• Journal of the Korean Society for information Management
• /
• v.23 no.2
• /
• pp.265-285
• /
• 2006

In text categorization a certain level of correctness of labels assigned to training documents is assumed without solid knowledge on that of real-world collections. Our research attempts to explore the quality of pre-assigned subject categories in a real-world collection, and to identify the relationship between the quality of category assignment in training set and text categorization performance. Particularly, we are interested in to what extent the performance can be improved by enhancing the quality (i.e., correctness) of category assignment in training documents. A collection of 1,150 abstracts in computer science is re-classified by an expert group, and divided into 907 training documents and 227 test documents (15 duplicates are removed). The performances of before and after re-classification groups, called Initial set and Recat-1/Recat-2 sets respectively, are compared using a kNN classifier. The average correctness of subject categories in the Initial set is 16%, and the categorization performance with the Initial set shows 17% in $F_1$ value. On the other hand, the Recat-1 set scores $F_1$ value of 61%, which is 3.6 times higher than that of the Initial set.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.8
• /
• pp.429-439
• /
• 2020

This study examined the effect size of virtual reality programs on the upper extremity function of stroke patients through a meta-analysis. Databases, such as the Research Information Sharing Service, the Korean Studies Information Service System, the National Library of Korea, the Korean Citation Index, and the National Digital Science Library, were used. Previous articles were surveyed for virtual reality programs between January 2010 and June 2019. A meta-analysis was performed by selecting the final 14 studies based on the PICO standard. The RoB and RoBANS tools were used as quality assessment tools for randomized and non-randomized control trials, respectively. The CMA 3.0 program was used to calculate the effect size of each study. Sub-group analysis, meta-regression analysis, and publication bias were performed. The total effect size of the virtual reality programs on the upper extremity function was Hedges's g=0.390 (95% CI: 0.192~0.587) (p<.05). The virtual reality program positively affects the upper extremity function of stroke patients. Therefore, the development of various virtual reality programs and industry-academia cooperation technology for stroke patients is required in accordance with the fourth industry. Randomized control trials and detailed upper extremity function studies for virtual reality programs will be needed in follow-up studies.

• Journal of KIISE:Databases
• /
• v.30 no.3
• /
• pp.336-349
• /
• 2003

Histograms have been getting a lot of attention recently. Histograms are commonly utilized in commercial database systems to capture attribute value distributions for query optimization Recently, in the advent of researches on approximate query answering and stream data, the interests in histograms are widely being spread. The simplest approach assumes that the attributes in relational tables are independent by AVI(Attribute Value Independence) assumption. However, this assumption is not generally valid for real-life datasets. To alleviate the problem of approximation on multi-dimensional data with multiple one-dimensional histograms, several techniques such as wavelet, random sampling and multi-dimensional histograms are proposed. Among them, GENHIST is a multi-dimensional histogram that is designed to approximate the data distribution with real attributes. It uses overlapping buckets that allow more efficient approximation on the data distribution. In this paper, we propose a scheme, OPT that can determine the optimal frequencies of overlapped buckets that minimize the SSE(Sum Squared Error). A histogram with overlapping buckets is first generated by GENHIST and OPT can improve the histogram by calculating the optimal frequency for each bucket. Our experimental result confirms that our technique can improve the accuracy of histograms generated by GENHIST significantly.

• The KIPS Transactions:PartC
• /
• v.12C no.1 s.97
• /
• pp.83-96
• /
• 2005

The multichannel switch is an architecture widely used for ATM (Asynchronous Transfer Mode). It is known that the fault tolerant characteristic can be incorporated into the multichannel crossbar switching fabric. For example, if a link belonging to a multichannel group fails, the remaining links can assume responsibility for some of the traffic on the failed link. On the other hand, if a fault occurs in a switching element, it can lead to erroneous routing and sequencing in the multichannel switch. We investigate several fault localization algorithm in multichannel crossbar ATM switches with a view to early fault recovery. The optimal algorithm gives the best performance in terms of time to localization but it is computationally complex which makes it difficult to implement. We develop an on-line algorithm which is computationally more efficient than the optimal one. We evaluate its performance through simulation. The simulation results show that the Performance of the on-line algorithm is only slightly sub-optimal for both random and bursty traffic. There are cases where the proposed on-line algorithm cannot pinpoint down to a single fault. We enumerate those cases and investigate the causes. Finally, a fault recovery algorithm is described which utilizes the information provided by the fault localization algorithm The fault recovery algorithm providesadditionalrowsandcolumnstoallowcellstodetourthefaultyelement.

• The KIPS Transactions:PartD
• /
• v.11D no.7 s.96
• /
• pp.1385-1398
• /
• 2004

This paper discusses an effective processing of subsequence matching under time warping in time-series databases. Time warping is a trans-formation that enables finding of sequences with similar patterns even when they are of different lengths. Through a preliminary experiment, we first point out that the performance bottleneck of Naive-Scan, a basic method for processing of subsequence matching under time warping, is on the CPU processing step. Then, we propose a novel method that optimizes the CPU processing step of Naive-Scan. The proposed method maximizes the CPU performance by eliminating all the redundant calculations occurring in computing the time warping distance between the query sequence and data subsequences. We formally prove the proposed method does not incur false dismissals and also is the optimal one for processing Naive-Scan. Also, we discuss the we discuss to apply the proposed method to the post-processing step of LB-Scan and ST-Filter, the previous methods for processing of subsequence matching under time warping. Then, we quantitatively verify the performance improvement ef-fects obtained by the proposed method via extensive experiments. The result shows that the performance of all the three previous methods im-proves by employing the proposed method. Especially, Naive-Scan, which is known to show the worst performance, performs much better than LB-Scan as well as ST-Filter in all cases when it employs the proposed method for CPU processing. This result is so meaningful in that the performance inversion among Nive- Scan, LB-Scan, and ST-Filter has occurred by optimizing the CPU processing step, which is their perform-ance bottleneck.

