• Journal of Internet Computing and Services
• /
• v.22 no.6
• /
• pp.33-40
• /
• 2021

Automatic Speech Recognition(ASR) is a technology that analyzes human speech sound into speech signals and then automatically converts them into character strings that can be understandable by human. Speech recognition technology has evolved from the basic level of recognizing a single word to the advanced level of recognizing sentences consisting of multiple words. In real-time voice conversation, the high recognition rate improves the convenience of natural information delivery and expands the scope of voice-based applications. On the other hand, with the active application of speech recognition technology, concerns about related cyber attacks and threats are also increasing. According to the existing studies, researches on the technology development itself, such as the design of the Automatic Speaker Verification(ASV) technique and improvement of accuracy, are being actively conducted. However, there are not many analysis studies of attacks and threats in depth and variety. In this study, we propose a cyber attack model that bypasses voice authentication by simply manipulating voice frequency and voice speed for AI voice recognition service equipped with automated identification technology and analyze cyber threats by conducting extensive experiments on the automated identification system of commercial smartphones. Through this, we intend to inform the seriousness of the related cyber threats and raise interests in research on effective countermeasures.

• Journal of Internet Computing and Services
• /
• v.23 no.4
• /
• pp.87-94
• /
• 2022

Recently, with the development of information and communication infrastructure, the number of Internet access devices is rapidly increasing. Smartphones, laptops, computers, and even IoT devices are receiving information and communication services through Internet access. Since most of the device operating environment consists of web (WEB), it is vulnerable to web cyber attacks using web shells. When the web shell is uploaded to the web server, it is confirmed that the attack frequency is high because the control of the web server can be easily performed. As the damage caused by the web shell occurs a lot, each company is responding to attacks with various security devices such as intrusion prevention systems, firewalls, and web firewalls. In this case, it is difficult to detect, and in order to prevent and cope with web shell attacks due to these characteristics, it is difficult to respond only with the existing system and security software. Therefore, it is an automated defense system through the collection and analysis of web shells based on artificial intelligence machine learning that can cope with new cyber attacks such as detecting unknown web shells in advance by using artificial intelligence machine learning and deep learning techniques in existing security software. We would like to propose about. The machine learning-based web shell defense system model proposed in this paper quickly collects, analyzes, and detects malicious web shells, one of the cyberattacks on the web environment. I think it will be very helpful in designing and building a security system.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.5
• /
• pp.537-542
• /
• 2021

This paper improves the possibility of recognizing fast-moving objects through the YOLO (You Only Look Once) deep learning recognition model in an application environment for object recognition in images. The purpose was to study the method of collecting semantic data through processing. In the recognition model, the moving object recognition error was identified as unrecognized because of the difference between the frame rate of the camera and the moving speed of the object and a misrecognition due to the existence of a similar object in an environment adjacent to the object. To minimize the recognition errors by compensating for errors, such as unrecognized and misrecognized objects through the proposed data collection method, and applying vision processing technology for the causes of errors that may occur in images acquired for sports (tennis games) that can represent real similar environments. The effectiveness of effective secondary data collection was improved by research on methods and processing structures. Therefore, by applying the data collection method proposed in this study, ordinary people can collect and manage data to improve their health and athletic performance in the sports and health industry through the simple shooting of a smart-phone camera.

• Journal of Korean Home Economics Education Association
• /
• v.34 no.1
• /
• pp.1-16
• /
• 2022

This study was performed to develop educational materials in the form of card news that can be easily accessed on mobile phones or the Internet for milk intake education of the elderly based on the scientific evidence and their needs. The themes included in the card news were selected based on the literature and focus group interviews with 10 elderly individuals (78.10±6.66 years old). For the selected themes, information that elderly users most want to know was selected for the purpose of effective communication, while reflecting the eating habits, lifestyle, living environment, and nutrition and health status of the elderly in Korea. The draft of the card news was reviewed by the researcher, consulted by experts, and surveyed with 50 elderly individuals (70.44±5.16 years old). Based on the results of the review, consultations, and the survey, a final draft of the card news consisting of 12 pages was completed. The card news of the present study is expected to be an effective educational material considering the high level of satisfaction (higher than 4 on the 5-point scales) indicated by the survey respondents. Therefore this card news is expected to help increase milk intake through friendly milk education for the elderly.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.8
• /
• pp.77-84
• /
• 2022

In this paper, we propose a system for monitoring air pollutants such as fine dust using an unmanned aerial vehicle capable of autonomous navigation. The existing air quality management system used a method of collecting information through a fixed sensor box or through a measurement sensor of a drone using a control device. This has disadvantages in that additional procedures for data collection and transmission must be performed in a limited space and for monitoring. In this paper, to overcome this problem, a GPS module for location information and a PMS7003 module for fine dust measurement are embedded in an unmanned aerial vehicle capable of autonomous navigation through flight information designation, and the collected information is stored in the SD module, and after the flight is completed, press the transmit button. It configures a system of one-stop structure that is stored in a remote database through a smartphone app connected via Bluetooth. In addition, an HTML5-based web monitoring page for real-time monitoring is configured and provided to interested users. The results of this study can be utilized in an environmental monitoring system through an unmanned aerial vehicle, and in the future, various pollutants measuring sensors such as sulfur dioxide and carbon dioxide will be added to develop it into a total environmental control system.

