• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.12
• /
• pp.459-465
• /
• 2017

This research aims to assess whether neurofeedback training can reduce theta waves in adolescents. The experiment was conducted on 35 early youths living in Gyeonggi-do at youth counseling centers during April-October. According to circumstances and opinions of participants in the pre-brain analysis, they were classified into a non-training group (A), 12-week training group (B), and 24-week training group (C), containing 10, 15, and 10 members, respectively. EEG measurement and neurofeedback training was performed using the prefrontal 2-channel NeuroharmonyS and Brain Optimization program. EEG data was processed utilizing Brain Analysis ver1.3. Deducted data was converted to SPSS 21.0 to enable statistical processing. As a strategy to reduce theta through the Beta increase training, we applied the appropriate Alpha, SMR, Beta low reward training to the individual. Study results confirmed that theta waves of adolescents decreased through the prefrontal neurofeedback training. Groups (B) and (C) exhibited a greater decrease in theta waves compared with the control group.

• Journal of Korea Multimedia Society
• /
• v.20 no.8
• /
• pp.1406-1420
• /
• 2017

Artificial neural networks (ANNs) play an important role in the fields of function approximation, prediction, and classification. ANN performance is critically dependent on the input parameters, including the number of neurons in each layer, and the optimal values of weights and biases assigned to each neuron. In this study, we apply the particle swarm optimization method, a popular optimization algorithm for determining the optimal values of weights and biases for every neuron in different layers of the ANN. Several regression models, including general linear regression, Fourier regression, smoothing spline, and polynomial regression, are conducted to evaluate the proposed method's prediction power compared to multiple linear regression (MLR) methods. In addition, residual analysis is conducted to evaluate the optimized ANN accuracy for both training and test datasets. The experimental results demonstrate that the proposed method can effectively determine optimal values for neuron weights and biases, and high accuracy results are obtained for prediction applications. Evaluations of the proposed method reveal that it can be used for prediction and estimation purposes, with a high accuracy ratio, and the designed model provides a reliable technique for optimization. The simulation results show that the optimized ANN exhibits superior performance to MLR for prediction purposes.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.28 no.7
• /
• pp.879-886
• /
• 2004

A numerical optimization has been carried out to determine the shape of the three-dimensional channel with oblique ribs attached on both walls to enhance turbulent heat transfer. The response surface based optimization is used as an optimization technique with Reynolds-averaged Navier-Stokes analysis of fluid flow and heat transfer. Shear stress transport (SST) turbulence model is used as a turbulence closure. Numerical results fur heat transfer rate show good agreements with experimental data. four dimensionless variables such as, rib pitch-to-rib height ratio, rib height-to-channel height ratio, streamwise rib distance on opposite wall to rib pitch ratio, and the attack angle of the rib are chosen as design variables. The objective function is defined as a linear combination of heat-transfer and friction-loss related coefficients with a weighting factor. D-optimal method is used to determine the training points as a means of design of experiment. Sensitivity of the objective parameters to each design variable has been analyzed. And, optimal values of the design variables have been obtained in a range of the weighting factor.

• Proceedings of the KSR Conference
• /
• 2002.10a
• /
• pp.727-732
• /
• 2002

This study is to develop the model of alignment optimization based on design criteria by approaching through alignment of railway design and problems in economy, environment and technology for satisfying traffic volume of the main roads caused by economical and social developments. Now, Geographic Information System isn't applied when designing a present railway in home. And the design of railway alignment is still set on importance of transition curves and cant according to passenger comfort in abroad so tile study of railway alignment is at initiation phase so far. This paper is about decision of optimal alignment between two stations such as starting point and ending point automatically using GIS in optimization of railway alignment. A route between Sungsan city and Shinpung city is the training area and the study compared and evaluated optimal railway route by GIS automatically with present railway route designed. Present optimal fomulas was used in this study for optimization of railway alignment. The model of optimization of railway alignment was developed through topographical elements and it was mentioned by the model of road alignment because of the similarity in design of alignment. But the design of lateral track irregularities, cant fur passenger comfort and motion sickness fellowed by train rolling have to be considered more. Anyway, this study farmed the basis of using GIS and the study should be keep going on in the future.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.6
• /
• pp.319-325
• /
• 2023

In this study, we proposed a method for hyperparameter optimization in the building and training of a deep learning model designed to process point cloud data collected by a millimeter-wave radar system. The primary aim of this study is to facilitate the deployment of a baseline model in resource-constrained IoT devices. We evaluated a RadHAR baseline deep learning model trained on a public dataset composed of point clouds representing five distinct human activities. Additionally, we introduced a coarse-to-fine hyperparameter optimization procedure, showing substantial potential to enhance model efficiency without compromising predictive performance. Experimental results show the feasibility of significantly reducing model size without adversely impacting performance. Specifically, the optimized model demonstrated a 3.3% improvement in classification accuracy despite a 16.8% reduction in number of parameters compared th the baseline model. In conclusion, this research offers valuable insights for the development of deep learning models for resource-constrained IoT devices, underscoring the potential of hyperparameter optimization and model size reduction strategies. This work contributes to enhancing the practicality and usability of deep learning models in real-world environments, where high levels of accuracy and efficiency in data processing and classification tasks are required.

