• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.18 no.4
• /
• pp.153-166
• /
• 2008

According to the growth of the internet and the usage of software agents, the CAPTCHA that is a method for taking apart humans and computers has been widely deployed and used. As the results of many research activities, the CAPTCHA, which is spoken for a distorted image material including random text, has known to be easily breakable via artificial intelligence techniques. As one of alternatives for those text-based CAPTCHAs, methods using photos are concerned and various image-based CAPTCHAs are suggested. However, image-based CAPTCHAs still have some problems. In this paper, we discuss what are the problems in each image-based CAPTCHA and propose a new image-based CAPTCHA using image composition as the solution of those problems. Furthermore, for the secure operation of the CAPTCHA, we suggest a communication protocol that works without the virtual session and consider possible security and usability problems in the protocol.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.19 no.6
• /
• pp.105-112
• /
• 2009

Nowadays, completely automated public turing tests to tell computers and humans apart(CAPTCHAs) are widely used to prevent various attacks by automated software agents such as creating accounts, advertising, sending spam mails, and so on. In early CAPTCHAs, the characters were simply distorted, so that users could easily recognize the characters. From that reason, using various techniques such as image processing, artificial intelligence, etc., one could easily break many CAPTCHAs, either. As an alternative, By adding noise to CAPTCHAs and distorting the characters in CAPTCHAs, it made the attacks to CAPTCHA more difficult. Naturally, it also made users more difficult to read the characters in CAPTCHAs. To improve the readability of CAPTCHAs, some CAPTCHAs used different colors for the characters. However, the usage of the different colors gives advantages to the adversary who wants to break CAPTCHAs. In this paper, we suggest a method of increasing the recognition ratio of CAPTCHAs based on colors.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.6
• /
• pp.118-133
• /
• 2020

Research interest in the Mobility-as-a-Service (MaaS) concept for enhancing users' mobility experience is increasing. In particular, dynamic pricing techniques based on reinforcement learning have emerged since adjusting prices based on the demand is expected to help mobility services, such as taxi and car-sharing services, to gain more profit. This paper provides a simulation framework that considers more practical factors, such as demand density per location, preferred prices, the distance between users and drivers, and distance to the destination that critically affect the probability of matching between the users and the mobility service providers (e.g., drivers). The aforementioned new practical features are reflected on a data structure referred to as the Matching Matrix. Using an efficient algorithm of computing the probability of matching between the users and drivers and given a set of precisely identified high-demand locations using HDBSCAN, this study developed a better reward function that can gear the reinforcement learning process towards finding more realistic dynamic pricing policies.

• The Journal of Bigdata
• /
• v.5 no.2
• /
• pp.111-120
• /
• 2020

Despite the recent economic contraction caused by the Corona 19 incident, interest in the residential environment is growing as more people live at home due to the increase in telecommuting, thereby increasing demand for remodeling. In addition, the government's real estate policy is also expected to have a visible impact on the sales of the interior and furniture industries as it shifts from regulatory policy to the expansion of housing supply. Accurate demand forecasting is a problem directly related to inventory management, and a good demand forecast can reduce logistics and inventory costs due to overproduction by eliminating the need to have unnecessary inventory. However, it is a difficult problem to predict accurate demand because external factors such as constantly changing economic trends, market trends, and social issues must be taken into account. In this study, LSTM model and 1D-CNN model were compared and analyzed by artificial intelligence-based time series analysis method to produce reliable results for manufacturers producing furniture components.

• The Journal of the Korea Contents Association
• /
• v.21 no.6
• /
• pp.51-61
• /
• 2021

In the era of the 4th industrial revolution symbolized by the Internet of Things, big data and artificial intelligence, various embedded devices are increasing exponentially. These devices have communication functions despite their low specifications, so the possibility of personal information leakage is increasing, and security threats are also increasing. Embedded devices can have security issues at most levels, from hardware to services over the network. In addition, it is difficult to apply general security techniques because it has characteristics of resource constraints such as low specifications and low power, and the related technology has not been standardized. In this study, we present vulnerabilities and possible problems and considerations in applying SDN to embedded devices in consideration of structural characteristics and real-world discovered cases. This study presents vulnerabilities and possible problems and considerations when applying SDN to embedded devices. From a hardware perspective, we consider the problems of Wi-Fi chips and Bluetooth, the problems of open flow implementation, SDN controllers, and examples of structural properties. SDN separates the data plane and the control plane, and provides a standardized interface between the two, enabling efficient communication control. It can respond to the security limitations of existing network technologies that are difficult to respond to rapid changes.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.35 no.1
• /
• pp.22-27
• /
• 2021

