According to the result of correlation analysis, the greater the increased in the component ratio of sky, mountain ,the greater the degree of harmony within the landscape. As well, the degree of harmony increased when the landscape component ratio of a distant view was greater than that of a near view. Moreover, it was proved that the relationships of ´chu-jong´, ´heo-sil´, ´so-mil´ are correlative, not independent.

• The KIPS Transactions:PartD
• /
• v.8D no.5
• /
• pp.573-580
• /
• 2001

The large amounts of high dimensional data contains a significant amount of noises by it own sparsity, which adds difficulties in high dimensional clustering. The CLIP is developed as a clustering algorithm to support characteristics of the high dimensional data. The CLIP is based on the incremental one dimensional projection on each axis and find product sets of the dimensional clusters. These product sets contain not only all high dimensional clusters but also they may contain noises. In this paper, we propose extended CLIP algorithm which refines the product sets that contain cluster. We remove high dimensional noises by applying two dimensional projections iteratively on the already found product sets by CLIP. To evaluate the performance of extended algorithm, we demonstrate its effectiveness through a series of experiments on synthetic data sets.

• Journal of Communications and Networks
• /
• v.15 no.4
• /
• pp.370-382
• /
• 2013

Distributed massive MIMO systems, which have high bandwidth efficiency and can accommodate a tremendous amount of traffic using algorithms such as zero-forcing beam forming (ZFBF), may be deployed in large public venues with the antennas mounted under-floor. In this case the channel gain matrix H can be modeled as a multi-banded matrix, in which off-diagonal entries decay both exponentially due to heavy human penetration loss and polynomially due to free space propagation loss. To enable practical implementation of such systems, we present a multi-banded matrix inversion algorithm that substantially reduces the complexity of ZFBF by keeping the most significant entries in H and the precoding matrix W. We introduce a parameter p to control the sparsity of H and W and thus achieve the tradeoff between the computational complexity and the system throughput. The proposed algorithm includes dense and sparse precoding versions, providing quadratic and linear complexity, respectively, relative to the number of antennas. We present analysis and numerical evaluations to show that the signal-to-interference ratio (SIR) increases linearly with p in dense precoding. In sparse precoding, we demonstrate the necessity of using directional antennas by both analysis and simulations. When the directional antenna gain increases, the resulting SIR increment in sparse precoding increases linearly with p, while the SIR of dense precoding is much less sensitive to changes in p.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.49 no.4
• /
• pp.168-176
• /
• 2000

This paper presents the Hessenberg method, a new sparsity-based small signal stability analysis program for large interconnected power systems. The Hessenberg method as well as the Arnoldi method computes the partial eigen-solution of large systems. However, the Hessenberg method with pivoting is numerically very stable comparable to the Householder method and thus re-orthogonalization of the krylov vectors is not required. The fractional transformation with a complex shift is used to compute the modes around the shift point. If only the dominant electromechanical oscillation modes are of concern, the modes can be computed fast with the shift point determined by Fourier transforming the time simulation results for transient stability analysis, if available. The program has been successfully tested on the New England 10-machine 39-bus system and Korea Electric Power Co. (KEPCO) system in the year of 2000, which is comprised of 791-bus, 1575-branch, and 215-machines. The method is so efficient that CPU time for computing five eigenvalues of the KEPCO system is 3.4 sec by a PC with 400 MHz Pentium IIprocessor.

• Journal of Intelligence and Information Systems
• /
• v.9 no.3
• /
• pp.177-191
• /
• 2003

Recommender systems are a personalized information filtering technology to help customers find the products they would like to purchase. Collaborative filtering is the most successful recommendation technology. Web usage mining and clustering analysis are widely used in the recommendation field. In this paper, we propose several hybrid collaborative filtering-based recommender procedures to address the effect of web usage mining and cluster analysis. Through the experiment with real e-commerce data, it is found that collaborative filtering using web log data can perform recommendation tasks effectively, but using cluster analysis can perform efficiently.