• 산업경영시스템학회지
• /
• 제44권4호
• /
• pp.169-176
• /
• 2021

Maritime monitoring requirements have been beyond human operators capabilities due to the broadness of the coverage area and the variety of monitoring activities, e.g. illegal migration, or security threats by foreign warships. Abnormal vessel movement can be defined as an unreasonable movement deviation from the usual trajectory, speed, or other traffic parameters. Detection of the abnormal vessel movement requires the operators not only to pay short-term attention but also to have long-term trajectory trace ability. Recent advances in deep learning have shown the potential of deep learning techniques to discover hidden and more complex relations that often lie in low dimensional latent spaces. In this paper, we propose a deep autoencoder-based clustering model for automatic detection of vessel movement anomaly to assist monitoring operators to take actions on the vessel for more investigation. We first generate gridded trajectory images by mapping the raw vessel trajectories into two dimensional matrix. Based on the gridded image input, we test the proposed model along with the other deep autoencoder-based models for the abnormal trajectory data generated through rotation and speed variation from normal trajectories. We show that the proposed model improves detection accuracy for the generated abnormal trajectories compared to the other models.

• Nuclear Engineering and Technology
• /
• 제48권1호
• /
• pp.129-143
• /
• 2016

Sometimes, we need or try to figure out somebody's thoughts from his or her behaviors such as eye movement, facial expression, gestures, and motions. In safety-critical and complex systems such as nuclear power plants, the inference of operators' thoughts (understanding or diagnosis of a current situation) might provide a lot of opportunities for useful applications, such as development of an improved operator training program, a new type of operator support system, and human performance measures for human factor validation. In this experimental study, a novel method for inference of an operator's thoughts from his or her eye movement data is proposed and evaluated with a nuclear power plant simulator. In the experiments, about 80% of operators' thoughts can be inferred correctly using the proposed method.

• 감성과학
• /
• 제14권2호
• /
• pp.221-226
• /
• 2011

인체의 동작 센싱 방법에 대한 연구가 다양하게 진행되어 왔으나, 기존의 동작 센싱 방식에는 많은 한계점들이 있다. 기존의 동작 센싱 방식의 한계점을 보완하기 위한 일환의 노력으로, 이 논문에서는 비구속적인 동작 센싱이 가능한 광섬유 기반 의류 소매형 동작센서를 탐색적으로 연구하는데 목표를 두었다. 이 논문에서는 광섬유 기반의 의류 소매형 동작 센서를 고안하고, 이를 통하여 일상생활 중에 다양한 동작을 센싱하는 것이 가능한가에 대하여 탐색적 연구를 수행하였다. 또한 본 연구의 범위는 광섬유 기반 동작센서의 가능성 여부와 주요 요건을 탐색하는 것이며, 소매 패턴과 봉제 방식의 특성, 착용자의 체형 특성이 미친 영향은 연구 범위에서 제외되었다. 이러한 방식으로 의복에 적용 가능하도록 고안된 광섬유 기반 의류 소매형 동작센서는, 기존의 동작 센싱 시스템에 비하여 더욱 미세한 인체 동작 측정이 가능하며 시간 공간의 제약 없이 저 비용으로 인체 동작 측정이 가능하다는 장점을 갖는다.

• Steel and Composite Structures
• /
• 제35권6호
• /
• pp.779-788
• /
• 2020

Multi-Walled Carbon nanotubes (MWCNT) coupled with Silicone Rubber (SR) can represent applicable strain sensors with accessible materials, which result in good stretchability and great sensitivity. Employing these materials and given the fact that the combination of these two has been addressed in few studies, this study is trying to represent a low-cost, durable and stretchable strain sensor that can perform excellently in a high number of repeated cycles. Great stability was observed during the cyclic test after 2000 cycles. Ultrahigh sensitivity (GF>1227) along with good extensibility (ε>120%) was observed while testing the sensor at different strain rates and the various number of cycles. Further investigation is dedicated to sensor performance in the detection of human body movements. Not only the sensor performance in detecting the small strains like the vibrations on the throat was tested, but also the larger strains as observed in extension/bending of the muscle joints like knee were monitored and recorded. Bearing in mind the applicability and low-cost features, this sensor may become promising in skin-mountable devices to detect the human body motions.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권4호
• /
• pp.88-95
• /
• 2022

Detecting anomalies in human movement is an important task in industrial applications, such as monitoring industrial disasters or accidents and recognizing unauthorized factory intruders. In this paper, we propose an abnormal worker movement detection system based on data stream processing and hierarchical clustering. In the proposed system, Apache Spark is used for streaming the location data of people. A hierarchical clustering-based anomalous trajectory detection algorithm is designed for detecting anomalies in human movement. The algorithm is integrated into Apache Spark for detecting anomalies from location data. Specifically, the location information is streamed to Apache Spark using the message queuing telemetry transport protocol. Then, Apache Spark processes and stores location data in a data frame. When there is a request from a client, the processed data in the data frame is taken and put into the proposed algorithm for detecting anomalies. A real mobility trace of people is used to evaluate the proposed system. The obtained results show that the system has high performance and can be used for a wide range of industrial applications.

