• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.3
• /
• pp.167-175
• /
• 2022

With the recent expansion of electric kickboards and bicycle sharing services, more and more people use them. In addition, the rapid growth of the delivery business due to the COVID-19 has significantly increased the use of two-wheeled vehicles and personal mobility. As the accident rate increases, the rule related to the two-wheeled vehicles is changed to 'mandatory helmets for kickboards and single-person transportation' and was revised to prevent boarding itself without driver's license. In this paper, we propose a wearable smart safety equipment, called SafetyHelmet, that can keep helmet-wearing duty and lower the accident rate with the communication between helmets and mobile devices. To make this function available, we propose a safe driving assistance function by notifying the driver when an object that interferes with driving such as persons or other vehicles are detected by applying the YOLO v5 object detection algorithm. Therefore it is intended to provide a safer driving assistance by reducing the failure rate to identify dangers while driving single-person transportation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.538-540
• /
• 2021

In this paper, we proposed a smart target detection system that detects and recognizes a designated target to provide relative motion information when performing a target detection mission of a drone. The proposed system focused on developing an algorithm that can secure adequate accuracy (i.e. mAP, IoU) and high real-time at the same time. The proposed system showed an accuracy of close to 1.0 after 100k learning of the Google Inception V2 deep learning model, and the inference speed was about 60-80[Hz] when using a high-performance laptop based on the real-time performance Nvidia GTX 2070 Max-Q. The proposed smart target detection system will be operated like a drone and will be helpful in successfully performing surveillance and reconnaissance missions by automatically recognizing the target using computer image processing and following the target.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.101-103
• /
• 2022

Elliptic curve cryptography (ECC) is widely used in hardware implementations of public-key crypto-systems for IoT devices and V2X communication because it is suitable for efficient hardware implementation and has high security strength. However, ECC-based public-key cryptography is known to have security vulnerabilities against side-channel attacks, so it is necessary to apply countermeasures against security attacks in designing ECC processor. This paper describes a survey on the side-channel attacks and countermeasures applicable to ECC processor design.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.6
• /
• pp.1462-1477
• /
• 2024

With the evolving complexity of connected vehicle features, the volume and diversity of data generated during driving continue to escalate. Enabling data sharing among interconnected vehicles holds promise for improving users' driving experiences and alleviating traffic congestion. Yet, the unintentional disclosure of users' private information through data sharing poses a risk, potentially compromising the interests of vehicle users and, in certain cases, endangering driving safety. Federated learning (FL) is a newly emerged distributed machine learning paradigm, which is expected to play a prominent role for privacy-preserving learning in autonomous vehicles. While FL holds significant potential to enhance the architecture of the Internet of Vehicles (IoV), the dynamic mobility of vehicles poses a considerable challenge to integrating FL with vehicular networks. In this paper, a novel clustered FL framework is proposed which is efficient for reducing communication and protecting data privacy. By assessing the similarity among feature vectors, vehicles are categorized into distinct clusters. An optimal vehicle is elected as the cluster head, which enhances the efficiency of personalized data processing and model training while reducing communication overhead. Simultaneously, the Local Differential Privacy (LDP) mechanism is incorporated during local training to safeguard vehicle privacy. The simulation results obtained from the 20newsgroups dataset and the MNIST dataset validate the effectiveness of the proposed scheme, indicating that the proposed scheme can ensure data privacy effectively while reducing communication overhead.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.441-442
• /
• 2021

본 논문에서는 고해상도의 시계열 위성영상을 딥러닝 알고리즘으로 학습하여 도시 변화탐지를 수행한다. 고해상도 위성영상을 활용한 서비스는 4 차 산업혁명 융합 신사업 중 하나인 스마트시티에 적용하여 도시 노후화, 교통 혼잡, 범죄 등 다양한 도시 문제 해결 및 효율적인 도시를 구축하는데 활용이 가능하다. 이에 본 연구에서는 도시 변화탐지를 위한 딥러닝 알고리즘으로 DeepLabV3+를 사용한다. 이는 인코더-디코더 구조로, 공간 정보를 점진적으로 회복함으로써 더욱 정확한 물체의 경계면을 찾을 수 있다. 제안하는 방법은 DeepLabV3+의 레이어와 loss function 을 수정하여 기존보다 좋은 결과를 얻었다. 객관적인 성능평가를 위해, 공개된 데이터셋 LEVIR-CD 으로 학습한 결과로 평균 IoU 는 0.87, 평균 Dice 는 0.93 을 얻었다.

• Journal of Korea Multimedia Society
• /
• v.19 no.5
• /
• pp.901-909
• /
• 2016

Unprecedented attention is being given to Smart Grid, Micro Grid and Internet of Things (IoT) in the Republic of Korea recently but such systems' effect is not well experienced by the market since they require additional and costly reforms for the existing household electrical system where adaptive communication platforms are needed. As such platforms, both wireless and wire communication technologies are being considered at the moment. Usually, they include WiFi, Zigbee technologies and the latter, LAN technology. However, communication speed decline due to signal attenuation and interference during wireless communications are considered to be the major problem and the extra works involving time and costs for the LAN system construction can be another demerit. Therefore, in this paper, we have introduced a Power Line Communication-based Smart Outlet System Expandable at Home to complement these disadvantages. Proposed IoT system involves Power Line Communication (PLC) technology which is essential to constructing a Smart Grid.

