• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.10a
• /
• pp.271-274
• /
• 1997

This paper presents an adaptive quantization of image sequences using the Radial Basis Function Network(RBFN) which classifies interframe image blocks. The clssification algorithm consists of two steps. Blocks are classified into NA(No Activity), SA(Small Activity), VA(Verical Activity), and HA(Horizontal Activity) classes according to edges, image activity and AC anergy distribution. RBFN is trained using the classification results of the above algorithm, which are nonlinear classification features are acquired from the complexity and variability of difference blocks. Simulation result shows that the the adaptive quantization using the RBFN method produced better results better results than that of the sorting and MLP methods.

• Nuclear Engineering and Technology
• /
• v.55 no.5
• /
• pp.1814-1820
• /
• 2023

Safety classification of systems, structures, and components (SSC) is an essential activity for nuclear reactor design and operation. The current regulatory trend is to require risk-informed safety classification that considers first, the severity, but also the frequency of SSC failures. While safety classification for nuclear power plants is covered in many regulatory and scientific publications, research reactors received less attention. Research reactors are typically of lower power but, at the same time, are less standardized i.e., have more variability in the design, operational modes, and operating conditions. This makes them more challenging when considering safety classification. This work presents the Integrated Risk-Informed Safety Classification (IRISC) procedure which is a novel extension of the IAEA recommended process with dedicated probabilistic treatment of research reactor designs. The article provides the details of probabilistic analysis performed within safety classification process to a degree that is often missing in most literature on the topic. The article presents insight from the implementation of the procedure in the safety classification for the MARIA Research Reactor operated by the National Center for Nuclear Research in Poland.

• International conference on construction engineering and project management
• /
• 2017.10a
• /
• pp.80-88
• /
• 2017

Although hazard identification is one of the most important steps of safety management process, numerous hazards remain unidentified in the construction workplace due to the dynamic environment of the construction site and the lack of available resource for visual inspection. To this end, our previous study proposed the collective sensing approach for safety hazard identification and showed the feasibility of identifying hazards by capturing collective abnormalities in workers' walking patterns. However, workers generally performed different activities during the construction task in the workplace. Thereby, an additional process that can identify the worker's walking activity is necessary to utilize the proposed hazard identification approach in real world settings. In this context, this study investigated the feasibility of identifying walking activities during construction task using Wearable Inertial Measurement Units (WIMU) attached to the worker's ankle. This study simulated the indoor masonry work for data collection and investigated the classification performance with three different machine learning algorithms (i.e., Decision Tree, Neural Network, and Support Vector Machine). The analysis results showed the feasibility of identifying worker's activities including walking activity using an ankle-attached WIMU. Moreover, the finding of this study will help to enhance the performance of activity recognition and hazard identification in construction.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2013.05a
• /
• pp.1475-1476
• /
• 2013

• The Korean Journal of Archival Studies
• /
• no.10
• /
• pp.145-194
• /
• 2004

Church archives are the evidential instruments to remember church activity and important information aggregate which has administrative, legal, financial, historical, faithful value as the collective memory of church community. So it must be managed necessarily and the management orders are based on the Bible. The western churches which have a correct understanding about the importance of church records and management order have taken multilateral endeavor to create, manage church archives systematically. On the other hand, korean churches don't have the records management systems. Therefore, Records created in individual church are mostly managed unsystematically and exist as 'backlogs', finally, they are destructed without reasonable formalities. In those problems, the purpose of this study is to offer the way of records classification and disposition instrument with recognition that records management should be done from the time of creation or previous to it. As a concrete device for them, I tried to embody the function-based classification method and disposal schedule. I prefer the function-based classification and disposal schedule to the organization and function-based classification to present stable classification and disposal schedule, as we can say the best feature of the modern organization is multilateral and also churches have same aspect. For this study, I applied DIRKS(Designing and Implementing Recordkeeping Systems) manual which National Archives of Australia provide and guidelines in ICA/IRMT series to construct the theory of the function-based classification in individual churches. Through them, it was possible to present a model for preliminary investigation, analysis of business activity, records survey, disposal schedule. And I took an example of 'Myong Sung Presbyterian Church' which belong to 'The Presbyterian church in Korea'. I explained in detail codifying process and results of preliminary investigation in 'Myong Sung Presbyterian Church', analysis of business activity based on it, process of presenting the function-based classification and disposal schedule got from all those steps. For establishing disposal schedule, I planned 'General Disposal Schedule' and 'Agency Disposal Schedule' which categorized 'general function' and 'agency function' of an agency, according to DIRKS in Australia and ICA/IRMT. And for estimation of disposal date I had a thorough grasp of important records category presented in 'Constitution of General Assembly', interview to know the importance of tasks, and added examples of disposal schedule in western church archives. This study has significance that it was intended to embody 'the function-based classification' and 'disposal schedule' suitable for individual church, applying DIRKS in Australia and ICA/IRMT on absence of the theory or example which tried to present the function-based classification and disposal schedule for individual church. Also it is meaningful to present a model that can classify and disposal real records according to the function in individual church which has no recognition or way about records management.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.50 no.6
• /
• pp.42-57
• /
• 2022