• The Journal of the Korea Contents Association
• /
• v.22 no.2
• /
• pp.125-134
• /
• 2022

Due to the development of smartphone technology, as of 2020, 91.9% of people use the Internet[1] to frequently acquire information through websites and mobile apps. As the number of homepages in charge of providing information is increasing every year, the number of applications for web vulnerability diagnosis, which diagnoses the safety of homepages, is also increasing. In the existing web vulnerability check, the number of diagnostic personnel should increase in proportion to the number of homepages that need diagnosis because the diagnosticians manually test the homepages for vulnerabilities. In reality, however, there is a limit to securing a web vulnerability diagnosis manpower, and if the number of diagnosis manpower is increased, a lot of costs are incurred. To solve these problems, an automatic diagnosis tool is used to replace a part of the manual diagnosis. This paper explores a new method to expand the current automatic diagnosis range. In other words, automatic diagnosis possible items were derived by analyzing the impact of web vulnerability diagnosis items. Furthermore, automatic diagnosis identified possible items through comparative analysis of diagnosis results by performing manual and automatic diagnosis on the website in operation. In addition, it is possible to replace manual diagnosis for possible items, but not all vulnerability items, through the improvement of automatic diagnosis tools. This paper will explore some suggestions that can help improve plans to support and implement automatic diagnosis. Through this, it will be possible to contribute to the creation of a safe website operating environment by focusing on the parts that require precise diagnosis.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.1
• /
• pp.41-49
• /
• 2023

A convolutional neural network (CNN) is a representative algorithm for implementing artificial neural networks. CNNs have improved on the issues of rapid increase in calculation amount and low object classification rates, which are associated with a conventional multi-layered fully-connected neural network (FNN). However, because of the rapid development of IT devices, the maximum resolution of images captured by current smartphone and tablet cameras has reached 108 million pixels (MP). Specifically, a traditional CNN algorithm requires a significant cost and time to learn and process simple, high-resolution images. Therefore, this study proposes an improved CNN algorithm for implementing an object classification learning model for simple, high-resolution images. The proposed method alters the adjacency matrix value of the pooling layer's max pooling operation for the CNN algorithm to reduce the high-resolution image learning model's creation time. This study implemented a learning model capable of processing 4, 8, and 12 MP high-resolution images for each altered matrix value. The performance evaluation result showed that the creation time of the learning model implemented with the proposed algorithm decreased by 36.26% for 12 MP images. Compared to the conventional model, the proposed learning model's object recognition accuracy and loss rate were less than 1%, which is within the acceptable error range. Practical verification is necessary through future studies by implementing a learning model with more varied image types and a larger amount of image data than those used in this study.

• Journal of Korea Entertainment Industry Association
• /
• v.13 no.3
• /
• pp.1-12
• /
• 2019

The 4th industrial revolution has become a topic of 'experiential games' that utilize technologies such as virtual reality, augmented reality, and complex reality, and they are promoting various experiential game contents to attract tourists in the tourism industry have. The trend of tourism is the concept of the healing which aims to enhance the quality of life of the individual in the concept of simple travel, that is, the consumer is not satisfied with the sight, There are many changes in the form of tourism. In this study, domestic and foreign cases that utilized the fun and experience of tourism in the game were examined using case study methods. In domestic case, although service was provided by using smart phone, there is a problem that simple information is provided, mission quest method is not continuously provided, and the story is limited. I tried to find out the solution through this case. Developing and applying various experience contents, utilizing active investment and various stories for continuous service, and utilizing new technology such as virtual reality, it will bring about improvement of domestic tourism industry and satisfaction.

• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.3-12
• /
• 2022

Image deblurring aims to remove image blur, which can be generated while shooting the pictures by the movement of objects, camera shake, blurring of focus, and so forth. With the rise in popularity of smartphones, it is common to carry portable digital cameras daily, so image deblurring techniques have become more significant recently. Originally, image deblurring techniques have been studied using traditional optimization techniques. Then with the recent attention on deep learning, deblurring methods based on convolutional neural networks have been actively proposed. However, most of them have been developed while focusing on better performance. Therefore, it is not easy to use in real situations due to the speed of their algorithms. To tackle this problem, we propose a novel deep learning-based deblurring algorithm that can be operated in real-time on HD resolution. In addition, we improved the training and inference process and could increase the performance of our model without any significant effect on the speed and the speed without any significant effect on the performance. As a result, our algorithm achieves real-time performance by processing 33.74 frames per second at 1280×720 resolution. Furthermore, it shows excellent performance compared to its speed with a PSNR of 29.78 and SSIM of 0.9287 with the GoPro dataset.

• Journal of Korea Entertainment Industry Association
• /
• v.6 no.4
• /
• pp.82-92
• /
• 2012

Recently people who enjoy social game via mobile devices significantly are increasing depending on the rapid adoption of smart phones and the development of the network such as LTE. Most of them are enjoying the casual gaming mobile social games that you are able to play easily, but social issues like health problems due to long play time are emerging. The users, however, do not last long because of the simplicity of the game, and there are few people who actually buy game items even though they play it long time. This study has been conducted aiming to overcome such difficulties. This study suggests ways to generate constantly revenue avoiding short-term box-office after the release of mobile social games based on the analysis for market trend and profitability of the mobile social game. In addition, by applying profitability model analyzed to Japan's most successful game practices, this paper suggests the concrete methods about the commitment of the users. For summarizing the main achievements of this paper, providing the latest market information about mobile social games, analysis of profitability, practical implications for the commitment of the users are presented.