• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.11
• /
• pp.46-52
• /
• 2017

Along with the expansion of areas in which ICT and Internet of Things (IoT) devices are utilized, open source software has recently expanded its scope of applications to include computers, smart phones, and IoT devices. Hence, as the scope of open source software applications has varied, there have been increasing malicious attempts to attack the weaknesses of open source software. In order to address this issue, various secure coding programs have been developed. Nevertheless, numerous vulnerabilities are still left unhandled. This paper provides some methods to handle newly raised weaknesses based on the analysis of histories and patterns of previous open source vulnerabilities. Through this study, we have designed a weaknesses analysis system that utilizes weakness histories and pattern learning, and we tested the performance of the system by implementing a prototype model. For five vulnerability categories, the average vulnerability detection time was shortened by about 1.61 sec, and the average detection accuracy was improved by 44%. This paper can provide help for researchers studying the areas of weaknesses analysis and for developers utilizing secure coding for weaknesses analysis.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.3
• /
• pp.134-139
• /
• 2023

Rehabilitators perform outpatient treatment and daily rehabilitation exercises to recover physical function with the aim of quickly returning to society after surgical treatment. Unlike performing exercises in a hospital with the help of a professional therapist, there are many difficulties in performing rehabilitation exercises by the patient on a daily basis. In this paper, we propose a CNN-LSTM-based upper limb rehabilitation real-time monitoring system so that patients can perform rehabilitation efficiently and with correct posture on a daily basis. The proposed system measures biological signals through shoulder-mounted hardware equipped with EMG and IMU, performs preprocessing and normalization for learning, and uses them as a learning dataset. The implemented model consists of three polling layers of three synthetic stacks for feature detection and two LSTM layers for classification, and we were able to confirm a learning result of 97.44% on the validation data. After that, we conducted a comparative evaluation with the Teachable machine, and as a result of the comparative evaluation, we confirmed that the model was implemented at 93.6% and the Teachable machine at 94.4%, and both models showed similar classification performance.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.4
• /
• pp.189-198
• /
• 2024

Lipreading is one of the important parts of speech recognition, and several studies have been conducted to improve the performance of lipreading in lipreading systems for speech recognition. Recent studies have used method to modify the model architecture of lipreading system to improve recognition performance. Unlike previous research that improve recognition performance by modifying model architecture, we aim to improve recognition performance without any change in model architecture. In order to improve the recognition performance without modifying the model architecture, we refer to the cues used in human lipreading and set other regions such as chin and cheeks as regions of interest along with the lip region, which is the existing region of interest of lipreading systems, and compare the recognition rate of each region of interest to propose the highest performing region of interest In addition, assuming that the difference in normalization results caused by the difference in interpolation method during the process of normalizing the size of the region of interest affects the recognition performance, we interpolate the same region of interest using nearest neighbor interpolation, bilinear interpolation, and bicubic interpolation, and compare the recognition rate of each interpolation method to propose the best performing interpolation method. Each region of interest was detected by training an object detection neural network, and dynamic time warping templates were generated by normalizing each region of interest, extracting and combining features, and mapping the dimensionality reduction of the combined features into a low-dimensional space. The recognition rate was evaluated by comparing the distance between the generated dynamic time warping templates and the data mapped to the low-dimensional space. In the comparison of regions of interest, the result of the region of interest containing only the lip region showed an average recognition rate of 97.36%, which is 3.44% higher than the average recognition rate of 93.92% in the previous study, and in the comparison of interpolation methods, the bilinear interpolation method performed 97.36%, which is 14.65% higher than the nearest neighbor interpolation method and 5.55% higher than the bicubic interpolation method. The code used in this study can be found a https://github.com/haraisi2/Lipreading-Systems.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.7
• /
• pp.129-138
• /
• 2012

Despite of increasing pressure of opening to free for medical market by an advanced nation and increasing number of portal websites for health information, there have been few studies on the issues of enhancing the service quality of health information websites. The survey exhibited that the quality factors mainly affect significant and satisfied level of health information websites were usability, information structure and contents, interaction, and revisiting. This study was conducted to develop the consumer-focused quality factor of health information websites using WebQual model which was valued at efficient evaluation tool for this information system The methods taken in this research was to survey quality factors for significant and satisfied level of 323 consumers live in Chungcheong-do which is based on 48 questionnaires of WebQual quality factors. Our research extracted quality factors, usability, information quality (information structure and contents), interaction (personalisation and privacy) about view of criticality and satisfaction and relevant degree of revisiting. The research results presented in the paper will provide an efficient way of installing healthcare websites, moreover stone toward a marketing strategy for the consumer focus website provides under fierce competition.

• The Journal of the Korea Contents Association
• /
• v.20 no.3
• /
• pp.298-308
• /
• 2020

This study was designed to verify reliability and feasibility by analyzing elderly drivers' ability test tools for older drivers aged 65 or older, which were improved in 2018 and are currently being conducted by the Korea Highway Traffic Authority. Only those aged 65 or older who voluntarily applied to the elderly driving ability evaluation system implemented by the Seoul branch of the Korea Highway Traffic Authority. The research was conducted for about 50 days until Aug. 31, 2018, starting with the registration and inspection of the first study subjects. The analysis performed a correlation analysis with existing tools and cognitive testing tools (MMSE_K) to determine their feasibility and reliability as an improved tool in 2018. As a result, the first, the speed distance, time-space memory, and dispersionism of each sub-component of the old version showed statistically significant static correlation with the sub-factor of the current version. Persistence, on the other hand, was not statistically significant to the current version. The limitations of this study were as follows. Most of the people in the study were highly educated and residents in the metropolitan area. Therefore, it is likely that the results of MSE_K, which checks cognitive and judgment skills, have been upgraded. Also, cognitive tools that are measured by computers are likely to have real measurement errors for generations who are not familiar with computers. Therefore, it is expected that improvement and development of tools for improving the limit points at the site and assessing actual operation capability will be required.

