• Smart Media Journal
• /
• v.7 no.1
• /
• pp.16-23
• /
• 2018

In this paper, we used the Deep Neural Network (DNN) to predict the number of daily spectators of Gwangju - KIA Champions Field in order to provide marketing data for the team and related businesses and for managing the inventories of the facilities in the stadium. In this study, the DNN model, which is based on an artificial neural network (ANN), was used, and four kinds of DNN model were designed along with dropout and batch normalization model to prevent overfitting. Each of four models consists of 10 DNNs, and we added extra models with ensemble model. Each model was evaluated by Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). The learning data from the model randomly selected 80% of the collected data from 2008 to 2017, and the other 20% were used as test data. With the result of 100 data selection, model configuration, and learning and prediction, we concluded that the predictive power of the DNN model with ensemble model is the best, and RMSE and MAPE are 15.17% and 14.34% higher, correspondingly, than the prediction value of the multiple linear regression model.

• Progress in Superconductivity
• /
• v.5 no.2
• /
• pp.98-104
• /
• 2004

We analyzed a noise-sensitivity profile of a specific SQUID sensor system for the localization of brain activity. The location of a neuromagnetic current source is estimated from the recording of spatially distributed SQUID sensors. According to the specific arrangement of the sensors, each site in the source space has different sensitivity, that is, the difference in the lead field vectors. Conversely, channel noises on each sensor will give a different amount of the estimation error to each of the source sites. e.g., a distant source site from the sensor system has a small lead-field vector in magnitude and low sensitivity. However, when we solve the inverse problem from the recorded sensor data, we use the inverse of the lead-field vector that is rather large, which results in an overestimated noise power on the site. Especially, the spatial sensitivity profile of a gradiometer system measuring tangential fields is much more complex than a radial magnetometer system. This is one of the causes to make the solutions of inverse problems unstable on intervening of the sensor noise. In this study, in order to improve the localization accuracy, we calculated the noise-sensitivity profile of our 40-channel planar SQUID gradiometer system, and applied it as a normalization weight factor to the source localization using synthetic aperture magnetometry.

• Tribology and Lubricants
• /
• v.38 no.3
• /
• pp.73-83
• /
• 2022

This paper is concerned with an analysis of a surface edge crack emanated from a sharp contact edge. For a geometrical model, a square wedge is in contact with a half plane whose materials are identical, and a surface perpendicular crack initiated from the contact edge exists in the half plane. To analyze this crack problem, it is necessary to evaluate the stress field on the crack line which are induced by the contact tractions and pseudo-dislocations that simulate the crack, using the Bueckner principle. In this Part I, the stress filed in the half plane due to the contact is re-summarized using an asymptotic analysis method, which has been published before by the author. Further focus is given to the stress field in the half plane due to a pseudo-edge dislocation, which will provide a stress solution due to a crack (i.e. a continuous distribution of edge dislocations) later, using the Burgers vector. Essential result of the present work is the corrective functions which modify the stress field of an infinite domain to apply for the present one which has free surfaces, and thus the infiniteness is no longer preserved. Numerical methods and coordinate normalization are used, which was developed for an edge crack problem, using the Gauss-Jacobi integration formula. The convergence of the corrective functions are investigated here. Features of the corrective functions and their application to a crack problem will be given in Part II.

• Journal of Biosystems Engineering
• /
• v.33 no.5
• /
• pp.309-316
• /
• 2008

The goal of this study was to develop prediction models to estimate the storage days of tomato. The transmittance spectral data measured on tomato were preprocessed through normalization, SNV, Savitzky-Golay, and Norris Gap and then were used to build the prediction models using partial least square (PLS) method. For the experiments, the tomato samples of different varieties were collected at different harvest time. The samples were taken right after harvest from the field and then were stored in a low-temperature storage room in which room temperature was maintained at $10^{\circ}C$. The transmittance spectral data of the tomato samples were measured at three-day intervals for 16 days. The performance of the prediction models was affected by the preprocessing techniques as well as the varieties and harvest time of the tomato. The best model was found when SNV was applied. The accuracy of the best model was 90.2%. It can be concluded that the transmittance spectra are useful information for predicting the period of storage of tomato.

• Geomechanics and Engineering
• /
• v.12 no.1
• /
• pp.35-52
• /
• 2017

In order to evaluate the grouting effects of water-rich fault in tunnels systematically, a feasible and scientific method is introduced based on the extension theory. First, eight main influencing factors are chosen as evaluation indexes by analyzing the changes of permeability, mechanical properties and deformation of surrounding rocks. The model of evaluating grouting effects based on the extension theory is established following this. According to four quality grades of grouting effects, normalization of evaluation indexes is carried out, aiming to meet the requirement of extension theory on data format. The index weight is allocated by adopting the entropy method. Finally, the model is applied to the grouting effects evaluation in water-rich fault F4-4 of Qingdao Jiaozhou Bay Subsea Tunnel, China. The evaluation results are in good agreement with the test results on the site, which shows that the evaluation model is feasible in this field, providing a powerful tool for systematically evaluating the grouting effects of water-rich fault in tunnels.

