• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.5
• /
• pp.160-172
• /
• 2018

The method of estimating a position using a GPS has been applied to various fields including a navigation system of an automobile. However, since it is difficult to measure GPS signals indoors, it is difficult to locate specific objects indoors such as a building or factory. To overcome these limitations, this study proposes a system for object location estimation based on Bluetooth5 for the management of materials in factories. The object position estimation system consists of a Bluetooth signal generator, a receiver, and a database server. A signal generator based on Bluetooth Low Energy(BLE) is attached to the material and a receiver is appropriately arranged inside the factory. In this study, we propose "Diagonal Survey Method", a 4 - axis survey algorithm using four receivers to reduce the error of existing trilateration method. The proposed algorithm showed good performance compared to the conventional trilateration and we verified the effectiveness of the proposed system and algorithm by performing the experiment by installing the system in the factory.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.6
• /
• pp.573-581
• /
• 2019

In the era of the 4th Industrial Revolution, the necessity of training advanced engineering personnel with convergent creativity to handle technologies such as artificial intelligence, big data, and the internet of things (IoT) is increasing. In this paper, a new approach of engineering education based on academia-industrial cooperation and design-centered teaching technique for the students who need to learn practicable engineering skill with convergent creativity for the fourth industrial age is presented. It analyzes the strengths and weaknesses of the existing engineering education innovation activities, presents the practical necessities based on the experience of the educational system and the requirements of the educational environment, and analyzes the existing activities and the new roles. In particular, we discuss how to combine student-centered teaching methodology for effective design education, which is a key element of innovative engineering education. Most of the presented methods are verified by the authors' needs and effects in the education field.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.309-309
• /
• 2018

기후변화에 따른 강우의 규모와 발생빈도 증가로 농촌유역의 홍수 피해는 지속적으로 증가하고 있다. 하지만 우리나라의 홍수 피해 저감 대책은 도시지역의 대하천 주변으로 집중되어있으며, 소하천 및 농촌유역의 홍수 피해 저감에 대한 관리와 투자 노력은 부족한 실정이다. 특히, 최근 들어 갑작스런 집중호우 등으로 인한 농촌유역 돌발홍수 피해 사례가 증가하고 있으며, 이에 대응하기 위해서는 홍수 발생 등을 신속하게 파악하기 위한 돌발홍수 예경보 시스템 개발이 필요하다. 한편, 최근 산업의 혁신과 생산성 향상을 위한 새로운 패러다임으로 4차 산업혁명이 대두되고 있으며, 빅데이터와 인공지능 (Artificial Intelligence, AI)을 비롯하여 사물인터넷 (Internet of Things, IoT), 드론, 슈퍼컴퓨팅 등의 이른바 4차 산업혁명 기술을 활용한 연구가 수행되고 있다. 본 연구에서는 기후변화에 따른 농촌유역 홍수 피해를 저감하고 또한 사전에 대비하기 위해 빅데이터와 인공지능 등 4차 산업혁명 기술을 적용한 농촌유역 돌발홍수 예경보 시스템을 개발하고 그 적용성을 평가하고자 한다. 우선, 농촌유역의 홍수와 관련된 빅데이터 (기상 자료, 수문 자료, 기후변화 자료, 농업용 수리구조물 자료 등)를 토대로 정형 빅데이터와 비정형 빅데이터를 구분 추출하고 이를 연계 해석할 수 있는 시스템을 개발하였다. 추출한 정형 및 비정형 빅데이터를 활용하여 딥러닝을 기반으로 농촌유역의 홍수를 예측하고 홍수 예경보 기준에 따른 평가를 수행할 수 있는 시스템을 개발하였다. 과거 강우사상을 홍수 예경보 시스템에 적용하여 홍수 모의 결과를 도출하였으며, 재해연보 등과 비교 분석하여 시스템의 적용성을 분석하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.100-103
• /
• 2019

Due to the fourth industrial revolution called 'fusion and connection', interest in 'high connectivity society' and 'highland society' is increasing, and related objects are not limited to automation and connected cars. The Internet of Things is the main concern of the 4th Industrial Revolution and it is expected to play an important role in establishing the basis of the next generation mobile communication service. Several domestic and foreign companies have been studying various types of LPWANs for the construction of the Internet based on things, and there is Semtech's LoRaWAN technology as representative. LoRaWAN is a long-distance, low-power network designed to manage a large number of devices and sensors, with communications from hundreds to thousands to thousands of devices and sensors. In this paper, we analyze the optimum node capacity of gateway for maximum performance while reducing resource waste in using LoRaWAN.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.4
• /
• pp.553-568
• /
• 2024

Due to the rapid development of IoT technology and the increase in home activities after the COVID-19 pandemic, users' demand for smart homes has increased significantly. As the size of the smart home market increases every year and the number of users increases, the importance of personal information protection and various security issues is also growing. It often grants temporary users smart home owner rights and gives them access to the system. However, this can easily allow access to third parties because the authorities granted are not properly managed. In addition, it is necessary to prevent the possibility of secondary damage using personal information collected through smart home devices and sensors. Therefore, in this paper, to prevent indiscriminate access to smart home systems without reducing user convenience, access rights are subdivided and designed according to the functions and types of smart home devices, and a token-based user access control technique using personal devices is proposed.

