• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.5
• /
• pp.443-461
• /
• 2022

Target Detection in synthetic aperture radar(SAR) image is critical for military and national defense. In this paper, we propose YOLOv4-Attention architecture which adds attention modules to YOLOv4 backbone architecture to complement the feature extraction ability for SAR target detection with high accuracy. For training and testing our framework, we present new SAR embedding datasets based on MSTAR SAR public datasets which are about poor environments for target detection such as various clutter, crowded objects, various object size, close to buildings, and weakness of signal-to-clutter ratio. Experiments show that our Attention YOLOv4 architecture outperforms original YOLOv4 architecture in SAR image target detection tasks in poor environments for target detection.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.12
• /
• pp.1880-1889
• /
• 2022

The online portal platform provides online news with online comments, but the anonymity of comments causes incivility, and online comments are considered social problems. While there are many foreign language-based incivility detection studies, in-depth research is not being conducted in Korea since there has not been implemented Korean language dataset which is labeled detailed criteria of incivility. In this study, the incivility notation of comments was conducted in a total of 13 items, uncivil words were summarized. Furthermore, Attention algorithm was applied to each comment and summary to extract embedding vectors. 2-d CNN followed at the end to detect incivility in given data. As a result, we showed that the proposed algorithm is useful for anti-citizen detection such as name-calling and offensive tones. This study is expected to contribute to the formation of a healthy online comment culture by detecting uncivil comments which hinder democratic discourse.

• 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 radiological science and technology
• /
• v.47 no.1
• /
• pp.29-37
• /
• 2024

This study aims to evaluate the performance of the U-Net based learning model that may vary depending on the histogram equalization algorithm. The subject of the experiment were 17 radiology students of this college, and 1,727 data sets in which the region of interest was set in the thyroid after acquiring ultrasound image data were used. The training set consisted of 1,383 images, the validation set consisted of 172 and the test data set consisted of 172. The equalization algorithm was divided into Histogram Equalization(HE) and Contrast Limited Adaptive Histogram Equalization(CLAHE), and according to the clip limit, it was divided into CLAHE8-1, CLAHE8-2. CLAHE8-3. Deep Learning was learned through size control, histogram equalization, Z-score normalization, and data augmentation. As a result of the experiment, the Attention U-Net showed the highest performance from CLAHE8-2 to 0.8355, and the U-Net and BSU-Net showed the highest performance from CLAHE8-3 to 0.8303 and 0.8277. In the case of mIoU, the Attention U-Net was 0.7175 in CLAHE8-2, the U-Net was 0.7098 and the BSU-Net was 0.7060 in CLAHE8-3. This study attempted to confirm the effects of U-Net, Attention U-Net, and BSU-Net models when histogram equalization is performed on ultrasound images. The increase in Clip Limit can be expected to increase the ROI match with the prediction mask by clarifying the boundaries, which affects the improvement of the contrast of the thyroid area in deep learning model learning, and consequently affects the performance improvement.

• The Journal of Korean Association of Computer Education
• /
• v.9 no.3
• /
• pp.109-119
• /
• 2006

Algorithm is a fundamental concept for all related research areas in computer science. Though many researches have paid attention to computer algorithm in solving applied problems, few researches have been conducted on how to effectively instruct the computer algorithm concept. This paper proposed the instructional method for the computer algorithm concept by using mathematics problems of the fourth grade, elementary school. We have applied our the instructional methodology to classroom, and empirically tested the effectiveness of our methodology. The results show that the effectiveness of instructional method, compared to the traditional instructional methodology.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2004.05a
• /
• pp.409-412
• /
• 2004

Today, meta-heuristic algorithms have been much attention by researcher because they have the power of solving combinational optimization problems efficiently. As the result, many variants of a meta-heuristic algorithm (e.g., simulated annealing) have been proposed for specific application domains. However, there are few efforts to classify them into a unified software framework, which is believed to provide the users with the reusability of the software, thereby significantly reducing the development time of algorithms. In this paper, we present an object-oriented framework to be used as a general tool for efficiently developing variants of simulated annealing algorithm. The interface classes in the framework achieve the modulization of the algorithm, and the users are allowed to specialize some of the classes appropriate for solving their problems. The core of the framework is Algorithm Configuration Pattern (ACP) which facilitates creating user-specific variants flexibly. Finally, we summarize our experiences and discuss future research topics.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.1-16
• /
• 2022