• Journal of Forest and Environmental Science
• /
• 제38권2호
• /
• pp.128-132
• /
• 2022

Wild boars (Sus scrofa) not only cause crop damage and human casualties, but also facilitate the spread of many infectious diseases in domestic animals and humans. To determine the efficiency of a fencing system in blocking the movement of wild boars, long-term monitoring was performed in a fenced area in Bukhansan National Park using camera traps. Upon monitoring for a period of 46 months, there was a 72.6% reduction in the number of wild boar appearances in the fence-enclosed area, compared to that in the unenclosed area. For 20 months after the fence installation, the blocking effect of the fence was effective enough to reduce the appearance of wild boars by 92.6% in the fence-enclosed area, compared to that in the unenclosed area. The blocking effect of the fence remained effective for 20 months after its installation, after which its effectiveness decreased. Maintaining a fence for a long time is likely to lead to habitat fragmentation. It can also block the movement of other wild animals, including the endangered species - the long-tailed goral. This study suggests a 20-month retention period for the fences installed to inhibit the movement of wild boars in wide forests such as Gangwon-do in South Korea. To identify how long the blocking effect of the fences lasts, further studies are needed focusing on the length and height of the fence, and the conditions of the ground surface.

• 로봇학회논문지
• /
• 제4권2호
• /
• pp.130-138
• /
• 2009

Recently, people tracking technology is being required to various area including security application. This paper suggests a method to track people with multiple laser scanners to detect the waist part of human. Multi-target model and Kalman filter based estimation are employed to track the human movement. The proposed method is applied to a novel system to monitor the entrance area and to filter out the trespasser to pass through the door without identification. Experiments for various cases are performed to verify the usefulness of the developed system.

• International Journal of Contents
• /
• 제16권3호
• /
• pp.1-17
• /
• 2020

Human motion recognition is essential for user-centric services such as surveillance-based security, elderly condition monitoring, exercise tracking, daily calories expend analysis, etc. It is typically based on the movement data analysis such as the acceleration and angular velocity of a target user. The existing motion recognition studies are only intended to measure the basic information (e.g., user's stride, number of steps, speed) or to recognize single motion (e.g., sitting, running, walking). Thus, a new mechanism is required to identify the transition of single motions for assessing a user's consecutive motion more accurately as well as recognizing the user's body and surrounding situations arising from the motion. Thus, in this paper, we collect the human movement data through Android smartphones in real time for five targeting single motions and propose a mechanism to recognize a consecutive motion including transitions among various motions and an occurred situation, with the state transition model to check if a vulnerable (life-threatening) condition, especially for the elderly, has occurred or not. Through implementation and experiments, we demonstrate that the proposed mechanism recognizes a consecutive motion and a user's situation accurately and quickly. As a result of the recognition experiment about mix sequence likened to daily motion, the proposed adoptive weighting method showed 4% (Holding time=15 sec), 88% (30 sec), 6.5% (60 sec) improvements compared to static method.

• 비파괴검사학회지
• /
• 제35권1호
• /
• pp.68-72
• /
• 2015

초음파 로봇 검사시스템은 발전설비 등 상시감시가 요구되는 구조물의 감시를 위해 연구와 개발이 활발히 진행되고 있다. 그러나 이러한 설비의 구조물은 형상과 구조가 매우 다양하고 복잡하여 단순한 패턴으로 이동과 검사가 가능한 로봇으로는 상시감시에 한계를 가지게 된다. 복잡한 구조물의 정밀검사는 정교한 행동이 가능한 로봇 시스템이 필요하다. 로봇의 제어를 초음파검사 작업자의 손의 형상에 따라 직관적으로 움직이도록 한다면 보다 정밀한 검사 로봇의 개발이 가능할 것으로 판단된다. 폴리머 굽힘센서는 대변형의 측정이 가능하고 곡면에 적용성이 높아 최근 인체 형상 측정 및 재활보조 등 다양한 활용을 위한 연구가 활발히 진행되고 있다. 본 연구에서는 구조물의 상시감시를 위한 초음파검사 로봇이 작업자의 손동작에 따라 동작이 가능한 직관적 제어를 위해 폴리머 굽힘센서를 이용하여 사람 손의 형상 감시 연구를 수행하였다. 다수의 센서를 적용하여 손의 다양한 움직임을 추정하고 실험적 검증을 통해 사람 손의 형상에 따른 직관적 로봇의 제어가 가능함을 확인하였다.

• 복식
• /
• 제65권1호
• /
• pp.118-135
• /
• 2015

In recent years, smart clothing had been developed in order to better detect and monitor physical movement of the patient, so that such activities such as location identification and biometric recognition could be done. However, most of the sensing devices of smart clothing were limited to smart sensing sports clothing and the designs did not consider the physical characteristics and the behavior of the wearer. Therefore, this study aimed to create an open protection system by developing a wearable sensing device for health monitoring and location information. For this purpose, this study developed eleven types of wearable sensing design that could be commercially sold and worn by people who needed their biological information to be constantly monitored. The study conducted four tests in order to develop three types of sensing devices for various sensing wears. The purpose of this study was to expand the user rang of smart sensing wears, and provide a foundation for the development of distinctive wearable sensing devices reflecting the user. Furthermore, contribute to the design for the person subject to protection.