• Smart Structures and Systems
• /
• 제29권5호
• /
• pp.653-660
• /
• 2022

Gravel scattering that is generated during operation of high-speed railway vehicle is cause to damage of vehicle such as windows, axle protector and so on. Especially, those are frequently occurred in winter season when snow ice is generated easily. Above all, damage of vehicle windows has not only caused maintenance cost but also increased psychological anxiety of passengers. Various methods such as heating system using copper wire, heating jacket and heating air are applied to remove snow ice generated on the under-body of vehicle. However, the methods require much run-time and man power which can be low effectiveness of work. Therefore, this paper shows that large-area heating system was developed based on heating coat in order to fundamentally prevent snow ice damage on high-speed railway vehicle in the winter season. This system gives users high convenience because that can remotely control the heating system using IoT-based wireless communication. For evaluating the applicability to railroad sites, a field test on an actual high-speed railroad operation was conducted by applying these techniques to the brake cylinder of a high-speed railroad vehicle. From the results, it evaluated how input voltage and electric power per unit area of the heating specimen influences exothermic performance to draw the permit power condition for icing. In the future, if the system developed in the study is applied at the railroad site, it may be used as a technique for preventing all types of damages occurring due to snow ice in winter.

• Smart Structures and Systems
• /
• 제29권5호
• /
• pp.661-675
• /
• 2022

In this paper, an electric vehicle drives with efficient control and low cost hardware using four quadrant DC converter with Permanent Magnet Direct Current (PMDC) motor fed by DC boost converter is presented. The main idea of this work is to improve the energy efficiency of the conversion chain of an electric vehicle by inserting a boost converter between the battery and the four quadrant-DC motor chopper assembly. Consequently, this method makes it possible to maintain the amplification gain of the 4 quadrant chopper constant regardless of the battery voltage drop and even in the presence of a fault in the battery. One of the most important control problems is control under heavy uncertainty conditions. The higher order sliding mode control technique is introduced for the adjustment of DC bus voltage and mechanical motor speed. To implement the proposed approach in the automotive field, experimental tests were carried out. The performances obtained show the usefulness of this system for a better energy management of an electric vehicle and an ideal control under different operating conditions and constraints, mostly at nominal operation, in the presence of a load torque, when reversing the direction of rotation of the motor speed and even in case of battery chamber failure. The whole system has been tested experimentally and its performance has been analyzed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권5호
• /
• pp.1339-1355
• /
• 2023

Localization is a hot research spot for many areas, especially in the mobile robot field. Due to the weak signal of the global positioning system (GPS), the alternative schemes in an indoor environment include wireless signal transmitting and receiving solutions, laser rangefinder to build a map followed by a re-localization stage and visual positioning methods, etc. Among all wireless signal positioning techniques, Wi-Fi is the most common one. Wi-Fi access points are installed in most indoor areas of human activities, and smart devices equipped with Wi-Fi modules can be seen everywhere. However, the localization of a mobile robot using a Wi-Fi scheme usually lacks orientation information. Besides, the distance error is large because of indoor signal interference. Another research direction that mainly refers to laser sensors is to actively detect the environment and achieve positioning. An occupancy grid map is built by using the simultaneous localization and mapping (SLAM) method when the mobile robot enters the indoor environment for the first time. When the robot enters the environment again, it can localize itself according to the known map. Nevertheless, this scheme only works effectively based on the prerequisite that those areas have salient geometrical features. If the areas have similar scanning structures, such as a long corridor or similar rooms, the traditional methods always fail. To address the weakness of the above two methods, this work proposes a coarse-to-fine paradigm and an improved localization algorithm that utilizes Wi-Fi to assist the robot localization in a geometrically similar environment. Firstly, a grid map is built by using laser SLAM. Secondly, a fingerprint database is built in the offline phase. Then, the RSSI values are achieved in the localization stage to get a coarse localization. Finally, an improved particle filter method based on the Wi-Fi signal values is proposed to realize a fine localization. Experimental results show that our approach is effective and robust for both global localization and the kidnapped robot problem. The localization success rate reaches 97.33%, while the traditional method always fails.

