• The Journal of the Acoustical Society of Korea
• /
• v.39 no.6
• /
• pp.505-514
• /
• 2020

Since a large amount of training data is typically needed to train Deep Neural Networks (DNNs), a parallel training approach is required to train the DNNs. The Stochastic Gradient Descent (SGD) algorithm is one of the most widely used methods to train the DNNs. However, since the SGD is an inherently sequential process, it requires some sort of approximation schemes to parallelize the SGD algorithm. In this paper, we review various efforts on parallelizing the SGD algorithm, and analyze the computational overhead, communication overhead, and the effects of the approximations.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.392-395
• /
• 2017

본 연구에서는 일 증발접시 증발량 산정을 위한 딥러닝 (deep learning) 모형의 적용성을 평가하였다. 본 연구에서 적용된 딥러닝 모형은 deep belief network (DBN) 기반 deep neural network (DNN) (DBN-DNN) 모형이다. 모형 적용성 평가를 위하여 부산 관측소에서 측정된 기상자료를 활용하였으며, 증발량과의 상관성이 높은 기상변수들 (일사량, 일조시간, 평균지상온도, 최대기온)의 조합을 고려하여 입력변수집합 (Set 1, Set 2, Set 3)별 모형을 구축하였다. DBN-DNN 모형의 성능은 통계학적 모형성능 평가지표 (coefficient of efficiency, CE; coefficient of determination, $r^2$; root mean square error, RMSE; mean absolute error, MAE)를 이용하여 평가되었으며, 기존의 두가지 형태의 ANN (artificial neural network), 즉 모형학습 시 SGD (stochastic gradient descent) 및 GD (gradient descent)를 각각 적용한 ANN-SGD 및 ANN-GD 모형과 비교하였다. 효과적인 모형학습을 위하여 각 모형의 초매개변수들은 GA (genetic algorithm)를 이용하여 최적화하였다. 그 결과, Set 1에 대하여 ANN-GD1 모형, Set 2에 대하여 DBN-DNN2 모형, Set 3에 대하여 DBN-DNN3 모형이 가장 우수한 모형 성능을 나타내는 것으로 분석되었다. 비록 비교 모형들 사이의 모형성능이 큰 차이를 보이지는 않았으나, 모든 입력집합에 대하여 DBN-DNN3, DBN-DNN2, ANN-SGD3 순으로 모형 효율성이 우수한 것으로 나타났다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.8
• /
• pp.3519-3533
• /
• 2020

Tuberculosis is a chronic and delayed infection which is easily experienced by young people. According to the statistics of the World Health Organization (WHO), there are nearly ten million fell ill with tuberculosis and a total of 1.5 million people died from tuberculosis in 2018 (including 251000 people with HIV). Tuberculosis is the largest single infectious pathogen that leads to death. In order to help doctors with tuberculosis diagnosis, we compare the tuberculosis classification abilities of six popular convolutional neural network (CNN) models in the same data set to find the best model. Before training, we optimize three parts of CNN to achieve better results. We employ sigmoid function to replace the step function as the activation function. What's more, we use binary cross entropy function as the cost function to replace traditional quadratic cost function. Finally, we choose stochastic gradient descent (SGD) as gradient descent algorithm. From the results of our experiments, we find that Densenet121 is most suitable for tuberculosis diagnosis and achieve a highest accuracy of 0.835. The optimization and expansion depend on the increase of data set and the improvements of Densenet121.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.5
• /
• pp.1125-1132
• /
• 2017

In a situation where the severity and frequency of drought events getting stronger and higher, many studies related to drought forecast have been conducted to improve the drought forecast accuracy. However it is difficult to predict drought events using a single model because of nonlinear and complicated characteristics of temporal behavior of drought events. In this study, in order to overcome the shortcomings of the single model approach, we first build various single models capable to explain the relationship between the meteorological drought index, Standardized Precipitation Index (SPI), and other independent variables such as world climate indices. Then, we developed a combined models using Stochastic Gradient Descent method among Ensemble Learnings.

• Journal of the Korean Society for information Management
• /
• v.38 no.2
• /
• pp.113-127
• /
• 2021

The purpose of this study is to propose a personalized book recommendation system to promote the use of university libraries. In particular, unlike many recommended services that are based on existing users' preferences, this study proposes a method that derive evaluation metrics using individual users' book rental history and tendencies, which can be an effective alternative when users' preferences are not available. This study suggests models using two matrix decomposition methods: Singular Value Decomposition(SVD) and Stochastic Gradient Descent(SGD) that recommend books to users in a way that yields an expected preference score for books that have not yet been read by them. In addition, the model was implemented using a user-based collaborative filtering algorithm by referring to book rental history of other users that have high similarities with the target user. Finally, user evaluation was conducted for the three models using the derived evaluation metrics. Each of the three models recommended five books to users who can either accept or reject the recommendations as the way to evaluate the models.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.8
• /
• pp.521-529
• /
• 2020

Forest fires are one of the most important environmental risks that have adverse effects on many aspects of life, such as the economy, environment, and health. The early detection, quick prediction, and rapid response of forest fires can play an essential role in saving property and life from forest fire risks. For the rapid discovery of forest fires, there is a method using meteorological data obtained from local sensors installed in each area by the Meteorological Agency. Meteorological conditions (e.g., temperature, wind) influence forest fires. This study evaluated a Data Mining (DM) approach to predict the burned area of forest fires. Five DM models, e.g., Stochastic Gradient Descent (SGD), Support Vector Machines (SVM), Decision Tree (DT), Random Forests (RF), and Deep Neural Network (DNN), and four feature selection setups (using spatial, temporal, and weather attributes), were tested on recent real-world data collected from Gyeonggi-do area over the last five years. As a result of the experiment, a DNN model using only meteorological data showed the best performance. The proposed model was more effective in predicting the burned area of small forest fires, which are more frequent. This knowledge derived from the proposed prediction model is particularly useful for improving firefighting resource management.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1329-1341
• /
• 2022

