• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.3
• /
• pp.490-493
• /
• 2021

This paper proposes an embedded system that detects mask and face recognition based on a microprocessor instead of Nvidia Jetson Board what is popular development kit. We use a class of efficient models called Mobilenets for mobile and embedded vision applications. MobileNets are based on a streamlined architechture that uses depthwise separable convolutions to build light weight deep neural networks. The device used a Maix development board with CNN hardware acceleration function, and the training model used MobileNet_V2 based SSD(Single Shot Multibox Detector) optimized for mobile devices. To make training model, 7553 face data from Kaggle are used. As a result of test dataset, the AUC (Area Under The Curve) value is as high as 0.98.

• Journal of Biomedical Engineering Research
• /
• v.44 no.3
• /
• pp.182-189
• /
• 2023

CT is a medical device that acquires medical images based on Attenuation coefficient of human organs related to X-rays. In addition, using this theory, it can acquire sagittal and coronal planes and 3D images of the human body. Then, CT is essential device for universal diagnostic test. But Exposure of CT scan is so high that it is regulated and managed with special medical equipment. As the special medical equipment, CT must implement quality control. In detail of quality control, Spatial resolution of existing phantom imaging tests, Contrast resolution and clinical image evaluation are qualitative tests. These tests are not objective, so the reliability of the CT undermine trust. Therefore, by applying an artificial intelligence classification model, we wanted to confirm the possibility of quantitative evaluation of the qualitative evaluation part of the phantom test. We used intelligence classification models (VGG19, DenseNet201, EfficientNet B2, inception_resnet_v2, ResNet50V2, and Xception). And the fine-tuning process used for learning was additionally performed. As a result, in all classification models, the accuracy of spatial resolution was 0.9562 or higher, the precision was 0.9535, the recall was 1, the loss value was 0.1774, and the learning time was from a maximum of 14 minutes to a minimum of 8 minutes and 10 seconds. Through the experimental results, it was concluded that the artificial intelligence model can be applied to CT implements quality control in spatial resolution and contrast resolution.

• Nuclear Engineering and Technology
• /
• v.46 no.3
• /
• pp.387-394
• /
• 2014

A Slowing Down Time Spectrometer (SDTS) system is a highly efficient technique for isotopic nuclear material content analysis. SDTS technology has been used to analyze spent nuclear fuel and the pyro-processing of spent fuel. SDTS requires an external neutron source to induce the isotopic fissile fission. A high intensity neutron source is required to ensure a high for a good fissile fission. The electron linear accelerator system was selected to generate proper source neutrons efficiently. As a first step, the electron generator of an 80-keV electron gun was manufactured. In order to produce the high beam power from electron linear accelerator, a proper beam current is required form the electron generator. In this study, the beam current was measured by evaluating the performance of the electron generator. The beam current was determined by five parameters: high voltage at the electron gun, cathode voltage, pulse width, pulse amplitude, and bias voltage at the grid. From the experimental results under optimal conditions, the high voltage was determined to be 80 kV, the pulse width was 500 ns, and the cathode voltage was from 4.2 V to 4.6 V. The beam current was measured as 1.9 A at maximum. These results satisfy the beam current required for the operation of an electron linear accelerator.

• Nuclear Engineering and Technology
• /
• v.52 no.7
• /
• pp.1565-1570
• /
• 2020

Photons with the energy of 60 keV are regularly used for some kinds of bone density examination devices, like the single photon absorptiometry (SPA). This article reports a flexible and lightweight rare earth/polymer composite for enhancing shielding efficiency against photon radiation with the energy of 60 keV. Lead oxide (PbO) and several rare earth element oxides (La₂O₃, Ce₂O₃, Nd₂O₃) were dispersed into natural rubber (NR) and the photon radiation shielding performance of the composites were assessed using monte carlo simulation method. For 60 keV photons, the shielding efficiency of rare earthbased composites were found to be much higher than that of the traditional lead-based composite, which has bad absorbing ability for photons with energies between 40 keV and 88 keV. In comparison with the lead oxide based composite, Nd₂O₃-NR composite with the same protection standard (the lead equivalent is 0.25 mmPb, 0.35 mmPb and 0.5 mmPb, respectively), can reduce the thickness by 35.29%, 37.5% and 38.24%, and reduce the weight by 38.91%, 40.99% and 41.69%, respectively. Thus, a flexible, lightweight and lead-free rare earth/NR composite could be designed, offering efficient photon radiation protection for the users of the single photon absorptiometry (SPA) with certain energy of 60 keV.

