• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권7호
• /
• pp.3497-3515
• /
• 2018

Differential privacy has broadly applied to statistical analysis, and its mainly objective is to ensure the tradeoff between the utility of noise data and the privacy preserving of individual's sensitive information. However, an individual could not achieve expected data utility under differential privacy mechanisms, since the adding noise is random. To this end, we proposed an adaptive Gaussian mechanism based on expected data utility under conditional filtering noise. Firstly, this paper made conditional filtering for Gaussian mechanism noise. Secondly, we defined the expected data utility according to the absolute value of relative error. Finally, we presented an adaptive Gaussian mechanism by combining expected data utility with conditional filtering noise. Through comparative analysis, the adaptive Gaussian mechanism satisfies differential privacy and achieves expected data utility for giving any privacy budget. Furthermore, our scheme is easy extend to engineering implementation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권5호
• /
• pp.2778-2791
• /
• 2017

In the age of big data, distributed data providers need to ensure the privacy, while data analysts need to mine the value of data. Therefore, how to find the privacy-utility tradeoff has become a research hotspot. Besides, the adversary may have the background knowledge of the data source. Therefore, it is significant to solve the privacy-utility tradeoff problem in the distributed environment with side information. This paper proposes a distributed privacy-utility tradeoff method using distributed lossy source coding with side information, and quantitatively gives the privacy-utility tradeoff region and Rate-Distortion-Leakage region. Four results are shown in the simulation analysis. The first result is that both the source rate and the privacy leakage decrease with the increase of source distortion. The second result is that the finer relevance between the public data and private data of source, the finer perturbation of source needed to get the same privacy protection. The third result is that the greater the variance of the data source, the slighter distortion is chosen to ensure more data utility. The fourth result is that under the same privacy restriction, the slighter the variance of the side information, the less distortion of data source is chosen to ensure more data utility. Finally, the provided method is compared with current ones from five aspects to show the advantage of our method.

• ETRI Journal
• /
• 제32권5호
• /
• pp.676-686
• /
• 2010

Mining sequential patterns is an important research issue in data mining and knowledge discovery with broad applications. However, the existing sequential pattern mining approaches consider only binary frequency values of items in sequences and equal importance/significance values of distinct items. Therefore, they are not applicable to actually represent many real-world scenarios. In this paper, we propose a novel framework for mining high-utility sequential patterns for more real-life applicable information extraction from sequence databases with non-binary frequency values of items in sequences and different importance/significance values for distinct items. Moreover, for mining high-utility sequential patterns, we propose two new algorithms: UtilityLevel is a high-utility sequential pattern mining with a level-wise candidate generation approach, and UtilitySpan is a high-utility sequential pattern mining with a pattern growth approach. Extensive performance analyses show that our algorithms are very efficient and scalable for mining high-utility sequential patterns.

• Communications for Statistical Applications and Methods
• /
• 제16권1호
• /
• pp.1-11
• /
• 2009

마이크로데이터를 이용자에게 제공하면 레코드 단위의 데이터가 노출되고 응답자의 정보 노출위험이 불가피하다. 통계적 노출조절기법은 통계데이터 제공시 노출위험을 줄이면서 데이터 유용성을 높이기 위한 통계적 기법이다. 본 논문에서는 노출과 노출위험, 그리고 통계적 노출조절기법을 고찰하였고 데이터 유용성과 연관하여 노출조절기법 선택 전략을 살펴보았으며, '위험-유용성 경계 지도' 방법의 예를 알아보았다. 마지막으로 마이크로데이터를 이용자에게 제공할 때 단계별로 검토할 사항을 알아보았다.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제7권2호
• /
• pp.51-62
• /
• 2018

높은 유틸리티 순차 패턴 탐사는 데이터 마이닝에서 중요한 연구 주제로 간주되고 있다. 이 주제에 대해 몇 개의 알고리즘들이 제안되었지만, 그것들은 높은 유틸리티 순차 패턴 탐사의 탐색 공간이 커지는 문제에 부딪히게 된다. 한 시퀀스의 더 엄격한 유틸리티 상한 값은 탐색 공간에서 초기에 유망하지 않은 패턴들을 더 가지치기할 수 있다. 본 논문에서 새로운 유틸리티 상한 값을 제안하는데, 그것은 한 시퀀스와 그 자손 시퀀스들의 최대 예상 유틸리티인 sequence expected utility (SEU)이다. 높은 유틸리티 순차 패턴들을 탐사하는데 필수적인 정보를 유지하기 위해 각 패턴에 대한 시퀀스 유틸리티 리스트를 새로운 자료구조로 사용한다. SEU를 활용하여 높은 유틸리티 순차 패턴들을 찾아내는 알고리즘인 High Sequence Utility List-Span (HSUL-Span)을 제안한다. 서로 다른 영역의 합성 데이터세트와 실제 데이터세트에 대한 실험 결과는 HSUL-Span이 상당히 적은 수의 후보 패턴들을 생성하고 실행 시간 면에서 다른 알고리즘들보다 우수한 것을 보여준다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권3호
• /
• pp.1028-1046
• /
• 2022

