• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.5
• /
• pp.35-41
• /
• 2017

In this paper, we analyze the performance of the recently introduced Hint-knowledge distillation (KD) training approach based on the teacher-student framework for knowledge distillation and knowledge transfer. As a deep neural network (DNN) considered in this paper, the deep residual network (ResNet), which is currently regarded as the latest DNN, is used for the teacher-student framework. Therefore, when implementing the Hint-KD training, we investigate the impact on the weight of KD information based on the soften factor in terms of classification accuracy using the widely used open deep learning frameworks, Caffe. As a results, it can be seen that the recognition accuracy of the student model is improved when the fixed value of the KD information is maintained rather than the gradual decrease of the KD information during training.

• Imaging Science in Dentistry
• /
• v.52 no.4
• /
• pp.351-357
• /
• 2022

Purpose: Convolutional neural networks (CNNs) have rapidly emerged as one of the most promising artificial intelligence methods in the field of medical and dental research. CNNs can provide an effective diagnostic methodology allowing for the detection of early-staged diseases. Therefore, this study aimed to evaluate the performance of a deep CNN algorithm for apical lesion segmentation from panoramic radiographs. Materials and Methods: A total of 1000 panoramic images showing apical lesions were separated into training (n=800, 80%), validation (n=100, 10%), and test (n=100, 10%) datasets. The performance of identifying apical lesions was evaluated by calculating the precision, recall, and F1-score. Results: In the test group of 180 apical lesions, 147 lesions were segmented from panoramic radiographs with an intersection over union (IoU) threshold of 0.3. The F1-score values, as a measure of performance, were 0.828, 0.815, and 0.742, respectively, with IoU thresholds of 0.3, 0.4, and 0.5. Conclusion: This study showed the potential utility of a deep learning-guided approach for the segmentation of apical lesions. The deep CNN algorithm using U-Net demonstrated considerably high performance in detecting apical lesions.

• Korean Journal of Remote Sensing
• /
• v.36 no.2_1
• /
• pp.199-215
• /
• 2020

A seagrass that is marine vascular plants plays an important role in the marine ecosystem, so periodic monitoring ofseagrass habitatsis being performed. Recently, the use of dronesthat can easily acquire very high-resolution imagery is increasing to efficiently monitor seagrass habitats. And deep learning based on a convolutional neural network has shown excellent performance in semantic segmentation. So, studies applied to deep learning models have been actively conducted in remote sensing. However, the segmentation accuracy was different due to the hyperparameter, various deep learning models and imagery. And the normalization of the image and the tile and batch size are also not standardized. So,seagrass habitats were segmented from drone-borne imagery using a deep learning that shows excellent performance in this study. And it compared and analyzed the results focused on normalization and tile size. For comparison of the results according to the normalization, tile and batch size, a grayscale image and grayscale imagery converted to Z-score and Min-Max normalization methods were used. And the tile size isincreased at a specific interval while the batch size is allowed the memory size to be used as much as possible. As a result, IoU was 0.26 ~ 0.4 higher than that of Z-score normalized imagery than other imagery. Also, it wasfound that the difference to 0.09 depending on the tile and batch size. The results were different according to the normalization, tile and batch. Therefore, this experiment found that these factors should have a suitable decision process.

• International Journal of Computer Science & Network Security
• /
• v.21 no.8
• /
• pp.65-70
• /
• 2021

Waste accumulation is becoming a significant challenge in most urban areas and if it continues unchecked, is poised to have severe repercussions on our environment and health. The massive industrialisation in our cities has been followed by a commensurate waste creation that has become a bottleneck for even waste management systems. While recycling is a viable solution for waste management, it can be daunting to classify waste material for recycling accurately. In this study, transfer learning models were proposed to automatically classify wastes based on six materials (cardboard, glass, metal, paper, plastic, and trash). The tested pre-trained models were ResNet50, VGG16, InceptionV3, and Xception. Data augmentation was done using a Generative Adversarial Network (GAN) with various image generation percentages. It was found that models based on Xception and VGG16 were more robust. In contrast, models based on ResNet50 and InceptionV3 were sensitive to the added machine-generated images as the accuracy degrades significantly compared to training with no artificial data.

• Journal of Korea Multimedia Society
• /
• v.20 no.8
• /
• pp.1166-1174
• /
• 2017

In general, the detection of the vehicle license plate is a previous step of license plate recognition and has been actively studied for several decades. In this paper, we propose an algorithm to detect a license plate area of a moving vehicle from a video captured by a fixed camera installed on the road using the Convolution Neural Network (CNN) technology. First, license plate images and non-license plate images are applied to a previously learned CNN model (AlexNet) to extract and classify features. Then, after detecting the moving vehicle in the video, CNN detects the license plate area by comparing the features of the license plate region with the features of the license plate area. Experimental result shows relatively good performance in various environments such as incomplete lighting, noise due to rain, and low resolution. In addition, to protect personal information this proposed system can also be used independently to detect the license plate area and hide that area to secure the public's personal information.

