• The Journal of Internal Korean Medicine
• /
• v.41 no.6
• /
• pp.993-1014
• /
• 2020

Objective: Parkinson's disease (PD) is the second most common neurodegenerative disease after Alzheimer's disease. Antioxidant stress and inflammatory reactions are important causes of neurodegenerative diseases and are major causes of PD. Many animal experiments have been aimed at treating PD using the antioxidant effects of various traditional medicines and dietary supplements. This review reports the research investigating the antioxidant effects of herbs in in vivo PD models. Methods: The study consisted of a database search for articles related to PD and herbal treatments using the OASIS, NDSL, KTKP, Korean KISS, PubMed, Science Direct, CNKI, Wanfang, and J-STAGE databases. The search period was limited from the start of the search engine application to November 14, 2019. Studies were selected to confirm the antioxidant effects of herbal medicines in an in vivo PD model. Results: Eighty-two studies were summarized for plant species, extracts (or compounds), animal models, neurotoxins, and functional results. The most frequently used herbal materials were Bacopa monnieri, Camellia sinensis, Centella asiatica, and Withania somnifera. MPTP and 6-OHDA were the most commonly used neurotoxins for inducing PD. Most studies confirmed an increased expression and activation of antioxidant enzymes and a decrease in oxidative stress. Herbal materials showed their antioxidant effects regardless of the order of treatment and confirmed their possible use as treatments for the prevention and treatment of neurodegeneration. Conclusion: Many herbal medicines have antioxidant effects and are likely to be effective in delaying neurodegenerative damage by inhibiting or reducing oxidative stress by expression of antioxidant enzymes.

• Journal of Broadcast Engineering
• /
• v.25 no.6
• /
• pp.854-860
• /
• 2020

Deep neural networks have shown remarkable performance in various areas, including image classification and speech recognition. The variety of data generated by augmentation plays an important role in improving the performance of the neural network. The transformation of data in the augmentation process makes it possible for neural networks to be learned more generally through more diverse forms. In the traditional field of image process, not only new augmentation methods have been proposed for improving the performance, but also exploring methods for an optimal augmentation policy that can be changed according to the dataset and structure of networks. Inspired by the prior work, this paper aims to explore to search for an optimal augmentation policy in the field of sound data. We carried out many experiments randomly combining various augmentation methods such as adding noise, pitch shift, or time stretch to empirically search which combination is most effective. As a result, by applying the optimal data augmentation policy we achieve the improved classification accuracy on the environmental sound classification dataset (ESC-50).

• Herbal Formula Science
• /
• v.29 no.1
• /
• pp.19-31
• /
• 2021

Objectives : The root of Salvia miltiorrhiza, known as 'Dansam (DS, 丹參)', is used for and treating cardiovascular diseases based on its efficacy of promoting blood circulation and breaking through a blood stasis. In this study, we would like to see if DS could be effectively used for stroke from the perspective of network pharmacology. Methods : The analysis was conducted using Traditional Chinese Medicine Systems Pharmacology Database and Analysis Platform (TCMSP) database to derive the main active compounds of DS and identify the mechanism of each compound acting on the human body. The networks between compounds, target protein and disease were expressed through Cytoscape. Protein-protein interaction (PPI) analysis was performed using STRING database. Results : Fifty two active compounds of DS were identified by screening the ingredients of DS through TCMSP. Based on the networks of these compounds with target protein and disease, it can be said that DS might be effective for preventing and treating stroke. PPI result showed that adrenergic receptor has many interactions among proteins, indicating its significance in stroke pathway. Conclusion : In this study, we derived target proteins and target diseases of DS that could be used in study of stroke. However, since it is uncertain if these targets can be controlled by DS extracts or not, we would like to confirm the results with further animal experiments.

• The Journal of Society for e-Business Studies
• /
• v.26 no.1
• /
• pp.127-140
• /
• 2021

Recently, sequence data containing time information, such as sensor measurement data and purchase history, has been generated in various applications. So far, many methods for finding sequences that are significantly different from other sequences among given sequences have been proposed. However, most of them have a limitation that they consider only the order of elements in the sequences. Therefore, in this paper, we propose a new anomalous sequence detection method that considers both the order of elements and the time interval between elements. The proposed method uses an extended LSTM autoencoder model, which has an additional layer that converts a sequence into a form that can help effectively learn both the order of elements and the time interval between elements. The proposed method learns the features of the given sequences with the extended LSTM autoencoder model, and then detects sequences that the model does not reconstruct well as anomalous sequences. Using experiments on synthetic data that contains both normal and anomalous sequences, we show that the proposed method achieves an accuracy close to 100% compared to the method that uses only the traditional LSTM autoencoder.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.1
• /
• pp.57-64
• /
• 2020

Recently, due to the proliferation of IoT sensors, the development of big data and artificial intelligence, time series prediction research on fine dust pollution is actively conducted. However, because the data representing fine dust contamination changes rapidly, traditional time series prediction methods do not provide a level of accuracy that can be used in the field. In this paper, we propose a method that reflects the classification results of environmental conditions through CNN when predicting micro dust contamination using LSTM. Although LSTM and CNN are independent, they are integrated into one network through the interface, so this method is easier to understand than the application LSTM. In the verification experiments of the proposed method using Beijing PM2.5 data, the prediction accuracy and predictive power for the timing of change were consistently improved in various experimental cases.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.1
• /
• pp.83-89
• /
• 2022

