• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.4
• /
• pp.327-339
• /
• 2022

The purpose of this study is to present the effective smoke control flow rate and mode for securing safety through quantitative risk assessment according to the smoke control flow rate and mode (supply or exhaust) of the platform when a train fire occurs at the subway platform. To this end, a fire outbreak scenario was created using a side platform with a central staircase as a model and fire analysis was performed for each scenario to compare and analyze fire propagation characteristics and ASET, evacuation analysis was performed to predict the number of deaths. In addition, a fire accident rate (F)/number of deaths (N) diagram (F/N diagram) was prepared for each scenario to compare and evaluate the risk according to the smoke control flow rate and mode. In the ASET analysis of harmful factors, carbon monoxide, temperature, and visible distance determined by performance-oriented design methods and standards for firefighting facilities, the effect of visible distance is the largest, In the case where the delay in entering the platform of the fire train was not taken into account, the ASET was analyzed to be about 800 seconds when the air flow rate was 4 × 833 m³/min. The estimated number of deaths varies greatly depending on the location of the vehicle of fire train, In the case of a fire occurring in a vehicle adjacent to the stairs, it is shown that the increase is up to three times that of the vehicle in the lead. In addition, when the smoke control flow rate increases, the number of fatalities decreases, and the reduction rate of the air supply method rather than the exhaust method increases. When the supply flow rate is 4 × 833 m³/min, the expected number of deaths is reduced to 13% compared to the case where ventilation is not performed. As a result of the risk assessment, it is found that the current social risk assessment criteria are satisfied when smoke control is performed, and the number of deaths is the flow rate 4 × 833 m³/min when smoke control is performed at 29.9 people in 10,000 year, It was analyzed that it decreased to 4.36 people.

• Journal of Korean Society of Transportation
• /
• v.25 no.1 s.94
• /
• pp.109-119
• /
• 2007

Increasingly, the emphasis in regional Passenger rail Planning is finding ways to more efficiently use existing facilities, with particular attention being Paid to Policies designed to spread Peak-Period travel demand more evenly throughout the week with consideration of train classification. In this context the individual's choice of time to travel is of crucial significance. This paper investigates the use of multinomial logit analysis to model ridership by rail classification using data collected for travel from Seoul to Busan during the one week in October 2004. The Particular model form that was successfully calibrated was the multinomial logit (MNL) model : it describes the choice mechanism that will Permit rail systems and operations to be planned on a more reliable basis. The assumption of independently and identically distributed(IID) error terms in the MNL model leads to its infamous independence from irrelevant alternatives (IIA) property. Relaxation of the IID assumption has been undertaken along a number or isolated dimensions leading to the development of the MNL model. For business and related rail travel patterns, the most important variables of choice were time and frequency to the chosen destination. The calibrated model showed high agreement between observed and Predicted market shares. The model is expected to be of use to railroad authorities in Planning and determining business strategies in the Increasingly competitive environment or regional rail transport.

• Journal of Korea Water Resources Association
• /
• v.36 no.2
• /
• pp.195-209
• /
• 2003

Spatial-Stochastic Neural Networks Model(SSNNM) is used to estimate long-term streamflow in the parallel reservoir groups. SSNNM employs two kinds of backpropagation algorithms, based on LMBP and BFGS-QNBP separately. SSNNM has three layers, input, hidden, and output layer, in the structure and network configuration consists of 8-8-2 nodes one by one. Nodes in input layer are composed of streamflow, precipitation, pan evaporation, and temperature with the monthly average values collected from Andong and Imha reservoir. But some temporal differences apparently exist in their time series. For the SSNNM training procedure, the training sets in input layer are generated by the PARMA(1,1) stochastic model and they covers insufficient time series. Generated data series are used to train SSNNM and the model parameters, optimal connection weights and biases, are estimated during training procedure. They are applied to evaluate model validation using observed data sets. In this study, the new approaches give outstanding results by the comparison of statistical analysis and hydrographs in the model validation. SSNNM will help to manage and control water distribution and give basic data to develop long-term coupled operation system in parallel reservoir groups of the Upper Nakdong River.

