• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.47 no.2
• /
• pp.10-20
• /
• 2024

In recent automated manufacturing systems, compressed air-based pneumatic cylinders have been widely used for basic perpetration including picking up and moving a target object. They are relatively categorized as small machines, but many linear or rotary cylinders play an important role in discrete manufacturing systems. Therefore, sudden operation stop or interruption due to a fault occurrence in pneumatic cylinders leads to a decrease in repair costs and production and even threatens the safety of workers. In this regard, this study proposed a fault detection technique by developing a time-variant deep learning model from multivariate sensor data analysis for estimating a current health state as four levels. In addition, it aims to establish a real-time fault detection system that allows workers to immediately identify and manage the cylinder's status in either an actual shop floor or a remote management situation. To validate and verify the performance of the proposed system, we collected multivariate sensor signals from a rotary cylinder and it was successful in detecting the health state of the pneumatic cylinder with four severity levels. Furthermore, the optimal sensor location and signal type were analyzed through statistical inferences.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.1311-1311
• /
• 2024

Recent advances in artificial intelligence technology have led to active research aimed at systematically managing the productivity and environmental impact of major management targets such as heavy equipment at construction sites. However, challenges arise due to phenomena like partial occlusions, resulting from the dynamic working environment of construction sites (e.g., equipment overlapping, obstruction by structures), which impose practical constraints on precisely monitoring heavy equipment. To address these challenges, this study aims to enhance automated multi-object tracking (MOT) in scenarios involving long-term occlusions across consecutive frames for heavy construction equipment. To achieve this, two methodologies are employed to address long-term occlusions at construction sites: (i) tracking-by-detection and (ii) video inpainting with generative adversarial networks (GANs). Firstly, this study proposes integrating FairMOT with a tracking-by-detection algorithm like ByteTrack or SMILEtrack, demonstrating the robustness of re-identification (Re-ID) in occlusion scenarios. This method maintains previously assigned IDs when heavy equipment is temporarily obscured and then reappears, analyzing location, appearance, or motion characteristics across consecutive frames. Secondly, adopting video inpainting with GAN algorithms such as ProPainter is proposed, demonstrating robustness in removing objects other than the target object (e.g., excavator) during the video preprocessing and filling removed areas using information from surrounding pixels or other frames. This approach addresses long-term occlusion issues by focusing on a single object rather than multiple objects. Through these proposed approaches, improvements in the efficiency and accuracy of detection, tracking, and activity recognition for multiple heavy equipment are expected, mitigating MOT challenges caused by occlusions in dynamic construction site environments. Consequently, these approaches are anticipated to play a significant role in systematically managing heavy equipment productivity, environmental impact, and worker safety through the development of advanced construction and management systems.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.4
• /
• pp.1361-1364
• /
• 2012

Background: Results of screening colonoscopy from Western countries reported adenoma detection rates (ADRs) of 30-40% while those from Asia had ADR as low as 10%. There have been limited data regarding screening colonoscopy in Thailand. The objectives of this study were therefore to determine polyp and adenoma detection rates in Thai people, to evaluate the incidence of colorectal cancer detected during screening colonoscopy and to determine the endoscopic findings of the polyps which might have some impact on endoscopists to perform polypectomy. Materials & Methods: This study was a retrospective electronic chart review of asymptomatic Thai adults who underwent screening colonoscopy in our endoscopic center from June 2007 to October 2010.Results: A total of 1,594 cases were reviewed. The patients had an average age of $58.3{\pm}10.5$ years (range 27-82) and 55.5% were female. Most of the cases (83.8%) were handled by staff who were endoscopists. A total of 488 patients (30.6%) were reported to have colonic polyps. Left-sided colon was the most common site (45.1%), followed by right-sided colon (36.5%) and the rectum (18%). Those polyps were removed in 97.5% of cases and 88.5 % of the polyps were sent for histopathology (data lost 11.5%). Two hundred and sixty three cases had adenomatous polyps, accounting for 16.5 % ADR. Advanced adenomas were detected in 43 cases (2.6%). Hyperplastic polyps were mainly located distal to the splenic flexure of the colon whereas adenomas were found throughout the large intestine. Ten cases (0.6%) were found to have colorectal cancer. Four advanced adenomas and two malignant polyps were reported in lesions ${\leq}$ 5 mm. Conclusion: The polyp detection rate, adenoma detection rate, advanced adenoma detection rate and colorectal cancer detection rate in the screening colonoscopy of Thai adults were 30.9%, 16.5%, 2.6% and 0.6% respectively. Malignant transformation was detected regardless of the size and location of the polyps. Therefore, new technology would play an important role indistinguishing polyps.

