• Journal of Biomedical Engineering Research
• /
• v.43 no.4
• /
• pp.290-297
• /
• 2022

During surgery, Surgical instruments are often left behind due to accidents. Most of these are surgical gauze, so radioactive non-permeable gauze (X-ray gauze) is used for preventing of accidents which gauze is left in the body. This gauze is divided into wire and pad type. If it is confirmed that the gauze remains in the body, gauze must be detected by radiologist's reading by imaging using a mobile X-ray device. But most of operating rooms are not equipped with a mobile X-ray device, but equipped C-Arm equipment, which is of poorer quality than mobile X-ray equipment and furthermore it takes time to read them. In this study, Use C-Arm equipment to acquire gauze image for detection and Build dataset using artificial intelligence and select a detection model to Assist with the relatively low image quality and the reading of radiology specialists. mAP@50 and detection time are used as indicators for performance evaluation. The result is that two-class gauze detection dataset is more accurate and YOLOv5 model mAP@50 is 93.4% and detection time is 11.7 ms.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.6
• /
• pp.43-52
• /
• 2022

We can sense somebody's feeling fatigue, which means that fatigue can be detected through sensing human biometric signals. Numerous researches for assessing fatigue are mostly focused on diagnosing the edge of disease-level fatigue. In this study, we adapt quantitative analysis approaches for estimating qualitative data, and propose video analysis models for measuring fatigue state. Proposed three deep-learning based classification models selectively include stages of video analysis: object detection, feature extraction and time-series frame analysis algorithms to evaluate each stage's effect toward dividing the state of fatigue. Using frontal face videos collected from various fatigue situations, our CNN model shows 0.67 accuracy, which means that we empirically show the video analysis models can meaningfully detect fatigue state. Also we suggest the way of model adaptation when training and validating video data for classifying fatigue.

• Journal of radiological science and technology
• /
• v.46 no.4
• /
• pp.277-285
• /
• 2023

In this study, pneumonia identification networks with the small number of layers were constructed by using chest X-ray images. The networks had similar trainable-parameters, and the performance of the trained models was quantitatively evaluated with the modification of the network architectures. A total of 6 networks were constructed: convolutional neural network (CNN), VGGNet, GoogleNet, residual network with identity blocks, ResNet with bottleneck blocks and ResNet with identity and bottleneck blocks. Trainable parameters for the 6 networks were set in a range of 273,921-294,817 by adjusting the output channels of convolution layers. The network training was implemented with binary cross entropy (BCE) loss function, sigmoid activation function, adaptive moment estimation (Adam) optimizer and 100 epochs. The performance of the trained models was evaluated in terms of training time, accuracy, precision, recall, specificity and F1-score. The results showed that the trained models with the small number of layers precisely detect pneumonia from chest X-ray images. In particular, the overall quantitative performance of the trained models based on the ResNets was above 0.9, and the performance levels were similar or superior to those based on the CNN, VGGNet and GoogleNet. Also, the residual blocks affected the performance of the trained models based on the ResNets. Therefore, in this study, we demonstrated that the object detection networks with the small number of layers are suitable for detecting pneumonia using chest X-ray images. And, the trained models based on the ResNets can be optimized by applying appropriate residual-blocks.

• Nuclear Engineering and Technology
• /
• v.55 no.9
• /
• pp.3260-3267
• /
• 2023

Zr-Nb alloy have been widely used as fuel rods in nuclear power plants. However, from the Fukushima nuclear accident, the weakness of the rod was revealed under harsh conditions, and research on the safety of these types of rods was conducted after the disaster. The method of depositing chromium onto the existing Zr-Nb alloy fuel rods is being considered as a means by which to compensate for the weakness of Zr-Nb alloy rods because chromium is strong against oxidation at high temperatures and has high strength. In order to secure these advantages, it is important to maintain the Cr thickness of the rods and properly inspect the rods before and during their use in power generation. Eddy current testing is a typical means of evaluating the thickness of thin metals and detecting surface defects. Depending on the size and shape of the inspected object, various eddy current sensors can be applied. In particular, because pancake sensors can be manufactured in very small sizes, they can be used for inspections even in narrow spaces, such as a nuclear fuel assembly. In this study, an eddy current technique was developed to confirm the feasibility of Cr coating thickness evaluations. After determining the design parameters of the pancake sensor by means of a FEM simulation, a FPCB pancake sensor was manufactured and the optimal frequency was selected by measuring minute changes in the Cr-coating thickness using the developed sensor.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.101-103
• /
• 2022

CCTV is mainly used as a real-time detection system for critical facilities. In the case of CCTV, although the accuracy is high, the viewing angle is narrow, so it is used in combination with a sensor such as a radar. LiDAR is a technology that acquires distance information by detecting the time it takes to reflect off an object using a high-power pulsed laser. In the case of lidar, there is a problem in that the utilization is not high in terms of cost and technology due to the limitation of the number of simultaneous processing sensors in the server due to the data throughput. The detection method by the optical mesh sensor is also vulnerable to strong winds and extreme cold, and there is a problem of maintenance due to damage to animals. In this paper, by using the 1550nm wavelength band instead of the 905nm wavelength band used in the existing lidar sensor, the effect on the weather environment is strong and we propose to develop a system that can integrate and control multiple sensors.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.463-465
• /
• 2021

