• Asia pacific journal of information systems
• /
• v.29 no.1
• /
• pp.35-49
• /
• 2019

The paper attempts to document the application of relevant Machine Learning (ML) models on Yelp (a crowd-sourced local business review and social networking site) dataset to analyze, predict and recommend business. Strategically using two cloud platforms to minimize the effort and time required for this project. Seven machine learning algorithms in Azure ML of which four algorithms are implemented in Databricks Spark ML. The analyzed Yelp business dataset contained 70 business attributes for more than 350,000 registered business. Additionally, review tips and likes from 500,000 users have been processed for the project. A Recommendation Model is built to provide Yelp users with recommendations for business categories based on their previous business ratings, as well as the business ratings of other users. Classification Model is implemented to predict the popularity of the business as defining the popular business to have stars greater than 3 and unpopular business to have stars less than 3. Text Analysis model is developed by comparing two algorithms, uni-gram feature extraction and n-feature extraction in Azure ML studio and logistic regression model in Spark. Comparative conclusions have been made related to efficiency of Spark ML and Azure ML for these models.

• Journal of The Korea Institute of Healthcare Architecture
• /
• v.11 no.2
• /
• pp.73-81
• /
• 2005

The disabled has remarkable difficulties to participate social activities and those, that block them up from access to public facilities and the comfortable habitation so they should get help from others, are mainly made by architectural facts. Buildings without impediment which consider the disabled would be the things responding to the needs of the times. If the disabled would be convenient to use facilities, there should be no difficulties to normal people. A first began to examine into the role of the architecture. And to establish radical standards for the disabled to use cultural and assembly facilities through scrutinizing facilities to get access for the disabled and movement circulations in the cultural facilities should be the conclusion. This study which is a kind of fundamental study to construct cultural facilities without obstacles for the disabled began from consideration for the problem flow line of the disabled in cultural facilities and analyzed flow lines for them to use, access, and evacuate from those which are main facilities in the region. Though, evacuation rules in cultural and assembly facilities are recommendatory in existing laws for convenience of the disabled, the congestion of the crowd coming out after performances impedes safe flows of both the disabled and crowds. Further, in case of evacuation, there would be more serious problems. Therefore, consideration of reinforcement for existing laws for convenience of the disabled is needed.

• The Journal of the Korea Contents Association
• /
• v.20 no.11
• /
• pp.110-118
• /
• 2020

Social media data serves as a proxy indicator to understand the problems and the future of public opinion in Korean society. This research used 109,015 news data from 2016 to 2018 to analyze the sensitivity of the elderly and employment in Korean society, and explored the possibility of expanding the labor force in Korean society, which is facing a cliff between the elderly and the population. Topic keywords for employment of the elderly include "elderly*employment", "elderly*employment", and "elderly*wage". As a result of the analysis, positive sensitivity prevails for most of the period, and it is possible to expand the working-age population. Positive feelings about expanding employment opportunities for the elderly and negative feelings about low wages have brought to light the reality of the elderly who are still poor despite their work. In this study, social big data was used to analyze the perceptions and sensibilities of Korean society related to the elderly and employment through hierarchical crowd analysis and related text mining analysis.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.9
• /
• pp.11-17
• /
• 2012

Capacity is a traditional issue in wireless network and is closely related to the service quality of network providers, therefore it is a main interest of them. Especially, when a big match of sport game or a special event are held in a place and a large crowd temporarily gathers, a need of big transmission capacity greater than usual usage in the area is required, where network providers need a scheme to temporarily expand network capacity in any specified area. This paper focuses on temporary expansion of wireless network capacity for such situations. In this paper, we first investigate maximum transmission capacity of wireless ad-hoc networks. In the investigation, we consider a network topology with regularly located nodes. For the topology, we investigate the maximum transmission capacity with RTS/CTS medium access protocol, and then we study the maximum transmission capacity without the protocol. Next, we propose a scheme to expand network capacity and analyze the performance of the proposed scheme. From the results of analysis, we see that our proposed scheme is effective for temporary expansion of wireless network capacity.

