• The Journal of Bigdata
• /
• v.7 no.2
• /
• pp.235-244
• /
• 2022

The rental history data of public bicycles in Seoul were analyzed to examine how pandemic phenomena such as COVID-19 caused changes in people's micro mobility. Data for 2019 and 2021 were compared and analyzed by dividing them before and after COVID-19. Data were collected from public data portal sites, and data marts were created for in-depth analysis. In order to compare the changes in the two periods, the riding direction type dimension and the rental station type dimension were added, and the derived variables (rotation rate per unit, riding speed) were newly created. There is no significant difference in the average rental time before and after COVID-19, but the average rental distance and average usage speed decreased. Even in the mobility of Ttareungi, you can see the slow rhythm of daily life. On weekdays, the usage rate was the highest during commuting hours even before COVID-19, but it increased rapidly after COVID-19. It can be interpreted that people who are concerned about infection prefer Ttareungi to village buses as a means of micro-mobility. The results of data mart-based visualization and analysis proposed in this study will be able to provide insight into public bicycle operation and policy development. In future studies, it is necessary to combine SNS data such as Twitter and Instagram with public bicycle rental history data. It is expected that the value of related research can be improved by examining the behavior of bike users in various places.

• Journal of Cadastre & Land InformatiX
• /
• v.46 no.2
• /
• pp.269-281
• /
• 2016

The process of spatial big data, such as social media, is being paid more attention in the field of spatial information in recent years. This study, as an example of spatial big data analysis, analyzed the spatial and temporal distribution of Tweet data based on the location and time information. In addition, the characteristics of its spatial pattern by times were identified. Tweet data in Busan city are collected, processed, and analyzed to identify the characteristics of the temporal and spatial pattern. Then, the results of Tweet data analysis were compared with the characteristics of the land type. This study found that spatial pattern of tweeting in the city was associated with given time periods such as daytime and nighttime in both weekdays and weekends. The spatial distribution patterns of individual time periods were compared with the characteristics of the land for the spatially concentrated area. The results of this study showed that tweeted data would be related to different spatial distribution depending on the time, which potentially reflects the daily pattern and characteristics of the land type of urban area to some extent. This study presented the possible incorporation of social media data, e. g. Tweet data, into the field of spatial information. It is expected that there will be more advantage to use a variety of social media data in areas such as land planning and urban planning.

• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.34 no.3
• /
• pp.129-138
• /
• 2018

The purpose of this study is to analyze the daily living area of the elderly using the vast amount of travel route data collected through smart phones. In order to analyze the utilization status of the elderly into the visiting area and the living area, the subway station influence area was typed based on the number and ratio of the elderly visiting and the elderly living there. The characteristics of the elderly visiting area and the living area of the subway station area were derived by analyzing the walking route data for the three types of subway station influence areas where the elderly visit and live. First, we derive the range of visiting area and living area of the elderly near the subway station. Second, we derive the characteristic of moving distance which causes the linked walking of the elderly. Third, destination distribution and facility utilization are influenced by the subject of use, movement pattern, and facility awareness.

• Journal of the Korea Convergence Society
• /
• v.13 no.3
• /
• pp.203-216
• /
• 2022

In the recent business environment, purchase patterns are changing around the influence of COVID-19 and the online market. This study analyzed cluster and correlation analysis based on purchase and product information. The cluster analysis of new methods was attempted by creating customer, product, and cross-bonding clusters. The cross-bonding cluster analysis was performed based on the results of each cluster analysis. As a result of the correlation analysis, it was analyzed that more association rules were derived from a cross-bonding cluster, and the overlap rate was less. The cross-bonding cluster was found to be highly efficient. The cross-bonding cluster is the most suitable model for recommending products according to customer needs. The cross-bonding cluster model can save time and provide useful information to consumers. It is expected to bring positive effects such as increasing sales for the company.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.2
• /
• pp.58-71
• /
• 2021

The number of elderly people worldwide is rapidly increasing and the mobility handicapped suffering from inconvenient public transportation service is also increasing. In Korea and abroad, various policies are being implemented to provide high-quality transportation services for the mobility handicapped, and budget support and investment related to mobility facilities are being expanded. The mobility handicapped spends more time for transit transfer than normal users and their satisfaction with transit service is also lower. There exist transfer inconvenience points of the mobility handicapped due to various factors such as long transfer distances, absence of transportation facilities like elevators, escalators, etc. The purpose of this study is to find transfer inconvenience points for convenient transit transfer of the mobility handicapped using Smart card Big data. This study process traffic card transaction data and construct transfer travel data by user groups using smart card big data and analysis of the transfer characteristics for each user group ; normal, children, elderly, etc. Finally, find transfer inconveniences points by comparing transfer patterns between normal users and the mobility handicapped. This study is significant in that it can find transfer inconvenience points for convenient transit transfer of the mobility handicapped using Smart card Big data. In addition, it can be applicated of Smart card Big data for developing public transportation polices in the future. It is expected that the result of this study be used to improve the accessibility of transit transportation for mobility handicapped.

