• Proceedings of the Korean Society of Computer Information Conference
• /
• 2015.07a
• /
• pp.79-80
• /
• 2015

본 프로젝트는 신입생들을 대상으로 대학캠퍼스 및 대학생활을 빠르게 적응할 수 있도록 시설물의 위치 및 활용방법, 학사 행정, 수강 및 강의실 등 학교생활에 유용한 정보들을 자연스럽게 전달할 수 있는 오락용 어플리케이션이다. 빠른 학교생활적응과 부가적이고 적절한 유용 정보를 제공하기 위해 미션을 해결하면서 목적을 달성하는 시나리오로 최종 미션을 완성할 수 있도록 구성하였다. 기술적으로는 QR코드를 활용한 정보 및 미션을 제공하고 GPS 위치 정보를 활용한 자신의 위치와 캠퍼스 맵, 미션 힌트 정보를 제공한다. 이러한 미션 수행 과정을 통해 대학생활에 유용한 정보를 얻을 수 있는 오락용 프로젝트이다.

• Smart Media Journal
• /
• v.10 no.2
• /
• pp.76-83
• /
• 2021

With the development and use of smart devices such as smartphones and tablets increases, the mobile application market based on mobile devices is growing rapidly. Mobile application users write reviews to share their experience in using the application, which can identify consumers' various needs and application developers can receive useful feedback on improving the application through reviews written by consumers. However, there is a need to come up with measures to minimize the amount of time and expense that consumers have to pay to manually analyze the large amount of reviews they leave. In this work, we propose to collect delivery application user reviews from Google PlayStore and then use machine learning and deep learning techniques to classify them into four categories like application feature advantages, disadvantages, feature improvement requests and bug report. In the case of the performance of the Hugging Face's pretrained BERT-based Transformer model, the f1 score values for the above four categories were 0.93, 0.51, 0.76, and 0.83, respectively, showing superior performance than LSTM and GRU.

• Journal of Service Research and Studies
• /
• v.12 no.2
• /
• pp.23-37
• /
• 2022

Based on the service scenario proposed by the existing Kim Tae-wan (2018) who can safely evacuate inmates with the help of a mobile application linked to a fire detection system in the event of a fire, the final purpose of this study is to develop the scenario by incorporating more realistic scenarios with mobile stimuli that can help them escape or act through the Delph In addition, to make the scenarios produced more realistic considering the structure and copper lines of a typical building, expert scenario verification and Delphi technique were applied to exclude unnecessary or impractical aspects of the existing scenarios. The results of the second Delphi survey showed that the primary psychology that could be seen at the time of the fire alarm were doubts, safety concerns and alarm, and the results of the second Delphi survey were analyzed, and the satisfaction of the content adequacy (CVR), convergence, and consensus was derived. Finally, this was applied to create a scenario in which a mobile application was assisted to evacuate the fire response phase. This study will allow the use of methods to increase the evacuation rate of those who are in the event of a fire.

• Information and Communications Magazine
• /
• v.32 no.4
• /
• pp.10-15
• /
• 2015

본고에서는 u-Office 서비스를 실현하기 위하여 이동 단말 기기로부터 수신한 사용자의 시간 및 위치 이동 정보를 이용해서 사용자에게 유용한 서비스를 제공하는 데 필요한 사용자 맞춤형 서비스 제공 통합 프레임워크 및 추론 기술 알고리즘에 대해 기술하고자 한다. 사용자 맞춤형 서비스제공 통합 프레임워크는 사용자 이동단말기 및 시간 및 이동 데이터를 저장하는 AP, AP의 데이터를 수집하는 데이터베이스, 사용자 이동 단말 어플리케이션 등으로 구성되어있으며, 사용자의 시간 및 위치 정보를 학습하여 이동 경로를 예측하고 유용한 서비스를 제공하기 위해 사용된 기계학습 기반 추론 알고리즘에 대하여 알아본다. u-Office 서비스를 실현하기 위하여 실제로 캠퍼스 및 교실범위로 구현한 사용자 패턴기반 맞춤형 서비스 프레임워크에 대해 알아보고 제공 가능한 서비스에 대하여 논의한다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.10
• /
• pp.8-15
• /
• 2020

A forecasting method using deep learning does not have consistent results due to the differences in the characteristics of the dataset, even though they have the same forecasting models and parameters. For example, the forecasting model X optimized with dataset A would not produce the optimized result with another dataset B. The forecasting model with the characteristics of the dataset needs to be optimized to increase the accuracy of the forecasting model. Therefore, this paper proposes novel optimization steps for outlier removal, dataset classification, and a CNN-LSTM-based hyperparameter tuning process to forecast the daily power usage of a university campus based on the hourly interval. The proposing model produces high forecasting accuracy with a 2% of MAPE with a single power input variable. The proposing model can be used in EMS to suggest improved strategies to users and consequently to improve the power efficiency.

• Journal of Korean Society for Geospatial Information Science
• /
• v.15 no.3
• /
• pp.11-18
• /
• 2007

Recently 3D GIS and its applications are getting attention increasingly as various ubiquitous-related techniques for 3D spaces are being developed. Although they call for quantitative measures such as accessibility, most accessibilityrelated studies are limited to 2D networks, not 3D indoor space levels. In this paper, we develop an accessibility index applicable to 3D models. We first examine the theory of Space Syntax which has been developed and used to measure the connectivity or relationships between spatial segments in urban or architectural environments. Then, we expand the principle to a more general form so it can be applied to both street and indoor space levels. We incorporate different types of impedances in moving between places including distances, turns and transfers between floors into the traditional Space Syntax that measures the spatial depths solely based on the structural forms. Finally, we illustrate the use of the proposed measure comparatively using a campus building.

• Journal of Service Research and Studies
• /
• v.12 no.2
• /
• pp.106-116
• /
• 2022

As part of the Fire Evacuation Service scenario using mobile applications, this study aims to find the appropriate colors to be used in the interface of the application and to define and apply colors that can positively and reliably affect human unstable psychology in the course of evacuating the room in case of fire. In the situation of fire, proper design and placement of the colored escape guidance interface is important, taking into account the psychology of the occupants. However, literature and previous research have shown that colors used to induce evacuation are not suitable for effective evacuation in case of fire. In this study, the purpose of the study was to provide a color that would provide psychological stability in the event of a evacuation in consideration of the psychological issues of those who are still in need of shelter, and to use it to help induce an efficient evacuation in the event of a disaster. Using the image evaluation method, the form and color of images have been derived through frequency analysis to a number of unspecified people, and the main and secondary colors of images were analyzed through KSCA color analysis. Finally, the final application color was constructed through mutual verification between the results by comparing and analyzing the colors obtained through the image evaluation analysis results and the KSCA color analysis results. The results of the study showed that the green line can help stabilize the human mind through comparative analysis with prior research. Therefore, the main color for guiding calm and calm applications in case of fire escape is proposed in the green line. In this study, the experiment with image evaluation cannot accurately measure the effect of factors on color among complex factors. A subsequent study of this will help quantify images if it allows the subject matter of color and image to be defined to some extent through factor analysis.