• Journal of Computational Design and Engineering
• /
• v.3 no.3
• /
• pp.250-265
• /
• 2016

Owing to our rapidly aging society, accessibility evaluation to enhance the ease and safety of access to indoor and outdoor environments for the elderly and disabled is increasing in importance. Accessibility must be assessed not only from the general standard aspect but also in terms of physical and cognitive friendliness for users of different ages, genders, and abilities. Meanwhile, human behavior simulation has been progressing in the areas of crowd behavior analysis and emergency evacuation planning. However, in human behavior simulation, environment models represent only "as-planned" situations. In addition, a pedestrian model cannot generate the detailed articulated movements of various people of different ages and genders in the simulation. Therefore, the final goal of this research was to develop a virtual accessibility evaluation by combining realistic human behavior simulation using a digital human model (DHM) with "as-is" environment models. To achieve this goal, we developed an algorithm for generating human-like DHM walking motions, adapting its strides, turning angles, and footprints to laser-scanned 3D as-is environments including slopes and stairs. The DHM motion was generated based only on a motion-capture (MoCap) data for flat walking. Our implementation constructed as-is 3D environment models from laser-scanned point clouds of real environments and enabled a DHM to walk autonomously in various environment models. The difference in joint angles between the DHM and MoCap data was evaluated. Demonstrations of our environment modeling and walking simulation in indoor and outdoor environments including corridors, slopes, and stairs are illustrated in this study.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.531-537
• /
• 2009

When creating large crowds, it is unavoidable that the models and motions of many characters will be cloned. McDonnell implemented experiments focus on appearance and motion of characters to test user perception of crowds. As a result, appearance clones were easier to perceive than motion clones. In this paper, I researched about relation between character cloning and user perception for real-time game environment expanding McDonnell's research. This paper focuses on the way to recognition of multiple clones in dramatic environment free to change view point and has crowds move to every directions by trajectories. In particular, this paper shows the possibility of character diversification applied various shapes, colors and patterns to game item have important elements for game characters. Also, I suggests range of distances between clones by a series of experiments of user perception for clones's moving direction and distance.

• Journal of Navigation and Port Research
• /
• v.37 no.3
• /
• pp.239-244
• /
• 2013

To increase the safety of onboard evacuation of guests who is unfamiliar with onboard living conditions, this study measured and compared the onboard walking speeds of 81 participants on a passenger ship, I t were found that the walking speeds at corridor on navigation were slower than those at berth by 27.2%, and the speeds of walking on the corner on navigation were slower than those at berth by 23.2%. This means that the ship motion on navigation directly influenced walking speeds. The walking speeds of upward-stairs and downward-stairs were measured to be 0.71m/s and 0.75m/s, respectively. From the crowd counter-flow experiments, because of the narrow space between participants, the walking speeds were decreased as person after person. And it was clear that the group's walking speeds were determined by the walking speeds of leading person(s) of the group. The walking speeds obtained this study were different from those of IMO guideline(MSC/Circ 1033).

• The Journal of the Korea Contents Association
• /
• v.16 no.11
• /
• pp.644-660
• /
• 2016

With the development of Fintech industry, research interest in crowdfunding is growing. Crowdfunding, originated from crowdsourcing, involves the participation of many individuals' contributions to funding a new project. Specifically, lending based crowdfunding provides a platform for raising funds in the form of loans by connecting borrowers to funders(investors) via Internet, not through traditional financial institutions. Recently, lending based crowdfunding attracts much attention as a new investment alternative; however, there is a lack of research about lending based crowdfunding. This study aims to examine the factors influencing an investor's participation in lending based crowdfunding by focusing on platform features, investor features, and project features. Based on the findings, this study discusses theoretical and practical implications for promoting the crowd's investments through crowdfunding platforms.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.11
• /
• pp.135-147
• /
• 2016

Equity-based crowdfunding combines virtual technologies with traditional investing principles. Equity-based crowdfunding is a financing method for startups and small businesses to raise small amounts of capital from a "crowd" of investors. Small businesses can raise capital, advertise product or service, and receive feedback from crowds of investors in exchange for ownership equity in their business. This study examined the operational performance of equity-based crowdfunding in Korea. Data were collected from 125 success and failure equity-based crowdfunding of 75 firms. Results were as follows: First, success firms had a clear vision than failure firms in raising equity-based crowdfunding. Second, success firms had success experiences than failure firms in raising equity-based crowdfunding. Third, success firms had patents to technologies or products that are practical and that customers need. Fourth, success firms had three or more year long-term objectives than failure firms in raising equity-based crowdfunding. Finally, implications of the results were discussed.

• Journal of Labour Economics
• /
• v.39 no.4
• /
• pp.57-78
• /
• 2016

This study analyzes economic behaviors of government employee pension subscriber's household by comparison to national pension subscriber's household. First, government employee pension subscriber's household income is higher than national pension subscriber's one. Second, household net assets of government employee pension subscriber are smaller than the ones of national pension subscriber. Government employee pension could crowd out private household savings, and a national pension subscriber's household inherited more than a government employee pension subscriber's. Third, a government employee pension subscriber's household is also likely to expend more than a national pension subscriber's household. Both summary statistics and fixed effects estimates give significant coefficients to government employee's dummy. Government employee pension subscriber's households do not need to save more because they expect to receive a stable retirement pension which gives relatively higher compensation. Thus, they are likely to consume more than national pension subscriber's households.