• 로봇학회논문지
• /
• 제17권4호
• /
• pp.463-476
• /
• 2022

In this paper, we propose a table tennis posture classification system using a cooperative robot to develop a table tennis robot that can be trained like a real game. The most ideal table tennis robot would be a robot with a high joint driving speed and a high degree of freedom. Therefore, in this paper, we intend to use a cooperative robot with sufficient degrees of freedom to develop a robot that can be trained like a real game. However, cooperative robots have the disadvantage of slow joint driving speed. These shortcomings are expected to be overcome through quick recognition. Therefore, in this paper, we try to quickly classify the opponent's posture to overcome the slow joint driving speed. To this end, learning about dynamic postures was conducted using image data as input, and finally, three classification models were created and comparative experiments and evaluations were performed on the designated dynamic postures. In conclusion, comparative experimental data demonstrate the highest classification accuracy and fastest classification speed in classification models using MLP (Multi-Layer Perceptron), and thus demonstrate the validity of the proposed algorithm.

• 한국재난정보학회 논문집
• /
• 제19권1호
• /
• pp.76-83
• /
• 2023

연구목적: 지진, 호우, 태풍, 화재 등 긴급한 재난 알림 전달이 필요한 상황에서 청각장애인은 소리를 통한 알림을 인지할 수 없으며 문자를 통한 알림의 인지율도 비장애인에 비하여 상대적으로 낮은 편으로서 일반적인 수단의 재난알림을 신속하게 인지하기 어려운 경우가 많다. 이와 같은 청각장애인의 재난안전 긴급알림 인지의 취약성 문제를 해결하고자 픽토그램을 통한 재난안전 긴급알림 시스템이 개발되었다. 연구방법: 본 연구에서는 재난문자 통보문의 문구를 기반으로 청각장애인이 인지하기 보다 용 이한 일련의 픽토그램을 전달하는 시스템을 개발하고 자동 변환하는 방법을 탐색하고자 하였다. 연구결과: 이를 위해 재난안전 관련 긴급 통보문과 관련되는 픽토그램 기반의 알림을 전달하는 시스템이 개발되었고 자동변환에 적합한 인공신경망 구조와 훈련방법을 구성하여 재난문자에 대응되는 픽토그램 기반의 청각장애인 재난안전 긴급알림 시스템 구성이 제안되었다. 결론:본 연구를 통해 청각장애인 뿐만아니라 일반인 또는 한국어를 모르는 외국인도 쉽게 이해할 수 있는 픽토그램이 신속하게 표출될 수 있도록 하여 재난 취약계층의 취약성을 줄이는데 기여할 수 있을 것으로 기대된다.

• International journal of advanced smart convergence
• /
• 제12권3호
• /
• pp.1-12
• /
• 2023

A public address (PA) system installed in a building is a system that delivers alerts, announcements, instructions, etc. in an emergency or disaster situation. As for the products used in PA systems, with the development of information and communication technology, PA products with various functions have been introduced to the market. PA systems recently launched in the market may be connected through a single network to enable efficient management and operation, or use voice recognition technology to deliver quick information in case of an emergency. In addition, a system capable of locating a user inside a building using a location-based service and guiding or responding to a safe area in the event of an emergency is being launched on the market. However, the new PA systems currently on the market add some functions to the existing PA system configuration to make system operation more convenient, but they do not change the complex PA system configuration to reduce facility costs, maintenance, and management costs. In this paper, we propose a novel PA system configuration for buildings using audio networks and control hierarchy over peer-to-peer (Anchor) technology based on audio over IP (AoIP), which simplifies the complex PA system configuration and enables convenient operation and management. As a result of the study, through the emergency signal processing algorithm, fire broadcasting was made possible according to the detection of the existence of a fire signal in the Anchor system. In addition, the control device of the PA system was replaced with software to reduce the equipment installation cost, and the PA system configuration was simplified. In the future, it is expected that the PA system using Anchor technology will become the standard for PA facilities.

