• Journal of the Semiconductor & Display Technology
• /
• v.20 no.1
• /
• pp.64-69
• /
• 2021

In this paper, a method for improving the defect classification performance in low contrast, ununiformity and featureless steel plate surfaces has been studied based on deep convolution neural network and transfer-learning neural network. The steel plate surface images have low contrast, ununiformity, and featureless, so that the contrast between defect and defect-free regions are not discriminated. These characteristics make it difficult to extract the feature of the surface defect image. A classifier based on a deep convolution neural network is constructed to extract features automatically for effective classification of images with these characteristics. As results of the experiment, AlexNet-based transfer-learning classifier showed excellent classification performance of 99.43% with less than 160 seconds of training time. The proposed classification system showed excellent classification performance for low contrast, ununiformity, and featureless surface images.

• Communications for Statistical Applications and Methods
• /
• v.26 no.6
• /
• pp.591-610
• /
• 2019

Deep Learning is one of the machine learning methods to find features from a huge data using non-linear transformation. It is now commonly used for supervised learning in many fields. In particular, Convolutional Neural Network (CNN) is the best technique for the image classification since 2012. For users who consider deep learning models for real-world applications, Keras is a popular API for neural networks written in Python and also can be used in R. We try examine the parameter estimation procedures of Deep Neural Network and structures of CNN models from basics to advanced techniques. We also try to figure out some crucial steps in CNN that can improve image classification performance in the CIFAR10 dataset using Keras. We found that several stacks of convolutional layers and batch normalization could improve prediction performance. We also compared image classification performances with other machine learning methods, including K-Nearest Neighbors (K-NN), Random Forest, and XGBoost, in both MNIST and CIFAR10 dataset.

• International journal of advanced smart convergence
• /
• v.12 no.2
• /
• pp.56-66
• /
• 2023

The goal of deep learning is to extract complex features from multidimensional data use the features to create models that connect input and output. Deep learning is a process of learning nonlinear features and functions from complex data, and the user data that is employed to train deep learning models has become the focus of privacy concerns. Companies that collect user's sensitive personal information, such as users' images and voices, own this data for indefinite period of times. Users cannot delete their personal information, and they cannot limit the purposes for which the data is used. The study has designed a deep learning method that employs privacy protection technology that uses distributed collaborative learning so that multiple participants can use neural network models collaboratively without sharing the input datasets. To prevent direct leaks of personal information, participants are not shown the training datasets during the model training process, unlike traditional deep learning so that the personal information in the data can be protected. The study used a method that can selectively share subsets via an optimization algorithm that is based on modified distributed stochastic gradient descent, and the result showed that it was possible to learn with improved learning accuracy while protecting personal information.

• Korea Trade Review
• /
• v.46 no.1
• /
• pp.169-187
• /
• 2021

This paper analyzes the feasibility of using machine learning and deep learning methods to forecast the income and employment using the strategic industries as well as investment, export, and exchange rates. The decision tree, artificial neural network, support vector machine, and deep learning models were used to forecast the income and employment in Busan. The following were the main findings of the comparison of their predictive abilities. First, the decision tree models predict the income and employment well. The forecasting values for the income and employment appeared somewhat differently according to the depth of decision trees and several conditions of strategic industries as well as investment, export, and exchange rates. Second, since the artificial neural network models show that the coefficients are somewhat low and RMSE are somewhat high, these models are not good forecasting the income and employment. Third, the support vector machine models show the high predictive power with the high coefficients of determination and low RMSE. Fourth, the deep neural network models show the higher predictive power with appropriate epochs and batch sizes. Thus, since the machine learning and deep learning models can predict the employment well, we need to adopt the machine learning and deep learning models to forecast the income and employment.

• International Journal of Computer Science & Network Security
• /
• v.24 no.5
• /
• pp.212-216
• /
• 2024

Feature Selection have turned into the main point of investigations particularly in bioinformatics where there are numerous applications. Deep learning technique is a useful asset to choose features, anyway not all calculations are on an equivalent balance with regards to selection of relevant features. To be sure, numerous techniques have been proposed to select multiple features using deep learning techniques. Because of the deep learning, neural systems have profited a gigantic top recovery in the previous couple of years. Anyway neural systems are blackbox models and not many endeavors have been made so as to examine the fundamental procedure. In this proposed work a new calculations so as to do feature selection with deep learning systems is introduced. To evaluate our outcomes, we create relapse and grouping issues which enable us to think about every calculation on various fronts: exhibitions, calculation time and limitations. The outcomes acquired are truly encouraging since we figure out how to accomplish our objective by outperforming irregular backwoods exhibitions for each situation. The results prove that the proposed method exhibits better performance than the traditional methods.

