• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.20 no.2
• /
• pp.58-63
• /
• 2012

An altitude chamber, also known as a hypobaric chamber, is a device used during aerospace or high terrestrial altitude research or training to simulate the effects of high altitude on the human body. Although data from altitude chamber researches using experimental animals have been accumulated, studies in the humans exposed to hypobaric conditions are seldomly reported. Despite the importance of altitude chamber flight training in the field of aviation physiology, the hematological analysis of post-flight physiological changes has rarely been performed. The aims of the present study were to investigate the alterations in blood components during altitude chamber flight and to determine whether the differences between pre- and post-flight values are significant. Sixty experienced pilots in the Republic of Korea Air Force were enrolled in the altitude chamber flight training. Venous blood samples were obtained before and immediately after the flight. Compared with the pre-flight values($6.32{\times}10^3/mm^3$, $5.02{\times}10^6/mm^3$, 15.61 g/dL, respectively), white blood cell count, red blood cell count and hemoglobin level were significantly increased after the flight($6.77{\times}10^3/mm^3$, $5.44{\times}10^6/mm^3$, 16.26 g/dL; p=0.006, p=0.012, p<0.001, respectively). These alterations may be attributable to the exposure to hypobaric hypoxia, 100% oxygen supply for denitrogenation, considerable rise and fall in altitude and psychophysical stress due to these factors. In further studies, experimental groups and methods should be individualized to ensure objectivity and diversification. In addition, multiple time-frame analyses regarding the changing pattern of each blood component are also required to elucidate the physiological process for adapting to the high terrestrial altitude exposure.

• Nuclear Engineering and Technology
• /
• v.53 no.10
• /
• pp.3275-3285
• /
• 2021

A Nuclear Power Plant (NPP) is a complex dynamic system-of-systems with highly nonlinear behaviors. In order to control the plant operation under both normal and abnormal conditions, the different systems in NPPs (e.g., the reactor core components, primary and secondary coolant systems) are usually monitored continuously, resulting in very large amounts of data. This situation makes it possible to integrate relevant qualitative and quantitative knowledge with artificial intelligence techniques to provide faster and more accurate behavior predictions, leading to more rapid decisions, based on actual NPP operation data. Data-driven models (DDM) rely on artificial intelligence to learn autonomously based on patterns in data, and they represent alternatives to physics-based models that typically require significant computational resources and might not fully represent the actual operation conditions of an NPP. In this study, a feed-forward backpropagation artificial neural network (ANN) model was trained to simulate the interaction between the reactor core and the primary and secondary coolant systems in a pressurized water reactor. The transients used for model training included perturbations in reactivity, steam valve coefficient, reactor core inlet temperature, and steam generator inlet temperature. Uncertainties of the plant physical parameters and operating conditions were also incorporated in these transients. Eight training functions were adopted during the training stage to develop the most efficient network. The developed ANN model predictions were subsequently tested successfully considering different new transients. Overall, through prompt prediction of NPP behavior under different transients, the study aims at demonstrating the potential of artificial intelligence to empower rapid emergency response planning and risk mitigation strategies.

• Nuclear Engineering and Technology
• /
• v.56 no.1
• /
• pp.132-140
• /
• 2024

In the event of a severe accident in Sodium Cooled Fast Reactors (SFR), the sodium combustion aerosols along with fission product aerosols would migrate to the environment through leak paths of the Reactor Containment Building (RCB) concrete wall under positive pressure. Understanding the characteristics of sodium aerosol transport through concrete leak paths is important as it governs the environmental source term. In this context, experiments are conducted to study the influence of various parameters like pressure, initial mass concentration, leak path diameter, humidity etc., on the transport and deposition of sodium aerosols in straight leak paths of concrete. The leak paths in concrete specimens are prepared by casting and the diameter of the leak path is measured using thermography technique. Aerosol transport experiments are conducted to measure the transported and plugged aerosol mass in the leak paths and corresponding plugging times. The values of differential pressure, aerosol concentration and relative humidity taken for the study are in the ranges 10-15 kPa, 0.65-3.04 g/m³ and 30-90% respectively. These observations are numerically simulated using 1-Dimensional transport equation. The simulated values are compared with the experimental results and reasonable agreement among them is observed. From the safety assessment view of reactor, the approach presented here is conservative as it is with straight leak paths.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.4
• /
• pp.721-732
• /
• 2024

Species identification of zooplankton is the most basic process in understanding the marine ecosystem and studying global warming. In this study, we propose an convolutional neural network model that can classify females and males of three zooplankton at the species level. First, training data including morphological features is constructed based on microscopic images acquired by researchers. In constructing training data, a data argumentation method that preserves morphological feature information of the target species is applied. Next, we propose a convolutional neural network model in which features can be learned from the constructed learning data. The proposed model minimized the information loss of training image in consideration of high resolution and minimized the number of learning parameters by using the global average polling layer instead of the fully connected layer. In addition, in order to present the generality of the proposed model, the performance was presented based on newly acquired data. Finally, through the visualization of the features extracted from the model, the key features of the classification model were presented.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.3
• /
• pp.439-448
• /
• 1996

