• International conference on construction engineering and project management
• /
• 2020.12a
• /
• pp.87-95
• /
• 2020

Generally, occupational safety and particularly construction safety is an intricate phenomenon. Industry professionals have devoted vital attention to enforcing Occupational Safety and Health (OHS) from the last three decades to enhance safety management in construction. Despite the efforts of the safety professionals and government agencies, current safety management still relies on manual inspections which are infrequent, time-consuming and prone to error. Extensive research has been carried out to deal with high fatality rates confronting by the construction industry. Sensor systems, visualization-based technologies, and tracking techniques have been deployed by researchers in the last decade. Recently in the construction industry, computer vision has attracted significant attention worldwide. However, the literature revealed the narrow scope of the computer vision technology for safety management, hence, broad scope research for safety monitoring is desired to attain a complete automatic job site monitoring. With this regard, the development of a broader scope computer vision-based risk recognition system for correlation detection between the construction entities is inevitable. For this purpose, a detailed analysis has been conducted and related rules which depict the correlations (positive and negative) between the construction entities were extracted. Deep learning supported Mask R-CNN algorithm is applied to train the model. As proof of concept, a prototype is developed based on real scenarios. The proposed approach is expected to enhance the effectiveness of safety inspection and reduce the encountered burden on safety managers. It is anticipated that this approach may enable a reduction in injuries and fatalities by implementing the exact relevant safety rules and will contribute to enhance the overall safety management and monitoring performance.

• The Journal of Bigdata
• /
• v.8 no.2
• /
• pp.177-187
• /
• 2023

Semi-supervised learning (SSL) is an effective approach to training models using a small amount of labeled data and a larger amount of unlabeled data. However, many papers in the field use a fixed threshold when applying pseudo-labels without considering the feature-wise differences among images of different classes. In this paper, we propose a SSL method for synthetic aperture radar (SAR) image classification that applies different thresholds for each class instead of using a single fixed threshold for all classes. We propose a threshold learning module into the model, considering the differences in feature distributions among classes, to dynamically learn thresholds for each class. We compare the application of a SSL SAR image classification method using different thresholds and examined the advantages of employing class-specific thresholds.

• Smart Media Journal
• /
• v.13 no.7
• /
• pp.9-17
• /
• 2024

Due to the increase in energy consumption, and eco-friendly policies, there is a need for efficient energy consumption in buildings. Anomaly power detection based on deep learning are being used. Because of the difficulty in collecting anomaly data, anomaly detection is performed using reconstruction error with a Recurrent Neural Network(RNN) based autoencoder. However, there are some limitations such as the long time required to fully learn temporal features and its sensitivity to noise in the train data. To overcome these limitations, this paper proposes the TCN-USAD, combined with Temporal Convolution Network(TCN) and UnSupervised Anomaly Detection for multivariate data(USAD). The proposed model using TCN-based autoencoder and the USAD structure, which uses two decoders and adversarial training, to quickly learn temporal features and enable robust anomaly detection. To validate the performance of TCN-USAD, comparative experiments were performed using two building energy datasets. The results showed that the TCN-based autoencoder can perform faster and better reconstruction than RNN-based autoencoder. Furthermore, TCN-USAD achieved 20% improved F1-Score over other anomaly detection models, demonstrating excellent anomaly detection performance.

• Nuclear Engineering and Technology
• /
• v.56 no.8
• /
• pp.3123-3128
• /
• 2024

The dicentric chromosome assay is a gold standard method to estimate radiation exposure by calculating the ratio of dicentric chromosomes existing in cells. The objective of this study was to propose an automatic dicentric chromosome discrimination method based on deep convolutional neural networks using radiation exposure patient data. From 45 patients with radiation exposure, conventional Giemsa-stained images of 116,258 normal and 2800 dicentric chromosomes were confirmed. ImageNet was used to pre-train VGG19, which was modified and fine-tuned. The proposed modified VGG19 demonstrated dicentric chromosome discrimination performance, with a true positive rate of 0.927, a true negative rate of 0.997, a positive predictive value of 0.882, a negative predictive value of 0.998, and an area under the receiver operating characteristic curve of 0.997.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.12
• /
• pp.889-898
• /
• 2013

