• Journal of the Korean Society of Radiology
• /
• v.15 no.7
• /
• pp.1049-1056
• /
• 2021

The purpose of this study was to develop a respiratory synchronization device for X-ray (X-RSD) to increase the reproducibility of inspiration when examining the Chest X-ray of a patient who difficulty in breathing coordination. The X-RSD was self-made using an air pressure sensor and air was injected by connecting a ventilator to the mannequin for CPR. At this time, the amount of injected air was quantified using the SkillReporting device. After placing the X-RSD on the chest of the mannequin, the amount of air was tested in 6 steps from 200 to 700 cc by 100 cc increased. For the accuracy evaluation, the sensitivity of X-RSD was measured by repeating a total of 80 measurements, and the sensitivity was 100%, and very precise results were obtained. After that, the images examined while viewing the X-RSD of the chest lateral examination and the images obtained by the blind examination were compared and evaluated. The lung volume of X-RSD was larger than that of the blind test, and the deviation was smaller. Overall, the use of X-RSD can help with chest X-ray examination of patients who have difficulty in cooperating, and it is thought that it will be possible to contribute to the reduction of exposure dose by reducing the repeat rate of general X-ray examinations.

• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.368-376
• /
• 2021

Artificial intelligence clouds help to efficiently develop the autonomous things integrating artificial intelligence technologies and control technologies by sharing the learned models and providing the execution environments. The existing autonomous things development technologies only take into account for the accuracy of artificial intelligence models at the cost of the increment of the complexity of the models including the raise up of the number of the hidden layers and the kernels, and they consequently require a large amount of computation. Since resource-constrained computing environments, could not provide sufficient computing resources for the complex models, they make the autonomous things violate time criticality. In this paper, we propose a digital twin software development framework that selects artificial intelligence models optimized for the computing environments. The proposed framework uses a load estimation DNN model to select the optimal model for the specific computing environments by predicting the load of the artificial intelligence models with digital twin data so that the proposed framework develops the control software. The proposed load estimation DNN model shows up to 20% of error rate compared to the formula-based load estimation scheme by means of the representative CNN models based experiments.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.5
• /
• pp.7-14
• /
• 2021

Tomato crops are highly affected by tomato diseases, and if not prevented, a disease can cause severe losses for the agricultural economy. Therefore, there is a need for a system that quickly and accurately diagnoses various tomato diseases. In this paper, we propose a system that classifies nine diseases as well as healthy tomato plants by applying various pretrained deep learning-based CNN models trained on an ImageNet dataset. The tomato leaf image dataset obtained from PlantVillage is provided as input to ResNet, Xception, and DenseNet, which have deep learning-based CNN architectures. The proposed models were constructed by adding a top-level classifier to the basic CNN model, and they were trained by applying a 5-fold cross-validation strategy. All three of the proposed models were trained in two stages: transfer learning (which freezes the layers of the basic CNN model and then trains only the top-level classifiers), and fine-tuned learning (which sets the learning rate to a very small number and trains after unfreezing basic CNN layers). SGD, RMSprop, and Adam were applied as optimization algorithms. The experimental results show that the DenseNet CNN model to which the RMSprop algorithm was applied output the best results, with 98.63% accuracy.

• Journal of the Korean Society of Radiology
• /
• v.15 no.2
• /
• pp.153-158
• /
• 2021

