• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.681-683
• /
• 2022

코로나 19 로 인해 사회적으로 활동 범위에 제약이 많아져 신체 노화가 진행중인 노년층의 심각한 운동 부족 현상 발생했다. 이에 따라 본 연구는 스마트 미러 트레이닝 프로그램의 범람 속에 신체적인 불편함을 가지고 있는 노인의 건강 증진에 주목하여 스마트 미러와 노인 자세 탐지, 자세 정확성 판단 시스템을 기반으로 한 자세 분류 서비스 제공 프로그램을 제안한다. 스마트 미러에 탑재된 카메라로 받아온 영상을 MoveNet 과 머신러닝 모델을 사용하여 사용자의 동작을 파악하는 방식으로 활동 프로그램을 진행한다. 향후 디지털 소외 계층의 사용 및 노인 자세 데이터 분석에 활용할 수 있을 것으로 기대한다.

• Nuclear Engineering and Technology
• /
• v.55 no.10
• /
• pp.3808-3814
• /
• 2023

The thermal stability of nitric acid solutions after contact with non-irradiated and irradiated tributyl phosphate (TBP) and its solution in Isopar-M has been studied. It has been established that exothermic processes occur during heating due to the interaction of soluble radiolysis products and the decomposition of the extractant with nitric acid. Such processes can occur at temperatures below 100 ℃, but unlike a thermal explosion that occurs in seconds, they are longer in time and are accompanied by weak heat evolution. Their intensity depends on the composition of the extractant, the concentration of HNO₃, and the volume ratio of the organic and aqueous phases. The presence of extractant degradation products in raffinates does not pose a risk of a rapid evolution of gaseous products during evaporation, however, the presence of reducing agents can significantly increase the intensity of the exothermic decomposition of raffinates.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.9-16
• /
• 2023

Technological advancement is being advanced in sports such as electronic protection of taekwondo competition and VAR of soccer. However, a person judges and guides the posture by looking at the posture, so sometimes a judgment dispute occurs at the site of the competition in Taekwondo Poomsae. This study proposes an artificial intelligence model that can more accurately judge and evaluate Taekwondo movements using artificial intelligence. In this study, after pre-processing the photographed and collected data, it is separated into train, test, and validation sets. The separated data is trained by applying each model and conditions, and then compared to present the best-performing model. The models under each condition compared the values of loss, accuracy, learning time, and top-n error, and as a result, the performance of the model trained under the conditions using ResNet50 and Adam was found to be the best. It is expected that the model presented in this study can be utilized in various fields such as education sites and competitions.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2014.05a
• /
• pp.198-199
• /
• 2014

In construction management the estimation procedure of construction expanses follows a series of submission phases: production of drawings, the assessment report, and the expanse report. In South Korea, it is a widely known issue that the expanse report only includes the net expanses at each construction phase and part, which makes it difficult to trace detailed basis from the records. This issue with inefficient record management should pose a number of problems, which result from discontinuation of construction record, unproductiveness for reproduction of records at each construction and submission phases for construction management, and failure to perform fair management among the contracting parties. Thus, the amendment in which the assessment report and the quantity estimation report reflect common codes to share throughout types of construction, space, and parts should be applied into practices so as to model production of acceptable reports and record.

• Nuclear Engineering and Technology
• /
• v.46 no.4
• /
• pp.489-500
• /
• 2014

In this study, remote handling strategies for a large-scale argon cell facility were considered. The suggested strategies were evaluated by several types of field test. The teleoperation tasks were performed using a developed remote handling system, which enabled traveling over entire cell area using a bridge transport system. Each arm of the system had six DOFs (degrees of freedom), and the bridge transport system had four DOFs. However, despite the dexterous manipulators and redundant monitoring system, many operators, including professionals, experienced difficulties in operating the remote handling system. This was because of the lack of a strategy for handling the installed camera system, and the difficulty in recognizing the gripper pose, which might fall outside the FOV (field of vision) of the system during teleoperation. Hence, in this paper, several considerations for the remote handling tasks performed in the target facility were discussed, and the tasks were analyzed based on ergonomic factors such as the workload. Toward the development of a successful operation strategy, several ergonomic issues, such as active/passive view of the remote handling system, eye/hand alignment, and FOV were considered. Furthermore, using the method for classifying remote handling tasks, several unit tasks were defined and evaluated.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.63-75
• /
• 2022

The raw data collected by structural health monitoring (SHM) systems may suffer multiple patterns of anomalies, which pose a significant barrier for an automatic and accurate structural condition assessment. Therefore, the detection and classification of these anomalies is an essential pre-processing step for SHM systems. However, the heterogeneous data patterns, scarce anomalous samples and severe class imbalance make data anomaly detection difficult. In this regard, this study proposes a convolutional neural network-based data anomaly detection method. The time and frequency domains data are transferred as images and used as the input of the neural network for training. ResNet18 is adopted as the feature extractor to avoid training with massive labelled data. In addition, the focal loss function is adopted to soften the class imbalance-induced classification bias. The effectiveness of the proposed method is validated using acceleration data collected in a long-span cable-stayed bridge. The proposed approach detects and classifies data anomalies with high accuracy.