• The KIPS Transactions:PartD
• /
• v.12D no.2 s.98
• /
• pp.233-246
• /
• 2005

To enhance the user response time of content-based retrieval service for multimedia information, several multi-dimensional index schemes have been proposed. M-tree, a well-known multidimensional index scheme is of metric space access method, and is based on the distance between objects in the metric space. However, since the overlap between index spaces of nodes might enlarge the number of nodes of M-tree accessed for query processing, the user response time for content-based multimedia information retrieval grows longer. In this paper, we propose a node split algorithm which is able to reduce the sire of overlap between index spaces of nodes in M-tree. In the proposed scheme, we choose a virtual center point as the routing object and entry redistribution as the postprocessing after node split in order to reduce the radius of index space of a node, and finally in order to reduce the overlap between the index spaces of routing nodes. From the experimental results, we can see the proposed split algorithm reduce the overlap between index space of nodes and finally enhance the user response time for similarity-based query processing.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.6
• /
• pp.1404-1417
• /
• 1998

Currently, there exists two different methods for database retrieval in the internet. First is to use the search engine and the second is to use the plug-in or ActiveX technology, If a search engine, which makes use of indices built from keywords of simple text data in order to do a search, is used when accessing a database, first it is not possible to access more than one database at a time, second it is also not possible to support various conditional retrievals as in using query language, and third the set of data received might include many unwanted data, in other words, precision rate might be relatively low. Plug in or Active technology make use of Web browset to execute chents' query in order to do a database retrieval. Problems associated with this is that it is not possible to activate more than one DBMS simultaneously even if they are of the same data model. sefond it is not possible to execute a user query other than the ones thai arc previou sly defined by the client program In this paper, to resolve those aforementioned problems we design and implement database retrieval system using a virtual database, which makes it possible to provide direct query jntertacc through the conventional Web browser. We assume that the virtual database is designed and aggregated from more than one relational database using the same data model.

• The KIPS Transactions:PartD
• /
• v.18D no.1
• /
• pp.9-22
• /
• 2011

In this paper we present an efficient solution to rotation?invariant boundary image matching. Computing the rotation-invariant distance between image time-series is a time-consuming process since it requires a lot of Euclidean distance computations for all possible rotations. In this paper we propose a novel solution that significantly reduces the number of distance computations using the envelope-based lower bound. To this end, we first present how to construct a single envelope from a query sequence and how to obtain a lower bound of the rotation-invariant distance using the envelope. We then show that the single envelope-based lower bound can reduce a number of distance computations. This approach, however, may cause bad performance since it may incur a larger lower bound by considering all possible rotated sequences in a single envelope. To solve this problem, we present a concept of rotation interval, and using the rotation interval we generalize the envelope-based lower bound by exploiting multiple envelopes rather than a single envelope. We also propose equi-width and envelope minimization divisions as the method of determining rotation intervals in the multiple envelope approach. Experimental results show that our envelope-based solutions outperform existing solutions by one or two orders of magnitude.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.10 no.1
• /
• pp.169-182
• /
• 2007

The purpose of this study is to assess the urban amenity on physical environmental factors, and to verify the effectiveness of the amenity map using correlation analysis of the environmental quality. The physical environmental factors were set to 4 items of green space, landscape, water environment and land use, and the items were composed of 11 detail factors. Based on the factors, GIS maps were constructed and the amenity map was produced using overlay analysis. The results of this study are as follow; the proportion of 1~2 ranks was 40.8% of total area around Dalseong-gun, Dong-gu, Suseong-gu. The lower 6~7 ranks in the amenity assessment was 5.7% of total area around Jung-gu, Seo-gu, Dalseo-gu. According to the results of correlation analysis between the amenity and environmental observed data, $SO_2$ among the air pollution material had a negative correlation with amenity(r=-0.649, p<0.05). In case of water pollution, TN and TP had the negative correlations with amenity (r=-0.643, P<0.01; r=0.642, p<0.01).

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.7
• /
• pp.165-174
• /
• 2013

Recently, many universities in Korea have been faced with critical crisis such as the decrease in the number of freshmen, the pressure for tuition cuts, M&A between universities and so on. Nobody has expected that universities will have this kind of difficulties. The universities are making attempts to innovate the quality of education to secure high level of education and to meet social needs to overcome these internal and external environment of crisis. For this innovation, the universities have sought to reduce the budget as well as conducted the self-evaluation to figure out their relative positions annually. Innovations cannot have having the limitation without education funds. Budget spent in universities have influences directly or indirectly on the structural improvement of the finance and on the growth of universities. The purpose of this study is to explore the decision-making method to find the optimal budget allocation so as to minimize the execution budget and to maximize the management evaluation by taking the advantage to analyse the relationship between the evaluation and the budget. Therefore, in this paper, we implement the development of the mathematical model for the University Evaluation and Budget Allocation Optimization in the form of the linear programming.