• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.538-561
• /
• 2020

Recommender Systems (RecSys) have a major role in e-commerce for recommending products, which they may like for every user and thus improve their business aspects. Although many types of RecSyss are there in the research field, the state of the art RecSys has focused on finding the user similarity based on sequence (e.g. purchase history, movie-watching history) analyzing and prediction techniques like Recurrent Neural Network in Deep learning. That is RecSys has considered as a sequence prediction problem. However, evaluation of similarities among the customers is challenging while considering temporal aspects, context and multi-component ratings of the item-records in the customer sequences. For addressing this issue, we are proposing a Deep Learning based model which learns customer similarity directly from the sequence to sequence similarity as well as item to item similarity by considering all features of the item, contexts, and rating components using Dynamic Temporal Warping(DTW) distance measure for dynamic temporal matching and 2D-GRU (Two Dimensional-Gated Recurrent Unit) architecture. This will overcome the limitation of non-linearity in the time dimension while measuring the similarity, and the find patterns more accurately and speedily from temporal and spatial contexts. Experiment on the real world movie data set LDOS-CoMoDa demonstrates the efficacy and promising utility of the proposed personalized RecSys architecture.

• Asian Journal of Business Environment
• /
• v.9 no.2
• /
• pp.5-15
• /
• 2019

Purpose - The present study endeavours to investigate the impact of intellectual capital (IC) and its components on corporate sustainable growth in India. In addition, this study aims to find out the most influential component of IC on corporate sustainable growth in India. Research design, data, and methodology - A sample size of top 139 NSE listed non-financial companies over a time period of five years has been used in this monograph. The impact of intellectual capital and its components on corporate sustainable growth has been examined using the longitudinal data analysis technique. Results - The findings of this study bring to light that intellectual capital (IC) as measured by the M-VAIC model demonstrates a significant impact on corporate sustainable growth. Considerably, the results also reveal that almost all the explanatory variables viz. Physical Capital, Relational Capital, Innovation Capital, and Process Capital exercise notable influence in explaining corporate sustainable growth. Moreover, the results demonstrate Innovation Capital (controlling the effect of Physical Capital) represents the most influential component of IC on corporate sustainable growth. Conclusions - The research findings show that in the Indian context, both physical capital, and IC (overall), as well as its components, play a crucial role to explain corporate sustainable growth.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.30 no.9_10 s.157
• /
• pp.1455-1463
• /
• 2006

The purpose of this study was to examine the advertisement effects of mobile fashion advertisements, specifically focusing on how the mobile fashion advertisement effects work according to advertisement types and categories. Two hundred female college students participated in this study. For data analysis, descriptive statistics, factor analysis, and t-test were used for this study. As the results, first, advertisement attitudes were classed into three factors such as cognitive factor emotional factor, and behavioral factor. Second, regarding the effect of advertisement types, pull advertisement type had higher advertisement attitudes, and higher purchasing intention than push advertisement type. There was not significant in brand attitudes between pull advertisement and push advertisement. Third, for the effects of advertisement categories, clothing advertisement had higher cognitive factor and behavioral factor, and higher purchasing intention than accessory advertisement. There were not significant in emotional factor and brand attitude between clothing and accessory advertisements. Based on these results, M-commerce fashion advertisement marketing strategies would be suggested.

• Annual Conference of KIPS
• /
• 2017.11a
• /
• pp.306-309
• /
• 2017

소프트웨어의 보안에 대한 중요성이 점차 높아짐에 따라, 소스코드 기반의 소프트웨어의 보안약점 분석 기법에서 더 나아가 소스 코드가 존재하지 않는 바이너리 파일을 대상으로 분석을 수행하는 연구가 진행되고 있다. 왜냐하면 소프트웨어 개발의 복잡성 증가에 따른 서드파티 라이브러리 활용과 레거시 코드의 관리 부재, 임베디드 소프트웨어의 특성 등으로 인해 소스 코드가 존재하지 않는 바이너리 코드의 사용이 늘어나고 있기 때문이다. 따라서 최근 바이너리 코드에 내제된 보안약점을 분석하기 위해서 중간코드를 이용하여 정적분석을 수행하는 다양한 연구가 진행되고 있다. 중간언어를 사용함으로 실행환경에 따라 달라지는 바이너리 코드가 중간언어로만 변환이 된다면 동일한 형태의 보안약점 분석기술을 통해 효과적인 수행이 가능하다. 본 논문에서는 이러한 바이너리 코드로부터 중간언어로 변환시 컴파일 과정에서 상실된 복합 자료형을 재구성하기 위해 Word2vec 딥러닝 기법을 이용한 추론기법을 제안한다.

• Annual Conference of KIPS
• /
• 2017.04a
• /
• pp.276-279
• /
• 2017

오늘날 사회 전반적인 부분에서 소프트웨어의 비중은 지속적으로 증가하고 있다. 또한 소프트웨어는 점차 대규모화되고 있고 동시에 개인의 중요한 정보 등을 다루는 경우도 매우 늘어나고 있기에 소프트웨어의 보안성 검증은 매주 중요한 문제이다. 그러나 소스코드가 존재하지 않는 라이브러리의 경우 보안성 검증은 매우 어려운 문제로, 이를 해결하기 위해 바이너리 내에 존재하는 보안약점을 검사하기 위한 기술의 개발이 매우 요구되는 상황이며, 이를 위해 중간언어를 활용하여 보안약점을 분석하는 기술이 활발히 논의되고 있다. 본 논문에서는 바이너리 코드내에 존재하는 보안약점을 효과적으로 분석하기 위해서 바이너리 코드로부터 보안약점 분석에 효과적인 중간언어로 변환하는 시스템을 제안한다.

