• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.05a
• /
• pp.543-544
• /
• 2018

가상 현실 네비게이션을 위한 전방향 트레드밀은 사용자가 걷거나 달리면서 물리적으로 고정된 공간 내에 사용자를 유지할 수 있도록 지면 모션을 시뮬레이션하는 장비이다. 이러한 트레드밀 시스템의 성능이나 안정성을 정량적으로 측정하거나 분석하기가 어렵기 때문에 이전의 연구에서는 주관적 설문 조사와 같은 정성적 분석 방법을 사용하였다. 본 연구에서는 인간의 보행 경로와 유사한 궤도를 따라 움직이는 무인 차량 시스템을 이용한 새로운 정량적 데이터 측정 방법을 제안한다. 무인 차량 시스템은 미리 정의 된 인간의 보행 동작을 시뮬레이션하고 트레드밀 시스템에 대한 제어 입력을 제공하며, 다축 가속 및 방향과 같은 차량의 동적 데이터를 측정 할 수 있다. 또한 이 데이터는 평상시의 정기 또는 다른 제어 알고리즘과의 비교를 수행할 수 있다. 본 연구에서는 궤적 시뮬레이션 모듈, 데이터 수집 모듈, 성능 평가 모듈 등 전방향 트레드밀에 대한 정량 분석 방법의 설계 구조 및 초기구현 결과를 제시하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.05a
• /
• pp.541-542
• /
• 2018

CAE 와 같은 고충실도 대용량 엔지니어링 데이터의 시공간 정밀 분석검증을 위해서는 고해상도 몰입형 가시화 기술과 더불어 이를 직관적이고 효율적으로 제어하기 위한 휴먼 인터페이스 기술이 중요하다. 최근 대중화에 근접한 HMD 기기 및 컨트롤러를 이용한 응용 연구가 발표되고 있고, 이를 통해 엔지니어 위주의 정적 분석환경을 벗어나, 설계/해석/운용 전문가들의 동적 협업분석 환경 제공이 가능한 몰입형 가시화 환경 및 휴먼 인터페이스 기술이 적용되고 있다. 하지만 CAE 해석지원을 위한 대화면 몰입형 가시화 환경에서 사용가능한 직관적 인터페이스기술에 대한 연구는 미진한 상황이다. 본 연구에서는 신체의 자연스러운 움직임으로 가상현실을 탐색하고 데이터 조작을 구현할 수 있는 몰입형 가시화 전용의 휴먼 인터페이스 및 연동기술에 대한 연구과정을 소개한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.89-92
• /
• 2021

In a manufacturing fields, an abnormality or breakdown of equipment is a factor that causes product defects. Recently, with the spread of smart factory services, a lot of research to predict and prevent machine's failures is actively ongoing. However, there is a big difficulty in developing a classification model because the number of abnormal or failure data of the machine is severely smaller than normal data. In this paper, we present an algorithm for detecting abnormalities in an MCT at manufacturing work site depending on the differences between inputs and outputs of Autoencoder model and analyze its performance. The algorithm detects abnormalities using only features of normal data from manufacturing data of the MCT in which abnormal data does not exist.

• Smart Media Journal
• /
• v.12 no.1
• /
• pp.32-46
• /
• 2023

Natural Language Processing (NLP) has grown tremendously in recent years. Typically, bilingual, and multilingual translation models have been deployed widely in machine translation and gained vast attention from the research community. On the contrary, few studies have focused on translating between spoken and sign languages, especially non-English languages. Prior works on Sign Language Translation (SLT) have shown that a mid-level sign gloss representation enhances translation performance. Therefore, this study presents a new large-scale Korean sign language dataset, the Museum-Commentary Korean Sign Gloss (MCKSG) dataset, including 3828 pairs of Korean sentences and their corresponding sign glosses used in Museum-Commentary contexts. In addition, we propose a translation framework based on self-supervised learning, where the pretext task is a text-to-text from a Korean sentence to its back-translation versions, then the pre-trained network will be fine-tuned on the MCKSG dataset. Using self-supervised learning help to overcome the drawback of a shortage of sign language data. Through experimental results, our proposed model outperforms a baseline BERT model by 6.22%.

• Smart Media Journal
• /
• v.13 no.3
• /
• pp.45-52
• /
• 2024

In today's growing threat environment, rapid and effective detection and response to security events is essential. To solve these problems, many companies and organizations respond to security threats by introducing security control systems. However, existing security control systems are experiencing difficulties due to the complexity and diverse characteristics of security events. In this study, we propose an automated integrated security control system model based on artificial intelligence. It is based on deep learning, an artificial intelligence technology, and provides effective detection and processing functions for various security events. To this end, the model applies various artificial intelligence algorithms and machine learning methods to overcome the limitations of existing security control systems. The proposed model reduces the operator's workload, ensures efficient operation, and supports rapid response to security threats.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.48 no.4
• /
• pp.808-822
• /
• 2024

