• Korean Journal of Food Science and Technology
• /
• v.53 no.5
• /
• pp.657-668
• /
• 2021

We prepared the growth and survival models of enterohemorrhagic Escherichia coli (EHEC) and Campylobacter jejuni in milk as a function of temperature and assessed the microbiological risks associated with the consumption of whole milk. EHEC and C. jejuni were not detected in whole milk (n=195) in the retail market. The minimum growth temperature of EHEC in milk was 7℃. The lag time of EHEC in whole milk was longer than that in skim milk. The survival ability of C. jejuni in milk was better at 4℃ than at 10℃. Lower delta values were observed in whole milk than in skim milk, indicating that C. jejuni survived better in skim milk. The probability of foodborne illness from whole milk consumption was 5.70×10^-5 for EHEC and 9.86×10^-9 for C. jejuni. Sensitivity analysis results show that the market temperature of EHEC and the dose-response model of C. jejuni are correlated with the probability of foodborne illness.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.9 no.3
• /
• pp.303-310
• /
• 2021

Cracks in bridges are important factors that indicate the condition of bridges and should be monitored periodically. However, a visual inspection conducted by a human expert has problems in cost, time, and reliability. Therefore, in recent years, researches to apply a deep learning model are started to be conducted. Deep learning requires sufficient data on the situations to be predicted, but bridge crack data is relatively difficult to obtain. In particular, it is difficult to collect a large amount of crack data in a specific situation because the shape of bridge cracks may vary depending on the bridge's design, location, and construction method. This study developed a crack detection model that generates and trains insufficient crack data through a Generative Adversarial Network. GAN successfully generated data statistically similar to the given crack data, and accordingly, crack detection was possible with about 3% higher accuracy when using the generated image than when the generated image was not used. This approach is expected to effectively improve the performance of the detection model as it is applied when crack detection on bridges is required, though there is not enough data, also when there is relatively little or much data f or one class.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.3
• /
• pp.166-172
• /
• 2022

In this study, we photograph driving obstacle objects such as crosswalks, side spheres, manholes, braille blocks, partial ramps, temporary safety barriers, stairs, and inclined curb that hinder or cause inconvenience to the movement of the vulnerable using electric mobility aids. We develop an optimal AI model that classifies photographed objects and automatically recognizes them, and implement an algorithm that can efficiently determine obstacles in front of electric mobility aids. In order to enable object detection to be AI learning with high probability, the labeling form is labeled as a polygon form when building a dataset. It was developed using a Mask R-CNN model in Detectron2 framework that can detect objects labeled in the form of polygons. Image acquisition was conducted by dividing it into two groups: the general public and the transportation weak, and image information obtained in two areas of the test bed was secured. As for the parameter setting of the Mask R-CNN learning result, it was confirmed that the model learned with IMAGES_PER_BATCH: 2, BASE_LEARNING_RATE 0.001, MAX_ITERATION: 10,000 showed the highest performance at 68.532, so that the user can quickly and accurately recognize driving risks and obstacles.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.27-35
• /
• 2023

In this paper, we propose a process of increasing productivity by applying a deep learning-based defect detection and classification system to the prepreg fiber manufacturing process, which is in high demand in the field of producing composite materials. In order to apply it to toe prepreg manufacturing equipment that requires a solution due to the occurrence of a large amount of defects in various conditions, the optimal environment was first established by selecting cameras and lights necessary for defect detection and classification model production. In addition, data necessary for the production of multiple classification models were collected and labeled according to normal and defective conditions. The multi-classification model is made based on CNN and applies pre-learning models such as VGGNet, MobileNet, ResNet, etc. to compare performance and identify improvement directions with accuracy and loss graphs. Data augmentation and dropout techniques were applied to identify and improve overfitting problems as major problems. In order to evaluate the performance of the model, a performance evaluation was conducted using the confusion matrix as a performance indicator, and the performance of more than 99% was confirmed. In addition, it checks the classification results for images acquired in real time by applying them to the actual process to check whether the discrimination values are accurately derived.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.2
• /
• pp.119-125
• /
• 2023

In this study, we photograph driving obstacle objects such as crosswalks, side spheres, manholes, braille blocks, partial ramps, temporary safety barriers, stairs, and inclined curb that hinder or cause inconvenience to the movement of the vulnerable using electric mobility aids. We develop an optimal AI model that classifies photographed objects and automatically recognizes them, and implement an algorithm that can efficiently determine obstacles in front of electric mobility aids. In order to enable object detection to be AI learning with high probability, the labeling form is labeled as a polygon form when building a dataset. It was developed using a Mask R-CNN model in Detectron2 framework that can detect objects labeled in the form of polygons. Image acquisition was conducted by dividing it into two groups: the general public and the transportation weak, and image information obtained in two areas of the test bed was secured. As for the parameter setting of the Mask R-CNN learning result, it was confirmed that the model learned with IMAGES_PER_BATCH: 2, BASE_LEARNING_RATE 0.001, MAX_ITERATION: 10,000 showed the highest performance at 68.532, so that the user can quickly and accurately recognize driving risks and obstacles.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.27 no.5
• /
• pp.30-39
• /
• 2023

