• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.527-529
• /
• 2023

Generative Adversarial Networks (GANs) models have developed rapidly due to the emergence of various variation models and their wide applications. Despite many recent developments in GANs, mode collapse, and instability are still unresolved issues. To address these problems, we focused on the fact that a single GANs model itself cannot realize local failure during the training phase without external standards. This paper introduces a novel training process involving multiple GANs, inspired by auction mechanisms. During the training, auxiliary performance metrics for each GANs are determined by the others through the process of various auction methods.

• Journal of Korea Water Resources Association
• /
• v.33 no.5
• /
• pp.537-550
• /
• 2000

In this study, Neural Networks models were used to forecast daily streamflow at Jindong station of the Nakdong River basin. Neural Networks models consist of CASE 1(5-5-1) and CASE 2(5-5-5-1). The criteria which separates two models is the number of hidden layers. Each model has Fletcher-Reeves Conjugate Gradient BackPropagation(FR-CGBP) and Scaled Conjugate Gradient BackPropagation(SCGBP) algorithms, which are better than original BackPropagation(BP) in convergence of global error and training tolerance. The data which are available for model training and validation were composed of wet, average, dry, wet+average, wet+dry, average+dry and wet+average+dry year respectively. During model training, the optimal connection weights and biases were determined using each data set and the daily streamflow was calculated at the same time. Except for wet+dry year, the results of training were good conditions by statistical analysis of forecast errors. And, model validation was carried out using the connection weights and biases which were calculated from model training. The results of validation were satisfactory like those of training. Daily streamflow forecasting using Neural Networks models were compared with those forecasted by Multiple Regression Analysis Mode(MRAM). Neural Networks models were displayed slightly better results than MRAM in this study. Thus, Neural Networks models have much advantage to provide a more sysmatic approach, reduce model parameters, and shorten the time spent in the model development.

• Computers and Concrete
• /
• v.16 no.6
• /
• pp.919-932
• /
• 2015

This paper presents a new method for assessing the three-point-bending (3PB) strength of mortar beams in a non-destructive manner, based on neural network (NN) models. The models are based on the radial basis function (RBF) architecture and the fuzzy means algorithm is employed for training, in order to boost the prediction accuracy. Data for training the models were collected based on a series of experiments, where the cement mortar beams were subjected to various bending mechanical loads and the resulting pressure stimulated currents (PSCs) were recorded. The input variables to the NN models were then calculated by describing the PSC relaxation process through a generalization of Boltzmannn-Gibbs statistical physics, known as non-extensive statistical physics (NESP). The NN predictions were evaluated using k-fold cross-validation and new data that were kept independent from training; it can be seen that the proposed method can successfully form the basis of a non-destructive tool for assessing the bending strength. A comparison with a different NN architecture confirms the superiority of the proposed approach.

• Korean Journal of Remote Sensing
• /
• v.39 no.4
• /
• pp.395-407
• /
• 2023

Super-resolution (SR) has great significance in image processing because it enables downstream vision tasks with high spatial resolution. Recently, SR studies have adopted deep learning networks and achieved remarkable SR performance compared to conventional example-based methods. Deep-learning-based SR models generally require low-resolution (LR) images and the corresponding high-resolution (HR) images as training dataset. Due to the difficulties in obtaining real-world LR-HR datasets, most SR models have used only HR images and generated LR images with predefined degradation such as bicubic downsampling. However, SR models trained on simple image degradation do not reflect the properties of the images and often result in deteriorated SR qualities when applied to real-world images. In this study, we propose an image degradation model for HR satellite images based on the modulation transfer function (MTF) of an imaging sensor. Because the proposed method determines the image degradation based on the sensor properties, it is more suitable for training SR models on remote sensing images. Experimental results on HR satellite image datasets demonstrated the effectiveness of applying MTF-based filters to construct a more realistic LR-HR training dataset.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.1187-1193
• /
• 2022

A construction site is a highly complex and constantly changing environment, where hazardous areas are difficult to detect if workers lack sufficient knowledge and awareness. Thus, frequent worker safety training is required. Numerous studies on using virtual reality (VR) for safety training were published. While they demonstrate the potential for improving the skills necessary to avoid accidents in the construction industry, they remain difficult to apply at actual construction sites. VR requires specialized hardware and software, limiting workers' access and restricting workers' participation in training sessions. As a result, this paper proposes multiple platforms for immersive virtual reality safety training (VRMP) based on Industry Foundation Classes (IFC) and web technologies such as immersive web (WebXR). The VRMP is compatible with mobile and desktop devices currently by workers and demonstrates scenario models familiar to workers. Also, it reduces development time by utilizing Building Information Models (BIM). Additionally, The VRMP collects data from workers in a virtual environment to assess each worker's safety level, assisting workers in effectively and comfortably gaining a better understanding and raising their awareness. This paper develops a case study based on the VRPM in order to assess its effectiveness.