This study aims to develop a smart uniform with embedded luminescence for street cleaners to enhance visibility, safety, and long-term usability, informed by real users' opinions. It employed mixed-methods research comprising three phases: first, a pre-interview to identify existing problems; second, experiments to evaluate the visibility and durability of the technology embedded in smart uniforms during machine washing; and third, a post-survey and observation to assess user satisfaction regarding safety, long-term usability, and aesthetic aspects. Prototypes were developed to evaluate long-term usability and safety based on users' opinions. The findings indicated users desired long-term usage without the need for additional wear and highlighted concerns about the glare from light-emitting devices. The developed prototypes demonstrated long-term usability, remaining functional after more than 25 machine washes without reducing brightness or structural integrity. Regarding participant satisfaction, 83.5% of users were satisfied with the design, both aesthetically and functionally. This study offers a viable approach to developing user-centered designs incorporating light-emitting devices, which enhance visibility and provide aesthetic satisfaction while ensuring long-term usability. The results hold significant implications for future design research focused on vulnerable populations, emphasizing integrated satisfaction in terms of safety and long-term usability.

• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1071-1081
• /
• 2021

In addition to the current quality control procedures for the weather observation performed by the Korea Meteorological Administration (KMA), this study proposes quality inspection standards for Internet of Things (IoT) urban weather observed data based on machine learning that can be used in smart cities of the future. To this end, in order to confirm whether the standards currently set based on ASOS (Automated Synoptic Observing System) and AWS (Automatic Weather System) are suitable for urban weather, usability was verified based on SKT AWS data installed in Seoul, and a machine learning-based quality control algorithm was finally proposed in consideration of the IoT's own data's features. As for the quality control algorithm, missing value test, value pattern test, sufficient data test, statistical range abnormality test, time value abnormality test, spatial value abnormality test were performed first. After that, physical limit test, stage test, climate range test, and internal consistency test, which are QC for suggested by the KMA, were performed. To verify the proposed algorithm, it was applied to the actual IoT urban weather observed data to the weather station located in Songdo, Incheon. Through this, it is possible to identify defects that IoT devices can have that could not be identified by the existing KMA's QC and a quality control algorithm for IoT weather observation devices to be installed in smart cities of future is proposed.

• The KIPS Transactions:PartA
• /
• v.16A no.3
• /
• pp.209-216
• /
• 2009

The ubiquitous smart home is the home of the future that takes advantage of context information from the human and the home environment and provides an automatic home service for the human. Human location and motion are the most important contexts in the ubiquitous smart home. We present a real-time human tracker that predicts human location and motion for the ubiquitous smart home. We used four network cameras for real-time human tracking. This paper explains the real-time human tracker's architecture, and presents an algorithm with the details of two functions (prediction of human location and motion) in the real-time human tracker. The human location uses three kinds of background images (IMAGE1: empty room image, IMAGE2: image with furniture and home appliances in the home, IMAGE3: image with IMAGE2 and the human). The real-time human tracker decides whether the human is included with which furniture (or home appliance) through an analysis of three images, and predicts human motion using a support vector machine. A performance experiment of the human's location, which uses three images, took an average of 0.037 seconds. The SVM's feature of human's motion recognition is decided from pixel number by array line of the moving object. We evaluated each motion 1000 times. The average accuracy of all the motions was found to be 86.5%.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.6
• /
• pp.193-204
• /
• 2022

In a smart factory environment in a small and medium-sized enterprise (SME) environment, sensors and actuators operating on actual manufacturing lines, programmable logic controllers (PLCs) to manage them, human-machine interface (HMI) to control and manage such PLCs, and consists of operational technology server to manage PLCs and HMI again. PLC and HMI, which are in charge of control automation, perform direct connection with OT servers, application systems for factory operation, robots for on-site automation, and production facilities, so the development of security technology in a smart factory environment is demanded. However, smart factories in the SME environment are often composed of systems that used to operate in closed environments in the past, so there exist a vulnerable part to security in the current environment where they operate in conjunction with the outside through the Internet. In order to achieve the internalization of smart factory security in this SME environment, it is necessary to establish a process according to the IEC 62443-4-1 Secure Product Development Life cycle at the stage of smart factory SW and HW development. In addition, it is necessary to introduce a suitable development methodology that considers IEC 62443-4-2 Component security requirements and IEC 62443-3 System security requirements. Therefore, this paper proposes an application plan for the IEC 62443 based development security process to provide security internalization to smart factories in an SME environment.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.2
• /
• pp.165-170
• /
• 2021

Machine learning has recently been applied to research in most areas. This is because the results of machine learning are not determined, but the learning of input data creates the objective function, which enables the determination of new data. In addition, the increase in accumulated data affects the accuracy of machine learning results. The data collected here is an important factor in machine learning. The proposed system is a convergence system of cloud systems and local fog systems for service delivery. Thus, the cloud system provides machine learning and infrastructure for services, while the fog system is located in the middle of the cloud and the user to collect and refine data. The data for this application shall be based on the Sensitive data generated by smart devices. The machine learning technique applied to this system uses SVM algorithm for classification and RNN algorithm for status recognition.