• 재활복지
• /
• v.21 no.3
• /
• pp.129-146
• /
• 2017

In an event of an emergency, such as fire in a building, visually impaired and blind people are prone to exposed to a level of danger that is greater than that of normal people, for they cannot be aware of it quickly. Current fire detection methods such as smoke detector is very slow and unreliable because it usually uses chemical sensor based technology to detect fire particles. But by using vision sensor instead, fire can be proven to be detected much faster as we show in our experiments. Previous studies have applied various image processing and machine learning techniques to detect fire, but they usually don't work very well because these techniques require hand-crafted features that do not generalize well to various scenarios. But with the help of recent advancement in the field of deep learning, this research can be conducted to help solve this problem by using deep learning-based object detector that can detect fire using images from security camera. Deep learning based approach can learn features automatically so they can usually generalize well to various scenes. In order to ensure maximum capacity, we applied the latest technologies in the field of computer vision such as YOLO detector in order to solve this task. Considering the trade-off between recall vs. complexity, we introduced two convolutional neural networks with slightly different model's complexity to detect fire at different recall rate. Both models can detect fire at 99% average precision, but one model has 76% recall at 30 FPS while another has 61% recall at 50 FPS. We also compare our model memory consumption with each other and show our models robustness by testing on various real-world scenarios.

• The Journal of Society for e-Business Studies
• /
• v.24 no.1
• /
• pp.1-16
• /
• 2019

Recently, since responding to meteorological changes depending on increasing greenhouse gas and electricity demand, the importance prediction of photovoltaic power (PV) is rapidly increasing. In particular, the prediction of PV power generation may help to determine a reasonable price of electricity, and solve the problem addressed such as a system stability and electricity production balance. However, since the dynamic changes of meteorological values such as solar radiation, cloudiness, and temperature, and seasonal changes, the accurate long-term PV power prediction is significantly challenging. Therefore, in this paper, we propose PV power prediction model based on deep learning that can be improved the PV power prediction performance by learning to use meteorological and seasonal information. We evaluate the performances using the proposed model compared to seasonal ARIMA (S-ARIMA) model, which is one of the typical time series methods, and ANN model, which is one hidden layer. As the experiment results using real-world dataset, the proposed model shows the best performance. It means that the proposed model shows positive impact on improving the PV power forecast performance.

• Journal of Science Education
• /
• v.43 no.1
• /
• pp.17-42
• /
• 2019

This study, as an attempt to integrate mathematics and information for convergence education, was conducted to develop teaching-learning materials on mathematics education combined with coding education, which has recently been emphasized. We chose the subject of digital signature for coding education, and used SageMath as a coding program. In this study, we overview mathematics used in the elliptic curve digital signature algorithm, one of the many methods for digital signature, and developed the teaching-learning materials on the algorithm for mathematics education integrated with information education based on coding. The elliptic curve digital signature algorithm utilized in transactions of Bitcoin, which many people recently are interested in, is a good example, showing students that mathematics is applied to problem-solving in the real world and provides an optimal environment for implementation by coding. Accordingly, we expect that a class on algorithm will provide a specific teaching-learning program to achieve the goal of integrated mathematics education. By comprehensively considering the opinions of mathematicians, mathematics teachers and mathematics education experts, we expect that the teaching-learning program will be realized as a meaningful class in science high schools, high school's math clubs, and 'number theory' class in colleges.

• Journal of Korean Society of Archives and Records Management
• /
• v.21 no.3
• /
• pp.187-215
• /
• 2021

Archives should provide a web-based archival information service with good usability based on the understanding of users' needs. Thus, this study analyzed the usability of the National Archives of Korea (NAK) website's search service through expert and usability evaluations for various users and suggested improvement plans. A literature review, heuristic evaluation, one of the usability expert evaluation methods, and usability evaluation for users were performed. As a result of expert evaluation, the severity rating for the usability problem was highest regarding a match between the system and real world and the lowest in error prevention. In the usability evaluation, it was assumed that the user's background and whether the website's help was provided is associated with usability. Usability evaluation was conducted for 22 participants, including those majoring in records management, web/application developers, and people without such backgrounds. Furthermore, a presurvey, a five-second test, and search tasks were conducted in a row. The analysis based on usability components in ISO 9241-11: 2018, i.e., effectiveness, efficiency, and satisfaction, showed that web/application developers had the highest search effectiveness, and those majoring in records management showed high effectiveness only in the search for archival content services. Background factors did not affect efficiency, and the more familiar with the finding aids, the better the efficiency. Moreover, providing the website's help was found to be positively associated with effectiveness and satisfaction. This study suggests that the NAK website will offer a user-friendly interface and search function, expand help support, and display a consistent web interface.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1515-1526
• /
• 2022

