• The Korea Journal of Herbology
• /
• v.28 no.6
• /
• pp.145-153
• /
• 2013

Objectives : Neuroinflammation is characterized by microglial activation and the expression of major inflammatory mediators. The present study investigated the inhibitory effect of ginsenoside Rg1 ($GRg_1$), a principle active ingredient in Panax ginseng, on pro-inflammatory cytokines and microglial activation induced by systemic lipopolysaccharide (LPS) treatment in the mouse brain tissue. Methods : Varying doses of $GRg_1$ was orally administered (10, 20, and 30 mg/kg) 1 h before the LPS injection (3 mg/kg, intraperitoneally). The mRNA expression of pro-inflammatory cytokines in the brain tissue was measured using the quantitative real-time PCR method at 4 h after the LPS injection, Microglial activation was evaluated using western blotting and immunohistochemistry against ionized calcium binding adaptor molecule 1 (Iba1) in the brain tissue. Cyclooxigenase-2 (COX-2) expressions also observed using western blotting and immunohistochemistry at 4 h after the LPS injection, In addition, double-immunofluorescent labeling of tumor necrosis factor-${\alpha}$ (TNF-${\alpha}$) and COX-2 with microglia and neurons was processed in the brain tissue. Results : $GRg_1$ (30 mg/kg) significantly attenuated the upregulation of TNF-${\alpha}$, interleukin (IL)-$1{\beta}$ and IL-6 mRNA in the brain tissue at 4 h after LPS injection. Morphological activation and Iba1 protein expression of microglia induced by systemic LPS injection were reduced by the $GRg_1$ (30 mg/kg) treatment. Upregulation of COX-2 protein expression in the brain tissue was also attenuated by the $GRg_1$ (30 mg/kg) treatment. Conclusion : The results suggest that $GRg_1$ is effective in the early stage of neuroinflammation which causes neurodegenerative diseases.

• Journal of the Society of Disaster Information
• /
• v.18 no.3
• /
• pp.433-443
• /
• 2022

Purpose: In this paper, we propose a study of deep learning algorithms that estimate and predict sarcopenia by exploiting the high penetration rate of smart devices. Method: To utilize deep learning techniques, experimental data were collected by using the inertial sensor embedded in the smart device. We implemented a smart device application for data collection. The data are collected by labeling normal and abnormal gait and five states of running, falling and squat posture. Result: The accuracy was analyzed by comparative analysis of LSTM, CNN, and RNN models, and binary classification accuracy of 99.87% and multiple classification accuracy of 92.30% were obtained using the CNN-LSTM fusion algorithm. Conclusion: A study was conducted using a smart sensoring device, focusing on the fact that gait abnormalities occur for people with sarcopenia. It is expected that this study can contribute to strengthening the safety issues caused by sarcopenia.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.4
• /
• pp.355-360
• /
• 2022

As the increase cost of domestic red pepper and the increase of imported red pepper, damage cases such as false labeling of the origin of red pepper powder are issued. Accordingly we need to determine quickly and accurately for the origin of red pepper powder. The used method for presently determining the origin has the limitation in that it requires a lot of cost and time by experimentally comparing and analyzing the components of red pepper powder. To resolve the issues, this study proposes machine learning algorithm to classifiy domestic and imported red pepper powder. We have built machine learning model with 53 components contained in red pepper powder and validated. Through the proposed model, it was possible to identify which ingredients are importantly used in determining the origin. In the near future, it is expected that the cost of determining the origin can be further reduced by expanding to various foods as well as red pepper powder.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.4
• /
• pp.97-113
• /
• 2023

Swift and appropriate responses in emergency situations like objects falling on the road can bring convenience to road users and effectively reduces secondary traffic accidents. In Korea, current intelligent transportation system (ITS)-based detection systems for emergency road situations mainly rely on loop detectors and CCTV cameras, which only capture road data within detection range of the equipment. Therefore, a new detection method is needed to identify emergency situations in spatially shaded areas that existing ITS detection systems cannot reach. In this study, we propose a ResNet-based algorithm that detects and classifies emergency situations from vehicle camera footage. We collected front-view driving videos recorded on Korean highways, labeling each video by defining the type of emergency, and training the proposed algorithm with the data.

• Journal of Radiopharmaceuticals and Molecular Probes
• /
• v.6 no.2
• /
• pp.75-91
• /
• 2020

[^99mTc]Tc-Hexamethylpropylene amine oxime (HMPAO) is currently used as a regional cerebral blood flow imaging agent for single photon emission computed tomography (SPECT). The HMPAO ligand exists in two isomeric forms: d,l and meso showing different properties in vivo. Later studies indicated that brain uptake patterns of ^99mTc-complexes formed from separated enantiomers differed. Separation of enantiomers is difficult by fractional crystallizations method. Usually, the substance is obtained in low chemical yield in a time-consuming procedure. Furthermore, the final product still contains some impurity. So we have developed new efficient route for synthesis of R,R- and S,S-HMPAO enantiomeric compounds in 6-steps. Nucleophilic substitution (S_N2) reactions of 2,2-dimethylpropane-1,3-diamine either with S- (1a) or R-methyl2-chloropropanoate (1b) were performed to produce compounds R,R- (2a) or S,S-isomer (2b) derivatives protected with benzylchloroformate (Cbz), respectively. And then Weinreb amide and methylation reaction using Grignard reagent, oxime formation with ketone group and deprotectiion of Cbz group by hydrogenolysis gave S,S- (7a) or R,R-HMPAO (7b), respectively. Entaniomeric compounds were synthesied with high yield and purity without any undesired product. The 7a or 7b kits containing 10 ㎍ SnCl₂-2H₂O were labeled with ^99mTc with high radiolabeling yield (90%).