Currently, the inspection method printed on food packages and boxes is to sample only a few products and inspect them with human eyes. Such a sampling inspection has the limitation that only a small number of products can be inspected. Therefore, accurate inspection using a camera is required. This paper proposes a deep learning object recognition technology model, which is an artificial intelligence technology, as a method for detecting the defects of expiration date printed on the product packaging. Using the Faster R-CNN (region convolution neural network) model, the color images, converted gray images, and converted binary images of the printed expiration date are trained and then tested, and each detection rates are compared. The detection performance of expiration date printed on the package by the proposed method showed the same detection performance as that of conventional vision-based inspection system.

• Journal of Cadastre & Land InformatiX
• /
• v.53 no.1
• /
• pp.107-121
• /
• 2023

In order to acquire a wide range of land that changes in real time and quickly and accurately grasp it, we plan to utilize the recently released high-resolution S.Korea's satellite image data and artificial intelligence (AI). Compared to existing satellite images, the spectral and periodic resolutions of S.Korea's satellite are higher, making them a more suitable data source for periodically monitoring changes in land. Therefore, this study aims to acquire S.Korea's satellite, select 8 types of objects to detect land changes, construct data sets for them, and apply AI models to analyze them. In order to confirm the optimal model and variable conditions for detecting 8 types of objects of various types, several experiments are performed and AI-based image analysis is technically reviewed.

• Journal of the Society of Disaster Information
• /
• v.19 no.4
• /
• pp.968-975
• /
• 2023

Purpose: We would like to confirm that the false positive rate of flames/smoke is high when detecting fires. Propose a method and dataset to recognize and classify fire situations to reduce the false detection rate. Method: Using the video as learning data, the characteristics of the fire situation were extracted and applied to the classification model. For evaluation, the model performance of Yolov8 and Slowfast were compared and analyzed using the fire dataset conducted by the National Information Society Agency (NIA). Result: YOLO's detection performance varies sensitively depending on the influence of the background, and it was unable to properly detect fires even when the fire scale was too large or too small. Since SlowFast learns the time axis of the video, we confirmed that detects fire excellently even in situations where the shape of an atypical object cannot be clearly inferred because the surrounding area is blurry or bright. Conclusion: It was confirmed that the fire detection rate was more appropriate when using a video-based artificial intelligence detection model rather than using image data.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.1
• /
• pp.77-84
• /
• 2024

In this paper, we propose a method for accurately and rapidly detecting defects in wire harnesses by utilizing computer vision to calculate six crucial measurement values: the length of crimped terminals, the dimensions (width) of terminal ends, and the width of crimped sections (wire and core portions). We employ Harris corner detection to locate object positions from two types of data. Additionally, we generate reference points for extracting measurement values by utilizing features specific to each measurement area and exploiting the contrast in shading between the background and objects, thus reflecting the slope of each sample. Subsequently, we introduce a method using the Euclidean distance and correction coefficients to predict values, allowing for the prediction of measurements regardless of changes in the wire's position. We achieve high accuracy for each measurement type, 99.1%, 98.7%, 92.6%, 92.5%, 99.9%, and 99.7%, achieving outstanding overall average accuracy of 97% across all measurements. This inspection method not only addresses the limitations of conventional visual inspections but also yields excellent results with a small amount of data. Moreover, relying solely on image processing, it is expected to be more cost-effective and applicable with less data compared to deep learning methods.

• Economic and Environmental Geology
• /
• v.57 no.1
• /
• pp.17-23
• /
• 2024

Ground penetrating radar (GPR) survey is a geophysical method that utilizes electromagnetic waves reflecting from a boundary where the electromagnetic property changes. As the frequency of the antenna is about 25 MHz ~ 1 GHz, it is effective to acquire high resolution images of underground pipe, artificial structure, underground cavity, and underground structure. In this study, we analyzed the change of signals reflected from the same underground objects according to the arrangement of transceiver antennas used in ground penetrating radar survey. The antenna used in the experiment was 200 MHz, and the survey was performed in the vertical direction across the sewer and the parallel direction along the sewer to the sewer buried under the road, respectively. A total of five antenna array methods were applied to the survey. The most used arrangement is when the transmitting and receiving antennas are all perpendicular to the survey line (PR-BD). The PR-BD arrangement is effective when the object underground is a horizontal reflector with an angle of less than 30°, such as the sewer under investigation. In this case study, it was confirmed that the transmitter and receiver antennas perpendicular to the survey line (PR-BD) are the most effective way to show the underground structure. In addition, in the case where the transmitting and receiving antennas are orthogonal to each other (XPOL), no specific reflected wave was observed in both experiments measured across or parallel to the sewer. Therefore, in the case of detecting undiscovered objects in the underground, the PR-BD array method in which the transmitting and receiving antennas are aligned in the direction perpendicular to the survey line taken as a reference and the XPOL method in which the transmitting and receiving antennas are orthogonal to each other are all used, it can be effective to apply both of the above arrangements after setting the direction to 45° and 135°.