• The Journal of the Korea Contents Association
• /
• v.18 no.2
• /
• pp.147-157
• /
• 2018

Recently, with the advancement of network technologies, and the activation of IoT and social network services, many graph stream data have been generated. As the relationship between objects in the graph streams changes dynamically, studies have been conducting to detect or analyze the change of the graph. In this paper, we propose a scheme to incrementally detect frequent patterns by using frequent patterns information detected in previous sliding windows. The proposed scheme calculates values that represent whether the frequent patterns detected in previous sliding windows will be frequent in how many future silding windows. By using the values, the proposed scheme reduces the overall amount of computation by performing only necessary calculations in the next sliding window. In addition, only the patterns that are connected between the patterns are recognized as one pattern, so that only the more significant patterns are detected. We conduct various performance evaluations in order to show the superiority of the proposed scheme. The proposed scheme is faster than existing similar scheme when the number of duplicated data is large.

• Advanced Industrial SCIence
• /
• v.2 no.3
• /
• pp.22-28
• /
• 2023

In this study, we conducted research on the automated trading of U.S. stocks through a volatility strategy using the Fear and Greed index. Volatility in the stock market is a common phenomenon that can lead to fluctuations in stock prices. Investors can capitalize on this volatility by implementing a strategy based on it, involving the buying and selling of stocks based on their expected level of volatility. The goal of this thesis is to investigate the effectiveness of the volatility strategy in generating profits in the stock market.This study employs a quantitative research methodology using secondary data from the stock market. The dataset comprises daily stock prices and daily volatility measures for the S&P 500 index stocks. Over a five-year period spanning from 2016 to 2020, the stocks were listed on the New York Stock Exchange (NYSE). The strategy involves purchasing stocks from the low volatility group and selling stocks from the high volatility group. The results indicate that the volatility strategy yields positive returns, with an average annual return of 9.2%, compared to the benchmark return of 7.5% for the sample period. Furthermore, the findings demonstrate that the strategy outperforms the benchmark return in four out of the five years within the sample period. Particularly noteworthy is the strategy's performance during periods of high market volatility, such as the COVID-19 pandemic in 2020, where it generated a return of 14.6%, as opposed to the benchmark return of 5.5%.

• Journal of Advanced Navigation Technology
• /
• v.27 no.6
• /
• pp.835-840
• /
• 2023

RFID(Radio Frequency Identification) systems are attracting attention as a key component of Internet of Things technology due to the cost and energy efficiency of application services. In order to use RFID technology in the IoT application service field, it is necessary to be able to store and manage various information for a long period of time as well as simple recognition between the reader and tag of the RFID system. And in order to read and write information to tags, a performance improvement technology that is strong and reliable in poor wireless channels is needed. In particular, in the UHF(Ultra High Frequency) RFID system, since multiple tags communicate passively in a crowded environment, it is essential to improve the recognition rate and transmission speed of individual tags. In this paper, Middleton's Class A impulsive noise model was selected to analyze the performance of the RFID system in an impulsive noise environment, and FM0 encoding and Miller encoding were applied to the tag to analyze the error rate performance of the RFID system. As a result of analyzing the performance of the RFID system in Middleton's Class A impulsive noise channel, it was found that the larger the Gaussian noise to impulsive noise power ratio and the impulsive noise index, the more similar the characteristics to the Gaussian noise channel.

• Journal of Internet of Things and Convergence
• /
• v.10 no.6
• /
• pp.49-55
• /
• 2024

In this paper, AI models for predicting peak power usage were developed and comparatively analyzed using data collected from the Jeju Samdasoo factory through a big data collection system based on IoT sensing technology. The LSTM (Long Short-Term Memory) model demonstrated the highest prediction accuracy for univariate time-series data, achieving an R² of 0.98, RMSE of 0.039, and MAE of 0.026. Meanwhile, the XGBoost (eXtreme Gradient Boosting) model effectively handled multivariate data, achieving an R² of 0.93, RMSE of 0.018, and MAE of 0.013. Various data preprocessing methods and feature combinations were experimentally applied to optimize model performance, highlighting the significant impact of preprocessing and variable selection on prediction accuracy. The findings suggest that optimized AI models for peak power prediction can reduce power costs and achieve approximately 10-15% reductions in carbon emissions. This study offers companies pursuing ESG (environmental, social, and governance) management practical and specific strategies for achieving sustainability, while demonstrating the applicability of the predictive model across various industries, including manufacturing, logistics, and smart factories.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.1
• /
• pp.163-169
• /
• 2020

Recently, research on automation and unmanned operation of machines in the industrial field has been conducted with the advent of AI, Big data, and the IoT, which are the core technologies of the Fourth Industrial Revolution. The machines for these automation processes are controlled based on the data collected from the sensors attached to them, and further, the processes are managed. Conventionally, the abnormalities of sensors are periodically checked and managed. However, due to various environmental factors and situations in the industrial field, there are cases where the inspection due to the failure is not missed or failures are not detected to prevent damage due to sensor failure. In addition, even if a failure occurs, it is not immediately detected, which worsens the process loss. Therefore, in order to prevent damage caused by such a sudden sensor failure, it is necessary to identify the failure of the sensor in an embedded system in real-time and to diagnose the failure and determine the type for a quick response. In this paper, a deep neural network-based fault diagnosis system is designed and implemented using Raspberry Pi to classify typical sensor fault types such as erratic fault, hard-over fault, spike fault, and stuck fault. In order to diagnose sensor failure, the network is constructed using Google's proposed Inverted residual block structure of MobilieNetV2. The proposed scheme reduces memory usage and improves the performance of the conventional CNN technique to classify sensor faults.