Extraction and selection of the informative features play a central role in pattern recognition. This paper describes a modified back-propagation algorithm that performs selection of the informative features and trains a neural network simultaneously. The algorithm is mainly composed of three repetitive steps : training, connection pruning, and input unit elimination. Afer initial training, the connections that have small magnitude are first pruned. Any unit that has a small number of connections to the hidden units is deleted,which is equivalent to excluding the feature corresponding to that unit.If the error increases,the network is retraned,again followed by connection pruning and input unit elimination.As a result,the algorithm selects the most im-portant features in the measurement space without a transformation to another space.Also,the selected features are the most-informative ones for the classification,because feature selection is tightly coupled with the classifi-cation performance.This algorithm helps avoid measurement of redundant or less informative features,which may be expensive.Furthermore,the final network does not include redundant parameters,i.e.,weights and biases,that may cause degradation of classification performance.In applications,the algorithm preserves the most informative features and significantly reduces the dimension of the feature vectors whiout performance degradation.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.43 no.4
• /
• pp.326-333
• /
• 2015

A turbo fan engine performance analysis program combined with a particle swarm optimization(PSO) has been developed to optimize the major design parameters of the combat aircraft gas turbine engine. The optimized parameters includes bypass ratio, fan pressure ratio, high pressure compression ratio and burner exit temperature. The objective parameters have been determined using a multi-objective function consisting of the net thrust and specific fuel consumption along a weight function. The basic model for the combat aircraft gas turbine engine has been selected as the F404 turbofan engine which is widely used in the combat aircraft, F-18 and Korean high level training aircraft, T-50. The optimal conditions of four parameters have been obtained for various design conditions.

• Journal of ILASS-Korea
• /
• v.28 no.1
• /
• pp.1-9
• /
• 2023

In the cylinder of gasoline direct injection engines, the spray targeting from injectors is of great significance for fuel consumption and pollutant emissions. The automotive industry is putting a lot of effort into improving injector targeting accuracy. To improve the targeting accuracy of injectors, it is necessary to develop models that can predict the spray targeting positions. When developing spray targeting models, the most used technique is computational fluid dynamics (CFD). Recently, due to the superiority of machine learning in prediction accuracy, the application of machine learning in this field is also receiving constant attention. The purpose of this study is to build a machine learning model that can accurately predict spray targeting based on the design parameters of injectors. To achieve this goal, this study firstly used laser sheet beam visualization equipment to obtain many spray cross-sectional images of injectors with different parameters at different injection pressures and measurement planes. The spray images were processed by MATLAB code to get the targeting coordinates of sprays. A total of four models were used for the prediction of spray targeting coordinates, namely ANN, LSTM, Conv1D and Conv1D & LSTM. Features fed into the machine learning model include injector design parameters, injection conditions, and measurement planes. Labels to be output from the model are spray targeting coordinates. In addition, the spray data of 7 injectors were used for model training, and the spray data of the remaining one injector were used for model performance verification. Finally, the prediction performance of the model was evaluated by R² and RMSE. It is found that the Conv1D&LSTM model has the highest accuracy in predicting the spray targeting coordinates, which can reach 98%. In addition, the prediction bias of the model becomes larger as the distance from the injector tip increases.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.5
• /
• pp.2055-2060
• /
• 2015

Purpose: To present information about prognostic factors of gastric cancer patients treated in our Erzurum center including age, gender, tumour location, pathological grade, stage and the effect of treatment on survival. Materials and Methods: This retrospective study was performed on patients who applied to our clinic and diagnosed as gastric cancer. Age and gender of the patients, primary location, histopathological characteristics, TNM stage of the gastric cancers (GCs), treatment applied, oncological treatment modalities and survival outcomes were studied. A univariate analysis of potential prognostic factors was performed with the log-rank test for categorical factors and parameters with a p value < 0.05 at the univariate step were included in the multivariate regression. Results: A total of 228 patients with a confirmed diagnosis of gastric cancer were included in the study with a male/female ratio of 1.47. Median follow-up period was estimated as 22.3 (range, 3 to 96) months. When diagnosis of the patients at admission was analysed, stage III patients were most frequently encountered (n=147; 64.5%). One hundred and twenty-six (55.3%) underwent surgical treatment, while 117 (51.3%) were given adjuvant chemotherapy. Median overall survival time was 18.0 (${\pm}1.19$) months. Mean overall survival rates for 1, 2, 3 and 5 years were $68{\pm}0.031%$, $36{\pm}0.033%$, $24{\pm}0.031%$and $15.5{\pm}0.036%$, respectively. Univariate variables found to be significant for median OS in the multivariate analysis were evaluated with Cox regression analysis. A significant difference was found among TNM stage groups, location of the tumour and postoperative adjuvant treatment receivers (p values were 0.011, 0.025 and 0.001, respectively). Conclusions: This study revealed that it is possible to achieve long-term survival of gastric cancer with early diagnosis. Besides, in locally advanced GC patients, curative resection followed by adjuvant concomitant chemoradiotherapy based on the McDonald regimen was an independent prognostic factor for survival.

