• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.12
• /
• pp.291-306
• /
• 2020

Nowadays, Data-Network-AI (DNA)-based intelligent services and applications have become a reality to provide a new dimension of services that improve the quality of life and productivity of businesses. Artificial intelligence (AI) can enhance the value of IoT data (data collected by IoT devices). The internet of things (IoT) promotes the learning and intelligence capability of AI. To extract insights from massive volume IoT data in real-time using deep learning, processing capability needs to happen in the IoT end devices where data is generated. However, deep learning requires a significant number of computational resources that may not be available at the IoT end devices. Such problems have been addressed by transporting bulks of data from the IoT end devices to the cloud datacenters for processing. But transferring IoT big data to the cloud incurs prohibitively high transmission delay and privacy issues which are a major concern. Edge computing, where distributed computing nodes are placed close to the IoT end devices, is a viable solution to meet the high computation and low-latency requirements and to preserve the privacy of users. This paper provides a comprehensive review of the current state of leveraging deep learning within edge computing to unleash the potential of IoT big data generated from IoT end devices. We believe that the revision will have a contribution to the development of DNA-based intelligent services and applications. It describes the different distributed training and inference architectures of deep learning models across multiple nodes of the edge computing platform. It also provides the different privacy-preserving approaches of deep learning on the edge computing environment and the various application domains where deep learning on the network edge can be useful. Finally, it discusses open issues and challenges leveraging deep learning within edge computing.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.3
• /
• pp.91-98
• /
• 2021

Today's information and communication technology is rapidly developing, the security of IT infrastructure is becoming more important, and at the same time, cyber attacks of various forms are becoming more advanced and sophisticated like intelligent persistent attacks (Advanced Persistent Threat). Early defense or prediction of increasingly sophisticated cyber attacks is extremely important, and in many cases, the analysis of network-based intrusion detection systems (NIDS) related data alone cannot prevent rapidly changing cyber attacks. Therefore, we are currently using data generated by intrusion detection systems to protect against cyber attacks described above through Host-based Intrusion Detection System (HIDS) data analysis. In this paper, we conducted a comparative study on machine learning algorithms using LID-DS (Leipzig Intrusion Detection-Data Set) host-based intrusion detection data including thread information, metadata, and buffer data missing from previously used data sets. The algorithms used were Decision Tree, Naive Bayes, MLP (Multi-Layer Perceptron), Logistic Regression, LSTM (Long Short-Term Memory model), and RNN (Recurrent Neural Network). Accuracy, accuracy, recall, F1-Score indicators and error rates were measured for evaluation. As a result, the LSTM algorithm had the highest accuracy.

• Journal of Digital Convergence
• /
• v.19 no.8
• /
• pp.319-325
• /
• 2021

With the advancement of wireless technology and the rapid growth of the infrastructure of mobile communication technology, systems applying AI-based platforms are drawing attention from users. In particular, the system that understands users' tastes and interests and recommends preferred items is applied to advanced e-commerce customized services and smart homes. However, there is a problem that these recommendation systems are difficult to reflect in real time the preferences of various users for tastes and interests. In this research, we propose a Fuzzy-AHP-based movies recommendation system using the Gated Recurrent Unit (GRU) language model to address a problem. In this system, we apply Fuzzy-AHP to reflect users' tastes or interests in real time. We also apply GRU language model-based models to analyze the public interest and the content of the film to recommend movies similar to the user's preferred factors. To validate the performance of this recommendation system, we measured the suitability of the learning model using scraping data used in the learning module, and measured the rate of learning performance by comparing the Long Short-Term Memory (LSTM) language model with the learning time per epoch. The results show that the average cross-validation index of the learning model in this work is suitable at 94.8% and that the learning performance rate outperforms the LSTM language model.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.1
• /
• pp.67-74
• /
• 2022

In recent, the number of real-time traffic information sources and providers has increased as increasing smartphone users and intelligent transportation system facilities installed at roadways including vehicle detection system (VDS), dedicated short-ranged communications (DSRC), and global positioning system (GPS) probe vehicle. The accuracy of such traffic information would vary with these heterogeneous information sources or spatiotemporal traffic conditions. Therefore, the purpose of this study is to propose an empirical strategy of heterogeneous information fusion to improve the accuracy of real-time traffic information. To carry out this purpose, travel speed data collection based on the floating car technique was conducted on 227 freeway links (or 892.2 km long) and 2,074 national highway links (or 937.0 km long). The average travel speed for 5 probe vehicles on a specific time period and a link was used as a ground truth measure to evaluate the accuracy of real-time heterogeneous traffic information for that time period and that link. From the statistical tests, it was found that the proposed fusion strategy improves the accuracy of real-time traffic information.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.5
• /
• pp.28-41
• /
• 2022

