• Computers and Concrete
• /
• v.24 no.6
• /
• pp.555-560
• /
• 2019

During the application of shotcrete, a part of the concrete bounces back after hitting to the surface, the reinforcement or previously sprayed concrete. This rebound material is definitely not added to the mixture and considered as waste. In this study, a deep neural network model was developed to predict the rebound material during shotcrete application. The factors affecting rebound and the datasets of these parameters were obtained from previous experiments. The Long Short-Term Memory (LSTM) architecture of the proposed deep neural network model was used in accordance with this data set. In the development of the proposed four-tier prediction model, the dataset was divided into 90% training and 10% test. The deep neural network was modeled with 11 dependents 1 independent data by determining the most appropriate hyper parameter values for prediction. Accuracy and error performance in success performance of LSTM model were evaluated over MSE and RMSE. A success of 93.2% was achieved at the end of training of the model and a success of 85.6% in the test. There was a difference of 7.6% between training and test. In the following stage, it is aimed to increase the success rate of the model by increasing the number of data in the data set with synthetic and experimental data. In addition, it is thought that prediction of the amount of rebound during dry-mix shotcrete application will provide economic gain as well as contributing to environmental protection.

• Journal of information and communication convergence engineering
• /
• v.13 no.2
• /
• pp.123-131
• /
• 2015

Training neural networks is a complex task with great importance in the field of supervised learning. In the training process, a set of input-output patterns is repeated to an artificial neural network (ANN). From those patterns weights of all the interconnections between neurons are adjusted until the specified input yields the desired output. In this paper, a new hybrid algorithm is proposed for global optimization of connection weights in an ANN. Dynamic swarms are shown to converge rapidly during the initial stages of a global search, but around the global optimum, the search process becomes very slow. In contrast, the gradient descent method can achieve faster convergence speed around the global optimum, and at the same time, the convergence accuracy can be relatively high. Therefore, the proposed hybrid algorithm combines the dynamic particle swarm optimization (DPSO) algorithm with the backpropagation (BP) algorithm, also referred to as the DPSO-BP algorithm, to train the weights of an ANN. In this paper, we intend to show the superiority (time performance and quality of solution) of the proposed hybrid algorithm (DPSO-BP) over other more standard algorithms in neural network training. The algorithms are compared using two different datasets, and the results are simulated.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.4
• /
• pp.1110-1127
• /
• 2022

To improve the training efficiency and generalization performance of a support vector machine (SVM) in a large-scale set, an optimal SVM learning method based on adaptive sparse sampling and the granularity shift factor is presented. The proposed method combines sampling optimization with learner optimization. First, an adaptive sparse sampling method based on the potential function density clustering is designed to adaptively obtain sparse sampling samples, which can achieve a reduction in the training sample set and effectively approximate the spatial structure distribution of the original sample set. A granularity shift factor method is then constructed to optimize the SVM decision hyperplane, which fully considers the neighborhood information of each granularity region in the sparse sampling set. Experiments on an artificial dataset and three benchmark datasets show that the proposed method can achieve a relatively higher training efficiency, as well as ensure a good generalization performance of the learner. Finally, the effectiveness of the proposed method is verified.

• International journal of advanced smart convergence
• /
• v.13 no.2
• /
• pp.48-60
• /
• 2024

