• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.10
• /
• pp.5197-5218
• /
• 2019

Large-scale retrieval algorithm is problem for visual analyses applications, along its research track. In this paper, we propose a high-efficiency region division-based image retrieve approaches, which fuse low-level local color histogram feature and texture feature. A novel image region division is proposed to roughly mimic the location distribution of image color and deal with the color histogram failing to describe spatial information. Furthermore, for optimizing our region division retrieval method, an image descriptor combining local color histogram and Gabor texture features with reduced feature dimensions are developed. Moreover, we propose an extended Canberra distance method for images similarity measure to increase the fault-tolerant ability of the whole large-scale image retrieval. Extensive experimental results on several benchmark image retrieval databases validate the superiority of the proposed approaches over many recently proposed color-histogram-based and texture-feature-based algorithms.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.699-700
• /
• 2023

최근 국내 기업에서는 블라인트 테스트나 포트폴리오와 같은 자료를 활용하여 채용하는 추세이다. 지원자마다 개인의 역량이 다를 뿐만 아니라 기업에서 요구하는 기술/경험, 지원 자격, 특정 기술에 대한 경험을 요구한다. 따라서 본 논문에서는 국내 기업의 채용 공고에 기재된 지원 자격, 우대 기술, 우대 사항 등의 데이터와 지원자의 개인 역량(기술 스택, 전공 역량, 진행 프로젝트 등) 데이터를 활용하여 키워드를 추출한다. 지원자와 기업이 입력한 데이터를 통해 추출한 키워드들을 두 개의 집합으로 나눈 뒤 각각의 키워드를 할당한다. 할당받은 집합들을 비교하여 지원자의 정보가 기업의 채용 조건에 얼마나 부합하는지 계산한 후, 해당확률을 지원자에게 제공하는 방식의 시스템이다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.351-352
• /
• 2023

컴퓨터공학 분야 개발자를 채용할 때 대다수의 기업에서 일반 면접과는 달리 전공 분야 역량 파악을 위한 컴퓨터공학 기술 면접을 함께 진행한다. 컴퓨터공학 면접자의 기술 면접을 지원하기 위하여 이 논문에서는 컴퓨터공학 핵심 개념에 대한 면접자 답변의 정확도를 코사인 유사도를 이용하여 평가 후 결과를 알려주는 시스템을 제안한다. 제안한 시스템을 이용하면 개발자들의 컴퓨터공학 핵심 개념의 기술 면접 정확도를 향상시킬 수 있을 것으로 기대된다.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.376-376
• /
• 2000

Several algorithmic models have been proposed to estimate software cost and other management parameters. In particular, early prediction of completion time is absolutely essential for proper advance planning and a version of the possible ruin of a project. However, estimation is difficult because of its similarity to export judgment approaches and for its potential as an expert assistant in support of human judgment. Especially, the nature of the Norden/Rayleigh curve used by Putnam, renders it unreliable during the initial phases of the project, in projects involving a fast manpower buildup, as is the case with most software projects. Estimating software development effort is more complexity, because of infrastructure software related to target-machines hardware and process characteristics should be considered in software development for DCS (Distributed Control System). In this paper, we propose software development effort estimation technique using adaptive neural fuzzy inference system. The methods is applied to case-based projects and discussed.

• The Journal of Society for e-Business Studies
• /
• v.24 no.2
• /
• pp.1-14
• /
• 2019

Because of the characteristics of game software, it is important to quickly identify and reflect users' needs into game software after its launch. However, most sites such as the Google Play Store, where users can download games and post reviews, provide only very limited and ambiguous classification categories for game reviews. Therefore, in this paper, we develop an automatic classification system for game reviews that categorizes reviews into categories that are clearer and more useful for game providers. The developed system converts words in reviews into vectors using word2vec, which is a representative word embedding model, and classifies reviews into the most relevant categories by measuring the similarity between those vectors and each category. Especially, in order to choose the best similarity measure that directly affects the classification performance of the system, we have compared the performance of three representative similarity measures, the Euclidean similarity, cosine similarity, and the extended Jaccard similarity, in a real environment. Furthermore, to allow a review to be classified into multiple categories, we use a threshold-based multi-category classification method. Through experiments on real reviews collected from Google Play Store, we have confirmed that the system achieved up to 95% accuracy.