• Journal of Digital Contents Society
• /
• v.18 no.7
• /
• pp.1249-1257
• /
• 2017

Due to the 4th industrial revolution and an aged society, many studies are being conducted to apply virtual reality to medical field. Research on dementia is especially active. This paper proposes virtual reality based on cognitive rehabilitation contents using image recognition and clustering method to improve cognitive and physical disabilities caused by dementia. Unlike the existing cognitive rehabilitation system, this paper uses travel photos that reflect the memories of the subjects to be treated. In order to generate automated cognitive rehabilitation contents, we extract face information, food pictures, place information, and time information from photographs, and normalization is performed for clustering. And we present scenarios that can be used as cognitive rehabilitation contents using travel photos in virtual reality space.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.5
• /
• pp.97-102
• /
• 2017

Recently deep learning techniques such as convolutional neural networks (CNN) have been introduced to classify high-resolution remote sensing data. In this paper, we investigated the possibility of applying CNN to crop classification of farmland images captured by drones. The farming area was divided into seven classes: rice field, sweet potato, red pepper, corn, sesame leaf, fruit tree, and vinyl greenhouse. We performed image pre-processing and normalization to apply CNN, and the accuracy of image classification was more than 98%. With the output of this study, it is expected that the transition from the existing image classification methods to the deep learning based image classification methods will be facilitated in a fast manner, and the possibility of success can be confirmed.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.65 no.2
• /
• pp.47-57
• /
• 2023

The increase of impermeable area ratio is causing hydrologic cycle problems in urban areas and groundwater depletion in rural areas, permeable pavements are getting attention to expand permeable areas. The performance of the permeable concrete block pavement, which is part of the permeable pavement, is greatly affected by the porosity. In addition, the permeability coefficient is a major factor when designing permeable concrete block pavement. Existing porosity and permeability test methods have problems such as uneconomical or poor field applicability. The object of this study was to develop a methodology for evaluating porosity and permeability coefficient using a surface image of a permeable concrete block. Specimens are manufactured with various porosity ranges and porosity and permeability tests are performed. After surface image preprocessing, normalization and binarization methods were compared. Through this, the method with the highest correlation with the lab test result was determined. From the results, the PDR (pore determined ratio) was obtained. Simple linear regression analysis is performed with PDR and lab test results. The results showed a high correlation of R² more than 0.8, and the errors were also low.

• Biomedical Science Letters
• /
• v.29 no.4
• /
• pp.220-230
• /
• 2023

Identification of the pathogens causing infection is important in terms of patient's health management and infection control. Synovial fluids could be used as clinical samples to detect causative pathogens of prosthetic joint infections (PJIs) using molecular diagnostic assays, therefore, normalization and validation of clinical samples are necessary. Microbial culture is considered the gold standard for all infections, including PJIs. Recently, molecular diagnostic methods have been developed to overcome the limitation of microbial culture. Therefore, guideline for validating clinical samples to provide reliable results of molecular diagnostic assays for infectious diseases is required in clinical field. The present study aimed to develop an accurate validating method of synovial fluid clinical samples using GAPDH gene as an internal control to perform the quantitative PCR TaqMan probe assay to detect pathogens causing PJIs.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.290-297
• /
• 2024

We investigate the efficacy of ensemble learning methods, specifically the soft voting technique, for enhancing heart disease prediction accuracy. Our study uniquely combines Logistic Regression, SVM with RBF Kernel, and Random Forest models in a soft voting ensemble to improve predictive performance. We demonstrate that this approach outperforms individual models in diagnosing heart disease. Our research contributes to the field by applying a well-curated dataset with normalization and optimization techniques, conducting a comprehensive comparative analysis of different machine learning models, and showcasing the superior performance of the soft voting ensemble in medical diagnosis. This multifaceted approach allows us to provide a thorough evaluation of the soft voting ensemble's effectiveness in the context of heart disease prediction. We evaluate our models based on accuracy, precision, recall, F1 score, and Area Under the ROC Curve (AUC). Our results indicate that the soft voting ensemble technique achieves higher accuracy and robustness in heart disease prediction compared to individual classifiers. This study advances the application of machine learning in medical diagnostics, offering a novel approach to improve heart disease prediction. Our findings have significant implications for early detection and management of heart disease, potentially contributing to better patient outcomes and more efficient healthcare resource allocation.