• Convergence Security Journal
• /
• v.21 no.2
• /
• pp.57-66
• /
• 2021

Deep neural networks (DNNs) provide excellent performance for image, speech, and pattern recognition. However, DNNs sometimes misrecognize certain adversarial examples. An adversarial example is a sample that adds optimized noise to the original data, which makes the DNN erroneously misclassified, although there is nothing wrong with the human eye. Therefore studies on defense against adversarial example attacks are required. In this paper, we have experimentally analyzed the success rate of detection for adversarial examples by adjusting various parameters. The performance of the ensemble defense method was analyzed using fast gradient sign method, DeepFool method, Carlini & Wanger method, which are adversarial example attack methods. Moreover, we used MNIST as experimental data and Tensorflow as a machine learning library. As an experimental method, we carried out performance analysis based on three adversarial example attack methods, threshold, number of models, and random noise. As a result, when there were 7 models and a threshold of 1, the detection rate for adversarial example is 98.3%, and the accuracy of 99.2% of the original sample is maintained.

• Journal of the Korean Society of Radiology
• /
• v.13 no.2
• /
• pp.209-216
• /
• 2019

The purpose of this study was to suggest the optimum ambient illumination level for proper visualization in image inspection and reading on CRT and LCD monitors used for ultrasound and reading. The evaluators were divided into 4 groups: 20 (Ultra-sonographer: 20 groups (4 groups: ultra-sonographer, 1-5 years, 5 ultra-sonographers, 6 to 10 years, 5 ultra-sonographers, 11 to 15 years, The subjects were 32 questions. The evaluation method was image evaluation of ultrasonic soft copy images for 30 seconds per 10, 25, 100Lux ambient illumination. The evaluation results were evaluated as 6 points (Normal = Definitely no lesion), 2 points = possibly not a lesion, 3 points = probably not a lesion, 4 points = possibly a lesion, 5 points = probably a lesion, 6 points = Definitely a lesion). In this study, the results of ROC analysis according to ambient light illumination reading softcopy images used for lesion detection of all ultrasound images showed the highest sensitivity, specificity, and AUC results at 10Lux. It was found that optimal use of 10Lux for ambient light illumination would provide optimal detection of lesions in ultrasound soft copy images. Based on the future research data, it will be presented as basic data for designing ambient light brightness of ultrasound imaging laboratory and reading room.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.391-401
• /
• 2022

As deep learning-based object detection and recognition research have been developed recently, the scope of application to industry and real life is expanding. But deep learning-based systems in the construction system are still much less studied. Calculating materials in the construction system is still manual, so it is a reality that transactions of wrong volumn calculation are generated due to a lot of time required and difficulty in accurate accumulation. A fast and accurate automatic drawing recognition system is required to solve this problem. Therefore, we propose an AI-based automatic drawing recognition accumulation system that detects and recognizes steel materials in construction drawings. To accurately detect steel materials in construction drawings, we propose data augmentation techniques and spatial attention modules for improving small object detection performance based on YOLOv4. The detected steel material area is recognized by text, and the number of steel materials is integrated based on the predicted characters. Experimental results show that the proposed method increases the accuracy and precision by 1.8% and 16%, respectively, compared with the conventional YOLOv4. As for the proposed method, Precision performance was 0.938. The recall was 1. Average Precision AP_0.5 was 99.4% and AP_0.5:0.95 was 67%. Accuracy for character recognition obtained 99.9.% by configuring and learning a suitable dataset that contains fonts used in construction drawings compared to the 75.6% using the existing dataset. The average time required per image was 0.013 seconds in the detection, 0.65 seconds in character recognition, and 0.16 seconds in the accumulation, resulting in 0.84 seconds.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.2
• /
• pp.71-82
• /
• 2022

In order to replace the sampling tensile test of products produced in the tab welding process, which is one of the automotive battery manufacturing processes, vision inspectors are currently being developed and used. However, the vision inspection has the problem of inspection position error and the cost of improving it. In order to solve these problems, there are recent cases of applying deep learning technology. As one such case, this paper tries to examine the usefulness of applying Faster R-CNN, one of the deep learning technologies, to existing product inspection. The images acquired through the existing vision inspection machine are used as training data and trained using the Faster R-CNN ResNet101 V1 1024x1024 model. The results of the conventional vision test and Faster R-CNN test are compared and analyzed based on the test standards of 0% non-detection and 10% over-detection. The non-detection rate is 34.5% in the conventional vision test and 0% in the Faster R-CNN test. The over-detection rate is 100% in the conventional vision test and 6.9% in Faster R-CNN. From these results, it is confirmed that deep learning technology is very useful for detecting welding error of lead tabs in automobile batteries.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.5
• /
• pp.667-674
• /
• 2023