• Nuclear Engineering and Technology
• /
• v.54 no.3
• /
• pp.1062-1070
• /
• 2022

In the present communication, pure and stable α-Bismuth Oxide (Bi₂O₃) nanoparticles (NPs) were synthesized by low temperature solution combustion method using urea as a fuel and calcined at 500℃. The synthesized sample was characterized by using powder X-ray Diffraction (PXRD), Scanning Electron Microscopy (SEM), Energy dispersive X-ray analysis (EDAX), Transmission Electron Microscopy (TEM), Fourier Transform Infrared Spectroscopy (FTIR) and UV-Visible absorption spectroscopy. The PXRD pattern confirms the formation of mono-clinic, stable and low temperature phase α-Bi₂O₃. The direct optical energy band gap was estimated by using Wood and Tauc's relation which was found to be 2.81 eV. The characterized sample was studied for X-ray/gamma ray shielding properties in the energy range 0.081-1.332 MeV using NaI (Tl) detector and multi channel analyzer (MCA). The measured shielding parameters agrees well with the theory, whereas, slight deviation up to 20% is observed below 356 keV. This deviation is mainly due to the influence of atomic size of the target medium. Furthermore an accurate theory is necessary to explain the interaction of X-ray/gamma ray with the NPs.The present work opens new window to use this facile, economical, efficient, low temperature method to synthesize nanomaterials for X-ray/gamma ray shielding purpose.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.38 no.4
• /
• pp.293-299
• /
• 2002

The anchovy scoop net fishery is one of the important in the South sea and coastal of Jeju of Korea. They are using incandescent lamp as a fishing lamp at night to gather anchovy shoals in the water surface. Fishing lamp (AC 100 V 500 W$\times$2~3 or AC 100 V 1 ㎾$\times$1) was installed at 1 m ahead of the prow and 1.5 m height from the water surface. The fishing lamp let anchovy shoals rise to the water surface and are attracted to bag net. On this study, the distribution of submarine illumination of 1㎾ and 2 ㎾ incandescent lamp were analyzed and discussed to investigate the ability of fishing lamp which can gather anchovy shoals effectively. The submarine illumination of incandescent lamp showed peak in wave length 690 nm. The relationship between submarine illumination (L) and water depth (Z) of 1 ㎾ and 2 ㎾ incandescent lamp in vertical light is 1 ㎾ : L = 3851. 9 $e^{-1.4587Z}$ $R^2$=0.9952 2 ㎾ : L= 8211.9 $e^{-1.2852Z}$ $R^2$=0.9977 The submarine illumination of 2 ㎾ incandescent lamp of 0～4 m layers appeared to be 3 to 4 times higher than 1 ㎾ incandescent lamp, and in more deep layers than 6 m appeared to be equal value of each lamp. The light of incandescent lamp (1 ㎾) pass through much better into vertical direction than horizontal, and submarine illumination of 20 m layers was 1.0 l$\chi$. Therefore, fishing lamp power is thought that 1 ㎾ incandescent lamp is more efficient than 2 ㎾ to gather anchovy shoals in depth of 15~20 m to water surface.

• Nuclear Engineering and Technology
• /
• v.49 no.2
• /
• pp.395-403
• /
• 2017

An efficient evaluation method for the probability of a tornado missile strike without using the Monte Carlo method is proposed in this paper. A major part of the proposed probability evaluation is based on numerical results computed using an in-house code, Tornado-borne missile analysis code, which enables us to evaluate the liftoff and flight behaviors of unconstrained objects on the ground driven by a tornado. Using the Tornado-borne missile analysis code, we can obtain a stochastic correlation between local wind speed and flight distance of each object, and this stochastic correlation is used to evaluate the conditional strike probability, $Q_V(r)$, of a missile located at position r, where the local wind speed is V. In contrast, the annual exceedance probability of local wind speed, which can be computed using a tornado hazard analysis code, is used to derive the probability density function, p(V). Then, we finally obtain the annual probability of tornado missile strike on a structure with the convolutional integration of product of $Q_V(r)$ and p(V) over V. The evaluation method is applied to a simple problem to qualitatively confirm the validity, and to quantitatively verify the results for two extreme cases in which an object is located just in the vicinity of or far away from the structure.