Genome-wide association studies (GWAS) aim to find the significant genetic variants for common complex disease. However, genotype data has privacy information such as disease status and identity, which make data sharing and research difficult. Differential privacy is widely used in the privacy protection of data sharing. The current differential privacy approach in GWAS pays no attention to raw data but to statistical data, and doesn't achieve equilibrium between utility and privacy, so that data sharing is hindered and it hampers the development of genomics. To share data more securely, we propose a differential privacy preserving approach of data sharing for GWAS, and achieve the equilibrium between privacy and data utility. Firstly, a reasonable disturbance interval for the genotype is calculated based on the expected utility. Secondly, based on the interval, we get the Nash equilibrium point between utility and privacy. Finally, based on the equilibrium point, the original genotype matrix is perturbed with differential privacy, and the corresponding random genotype matrix is obtained. We theoretically and experimentally show that the method satisfies expected privacy protection and utility. This method provides engineering guidance for protecting GWAS data privacy.

• 기술사
• /
• 제33권4호
• /
• pp.27-32
• /
• 2000

The automatic utility program in electrical facilities has specially developed to fulfill the needs of electric CAD designers . Designers had separately managed the designing factors such as design, estimates and calculation sheets . However, this automatic utility program produces calculation sheets and volume reports simultaneously while designed. The program also accumulates all data automatically in database in order to be utilized as the statistics and the design data for later project management. Moreover, it is easy for new and inexperienced users to access by using the standard electric symbol libraries and utility modules.

• 산경연구논집
• /
• 제10권1호
• /
• pp.39-49
• /
• 2019

Purpose - Previous studies examined effects of sharing economy in the fields such as accommodation and automobile sector, while there are lack of researches in the field of skill-sharing economy. By classifying skill-sharing into general and special skill-sharing, this study explored effects of variables such as transaction utility, social utility, sustainability utility, emotional utility, economic utility, and trust utility, on attitudes, intention, satisfaction, and loyalty of demand (i.e., customers) and supply (i.e., providers) sides, potential, and actual customers. Research design, data, and methodology - Data were collected via both online and offline surveys. This study applied factor analysis and multiple regression analysis for findings. Results - Results show that utilities for general suppliers' skill-sharing are significant than other cases. Among utilities, this study found that trust utility shows significant for the cases of special customers', general suppliers' and special suppliers' potential skill-sharing. The results implies that trust is crucial in the transaction of the sharing economy. Conclusions - Enhanced managerial systems help resolve issues on the sharing economy. This study provides implications what are positive effects of skill-sharing economy and recommends proper establishment of the sharing economy.

• Asia Marketing Journal
• /
• 제16권2호
• /
• pp.15-38
• /
• 2014

This paper explores the influence of pursuing goals on customer channel preference in Chinese rural market. With the rapid change in distribution channels and increase in multi-channels, it is necessary to understand the preference for channel choice as well as product choice. This study empirically validated the conceptual framework of the relationship between the pursuing goals and customer channel choice proposed by Balasubramanian, Raghunathan, and Mahajan (2005). Based on the survey data of 232 fertilizer customers in Chinese rural market, this study explores how economic, social, and psychological pursuing goals can impact customer channel preference by mediating variables of product utility and process utility. The results indicate that pursuing goals positively related with product utility and process utility, and product / process utility can mediate the relationship between pursuing goals and customer channel preference positively. Consequently, we can conclude that customers' economic-social-psychological pursuing goals can directly influence customer channel preference via their purchase process utility and product utility. This result also implies that product utility is effective on process utility during consumer's buying decision making, and process utility and product utility are not mutually independent. Therefore, purchase process utility is a "latent driving force" on customer's channel choice decision.

• 한국컴퓨터정보학회논문지
• /
• 제29권6호
• /
• pp.69-76
• /
• 2024

최근 센서 기술과 모바일 기술의 급속한 발전으로 인하여 사용자 위치 데이터 수집이 가능해졌다. 사용자 위치 정보는 다양한 산업에서 중요한 자산으로 활용되고 있으며, 그 결과 위치 데이터의 수집 및 공유에 대한 수요가 증가하고 있다. 그러나 위치 정보에는 사용자의 민감한 데이터가 포함되어 있으므로, 무분별한 수집은 프라이버시 침해 문제를 일으킬 수 있다. 최근에는 차분 프라이버시의 한 방법으로 Geo-Indistinguishability (Geo-I)가 위치 데이터의 프라이버시 보호에 활용되고 있다. Geo-I는 사용자의 위치를 효과적으로 보호할 수 있는 강력한 방법을 제공하지만, 데이터 변조로 인해 수집된 위치 데이터의 유용성이 감소하는 문제가 있다. 따라서, 본 논문에서는 Geo-I 기술을 활용해 사용자 위치 데이터를 효과적으로 수집하면서 데이터의 유용성을 유지할 수 있는 방법을 제안한다. 제안 기법은 사용자의 사전 분포 정보를 활용하여 정확한 위치 정보를 보호하면서도 데이터의 전체적인 유용성을 향상시킨다. 실데이터를 이용한 실험 결과는 제안 기법이 기존 방법보다 수집된 데이터의 유용성을 상당히 향상시킬 수 있음을 보여준다.