• Journal of the Semiconductor & Display Technology
• /
• v.18 no.2
• /
• pp.1-5
• /
• 2019

As the number of IOT devices is growing rapidly, various 'see-thru connection' techniques have been reported for efficient communication with them. In this paper, we propose a deep learning based IOT device recognition system for interaction with these devices. The overall system consists of a TensorFlow based deep learning server and two Android apps for data collection and recognition purposes. As the basic neural network model, we adopted Google's inception-v3, and modified the output stage to classify 20 types of IOT devices. After creating a data set consisting of 1000 images of 20 categories, we trained our deep learning network using a transfer learning technology. As a result of the experiment, we achieve 94.5% top-1 accuracy and 98.1% top-2 accuracy.

• Journal of Korea Multimedia Society
• /
• v.20 no.5
• /
• pp.769-781
• /
• 2017

Deep learning networks like Convolutional Neural Networks (CNNs) show successful performances in many computer vision applications such as image classification, object detection, and so on. For implementation of deep learning networks in embedded system with limited processing power and memory, deep learning network may need to be simplified. However, simplified deep learning network cannot learn every possible scene. One realistic strategy for embedded deep learning network is to construct a simplified deep learning network model optimized for the scene images of the installation place. Then, automatic training will be necessitated for commercialization. In this paper, as an intermediate step toward automatic training under fisheye camera environments, we study more precise human localization in fisheye images, and propose an accurate human localization method, Automatic Ground-Truth Labelling Method (AGTLM). AGTLM first localizes candidate human object bounding boxes by utilizing GoogLeNet-LSTM approach, and after reassurance process by GoogLeNet-based CNN network, finally refines them more correctly and precisely(tightly) by applying saliency object detection technique. The performance improvement of the proposed human localization method, AGTLM with respect to accuracy and tightness is shown through several experiments.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.2
• /
• pp.147-155
• /
• 2024

Based on the recently developed deep learning technology, many studies have been conducted on deep learning networks that simultaneously detect and classify targets of interest in synthetic aperture radar(SAR) images. Although numerous research results have been derived mainly with the open SAR ship datasets, there is a lack of work carried out on the deep learning network aimed at detecting and classifying SAR ground targets and trained with the synthetic dataset generated from electromagnetic scattering simulations. In this respect, this paper presents the deep learning network trained with the synthetic dataset and applies it to detecting and classifying real SAR ground targets. With experiment results, this paper also analyzes the network performance according to the composition ratio between the real measured data and the synthetic data involved in network training. Finally, the summary and limitations are discussed to give information on the future research direction.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.9
• /
• pp.3730-3744
• /
• 2020

This study proposes a deep learning-based evolutionary recommendation model for heterogeneous big data integration, for which collaborative filtering and a neural-network algorithm are employed. The proposed model is used to apply an individual's importance or sensory level to formulate a recommendation using the decision-making feedback. The evolutionary recommendation model is based on the Deep Neural Network (DNN), which is useful for analyzing and evaluating the feedback data among various neural-network algorithms, and the DNN is combined with collaborative filtering. The designed model is used to extract health information from data collected by the Korea National Health and Nutrition Examination Survey, and the collaborative filtering-based recommendation model was compared with the deep learning-based evolutionary recommendation model to evaluate its performance. The RMSE is used to evaluate the performance of the proposed model. According to the comparative analysis, the accuracy of the deep learning-based evolutionary recommendation model is superior to that of the collaborative filtering-based recommendation model.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.5
• /
• pp.297-307
• /
• 2022

The simple procedural segment selection algorithm commonly used in Dynamic Adaptive Streaming over HTTP (DASH) reveals severe weakness to provide high-quality streaming services in the integrated mobile networks of various wired and wireless links. A major issue could be how to properly cope with dynamically changing underlying network conditions. The key to meet it should be to make the segment selection algorithm much more adaptive to fluctuation of network traffics. This paper presents a system architecture that replaces the existing procedural segment selection algorithm with a deep reinforcement learning algorithm based on the Asynchronous Advantage Actor-Critic (A3C). The distributed A3C-based deep learning server is designed and implemented to allow multiple clients in different network conditions to stream videos simultaneously, collect learning data quickly, and learn asynchronously, resulting in greatly improved learning speed as the number of video clients increases. The performance analysis shows that the proposed algorithm outperforms both the conventional DASH algorithm and the Deep Q-Network algorithm in terms of the user's quality of experience and the speed of deep learning.