• Journal of Engineering Education Research
• /
• v.19 no.2
• /
• pp.97-101
• /
• 2016

This paper examines the industry field training education model, analyze the operational status proposed improvement measures. Data were analyzed using a field training participating students participating industry last three years. On the other hand analysis field training participating students increased, industry participation has decreased. And most of the students took part in the seasonal short-term job training. In addition, it was difficult to analyze the employment status field training operations follow-up member. In this paper, a field training operations support system management models and practical training courses organized field trips how to improve. Field training operations support will be strengthened through the work associated with the company expanding participation model introduced and is expected to increase in the long-term practical training, students participate in field training system improvement. Run the job training Improvement in future research presented in this paper attempts to analyze the students' employment status and results of operations involved.

• Journal of the Society of Naval Architects of Korea
• /
• v.57 no.3
• /
• pp.140-151
• /
• 2020

It is important to identify the location of ship hull blocks with exact block identification number when scheduling the shipbuilding process. The wrong information on the location and identification number of some hull block can cause low productivity by spending time to find where the exact hull block is. In order to solve this problem, it is necessary to equip the system to track the location of the blocks and to identify the identification numbers of the blocks automatically. There were a lot of researches of location tracking system for the hull blocks on the stockyard. However there has been no research to identify the hull blocks on the stockyard. This study compares the performance of 5 Convolutional Neural Network (CNN) models with multi-view image set on the classification of the hull blocks to identify the blocks on the stockyard. The CNN models are open algorithms of ImageNet Large-Scale Visual Recognition Competition (ILSVRC). Four scaled hull block models are used to acquire the images of ship hull blocks. Learning and transfer learning of the CNN models with original training data and augmented data of the original training data were done. 20 tests and predictions in consideration of five CNN models and four cases of training conditions are performed. In order to compare the classification performance of the CNN models, accuracy and average F1-Score from confusion matrix are adopted as the performance measures. As a result of the comparison, Resnet-152v2 model shows the highest accuracy and average F1-Score with full block prediction image set and with cropped block prediction image set.

• ETRI Journal
• /
• v.32 no.1
• /
• pp.160-162
• /
• 2010

For the acoustic models of embedded speech recognition systems, hidden Markov models (HMMs) are usually quantized and the original full space distributions are represented by combinations of a few quantized distribution prototypes. We propose a maximum likelihood objective function to train the quantized distribution prototypes. The experimental results show that the new training algorithm and the link structure adaptation scheme for the quantized HMMs reduce the word recognition error rate by 20.0%.

• Electronics and Telecommunications Trends
• /
• v.38 no.6
• /
• pp.84-94
• /
• 2023

Open source has many advantages and is widely used in various fields. However, legal disputes regarding copyright and licensing of datasets and learning models have recently arisen in artificial intelligence developments. We examine how datasets affect artificial intelligence learning and services from the perspective of copyrighting and licensing when datasets are used for training models. The licensing conditions of datasets can lead to copyright infringement and license violation, thus determining the scope of disclosure and commercialization of the trained model. In addition, we examine related legal issues.

• The Bulletin of The Korean Astronomical Society
• /
• v.42 no.2
• /
• pp.60.1-60.1
• /
• 2017

In this study we apply Convolution Neural Network(CNN) to solar flare occurrence prediction with various parameter options using the 00:00 UT MDI images from 1996 to 2010 (total 4962 images). We assume that only X, M and C class flares correspond to "flare occurrence" and the others to "non-flare". We have attempted to look for the best options for the models with two CNN pre-trained models (AlexNet and GoogLeNet), by modifying training images and changing hyper parameters. Our major results from this study are as follows. First, the flare occurrence predictions are relatively good with about 80 % accuracies. Second, both flare prediction models based on AlexNet and GoogLeNet have similar results but AlexNet is faster than GoogLeNet. Third, modifying the training images to reduce the projection effect is not effective. Fourth, skill scores of our flare occurrence model are mostly better than those of the previous models.