In the event of a disaster occurring within a building, the prompt and efficient evacuation and rescue of occupants within the building becomes the foremost priority to minimize casualties. For the purpose of such rescue operations, it is essential to ascertain the distribution of individuals within the building. Nevertheless, there is a primary dependence on accounts provided by pertinent individuals like building proprietors or security staff, alongside fundamental data encompassing floor dimensions and maximum capacity. Consequently, accurate determination of the number of occupants within the building holds paramount significance in reducing uncertainties at the site and facilitating effective rescue activities during the golden hour. This research introduces a methodology employing computer vision algorithms to count the number of occupants within distinct building locations based on images captured by installed multiple CCTV cameras. The counting methodology consists of three stages: (1) establishing virtual Lines of Interest (LOI) for each camera to construct a multi-camera network environment, (2) detecting and tracking people within the monitoring area using deep learning, and (3) aggregating counts across the multi-camera network. The proposed methodology was validated through experiments conducted in a five-story building with the average accurary of 89.9% and the average MAE of 0.178 and RMSE of 0.339, and the advantages of using multiple cameras for occupant counting were explained. This paper showed the potential of the proposed methodology for more effective and timely disaster management through common surveillance systems by providing prompt occupancy information.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.1
• /
• pp.105-122
• /
• 2022

According to the statistics about the fatal crashes that have occurred on the expressways for the last 5 years, those who died on the shoulders of the road has been as 3 times high as the others who died on the expressways. It suggests that the crashes on the shoulders of the road should be fatal, and that it would be important to prevent the traffic crashes by cracking down on the vehicles intruding the shoulders of the road. Therefore, this study proposed a method to detect a vehicle that violates the shoulder lane by using the Faster R-CNN. The vehicle was detected based on the Faster R-CNN, and an additional reading module was configured to determine whether there was a shoulder violation. For experiments and evaluations, GTAV, a simulation game that can reproduce situations similar to the real world, was used. 1,800 images of training data and 800 evaluation data were processed and generated, and the performance according to the change of the threshold value was measured in ZFNet and VGG16. As a result, the detection rate of ZFNet was 99.2% based on Threshold 0.8 and VGG16 93.9% based on Threshold 0.7, and the average detection speed for each model was 0.0468 seconds for ZFNet and 0.16 seconds for VGG16, so the detection rate of ZFNet was about 7% higher. The speed was also confirmed to be about 3.4 times faster. These results show that even in a relatively uncomplicated network, it is possible to detect a vehicle that violates the shoulder lane at a high speed without pre-processing the input image. It suggests that this algorithm can be used to detect violations of designated lanes if sufficient training datasets based on actual video data are obtained.

• Journal of Internet Computing and Services
• /
• v.24 no.6
• /
• pp.119-125
• /
• 2023

Through the Ukraine-Russia war, the military importance of drones is being reassessed, and North Korea has completed actual verification through a drone provocation towards South Korea at 2022. Furthermore, North Korea is actively integrating artificial intelligence (AI) technology into drones, highlighting the increasing threat posed by drones. In response, the Republic of Korea military has established Drone Operations Command(DOC) and implemented various drone defense systems. However, there is a concern that the efforts to enhance capabilities are disproportionately focused on striking systems, making it challenging to effectively counter swarm drone attacks. Particularly, Air Force bases located adjacent to urban areas face significant limitations in the use of traditional air defense weapons due to concerns about civilian casualties. Therefore, this study proposes a new passive air defense method that aims at disrupting the object detection capabilities of AI models to enhance the survivability of friendly aircraft against the threat posed by AI based swarm drones. Using laser-based adversarial examples, the study seeks to degrade the recognition accuracy of object recognition AI installed on enemy drones. Experimental results using synthetic images and precision-reduced models confirmed that the proposed method decreased the recognition accuracy of object recognition AI, which was initially approximately 95%, to around 0-15% after the application of the proposed method, thereby validating the effectiveness of the proposed method.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.27 no.1
• /
• pp.115-127
• /
• 2024