• Structural Monitoring and Maintenance
• /
• v.9 no.3
• /
• pp.289-303
• /
• 2022

In this study, the impact of assigned pixel labels on the accuracy of crack image identification of steel structures is examined by using an atrous separable convolution neural network (ASCNN). Firstly, images containing fatigue cracks collected from steel structures are classified into four datasets by assigning different pixel labels based on image features. Secondly, the DeepLab v3+ algorithm is used to determine optimal parameters of the ASCNN model by maximizing the average mean-intersection-over-union (mIoU) metric of the datasets. Thirdly, the ASCNN model is trained for various image sizes and hyper-parameters, such as the learning rule, learning rate, and epoch. The optimal parameters of the ASCNN model are determined based on the average mIoU metric. Finally, the trained ASCNN model is evaluated by using 10% untrained images. The result shows that the ASCNN model can segment cracks and other objects in the captured images with an average mIoU of 0.716.

• Nuclear Engineering and Technology
• /
• v.55 no.3
• /
• pp.1061-1070
• /
• 2023

Over the last few years, lead-free inorganic metal perovskites have gained impressive ground in empowering satellites in space exploration owing to their material stability and performance evolution under extreme space environments. The present work has examined the versatility of eight such perovskites as space radiation shielding materials by computing their photon, charged particles and neutron interaction parameters. Photon interaction parameters were calculated for a wide energy range using PAGEX software. The ranges of heavy charged particles (H, He, C, N, O, Ne, Mg, Si and Fe ions) in these perovskites were estimated using SRIM software in the energy range 1 keV-10 GeV, and that of electrons was computed using ESTAR NIST software in the energy range 0.01 MeV-1 GeV. Further, the macroscopic fast neutron removal cross-sections were also calculated to estimate the neutron shielding efficiencies. The examined shielding parameters of the perovskites varied depending on the radiation type and energy. Among the selected perovskites, Cs₂TiI₆ and Ba₂AgIO₆ displayed superior photon attenuation properties. A 3.5 cm thick Ba₂AgIO₆-based shield could reduce the incident radiation intensity to half its initial value, a thickness even lesser than that of Pb-glass. Besides, CsSnBr₃ and La_0.8Ca_0.2Ni_0.5Ti_0.5O₃ displayed the highest and lowest range values, respectively, for all heavy charged particles. Ba₂AgIO₆ showed electron stopping power (on par with Kovar) better than that of other examined materials. Interestingly, La_0.8Ca_0.2Ni_0.5Ti_0.5O₃ demonstrated neutron removal cross-section values greater than that of standard neutron shielding materials - aluminium and polyethylene. On the whole, the present study not only demonstrates the employment prospects of eco-friendly perovskites for shielding space radiations but also suggests future prospects for research in this direction.

• Korean Journal of Microbiology
• /
• v.35 no.3
• /
• pp.185-191
• /
• 1999

This study was conducted to investigate the vibrio flora in an edible shellfish. sunset shelfish. Soletelliim olivacen. which were collected in the estuarine area. Dadaepo near Nakdong River in Korea lkoin January 1997 to November 1997. Including five pathogemc vibrios (Vibrio alginolyticus, Vibrio pamhaemol~~licz~s, Vibrio cholerae non-01. Vibrio vulnificus, and Vihrio jl~~vinlis), a lotal of eight species of vlbr~os (Vi61-io splendidrrs biovar I, Vibrio splendidus biovar 11, Vibrio snlrnonicida and Vibrio tr,~biasllii) were identified from the sunset shellfish by heir biochemical characters. The isolation of Vihrio pamhaemolyricns, which is known not to grow below $15^{\circ}C$, in winter season indicates that the sunset shelllish is one oT the natural owl.- wintering hosts for Vibrio parahuemolyticus.

• International Journal of Advanced Culture Technology
• /
• v.9 no.4
• /
• pp.320-328
• /
• 2021

As the number of visually impaired people steadily increases, interest in independent walking is also increasing. However, there are various inconveniences in the independent walking of the visually impaired at present, reducing the quality of life of the visually impaired. The white cane, which is an existing walking aid for the visually impaired, has difficulty in recognizing upper obstacles and obstacles outside the effective distance. In addition, it is inconvenient to cross the street because the sound signal to help the visually impaired cross the crosswalk is lacking or damaged. These factors make it difficult for the visually impaired to walk independently. Therefore, we propose the design of an embedded system that provides traffic light recognition through object recognition technology, voice guidance using TTS, and upper obstacle recognition through ultrasonic sensors so that blind people can realize safe and high-quality independent walking.