• The Journal of Korea Robotics Society
• /
• v.14 no.2
• /
• pp.139-149
• /
• 2019

In this paper, we present auto-annotation tool and synthetic dataset using 3D CAD model for deep learning based object detection. To be used as training data for deep learning methods, class, segmentation, bounding-box, contour, and pose annotations of the object are needed. We propose an automated annotation tool and synthetic image generation. Our resulting synthetic dataset reflects occlusion between objects and applicable for both underwater and in-air environments. To verify our synthetic dataset, we use MASK R-CNN as a state-of-the-art method among object detection model using deep learning. For experiment, we make the experimental environment reflecting the actual underwater environment. We show that object detection model trained via our dataset show significantly accurate results and robustness for the underwater environment. Lastly, we verify that our synthetic dataset is suitable for deep learning model for the underwater environments.

• Journal of KIISE:Information Networking
• /
• v.37 no.4
• /
• pp.255-262
• /
• 2010

Recently, automated signature generation systems(ASGSs) have been developed in order to cope with zero-day attacks with malicious codes exploiting vulnerabilities which are not yet publically noticed. To enhance the usefulness of the signatures generated by (ASGSs) it is essential to identify signatures only with the high accuracy of intrusion detection among a number of generated signatures and to provide them to target security systems in a timely manner. This automated signature exchange, distribution, and update operations have to be performed in a secure and universal manner beyond the border of network administrations, and also should be able to eliminate the noise in a signature set which causes performance degradation of the security systems. In this paper, we present a system architecture to support the identification of high quality signatures and to share them among security systems through a scheme which can evaluate the detection accuracy of individual signatures, and also propose a set of algorithms dealing with exchanging, distributing and updating signatures. Though the experiment on a test-bed, we have confirmed that the high quality signatures are automatically saved at the level that the noise rate of a signature set is reduced. The system architecture and the algorithm proposed in the paper can be adopted to a automated signature sharing framework.

• Safety and Health at Work
• /
• v.10 no.4
• /
• pp.461-469
• /
• 2019

Background: Collisions involving workers and mobile machines continue to be a major concern in underground coal mines. Over the last 30 years, these collisions have resulted in numerous injuries and fatalities. Recently, the Mine Safety and Health Administration (MSHA) proposed a rule that would require mines to equip mobile machines with proximity detection systems (PDSs) (systems designed for automated collision avoidance). Even though this regulation has not been enacted, some mines have installed PDSs on their scoops and hauling machines. However, early implementation of PDSs has introduced a variety of safety concerns. Past findings show that workers' trust can affect technology integration and influence unsafe use of automated technologies. Methods: Using a mixed-methods approach, the present study explores the effect that factors such as mine of employment, age, experience, and system type have on workers' trust in PDSs for mobile machines. The study also explores how workers are trained on PDSs and how this training influences trust. Results: The study resulted in three major findings. First, the mine of employment had a significant influence on workers' trust in mobile PDSs. Second, hands-on and classroom training was the most common types of training. Finally, over 70% of workers are trained on the system by the mine compared with 36% trained by the system manufacturer. Conclusion: The influence of workers' mine of employment on trust in PDSs may indicate that practitioners and researchers may need to give the organizational and physical characteristics of each mine careful consideration to ensure safe integration of automated systems.

• Applied Microscopy
• /
• v.51
• /
• pp.4.1-4.12
• /
• 2021

Fluorescence in situ hybridization (FISH) is a technique to visualize specific DNA/RNA sequences within the cell nuclei and provide the presence, location and structural integrity of genes on chromosomes. A confocal Whole Slide Imaging (WSI) scanner technology has superior depth resolution compared to wide-field fluorescence imaging. Confocal WSI has the ability to perform serial optical sections with specimen imaging, which is critical for 3D tissue reconstruction for volumetric spatial analysis. The standard clinical manual scoring for FISH is labor-intensive, time-consuming and subjective. Application of multi-gene FISH analysis alongside 3D imaging, significantly increase the level of complexity required for an accurate 3D analysis. Therefore, the purpose of this study is to establish automated 3D FISH scoring for z-stack images from confocal WSI scanner. The algorithm and the application we developed, SHIMARIS PAFQ, successfully employs 3D calculations for clear individual cell nuclei segmentation, gene signals detection and distribution of break-apart probes signal patterns, including standard break-apart, and variant patterns due to truncation, and deletion, etc. The analysis was accurate and precise when compared with ground truth clinical manual counting and scoring reported in ten lymphoma and solid tumors cases. The algorithm and the application we developed, SHIMARIS PAFQ, is objective and more efficient than the conventional procedure. It enables the automated counting of more nuclei, precisely detecting additional abnormal signal variations in nuclei patterns and analyzes gigabyte multi-layer stacking imaging data of tissue samples from patients. Currently, we are developing a deep learning algorithm for automated tumor area detection to be integrated with SHIMARIS PAFQ.