A road system with CV(Connected Vehicle)s, which is often referred to as a cooperative intelligent transportation system (C-ITS), provides various road information to drivers using an in-vehicle warning system. Road environments with CVs induce drivers to reduce their speed or change lanes to avoid potential risks downstream. Such avoidance maneuvers can be considered to improve driving behaviors from a traffic safety point of view. Thus, empirically evaluating how a given in-vehicle warning information affects driving behaviors, and monitoring of the correlation between them are essential tasks for traffic operators. To quantitatively evaluate the effect of in-vehicle warning information, this study develops a method to calculate compliance rate of drivers where two groups of speed profile before and after road information is provided are compared. In addition, conventional indexes (e.g., jerk and acceleration noise) to measure comfort of passengers are examined. Empirical tests are conducted by using PVD (Probe Vehicle Data) and DTG (Digital Tacho Graph) data to verify the individual effects of warning information based on C-ITS constructed in Seoul metropolitan area in South Korea. The results in this study shows that drivers tend to decelerate their speed as a response to the in-vehicle warning information. Meanwhile, the in-vehicle warning information helps drivers to improve the safety and comport of passengers.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.453-453
• /
• 2021

도시지역 비점오염원관리, 물순환 회복, 침투 및 증발산량 증가, 열섬현상 저감을 위한 주요한 방안으로 저영향개발(low impact development, LID)과 그린인프라 기법의 적용되고 있다. LID 시설은 소규모 분산형 시설로써 넓은 지역에 많고 다양한 시설들이 적용되어 시설의 개수가 많으며, 수질 및 토양 내 기성제품에 대한 센서들의 가격은 고가로 형성되어 있어 기기의 경제성 및 유지관리 등 적용하는데 제한적이다. 따라서 과거 모니터링 자료를 기반으로 오염물질들과의 상관성 분석을 통하여 계측이 어려운 항목들을 계측가능한 항목들로부터 예측 가능하며, 선정된 항목들에 대한 비용효율적인 센서를 개발하여 실시간 LID 모니터링이 가능한 비용효율적 모니터링을 개발하였다. 공주대학교 천안캠퍼스의 LID 시설들은 2013년에 조성되어 현재까지 시설이 운영되고 있으며, 5년이상의 과거 강우시 모니터링 자료들을 이용하여 오염물질 상관성 분석을 수행가능 하기에 대상지로 선정하였다. 오염물질 상관성 분석은 2013년부터 2017년도에 침투도랑에서 수행된 강우시 모니터링 자료를 활용하여 각 오염물질들의 상관성을 분석을 수행하였다. 침투도랑 내 유입되는 평균 유입수는 TSS 286.1±318.3 mg/L, BOD 22.6±39.5 mg/L, TN 8.96±5.85 mg/L, TP 1.01±1.11 mg/L로 나타났다. 겨울철에 비해 여름철에서의 오염물질의 유입농도가 높은 것으로 분석되었다. 이는 여름철 고온건조로 인한 노면 내 차량의 주행으로 인한 중금속, 폐타이어 등과 장마철 강우 시 유출된 토사로 인하여 유입수의 농도가 높은 것으로 분석되었다. 오염물질 부하량은 TSS와 COD 0.66으로 유의성이 높은 것으로 나왔으며, COD와 TSS, TP, TN 등 유의성이 높은 것으로 분석되었다. Arduino와 Raspberry PI를 활용하여 저비용 센서와 LTE 모뎀통신과 데이터 베이스 연결하여 개발된 프로그램을 통해서 무선으로 LID 시설에 대한 모니터링을 침투화분2와 식생체류지에 조성하였다. 전력공급이 어려운 식생체류지의 경우 태양열(Solar system) 시스템과 보조 전력 배터리를 조성하여 장마철이나 장기적인 악천후로 인한 전력을 생산하지 못할 경우 보조전력배터리에서 전력을 제공하여 지속적인 모니터링이 이루어지도록 설계하였다. 토양함수량, 토양온도와 Conductivity 등 3종류의 센서를 적용하였으며, 프로그램은 현재 2단계를 통한 2차수정을 통하여 프로그램을 구축하였다. 오차, 오작동, 계측값에 대한 검·보정 작업이 필요하다. 또한 대기자료의 구축을 통해 보다 토양과 LID 시설에 대한 영향분석이 필요한 것으로 사료된다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.23 no.2
• /
• pp.119-131
• /
• 2024