X-ray image analysis is a very important field to improve the early diagnosis rate and prediction accuracy of periodontal disease. Research on the development and application of artificial intelligence-based algorithms to improve the quality of such dental X-ray images is being widely conducted worldwide. Thus, the aim of this study was to design a super-resolution algorithm for predicting periodontal disease and to evaluate its applicability in dental X-ray images. The super-resolution algorithm was constructed based on the convolution layer and ReLU, and an image obtained by up-sampling a low-resolution image by 2 times was used as an input data. Also, 1,500 dental X-ray data used for deep learning training were used. Quantitative evaluation of images used root mean square error and structural similarity, which are factors that can measure similarity through comparison of two images. In addition, the recently developed no-reference based natural image quality evaluator and blind/referenceless image spatial quality evaluator were additionally analyzed. According to the results, we confirmed that the average similarity and no-reference-based evaluation values were improved by 1.86 and 2.14 times, respectively, compared to the existing bicubic-based upsampling method when the proposed method was used. In conclusion, the super-resolution algorithm for predicting periodontal disease proved useful in dental X-ray images, and it is expected to be highly applicable in various fields in the future.

• Land and Housing Review
• /
• v.12 no.2
• /
• pp.109-120
• /
• 2021

Global warming due to increased carbon dioxide is perceived as one of the factors threatening the future. Efforts are being made to reduce carbon dioxide emissions in each industry around the world. In particular, environmental loads and impacts during the life cycle of SOC structures and buildings have been quantitatively assessed through a quantitative method called Life Cycle Assessment (LCA). However, the construction sector has gone through difficulty in quantitative assessment for several reasons: 1) LCI DB is not fully established; 2) the life cycle is very long; 3) the building structures are unique. Therefore, it takes enormous effort and time to carry out LCA. Rather than estimating carbon emissions with accuracy, this study aims to present a simplified estimation model that allows owners or designers to easily estimate carbon dioxide emissions with little effort, given that rapid and rough decisions regarding environmental load reduction are to be made. This study performs the LCA using data from 25 road construction projects across the country, followed by multiple regression analyses to derive a simplified carbon estimation model (SLCA). The study also carries out a comparative analysis with values estimated by performing a typical LCA. The comparison analysis shows an error rate of less than 5% for 16 road projects.

• Journal of the Korean Geotechnical Society
• /
• v.35 no.4
• /
• pp.27-35
• /
• 2019

This study confirmed the applicability to the field of geotechnical engineering for relatively complicated space and many target design variables in back analysis. The Sharan's equation and the Blum's method were used for the tunnel field and the retaining wall as a model for the multi-variate problem of geotechnical engineering. Optimization methods are generally divided into a deterministic method and a stochastic method. In this study, Simulated Annealing Method (SA) was selected as a deterministic method and Differential Evolution Algorithm (DEA) and Particle Swarm Optimization Method (PSO) were selected as stochastic methods. The three selected optimization methods were compared by applying a multi-variate model. The problem of deterministic method has been confirmed in the multi-variate back analysis of geotechnical engineering, and the superiority of DEA can be confirmed. DEA showed an average error rate of 3.12% for Sharan's solution and 2.23% for Blum's problem. The iteration number of DEA was confirmed to be smaller than the other two optimization methods. SA was confirmed to be 117.39~167.13 times higher than DEA and PSO was confirmed to be 2.43~6.91 times higher than DEA. Applying a DEA to the multi-variate back analysis of geotechnical problems can be expected to improve computational speed and accuracy.

• Korean Journal of Clinical Laboratory Science
• /
• v.50 no.4
• /
• pp.470-476
• /
• 2018

Facial motor evoked potential (FMEP) by multi-pulse transcranial electrical stimulation (mpTES) can complement free-running electromyography (EMG) and direct facial nerve stimulation to predict the functional integrity of the facial nerve during cerebello-pontine angle (CPA) tumor surgery. The purpose of this paper is to examine the standardized test methods and the usefulness of FMEP as a predictor of facial nerve function and to minimize the incidence of facial paralysis as an aftereffect of surgery. TES was delivered through electrode Mz (cathode) - M3/M4 (anode), and extracranially direct distal facial muscle excitation was excluded by the absence of single pulse response (SPR) and by longer onset latency (more than 10 ms). FMEP from the orbicularis oris (o.oris) and the mentalis muscle simultaneously can improve the accuracy and success rate compared with FMEP from the o.oris alone. Using the methods described, we can effectively predict facial nerve outcomes immediately after surgery with a reduction of more than 50% of FMEP amplitude as a warning criterion. In conclusion, along with free-running EMG and direct facial nerve stimulation, FMEP is a useful method to reduce the incidence of facial paralysis as a sequela during CPA tumor surgery.