• Industrial Engineering and Management Systems
• /
• v.9 no.3
• /
• pp.275-284
• /
• 2010

Offshore software development (OSD) is international business collaboration. OSD projects often encounter intercultural and inter-linguistic problems disturbing the projects. Business documents are formal media of information and knowledge for OSD. While OSD documents should convey common understanding of the OSD products, the documents may contain unsuitable expressions which draw misunderstanding of the required products and offensive issues for the collaboration. Intercultural and inter-linguistic differences cause mistakes and inappropriate expressions. OSD from Japan to China is the largest in Asia, and Japanese language is often used in OSD documents. Large similarity is found between Japanese and Chinese in their languages, while many differences exist even for the same word. The similarity induces to write unsuitable expressions for both sides of OSD. To introduce risks for OSD projects caused by unsuitable or inappropriate expressions in OSD documents, we propose to apply a proofreading system of Japanese documents for OSD. Japanese consignor uses the system to refine OSD documents written by Japanese engineers for Chinese readers, and Chinese consignee uses it to refine Japanese documents written by Chinese Engineers as derivatives of OSD projects. Effectiveness of applying the proofreading system is discussed for actual projects.

• Journal of KIISE:Software and Applications
• /
• v.27 no.4
• /
• pp.384-392
• /
• 2000

As a software becomes more complicated and large-scaled, it is very important for a software engineer to analyze user's requirements precisely and apply them effectively in the development stage. Due to the growth of the internet, the necessity of requirements elicitation and analysis in distributed environments has also become larger. This paper proposes a requirements elicitation supporting system that offer the basis for effectively analyzing requirements collected in distributed environments. The proposed system automatically categorizes collected requirements sentences into selected subject fields by measuring their similarity using a similarity measurement technique. Therefore, it reduces the difficulties in the initial stage of requirements analysis and it supports rapid and correct requirements analysis. This paper verifies the efficiency of the proposed system in similarity measurement techniques through experiments, and presents a process for requirements specifications elicitation using the embodied system

• The Journal of Korean Institute of Next Generation Computing
• /
• v.14 no.5
• /
• pp.60-70
• /
• 2018

A software defined storage (SDS) is being deployed in cloud environment to allow multiple users to virtualize physical servers, but a solution for optimizing space efficiency with limited physical resources is needed. In the conventional data deduplication system, it is difficult to deduplicate redundant data uploaded to distributed storages. In this paper, we propose a distributed deduplication method using similarity-based clustering and multi-layer bloom filter. Rabin hash is applied to determine the degree of similarity between virtual machine servers and cluster similar virtual machines. Therefore, it improves the performance compared to deduplication efficiency for individual storage nodes. In addition, a multi-layer bloom filter incorporated into the deduplication process to shorten processing time by reducing the number of the false positives. Experimental results show that the proposed method improves the deduplication ratio by 9% compared to deduplication method using IP address based clusters without any difference in processing time.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.374-376
• /
• 2022

Community detection is meaningful research in social network analysis, and many existing studies use graph theory analysis methods to detect communities. This paper proposes a method to detect community by detecting maximal cliques and obtain the high influence cliques by high influence nodes, then merge the cliques with high similarity in social network.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.2
• /
• pp.71-76
• /
• 2015

In similarity join processing, a general technique employs a generation-verification framework, which includes two phases: the first phase generates a set of candidate pairs from a collection of records; and the second phase verifies each candidate pair by computing real similarity. In order to reduce the number of candidate pairs in the verification phase, the median of one record of each candidate pair is used as a filter in this paper to test whether the other record can has the proper number of overlapped tokens. We propose a similarity join algorithm with the median filter, and show that the proposed algorithm has better performance in execution time than recent algorithms without the filter through extensive experiments on real-world datasets.