• Phonetics and Speech Sciences
• /
• v.13 no.1
• /
• pp.45-51
• /
• 2021

End-to-end (E2E) automatic speech recognition (ASR) has achieved promising performance gains with the introduced self-attention network, Transformer. However, due to training time and the number of hyperparameters, finding the optimal hyperparameter set is computationally expensive. This paper investigates the impact of hyperparameters in the Transformer network to answer two questions: which hyperparameter plays a critical role in the task performance and training speed. The Transformer network for training has two encoder and decoder networks combined with Connectionist Temporal Classification (CTC). We have trained the model with Wall Street Journal (WSJ) SI-284 and tested on devl93 and eval92. Seventeen hyperparameters were selected from the ESPnet training configuration, and varying ranges of values were used for experiments. The result shows that "num blocks" and "linear units" hyperparameters in the encoder and decoder networks reduce Word Error Rate (WER) significantly. However, performance gain is more prominent when they are altered in the encoder network. Training duration also linearly increased as "num blocks" and "linear units" hyperparameters' values grow. Based on the experimental results, we collected the optimal values from each hyperparameter and reduced the WER up to 2.9/1.9 from dev93 and eval93 respectively.

• Nuclear Engineering and Technology
• /
• v.54 no.8
• /
• pp.3027-3033
• /
• 2022

Background: In this study, various types of deep-learning models for predicting in vitro radiosensitivity from gene-expression profiling were compared. Methods: The clonogenic surviving fractions at 2 Gy from previous publications and microarray gene-expression data from the National Cancer Institute-60 cell lines were used to measure the radiosensitivity. Seven different prediction models including three distinct multi-layered perceptrons (MLP), four different convolutional neural networks (CNN) were compared. Folded cross-validation was applied to train and evaluate model performance. The criteria for correct prediction were absolute error < 0.02 or relative error < 10%. The models were compared in terms of prediction accuracy, training time per epoch, training fluctuations, and required calculation resources. Results: The strength of MLP-based models was their fast initial convergence and short training time per epoch. They represented significantly different prediction accuracy depending on the model configuration. The CNN-based models showed relatively high prediction accuracy, low training fluctuations, and a relatively small increase in the memory requirement as the model deepens. Conclusion: Our findings suggest that a CNN-based model with moderate depth would be appropriate when the prediction accuracy is important, and a shallow MLP-based model can be recommended when either the training resources or time are limited.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.16 no.4
• /
• pp.293-298
• /
• 2016

Document summarization is an important task in various areas where the goal is to select a few the most descriptive sentences from a given document as a succinct summary. Even without training data of human labeled summaries, there has been several interesting existing work in the literature that yields reasonable performance. In this paper, within the same unsupervised learning setup, we propose a more principled learning framework for the document summarization task. Specifically we formulate an optimization problem that expresses the requirements of both faithful preservation of the document contents and the summary length constraint. We circumvent the difficult integer programming originating from binary sentence selection via continuous relaxation and the low entropy penalization. We also suggest an efficient convex-concave optimization solver algorithm that guarantees to improve the original objective at every iteration. For several document datasets, we demonstrate that the proposed learning algorithm significantly outperforms the existing approaches.

• Journal of Ocean Engineering and Technology
• /
• v.13 no.4 s.35
• /
• pp.143-150
• /
• 1999

Multipurpose fisheries base was conceptually designed to establish marine ranching system in the coastal waters around Tongyoung, southern sea of Korea. Fisheries base for marine ranching system has integrated various facilities which were required for the process of spawning, rearing, training, releasing, monitoring and catching functions. This base has five steel piles for supporting upper structure and systems. Four steel piles are surrounded by circular net pen made by steel wire, they have the function of the protection against fouling for pile and scouring for bottom soil as well as secondary rearing and short stocking. We can use the last pile to moor a ship and access to the base. Principal structure with steel piles is designed by optimization technique considering design external forces in the coastal waters of return period of 50 years. Design optimization Problem is formulated for this base. Optimal design of multipurpose fisheries base is numerically investigated by sequential quadratic programming method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.6
• /
• pp.106-118
• /
• 1998

The study concerns a design procedure of rule-based systems. The proposed rule-based fuzzy modeling implements system structure and parameter identification in the efficient from of "IF..., THEN..." statements, and exploits the theory of system optimization and fuzzy implication rules. The method for rule-based fuzzy modeling concerns the from of the conclusion part of the the rules that can be constant. Both triangular and Gaussian-like membership function are studied. The optimization hinges on an autotuning algorithm that covers as a modified constrained optimization method known as a complex method. The study introduces a weighted performance index (objective function) that helps achieve a sound balance between the quality of results produced for the training and testing set. This methodology sheds light on the role and impact of different parameters of the model on its performance. The study is illustrated with the aid of two representative numerical examples.