• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.378-390
• /
• 2022

With the recent development of deep composite multiplication neural network learning, deep learning techniques applied to single-image super-resolution have shown good results, and the strong expression ability of deep networks has enabled complex nonlinear mapping between low-resolution and high-resolution images. However, there are limitations in applying it to real-time or low-power devices with increasing parameters and computational amounts due to excessive use of composite multiplication neural networks. This paper uses blocks that extract hierarchical characteristics little by little using information distillation and suggests the Recursive Distillation Super Resolution Network (RDSRN), a lightweight network that improves performance by making more accurate high frequency components through high frequency residual purification blocks. It was confirmed that the proposed network restores images of similar quality compared to RDN, restores images 3.5 times faster with about 32 times fewer parameters and about 10 times less computation, and produces 0.16 dB better performance with about 2.2 times less parameters and 1.8 times faster processing time than the existing lightweight network CARN.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.568-570
• /
• 2023

The problem of classifying of age, gender, and race images still poses challenges. Despite deep and machine learning strides, convolutional neural networks (CNNs) remain pivotal in addressing these issues. This paper introduces a novel CNN-based approach for accurate and efficient age, gender, and race classification. Leveraging CNNs with residual blocks, our method enhances learning while minimizing computational complexity. The model effectively captures low-level and high-level features, yielding improved classification accuracy. Evaluation of the diverse 'fair face' dataset shows our model achieving 56.3%, 94.6%, and 58.4% accuracy for age, gender, and race, respectively.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.5
• /
• pp.460-468
• /
• 2023

Developmental Dysplasia of the Hip (DDH) is a pathological condition commonly occurring during the growth phase of infants. It acts as one of the factors that can disrupt an infant's growth and trigger potential complications. Therefore, it is critically important to detect and treat this condition early. The traditional diagnostic methods for DDH involve palpation techniques and diagnosis methods based on the detection of keypoints in the hip joint using X-ray or ultrasound imaging. However, there exist limitations in objectivity and productivity during keypoint detection in the hip joint. This study proposes a deep learning model-based keypoint detection method using X-ray and ultrasound imaging and analyzes the performance of keypoint detection using various deep learning models. Additionally, the study introduces and evaluates various data augmentation techniques to compensate the lack of medical data. This research demonstrated the highest keypoint detection performance when applying the residual network 152 (ResNet152) model with simple & complex augmentation techniques, with average Object Keypoint Similarity (OKS) of approximately 95.33 % and 81.21 % in X-ray and ultrasound images, respectively. These results demonstrate that the application of deep learning models to ultrasound and X-ray images to detect the keypoints in the hip joint could enhance the objectivity and productivity in DDH diagnosis.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.10
• /
• pp.5179-5196
• /
• 2019

To explore an effective non-invasion medical imaging diagnostics approach for hepatocellular carcinoma (HCC), we propose a method based on adopting the multiple technologies with the multi-parametric data fusion, transfer learning, and multi-scale deep feature extraction. Firstly, to make full use of complementary and enhancing the contribution of different modalities viz. multi-parametric MRI images in the lesion diagnosis, we propose a data-level fusion strategy. Secondly, based on the fusion data as the input, the multi-scale residual neural network with SPP (Spatial Pyramid Pooling) is utilized for the discriminative feature representation learning. Thirdly, to mitigate the impact of the lack of training samples, we do the pre-training of the proposed multi-scale residual neural network model on the natural image dataset and the fine-tuning with the chosen multi-parametric MRI images as complementary data. The comparative experiment results on the dataset from the clinical cases show that our proposed approach by employing the multiple strategies achieves the highest accuracy of 0.847±0.023 in the classification problem on the HCC differentiation. In the problem of discriminating the HCC lesion from the non-tumor area, we achieve a good performance with accuracy, sensitivity, specificity and AUC (area under the ROC curve) being 0.981±0.002, 0.981±0.002, 0.991±0.007 and 0.999±0.0008, respectively.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.6
• /
• pp.670-677
• /
• 2019

As the presence of background noise in acoustic signal degrades the performance of speech or acoustic event recognition, it is still challenging to extract noise-robust acoustic features from noisy signal. In this paper, we propose a combined structure of Wasserstein Generative Adversarial Network (WGAN) and MultiTask AutoEncoder (MTAE) as deep learning architecture that integrates the strength of MTAE and WGAN respectively such that it estimates not only noise but also speech features from noisy acoustic source. The proposed MTAE-WGAN structure is used to estimate speech signal and the residual noise by employing a gradient penalty and a weight initialization method for Leaky Rectified Linear Unit (LReLU) and Parametric ReLU (PReLU). The proposed MTAE-WGAN structure with the adopted gradient penalty loss function enhances the speech features and subsequently achieve substantial Phoneme Error Rate (PER) improvements over the stand-alone Deep Denoising Autoencoder (DDAE), MTAE, Redundant Convolutional Encoder-Decoder (R-CED) and Recurrent MTAE (RMTAE) models for robust speech recognition.

• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.301-307
• /
• 2022

Energy consumption has grown alongside dramatic population increases. Statistics show that buildings in particular utilize a significant amount of energy, worldwide. Because of this, building energy prediction is crucial to best optimize utilities' energy plans and also create a predictive model for consumers. To improve energy prediction performance, this paper proposes a ResNet-LSTM model that combines residual networks (ResNets) and long short-term memory (LSTM) for energy consumption prediction. ResNets are utilized to extract complex and rich features, while LSTM has the ability to learn temporal correlation; the dense layer is used as a regression to forecast energy consumption. To make our model more robust, we employed Huber loss during the optimization process. Huber loss obtains high efficiency by handling minor errors quadratically. It also takes the absolute error for large errors to increase robustness. This makes our model less sensitive to outlier data. Our proposed system was trained on historical data to forecast energy consumption for different time series. To evaluate our proposed model, we compared our model's performance with several popular machine learning and deep learning methods such as linear regression, neural networks, decision tree, and convolutional neural networks, etc. The results show that our proposed model predicted energy consumption most accurately.

• Journal of Information Processing Systems
• /
• v.19 no.6
• /
• pp.791-802
• /
• 2023

The manual inspection of photovoltaic (PV) panels to meet the requirements of inspection work for large-scale PV power plants is challenging. We present a hot spot detection and positioning method to detect hot spots in batches and locate their latitudes and longitudes. First, a network based on the YOLOv3 architecture was utilized to identify hot spots. The innovation is to modify the RU_1 unit in the YOLOv3 model for hot spot detection in the far field of view and add a neural network residual unit for fusion. In addition, because of the misidentification problem in the infrared images of the solar PV panels, the DeepLab v3+ model was adopted to segment the PV panels to filter out the misidentification caused by bright spots on the ground. Finally, the latitude and longitude of the hot spot are calculated according to the geometric positioning method utilizing known information such as the drone's yaw angle, shooting height, and lens field-of-view. The experimental results indicate that the hot spot recognition rate accuracy is above 98%. When keeping the drone 25 m off the ground, the hot spot positioning error is at the decimeter level.

• Journal of Digital Policy
• /
• v.3 no.3
• /
• pp.9-14
• /
• 2024

In this paper, proposes a method using a multi block structure composed of residual blocks with adaptive weights to improve the quality of results in single image super resolution. In the process of generating super resolution images using deep learning, the most critical factor for enhancing quality is feature extraction and application. While extracting various features is essential for restoring fine details that have been lost due to low resolution, issues such as increased network depth and complexity pose challenges in practical implementation. Therefore, the feature extraction process was structured efficiently, and the application process was improved to enhance quality. To achieve this, a multi block structure was designed after the initial feature extraction, with nested residual blocks inside each block, where adaptive weights were applied. Additionally, for final high resolution reconstruction, a multi kernel image reconstruction process was employed, further improving the quality of the results. The performance of the proposed method was evaluated by calculating PSNR and SSIM values compared to the original image, and its superiority was demonstrated through comparisons with existing algorithms.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.12
• /
• pp.1604-1611
• /
• 2020

Light field image captured by a microlens array-based camera has many limitations in practical use due to its low spatial resolution and angular resolution. High spatial resolution images can be easily acquired with a single image super-resolution technique that has been studied a lot recently. But there is a problem in that high angular resolution images are distorted in the process of using disparity information inherent among images, and thus it is difficult to obtain a high-quality angular resolution image. In this paper, we propose light field angular super-resolution that extracts an initial feature map using an dilated convolutional neural network in order to effectively extract the view difference information inherent among images and generates target image using a residual neural network. The proposed network showed superior performance in PSNR and subjective image quality compared to existing angular super-resolution networks.

• Journal of Broadcast Engineering
• /
• v.25 no.2
• /
• pp.242-251
• /
• 2020

Recently, many deep convolutional neural networks for image super-resolution have been studied. Existing deep learning-based super-resolution algorithms are architecture that up-samples the resolution at the end of the network. The post-upsampling architecture has an inefficient structure at large scaling factor result of predicting a lot of information for mapping from low-resolution to high-resolution at once. In this paper, we propose a single image super-resolution using Channel Attention Residual Dense Block based on an iterative up-down sampling architecture. The proposed algorithm efficiently predicts the mapping relationship between low-resolution and high-resolution, and shows up to 0.14dB performance improvement and enhanced subjective image quality compared to the existing algorithm at large scaling factor result.