Large dams, which are critical infrastructures for disaster prevention, are exposed to various risks such as aging, floods, and earthquakes. Better dam safety inspection and diagnosis using digital transformation technologies are needed. Traditional visual inspection methods by human inspectors have several limitations, including many inaccessible areas, danger of working at heights, and know-how based subjective inspections. In this study, drone photogrammetry was performed on two large dams to evaluate the applicability of digital data-based dam safety inspection and propose a data management methodology for continuous use. High-quality 3D digital models with GSD (ground sampling distance) within 2.5 cm/pixel were generated by flat double grid missions and manual photography methods, despite reservoir water surface and electromagnetic interferences, and severe altitude differences ranging from 42 m to 99.9 m of dam heights. Geometry profiles of the as-built conditions were easily extracted from the generated 3D mesh models, orthomosaic images, and digital surface models. The effectiveness of monitoring dam deformation by photogrammetry was confirmed. Cracks and deterioration of dam concrete structures, such as spillways and intake towers, were detected and visualized efficiently using the digital 3D models. This can be used for safe inspection of inaccessible areas and avoiding risky tasks at heights. Furthermore, a methodology for mapping the inspection result onto the 3D digital model and structuring a relational database for managing deterioration information history was proposed. As a result of measuring the labor and time required for safety inspection at the SYG Dam spillway, the drone photogrammetry method was found to have a 48% productivity improvement effect compared to the conventional manpower visual inspection method. The drone photogrammetry-based dam safety inspection is considered very effective in improving work productivity and data reliability.

• Smart Media Journal
• /
• v.12 no.11
• /
• pp.48-56
• /
• 2023

The technology of Three-dimensional human posture estimation is used in sports, motion recognition, and special effects of video media. Among various methods for this, multi-view 3D human pose estimation is essential for precise estimation even in complex real-world environments. But Existing models for multi-view 3D human posture estimation have the disadvantage of high order of time complexity as they use 3D feature maps. This paper proposes a method to extend an existing monocular viewpoint multi-frame model based on Transformer with lower time complexity to 3D human posture estimation for multi-viewpoints. To expand to multi-viewpoints our proposed method first generates an 8-dimensional joint coordinate that connects 2-dimensional joint coordinates for 17 joints at 4-vieiwpoints acquired using the 2-dimensional human posture detector, CPN(Cascaded Pyramid Network). This paper then converts them into 17×32 data with patch embedding, and enters the data into a transformer model, finally. Consequently, the MLP(Multi-Layer Perceptron) block that outputs the 3D-human posture simultaneously updates the 3D human posture estimation for 4-viewpoints at every iteration. Compared to Zheng[5]'s method the number of model parameters of the proposed method was 48.9%, MPJPE(Mean Per Joint Position Error) was reduced by 20.6 mm (43.8%) and the average learning time per epoch was more than 20 times faster.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.3
• /
• pp.568-576
• /
• 2003

This paper proposes a moving object tracking algorithm by using hierarchical search method in dynamic scenes. Proposed algorithm is based on two main steps: generation step of initial model from different pictures, and tracking step of moving object under the time-yawing scenes. With a series of this procedure, tracking process is not only stable under far distance circumstance with respect to the previous frame but also reliable under shape variation from the 3-dimensional(3D) motion and camera sway, and consequently, by correcting position of moving object, tracking time is relatively reduced. Partial Hausdorff distance is also utilized as an estimation function to determine the similarity between model and moving object. In order to testify the performance of proposed method, the extraction and tracking performance have tested using some kinds of moving car in dynamic scenes. Experimental results showed that the proposed algorithm provides higher performance. Namely, matching order is 28.21 times on average, and considering the processing time per frame, it is 53.21ms/frame. Computation result between the tracking position and that of currently real with respect to the root-mean-square(rms) is 1.148. In the occasion of different vehicle in terms of size, color and shape, tracking performance is 98.66%. In such case as background-dependence due to the analogy to road is 95.33%, and total average is 97%.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.2
• /
• pp.149-155
• /
• 2020

The Korea Highway Traffic Authority provides statistics that analyze the causes of traffic accidents that occurred since 2015 using the Traffic Accident Analysis System (TAAS). it was reported Through TAAS that the driver's forward carelessness was the main cause of traffic accidents in 2018. As statistics on the cause of traffic accidents, 51.2 percent used mobile phones and watched DMB while driving, 14 percent did not secure safe distance, and 3.6 percent violated their duty to protect pedestrians, representing a total of 68.8 percent. In this paper, we propose a system that has improved the advanced driver assistance system ADAS (Advanced Driver Assistance Systems) by utilizing CNN (Convolutional Neural Network) among the algorithms of Deep Learning. The proposed system learns a model that classifies the movement of the driver's face and eyes using Conv2D techniques which are mainly used for Image processing, while recognizing and detecting objects around the vehicle with cameras attached to the front of the vehicle to recognize the driving environment. Then, using the learned visual steering model and driving environment data, the hazard is classified and detected in three stages, depending on the driver's view and driving environment to assist the driver with the forward and blind spots.

• Journal of the Korean Chemical Society
• /
• v.53 no.6
• /
• pp.717-726
• /
• 2009

Multivariate models were developed for the simultaneous spectrophotometric determination of copper (II), nickel (II) and zinc (II) in water with 1-(2-thiazolylazo)-2-naphthol as chromogenic reagent in the presence of Triton X-100. To overcome the drawback of spectral interferences, principal component regression (PCR) and partial least square (PLS) multivariate calibration approaches were applied. Performances were validated with several test sets, and their results were then compared. In general, no significant difference in analytical performance between PLS and PCR models. The root mean square error of prediction (RMSEP) using three components for $Cu^{2+}$, $Ni^{2+}$ and $Zn^{2+}$ were 0.018, 0.010, 0.011 ppm, respectively. Figures of merit such as sensitivity, analytical sensitivity, limit of detection (LOD) were also estimated. High reliability was achieved when the proposed procedure was applied to simultaneous determination of $Cu^{2+}$, $Ni^{2+}$ and $Zn^{2+}$ in synthetic mixture and tap water.