• The Journal of the Korea Contents Association
• /
• v.4 no.1
• /
• pp.55-66
• /
• 2004

Recently, as the personal computers are supplied rapidly, they formed the nucleus of the computer system. But, because of the easiness that anyone uses them to go near easily, it is the fact that the security of personal computer is weakness. So, in the paper, 1 propose the technical method that minimizes the loss and leakage of important data. This paper implemented a crypto system for security of data file on personal computer and assistance storage medium. The way of encryption/decryption is applied by complexity method which mixed Diffie-Hellman key exchange protocol, a typical RC4(Rivest Cipher version 4) algorithm of stream cipher and a typical MD5(Message Digest version 5) of Hash Function. For valuation implemented crypto system, three criteria is presented, which are crypto complexity, processing time and pattern matching. And according to analysis the three criteria the crypto system is verified the security, efficiency and usefulness. The crypto system is programmed with Visual C++ language of Microsoft. And so, as this is software system, we shall have a technical security system at a minimum cost for all personal computer.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.3
• /
• pp.21-41
• /
• 2024

This study explores the relationship between users' attachment styles and their interactions with ChatGPT (Chat Generative Pre-trained Transformer), an advanced language model developed by OpenAI. As artificial intelligence (AI) becomes increasingly integrated into everyday life, it is essential to understand how individuals with different attachment styles engage with AI chatbots in order to build a better user experience that meets specific user needs and interacts with users in the most ideal way. Grounded in attachment theory from psychology, we are exploring the influence of attachment style on users' interaction with ChatGPT, bridging a significant gap in understanding human-AI interaction. Contrary to expectations, attachment styles did not have a significant impact on ChatGPT usage or reasons for engagement. Regardless of their attachment styles, hesitated to fully trust ChatGPT with critical information, emphasizing the need to address trust issues in AI systems. Additionally, this study uncovers complex patterns of attachment styles, demonstrating their influence on interaction patterns between users and ChatGPT. By focusing on the distinctive dynamics between users and ChatGPT, our aim is to uncover how attachment styles influence these interactions, guiding the development of AI chatbots for personalized user experiences. The introduction of the Perceived Partner Responsiveness Scale serves as a valuable tool to evaluate users' perceptions of ChatGPT's role, shedding light on the anthropomorphism of AI. This study contributes to the wider discussion on human-AI relationships, emphasizing the significance of incorporating emotional intelligence into AI systems for a user-centered future.

• KIPS Transactions on Computer and Communication Systems
• /
• v.7 no.6
• /
• pp.145-154
• /
• 2018

A loosely coupled message broker system is a popular method for integrating distributed software components. Especially, a distributed broker structure with multiple brokers with active-standby or active-active message replicas are used to enhance availability as well as message processing performance. However, there are problems in both active-standby and active-active replica structure. The active-standby has relatively low processing performance and The active-active structure requires a high synchronization overhead. In this paper, we propose an active-active structure of replicas to increase the availability of the brokers without compromising its high fault-tolerancy. In the proposed structure, standby replicas process the requests of the active replicas so that load balancing is achieved without additional brokers, while the distributed coordinators are used for the synchronization process to decrease the overhead. We formulated the overhead incurred when synchronizing messages among replicas, and the formulation was used to support the experiment results. From the experiment, we observed that replicas of the active-active structure show better performance than the active stand-by structure with increasing number of users.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.7
• /
• pp.191-198
• /
• 2021

Since the size of training dataset become large and the model is getting deeper to achieve high accuracy in deep learning, the deep neural network training requires a lot of computation and it takes too much time with a single node. Therefore, distributed deep learning is proposed to reduce the training time by distributing computation across multiple nodes. In this study, we propose hybrid allreduce strategy that considers the characteristics of each layer and communication and computational overlapping technique for synchronization of distributed deep learning. Since the convolution layer has fewer parameters than the fully-connected layer as well as it is located at the upper, only short overlapping time is allowed. Thus, butterfly allreduce is used to synchronize the convolution layer. On the other hand, fully-connecter layer is synchronized using ring all-reduce. The empirical experiment results on PyTorch with our proposed scheme shows that the proposed method reduced the training time by up to 33% compared to the baseline PyTorch.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.10
• /
• pp.2575-2583
• /
• 1998

The productionof the highly relible softwae systems and theirs performance evaluation hae become important interests in the software industry. The software evaluation has been mainly carried out in ternns of both reliability and performance of software system. Software reliability is the probability that no software error occurs for a fixed time interval during software testing phase. These theoretical software reliability models are sometimes unsuitable for the practical testing phase in which a software error at a certain testing stage occurs by causes of the imperfect debugging, abnornal software correction, and so on. Such a certatin software testing stage needs to be considered as an outlying stage. And we can assume that the software reliability does not improve by means of muisance factor in this outlying testing stage. In this paper, we discuss Bavesian software reliability growth modeling and estimation procedure in the presence of an imidentitied outlying software testing stage by the modification of Jehnski Moranda. Also we derive the Bayes estimaters of the software reliability panmeters by the assumption of prior information under the squared error los function. In addition, we evaluate the proposed software reliability growth model with an unidentified outlying stage in an exchangeable model according to the values of nuisance paramether using the accuracy, bias, trend, noise metries as the quantilative evaluation criteria through the compater simulation.