• Journal of Microbiology and Biotechnology
• /
• v.15 no.3
• /
• pp.595-602
• /
• 2005

A one-step real-time quantitative RT-PCR assay in combination with automated RNA extraction was evaluated for routine testing of HCV RNA in the laboratory. Specific primers and probes were developed to detect 302 bp on 5'-UTR of HCV RNA. The assay was able to quantitate a dynamic linear range of $10^7-10^1$ HCV RNA copies/reaction ($R^2=0.997$). The synthetic HCV RNA standard of $1.84{\pm}0.1\;(mean{\pm}SD)$ copies developed in this study corresponded to 1 international unit (IU) of WHO International Standard for HCV RNA (96/790 I). The detection limit of the assay was 3 RNA copies/reaction (81 IU/ml) in plasma samples. The assay was comparable to the Amplicor HCV Monitor (Monitor) assay with correlation coefficient r=0.985, but was more sensitive than the Monitor assay. The assay could be completed within 3 h from RNA extraction to detection and data analysis for up to 32 samples. It allowed rapid RNA extraction, detection, and quantitation of HCV RNA in plasma samples. The method provided sufficient sensitivity and reproducibility and proved to be fast and labor-saving, so that it was suitable for high throughput HCV RNA test.

• Journal of the Society of Naval Architects of Korea
• /
• v.59 no.4
• /
• pp.192-199
• /
• 2022

With the advent of autonomous ships, it is emerging as one of the very important issues not only to operate with a minimum crew or unmanned ships, but also to secure the safety of ships to prevent marine accidents. On-site inspection of the hull is mainly performed by the inspector's visual inspection, and video information is recorded using a small camera if necessary. However, due to the shortage of inspection personnel, time and space constraints, and the pandemic situation, the necessity of introducing an automated inspection system using artificial intelligence and remote inspection is becoming more important. Furthermore, research on hardware and software that enables the automated inspection system to operate normally even under the harsh environmental conditions of a ship is absolutely necessary. For automated inspection systems, it is important to review artificial intelligence technologies and equipment that can perform a variety of hull failure detection and classification. To address this, it is important to classify the hull failure. Based on various guidelines and expert opinions, we divided them into 6 types(Crack, Corrosion, Pitting, Deformation, Indent, Others). It was decided to apply object detection technology to cracks of hull failure. After that, YOLOv5 was decided as an artificial intelligence model suitable for survey and a common hull crack dataset was trained. Based on the performance results, it aims to present the possibility of applying artificial intelligence in the field by determining and testing the equipment required for survey.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_2
• /
• pp.975-988
• /
• 2020

Change detection is the process of identifying changes by observing the multi-temporal images at different times, and it is an important technique in remote sensing using satellite images. Among the change detection methods, the unsupervised change detection technique has the advantage of extracting rapidly the change area as a binary image. However, it is difficult to understand the changing pattern of land cover in binary images. This study used grid points generated from seamless digital map to evaluate the satellite image change detection results. The land cover change results were extracted using multi-temporal KOMPSAT-3A (K3A) data taken by Gimje Free Trade Zone and change detection algorithm used Spectral Angle Mapper (SAM). Change detection results were presented as binary images using the methods Otsu, Kittler, Kapur, and Tsai among the automated threshold selection algorithms. To consider the seasonal change of vegetation in the change detection process, we used the threshold of Differenced Normalized Difference Vegetation Index (dNDVI) through the probability density function. The experimental results showed the accuracy of the Otsu and Kapur was the highest at 58.16%, and the accuracy improved to 85.47% when the seasonal effects were removed through dNDVI. The algorithm generated based on this research is considered to be an effective method for accuracy assessment and identifying changes pattern when applied to unsupervised change detection.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.959-979
• /
• 2024