This research aimed to construct models with various structures based on the Transformer module and to perform land cover classification, thereby examining the applicability of the Transformer module. For the classification of land cover, the Unet model, which has a CNN structure, was selected as the base model, and a total of four deep learning models were constructed by combining both the encoder and decoder parts with the Transformer module. During the training process of the deep learning models, the training was repeated 10 times under the same conditions to evaluate the generalization performance. The evaluation of the classification accuracy of the deep learning models showed that the Model D, which utilized the Transformer module in both the encoder and decoder structures, achieved the highest overall accuracy with an average of approximately 89.4% and a Kappa coefficient average of about 73.2%. In terms of training time, models based on CNN were the most efficient. however, the use of Transformer-based models resulted in an average improvement of 0.5% in classification accuracy based on the Kappa coefficient. It is considered necessary to refine the model by considering various variables such as adjusting hyperparameters and image patch sizes during the integration process with CNN models. A common issue identified in all models during the land cover classification process was the difficulty in detecting small-scale objects. To improve this misclassification phenomenon, it is deemed necessary to explore the use of high-resolution input data and integrate multidimensional data that includes terrain and texture information.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1413-1425
• /
• 2023

The increasing frequency of wildfires due to climate change is causing extreme loss of life and property. They cause loss of vegetation and affect ecosystem changes depending on their intensity and occurrence. Ecosystem changes, in turn, affect wildfire occurrence, causing secondary damage. Thus, accurate estimation of the areas affected by wildfires is fundamental. Satellite remote sensing is used for forest fire detection because it can rapidly acquire topographic and meteorological information about the affected area after forest fires. In addition, deep learning algorithms such as convolutional neural networks (CNN) and transformer models show high performance for more accurate monitoring of fire-burnt regions. To date, the application of deep learning models has been limited, and there is a scarcity of reports providing quantitative performance evaluations for practical field utilization. Hence, this study emphasizes a comparative analysis, exploring performance enhancements achieved through both model selection and data design. This study examined deep learning models for detecting wildfire-damaged areas using Landsat 8 satellite images in California. Also, we conducted a comprehensive comparison and analysis of the detection performance of multiple models, such as U-Net and High-Resolution Network-Object Contextual Representation (HRNet-OCR). Wildfire-related spectral indices such as normalized difference vegetation index (NDVI) and normalized burn ratio (NBR) were used as input channels for the deep learning models to reflect the degree of vegetation cover and surface moisture content. As a result, the mean intersection over union (mIoU) was 0.831 for U-Net and 0.848 for HRNet-OCR, showing high segmentation performance. The inclusion of spectral indices alongside the base wavelength bands resulted in increased metric values for all combinations, affirming that the augmentation of input data with spectral indices contributes to the refinement of pixels. This study can be applied to other satellite images to build a recovery strategy for fire-burnt areas.

• Journal of the Korean Society of Radiology
• /
• v.18 no.3
• /
• pp.187-201
• /
• 2024

Osteoporosis is a major health issue globally, often remaining undetected until a fracture occurs. To facilitate early detection, deep learning (DL) models were developed to classify osteoporosis using abdominal computed tomography (CT) scans. This study was conducted using retrospectively collected data from 3,012 contrast-enhanced abdominal CT scans. The DL models developed in this study were constructed for using image data, demographic/clinical information, and multi-modality data, respectively. Patients were categorized into the normal, osteopenia, and osteoporosis groups based on their T-scores, obtained from dual-energy X-ray absorptiometry, into normal, osteopenia, and osteoporosis groups. The models showed high accuracy and effectiveness, with the combined data model performing the best, achieving an area under the receiver operating characteristic curve of 0.94 and an accuracy of 0.80. The image-based model also performed well, while the demographic data model had lower accuracy and effectiveness. In addition, the DL model was interpreted by gradient-weighted class activation mapping (Grad-CAM) to highlight clinically relevant features in the images, revealing the femoral neck as a common site for fractures. The study shows that DL can accurately identify osteoporosis stages from clinical data, indicating the potential of abdominal CT scans in early osteoporosis detection and reducing fracture risks with prompt treatment.