• Journal of Radiation Industry
• /
• v.9 no.3
• /
• pp.153-159
• /
• 2015

Reliability of printed circuit board (PCB), which is based on high integrated circuit technology, is having been important because of development of electric and self-driving car. In order to answer these demand, automated X-ray inspection (AXI) is best solution for PCB non-destructive test. PCB is consist of plastic, copper, and, lead, which have low to high Z-number materials. By using dual energy X-ray imaging, these materials can be inspected accurately and efficiently. Dual energy X-ray imaging, that have the advantage of separating materials, however, need some solution such as energy separation method and enhancing efficiency because PCB has materials that has wide range of Z-number. In this work, we found out several things by analysis of X-ray energy spectrum. Separating between lead and combination of plastic and copper is only possible with energy range not dose. On the other hand, separating between plastic and copper is only with dose not energy range. Moreover the copper filter of high energy part of dual X-ray imaging and 50 kVp of low energy part of dual X-ray imaging is best for efficiency.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.9
• /
• pp.339-348
• /
• 2021

In recent software defect prediction research, defect prediction between cross projects and cross-version projects are actively studied. Cross-version defect prediction studies assume WP(Within-Project) so far. However, in the CV(Cross-Version) environment, the previous work does not consider the distribution difference between project versions is important. In this study, we propose an automated Bayesian optimization framework that considers distribution differences between different versions. Through this, it automatically selects whether to perform transfer learning according to the difference in distribution. This framework is a technique that optimizes the distribution difference between versions, transfer learning, and hyper-parameters of the classifier. We confirmed that the method of automatically selecting whether to perform transfer learning based on the distribution difference is effective through experiments. Moreover, we can see that using our optimization framework is effective in improving performance and, as a result, can reduce software inspection effort. This is expected to support practical quality assurance activities for new version projects in a cross-version project environment.

• Journal of the Institute of Convergence Signal Processing
• /
• v.22 no.1
• /
• pp.1-6
• /
• 2021

Recently, unmanned facilities have been introduced and operated in a way that reduces the cost and development of IT technology. Although unmanned facilities have advantages in terms of efficiency and economy, they have disadvantages such as failure of unmanned facilities and malfunctions, causing damage to facilities caused by intruders, and information leakage. In addition, it is necessary to visit the person in charge at all times to inspect the unmanned facilities, resulting in management costs. In this paper, we designed a system that checks the status of unmanned surveillance facilities in real time to check and automatically recover problems such as malfunctions, and to notify managers of situations by text messages in real time. The system to be designed consists of an integrated network video server (NVR) that receives and determines information on the operation status of the main equipment such as video, sound, and lighting, and a real-time text message using an SMS server.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.4
• /
• pp.95-105
• /
• 2021

Road surface damage detection is essential for a comfortable driving environment and the prevention of safety accidents. Road management institutes are using automated technology-based inspection equipment and systems. As one of these automation technologies, a sensor to detect road surface damage plays an important role. For this purpose, several studies on sensors using deep learning have been conducted in recent years. Road images and label images are needed to develop such deep learning algorithms. On the other hand, considerable time and labor will be needed to secure label images. In this paper, the adversarial learning method, one of the semi-supervised learning techniques, was proposed to solve this problem. For its implementation, a lightweight deep neural network model was trained using 5,327 road images and 1,327 label images. After experimenting with 400 road images, a model with a mean intersection over a union of 80.54% and an F1 score of 77.85% was developed. Through this, a technology that can improve recognition performance by adding only road images was developed to learning without label images and is expected to be used as a technology for road surface management in the future.

• Journal of the Korean Society of Radiology
• /
• v.16 no.7
• /
• pp.969-974
• /
• 2022

In order to maximize dynamic range and to minimize image lag in digital X-ray imaging, diminishing residual parasitic capacitance in photodiode in pixels is critically necessary. These requirements are more specifically requested in dynamic X-ray imaging with high frame rate and low image lag for industrial 2D/3D automated X-ray inspection and medical CT imaging. This study proposes duoPIX^TM X-ray imaging sensor for the first time that is composed of reset thin film transistor, readout thin film transistor and photodiode in a pixel. To verify duoPIX^TM X-ray imaging sensor, designing duoPIX^TM pixel and imaging sensor was executed first then X-ray imaging sensor with 105 ㎛ pixel pitch, 347 mm × 430 mm imaging area and 3300 × 4096 pixels (13.5M pixels) was fabricated and evaluated by using module tester and image viewer specifically for duoPIX^TM imaging sensor.