• International journal of advanced smart convergence
• /
• 제11권4호
• /
• pp.206-215
• /
• 2022

For a long time, traditional culture has been regarded as one of the sources of the inspiration, method and language of Chinese writing. In this article, we studied the medium- and long-term impact of a traditional Chinese culture seminar attended by college students on the output of creative writing. The seminar included traditional Chinese philosophy, history, literature, art, etc. It spanned three years (22 months) and held lectures lasting for approximately two hours once a week. The subjects of the prospective cohort study included 130 first-year college students who participated in the seminar and 130 controls. From September 2016 to June 2018, 72 lectures were held. We measured the creative writing output from the first lecture (September 2016) to December 2021 (64 months in total), including novels, essays, poems, and plays. Two indicators, the total number of words (TNW) and the quality of yield (QY), were evaluated by a 15-member panel. Although the TNW and QY of the participants and their controls were similar before the seminar, we found that the participants have higher TNW and QY than the controls after participating in the seminar. The difference in TNW became significant after month 51 (p<0.05), and the difference in QY became significant after month 46 (p<0.05). After these dates, the differences stabilized. In addition, text analysis indicates that by month 64, traditional cultural elements in the works of the participating group had a higher frequency (p<0.001). The research shows that the traditional culture seminar not only enhanced the yield of college students' creative writing but also improved the quality of their work. The traditional cultural elements enriched the works of the seminar participants.

• 한국정보통신학회논문지
• /
• 제26권11호
• /
• pp.1660-1665
• /
• 2022

최근 많은 산업체에서 3차원 스캐닝 기술을 활용하고 있다. 3D 스캐너의 성능이 향상됨에 따라 점데이터를 획득하면 후처리를 통해서 일정 비율만큼 줄이는 샘플링 단계를 수행하거나, 잡음이라고 판단되는 부분을 제거한다. 하지만, 이와 같은 추가과정 수행에도 불구하고 오랜 시간 동안 스캐닝하면 점데이터들을 한꺼번에 처리할 수 없다. 일반적으로 멀티스레드 환경을 이용하여 기획득된 점데이터를 먼저 처리하는 방식을 이용하지만, 스캐닝 프로세스 작업 시간이 증가함에 따라 다양한 환경 조건과 누적된 연산으로 인하여 점차 처리 성능이 낮아진다. 본 연구에서는 3D 스캐너로부터 실시간으로 들어오는 점데이터를 누적된 고속 특징점 히스토그램 계산을 이용하여 불필요하다고 판단되는 점데이터를 초기에 제거하는 방식을 제안한다. 이 방법을 이용하면 전체 3D 스캐닝 프로세스의 속도 향상을 가져온다.

• 융합보안논문지
• /
• 제22권2호
• /
• pp.27-42
• /
• 2022

4차 산업혁명 시대에는 산업혁신이라는 목표를 달성하기 위해 기존 산업의 생산성을 높일 수 있는 디지털 전환이 더욱 중요해지고 있다. 디지털 전환에는 디지털 뉴딜과 스마트 국방 등이 있으며, 이들은 인공지능과 빅데이터 분석기술, 사물인터넷을 이용한다. 이러한 변화는 사이버공간을 지속해서 확장함으로써 국가의 국방, 사회, 보건 등의 산업화 영역을 더 지능적인 새로운 서비스들로 혁신하고 있다. 하지만 이로 인해 업무 생산성, 효율성, 편리성, 산업 안전성 등은 강화되겠지만, 디지털 전환영역의 확대로 사이버공격에 따른 위험성 또한 지속해서 증가할 것이다. 본 고의 목표는 이러한 위협에 선제적으로 대응하기 위해 미래의 변화로 나타날 수 있는 위협시나리오를 고찰하고, 이를 해결할 근본적인 대안 중의 하나인 미래의 복합안보 상황에서 요구되는 4차 산업혁명 시대의 선제적 위협 대응 모델을 제안한다. 본고는 향후 미래 사회에서 사이버 위협에 능동적으로 대응할 사이버안보 전략과 기술 개발의 선행 연구로 활용할 수 있을 것이다.

