• ETRI Journal
• /
• v.36 no.3
• /
• pp.333-342
• /
• 2014

Most hyper-ellipsoidal clustering (HEC) approaches use the Mahalanobis distance as a distance metric. It has been proven that HEC, under this condition, cannot be realized since the cost function of partitional clustering is a constant. We demonstrate that HEC with a modified Gaussian kernel metric can be interpreted as a problem of finding condensed ellipsoidal clusters (with respect to the volumes and densities of the clusters) and propose a practical HEC algorithm that is able to efficiently handle clusters that are ellipsoidal in shape and that are of different size and density. We then try to refine the HEC algorithm by utilizing ellipsoids defined on the kernel feature space to deal with more complex-shaped clusters. The proposed methods lead to a significant improvement in the clustering results over K-means algorithm, fuzzy C-means algorithm, GMM-EM algorithm, and HEC algorithm based on minimum-volume ellipsoids using Mahalanobis distance.

• International Journal of Safety
• /
• v.10 no.2
• /
• pp.16-20
• /
• 2011

The computer application on embedded system is recently more increased in accordance of the development of computer technology. In this trend, the depending of SW in embedded system, especially railway signaling system, is being increased further. So the testing for the safety of railway signaling system software became more important. Hence, the safety assurance of the vital software on the railway signaling system is very important but yet, not many works have been done. In this paper, we represented the implementation results of development of performance testing tool in railway signaling system. The implemented testing item had referred to the international standards in relation to the software for railway system, such as IEC 61508 and IEC 62279.

• ETRI Journal
• /
• v.37 no.3
• /
• pp.541-550
• /
• 2015

In this paper, we propose a classification-based approach for hybridizing statistical machine translation and rulebased machine translation. Both the training dataset used in the learning of our proposed classifier and our feature extraction method affect the hybridization quality. To create one such training dataset, a previous approach used auto-evaluation metrics to determine from a set of component machine translation (MT) systems which gave the more accurate translation (by a comparative method). Once this had been determined, the most accurate translation was then labelled in such a way so as to indicate the MT system from which it came. In this previous approach, when the metric evaluation scores were low, there existed a high level of uncertainty as to which of the component MT systems was actually producing the better translation. To relax such uncertainty or error in classification, we propose an alternative approach to such labeling; that is, a cut-off method. In our experiments, using the aforementioned cut-off method in our proposed classifier, we managed to achieve a translation accuracy of 81.5% - a 5.0% improvement over existing methods.

• Proceedings of the KSRS Conference
• /
• v.1
• /
• pp.376-379
• /
• 2006

A numerous oil slicks of natural origin were revealed in the southwest (SW) part of Caspian Sea by the synthetic aperture radar (SAR) images acquired by Envisat satellite in 2003-2004. On the basis of computer processing, visual analysis of SAR images and comparisons with bathymetry, geophysical and seismic data in geographic information system (GIS), a link between these slicks and unloading of liquid hydrocarbons in the SW Caspian is established. Oil slicks are basically concentrated above domes of local geological formations of the sedimentary cover. In total more than 90 seeps and mud volcanoes having a repeating regime and representing an active type were identified; they are distributed across the SW Azerbaijan and West Iranian sectors. Periodical occurrence of slicks can reflect alternation of mud volcanism pulses forced by intensive seismicity with the quiet periods. Seepage rate of oil in the SW part of the Caspian Sea according to SAR images is estimated to be up to 16,000 metric tons per year. The importance of unloading of oils on hydrochemistry and ecological conditions of the Caspian Sea is demonstrated. Conclusion is done that the Envisat SAR to be an excellent tool for studying oil seeps through observation oil slicks floating on the sea surface.

• Journal of Advanced Navigation Technology
• /
• v.13 no.6
• /
• pp.861-875
• /
• 2009

In order to make high quality software and high reliability software, systematic development management and organizational support are essential needed. Since 1990's Software process models such as ISO/IEC 15504 and CMMI have been used to improve organization capability. But these models have problems that are used to apply on large scaled organization or large project and so many practices are actually required. We present characteristics of ISO/IEC 15504, CMMI and K-model can easily apply to small and medium sized business or project, and propose the standard quality metric and accreditate procedure based on K-model for measuring quantitative quality level.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.9
• /
• pp.1-8
• /
• 2010

The key challenge in HW/SW co-design is how to choose the appropriate HW/SW partitioning from the vast array of possible options in the mapping set. In this paper we present a unique and efficient approach for addressing this problem known as Customized Heuristic Algorithm for Reducing Mapping Sets(CHARMS). CHARMS uses sensitivity to individual task computational complexity as well the computed weighted values of system performance influencing metrics to streamline the mapping sets and extract the most optimal cases. Using H.263 encoder, we show that CHARMS sieves out 95.17% of the sub-optimal mapping sets, leaving the designer with 4.83% of the best cases to select from for run-time implementation.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.10
• /
• pp.2451-2461
• /
• 2014

Mobile application is software executing on smart devices regardless of the time and place. Many individuals and companies have provided a lot of mobile applications services. However, there is not certain standard in terms of application's quality evaluation because study is deficient compared with increase amount of development of mobile application. Moreover, mobile application basically has many special characteristics. For these reasons mobile application is required special standard of quality different from general software. To satisfy these needs, I design and propose mobile application evaluation model. Evaluation model is mapped by characteristics of mobile application based on ISO/IEC 25000's quality characteristics and propose each quality characteristics and metrics. For verification, scenario-based studies were applied to quality model and carried out.