• Journal of Radiation Protection and Research
• /
• v.40 no.1
• /
• pp.55-64
• /
• 2015

Dose calculations which are a crucial requirement for radiotherapy treatment planning systems require accuracy and rapid calculations. The conventional radiotherapy treatment planning dose algorithms are rapid but lack precision. Monte Carlo methods are time consuming but the most accurate. The new combined system that Monte Carlo methods calculate part of interesting domain and the rest is calculated by neural can calculate the dose distribution rapidly and accurately. The preliminary study showed that neural networks can map functions which contain discontinuous points and inflection points which the dose distributions in inhomogeneous media also have. Performance results between scaled conjugated gradient algorithm and Levenberg-Marquardt algorithm which are used for training the neural network with a different number of neurons were compared. Finally, the dose distributions of homogeneous phantom calculated by a commercialized treatment planning system were used as training data of the neural network. In the case of homogeneous phantom;the mean squared error of percent depth dose was 0.00214. Further works are programmed to develop the neural network model for 3-dimensinal dose calculations in homogeneous phantoms and inhomogeneous phantoms.

• The KIPS Transactions:PartB
• /
• v.16B no.2
• /
• pp.131-140
• /
• 2009

This paper presents a new algorithm to the segmentation of the FISH images. First, for segmentation of the cell nuclei from background, a threshold is estimated by using the gaussian mixture model and maximizing the likelihood function of gray value of cell images. After nuclei segmentation, overlapped nuclei and isolated nuclei need to be classified for exact nuclei analysis. For nuclei classification, this paper extracted the morphological features of the nuclei such as compactness, smoothness and moments from training data. Three probability density functions are generated from these features and they are applied to the proposed Bayesian networks as evidences. After nuclei classification, segmenting of overlapped nuclei into isolated nuclei is necessary. This paper first performs intensity gradient transform and watershed algorithm to segment overlapped nuclei. Then proposed stepwise merging strategy is applied to merge several fragments in major nucleus. The experimental results using FISH images show that our system can indeed improve segmentation performance compared to previous researches, since we performed nuclei classification before separating overlapped nuclei.

• Geophysics and Geophysical Exploration
• /
• v.14 no.3
• /
• pp.220-226
• /
• 2011

In the elastic wave equations, both horizontal and vertical displacements are defined. Since we can measure both the horizontal and vertical displacements in field acquisition, these displacements compose a displacement vector. In this study, we propose a frequency-domain elastic waveform inversion technique taking advantage of the magnitudes of displacement vectors to define objective function. When we apply this displacement-vector objective function to the frequency-domain waveform inversion, the inversion process naturally incorporates the back-propagation algorithm. Through the inversion examples with the Marmousi model and the SEG/EAGE salt model, we could note that the RMS error of the solution obtained by our algorithm decreased more stably than that of the conventional method. Particularly, the density of the Marmousi model and the low-velocity sub-salt zone of the SEG/EAGE salt model were successfully recovered. Since the gradient direction obtained from the proposed objective function is numerically unstable, we need additional study to stabilize the gradient direction. In order to perform the waveform inversion using the displacementvector objective function, it is necessary to acquire multi-component data. Hence, more rigorous study should be continued for the multi-component land acquisition or OBC (Ocean Bottom Cable) multi-component survey.

• Journal of Animal Science and Technology
• /
• v.46 no.2
• /
• pp.137-144
• /
• 2004

Algorithms for estimating breeding values on several categorical data by using latent variables with threshold conception were developed and showed. Thresholds on each categorical trait were estimated by Newton’s method via gradients and Hessian matrix. This algorithm was developed by way of expansion of bivariate analysis provided by Quaas(2001). Breeding values on latent variables of categorical traits and observations on linear traits were estimated by preconditioned conjugate gradient(PCG) method, which was known having a property of fast convergence. Example was shown by simulated data with two linear traits and a categorical trait with four categories(CE=calving ease) and a dichotomous trait(SB=Still Birth) in threshold animal mixed model(TAMM). Breeding value estimates in TAMM were compared to those in linear animal mixed model (LAMM). As results, correlation estimates of breeding values to parameters were 0.91${\sim}$0.92 on CE and 0.87${\sim}$0.89 on SB in TAMM and 0.72~0.84 on CE and 0.59~0.70 on SB in LAMM. As conclusion, PCG method for estimating breeding values on several categorical traits with linear traits were feasible in TAMM.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.31-31
• /
• 2023