With the exponential growth of satellite data utilization, machine learning has become pivotal in enhancing innovation and cybersecurity in satellite systems. This paper investigates the role of machine learning techniques in identifying and mitigating vulnerabilities and code smells within satellite software. We explore satellite system architecture and survey applications like vulnerability analysis, source code refactoring, and security flaw detection, emphasizing feature extraction methodologies such as Abstract Syntax Trees (AST) and Control Flow Graphs (CFG). We present practical examples of feature extraction and training models using machine learning techniques like Random Forests, Support Vector Machines, and Gradient Boosting. Additionally, we review open-access satellite datasets and address prevalent code smells through systematic refactoring solutions. By integrating continuous code review and refactoring into satellite software development, this research aims to improve maintainability, scalability, and cybersecurity, providing novel insights for the advancement of satellite software development and security. The value of this paper lies in its focus on addressing the identification of vulnerabilities and resolution of code smells in satellite software. In terms of the authors' contributions, we detail methods for applying machine learning to identify potential vulnerabilities and code smells in satellite software. Furthermore, the study presents techniques for feature extraction and model training, utilizing Abstract Syntax Trees (AST) and Control Flow Graphs (CFG) to extract relevant features for machine learning training. Regarding the results, we discuss the analysis of vulnerabilities, the identification of code smells, maintenance, and security enhancement through practical examples. This underscores the significant improvement in the maintainability and scalability of satellite software through continuous code review and refactoring.

• Journal of Information Processing Systems
• /
• v.9 no.4
• /
• pp.633-650
• /
• 2013

All the imputation techniques proposed so far in literature for data imputation are offline techniques as they require a number of iterations to learn the characteristics of data during training and they also consume a lot of computational time. Hence, these techniques are not suitable for applications that require the imputation to be performed on demand and near real-time. The paper proposes a computational intelligence based architecture for online data imputation and extended versions of an existing offline data imputation method as well. The proposed online imputation technique has 2 stages. In stage 1, Evolving Clustering Method (ECM) is used to replace the missing values with cluster centers, as part of the local learning strategy. Stage 2 refines the resultant approximate values using a General Regression Neural Network (GRNN) as part of the global approximation strategy. We also propose extended versions of an existing offline imputation technique. The offline imputation techniques employ K-Means or K-Medoids and Multi Layer Perceptron (MLP)or GRNN in Stage-1and Stage-2respectively. Several experiments were conducted on 8benchmark datasets and 4 bank related datasets to assess the effectiveness of the proposed online and offline imputation techniques. In terms of Mean Absolute Percentage Error (MAPE), the results indicate that the difference between the proposed best offline imputation method viz., K-Medoids+GRNN and the proposed online imputation method viz., ECM+GRNN is statistically insignificant at a 1% level of significance. Consequently, the proposed online technique, being less expensive and faster, can be employed for imputation instead of the existing and proposed offline imputation techniques. This is the significant outcome of the study. Furthermore, GRNN in stage-2 uniformly reduced MAPE values in both offline and online imputation methods on all datasets.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.3
• /
• pp.423-432
• /
• 2022

This paper addresses the safety concern that the SOH of batteries in electric vehicles decreases sharply when drivers change or their driving patterns change. Such a change can overload the battery, reduce the battery life, and induce safety issues. This paper aims to present the SOH as the changes on a dashboard of an electric vehicle in real-time in response to user pattern changes. As part of the training process I used battery data among the datasets provided by NASA, and built models incorporating linear regression and ARIMA, and predicted new battery data that contained user changes based on previously trained models. Therefore, as a result of the prediction, the linear regression is better at predicting some changes in SOH based on the user's pattern change if we have more battery datasets with a wide range of independent values. The ARIMA model can be used if we only have battery datasets with SOH data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.6
• /
• pp.1530-1544
• /
• 2023

Data monitoring is an important foundation of modern science. In most cases, the monitoring data is time-series data, which has high application value. The deep learning algorithm has a strong nonlinear fitting capability, which enables the recognition of time series by capturing anomalous information in time series. At present, the research of time series recognition based on deep learning is especially important for data monitoring. Deep learning algorithms require a large amount of data for training. However, abnormal sample is a small sample in time series, which means the number of abnormal time series can seriously affect the accuracy of recognition algorithm because of class imbalance. In order to increase the number of abnormal sample, a data augmentation method called GANBATS (GAN-based Bi-LSTM and Attention for Time Series) is proposed. In GANBATS, Bi-LSTM is introduced to extract the timing features and then transfer features to the generator network of GANBATS.GANBATS also modifies the discriminator network by adding an attention mechanism to achieve global attention for time series. At the end of discriminator, GANBATS is adding averagepooling layer, which merges temporal features to boost the operational efficiency. In this paper, four time series datasets and five data augmentation algorithms are used for comparison experiments. The generated data are measured by PRD(Percent Root Mean Square Difference) and DTW(Dynamic Time Warping). The experimental results show that GANBATS reduces up to 26.22 in PRD metric and 9.45 in DTW metric. In addition, this paper uses different algorithms to reconstruct the datasets and compare them by classification accuracy. The classification accuracy is improved by 6.44%-12.96% on four time series datasets.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.6
• /
• pp.635-644
• /
• 2020

