• Journal of The Korean Society of Agricultural Engineers
• /
• v.59 no.4
• /
• pp.97-107
• /
• 2017

This study is to determine the coefficients of regression equations and to select the optimal regression equation in the LOADEST model after classifying the whole study period into 5 flow conditions for 16 watersheds located in the Nakdonggang waterbody. The optimized coefficients of regression equations were derived using the gradient descent method as a learning method in Tensorflow which is the engine of machine-learning method. In South Korea, the variability of streamflow is relatively high, and rainfall is concentrated in summer that can significantly affect the characteristic analysis of pollutant loads. Thus, unlike the previous application of the LOADEST model (adjusting whole study period), the study period was classified into 5 flow conditions to estimate the optimized coefficients and regression equations in the LOADEST model. As shown in the results, the equation #9 which has 7 coefficients related to flow and seasonal characteristics was selected for each flow condition in the study watersheds. When compared the simulated load (SS) to observed load, the simulation showed a similar pattern to the observation for the high flow condition due to the flow parameters related to precipitation directly. On the other hand, although the simulated load showed a similar pattern to observation in several watersheds, most of study watersheds showed large differences for the low flow conditions. This is because the pollutant load during low flow conditions might be significantly affected by baseflow or point-source pollutant load. Thus, based on the results of this study, it can be found that to estimate the continuous pollutant load properly the regression equations need to be determined with proper coefficients based on various flow conditions in watersheds. Furthermore, the machine-learning method can be useful to estimate the coefficients of regression equations in the LOADEST model.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.12
• /
• pp.1150-1158
• /
• 2010

In this study, the Polynomial-based Radial Basis Function Neural Networks is proposed as one of the recognition part of overall face recognition system that consists of two parts such as the preprocessing part and recognition part. The design methodology and procedure of the proposed pRBFNNs are presented to obtain the solution to high-dimensional pattern recognition problem. First, in preprocessing part, we use a CCD camera to obtain a picture frame in real-time. By using histogram equalization method, we can partially enhance the distorted image influenced by natural as well as artificial illumination. We use an AdaBoost algorithm proposed by Viola and Jones, which is exploited for the detection of facial image area between face and non-facial image area. As the feature extraction algorithm, PCA method is used. In this study, the PCA method, which is a feature extraction algorithm, is used to carry out the dimension reduction of facial image area formed by high-dimensional information. Secondly, we use pRBFNNs to identify the ID by recognizing unique pattern of each person. The proposed pRBFNNs architecture consists of three functional modules such as the condition part, the conclusion part, and the inference part as fuzzy rules formed in 'If-then' format. In the condition part of fuzzy rules, input space is partitioned with Fuzzy C-Means clustering. In the conclusion part of rules, the connection weight of pRBFNNs is represented as three kinds of polynomials such as constant, linear, and quadratic. Coefficients of connection weight identified with back-propagation using gradient descent method. The output of pRBFNNs model is obtained by fuzzy inference method in the inference part of fuzzy rules. The essential design parameters (including learning rate, momentum coefficient and fuzzification coefficient) of the networks are optimized by means of the Particle Swarm Optimization. The proposed pRBFNNs are applied to real-time face recognition system and then demonstrated from the viewpoint of output performance and recognition rate.

• Journal of Korean Neurosurgical Society
• /
• v.29 no.2
• /
• pp.240-248
• /
• 2000

Objective : Spontaneous intracranial hypotension is a rarely reported syndrome of spontaneous postural headache associated with low CSF pressure and has rarely been demonstrated radiographically or surgically. But recently, it is being recognized with increasing frequency. The purpose of this study was to characterize clinical and imaging features, etiologic factors, and outcome in the spontaneous intracranial hypotension. Patients and Methods : We reviewed our experience with documented cases of spontaneous intracranial hypotension in 5 consecutive patients with orthostatic headaches from April 1998 to April 1999. Results : The mean age was 41 years(from 35 to 49 years). All patients had postural headaches, which were completely alleviated by recumbency position. Nausea, neck pain, horizontal diplopia, photophobia, and blurred vision were noted in some of the patients. Brain MRI showed diffuse pachymeningeal gadolinium enhancement, subdural collections of fluid, and descent of the brain. The opening pressure from lumbar puncture was $4cmH_2O$ or less in three of five patients whereas the opening pressure was within normal range in two patients. All patients underwent radioisotope cisternography and computerized tomographic myelography. On radioisotope cisternography, CSF leakage was suspected at the level of cervical area(1 patient), upper thoracic area(2 patients), mid-thoracic area(1 patient). Computed tomography myelography revealed extraarachnoid accumulation of contrast media(compatible finding with CSF leakage) at the level of cervical or thoracic area. In all patients, the symptoms resolved in response to supportive measures or epidural blood patch(1 patient). Conclusion : Spontaneous spinal CSF leakage is increasingly recognized as a cause of spinal postural headache. Most CSF leaks are located at the cervicothoracic junction or in the thoracic spine and can be demonstrated by variable diagnostic method. The condition is usually self-limiting and its prognosis is typically good.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.15 no.3
• /
• pp.289-300
• /
• 2013

This study numerically considered the characteristic of smoke movement and the effect of hot smoke gas on tunnel wall surface temperature during road tunnel fire under boundary condition of fire growth curve that is applied to fire analysis in road tunnels. The maximum heat release rate were 20 MW and 100 MW and tunnel air velocities were 2.5 m/s and velocity induced by thermal buoyancy respectively, also the cooling effect of tunnel wall was considered. As results, when tunnel air velocity was constant at 2.5 m/s during tunnel fire, due to the cooling effect of tunnel wall, the smoke layer was rapidly descent after some distance and it flowed the same patterns at the downstream. When heat release rate was 100 MW (and jet fan was not installed), the maximum temperature of tunnel wall surface has risen up to $615^{\circ}C$. The heat transfer coefficient of tunnel wall surface was varied from 13 to $23W/m^2^{\circ}C$ approximately.

• Journal of Animal Science and Technology
• /
• v.54 no.2
• /
• pp.71-75
• /
• 2012

The present study data were obtained from 36,894 cows in Korea Animal Improvement Association from 2001 to 2009 which was subjected for ultrasound measurements (eye muscle area, back-fat thickness, marbling score) and descent. Repeated record models were carried out using 7,913 of 36,894 of total animal traits. The ultrasound measured traits and performance test data were used to study the chest girth, body condition score, eye muscle area, back-fat thickness and marbling score with genetic correlation and parameters for the ultrasound measured traits using REMLF90 program. Genetic correlation of eye muscle area with back-fat thickness, marbling score and back-fat thickness with marbling score were noticed in repeated records animal model as 0.69, 0.54, and 0.59, whereas in multiple trait animal model method were 0.07, 0.66, and 0.39, respectively. Repeated records of animal models were used as positive correlation of traits. Multiple trait animal models were used as negative correlation of eye muscle area with marbling score. The analysis on repeat records of animal models using ultrasound measurements about Korean cattle showed positive effects for each traits. In comparison differences between the repeat records of animal models and multiple trait animal models was found with higher traits of her, the heritability and repeatability was found higher in repeat records animal models. In light of these assessments, carcass traits by ultrasound measurements are expected to help and improve an accurate analysis of each trait and if the research analysis using repeat records of animal models continue when we estimate genetic ability of these traits.