• Journal of Internet Computing and Services
• /
• v.17 no.6
• /
• pp.1-8
• /
• 2016

Current indoor intrusion detection and location tracking methods have the weakness in seamless operations in tracking the objective because the object must possess a communicating device and the limitation of the single cell size (approximate $100cm{\times}100cm$) exits. Also, the utilization of CCTV technologies show the shortcomings in tracking when the object disappear the area where the CCTV is not installed or illumination is not enough for capturing the scene (e.g. where the context-awarded system is not installed or low illumination presents). Therefore, in this paper we present an improved in-door tracking system based on sensor networks. Such system is built on a simulated scenario and enables us to detect and extend the area of surveillance as well as actively responding the emergency situation. Through simulated studies, we have demonstrated that the proposed system is capable of supplementing the shortcomings of signal cutting, and of estimating the location of the moving object. We expect the study will improve the better analysis of the intruder behavior, the more effective prevention and flexible response to various emergency situations.

• Journal of the Korean earth science society
• /
• v.42 no.6
• /
• pp.688-699
• /
• 2021

On September 23, 2020, at 1:39 a.m., a bright fireball above Seocheon was observed across the country. Two fireball explosions were identified in the images of the All-Sky Camera (ASC), and the shock waves were recorded at seismic and infrasound stations in the southwestern Korean Peninsula. The location of the explosion was estimated by a Bayesian-based location method using the arrival times of the fireball-associated seismic and infrasound signals at 17 stations. Realistic azimuth- and rang-dependent propagation speeds of sound waves were incorporated into the location method to increase the reliability of the results. The location of the sound source was found to be 36.050°N, 126.855°E at an altitude of 35 km, which was close to the location of the second fireball explosion. The two explosions were identified as sequential infrasound arrivals at local infrasound stations. Simulations of waveforms for long ranges explain the detection results at distant infrasound stations, up to ~266 km from the sound source. The dominant period of the signals recorded at five infrasound stations is about 0.4 s. A period-energy relation suggests the explosion energy was equivalent to ~0.3 ton of TNT.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2008.04a
• /
• pp.197-202
• /
• 2008

In this paper, a hybrid vibration-impedance approaches is newly proposed to detect the occurrence of damage, the location of damage, and extent of damage in steel plate-girder bridges. The hybrid scheme mainly consists of three sequential phases: 1) to alarm the occurrence of damage, 2) to classify the alarmed damage, and 3) to estimate the classified damage in detail. Damage types of interest include flexural stiffness-loss in girder and bolts-loose in supports. In the first phase, the global occurrence of damage is alarmed by monitoring changes in acceleration features. In the second phase, the alarmed damage is classified into subsystems by recognizing patterns of impedance features. In the final phase, the location and the extent of damage are estimated by using modal strain energy-based damage index method and root mean square deviation method. The feasibility of the proposed system is evaluated on a laboratory-scaled steel plate-girder bridge model for which hybrid vibration-impedance signatures were measured for several damage scenarios.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.3
• /
• pp.901-920
• /
• 2015

