• Journal of the Korea Society of Computer and Information
• /
• v.26 no.12
• /
• pp.19-27
• /
• 2021

In this paper, we present a method for effectively predicting traffic volume based on vehicle location data that are collected by using LDP (Local Differential Privacy). The proposed solution in this paper consists of two phases: the process of collecting vehicle location data in a privacy-presering manner and the process of predicting traffic volume using the collected location data. In the first phase, the vehicle's location data is collected by using LDP to prevent privacy issues that may arise during the data collection process. LDP adds random noise to the original data when collecting data to prevent the data owner's sensitive information from being exposed to the outside. This allows the collection of vehicle location data, while preserving the driver's privacy. In the second phase, the traffic volume is predicted by applying deep learning techniques to the data collected in the first stage. Experimental results with real data sets demonstrate that the method proposed in this paper can effectively predict the traffic volume using the location data that are collected in a privacy-preserving manner.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.2
• /
• pp.405-416
• /
• 2022

Current AI technology is improving the quality of life by using machine learning based on data. When using machine learning, transmitting distributed data and collecting it in one place goes through a de-identification process because there is a risk of privacy infringement. De-identification data causes information damage and omission, which degrades the performance of the machine learning process and complicates the preprocessing process. Accordingly, Google announced joint learning in 2016, a method of de-identifying data and learning without the process of collecting data into one server. This paper analyzed the effectiveness by comparing the difference between the learning performance of data that went through the de-identification process of K anonymity and differential privacy reproduction data using actual financial data. As a result of the experiment, the accuracy of original data learning was 79% for k=2, 76% for k=5, 52% for k=7, 50% for 𝜖=1, and 82% for 𝜖=0.1, and 86% for Federated learning.

• Journal of Internet Computing and Services
• /
• v.18 no.1
• /
• pp.143-152
• /
• 2017

In order to ensure the right of self-determination of women, most of countries allow women to buy post-coital contraceptive pills or general medical supplies with ease. This study aims to analyze how ordinary people recognize and respond to post-coital contraceptive pills through collecting atypical data by using the keyword 'Contraception', rather than using the existing actual condition survey, such as questionnaire and interview, so that the results have been presented, which may be referred to for establishment of policies.

• Journal of the Korean Society of Tobacco Science
• /
• v.27 no.1 s.53
• /
• pp.120-126
• /
• 2005

The Fishtail Chimney system mounted on 1 channel smoking machine is not appropriate for the routine analysis of sidestream smoke, because of its low repeatability and very long time required for smoke collection. To overcome this inconvenience, we developed a new sidestream smoke collecting apparatus compatible for 8 channel linear smoking machine. An electric motor driven stroke and automatic control system were adopted in this device to maximize convenience and efficiency of its operation. Also, we carried out the international collaborative study on monitoring sidestream smoke analysis to test the performance of this system. From the statistical analysis of the data obtained in our laboratory and other participating labs, it has been indicated that the newly developed sidestream smoke collection apparatus could be applicable to the routine analysis of sidestream smoke.

• Journal of Korea Multimedia Society
• /
• v.15 no.1
• /
• pp.108-114
• /
• 2012

Government-related organizations and institutions are stepping up their efforts to establish information system and service for disaster prevention because of the increasing occurrence of disaster. Therefore, they are collecting numerous disaster data using various way such as using mobile device or disaster history document. However, these method requires large amount of time and effort. Moreover, it is difficult to connects with another system because previous ways fall short of standard and connectivity. Therefore, this paper focused on collecting various disaster information using smartphone application and then complement the drawbacks of previous system.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.9
• /
• pp.31-36
• /
• 2020

This research study designed a location image collecting technology. It provides the exact location information of an image which is not given in the photo to the user. Deep learning technology analysis and collects the images. The purpose of this service system is to provide the exact place name, location and the various information of the place such as nearby recommended attractions when the user upload the image photo to the service system. Suggested system has a deep learning model that has a size of 25.3MB, and the model repeats the learning process 50 times with a total of 15,266 data, performing 93.75% of the final accuracy. This system can also be linked with various services potentially for further development.