Due to the popularization of high-performance capturing equipments and the emergence of powerful image-editing softwares, it is easy to make high-quality counterfeit money. However, the probability of detecting counterfeit money to the general public is extremely low and the detection device is expensive. In this paper, a counterfeit money detection algorithm using a general purpose scanner and computer system is proposed. First, the printing features of color printers are calculated using morphological operations and gray-level co-occurrence matrix. Then, these features are used to train a support vector machine classifier. This trained classifier is applied for identifying either original or counterfeit money. In the experiment, we measured the detection rate between the original and counterfeit money. Also, the printing source was identified. The proposed algorithm was compared with the algorithm using wiener filter to identify color printing source. The accuracy for identifying counterfeit money was 91.92%. The accuracy for identifying the printing source was over 94.5%. The results support that the proposed algorithm performs better than previous researches.

• Journal of Families and Better Life
• /
• v.19 no.4
• /
• pp.49-68
• /
• 2001

The purpose of this study was 1) to review communal housing in the UK, 2) to consider the policy implications for elderly communal housing in Korea. The research methods used were 1) literature review about communal housing and related policy in the UK 2) field survey in the UK 3) interpretative suggestion for the proper policy implication to develope communal housing for the elderly in Korea. Sheltered housing in the UK had been developed as communal housing for the elderly with special needs since the 1970s. The type of sheltered housing were category 1 and category 2. Very sheltered housing with more facilities and meal services was added in 1980s. Sheltered housing was evaluated as the most humanistic solution for older people in the UK in 1980s. Because of the policy of moving institutional care to community care, sheltered housing became less in demand because of more options for older people including being able to stay in their own home. So new completion of sheltered housing by registered social landlords reduced saliently. Sheltered housing already totalled over half million units in which 5% of all elderly over 65 still lived and a small quantity of private sector for sale schemes emerged in the 1990s. The reason why the residents moved to sheltered housing was for sociable, secure, and manageable living arrangements. In general the residents were satisfied with these characteristics but dissatisfied with the service charge and quality of meals, especially in category 2.5 schemes. The degree of utilisation of communal spaces and facilities depended on the wardens ability and enthusiasm. Evaluation of sheltered housing indicated several problems such as wardens duty as a \"good neighbour\" ; difficult-to-let problems with poor location or individual units of bedsittiing type with shared bathroom ; and the under use of communal spaces and facilities. Some ideas to solve these problems were suggested by researchers through expanding wardens duty as a professional, opening the scheme to the public, improving interior standards, and accepting non-elderly applicants who need support. Some researchers insisted continuing development of sheltered housing, but higher standards must be considered for the minority who want to live in communal living arrangement. Recently, enhanced sheltered housing with greater involvement of relatives and with tied up policy in registration and funding suggested as an alternative for residential care. In conclusion, the rights of choice for older people should be policy support for special needs housing. Elderly communal housing, especially a model similar to sheltered housing category 2 with at least 1 meal a day might be recommended for a Korean Model. For special needs housing development either for rent or for sale, participation of the public sector and long term and low interest financial support for the private sector must be developed in Korea. Providing a system for scheme managers to train and retrain must be encouraged. The professional ability of the scheme manager to plan and to deliver services might be the most important factor for the success of elderly communal housing projects in Korea. In addition the expansion of a public health care service, the development of leisure programs in Senior Citizens Centre, home helper both for the elderly in communal housing and the elderly in mainstream housing of the community as well. Providing of elderly communal housing through the modified general Construction Act rather than the present Elderly Welfare Act might be more helpful to encourage the access of general people in Korea. in Korea.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.38 no.11
• /
• pp.1309-1315
• /
• 2014