• Smart Media Journal
• /
• v.13 no.3
• /
• pp.9-17
• /
• 2024

Due to the recent pandemic and the development of ICT technology, the use of non-face-to-face and unmanned systems is expanding, and it is very important to understand emotions in communication in non-face-to-face situations. As emotion recognition methods for various facial expressions are required to understand emotions, artificial intelligence-based research is being conducted to improve facial expression emotion recognition in image data. However, existing research on facial expression emotion recognition requires high computing power and a lot of learning time because it utilizes a large amount of data to improve accuracy. To improve these limitations, this paper proposes a method of recognizing facial expressions using age and gender, which are image meta information, as a method of recognizing facial expressions with even a small amount of data. For facial expression emotion recognition, a face was detected using the Yolo Face model from the original image data, and age and gender were classified through the VGG model based on image meta information, and then seven emotions were recognized using the EfficientNet model. The accuracy of the proposed data classification learning model was higher as a result of comparing the meta-information-based data classification model with the model trained with all data.

• Nuclear Engineering and Technology
• /
• v.51 no.4
• /
• pp.1091-1097
• /
• 2019

After the Fukushima accident in 2011, there has been increased public concern about radioactive contamination of water resources through fallout in neighboring countries. However, there is still no available initial response system that can promptly detect radionuclides. The purpose of this research is to develop the most efficient gamma spectrometer to monitor radionuclides in an aquatic environment. We chose a thallium-doped sodium iodide (NaI(Tl)) scintillator readout with a silicon photo multiplier (SiPM) due to its compactness and low operating voltage. Three types of a scintillation detector were tested. One was composed of a scintillator and a photomultiplier tube (PMT) as a reference; another system consisted of a scintillator and an array of SiPMs with a light guide; and the other was a scintillator directly coupled with an array of SiPMs. Among the SiPM-based detectors, the direct coupling system showed the best energy resolution at all energy peaks. It achieved 9.76% energy resolution for a 662 keV gamma ray. Through additional experiments and a simulation, we proved that the light guide degraded energy resolution with increasing statistical uncertainty. The results indicated that the SiPM-based scintillation detector with no light guide is the most efficient design for monitoring radionuclides in an aquatic environment.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.475-478
• /
• 2023

컴퓨터 단층촬영(CT)을 활용한 골격근 단면적은 근감소증과 관련된 기능을 평가하는 데 사용된다. 일반적인 근감소증 연구는 요추 3번의 골격근량을 주로 보지만 암 또는 폐절제술과의 상관관계를 예측하기 위한 다양한 연구에서는 흉추 4번, 7번, 8번, 10번, 12번 다양한 수준의 골격근량으로 연구를 진행하고 있음을 알 수 있다. 본 논문에서는 흉부와 복부 CT 영상에서 근감소증 진단을 위해서 흉추와 요추의 영역별 슬라이스를 검출하기 위해서 CNN 구조의 EfficientNetV2를 전이학습하여 인공지능 모듈을 개발하였다. 인공지능 모듈은 전체 흉부 및 복부 CT 영상에서 Cervical, T1, T2, T3, T4, T5, T6, T7, T8, T9, T10, T11, T12, L1, L2, L3, L4, L5, Sacral 총 19 클래스를 검출하도록 하였다. Test 데이터셋을 사용하여 Confusion Matrix와 Grad-CAM으로 모델의 정확도를 시각화하여 보였으며 검증으로 인공지능 모듈의 정확성을 측정하였다. 끝으로 우리가 개발한 다기관 공동연구 지원플랫폼에 적용하여 시각화된 결과를 보였다.