• Journal of Drive and Control
• /
• v.20 no.2
• /
• pp.15-23
• /
• 2023

In this study, two-dimensional location of crops for auto weeding was detected using deep learning. To construct a dataset for soybean detection, an image-capturing system was developed using a mono camera and single-board computer and the system was mounted on a weeding robot to collect soybean images. A dataset was constructed by extracting RoI (region of interest) from the raw image and each sample was labeled with soybean and the background for classification learning. The deep learning model consisted of four convolutional layers and was trained with a weakly supervised learning method that can provide object localization only using image-level labeling. Localization of the soybean area can be visualized via CAM and the two-dimensional position of the soybean was estimated by clustering the pixels associated with the soybean area and transforming the pixel coordinates to world coordinates. The actual position, which is determined manually as pixel coordinates in the image was evaluated and performances were 6.6(X-axis), 5.1(Y-axis) and 1.2(X-axis), 2.2(Y-axis) for MSE and RMSE about world coordinates, respectively. From the results, we confirmed that the center position of the soybean area derived through deep learning was sufficient for use in automatic weeding systems.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.607-610
• /
• 2021

When learning a model in supervised learning, input data and the label of the data are required. However, labeling is high cost task and if automated, there is no guarantee that the label will always be correct. In the case of supervised learning in such a noisy labels environment, the accuracy of the model increases at the initial stage of learning, but decrease significantly after a certain period of time. There are various methods to solve the noisy label problem. But in most cases, the probability predicted by the model is used as the pseudo label. So, we proposed a method to predict the true label more quickly by refining the probabilities predicted by the model. Result of experiments on the same environment and dataset, it was confirmed that the performance improved and converged faster. Through this, it can be applied to methods that use the probability distribution predicted by the model among existing studies. And it is possible to reduce the time required for learning because it can converge faster in the same environment.

• Journal of Korea Entertainment Industry Association
• /
• v.5 no.1
• /
• pp.127-133
• /
• 2011

Characters in natural image are an important information with various context. Previous work of character region detection algorithms is not detect of character region in case of image complexity and the surrounding lighting, similar background to character, so this paper propose an method of character region detection in natural image using edge and connected component by morphological reconstructions. Firstly, we detect edge using Canny-edge detector and connected component with local min/max value by morphological reconstructed-operation in gray-scale image, and labeling each of detected connected component elements. lastly, detected candidate of text regions was merged for generation for one candidate text region, Final text region detected by checking the similarity and adjacency of neighbor of text candidate individual character. As the results of experiments, proposed algorithm improved the correctness of character regions detection using edge and connected components.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.5
• /
• pp.315-321
• /
• 2023

Long-span bridges are flexible structures with low natural frequencies and damping ratios, making them susceptible to vibrational serviceability problems. However, the current design guideline of South Korea assumes a uniform threshold of wind speed or vibrational amplitude to assess the occurrence of harmful vibrations, potentially overlooking the complex vibrational patterns observed in long-span bridges. In this study, we propose a pointwise vortex-induced vibration (VIV) detection method using a deep-learning-based signalsegmentation model. Departing from conventional supervised methods of data acquisition and manual labeling, we synthesize training data by generating sinusoidal waves with an envelope to accurately represent VIV. A Fourier synchrosqueezed transform is leveraged to extract time-frequency features, which serve as input data for training a bidirectional long short-term memory model. The effectiveness of the model trained on synthetic VIV data is demonstrated through a comparison with its counterpart trained on manually labeled real datasets from an actual cable-supported bridge.

• Journal of the Microelectronics and Packaging Society
• /
• v.30 no.4
• /
• pp.69-78
• /
• 2023

With the rapid growth of artificial intelligence, the demand for semiconductors is enormously increasing everywhere. To ensure the manufacturing quality and quantity simultaneously, the importance of automatic defect detection during the packaging process has been re-visited by adapting various deep learning-based methodologies into automatic packaging defect inspection. Deep learning (DL) models require a large amount of data for training, but due to the nature of the semiconductor industry where security is important, sharing and labeling of relevant data is challenging, making it difficult for model training. In this study, we propose a new framework for securing sufficient data for DL models with fewer computing resources through a divide-and-conquer approach. The proposed method divides high-resolution images into pre-defined sub-regions and assigns conditional labels to each region, then trains individual sub-regions and boundaries with boundary loss inducing the globally coherent and seamless images. Afterwards, full-size image is reconstructed by combining divided sub-regions. The experimental results show that the images obtained through this research have high efficiency, consistency, quality, and generality.