This study conducted a questionnaire for students of Pusan National University Graduate School of Korean Medicine who practiced using the Oriental Medicine Diagnosis System (ODS). From the questionnaire, this study investigated current state of application and perception of AI in Korean Medicine and explored the direction of ODS improvement and utilization. The survey questions consisted of six questions examining the satisfaction of the diagnostic expert system, five questions evaluating the availability of the diagnostic expert system, and six questions to predict the impact of AI on the Korean medicine community. The survey analysis showed high satisfaction with practice using ODS. On the other hand, the possibility of using ODS, especially in clinical use, was evaluated as relatively low compared to the satisfaction of the practice. Therefore, the overall impact of AI on the Korean medical community is not expected to be large. Although there are difficulties in standardization of clinical data due to the academic characteristics of Korean medicine, it is necessary to continue attempts to apply AI. By actively introducing educational tools using the latest AI techniques to the diagnosis experience and doctor-patient role in a practice, students will be able to increase their satisfaction with their practice and respond appropriately to the state-of-the-art medical environment.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.842-849
• /
• 2022

With the development of deep learning technology, there are many cases of using DNNs in embedded systems such as unmanned vehicles, drones, and robotics. Typically, in the case of an autonomous driving system, it is crucial to run several DNNs which have high accuracy results and large computation amount at the same time. However, running multiple DNNs simultaneously in an embedded system with relatively low performance increases the time required for the inference. This phenomenon may cause a problem of performing an abnormal function because the operation according to the inference result is not performed in time. To solve this problem, the solution proposed in this paper first reduces the computation by applying the Tucker decomposition to DNN models with big computation amount, and then, make DNN models run in parallel as much as possible in the unit of hidden layer inside the GPU. The experimental result shows that the DNN inference time decreases by up to 75.6% compared to the case before applying the proposed technique.

• Journal of The Korean Association of Information Education
• /
• v.26 no.2
• /
• pp.97-104
• /
• 2022

As the era of digital transformation begins in earnest, the importance of convergent thinking based on software, artificial intelligence, and big data is increasing. In line with these social needs, this study developed a 5th hour SW-STEAM education program using Monte Carlo simulation techniques for Mendelian inheritance in the field of life science. By programming and implementing Mendelian inheritance using Monte carlo simulation, the program was organized so that not only convergent thinking skills but also related knowledge could be understood in depth. In order to verify the validity of the developed education program, 11 experts in related fields were requested to test the content validity, and the validity was verified by meeting the CVR reference value of 0.59 suggested by Lawshe.

• Journal of the Korea Convergence Society
• /
• v.12 no.11
• /
• pp.27-33
• /
• 2021

With increasing interest in key areas of the 4th industrial revolution such as artificial intelligence, deep learning and big data, scientific approaches have developed in order to overcome the limitations of traditional decision-making methodologies. These scientific techniques are mainly used to predict the direction of financial products. In this study, the factors of apartment prices, which are of high social interest, were analyzed through SOM. For this analysis, we extracted the real prices of the apartments and selected a total of 16 input variables that would affect these prices. The data period was set from 1986 to 2021. As a result of examining the characteristics of the variables during the rising and faltering periods of the apartment prices, it was found that the statistical tendencies of the input variables of the rising and the faltering periods were clearly distinguishable. I hope this study will help us analyze the status of the real estate market and study future predictions through image learning.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.8
• /
• pp.1111-1120
• /
• 2022

Image Capturing is a matter of viewing images and describing images in language. The problem is an important problem that can be solved by keeping, understanding, and bringing together two areas of image processing and natural language processing. In addition, by automatically recognizing and describing images in text, images can be converted into text and then into speech for visually impaired people to help them understand their surroundings, and important issues such as image search, art therapy, sports commentary, and real-time traffic information commentary. So far, the image captioning research approach focuses solely on recognizing and texturing images. However, various environments in reality must be considered for practical use, as well as being able to provide image descriptions for the intended purpose. In this work, we limit the universally available Korean and English image captioning models and text generation techniques for the purpose of image captioning.