This study aims to create a basic model for classifying the activity photos that urban park users shared on social media using Deep Learning through Artificial Intelligence. Regarding the social media data, photos related to urban parks were collected through a Naver search, were collected, and used for the classification model. Based on the indicators of Naturalness, Potential Attraction, and Activity, which can be used to evaluate the characteristics of urban parks, 21 classification categories were created. Urban park photos shared on Naver were collected by category, and annotated datasets were created. A custom CNN model and a transfer learning model utilizing a CNN pre-trained on the collected photo datasets were designed and subsequently analyzed. As a result of the study, the Xception transfer learning model, which demonstrated the best performance, was selected as the urban park user activity image classification model and evaluated through several evaluation indicators. This study is meaningful in that it has built AI as an index that can evaluate the characteristics of urban parks by using user-shared photos on social media. The classification model using Deep Learning mitigates the limitations of manual classification, and it can efficiently classify large amounts of urban park photos. So, it can be said to be a useful method that can be used for the monitoring and management of city parks in the future.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.17 no.4
• /
• pp.587-601
• /
• 1993

In the order to grasp their physical characteristics stemming from activity amount, this paper has divided elderly women into the following group ; those with high activity in the past, those with low activity in the present, those with high activity in the present and those with low activity in the present. The analyses of the body measurements and the pie chart, and the classification of back shapes by taking photographs have led to the following results. 1. The items of depth and girth among the body measurements were significant in the past and the present activity. Those with high activity in the past had smaller sizes in depth and girth than those with low activity. 2. From the pie chart, it was shown that those with high activity in the past had smaller sizes in every index as well as in girth than those with low activity in the past. Both those with low activity in the present and those with medium activity in the present had somewhat large sizes in waist girth, bust girth, hip girth and abdominal girth and in the indices of these items. 3. The classification of back shapes by taking photograpes has shown that those with high activity in the past had the less bent body type-42 percent of Type A and 6.5 percent of Type D. Among those with medium activity in the present, Type A was most outstanding and Type C and Type D were less, This fact shows that those with medium activity in the present keep the most normal body type. This proves that the medium activity of elderly women is desirable for keeping the normal body type.

• The Journal of Korean Physical Therapy
• /
• v.27 no.4
• /
• pp.234-239
• /
• 2015

Purpose: This study is not a fragmentary study on characteristics of respiratory synergist when breathing, however it was intended to determine the effect of currently available respiratory exercise and to provide basic clinical information through investigation of oxygen demand and respiratory synergist that mobilizes for respiration during application of respiratory exercise. Methods: Experimental group I was selected from second grade of severity classification of GOLD, which has the highest percentage among patients with COPD, and experimental group II was selected from third grade of severity classification as a clinical sampling. After respiration pursing up lips and diaphragm respiration exercise were mediated together for six weeks, activity of respiratory muscles and oxygen saturation were measured and analyzed. Results: In comparison of change of respiratory synergist and oxygen saturation, activity of respiratory synergist in sternocleidomastoid muscle and scalene muscle showed a meaningful decrease in experimental group I. And, in comparison of change of respiratory synergist and oxygen saturation, activity of respiratory synergist in rectus abdominis muscle showed a meaningful increase in experimental group II. In comparison of change of respiratory synergist and oxygen saturation, activity of respiratory synergist in sternocleidomastoid muscle, scalene muscle, and rectus abdominis muscle showed a meaningful difference between experimental groups. Conclusion: Respiratory synergists work mainly as agonist of chest and upper limbs. Therefore it is very important to lower mobilization of respiratory synergist when breathing. It is considered that a multilateral approach and continued clinical research for improvement of respiratory function for patients with COPD will be needed in the future.

• Nuclear Engineering and Technology
• /
• v.56 no.4
• /
• pp.1372-1384
• /
• 2024

The discrimination of the source for xenon gases' release can provide an important clue for detecting the nuclear activities in the neighboring countries. In this paper, three machine learning techniques, which are logistic regression, support vector machine (SVM), and k-nearest neighbors (KNN), were applied to develop the predictive models for discriminating the source for xenon gases' release based on the xenon isotopic activity ratio data which were generated using the depletion codes, i.e., ORIGEN in SCALE 6.2 and Serpent, for the probable sources. The considered sources for the neighboring countries of South Korea include PWRs, CANDUs, IRT-2000, Yongbyun 5 MWe reactor, and nuclear tests with plutonium and uranium. The results of the analysis showed that the overall prediction accuracies of models with SVM and KNN using six inputs, all exceeded 90%. Particularly, the models based on SVM and KNN that used six or three xenon isotope activity ratios with three classification categories, namely reactor, plutonium bomb, and uranium bomb, had accuracy levels greater than 88%. The prediction performances demonstrate the applicability of machine learning algorithms to predict nuclear threat using ratios of xenon isotopic activity.

• Journal of Internet of Things and Convergence
• /
• v.10 no.3
• /
• pp.57-64
• /
• 2024

In this paper, we propose a Line-of-Sight (LoS)/Non-Line-of-Sight (NLoS) identification- based Human Activity Recognition (HAR) system using Channel State Information (CSI) to improve the accuracy of HAR, which dynamically changes depending on the reception environment. to consider the reception environment of HAR system, the proposed system includes three operational phases: Preprocessing phase, Classification phase, and Activity recognition phase. In the preprocessing phase, amplitude is extracted from CSI raw data, and noise in the extracted amplitude is removed. In the Classification phase, the reception environment is categorized into LoS and NLoS. Then, based on the categorized reception environment, the HAR model is determined based on the result of the reception environment categorization. Finally, in the activity recognition phase, human actions are classified into sitting, walking, standing, and absent using the determined HAR model. To demonstrate the superiority of the proposed system, an experimental implementation was performed and the accuracy of the proposed system was compared with that of the existing HAR system. The results showed that the proposed system achieved 16.25% higher accuracy than the existing system.