• Journal of the Korea Convergence Society
• /
• v.10 no.6
• /
• pp.7-14
• /
• 2019

In this paper, we propose a Cascade Classifier face detection method using the Haar-like feature, which is complemented by the Flood Fill algorithm for lossy areas due to illumination and shadow in YCbCr color space extraction. The Cascade Classifier using Haar-like features can generate noise and loss regions due to lighting, shadow, etc. because skin color extraction using existing YCbCr color space in image only uses threshold value. In order to solve this problem, noise is removed by erosion and expansion calculation, and the loss region is estimated by using the Flood Fill algorithm to estimate the loss region. A threshold value of the YCbCr color space was further allowed for the estimated area. For the remaining loss area, the color was filled in as the average value of the additional allowed areas among the areas estimated above. We extracted faces using Haar-like Cascade Classifier. The accuracy of the proposed method is improved by about 4% and the detection rate of the proposed method is improved by about 2% than that of the Haar-like Cascade Classifier by using only the YCbCr color space.

• Explosives and Blasting
• /
• v.37 no.2
• /
• pp.22-30
• /
• 2019

On sites where explosives are used, the effects of noise and vibration produced by the blast wave are subject to a number of operational restrictions. Recently, the number of civil complaints has increased and the standard of environmental regulations on secure goods has been greatly tighten. Therefore, work is generally carried out by machine excavation in case of close proximity of safety thing. Machine excavation methods have the advantage as reducing noise and vibration compared to blasting methods, but depending on the conditions of rock intended to be excavated, they are sometimes less constructive than planned. In general, the closer a rock type is to hard rock, the less constructible it becomes. In this paper, we are going to explain the construction of a construction section with a close proximity to a safety thing using electronic detonators. While the project site was designed with a machine excavation methods due to the close(9.9m) proximity of safety thing(the railroad), construction using electronic detonators was reviewed as an alternative method for improving rate of advance time and construction efficiency when expose to hard rock. Through blasting using electronic detonators, construction and economic efficiency were maximized while minimizing impact on surrounding safety things. Because $HiTRONIC^{TM}$, which is produced by Hanwha, has innovative stability and high explosion reliability, it is able to explode with high-precision accuracy. Electronic detonators are widely used in construction sites of railway or highway, other urban burrowing areas and large limestone mines.

• Journal of Food Hygiene and Safety
• /
• v.34 no.1
• /
• pp.52-57
• /
• 2019

Method development and validation of decursin for the standardization of Angelica gigas Nakai as a functional ingredient and health food were accomplished. The quantitative determination method of decursin as a marker compound of aerial parts of Angelica gigas Nakai extract (AAGE) was optimized by HPLC analysis using a C18 column ($3{\times}150mm$, $3{\mu}m$) with 0.1% TFA in water and acetonitrile as the mobile phase at a flow rate of 0.5 mL/min and detection wavelength of 330 nm. The HPLC/PDA method was applied successfully to quantification of the marker compound in AAGE after validation of the method with linearity, accuracy, and precision. The method showed high linearity in the calibration curve at a coefficient of correlation ($R^2$) of 0.9994 and the limit of detection and limit of quantitation were $0.011{\mu}g/mL$ and $0.033{\mu}g/mL$, respectively. Relative standard deviation (RSD) values of data from intra- and inter-day precision were less than 1.10% and 1.13%, respectively. Recovery of decursin at 0.5, 1, 5 and $10{\mu}g/mL$ were 92.38 ~ 104.11%. These results suggest that the developed HPLC method is very useful for the determination of marker compound in AAGE to develop a health functional material.