• Journal of KIISE:Software and Applications
• /
• v.41 no.7
• /
• pp.469-480
• /
• 2014

Software Product Line (SPL) is a software development paradigm that guarantees high productivity, reduced cost, and shorter time-to-market by systematically planning and reusing commonality and variability. In order to maximize the benefits of SPL engineering, testing should be integrated into the SPL engineering lifecycle processes that consist of domain engineering and application engineering and should be performed with as little test efforts as possible. This paper proposes a systematic software product line test cases derivation method using combinatorial test design. By applying combinatorial test design to product line test cases derivation and exploiting commonality between products at the same time, the number of generated test cases is dramatically reduced with the result that they can be effectively reused by the products of the given product line. Case studies conducted in this paper show the efficacy of our method compared with other methods that use only commonality or combinatorial design or neither of them in terms of the number of derived test cases.

• CELLMED
• /
• v.3 no.2
• /
• pp.10.1-10.8
• /
• 2013

Cancer is one of the major dreaded diseases causing high mortality. Lung cancer is second in position of all cancer related deaths and mainly divided into two morphologic sub-types: small-cell lung cancer and non-small cell lung cancer (NSCLC). NSCLC is an aggressive neoplasm which hardly responds to any conventional chemotherapy. Epidermal growth factor receptor (EGFR) belongs to the ErbB family of receptor tyrosine kinase that is mainly over-expressed in NSCLC. EGFR is mainly involved in the pathogenesis and progression of different carcinoma. In vivo and in vitro studies suggest that EGFR and EGF like peptides are often over-expressed in human NSCLC and these proteins are able to induce cell transformation. The conventional therapies mostly inhibit the EGFR activity and expression level in human NSCLC with the use of some EGFR-inhibitors like HKI-272, EKB569, CL-387785 etc. and some synthetic chemotherapeutic drugs like erlotinib, gefitinib, plumbagin, docetaxel, cisplatin etc., alone or in combination of two or more drugs. These therapies selectively act by competitive inhibition of the binding of adenosine triphosphate to the tyrosine kinase domain of the EGFR, resulting in inhibition of the EGFR signaling pathway. But these chemotherapeutic drugs have some cytotoxic activities to the normal cells and have some adverse side-effects. Recent studies on some traditional alternative therapies including some herbal and plant extracts, active ingredients like curcumin, different homeopathic drugs, etc. can target EGFR-signalling in NSCLC with less toxic side-effects are being currently developed.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.59 no.2
• /
• pp.37-47
• /
• 2017

In this study, we analyzed the variability of irrigation water amounts based on the combination of various crops and soil textures using the Irrigation Water Management Model (IWMM). IWMM evaluates the degree of agricultural drought using the Soil Moisture Deficit Index (SMDI). When crops are damaged by the water scarcity under the drought condition indicating that the SMDI values are in negative (SMDI<0), IWMM irrigates appropriate water amounts that can shift the negative SMDI values to "0" to crop fields. To test the IWMM model, we selected the Bandong-ri (BDR) and Jucheon (JC) sites in Gangwon-do and Jeollabuk-do provinces. We derived the soil hydraulic properties using the near-surface data assimilation scheme form the Time Domain Reflectrometry (TDR)-based soil moisture measurements. The daily root zone soil moisture dynamics (R: 0.792/0.588 and RMSE: 0.013/0.018 for BDR/JC) estimated by the derived soil parameters were matched well with the TDR-based measurements for validation. During the long-term (2001~2015) period, IWMM irrigated the minimum water amounts to crop fields, while there were no irrigation events during the rainy days. Also, Sandy Loam (SL) and Silt (Si) soils require more irrigation water amounts than others, while the irrigation water were higher in the order of radish, wheat, soybean, and potato, respectively. Thus, the IWMM model can provide efficient irrigation water amounts to crop fields and be useful for regions at where limited water resources are available.

• Journal of KIISE:Software and Applications
• /
• v.29 no.3
• /
• pp.192-201
• /
• 2002

Automated text classification is considered as an important method to manage and process a huge amount of documents in digital forms that are widespread and continuously increasing. Recently, text classification has been addressed with machine learning technologies such as k-nearest neighbor, decision tree, support vector machine and neural networks. However, only few investigations in text classification are studied on real problems but on well-organized text corpus, and do not show their usefulness. This paper proposes and analyzes text classification methods for a real application, email document classification task. First, we propose a combining method of multiple neural networks that improves the performance through the combinations with maximum and neural networks. Second, we present another strategy of combining multiple machine learning classifiers. Voting, Borda count and neural networks improve the overall classification performance. Experimental results show the usefulness of the proposed methods for a real application domain, yielding more than 90% precision rates.