Despite recent breakthroughs in deep learning and computer vision fields, the pixel-wise identification of tiny objects in high-resolution images with complex disturbances remains challenging. This study proposes a modified U-net for tiny crack segmentation in real-world steel-box-girder bridges. The modified U-net adopts the common U-net framework and a novel Self-Attention-Self-Adaption (SASA) neuron as the fundamental computing element. The Self-Attention module applies softmax and gate operations to obtain the attention vector. It enables the neuron to focus on the most significant receptive fields when processing large-scale feature maps. The Self-Adaption module consists of a multiplayer perceptron subnet and achieves deeper feature extraction inside a single neuron. For data augmentation, a grid-based crack random elastic deformation (CRED) algorithm is designed to enrich the diversities and irregular shapes of distributed cracks. Grid-based uniform control nodes are first set on both input images and binary labels, random offsets are then employed on these control nodes, and bilinear interpolation is performed for the rest pixels. The proposed SASA neuron and CRED algorithm are simultaneously deployed to train the modified U-net. 200 raw images with a high resolution of 4928 × 3264 are collected, 160 for training and the rest 40 for the test. 512 × 512 patches are generated from the original images by a sliding window with an overlap of 256 as inputs. Results show that the average IoU between the recognized and ground-truth cracks reaches 0.409, which is 29.8% higher than the regular U-net. A five-fold cross-validation study is performed to verify that the proposed method is robust to different training and test images. Ablation experiments further demonstrate the effectiveness of the proposed SASA neuron and CRED algorithm. Promotions of the average IoU individually utilizing the SASA and CRED module add up to the final promotion of the full model, indicating that the SASA and CRED modules contribute to the different stages of model and data in the training process.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.273-275
• /
• 2022

The use of drugs by pregnant women poses a potential risk to the fetus. Therefore, it is essential to classify drugs that pregnant women should prohibit. However, the fetal toxicity of most drugs has not been identified. This takes a lot of time and cost. In silico approaches, such as virtual screening, can identify compounds that may present a high risk to the fetus for a wide range of compounds at the low cost and time. We collected class information of each drug from the hazard classification lists for prescribing drugs in pregnancy by the government of Korea and Australia. Using the structural and chemical features of each drug, various machine learning models were constructed to predict fetal toxicity of drugs. For all models, the quantitative performance evaluation was performed. Based on the attention algorithm, important molecular substructures of compounds were identified in the process of predicting the fetal toxicity of the drug by the proposed model. From the results, we confirmed that drugs with a high risk of fetal toxicity can be predicted for a wide range of compounds by machine learning. This study can be used as a pre-screening tool for fetal toxicity predictions, as it provides key molecular substructures associated with the fetal toxicity of compounds.

• Journal of Korean Society of Transportation
• /
• v.20 no.6
• /
• pp.99-113
• /
• 2002

The multi-class traffic assignment problem is the most typical one of the multi-solution traffic assignment problems and, recently formulation of the models and the solution algorithm have been received a great deal of attention. The useful solution algorithm, however, has not been proposed while formulation of the multi-class traffic assignment could be performed by adopting the variational inequality problem or the fixed point problem. In this research, we developed a hybrid solution algorithm which combines GA algorithm, diagonal algorithm and clustering algorithm for the multi-class traffic assignment formulated as a variational inequality Problem. GA algorithm and clustering algorithm are introduced for the wide area and small cost. We also performed an experiment with toy network(2 link) and tested the characteristics of the suggested algorithm.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.8
• /
• pp.1518-1527
• /
• 1994

An algorithm for BPSK demodulation of which channel is an electric distribution line is developed, and realized in this paper. To realize the BPSK demodulation by microprocessor, BPSK signal that is received through the distribution line must be converted to digital signal. A hardware which converts BPSK signal to digital one has been designed in this paper, and an algorithm for BPSK demoduation of which channel is distribution line has been also developed in algorithm for BPSK demoduation of which channel is distribution line has been also developed in this paper by paying the attention to the fact that a modulated point appears up and down according to the rising edge and falling edge of the modulated binary signal if the carrier frequency is even times to the modulated binary signal, and by paying the attention to the fact that the signal duration or modulated point is twice of the other point. The microprocessor demodulation system with the algorithm has been realized. The system proved to have 0.02%(or less) bit error rate in real BPSK demodulation.