During December 2022, the northeast monsoon, which dominates the south and the Gulf of Thailand, had significant rainfall that impacted the lower southern region, causing flash floods, landslides, blustery winds, and the river exceeding its bank. The Golok River, located in Narathiwat, divides the border between Thailand and Malaysia was also affected by rainfall. In flood management, instruments for measuring precipitation and water level have become important for assessing and forecasting the trend of situations and areas of risk. However, such regions are international borders, so the installed measuring telemetry system cannot measure the rainfall and water level of the entire area. This study aims to predict 72 hours of water level and evaluate the situation as information to support the government in making water management decisions, publicizing them to relevant agencies, and warning citizens during crisis events. This research is applied to machine learning (ML) for water level prediction of the Golok River, Lan Tu Bridge area, Sungai Golok Subdistrict, Su-ngai Golok District, Narathiwat Province, which is one of the major monitored rivers. The eXtreme Gradient Boosting (XGBoost) algorithm, a tree-based ensemble machine learning algorithm, was exploited to predict hourly water levels through the R programming language. Model training and testing were carried out utilizing observed hourly rainfall from the STH010 station and hourly water level data from the X.119A station between 2020 and 2022 as main prediction inputs. Furthermore, this model applies hourly spatial rainfall forecasting data from Weather Research and Forecasting and Regional Ocean Model System models (WRF-ROMs) provided by Hydro-Informatics Institute (HII) as input, allowing the model to predict the hourly water level in the Golok River. The evaluation of the predicted performances using the statistical performance metrics, delivering an R-square of 0.96 can validate the results as robust forecasting outcomes. The result shows that the predicted water level at the X.119A telemetry station (Golok River) is in a steady decline, which relates to the input data of predicted 72-hour rainfall from WRF-ROMs having decreased. In short, the relationship between input and result can be used to evaluate flood situations. Here, the data is contributed to the Operational support to the Special Water Resources Management Operation Center in Southern Thailand for flood preparedness and response to make intelligent decisions on water management during crisis occurrences, as well as to be prepared and prevent loss and harm to citizens.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.10
• /
• pp.299-308
• /
• 2023

As the spectrum shortage problem has accelerated by the emergence of various services, New Radio-Unlicensed (NR-U) has appeared, allowing users who communicated in licensed bands to communicate in unlicensed bands. However, NR-U network users reduce the performance of Wi-Fi network users who communicate in the same unlicensed band. In this paper, we aim to simultaneously maximize the fairness and throughput of the unlicensed band, where the NR-U network users and the WiFi network users coexist. First, we propose an optimal power allocation scheme based on Monte Carlo Policy Gradient of reinforcement learning to maximize the sum of rates of NR-U networks utilizing rate-splitting multiple access in unlicensed bands. Then, we propose a channel occupancy time division algorithm based on sequential Raiffa bargaining solution of game theory that can simultaneously maximize system throughput and fairness for the coexistence of NR-U and WiFi networks in the same unlicensed band. Simulation results show that the rate splitting multiple access shows better performance than the conventional multiple access technology by comparing the sum-rate when the result value is finally converged under the same transmission power. In addition, we compare the data transfer amount and fairness of NR-U network users, WiFi network users, and total system, and prove that the channel occupancy time division algorithm based on sequential Raiffa bargaining solution of this paper satisfies throughput and fairness at the same time than other algorithms.

• Ecology and Resilient Infrastructure
• /
• v.10 no.4
• /
• pp.107-115
• /
• 2023

High turbidity in source water can have adverse effects on water treatment plant operations and aquatic ecosystems, necessitating turbidity management. Consequently, research aimed at predicting river turbidity continues. This study developed a multi-class classification model for prediction of turbidity using LightGBM (Light Gradient Boosting Machine), a representative ensemble machine learning algorithm. The model utilized data that was classified into four classes ranging from 1 to 4 based on turbidity, from low to high. The number of input data points used for analysis varied among classes, with 945, 763, 95, and 25 data points for classes 1 to 4, respectively. The developed model exhibited precisions of 0.85, 0.71, 0.26, and 0.30, as well as recalls of 0.82, 0.76, 0.19, and 0.60 for classes 1 to 4, respectively. The model tended to perform less effectively in the minority classes due to the limited data available for these classes. To address data imbalance, the SMOTE (Synthetic Minority Over-sampling Technique) algorithm was applied, resulting in improved model performance. For classes 1 to 4, the Precision and Recall of the improved model were 0.88, 0.71, 0.26, 0.25 and 0.79, 0.76, 0.38, 0.60, respectively. This demonstrated that alleviating data imbalance led to a significant enhancement in Recall of the model. Furthermore, to analyze the impact of differences in input data composition addressing the input data imbalance, input data was constructed with various ratios for each class, and the model performances were compared. The results indicate that an appropriate composition ratio for model input data improves the performance of the machine learning model.