• Annual Conference of KIPS
• /
• 2017.04a
• /
• pp.280-282
• /
• 2017

최근 소프트웨어에 내장된 취약점 분석을 위한 자동화 도구 개발 연구가 각 분야에서 활발히 연구되고 있다. 그 중 바이너리 코드를 대상으로 바로 보안취약점을 분석하는 방법이 아닌 중간언어를 활용하여 분석하는 방법이 대두되고 있으며 이를 위한 다양한 중간언어가 제시되었다. 그 중 하이레벨 언어 수준의 내용의 기술이 가능하며 명령어 자체적으로 자료형을 유지하여 보안 취약점 분석에 효과적인 언어로 SIL 중간언어가 재조명 받고 있다. 따라서 본 논문에서는 이룰 위해서 x86/64 기반 어셈블리어를 SIL 로 효과적으로 변환하며 프로그램의 의미가 변하지 않는 것을 확인하기 위해서 프로그램의 제어흐름을 시각화하는 기능을 가진 시스템을 제안한다.

• Annual Conference of KIPS
• /
• 2017.04a
• /
• pp.283-286
• /
• 2017

소프트웨어 내제되어 있는 보안약점과 보안취약점으로 인해 사회적으로 많이 비용이 발생함에 따라 안전한 소프트웨어를 개발하고자하는 요구가 증가하고 있다. 최근 바이너리 코드에 내제된 보안약점을 분석하기 위해서 중간코드를 이용하여 정적분석을 수행하는 다양한 연구가 진행되고 있다. 중간 언어를 사용함으로 실행환경에 따라 달라지는 바이너리 코드가 중간언어로만 변환이 된다면 동일한 형태의 보안약점 분석기술을 통해 효과적인 수행이 가능하다. 이 기술의 핵심은 바이너리 코드로부터 얼마나 코드내의 자료형 및 변수를 재구성하여 중간언어로 변환하는 것이다. 본 논문에서는 이와 같은 바이너리 코드로부터 보안약점 분석을 위한 중간언어 변환시 효과적으로 자료형 및 변수 등에 관한 정보를 재구성하는 기법들에 대해서 조사 분석하였다.

• Communications of the Korean Mathematical Society
• /
• v.35 no.3
• /
• pp.855-866
• /
• 2020

For two essentially bounded Lebesgue measurable functions 𝜙 and ξ on unit circle 𝕋, we attempt to study properties of operators $S^k_{\mathcal{M}({\phi},{\xi})=S^k_{T_{\phi}}+S^k_{H_{\xi}}$ on H²(𝕋) (k ≥ 2), where $S^k_{T_{\phi}}$ is a k^th-order slant Toeplitz operator with symbol 𝜙 and $S^k_{H_{\xi}}$ is a k^th-order slant Hankel operator with symbol ξ. The spectral properties of operators S^k_{𝓜(𝜙,𝜙)} (or simply S^k_𝓜(𝜙)) are investigated on H²(𝕋). More precisely, it is proved that for k = 2, the Coburn's type theorem holds for S^k_𝓜(𝜙). The conditions under which operators S^k_𝓜(𝜙) commute are also explored.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2006.05a
• /
• pp.611-612
• /
• 2006

Many data mining techniques have been proved useful in revealing important patterns from large data sets. Especially, data mining techniques play an important role in a customer data analysis in a financial industry and an electronic commerce. Also, there are many data mining related research papers in a semiconductor industry and an automotive industry. In addition, data mining techniques are applied to the bioinformatics area. To satisfy customers' various requirements, each industry should develop new processes with more accurate production criteria. Also, they spend more money to guarantee their products' quality. In this manner, we apply data mining techniques to the production-related data such as a test data, a field claim data, and POP (point of production) data in the automotive parts industry. Data collection and transformation techniques should be applied to enhance the analysis results. Also, we classify various types of manufacturing processes and proposed an analysis scheme according to the type of manufacturing process. As a result, we could find inter- or intra-process relationships and critical features to monitor the current status of the each process. Finally, it helps an industry to raise their profit and reduce their failure cost.

• Journal of Information Technology Services
• /
• v.12 no.2
• /
• pp.215-229
• /
• 2013

The purpose of this research is to identify what factors influence a customer satisfaction and re-purchasing intention and to identify if customer's Intentions are different between a mobile shopping mall and Internet Shopping mall. To perform empirical analysis for the mobile shopping mall, this research reapplied the factors of Parasuraman et al.[77] in a Internet shopping mall, including reliability, reactivity, tangibility, and this research also applied the factors of a mobile properties, including ubiquity, localization, instant connectivity. The empirical results of this research indicate that all hypotheses in our model are significant; However, the factors of a mobile properties negatively. The results of a analysis indicate that the mobile properties in a mobile shopping mall are not significant yet. and customer's recognition in both mobile shopping mall and Internet shopping mall are the similarity. In Conclusion, with the rapid growth of the Mobile Shopping mall market, many mobile shopping mall researches based on customer's Intentions must be published. Therefore, this research will be the foundation of these researches.