Rice pest identification is essential in modern agriculture for the health of rice crops. As global rice consumption rises, yields and quality must be maintained. Various methodologies were employed to identify pests, encompassing sensor-based technologies, deep learning, and remote sensing models. Visual inspection by professionals and farmers remains essential, but integrating technology such as satellites, IoT-based sensors, and drones enhances efficiency and accuracy. A computer vision system processes images to detect pests automatically. It gives real-time data for proactive and targeted pest management. With this motive in mind, this research provides a novel farmland fertility algorithm with a deep learning-based automated rice pest detection and classification (FFADL-ARPDC) technique. The FFADL-ARPDC approach classifies rice pests from rice plant images. Before processing, FFADL-ARPDC removes noise and enhances contrast using bilateral filtering (BF). Additionally, rice crop images are processed using the NASNetLarge deep learning architecture to extract image features. The FFA is used for hyperparameter tweaking to optimise the model performance of the NASNetLarge, which aids in enhancing classification performance. Using an Elman recurrent neural network (ERNN), the model accurately categorises 14 types of pests. The FFADL-ARPDC approach is thoroughly evaluated using a benchmark dataset available in the public repository. With an accuracy of 97.58, the FFADL-ARPDC model exceeds existing pest detection methods.

• Geomechanics and Engineering
• /
• v.38 no.1
• /
• pp.29-44
• /
• 2024

This research investigates the effectiveness of data augmentation techniques in the automated analysis of B-scan images from ground-penetrating radar (GPR) using deep learning. In spite of the growing interest in automating GPR data analysis and advancements in deep learning for image classification and object detection, many deep learning-based GPR data analysis studies have been limited by the availability of large, diverse GPR datasets. Data augmentation techniques are widely used in deep learning to improve model performance. In this study, we applied four data augmentation techniques (geometric transformation, color-space transformation, noise injection, and applying kernel filter) to the GPR datasets obtained from a testbed. A deep learning model for GPR data analysis was developed using three models (Faster R-CNN ResNet, SSD ResNet, and EfficientDet) based on transfer learning. It was found that data augmentation significantly enhances model performance across all cases, with the mAP and AR for the Faster R-CNN ResNet model increasing by approximately 4%, achieving a maximum mAP (Intersection over Union = 0.5:1.0) of 87.5% and maximum AR of 90.5%. These results highlight the importance of data augmentation in improving the robustness and accuracy of deep learning models for GPR B-scan analysis. The enhanced detection capabilities achieved through these techniques contribute to more reliable subsurface investigations in geotechnical engineering.

• Annals of Laboratory Medicine
• /
• v.38 no.6
• /
• pp.578-584
• /
• 2018

Background: Accurate, rapid, and cost-effective screening tests for hepatitis B virus (HBV) and hepatitis C virus (HCV) infection may be useful in laboratories that cannot afford automated chemiluminescent immunoassays (CLIAs). We evaluated the diagnostic performance of a novel rapid automated fluorescent lateral flow immunoassay (LFIA). Methods: A fluorescent LFIA using a small bench-top fluorescence reader, Automated Fluorescent Immunoassay System (AFIAS; Boditech Med Inc., Chuncheon, Korea), was developed for qualitative detection of hepatitis B surface antigen (HBsAg), antibody to HBsAg (anti-HBs), and antibody to HCV (anti-HCV) within 20 minutes. We compared the diagnostic performance of AFIAS with that of automated CLIAs-Elecsys (Roche Diagnostics GmbH, Penzberg, Germany) and ARCHITECT (Abbott Laboratories, Abbott Park, IL, USA)-using 20 seroconversion panels and 3,500 clinical serum samples. Results: Evaluation with the seroconversion panels demonstrated that AFIAS had adequate sensitivity for HBsAg and anti-HCV detection. From the clinical samples, AFIAS sensitivity and specificity were 99.8% and 99.3% for the HBsAg test, 100.0% and 100.0% for the anti-HBs test, and 98.8% and 99.1% for the anti-HCV test, respectively. Its agreement rates with the Elecsys HBsAg, anti-HBs, and anti-HCV detection assays were 99.4%, 100.0%, and 99.0%, respectively. AFIAS detected all samples with HBsAg genotypes A-F and H and anti-HCV genotypes 1, 1a, 1b, 2a, 2b, 4, and 6. Cross-reactivity with other infections was not observed. Conclusions: The AFIAS HBsAg, anti-HBs, and anti-HCV tests demonstrated diagnostic performance equivalent to current automated CLIAs. AFIAS could be used for a large-scale HBV or HCV screening in low-resource laboratories or low-to middle-income areas.