• The Journal of Korean Academy of Orthopedic Manual Physical Therapy
• /
• v.10 no.1
• /
• pp.83-101
• /
• 2004

The propose of the study was to evaluate the efficacy of the partial body weight support during treadmill training on the ambulation in elderly with chronic stroke. Fourteen hemiplegic volunteers participated and were divided into an experimental and control groups. In the experimental group, the body weight support during treadmill training was performed 3 times per week for 6 weeks. In the control group, usual treadmill training was applied. Before and after experiments, temporal-spatial gait parameters were measured. The date of 14 patients who carried out the whole experimental course were statistically analyzed. The results of the study were : 1. In the comparison of gait velocity before and after experiment, the gait velocity was significantly increased in the experimental group and the control group(p<.05). In the comparison of difference of the gait velocity between groups, there was not, significant difference between the experimental group and the control group(p>.05). 2. In comparison of gait cadence before and after experiment, the gait cadence was significantly increased in both groups(p<.05). In the comparison of difference of the gait cadence between groups, there was not significant difference between the experimental group and the control group(p>.05). 3. In the comparison of step length before and after experiment, the step length was significantly increased in the experimental group and the control group(p<.05). In the comparison of difference of the step length between groups, there was not significant difference between the experimental group and the control group(p>.05). 4. In the comparison of single support time asymmetry before and after experiment, the single support time asymmetry was no significant difference between groups(p>.05). In the comparison of difference of the single support time asymmetry between groups, there was not significant difference between the experimental group and the control group(p>.05). 5. In the comparison of step length asymmetry before and. after experiment, the step length asymmetry was not significant difference between the experimental group and the control group(p>.05). In the comparison of difference of the single step length asymmetry between groups, there was not significant difference between the experimental group and the control group(p>.05).

• Journal of Korean Physical Therapy Science
• /
• v.11 no.2
• /
• pp.27-37
• /
• 2004

The propose of the study was to evaluate the efficacy of the partial body weight support during treadmill training on the ambulation in elderly with chronic stroke. Fourteen hemiplegic volunteers participated and were divided into an experimental and control groups. In the experimental group, the body weight support during treadmill training was performed 3 times per week for 6 weeks. In the control group, usual treadmill training was applied. Before and after experiments, temporal-spatial gait parameters were measured. The date of 14 patients who carried out the whole experimental course were statistically analyzed. The results of the study were : 1. In the comparison of gait velocity before and after experiment, the gait velocity was significantly increased in the experimental group and the control group(p<.05). In the comparison of difference of the gait velocity between groups, there was not significant difference between the experimental group and the control group(p>.05). 2. In comparison of gait cadence before and after experiment, the gait cadence was significantly increased in both groups(p<.05). In the comparison of difference of the gait cadence between groups, there was not significant difference between the experimental group and the control group(p>.05). 3. In the comparison of step length before and after experiment, the step length was significantly increased in the experimental group and the control group(p<.05). In the comparison of difference of the step length between groups, there was not significant difference between the experimental group and the control group(p>.05). 4. In the comparison of vastus medialis root mean square(RMS) before and after experiment, the vastus medialis RMS was significantly increased in the experimental group(p<.05). In the comparison of vastus medialis root mean square(RMS) before and after experiment, the vastus medialis RMS was not significantly increased in the experimental group(p>.05). In the comparison of difference of the vastus medialis RMS between groups, there was not significant difference between the experimental group and the control group(p>.05). 5. In the comparison of latency of somatosensory evoke potential(SSEP) before and after experiment, the latency of SSEP was significantly increased in the experimental group(p<.05). In the comparison of latency of somatosensory evoke potential(SSEP) before and after experiment, the latency of SSEP was significantly decreased in the control group(p>.05). In the comparison of difference of the latency of SSEP between groups, there was not significant difference between the experimental group and the control group(p>.05). 6. In the comparison of functional ambulation profile(FAP) before and after experiment, the FAP was not significant difference in the experimental group and the control group(p>.05). In the comparison of difference of the FAP between groups, there was not significant difference between the experimental group and the control group(p>.05).