Destroying the marine environment and marine ecosystem and causing marine accidents, marine debris is generated every year, and among them, submerged marine debris is difficult to identify and collect because it is on the seabed. Therefore, deep-learning-based semantic segmentation was experimented on waste fish nets and waste ropes using underwater images to identify efficient collection and distribution. For segmentation, a high-resolution network (HRNet), a state-of-the-art deep learning technique, was used, and the performance of each optimizer was compared. In the segmentation result fish net, F1 score=(86.46%, 86.20%, 85.29%), IoU=(76.15%, 75.74%, 74.36%), For the rope F1 score=(80.49%, 80.48%, 77.86%), IoU=(67.35%, 67.33%, 63.75%) in the order of adaptive moment estimation (Adam), Momentum, and stochastic gradient descent (SGD). Adam's results were the highest in both fish net and rope. Through the research results, the evaluation of segmentation performance for each optimizer and the possibility of segmentation of marine debris in the latest deep learning technique were confirmed. Accordingly, it is judged that by applying the latest deep learning technique to the identification of submerged marine debris through underwater images, it will be helpful in estimating the distribution of marine sedimentation debris through more accurate and efficient identification than identification through the naked eye.

• Journal of Digital Convergence
• /
• v.20 no.4
• /
• pp.389-396
• /
• 2022

Deep Learning is based on a perceptron, and is currently being used in various fields such as image recognition, voice recognition, object detection, and drug development. Accordingly, a variety of learning algorithms have been proposed, and the number of neurons constituting a neural network varies greatly among researchers. This study analyzed the learning characteristics according to the number of neurons of the currently used SGD, momentum methods, AdaGrad, RMSProp, and Adam methods. To this end, a neural network was constructed with one input layer, three hidden layers, and one output layer. ReLU was applied to the activation function, cross entropy error (CEE) was applied to the loss function, and MNIST was used for the experimental dataset. As a result, it was concluded that the number of neurons 100-300, the algorithm Adam, and the number of learning (iteraction) 200 would be the most efficient in deep learning learning. This study will provide implications for the algorithm to be developed and the reference value of the number of neurons given new learning data in the future.

• International Journal of Computer Science & Network Security
• /
• v.24 no.2
• /
• pp.101-112
• /
• 2024

Telugu language is considered as fourth most used language in India especially in the regions of Andhra Pradesh, Telangana, Karnataka etc. In international recognized countries also, Telugu is widely growing spoken language. This language comprises of different dependent and independent vowels, consonants and digits. In this aspect, the enhancement of Telugu Handwritten Character Recognition (HCR) has not been propagated. HCR is a neural network technique of converting a documented image to edited text one which can be used for many other applications. This reduces time and effort without starting over from the beginning every time. In this work, a Unicode based Handwritten Character Recognition(U-HCR) is developed for translating the handwritten Telugu characters into English language. With the use of Centre of Gravity (CG) in our model we can easily divide a compound character into individual character with the help of Unicode values. For training this model, we have used both online and offline Telugu character datasets. To extract the features in the scanned image we used convolutional neural network along with Machine Learning classifiers like Random Forest and Support Vector Machine. Stochastic Gradient Descent (SGD), Root Mean Square Propagation (RMS-P) and Adaptative Moment Estimation (ADAM)optimizers are used in this work to enhance the performance of U-HCR and to reduce the loss function value. This loss value reduction can be possible with optimizers by using CNN. In both online and offline datasets, proposed model showed promising results by maintaining the accuracies with 90.28% for SGD, 96.97% for RMS-P and 93.57% for ADAM respectively.

• Journal of the Korean Society of Radiology
• /
• v.16 no.1
• /
• pp.25-34
• /
• 2022

Brain computed tomography (CT) is useful for brain lesion diagnosis, such as brain hemorrhage, due to non-invasive methodology, 3-dimensional image provision, low radiation dose. However, there has been numerous misdiagnosis owing to a lack of radiologist and heavy workload. Recently, object detection technologies based on artificial intelligence have been developed in order to overcome the limitations of traditional diagnosis. In this study, the applicability of a deep learning-based YOLOv5s model was evaluated for brain hemorrhage detection using brain CT images. Also, the effect of hyperparameters in the trained YOLOv5s model was analyzed. The YOLOv5s model consisted of backbone, neck and output modules. The trained model was able to detect a region of brain hemorrhage and provide the information of the region. The YOLOv5s model was trained with various activation functions, optimizer functions, loss functions and epochs, and the performance of the trained model was evaluated in terms of brain hemorrhage detection accuracy and training time. The results showed that the trained YOLOv5s model is able to provide a bounding box for a region of brain hemorrhage and the accuracy of the corresponding box. The performance of the YOLOv5s model was improved by using the mish activation function, the stochastic gradient descent (SGD) optimizer function and the completed intersection over union (CIoU) loss function. Also, the accuracy and training time of the YOLOv5s model increased with the number of epochs. Therefore, the YOLOv5s model is suitable for brain hemorrhage detection using brain CT images, and the performance of the model can be maximized by using appropriate hyperparameters.