• Nuclear Engineering and Technology
• /
• v.56 no.2
• /
• pp.707-714
• /
• 2024

Different degrees of natural radioactivity found in quartz can have negative consequences on health. Quartz vein along the investigated Abu Ramad area, Egypt, had its natural radioactivity assessed. The HPGe spectrometer was used to determine the role played by the radionuclides ²³⁸U, ²³²Th, and ⁴⁰K in the gamma radiation that was emitted, and the results showed that these concentrations are 484.64 ± 288.4, 36.8 ± 13.1 and 772.2 ± 134.6 Bq kg^-1 were higher than the corresponding reported global limits of 33, 45, and 412 Bq kg^-1 for each radionuclide (²³⁸U, ²³²Th, and ⁴⁰K). Among the radiological hazard parameters, the excess lifetime cancer risk (ELCR) is estimated and it's mean value of ELCR (1.2) is higher than the permissible limit of 0.00029. The relationship between the radionuclides and the associated radiological hazard characteristics was investigated based on multivariate statistical methods including Pearson correlation, principal component analysis (PCA), and hierarchical cluster analysis (HCA). According to statistical research, the radioactive risk of quartz is primarily caused by the ²³⁸U, ²³²Thand ⁴⁰K. Finally, applying quartz to building materials would pose a significant risk to the public.

• Journal of Broadcast Engineering
• /
• v.23 no.6
• /
• pp.780-789
• /
• 2018

Nowadays, gun crimes occur very frequently not only in public places but in alleyways around the world. In particular, it is essential to detect a person armed by a pistol to prevent those crimes since small guns, such as pistols, are often used for those crimes. Because conventional works for armed person detection have treated an armed person as a single object in an input image, their accuracy is very low. The reason for the low accuracy comes from the fact that the gunman is treated as a single object although the pistol is a relatively much smaller object than the person. To solve this problem, we propose a novel algorithm called APDA(Armed Person Detection Algorithm). APDA detects the armed person using in a post-processing the positions of both wrists and the pistol achieved by the CNN-based human body feature detection model and the pistol detection model, respectively. We show that APDA can provide both 46.3% better recall and 14.04% better precision than SSD-MobileNet.

• Nuclear Engineering and Technology
• /
• v.54 no.6
• /
• pp.2230-2243
• /
• 2022

The tin tailing processing industry in Malaysia has operated with minimal regard and awareness for material management and working environment safety, impacting the environment and workers in aspects of radiation and heavy metal exposure. RIA was conducted where environmental samples were analyzed, revealing concentrations of ²²⁶Ra, ²³²Th and ⁴⁰K between the range of 0.1-10.0, 0.0-25.7, and 0.1-5.8 Bq/g respectively, resulting in the AED exceeding UNCEAR recommended value and regulation limit enforced by AELB (1 mSv/y). Ra_eq calculated indicates that samples collected pose a significant threat to human health from gamma-ray exposure. Assessment of heavy metal content via pollution indices of soil and sediment showed significant contamination and enrichment from processing activities conducted. As and Fe were two of the highest metals exposed both via soil ingestion with an average of 4.6 × 10^-3 mg/kg-day and 1.4 × 10^-4 mg/kg-day, and dermal contact with an average of 5.6 × 10^-4 mg/kg-day and 6.0 × 10^-4. mg/kg-day respectively. Exposure via accidental ingestion of soil and sediment could potentially cause adverse non-carcinogenic and carcinogenic health effect towards workers in the industry. Correlation analysis indicates the presence of a relationship between the concentration of NORM and trace elements.

• Nuclear Engineering and Technology
• /
• v.54 no.10
• /
• pp.3909-3918
• /
• 2022

In the event of a severe accident, the reactor core may melt due to insufficient cooling. the high-temperature core melt will have a strong interaction (FCI) with the coolant, which may lead to steam explosion. Steam explosion would pose a serious threat to the safety of the reactors. Therefore, the study of steam explosion is of great significance to the assessment of severe accidents in nuclear reactors. This research focuses on the development of a two-dimensional steam explosion integrated analysis code called SEINA. Based on the semi-implicit Euler scheme, the three-phase field was considered in this code. Besides, the influence of evaporation drag of melt and the influence of solidified shell during the process of melt droplet fragmentation were also considered. The code was simulated and validated by FARO L-14 and KROTOS KS-2 experiments. The calculation results of SEINA code are in good agreement with the experimental results, and the results show that if the effects of evaporation drag and melt solidification shell are considered, the FCI process can be described more accurately. Therefore, it is proved that SEINA has the potential to be a powerful and effective tool for the analysis of steam explosions in nuclear reactors.