• Journal of Bio-Environment Control
• /
• v.31 no.3
• /
• pp.255-260
• /
• 2022

This study aimed to develop a service model that uses a deep learning algorithm for detecting diseases and pests in strawberries through image data. In addition, the pest detection performance of deep learning models was further improved by proposing segmented image data sets specialized in disease and pest symptoms. The CNN-based YOLO deep learning model was selected to enhance the existing R-CNN-based model's slow learning speed and inference speed. A general image data set and a proposed segmented image dataset was prepared to train the pest and disease detection model. When the deep learning model was trained with the general training data set, the pest detection rate was 81.35%, and the pest detection reliability was 73.35%. On the other hand, when the deep learning model was trained with the segmented image dataset, the pest detection rate increased to 91.93%, and detection reliability was increased to 83.41%. This study concludes with the possibility of improving the performance of the deep learning model by using a segmented image dataset instead of a general image dataset.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.9
• /
• pp.17-25
• /
• 2023

In this paper, we propose a model that can perform human pose estimation through a MobileViT-based model with fewer parameters and faster estimation. The based model demonstrates lightweight performance through a structure that combines features of convolutional neural networks with features of Vision Transformer. Transformer, which is a major mechanism in this study, has become more influential as its based models perform better than convolutional neural network-based models in the field of computer vision. Similarly, in the field of human pose estimation, Vision Transformer-based ViTPose maintains the best performance in all human pose estimation benchmarks such as COCO, OCHuman, and MPII. However, because Vision Transformer has a heavy model structure with a large number of parameters and requires a relatively large amount of computation, it costs users a lot to train the model. Accordingly, the based model overcame the insufficient Inductive Bias calculation problem, which requires a large amount of computation by Vision Transformer, with Local Representation through a convolutional neural network structure. Finally, the proposed model obtained a mean average precision of 0.694 on the MS COCO benchmark with 3.28 GFLOPs and 9.72 million parameters, which are 1/5 and 1/9 the number compared to ViTPose, respectively.

• Journal of Hospice and Palliative Care
• /
• v.12 no.3
• /
• pp.132-138
• /
• 2009

Proper education of hospice professionals is essential for ensuring quality of end-of-life care. In 2005, 'End-of-life Care Task Force Team' by Ministry of Health and Welfare established '60 hours of hospice education' as basic requirement for hospice professionals. This study is aimed to determine how many of the hospice professionals meet with the criteria and whether there are significant regional variations. Methods: We analyzed the data from 46 hospice organizations, which submitted the application to the 2008 designation program of Ministry of Health, Welfare, and Family Affairs. Data included details of the educational records of each hospice professionals. Results: Total 673 hospice professionals were included in the analysis. Overall, only 41.5% (279/673) met the requirement. Nurses (46.8%; 177/378) were more likely to meet the requirement than doctors (35.8%; 38/106), social workers (32.0%; 24/75) and clergies (35.1%; 40/114). Hospice professionals of the organizations in metropolitan area received more education than those in small cities or rural area (52.4% vs. 25.0% for doctors, 50.6% vs. 43.9% for nurses, 42.9% vs. 25.5% for social workers). By geographic areas, hospice professionals in southeast regions received less education than other part of Korea (28.1% vs. 43.0${\sim}$48.8%, respectively). Conclusion: Less than half of the Korean hospice professionals has received proper amount of hospice education, and significant regional variations existed. National programs to promote the education of hospice professionals and eliminate its disparities are greatly warranted. Implementation of the 60-hour currirulum for hospice professionals, based on the train-the-trainer model, would be regarded as one potential solution.

• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.127-142
• /
• 2016

Deep learning model is a kind of neural networks that allows multiple hidden layers. There are various deep learning architectures such as convolutional neural networks, deep belief networks and recurrent neural networks. Those have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. Among those architectures, convolutional neural networks and recurrent neural networks are classified as the supervised learning model. And in recent years, those supervised learning models have gained more popularity than unsupervised learning models such as deep belief networks, because supervised learning models have shown fashionable applications in such fields mentioned above. Deep learning models can be trained with backpropagation algorithm. Backpropagation is an abbreviation for "backward propagation of errors" and a common method of training artificial neural networks used in conjunction with an optimization method such as gradient descent. The method calculates the gradient of an error function with respect to all the weights in the network. The gradient is fed to the optimization method which in turn uses it to update the weights, in an attempt to minimize the error function. Convolutional neural networks use a special architecture which is particularly well-adapted to classify images. Using this architecture makes convolutional networks fast to train. This, in turn, helps us train deep, muti-layer networks, which are very good at classifying images. These days, deep convolutional networks are used in most neural networks for image recognition. Convolutional neural networks use three basic ideas: local receptive fields, shared weights, and pooling. By local receptive fields, we mean that each neuron in the first(or any) hidden layer will be connected to a small region of the input(or previous layer's) neurons. Shared weights mean that we're going to use the same weights and bias for each of the local receptive field. This means that all the neurons in the hidden layer detect exactly the same feature, just at different locations in the input image. In addition to the convolutional layers just described, convolutional neural networks also contain pooling layers. Pooling layers are usually used immediately after convolutional layers. What the pooling layers do is to simplify the information in the output from the convolutional layer. Recent convolutional network architectures have 10 to 20 hidden layers and billions of connections between units. Training deep learning networks has taken weeks several years ago, but thanks to progress in GPU and algorithm enhancement, training time has reduced to several hours. Neural networks with time-varying behavior are known as recurrent neural networks or RNNs. A recurrent neural network is a class of artificial neural network where connections between units form a directed cycle. This creates an internal state of the network which allows it to exhibit dynamic temporal behavior. Unlike feedforward neural networks, RNNs can use their internal memory to process arbitrary sequences of inputs. Early RNN models turned out to be very difficult to train, harder even than deep feedforward networks. The reason is the unstable gradient problem such as vanishing gradient and exploding gradient. The gradient can get smaller and smaller as it is propagated back through layers. This makes learning in early layers extremely slow. The problem actually gets worse in RNNs, since gradients aren't just propagated backward through layers, they're propagated backward through time. If the network runs for a long time, that can make the gradient extremely unstable and hard to learn from. It has been possible to incorporate an idea known as long short-term memory units (LSTMs) into RNNs. LSTMs make it much easier to get good results when training RNNs, and many recent papers make use of LSTMs or related ideas.

• Proceedings of the KSR Conference
• /
• 2011.05a
• /
• pp.740-744
• /
• 2011

Precast slab track system(PSTS) is a concrete track laying system where the slab panels are pre-manufactured in factories and assembled and installed on-site. PSTS has been developed for the past 30 years in countries where railway technologies are advanced such as Japan and Germany to improve the various drawbacks of the in-situ concrete slab track. However, the usefulness of PSTS is being continuously approved by many other countries such as China, Taiwan, Austria, Italy, Spain, etc,. Lately, not only Japan and Germany, but also Austria, Italy and China have developed their own PSTS by collaboration between their Governments and private enterprises and are now attempting to expand their businesse soverseas. In accordance to such movement, in 2006, the Korean Railroad Research Institution and Sampyo E&C have developed a Korean PSTS by joint research. PSTS consists of concrete panel, under pouring layer and concrete base layer. Amongst these components, the panel is the main component of PSTS which supports the train load and has a great effect on the track quality, workability and economics. Therefore, a study is to be conducted to select the optimum size for the Panel of the precast slab track system panel by analyzing the various standards & forms, interpretation of finite elements of the selected model and economical analysis.

• Proceedings of the KSR Conference
• /
• 2011.05a
• /
• pp.1735-1741
• /
• 2011

The safety of station structures among railway infrastructures should be considered as a top priority because hundreds of thousands passengers a day take a subway. The station structures, which have been being operated since the 1970s, are especially vulnerable to the earthquake and long-term vibrations such as ambient train vibrations as well. This is why the structural-health monitoring system of station structures should be required. For these reason, Korean government has made an effort to develop the structural health-monitoring system of them, which can evaluate the health-state of station structures as well as can monitor the vulnerable structural members in real-time. Then, through the monitoring system, the vulnerable structural members could be retrofitted. For the development of health-state evaluation method for station structures with the real-time sensing data measured in the fields, authors carried out the numerical simulations to develop evaluation algorithms based on statistical pattern recognition techniques. In this study, the dynamic behavior of Chungmuro station in Seoul was numerically analyzed and then critical members were chosen. Damages were artificially simulated at the selected critical members of the numerical model. And, the supervised and unsupervised learning based pattern recognition algorithms were applied to quantify and localize the structural defects.

• Proceedings of the KSR Conference
• /
• 2011.10a
• /
• pp.2464-2472
• /
• 2011

Train runs on high speed and the concrete track is constructed. Rail fastening device needs to reduce elasticity, transferred load, noise, and vibration etc. Consequently, low elastic pad has a great impact of the durability and stability of the track. In this study, discussed in previous studies, static numerical analysis and real scale repeated loading test, followed by dynamic response analysis were implemented. The most distinctive characteristics of the model proposed is to simulate the real wheel behavior on rail. And the main analysis object is to evaluate and compare the deformation characteristics of the transition track while load reduction effect of transfer on roadbed assessed by various low elastic pad.