Wireless Sensor Networks (WSNs) are widely used in geographically isolated applications like military border area monitoring, battle field surveillance, forest fire detection systems, etc. Uninterrupted power supply is not possible in isolated locations and hence sensor nodes live on their own battery power. Localization of sensor nodes in isolated locations is important to identify the location of event for further actions. Existing localization algorithms consume more energy at sensor nodes for computation and communication thereby reduce the lifetime of entire WSNs. Existing approaches also suffer with less localization coverage and localization accuracy. The objective of the proposed work is to increase the lifetime of WSNs while increasing the localization coverage and localization accuracy. A novel intelligent unmanned aerial vehicle anchor node (IUAN) is proposed to reduce the communication cost at sensor nodes during localization. Further, the localization computation cost is reduced at each sensor node by the proposed intelligent arc selection (IAS) algorithm. IUANs construct the location-distance messages (LDMs) for sensor nodes deployed in isolated locations and reach the Control Station (CS). Further, the CS aggregates the LDMs from different IUANs and computes the position of sensor nodes using IAS algorithm. The life time of WSN is analyzed in this paper to prove the efficiency of the proposed localization approach. The proposed localization approach considerably extends the lifetime of WSNs, localization coverage and localization accuracy in isolated environments.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10c
• /
• pp.616-620
• /
• 2006

한 해에도 수많은 해킹 사고가 발생하고 있고, 이 중에서 웹 해킹이 차지하는 비율은 급격하게 증가하고 있다. 또한 최근의 해킹 동향을 분석해 보았을 때 웹 해킹의 비율은 더욱 증가할 것이라고 예상된다. HTTP 프로토콜을 이용한 공격의 특성 상 정상행위와 비정상 행위의 구분이 어렵다. 따라서 웹 서비스에 특화된 침입탐지 시스템이 요구된다. 또한 웹 사이트 관리자는 빠른 탐지와 대응을 위해 이상 행위에 대한 신속하고 정확한 인식을 필요로 한다. 본 논문에서는 이러한 필요성을 기반으로 Location-based Visualization Tool을 제안한다. 웹 사용 현황 및 이상행위에 대해 시각적인 정보를 제공하기 위해 웹 서버의 access log를 분석하여 이상 행위를 탐지하였고, IP정보를 기반으로 지역 정보의 시각화를 구현하였다.

• Journal of Korea Multimedia Society
• /
• v.19 no.11
• /
• pp.1837-1851
• /
• 2016

Newspaper reader mobile applications using text-to-speech (TTS) function enable blind people to read newspaper contents. But, tables cannot be easily read by the reader program because most of the tables are stored as images in the contents. Even though we try to use OCR (Optical character reader) programs to recognize letters from the table images, it cannot be simply applied to the table reading function because the table structure is unknown to the readers. Therefore, identification of exact location of each table cell that contains the text of the table is required beforehand. In this paper, we propose an efficient image processing algorithm to recognize all the cells in tables by identifying columns and rows in table images. From the cell location data provided by the table column and row identification algorithm, we can generate table structure information and table reading scenarios. Our experimental results with table images found commonly in newspapers show that our cell identification approach has 100% accuracy for simple black and white table images and about 99.7% accuracy for colored and complicated tables.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.20 no.6
• /
• pp.568-576
• /
• 2010

It is widely known that the leak locating of underground plastic pipelines is much more difficult than that of cast iron pipelines. The precision of the leak locating depends upon the speed of leak signal and the time delay estimation between the two sensors on the pipeline. In this paper, six different windowing filters are considered to improve the time delay estimation especially for the plastic pipelines. The time delay is usually estimated from the peak time of cross-correlation functions. The filtering windows including rectangle, Roth, Wiener, SCOT, PHAT and maximum likelihood are applied to derive the generalized cross-correlation function and compared each other. Experimental results for the actual plastic underground water supply pipeline show that the introduction of the filtering windows improved the precision of time delay estimation. Some window functions provide excellent leak locating capability for the plastic pipe of 98 m long, which is less than 1 % of the pipe lengths. Also a new probabilistic approach that the combinations of all results from each filtering window is suggested for the better leak locating.