Image-based 3D reconstruction is to restore the shape and color of real-world objects, and image sensors mounted on mobile platforms are used for positioning and mapping purposes in indoor and outdoor environments. Due to the increase in accidents in underground space, the location accuracy problem of underground spatial information has been raised. Image-based location estimation studies have been conducted with the advantage of being able to determine the 3D location and simultaneously identify internal damage from image data acquired from the inside of pipeline-type underground facilities. In this study, we studied 3D reconstruction based on the images acquired inside the pipe-type underground facility and reference data. An unmanned mobile system equipped with a stereo camera was used to acquire data and image data within a pipe-type underground facility where reference data were placed at the entrance and exit. Using the acquired image and reference data, the pipe-type underground facility is reconstructed to a geo-referenced 3D shape. The accuracy of the 3D reconstruction result was verified by location and length. It was confirmed that the location was determined with an accuracy of 20 to 60 cm and the length was estimated with an accuracy of about 20 cm. Using the image-based 3D reconstruction method, the position and line-shape of the pipe-type underground facility will be effectively updated.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.67-76
• /
• 2023

Although deep learning models are making innovative achievements in the field of computer vision, the problem of vulnerability to adversarial examples continues to be raised. Adversarial examples are attack methods that inject fine noise into images to induce misclassification, which can pose a serious threat to the application of deep learning models in the real world. In this paper, we propose a model that detects adversarial examples using differences in predictive values between edge-learned classification models and underlying classification models. The simple process of extracting the edges of the objects and reflecting them in learning can increase the robustness of the classification model, and economical and efficient detection is possible by detecting adversarial examples through differences in predictions between models. In our experiments, the general model showed accuracy of {49.9%, 29.84%, 18.46%, 4.95%, 3.36%} for adversarial examples (eps={0.02, 0.05, 0.1, 0.2, 0.3}), whereas the Canny edge model showed accuracy of {82.58%, 65.96%, 46.71%, 24.94%, 13.41%} and other edge models showed a similar level of accuracy also, indicating that the edge model was more robust against adversarial examples. In addition, adversarial example detection using differences in predictions between models revealed detection rates of {85.47%, 84.64%, 91.44%, 95.47%, and 87.61%} for each epsilon-specific adversarial example. It is expected that this study will contribute to improving the reliability of deep learning models in related research and application industries such as medical, autonomous driving, security, and national defense.

• Information Systems Review
• /
• v.24 no.1
• /
• pp.105-123
• /
• 2022

Thanks to the remarkable success of Artificial Intelligence (A.I.) techniques, a new possibility for its application on the real-world problem has begun. One of the prominent applications is the bankruptcy prediction model as it is often used as a basic knowledge base for credit scoring models in the financial industry. As a result, there has been extensive research on how to improve the prediction accuracy of the model. However, despite its impressive performance, it is difficult to implement machine learning (ML)-based models due to its intrinsic trait of obscurity, especially when the field requires or values an explanation about the result obtained by the model. The financial domain is one of the areas where explanation matters to stakeholders such as domain experts and customers. In this paper, we propose a novel approach to incorporate financial domain knowledge into local rule generation to provide explanations for the bankruptcy prediction model at instance level. The result shows the proposed method successfully selects and classifies the extracted rules based on the feasibility and information they convey to the users.

• Journal of Korean Society of Transportation
• /
• v.19 no.1
• /
• pp.101-114
• /
• 2001

Transportation enterprises should maintain constant and qualitative operation. Thus, in short period, transportation enterprises don't change supply in accordance with demand. In the result, transportation enterprises don't reduce operation in spite of management deficit at will. In freight transportation type, less-than-truckload(LTL) has more relation with above transportation feature than truckload(TL) does. Because freight transportation supply of TL is more flexible than that of LTL in correspondence of freight transportation demand. Relating to above mention, it appears that shortage of road and freight terminal of LTL is larger than that of TL. Especially in road and freight terminal comparison, shortage of freight terminal is larger than that of road. Shortage of road is the largest in 1990, and improved after-ward. But shortage of freight terminal is serious lately. So freight terminal needs more expansion than road, and shows better investment condition than road. Freight terminal expansion brings road expansion in LTL, on the contrary, freight terminal expansion substitutes freight terminal for road in TL. In transportation revenue, freight terminal's contribution to LTL is larger than that to TL. However, when we adjust quasi-fixed factor - road and freight terminal - to optimal level in the long run, in TL, diseconomies of scale becomes large, but in LTL, economies of scale becomes large. Consequently, it is necessary for TL to make counterplans to activate management of small size enterprises and owner drivers. And LTL should make use of economies of scale by solving the problem, such as nonprofit route, excess of rental freight handling of office, insufficiency of freight terminal, shortage of driver, and unpreparedness of freight insurance.