Understanding accurate traffic performance is crucial for ensuring efficient highway operation and providing a sustainable mobility environment. On the other hand, an immediate and precise estimation of highway traffic performance faces challenges because of infrastructure and technological constraints, data processing complexities, and limitations in using integrated big data. This paper introduces a framework for estimating traffic performance by analyzing real-time data sourced from toll collection systems and dedicated short-range communications used on highways. In particular, this study addresses the data errors arising from segmented information in data, influencing the individual travel trajectories of vehicles and establishing a more reliable Origin-Destination (OD) framework. The study revealed the necessity of trip linkage for accurate estimations when consecutive segments of individual vehicle travel within the OD occur within a 20-minute window. By linking these trip ODs, the daily average highway traffic performance for South Korea was estimated to be248,624 thousand vehicle kilometers per day. This value shows an increase of approximately 458 thousand vehicle kilometers per day compared to the 248,166 thousand vehicle kilometers per day reported in the highway operations manual. This outcome highlights the potential for supplementing previously omitted traffic performance data through the methodology proposed in this study.

• Knowledge Management Research
• /
• v.24 no.4
• /
• pp.131-152
• /
• 2023

One of the key domains within a smart tourism city, smart mobility, encompasses advanced transportation means and services rooted in Information and Communication Technology (ICT). This includes shared bicycles, scooters, car-sharing services, smart transportation infrastructure, and more, aiming to surpass limitations of conventional transport and improve the movement of people and goods. It also serves tourists as an affordable and convenient mode of transport between attractions while also enhancing the overall travel experience. This study has defined 'smart tourism mobility' as a form of mobility grounded in ICT, exhibiting exceptional connectivity, serving public interest, and serving as a mode of transport for both residents and tourists in a smart tourism city. The research aimed to outline the scope of smart tourism mobility-related industries through expert Delphi surveys and estimate their economic effects within a smart tourism city. Specifically, this study updated 2015 input-output table and made 2020 regional input-output table of Seoul adopting RAS method and location quotient method. The results showed that the about 2.8 billion KRW investment of Seoul in smart tourism mobility may create more than 4.1 billion KRW in production inducement effect which is expected to create more than 1.6 billion KRW of income-inducing effect, 3.6 billion KRW of value-added-inducing effect, and 54 employment across all industries in Seoul in 2022.

• Journal of Christian Education in Korea
• /
• v.76
• /
• pp.259-280
• /
• 2023

Purpose of study: This study aims to analyze the educational use of metaverses among pre-service nursing teachers at a university and explore the implications of designing and operating effective metaverse lessons. Research content and method: This study collected and analyzed data on the experiences and perceptions of 32 pre-nursing teachers enrolled in J University, a very small Christian-based university in Jeonju, Jeollabuk-do, Korea, who participated in a class using metaverses. And based on this, we analyzed the advantages, difficulties, and improvements of the class, differences from classes using Zoom, impressions of the class, and suggestions for effective classes. Conclusions and Suggestions: As a result of analyzing various aspects of perceptions and experiences of classes utilizing the metaverse, it was found that in order to conduct effective classes utilizing the metaverse, it is necessary to check the infrastructure for communication and devices before class, select a metaverse platform according to the goals and contents of the course, and build a space for educational activities. In addition, it was found that it is necessary to provide guidance on how to use the metaverse and conduct sufficient training before running classes with learner-centered teaching methods. In the future, it is expected that systematic research on the principles and teaching-learning models of classroom design using the metaverse will continue to be conducted.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.5
• /
• pp.551-561
• /
• 2024

Underground utility tunnels are spaces densely packed with various infrastructure facilities, such as power, telecommunications, and water supply and drainage systems, making internal environment management crucial. An investigation into accident cases and on-site demands in these tunnels revealed that while fires and floods are the most common types of incidents, the demand for real-time condensation prevention and response is frequent according to on-site managers. Condensation occurs due to the difference in humidity and temperature between the inside and outside of the tunnel. Frequent or prolonged condensation can lead to metal pipe corrosion, electrical failures, and reduced equipment lifespan. Therefore, this study developed a control algorithm and monitoring system to prevent condensation in underground utility tunnels. The proposed control algorithm estimates the likelihood of condensation in real-time based on the measured temperature and humidity and suggests appropriate responses for each stage to the managers. Finally, a practical condensation prevention monitoring system was built based on the developed algorithm, verifying the feasibility and applicability of this technology in the field.