• Journal of Digital Contents Society
• /
• v.19 no.3
• /
• pp.435-443
• /
• 2018

Recently, with the explosive development of computing power, various methods such as RNN and CNN have been proposed under the name of Deep Learning, which solve many problems of Computer Vision have. The Generative Adversarial Network, released in 2014, showed that the problem of computer vision can be sufficiently solved in unsupervised learning, and the generation domain can also be studied using learned generators. GAN is being developed in various forms in combination with various models. Machine learning has difficulty in collecting data. If it is too large, it is difficult to refine the effective data set by removing the noise. If it is too small, the small difference becomes too big noise, and learning is not easy. In this paper, we apply a deep CNN model for extracting facial region in image frame to GAN model as a preprocessing filter, and propose a method to produce composite images of various facial expressions by stably learning with limited collection data of two persons.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.1
• /
• pp.211-216
• /
• 2018

In this paper, we studied the way that classify whether unknown PE file is malware or not. In the classification problem of malware detection domain, feature extraction and classifier are important. For that purpose, we studied what the feature is good for classifier and the which classifier is good for the selected feature. So, we try to find the good combination of feature and classifier for detecting malware. For it, we did experiments at two step. In step one, we compared the accuracy of features using Opcode only, Win. API only, the one with both. We founded that the feature, Opcode and Win. API, is better than others. In step two, we compared AUC value of classifiers, Bernoulli Naïve Bayes, K-nearest neighbor, Support Vector Machine and Decision Tree. We founded that Decision Tree is better than others.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.5
• /
• pp.1082-1092
• /
• 1996

The design of distrbuted systems is difficult to achieve as the execution patterns of distrbuted systems are typically more complex than those of non- distributed systems. Thus, research toward the development of design methods for distributed systems is quitely needed. As object-oriented systems and distrbuted systems share similar properties, the combination of these two is somehow natural. In this work, a design of distributed systems is introduced. The goal of the method in this paper is to provide assistance to the process of specifying a formal object- oriented specification from graphical representation specification inputs such as data flow diagrams, state transition diagrams and Petri nets. It addresses the extraction of objects, operations and reationshipsfrom the problem domain with emphasis on the specification of the characteristics of distributed systems. This object identification method is supported by a knowledge base that provides for the automated analysis and reasoning about objects and their relationsships. The final object model is represented in a format which provides a formal mechanism for reprsenting the object information.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.5
• /
• pp.1103-1111
• /
• 1996

The design of distrbuted systems is difficult to achieve as the execution patterns of distrbuted systems are typically more complex than those of non- distributed systems. Thus, research toward the development of design methods for distributed systems is quitely needed. As object-oriented systems and distrbuted systems share similar properties, the combination of these two is somehow natural. In this work, a design of distributed systems is introduced. The goal of the method in this paper is to provide assistance to the process of specifying a formal object- oriented specification from graphical representation specification inputs such as data flow diagrams, state transition diagrams and Petri nets. It addresses the extraction of objects, operations and reationshipsfrom the problem domain with emphasis on the specification of the characteristics of distributed systems. This object identification method is supported by a knowledge base that provides for the automated analysis and reasoning about objects and their relationsships. The final object model is represented in a format which provides a formal mechanism for reprsenting the object information.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.6 no.1
• /
• pp.34-42
• /
• 2011

In an effort to the practical realization of phonetic typewriter, we concentrate on the classification of consonants in this paper. Since many of consonants do not show periodic behavior in time domain and thus the validity for Fourier analysis of them are not convincing, vector quantization (VQ) via LBG clustering is first performed to check if the feature vectors of MFCC and LPCC are ever meaningful for consonants. Experimental results of VQ showed that it's not easy to draw a clear-cut conclusion as to the validity of Fourier analysis for consonants. For classification purpose, two kinds of neural networks are employed in our study: self organizing map (SOM) and learning vector quantization (LVQ). Results from SOM revealed that some pairs of phonemes are not resolved. Though LVQ is free from this difficulty inherently, the classification accuracy was found to be low. This suggests that, as long as consonant classification by LVQ is concerned, other types of feature vectors than MFCC should be deployed in parallel. However, the combination of MFCC/LVQ was not found to be inferior to the classification of phonemes by language-moded based approach. In all of our work, LPCC worked worse than MFCC.

• Herbal Formula Science
• /
• v.14 no.2
• /
• pp.1-8
• /
• 2006

ElM (Eighteen Incompatible Medicaments) is an important component in Oriental pharmacology and is directly related to clinical prescriptions. Medical practitioners argued that the definite cause and meaning of ElM was ambiguous and therefore debated the issue of clinical application of the ElM. This study conducted an in-depth literary research on the origin, meaning and contents of ElM with the purpose to contribute in its efforts to be used clinically. Even after thousands of years have past since establishment of Oriental medicine. ElM is still tabooed and was an obstacle that hindered ideologies. Modern herbal medicine texts claim that the use of ElM can reduce treatment effects and promote poisoning and side effects. However, since long ago, there has been medical practitioners who reject this as false. Recently, poisoning caused by ElM has been claimed to be from the toxicity of the drug itself, rather than the result of interaction between the drugs. and therefore they suggest that ElM is not a forbidden domain. In addition. ElM showed a difference in number depending on the era. However, this can be understood not as a definite number. but instead as a warning to be careful during combination of drugs for use as clinical medicine. Historically. there were very few cases in which ElM was used for clinical tests and thus, the clinical value is not yet clear. However. some medical practitioners clinically applied it and found clear results for it. while others applied ElM directly to their bodies. which showed signs for the usefulness and potential of ElM for us. A more concrete and in-depth study must be made on ELM.