The switch for a maglev vehicle should be designed such that the vehicle safely changes its track without touching the guiderail. In particular, a medium-to-low-speed EMS -type maglev train relies heavily on a U-type electromagnet where it generates levitation force and guidance force simultaneously. Therefore, it is necessary to evaluate the safety of the vehicle whenever it passes the switch, as it lacks active control of the guidance force. Furthermore, when the vehicle passes a segmented switch, which is a group of curves made up of connected lines with a small radius of curvature, it may come into mechanical contact with the guiderail owing to the excessive lateral displacement of the electromagnet. The goal of this study is to analyze the influence of a segmented switch on the safety of major design-related variables for achieving improved running safety. We propose a three-dimensional multibody dynamics model composed of two cars with one body. Using the proposed model, we perform a simulation of the lateral air gap, which is one of the measurements of the running safety of the vehicle when it passes the switch. The analyzed design variables are the length between short span girder, the articulation angle, the length between two centers of a fixed girder at its ends, and the number of girders. On the basis of the effects of the considered design variables, we establish an optimized design of a switch with improved safety.

• The Journal of the Korea Contents Association
• /
• v.20 no.7
• /
• pp.674-682
• /
• 2020

Recently, the problem of air pollution has become a global concern due to industrialization and overcrowding. Air pollution can cause various adverse effects on human health, among which respiratory diseases such as asthma, which have been of interest in this study, can be directly affected. Previous studies have used clinical data to identify how air pollutant affect diseases such as asthma based on relatively small samples. This is high likely to result in inconsistent results for each collection samples, and has significant limitations in that research is difficult for anyone other than the medical profession. In this study, the main focus was on predicting the actual asthmatic occurrence, based on data on the atmospheric environment data released by the government and the frequency of asthma outbreaks. First of all, this study verified the significant effects of each air pollutant with a time lag on the outbreak of asthma through the time-lag Pearson Correlation Coefficient. Second, train data built on the basis of verification results are utilized in Deep Learning algorithms, and models optimized for predicting the asthmatic occurrence are designed. The average error rate of the model was about 11.86%, indicating superior performance compared to other machine learning-based algorithms. The proposed model can be used for efficiency in the national insurance system and health budget management, and can also provide efficiency in the deployment and supply of medical personnel in hospitals. And it can also contribute to the promotion of national health through early warning of the risk of outbreak by atmospheric environment for chronic asthma patients.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.2
• /
• pp.47-55
• /
• 2011

Hemorrhagic shock is a cause of one third of death resulting from injury in the world. Early diagnosis of hemorrhagic shock makes it possible for physician to treat successfully. The objective of this paper was to select an optimal classifier model using physiological signals from rats measured during hemorrhagic experiment. This data set was used to train and predict survival rate using artificial neural network (ANN) and support vector machine (SVM). To avoid over-fitting, we chose the best classifier according to performance measured by a 10-fold cross validation method. As a result, we selected ANN having three hidden nodes with one hidden layer and SVM with Gaussian kernel function as trained prediction model, and the ANN showed 88.9 % of sensitivity, 96.7 % of specificity, 92.0 % of accuracy and the SVM provided 97.8 % of sensitivity, 95.0 % of specificity, 96.7 % of accuracy. Therefore, SVM was better than ANN for survival prediction.

• Journal of the Korean Society for Railway
• /
• v.20 no.2
• /
• pp.234-240
• /
• 2017

In this study, the influences of rail surface roughness on dynamic wheel-rail forces currently employed in conventional lines were assessed by performing field measurements according to grinding of rail surface roughness. The influence of the grinding effect was evaluated using a previous empirical prediction model for dynamic wheel-rail forces; model includes first-order derivatives of QI (Quality Index) and vehicle velocity. The theoretical dynamic wheel-rail force determined using the previous prediction equation was analyzed using the QI, which decreased due to rail grinding as determined through field measurements. At a constant track support stiffness, an increase in the QI caused an increase in dynamic wheel-rail forces. Further, it can be inferred that the results of dynamic wheel-rail analysis obtained using the measured data, such as the variation of QI due to rail grinding, can be used to predict the peak dynamic forces. Therefore, it is obvious that the optimum amount of rail grinding can be determined by considering the QI, that was regarding an operation characteristics of the target track (vehicle velocity and wheel load).