Object recognition, detection and instance segmentation based on DL (Deep Learning) have being used in various practices, and mainly optical images are used as training data for DL models. The major objective of this paper is object segmentation and building detection by utilizing multimodal datasets as well as optical images for training Detectron2 model that is one of the improved R-CNN (Region-based Convolutional Neural Network). For the implementation, infrared aerial images, LiDAR data, and edges from the images, and Haralick features, that are representing statistical texture information, from LiDAR (Light Detection And Ranging) data were generated. The performance of the DL models depends on not only on the amount and characteristics of the training data, but also on the fusion method especially for the multimodal data. The results of segmenting objects and detecting buildings by applying hybrid fusion - which is a mixed method of early fusion and late fusion - results in a 32.65% improvement in building detection rate compared to training by optical image only. The experiments demonstrated complementary effect of the training multimodal data having unique characteristics and fusion strategy.

• The Journal of the Korea Contents Association
• /
• v.21 no.11
• /
• pp.135-144
• /
• 2021

Recently, data-driven decision-making technology has become a key technology leading the data industry, and machine learning technology for this requires high-quality training datasets. However, real-world data contains missing values for various reasons, which degrades the performance of prediction models learned from the poor training data. Therefore, in order to build a high-performance model from real-world datasets, many studies on automatically imputing missing values in initial training data have been actively conducted. Many of conventional machine learning-based imputation techniques for handling missing data involve very time-consuming and cumbersome work because they are applied only to numeric type of columns or create individual predictive models for each columns. Therefore, this paper proposes a new data imputation technique called 'Denoising Self-Attention Network (DSAN)', which can be applied to mixed-type dataset containing both numerical and categorical columns. DSAN can learn robust feature expression vectors by combining self-attention and denoising techniques, and can automatically interpolate multiple missing variables in parallel through multi-task learning. To verify the validity of the proposed technique, data imputation experiments has been performed after arbitrarily generating missing values for several mixed-type training data. Then we show the validity of the proposed technique by comparing the performance of the binary classification models trained on imputed data together with the errors between the original and imputed values.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_4
• /
• pp.1111-1123
• /
• 2023

In recent times, semantic image segmentation methods using deep learning models have been widely used for monitoring changes in surface attributes using remote sensing imagery. To enhance the performance of various UNet-based deep learning models, including the prominent UNet model, it is imperative to have a sufficiently large training dataset. However, enlarging the training dataset not only escalates the hardware requirements for processing but also significantly increases the time required for training. To address these issues, transfer learning is used as an effective approach, enabling performance improvement of models even in the absence of massive training datasets. In this paper we present three transfer learning models, UNet-ResNet50, UNet-VGG19, and CBAM-DRUNet-VGG19, which are combined with the representative pretrained models of VGG19 model and ResNet50 model. We applied these models to building extraction tasks and analyzed the accuracy improvements resulting from the application of transfer learning. Considering the substantial impact of learning rate on the performance of deep learning models, we also analyzed performance variations of each model based on different learning rate settings. We employed three datasets, namely Kompsat-3A dataset, WHU dataset, and INRIA dataset for evaluating the performance of building extraction results. The average accuracy improvements for the three dataset types, in comparison to the UNet model, were 5.1% for the UNet-ResNet50 model, while both UNet-VGG19 and CBAM-DRUNet-VGG19 models achieved a 7.2% improvement.