• Investigative Magnetic Resonance Imaging
• /
• v.1 no.1
• /
• pp.109-113
• /
• 1997

Purpose: To evaluate the differences of functional imaging patterns between conventional spoiled gradient echo (SPGR) and echo planar imaging (EPI) methods in cerebral motor cortex activation. Materials and Methods: Functional MR imaging of cerebral motor cortex activation was examined on a 1.5T MR unit with SPGR (TRfrE/flip angle=50ms/4Oms/$30^{\circ}$, FOV=300mm, matrix $size=256{\times}256$, slice thickness=5mm) and an interleaved single shot gradient echo EPI (TRfrE/flip angle = 3000ms/40ms/$90^{\circ}$, FOV=300mm, matrix $size=128{\times}128$, slice thickness=5mm) techniques in five male healthy volunteers. A total of 160 images in one slice and 960 images in 6 slices were obtained with SPGR and EPI, respectively. A right finger movement was accomplished with a paradigm of an 8 activation/ 8 rest periods. The cross-correlation was used for a statistical mapping algorithm. We evaluated any differences of the time series and the signal intensity changes between the rest and activation periods obtained with two techniques. Also, the locations and areas of the activation sites were compared between two techniques. Results: The activation sites in the motor cortex were accurately localized with both methods. In the signal intensity changes between the rest and activation periods at the activation regions, no significant differences were found between EPI and SPGR. Signal to noise ratio (SNR) of the time series data was higher in EPI than in SPGR by two folds. Also, larger pixels were distributed over small p-values at the activation sites in EPI. Conclusions: Good quality functional MR imaging of the cerebral motor cortex activation could be obtained with both SPGR and EPI. However, EPI is preferable because it provides more precise information on hemodynamics related to neural activities than SPGR due to high sensitivity.

• Journal of KIISE:Computing Practices and Letters
• /
• v.8 no.3
• /
• pp.344-355
• /
• 2002

Having a variety of good characteristics against other pattern recognition techniques, Multilayer Perceptron (MLP) has been used in wide applications. But, it is known that Error Backpropagation (EBP) algorithm which MLP uses in learning has a defect that requires relatively long leaning time. Because learning data in pattern recognition contain abundant redundancies, in order to increase learning speed it is very effective to use online-based teaming methods, which update parameters of MLP pattern by pattern. Typical online EBP algorithm applies fixed learning rate for each update of parameters. Though a large amount of speedup with online EBP can be obtained by choosing an appropriate fixed rate, fixing the rate leads to the problem that the algorithm cannot respond effectively to different leaning phases as the phases change and the learning pattern areas vary. To solve this problem, this paper defines learning as three phases and proposes a Instant Learning by Varying Rate and Skipping (ILVRS) method to reflect only necessary patterns when learning phases change. The basic concept of ILVRS is as follows. To discriminate and use necessary patterns which change as learning proceeds, (1) ILVRS uses a variable learning rate which is an error calculated from each pattern and is suppressed within a proper range, and (2) ILVRS bypasses unnecessary patterns in loaming phases. In this paper, an experimentation is conducted for speaker verification as an application of pattern recognition, and the results are presented to verify the performance of ILVRS.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.10 no.6 s.52
• /
• pp.19-28
• /
• 2006

Most conventional model updating methods must use mathematical objective function with experimental modal matrices and analytical system matrices or must use information about the gradient or higher derivatives of modal properties with respect to each updating parameter. Therefore, most conventional methods are not appropriate for complex structural system such as bridge structures due to stability problem in inverse analysis with ill-conditions. Sometimes, moreover, the updated model may have no physical meaning. In this paper, a new FE model updating method based on a hybrid optimization technique using genetic algorithm (GA) and Holder-Mead simplex method (NMS) is proposed. The performance of hybrid optimization technique on the nonlinear problem is demonstrated by the Goldstein-Price function with three local minima and one global minimum. The influence of the objective function is evaluated by the case study of a simulated 10-dof spring-mass model. Through simulated case studies, finally, the objective function is proposed to update mass as well as stiffness at the same time. And so, the proposed hybrid optimization technique is proved to be an efficient method for FE model updating.