As a representative technique of recommender systems, collaborative filtering has been successfully in service through many commercial and academic systems. This technique recommends items highly rated by similar neighbor users, based on similarity of ratings on common items rated by two users. Recently research on time-aware recommender systems has been conducted, which attempts to improve system performance by reflecting user rating time of items. However, the decay rate uniform to past ratings has a risk of lowering the rating prediction performance of the system. This study proposes a rating time-aware similarity measure between users, which is a novel approach different from previous ones. The proposed approach considers changes of similarity value over time, not item rating time. In order to evaluate performance of the proposed method, experiments using various parameter values and types of time change functions are conducted, resulting in improving prediction accuracy of existing traditional similarity measures significantly.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.2
• /
• pp.10-16
• /
• 2022

As an important part of virtual production, In-camera VFX is the process of shooting actual objects and virtual three-dimensional backgrounds in real-time through computer graphics technology and display technology, and obtaining the final film. In the In-camera VFX process, there are currently only two types of medium used to undertake background imaging, LED wall and chroma key screen. Among them, the In-camera VFX based on LED wall realizes background imaging through LED display technology. Although the imaging quality is guaranteed, the high cost of LED wall increases the cost of virtual production. The In-camera VFX based on chroma key screen, the background imaging is realized by real-time keying technology. Although the price is low, due to the limitation of real-time keying technology and lighting conditions, the usability of the final picture is not high. The short-throw projection technology can compress the projection distance to within 1 meter and get a relatively large picture, which solves the problem of traditional projection technology that must leaving a certain space between screen and the projector, and its price is relatively cheap compared to the LED wall. Therefore, in the In-camera VFX process, short-throw projection technology can be tried to project backgrounds. This paper will analyze the principle of short-throw projection technology and the existing In-camera VFX solutions, and through the comparison experiments, propose a low-cost solution that uses short-throw projectors to project virtual backgrounds and realize the In-camera VFX process.

• Fisheries and Aquatic Sciences
• /
• v.25 no.5
• /
• pp.264-275
• /
• 2022

A non-destructive environmental DNA protocol for the genetic analysis of sea cucumber (Apostichopus japonicus) resources DNA was established. Among the several commercial DNA extraction kits, the DNeasy^® Plant Mini Kit was selected as the best choice to obtain the high-quality genomic DNAs from the mucous sea cucumber. As the temperature and incubation time increased, the amount of extracted environmental DNA was also large, but it was judged that the increased amount did not affect as much as 2-3 times. Therefore, these conditions were not considered to be the main factors to consider in actual environmental DNA extraction. However, the amount of seawater relative to the size of the sample was judged as a major consideration, and a sufficient amount of environmental DNA for analysis was secured when stored within 1 min while stirring the volume of seawater corresponding to the total sea cucumber weight (g). In securing the environmental DNA of sea cucumbers, the mortality rate of sea cucumbers in all experiments was 0, and it was judged that the effects of sea cucumbers were not significant through this treatment. Through the results of this study, sea cucumber DNA research, which has been conducted in a destructive method, can be conducted non-destructively through environmental DNA analysis. Through this study, we have secured a standard protocol that can successfully extract the sea cucumber DNA through environmental DNA. It is not only excellent in terms of time and cost of traditional DNA analysis method currently used, but it is completely non-destructive in the ecosystem of the survey area. It is believed that the system can be transformed in a way that does not affect it. However, it is thought that various standard protocols should be established considering the characteristics of each type.

• Electronics and Telecommunications Trends
• /
• v.36 no.2
• /
• pp.43-55
• /
• 2021

National and social issues are becoming increasingly common, but traditional policy-making methods are no longer effective. Therefore, evidence-based policy making is emerging as an alternative paradigm. Digital twin technology is one of the digital support tools for the new data-driven policy-making process. This study presents ongoing government experiments in the world where digital twin technology is applied to policy making and describes our experience in developing digital twin platforms in Sejong-the de facto administrative capital of South Korea.

• International Journal of Computer Science & Network Security
• /
• v.22 no.6
• /
• pp.230-240
• /
• 2022

Sharing of online videos via internet is an emerging and important concept in different types of applications like surveillance and video mobile search in different web related applications. So there is need to manage personalized web video retrieval system necessary to explore relevant videos and it helps to peoples who are searching for efficient video relates to specific big data content. To evaluate this process, attributes/features with reduction of dimensionality are computed from videos to explore discriminative aspects of scene in video based on shape, histogram, and texture, annotation of object, co-ordination, color and contour data. Dimensionality reduction is mainly depends on extraction of feature and selection of feature in multi labeled data retrieval from multimedia related data. Many of the researchers are implemented different techniques/approaches to reduce dimensionality based on visual features of video data. But all the techniques have disadvantages and advantages in reduction of dimensionality with advanced features in video retrieval. In this research, we present a Novel Intent based Dimension Reduction Semi-Supervised Learning Approach (NIDRSLA) that examine the reduction of dimensionality with explore exact and fast video retrieval based on different visual features. For dimensionality reduction, NIDRSLA learns the matrix of projection by increasing the dependence between enlarged data and projected space features. Proposed approach also addressed the aforementioned issue (i.e. Segmentation of video with frame selection using low level features and high level features) with efficient object annotation for video representation. Experiments performed on synthetic data set, it demonstrate the efficiency of proposed approach with traditional state-of-the-art video retrieval methodologies.