• Journal of the Korean Association of African Studies
• /
• v.29
• /
• pp.27-53
• /
• 2009

At the start of the new century, South Africa probably had the largest number of HIV-infected people of any country in the world. The only nation that comes close is India with a population of one billion people compared to South Africa's figure of 57 million. The tragedy is that this did not have to happen. South Africa was aware of the dangers posed by AIDS as early as 1985. In 1991, the national survey of women attending antenatal clinics found that only 0.8percent were infected. In 1994, when the new government took power, the figure was still comparatively low at 7.6 %. The 2004 figure which has been published is 26.5%. This article tracks the epidemic globally, in the region and in South Africa. I explain some of the basic concepts around the disease and look at what may happen with respect to numbers. The situation is bad, and the number of people falling ill, dying and leaving families will rise over next few years. This will impact on South Africa in a number of important ways. This article assesses the demographic, economic and social consequences of the epidemic. It disposes of a number of myths and present the real facts. The AIDS in South Africa is not related to individuals only. It warns that AIDS in Africa is becoming a community and systemic problem. The acuteness of the problem does not stem merely from the fact that communities are affected, or could even be wipe out by the end of this decade, but from the fact that AIDS will place incredible burdens and obligations upon medical services, health care and religious communities such as churches. The facts confront churches' mission with the important question: who is going to take care of all the patients and where? The reality is that people dying of AIDS will have to be cared for at home by relatives and friends. A further question that arises is whether our people are prepared for this. AIDS was considered to be a homo-plague and the hunt was on for a scapegoat in the light of the fatal implication of the disease. At present we are in the strategic phase where we all realize that it will be of no avail to scare people with the ominous threat of AIDS AIDS destroys the optimism of our achievement ethics. This exposure of the culture of optimism is also an exposure of the so-called 'human basic fear which accuses Christianity that their concept of sin is a damper on man's search for liberation and basic need to be freed from all Imitation. AIDS is also a test for our ecclesiastical genuineness and the sincerity of our mission sensibility. It poses the question: How unconditional is Christian love? Is there room for the AIDS sufferer in the community of believers, despite the fact he is an acknowledged homosexual? The question to put to the church is whether the community of believers is an exclusive to put to the koinonia which excludes homosexuals. They may be welcome on principle, but in actual fact are not acceptable to the church community. As South Africa enters the new century, it is clear that the epidemic is not having a measurable impact. However, the impact of AIDS is gradual, subtle and incremental. The author's proposal of what is currently most needed in South Africa is that the little things will make a difference. It's about doing lots of little things better at grassroots level, with the emphasis on doing. There are so many community, churches and NGOs initiatives worth building on and intensifying. One must not underestimate the therapeutic value of working together in small groups to overcome a problem

• Journal of Intelligence and Information Systems
• /
• v.20 no.3
• /
• pp.45-58
• /
• 2014

The Korean Culture Contents spread out to Worldwide, because the Korean wave is sweeping in the world. The contents stand in the middle of the Korean wave that we are used it. Each country is ongoing to keep their Culture industry improve the national brand and High added value. Performing contents is important factor of arousal in the enterprise industry. To improve high arousal confidence of product and positive attitude by populace is one of important factor by advertiser. Culture contents is the same situation. If culture contents have trusted by everyone, they will give information their around to spread word-of-mouth. So, many researcher study to measure for person's arousal analysis by statistical survey, physiological response, body movement and facial expression. First, Statistical survey has a problem that it is not possible to measure each person's arousal real time and we cannot get good survey result after they watched contents. Second, physiological response should be checked with surround because experimenter sets sensors up their chair or space by each of them. Additionally it is difficult to handle provided amount of information with real time from their sensor. Third, body movement is easy to get their movement from camera but it difficult to set up experimental condition, to measure their body language and to get the meaning. Lastly, many researcher study facial expression. They measures facial expression, eye tracking and face posed. Most of previous studies about arousal and interest are mostly limited to reaction of just one person and they have problems with application multi audiences. They have a particular method, for example they need room light surround, but set limits only one person and special environment condition in the laboratory. Also, we need to measure arousal in the contents, but is difficult to define also it is not easy to collect reaction by audiences immediately. Many audience in the theater watch performance. We suggest the system to measure multi-audience's reaction with real-time during performance. We use difference image analysis method for multi-audience but it weaks a dark field. To overcome dark environment during recoding IR camera can get the photo from dark area. In addition we present Multi-Audience Engagement Index (MAEI) to calculate algorithm which sources from sound, audience' movement and eye tracking value. Algorithm calculates audience arousal from the mobile survey, sound value, audience' reaction and audience eye's tracking. It improves accuracy of Multi-Audience Engagement Index, we compare Multi-Audience Engagement Index with mobile survey. And then it send the result to reporting system and proposal an interested persons. Mobile surveys are easy, fast, and visitors' discomfort can be minimized. Also additional information can be provided mobile advantage. Mobile application to communicate with the database, real-time information on visitors' attitudes focused on the content stored. Database can provide different survey every time based on provided information. The example shown in the survey are as follows: Impressive scene, Satisfied, Touched, Interested, Didn't pay attention and so on. The suggested system is combine as 3 parts. The system consist of three parts, External Device, Server and Internal Device. External Device can record multi-Audience in the dark field with IR camera and sound signal. Also we use survey with mobile application and send the data to ERD Server DB. The Server part's contain contents' data, such as each scene's weights value, group audience weights index, camera control program, algorithm and calculate Multi-Audience Engagement Index. Internal Device presents Multi-Audience Engagement Index with Web UI, print and display field monitor. Our system is test-operated by the Mogencelab in the DMC display exhibition hall which is located in the Sangam Dong, Mapo Gu, Seoul. We have still gotten from visitor daily. If we find this system audience arousal factor with this will be very useful to create contents.