• Advances in nano research
• /
• v.12 no.5
• /
• pp.489-499
• /
• 2022

Nanofluids have recently triggered a substantial scientific interest as cooling media. However, their stability is challenging for successful engagement in industrial applications. Different factors, including temperature, nanoparticles and base fluids characteristics, pH, ultrasonic power and frequency, agitation time, and surfactant type and concentration, determine the nanofluid stability regime. Indeed, it is often too complicated and even impossible to accurately find the conditions resulting in a stabilized nanofluid. Furthermore, there are no empirical, semi-empirical, and even intelligent scenarios for anticipating the stability of nanofluids. Therefore, this study introduces a straightforward and reliable intelligent classifier for discriminating among the stability regimes of alumina-water nanofluids based on the Zeta potential margins. In this regard, various intelligent classifiers (i.e., deep learning and multilayer perceptron neural network, decision tree, GoogleNet, and multi-output least squares support vector regression) have been designed, and their classification accuracy was compared. This comparison approved that the multilayer perceptron neural network (MLPNN) with the SoftMax activation function trained by the Bayesian regularization algorithm is the best classifier for the considered task. This intelligent classifier accurately detects the stability regimes of more than 90% of 345 different nanofluid samples. The overall classification accuracy and misclassification percent of 90.1% and 9.9% have been achieved by this model. This research is the first try toward anticipting the stability of water-alumin nanofluids from some easily measured independent variables.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.15-17
• /
• 2021

Handwriting recognition research is mainly focused on deep learning techniques and has achieved a great performance in the last few years. Especially, handwritten Thai digit recognition has been an important research area including generic digital numerical information, such as Thai official government documents and receipts. However, it becomes also a challenging task for a long time. For resolving the unavailability of a large Thai digit dataset, this paper constructs our dataset and learns them with some variants of the CNN model; Decision tree, K-nearest neighbors, Alexnet, LaNet-5, and VGG (11,13,16,19). The experimental results using the accuracy metric show the maximum accuracy of 98.29% when using VGG 13 with batch normalization.

• Nuclear Engineering and Technology
• /
• v.53 no.4
• /
• pp.1181-1188
• /
• 2021

When abnormal events occur in a nuclear power plant, operators must conduct appropriate abnormal operating procedures. It is burdensome though for operators to choose the appropriate procedure considering the numerous main plant parameters and hundreds of alarms that should be judged in a short time. Recently, various research has applied deep-learning algorithms to support this problem by classifying each abnormal condition with high accuracy. Most of these models are trained with simulator data because of a lack of plant data for abnormal states, and as such, developed models may not have tolerance for plant data in actual situations. In this study, two approaches are investigated for a deep-learning model trained with simulator data to overcome the performance degradation caused by noise in actual plant data. First, a preprocessing method using several filters was employed to smooth the test data noise, and second, a data augmentation method was applied to increase the acceptability of the untrained data. Results of this study confirm that the combination of these two approaches can enable high model performance even in the presence of noisy data as in real plants.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.6
• /
• pp.1818-1832
• /
• 2022

Violence in the Internet era poses a new challenge to the current counter-riot work, and according to research and analysis, most of the violent incidents occurring are related to the dissemination of violence images. The use of the popular deep learning neural network to automatically analyze the massive amount of images on the Internet has become one of the important tools in the current counter-violence work. This paper focuses on the use of transfer learning techniques and the introduction of an attention mechanism to the residual network (ResNet) model for the classification and identification of violence images. Firstly, the feature elements of the violence images are identified and a targeted dataset is constructed; secondly, due to the small number of positive samples of violence images, pre-training and attention mechanisms are introduced to suggest improvements to the traditional residual network; finally, the improved model is trained and tested on the constructed dedicated dataset. The research results show that the improved network model can quickly and accurately identify violence images with an average accuracy rate of 92.20%, thus effectively reducing the cost of manual identification and providing decision support for combating rebel organization activities.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3991-4007
• /
• 2022

In the public healthcare, a computational system that can automatically and efficiently detect and classify falls from a video sequence has significant potential. With the advancement of deep learning, which can extract temporal and spatial information, has become more widespread. However, traditional 3D CNNs that usually adopt shallow networks cannot obtain higher recognition accuracy than deeper networks. Additionally, some experiences of neural network show that the problem of gradient explosions occurs with increasing the network layers. As a result, an enhanced three-dimensional ResNet-based method for fall detection (3D-ERes-FD) is proposed to directly extract spatio-temporal features to address these issues. In our method, a 50-layer 3D residual network is used to deepen the network for improving fall recognition accuracy. Furthermore, enhanced residual units with four convolutional layers are developed to efficiently reduce the number of parameters and increase the depth of the network. According to the experimental results, the proposed method outperformed several state-of-the-art methods.