• Journal of the Korean Society of Radiology
• /
• v.17 no.4
• /
• pp.625-631
• /
• 2023

The important requirement of industrial dynamic X-ray detector operating under high tube voltage up to 450 kVp for 24 hours and 7 days is to obtain significantly high radiation resistance. This study presents the radiation resistance characteristics of various thin film transistors (TFTs) with a-Si, poly-Si and IGZO semiconducting layers. IGZO TFT offering dozens of times higher field effect mobility than a-Si TFT was processed with highly hydrogenated plasma in between IGZO semiconducting layer and inter-layered dielectric. The hydrogenated IGZO TFT showed most sustainable radiation resistance up to 10,000Gy accumulated, thus, concluded that it is a sole switching device in X-ray imaging sensor offering dynamic X-ray imaging at high frame rate under extremely severe radiation environment such as automated X-ray inspection.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.237-239
• /
• 2021

Failure and malfunction of the unmanned surveillance facility cost can lead to delays occurring until the person in charge arrives at the unmanned surveillance facility, and theft, damage, and information leakage damage caused by intruders. In addition, due to equipment failure and malfunction, additional costs are incurred due to constant inspection by the manager. In this paper, in order to compensate for the malfunction of unmanned facility costs, we propose a system that diagnoses the monitoring facility in real time, displays the contents of the problem, automatically restores the facility power, and informs the person in charge of the situation by text message. The proposed system is a surveillance facility consisting of main facilities such as video equipment (CCTV), sound equipment, floodlights, etc. And SMS server that can send text messages in real time. Through experiments, the effectiveness of the proposed system was verified.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.849-854
• /
• 2023

The Korea Post is providing postal, savings, and insurance services to the public. Although it has been automated due to the development of the industry, the risk of industrial accidents is high. Safety and health education should be effectively conducted to reduce industrial accidents. In this study, a survey was conducted for postal service workers. As a result, there was a tendency to prefer instructors with technical experience and professional qualifications, and increasing direct participation training through on-site inspection and audio-visual training and hands-on training were found to be helpful. analyzed. Based on this, an efficient safety and health education plan was presented to improve safety and health awareness, and it can be used as a basic data

• The Korean Journal of Nuclear Medicine Technology
• /
• v.16 no.1
• /
• pp.108-114
• /
• 2012

Purpose: Immunosorbent assay most commonly used in the laboratory and commercial third-party quality control material is a substance that provided by BIO-RAD. However, in Reference Sheet by radioimmunoassay test kit or a measuring device for the mention of Acceptable Range is somewhat lacking. Radioimmunoassay for the inspection of test results by setting Acceptable Range to increase the objectivity of the recommendations on the data accumulated by the manufacturer listed in the Reference Sheet is to be issued. Materials and Methods : In our hospital since 2009 partially BIO-RAD using quality control materials in 2011, excluding certain items, some items were most of the BIO-RAD third-party quality control materials are used. Thus, internal quality control data accumulated BIO-RAD's Unity Real Time program by using the items were measured. Results : BIO-RAD using quality control material items were about 50 of the 20 Point Data averages, standard deviations, variation coefficients were calculated to measure the Acceptable Range of kit, automated immunoassay attributed Roche Elecsys / E170 / cobas e Systems the measures and compared. Conclusions : BIO-RAD QC materials commonly used hospital and peer group by setting the measurement kit, suitable for laboratory equipment for radioimmunoassay of Acceptable Range manufacturer recommendation to increase the objectivity of the test results by national and international recognition for radioimmunoassay should seek to increase.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.28 no.5
• /
• pp.436-442
• /
• 2008

Graphite material has been recognized as a very competitive candidate for reflector, moderator, and structural material for very high temperature reactor (VHTR). Since VHTR is operated up to $900-950^{\circ}C$, small amount of impurity may accelerate the oxidation and degradation of carbon graphite, which results in increased porosity and lowered fracture toughness. In this study, ultrasonic wave propagation properties were investigated for both as-received and degradated material, and the feasibility of ultrasonic testing (UT) was estimated based on the result of ultrasonic property measurements. The ultrasonic properties of carbon graphite were half, more than 5 times, and 1/3 for velocity, attenuation, and signal-to-noise (S/N) ratio respectively. Degradation reduces the ultrasonic velocity slightly by 100 m/s, however the attenuation is about 2 times of as-receive state. The results of probability of detection (POD) estimation based on S/N ratio for side-drilled-hole (SDHs) of which depths were less than 100 mm were merely affected by oxidation and degradation. This result suggests that UT would be reliable method for nondestructive testing of carbon graphite material of which thickness is not over 100 mm. In accordance with the result produced by commercial automated ultrasonic testing (AUT) system, human error of ultrasonic testing is barely expected for the material of which thickness is not over 80 mm.