• PNF and Movement
• /
• 제21권2호
• /
• pp.223-229
• /
• 2023

Purpose: Assessing physical strength and muscle mass is crucial, but many methods rely on specialized equipment, which can be challenging. In situations where a quick and straightforward test is needed, the sit-to-stand test (STST) proves useful. Although several studies have investigated STST and muscle mass separately, the actual correlation between these two factors has not been extensively researched. Hence, the objective was to comprehensively investigate the correlations between the different tests. Methods: The study participants consisted of 20 healthy young men in their 20s. In this study, measurements were taken for muscle mass, the five-times sit-to-stand test, the 30-second sit-to-stand test, and the 1-minute sit-to-stand test. The results of each test were analyzed using Pearson's correlation analysis. Results: Although no significant correlation was found between muscle mass and STST, interestingly, significant correlations were observed among the different types of STST. Conclusion: The STST is a rapid and straightforward test used to assess lower limb strength and balance ability in individuals. However, there is a dearth of research on STST conducted in domestic settings. Based on the findings of this study, further research is necessary to establish age- and gender-specific reference values for STST. This will allow its broader application, encompassing not only older adults and patients but also healthy individuals.

• Steel and Composite Structures
• /
• 제45권3호
• /
• pp.389-408
• /
• 2022

Residual capacity is defined as the load carrying capacity of an RC column after undergoing severe damage. Evaluation of residual capacity of RC columns is necessary to avoid damage initiation in RC structures. The central aspect of the current research is to propose an empirical formula to estimate the residual capacity of RC columns after undergoing severe damage. This formula facilitates decision making of whether a replacement or a repair of the damaged column is adequate for further use. Available literature mainly focused on the simulation of explosion loads by using simplified pressure time histories to develop residual capacity of RC columns and rarely simulated the actual explosive. Therefore, there is a gap in the literature concerning general relation between blast damage of columns with different explosive loading conditions for a reliable and quick evaluation of column behavior subjected to blast loading. In this paper, the Arbitrary Lagrangian Eulerian (ALE) technique is implemented to simulate high fidelity blast pressure propagations. LS-DYNA software is utilized to solve the finite element (FE) model. The FE model is validated against the practical blast tests, and outcomes are in good agreement with test results. Multivariate linear regression (MLR) method is utilized to derive an analytical formula. The analytical formula predicts the residual capacity of RC columns as functions of structural element parameters. Based on intensive numerical simulation data, it is found that column depth, longitudinal reinforcement ratio, concrete strength and column width have significant effects on the residual axial load carrying capacity of reinforced concrete column under blast loads. Increasing column depth and longitudinal reinforcement ratio that provides better confinement to concrete are very effective in the residual capacity of RC column subjected to blast loads. Data obtained with this study can broaden the knowledge of structural response to blast and improve FE models to simulate the blast performance of concrete structures.

• 보건행정학회지
• /
• 제33권1호
• /
• pp.29-39
• /
• 2023

Background: Breaking the chain of disease transmission from overseas is necessary to control new infectious diseases such as coronavirus disease 2019 effectively. In this study, we developed a mobile app called Self-Symptom Checker (SSC) to monitor the health of inbound travelers. Methods: SSC was developed for general users and administrators. The functions of SSC include non-repudiation using QR (quick response) codes, monitoring fever and respiratory symptoms, and requiring persons showing symptoms to undergo polymerase chain reaction tests at nearby screening stations following a review of reported symptoms by the Korea Disease Control and Prevention Agency, as well as making phone calls, via artificial intelligence or public health personnel, to individuals who have not entered symptoms to provide the necessary information. Results: From February 12 to March 27, 2020, 165,000 people who were subjected to the special entry procedure installed SSC. The expected number of public health officers and related resources needed per day would be 800 if only the phone was used to perform symptom monitoring during the above period. Conclusion: By applying SSC, more effective symptom monitoring was possible. The daily average number of health officers decreased to 100, or 13% of the initial estimate. SSC reduces the work burden on public healthcare personnel. SSC is an electronic solution conceived in response to health questionnaires completed by inbound travelers specified in the World Health Organization International Health Regulations as a requirement in the event of a pandemic.

• 한국건설관리학회논문집
• /
• 제24권2호
• /
• pp.3-12
• /
• 2023

건축물에서 발생하는 화재 사고는 주변에서 빈번하게 확인할 수 있는 문제이다. 건축물의 화재사고는 시간의 경과에 따라 인적·물적 자원의 피해가 커지고 대형사고로 이어지게 됨으로 신속한 화재 진압·구조 방안의 모색이 필요하다. 현재 사회적으로도 화재 사고에 관한 관심은 주목되고 있으나 실제 화재 상황에 대처하는 부분에 미흡함이 존재해 안전사고에 관하여 사회가 요구하는 기대치를 충족하지 못하는 실정이다. 이러한 사회의 요구에 맞추어 본 연구는 건물 내 화재로 인한 피해를 최소화하기 위한 신속하고 체계적인 화재 관리 방안을 제시하고 있다. 연구의 목적을 달성시키기 위한 방안으로 아두이노 센서 및 Excel, Revit-Dynamo 툴을 연동하여 새로운 화재정보 관리 시스템을 개발 및 실시간 3D 시각화 Model을 개발하고, 실제 사례에 적용하여 화재 관리의 우수성을 보였다. 추후 활용방안으로 화재 관리 어플리케이션을 제안하여 실시간 스마트 화재 관리시스템에 기여할 수 있다고 기대하는 바이다.