• Spatial Information Research
• /
• v.23 no.2
• /
• pp.69-81
• /
• 2015

If one can infer the residential area of SNS users by analyzing the SNS big data, it can be an alternative by replacing the spatial big data researches which result from the location sparsity and ecological error. In this study, we developed the way of utilizing the daily life activity pattern, which can be found from timeline data of tweet users, to infer the residential areas of tweet users. We recognized the daily life activity pattern of tweet users from user's movement pattern and the regional cognition words that users text in tweet. The models based on user's movement and text are named as the daily movement pattern model and the daily activity field model, respectively. And then we selected the variables which are going to be utilized in each model. We defined the dependent variables as 0, if the residential areas that users tweet mainly are their home location(HL) and as 1, vice versa. According to our results, performed by the discriminant analysis, the hit ratio of the two models was 67.5%, 57.5% respectively. We tested both models by using the timeline data of the stress-related tweets. As a result, we inferred the residential areas of 5,301 users out of 48,235 users and could obtain 9,606 stress-related tweets with residential area. The results shows about 44 times increase by comparing to the geo-tagged tweets counts. We think that the methodology we have used in this study can be used not only to secure more location data in the study of SNS big data, but also to link the SNS big data with regional statistics in order to analyze the regional phenomenon.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.4
• /
• pp.780-786
• /
• 2015

Social media, such as Social Network Service include a lot of spontaneous opinions from customers, so recent companies collect and analyze information about customer feedback by using the system that analyzes Big Data on social media in order to efficiently operate businesses. However, it is difficult to analyze data collected from online sites accurately with existing morpheme analyzer because those data have spacing errors and spelling errors. In addition, many online sentences are short and do not include enough meanings which will be selected, so established meaning selection methods, such as mutual information, chi-square statistic are not able to practice Emotional Classification. In order to solve such problems, this paper suggests a module that can revise the meanings by using initial consonants/vowels and phase pattern dictionary and meaning selection method that uses priority of word class in a sentence. On the basis of word class extracted by morpheme analyzer, these new mechanisms would separate and analyze predicate and substantive, establish properties Database which is subordinate to relevant word class, and extract positive/negative emotions by using accumulated properties Database.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.9
• /
• pp.53-62
• /
• 2020

Product recommendation services that have been researched recently are only recommended through the customer's product purchase history. In this paper, we propose the digital signage service through customers' behavior pattern analysis that is recommending through not only purchase history, but also behavior pattern that customers take when choosing products. This service analyzes customer behavior patterns and extracts interests about products that are of practical interest. The service is learning extracted interest rate and customers' purchase history through the Wide & Deep model. Based on this learning method, the sparse vector of other products is predicted through the MF(Matrix Factorization). After derive the ranking of predicted product interest rate, this service uses the indoor signage that can interact with customers to expose the suitable advertisements. Through this proposed service, not only online, but also in an offline environment, it would be possible to grasp customers' interest information. Also, it will create a satisfactory purchasing environment by providing suitable advertisements to customers, not advertisements that advertisers randomly expose.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.10
• /
• pp.159-165
• /
• 2019

About 58% of fires are electric fires. In this study, we analyzed the factors of fire caused by electricity and studied the system that can prevent fire in advance. In order to prevent disasters, basically, various electrical IoT sensors are needed to detect fire signs. Each of these sensors continuously receives a lot of situation information and sends it to the main system. The collected big data continuously checks whether the disaster is over the threshold that can cause disaster through pattern analysis, and can check whether there is any problem by comparing the data. In the event of a threshold, alarms are signaled and problems are reported. This prevents fire by preventing electrical problems such as overcurrent and leakage current.

• Journal of KIISE
• /
• v.45 no.3
• /
• pp.280-287
• /
• 2018

Recently, the use of a recommendation system and tensor data analysis, which has high-dimensional data, is increasing, as they allow us to analyze the tensor and extract potential elements and patterns. However, due to the large size and complexity of the tensor, it needs to be decomposed in order to analyze the tensor data. While several tools are used for tensor decomposition such as rTensor, pyTensor, and MATLAB, since such tools run on a single machine, they are unable to handle large data. Also, while distributed tensor decomposition tools based on Hadoop can handle a scalable tensor, its computing speed is too slow. In this paper, we propose S-PARAFAC, which is a tensor decomposition tool based on Apache Spark, in distributed in-memory environments. We converted the PARAFAC algorithm into an Apache Spark version that enables rapid processing of tensor data. We also compared the performance of the Hadoop based tensor tool and S-PARAFAC. The result showed that S-PARAFAC is approximately 4~25 times faster than the Hadoop based tensor tool.