• Journal of the Korean housing association
• /
• v.13 no.3
• /
• pp.1-9
• /
• 2002

Desolation of the earth due to environmental pollution is rising as a world wide problem and concern. At this point we need to look into the problem and set up a direction for the future. In order to reveal the change of garbage problems in our county's civil life, a researcher analyzed 369 garbage related articles from the first edition of Dong A Ilbo up to 1990. The following is the result of data from garbage related articles. It is organized by age and era(10 years). 1) Number of articles by year roses in 1921 after first publication of garbage problem article. In the 1930s, the number of articles drastically increased in 1937. From then on, the number of articles declined until early 1970s but roses again from 1978. 2) Yearly change in articles was a mere 1.2 columns in between 1920 to 1960. In the 1970's, relative importance increased and over 5 columns were published. Articles rose in the 1980s with over 3.4 and 5 columns. 3) The contents of the articles can be classified into cleaning problems, collecting and transporting, expenses, and recycling. Garbage disposal problems continued until the 1970s. Regarding garbage collecting problems, form of collecting container and location was discussed. Laws were revised after garbage disposal areas were discussed in the 1920s. Expenses were levied from the 1930s and rising cost and double charge problems were subjected. Garbage recycling began in the 1920s and continued until 1900s.

• Journal of Korean Library and Information Science Society
• /
• v.15
• /
• pp.79-111
• /
• 1988

The purpose of this study has its meaning to indicate the direction on collection and preservation of national literature which is one of the must important functions of the Central National Library. The Central National Library is, however, a representative library of our country and collect every kind of literature and to meet the requests of its users, the present situation of The Central National Library can't be performed sufficiently on these actions. According to studies of this paper, it have suggested the following five methods as a method of collecting national literature. First, the method by registering copyright endowing the number of copyright like ISBN. Second, the method a n.0, pplied by revising and su n.0, pplementing present legal deposit system. Thirdly, the method that the central one institution secure national budget collect literature of nation i.e., central intensive collection one. Fouthly , method of collecting literature by partial charge through local library networks. Fifthly, method by subject intensive collecting. As the preserving method of national literature, this research has indicated the following two ways. First, to keep the literatures forever, the method of The Central National Library keeps records as a limited volume. Second, The method of dispersing records as the local libraries. To put these methods into practice, it must be preceded that not only national helps, budget secures are needed but special committee must be organized to keep and preserve national literatures and material range also be extended and bibliographies for information data issuing must be worked out.

• Journal of the Korean Solar Energy Society
• /
• v.37 no.2
• /
• pp.67-75
• /
• 2017

We have investigated the operating characteristics of $1,600m^2$ large-scale solar thermal system installed in an eco-friendly energy town in Chungbuk Innovation City. The operation criteria of the collecting pump and storage pump were different from the existing standard, and it was confirmed that each pump works well according to the changed criteria. Based on the data of the representative day, the daily collecting heat (efficiency) and the production (storing) heat (efficiency) were estimated. It was confirmed that the daily collecting heat (efficiency) of the flat plate type was higher than that of the evacuated tube type, but the useful heat production was more in evacuated tube type collector.

• The Journal of the Korea Contents Association
• /
• v.1 no.1
• /
• pp.100-108
• /
• 2001

To develope more competitive products, lots of attentions are paid to the study of user participation in the process of product design. In this circumstance, the user participation at a usability testing phase is relatively active. However, the usability testing in the controlled laboratory has some drawbacks. for stance, It needs a lot of money, efforts, and time. Most of all, it is difficult to collect a vast range of data and gain a fast feedback Recently, to overcome these difficulties mentioned above, international usability testing has been applied. Especially, usability testing Contents through Internet is considered most effective one. Because it has a lot of merits such as easiness of collecting remote user, simplicity of collecting data, cost effectiveness and so on. With these merits, this study takes advantage of using a WWW to carry out usability test and to collect remote usability data. And a website was development for posting computer simulated product so that the remote users can test its usability through internet.