• Journal of Internet Computing and Services
• /
• v.20 no.3
• /
• pp.119-128
• /
• 2019

This study aims to analyze the research trends on Smart City and to present implications to policy maker, industry professional, and researcher. Cities around globe have undergone the rapid progress in urbanization and the consequent dramatic increase in urban dwellings over the past few decades, and faced many urban problems in such areas as transportation, environment and housing. Cities around the globe are in a hurry to introduce Smart City to pursue a common goal of solving these urban problems and improving the quality of their lives. However, various conceptual approaches to smart city are causing uncertainty in setting policy goals and establishing direction for implementation. The study collected 11,527 papers titled "Smart City(cities)" from the Scopus DB and Springer DB, and then analyze research status, topic, trends based on abstracts and publication date(year) information using the LDA based Topic Modeling approaches. Research topics are classified into three categories(Services, Technologies, and User Perspective) and eight regarding topics. Out of eight topics, citizen-driven innovation is the most frequently referred. Additional topic network analysis reveals that data and privacy/security are the most prevailing topics affecting others. This study is expected to helps understand the trends of Smart City researches and predict the future researches.

• 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.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.5
• /
• pp.591-598
• /
• 2019

The statistics of committing suicide in S. Korea is ranked in top with serious attempts of falling among OECD countries since 2003. The rates is slightly dropped by 5 percent point, nevertheless the falling is still high for the age of over 10 years old and this matter must be solved. Most of the case of suicides are the falling based on a trend view of falling which is serious matter and cannot be solved easily for both domestic and foreign countries. For example, the steel net of falling prevent was installed in the Golden Gate Bridge costed by 200 million-dollar. In New Zealand, the steel net of falling prevention had been removed and re-installed beccause of the high suicide rates. Canada and Australia also surrounded the bridge with steel fences to prevent suicide without consideration of the beauty of bridge. Therefore, this paper suggested a comparison study on both falling prevention systems in all countries and patent technologies. Also, it covers the blocking skills of approach in both security and limited area. This paper suggested the technical Rollinder system equipped with the mechanical apprentice to prevent effectively the falling sucides and wall passing. Before the installation of Rollinder System by 2016, there were 33 person who tried to fall in the river in Machang Bridge. However, the number of the committing suicides were dramatically reduced to zero after the installation of the system.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.4
• /
• pp.470-478
• /
• 2019

As the growth of the domestic defense industry is remarkable regarding technology level and export size, technology protection is necessary. Particularly, there is a need to apply anti-tamper measures to prevent critical technologies from illegally being taken out of weapon systems. However, there is no security protection strategy and system built yet in ROK. Precedent studies discussed the trend analysis and technical research for specific protective techniques, and the application of anti-tamper using limited procedures was provided. Recently, methods of how to select the technology for protection were studied based on risk management. Nonetheless, these studies cannot be associated with the acquisition process for the whole life-cycle, having difficulty with actual development and evaluation of the weapon systems. The objective of our study is to derive the system requirements of the weapon system for which anti-tamper measures have been determined to apply. Specifically, requirements items suitable for the development of anti-tamper weapon systems were derived based on ISO/IEC 19790, the CMVP standard for the development and verification of cryptographic modules. Also, its utilization in technical reviews and test & evaluations was presented. The usefulness of the research results was confirmed through inductive inference and comparative evaluation. The result can be expected to play a role in initiating extensive activities needed for technology protection of the weapon systems.

• Journal of Convergence for Information Technology
• /
• v.12 no.1
• /
• pp.76-82
• /
• 2022

Recently, natural and social disasters in Korea are increasing, and new disasters such as COVID 19 and sinkholes, and large-scale disasters that combine natural and social disasters are occurring frequently. In order to reduce damage caused by disasters and effectively respond to disasters, the importance of disaster safety education is emerging because it is necessary to understand the awareness of disaster situations and the functional response process. Ministry of Public Interior and Security is providing disaster safety education for emergency managers through 54 specialized disaster safety education institutions. There is also a lack of experience facilities. This has a problem in that it makes it difficult for disaster safety personnel to effectively respond to disasters due to lack of experience in actual disaster sites. Also, unlike other education fields, the connection between disaster safety education contents and new technologies such as AI is still lacking. In this study, focusing on natural disaster, the current status and problems of domestic disaster safety education institutions and their contents are investigated and analyzed, and based on this, this study suggested improvement plans for domestic disaster safety education contents such as establishment of a unified disaster safety standard curriculum, production and distribution of disaster safety education experience contents using virtual reality technology and infotainment technology, and development of mobile AI tutoring service.