• International Journal of Computer Science & Network Security
• /
• 제23권5호
• /
• pp.148-162
• /
• 2023

Classification systems can significantly assist the medical sector by allowing for the precise and quick diagnosis of diseases. As a result, both doctors and patients will save time. A possible way for identifying risk variables is to use machine learning algorithms. Non-surgical technologies, such as machine learning, are trustworthy and effective in categorizing healthy and heart-disease patients, and they save time and effort. The goal of this study is to create a medical intelligent decision support system based on machine learning for the diagnosis of heart disease. We have used a mixed feature creation (MFC) technique to generate new features from the UCI Cleveland Cardiology dataset. We select the most suitable features by using Least Absolute Shrinkage and Selection Operator (LASSO), Recursive Feature Elimination with Random Forest feature selection (RFE-RF) and the best features of both LASSO RFE-RF (BLR) techniques. Cross-validated and grid-search methods are used to optimize the parameters of the estimator used in applying these algorithms. and classifier performance assessment metrics including classification accuracy, specificity, sensitivity, precision, and F1-Score, of each classification model, along with execution time and RMSE the results are presented independently for comparison. Our proposed work finds the best potential outcome across all available prediction models and improves the system's performance, allowing physicians to diagnose heart patients more accurately.

• 한국지반공학회논문집
• /
• 제22권11호
• /
• pp.113-122
• /
• 2006

국내에서 말뚝 정재하 실험이 수많이 수행되고 있지만, 그 결과의 활용도가 낮아서 재하실험 방법과 분석방법 등에 대하여 재고할 필요성이 제기되고 있다. 본 연구에서는 두터운 연약지반 하부의 모래층에 PHC 말뚝 선단을 지지시킨 후 하중전이 정재하 실험을 수행하였다. 말뚝의 설치 이후에 장기간에 걸쳐 주면 마찰력을 측정하였으며, 국내에서 보편적으로 적용되고 있는 재하법과는 다른 급속재하법에 의하여 정재하실험을 실시하였다 그 실험결과를 이용하여 말뚝의 탄성계수, 잔류응력 및 참 지지력을 산정하였다. 결과적으로, 재하실험 전에 말뚝에 존재하는 잔류하중이 주면 마찰력과 선단지지력에 크게 영향을 미친다는 사실을 확인할 수 있었다. 또한, 점성토 지반에서의 장대말뚝에 대해서는 지반의 강도회복(setup) 효과가 매우 크다는 사실을 알 수 있었다.

• 한국지반공학회논문집
• /
• 제25권8호
• /
• pp.57-64
• /
• 2009

본 연구에서는 등가변형을 이용하며 테이퍼 말뚝의 지지력을 산정하는 방법을 제안하였다. 지반조건과 테이퍼각도를 고려하여 지지력을 산정하던 기존의 방법과 달리, 테이퍼말뚝의 지지력산정시 콘관입시험 결과를 활용하도록 하였다. 이때 테이퍼말뚝은 등가변형을 이용하여 형태를 단순화 시켰으며 이를 통해 실무에서 비교적 쉽게 지지력을 산정 할 수 있는 방법을 제안하였다. 제안된 방법의 검증을 위해 실내시험과 현장시험을 실시하였다. 실내모형시험 결과로부터 측정된 극한지지력과 본 연구에서 제안된 방법에 의한 예측값을 비교한 결과 표준편차는 $0.05{\sim}0.121$, COV는 $0.04{\sim}0.05$의 값을 보여 대체적으로 유사한 결과를 보였으며, 현장시험은 약 2.5%의 오차를 보여 측정값에 근접함을 알 수 있었다. 그 결과 제안된 지지력 산정법은 테이퍼말뚝의 지지력을 비교적 정확하게 예측하는 것으로 나타났다.