• International Journal of Computer Science & Network Security
• /
• 제23권7호
• /
• pp.155-164
• /
• 2023

Machine learning with its high precision algorithms, Precision agriculture (PA) is a new emerging concept nowadays. Many researchers have worked on the quality and quantity of PA by using sensors, networking, machine learning (ML) techniques, and big data. However, there has been no attempt to work on trends of artificial intelligence (AI) techniques, dataset and crop type on precision agriculture using internet of things (IoT). This research aims to systematically analyze the domains of AI techniques and datasets that have been used in IoT based prediction in the area of PA. A systematic literature review is performed on AI based techniques and datasets for crop management, weather, irrigation, plant, soil and pest prediction. We took the papers on precision agriculture published in the last six years (2013-2019). We considered 42 primary studies related to the research objectives. After critical analysis of the studies, we found that crop management; soil and temperature areas of PA have been commonly used with the help of IoT devices and AI techniques. Moreover, different artificial intelligence techniques like ANN, CNN, SVM, Decision Tree, RF, etc. have been utilized in different fields of Precision agriculture. Image processing with supervised and unsupervised learning practice for prediction and monitoring the PA are also used. In addition, most of the studies are forfaiting sensory dataset to measure different properties of soil, weather, irrigation and crop. To this end, at the end, we provide future directions for researchers and guidelines for practitioners based on the findings of this review.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.291-295
• /
• 2022

본 논문은 시민들의 Life Style 변화에 대응하고 송산그린시티의 미래상을 달성하기 위해 기술과 주거, 산업, 관광레저 등 기능이 상호 효율적으로 융합된 환경친화적 첨단도시를 건설하기 위하여 스마트도시에 적용한 u-상수도 관로파손감지시스템 구축기술에 대하여 기술하기로 한다. 관로파손감지시스템은 송산그린시티 동측지구내 상수도관 상부에 설치되는 스마트예방시트, 관로파손감지기, 관파손감지 소프트웨어, 서버 등으로 구성되며 중앙제어부(관파손감지소프트웨어, 서버)는 화성시 맑은물사업소내에 설치되어 SKT의 WCDMA방식의 무선통신망을 통하여 현장에서 화성시로 데이터를 전송하고 있다. 본 시스템은 굴착공사중 시설물 파손을 예방하고 관로 손상여부를 실시간으로 감지하여 이벤트 발생위치를 관리자에게 알려주여 누수손실을 예방하여 시설물의 수명연장을 도모한다.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2022년도 춘계학술대회
• /
• pp.385-386
• /
• 2022

현재 전세계 해운물류 선진국들은 앞다퉈 자동화 터미널, 공유플랫폼 등 다양한 디지털 기술을 도입하며 스마트항만을 구축하고 있다. 이처럼 자원 활용 효율 향상 및 작업 유휴시간 최소화를 통한 항만 전반에 걸친 효율화의 중요성이 증가하고 있다. 이에 본 연구에서는 자원 활용 효율 향상을 위한 방법의 하나로 개선된 Y/T(Yard Truck) 배차 방식을 제안하고자 한다. 이를 위해, 기존 배차 방식의 문제점을 분석하고 이와 관련한 제약사항을 종합적으로 고려한 Y/T 배차 알고리즘을 개발한다. 또한, 부산 신항 컨테이너터미널 운영 데이터를 기반으로 터미널 혼잡 상황에 따른 다양한 시나리오를 가정하고 시나리오에 대해 기존 배차 방식과 Y/T 배차 알고리즘을 적용한 시뮬레이션 실험을 실시한 후 분석결과를 바탕으로 Y/T 배차 알고리즘 활용에 따른 운영적 효과를 평가한다.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2022년도 추계학술대회
• /
• pp.388-389
• /
• 2022

최근 인공지능 분야는 자율주행, 로봇 및 스마트 통신등 다양한 분야에 응용되고 있다. 현재의 인공지능 응용분야는 파이썬을 기반으로 한 tensor flow를 이용하는 소프트웨어 방식을 이용하고 있으며, 프로세서로는 PC의 그래픽 카드 내부에 존재하는 GPU (Graphics Processing Unit)를 이용하고 있다. 그러나 GPU 기반의 소프트웨어 방식은 하드웨어를 변경할 수 없다는 문제점을 가지고 있다. 이러한 문제점으로 인해 높은 수준의 판단이나 작업을 요구하는 경우에는 이에 적합한 높은 사양의 GPU가 필요하며, 이러한 경우에는 인공지능 작업을 처리하는 그래픽 카드로 교체해야 한다. 이러한 문제점을 해결하기 위해 본 연구에서는 HDL (Hardware Description Language)을 이용하여 반도체 내부의 회로를 변경할 수 있는 FPGA (Field Programmable Gate Array)를 기반으로 한 신경망 회로를 이용하여 합성곱 신경망 기반의 인공지능 시스템을 구현하고자 한다.