• Journal of the Korea Convergence Society
• /
• v.13 no.3
• /
• pp.67-75
• /
• 2022

Medical information is variously generated not only from medical devices but also from electronic devices. Recently, related convergence technologies from big data collection in healthcare to medical AI products for patient's condition analysis are rapidly increasing. However, there are difficulties in applying them because of independent developmental procedures. In this paper, we propose an intelligent hospital information system (iHIS) model to simplify and integrate research, development and application of medical AI technology. The proposed model includes (1) real-time patient data management, (2) specialized data management for medical AI development, and (3) real-time monitoring for patient. Using this, real-time biometric data collection and medical AI specialized data generation from patient monitoring devices, as well as specific AI applications of camera-based patient gait analysis and brain MRA-based cerebrovascular disease analysis will be introduced. Based on the proposed model, it is expected that it will be used to improve the HIS by increasing security of data management and improving practical use through consistent interface platformization.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.5
• /
• pp.913-926
• /
• 2022

As information is recognized as a core competency of organizations, organizations are increasingly investing in policies and technologies for information security(IS). Recently, as information exposure accidents by people have occurred continuously, interest in IS behaviors of organization insiders is increasing. This study aims to confirm the effect of the IS environment and support structure established by the organization on the intention of individuals to comply with IS. We conducted a survey of employees in organizations with IS policies and tested the hypothesis using the structural equation of AMOS 22.0 and Process 3.1 using 421 samples. As a result of the analysis, authentic leadership and justice climate, which are factors that build an IS environment, and communication and feedback, which are factors supporting IS compliance, have a positive effect on employees' compliance intention. In addition, authentic leadership, punishment, communication, and feedback were found to reinforce the positive impact of IS justice climate. As the study suggested the overall structural design direction to be pursued to reinforce insider's IS behavior, and the results help to achieve the IS goal.

• Journal of Convergence for Information Technology
• /
• v.11 no.5
• /
• pp.30-37
• /
• 2021

Various devices are connected to the Internet, and attacks using the Internet are occurring. Among such attacks, there are attacks that use malicious URLs to make users access to wrong phishing sites or distribute malicious viruses. Therefore, how to detect such malicious URL attacks is one of the important security issues. Among recent deep learning technologies, neural networks are showing good performance in image recognition, speech recognition, and pattern recognition. This neural network can be applied to research that analyzes and detects patterns of malicious URL characteristics. In this paper, performance analysis according to various parameters was performed on a method of detecting malicious URLs using neural networks. In this paper, malicious URL detection performance was analyzed while changing the activation function, learning rate, and neural network structure. The experimental data was crawled by Alexa top 1 million and Whois to build the data, and the machine learning library used TensorFlow. As a result of the experiment, when the number of layers is 4, the learning rate is 0.005, and the number of nodes in each layer is 100, the accuracy of 97.8% and the f1 score of 92.94% are obtained.

• Journal of Software Assessment and Valuation
• /
• v.16 no.1
• /
• pp.65-79
• /
• 2020

As Programmable Logic Controllers (PLCs), popular components in industrial control systems (ICS), are incorporated with the technologies such as micro-controllers, real-time operating systems, and communication capabilities. As the latest PLCs have been connected to the Internet, they are becoming a main target of cyber threats. This paper proposes two sanitizers that improve the security of uC/OS-II based firmware for a PLC. That is, we devise BU sanitizer for detecting out-of-bounds accesses to buffers and UaF sanitizer for fixing use-after-free bugs in the firmware. They can sanitize the binary firmware image generated in a desktop PC before downloading it to the PLC. The BU sanitizer can also detect the violation of control flow integrity using both call graph and symbols of functions in the firmware image. We have implemented the proposed two sanitizers as a prototype system on a PLC running uC/OS-II and demonstrated the effectiveness of them by performing experiments as well as comparing them with the existing sanitizers. These findings can be used to detect and mitigate unintended vulnerabilities during the firmware development phase.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.11
• /
• pp.449-456
• /
• 2021

An intrusion detection system is a technology that detects abnormal behaviors that violate security, and detects abnormal operations and prevents system attacks. Existing intrusion detection systems have been designed using statistical analysis or anomaly detection techniques for traffic patterns, but modern systems generate a variety of traffic different from existing systems due to rapidly growing technologies, so the existing methods have limitations. In order to overcome this limitation, study on intrusion detection methods applying various machine learning techniques is being actively conducted. In this study, a comparative study was conducted on data preprocessing techniques that can improve the accuracy of anomaly detection using NGIDS-DS (Next Generation IDS Database) generated by simulation equipment for traffic in various network environments. Padding and sliding window were used as data preprocessing, and an oversampling technique with Adversarial Auto-Encoder (AAE) was applied to solve the problem of imbalance between the normal data rate and the abnormal data rate. In addition, the performance improvement of detection accuracy was confirmed by using Skip-gram among the Word2Vec techniques that can extract feature vectors of preprocessed sequence data. PCA-SVM and GRU were used as models for comparative experiments, and the experimental results showed better performance when sliding window, skip-gram, AAE, and GRU were applied.