• Title/Summary/Keyword: Network loss

Search Result 2,304, Processing Time 0.026 seconds

A Prediction Model for Agricultural Products Price with LSTM Network (LSTM 네트워크를 활용한 농산물 가격 예측 모델)

  • Shin, Sungho;Lee, Mikyoung;Song, Sa-kwang
    • The Journal of the Korea Contents Association
    • /
    • v.18 no.11
    • /
    • pp.416-429
    • /
    • 2018
  • Typhoons and floods are natural disasters that occur frequently, and the damage resulting from these disasters must be in advance predicted to establish appropriate responses. Direct damages such as building collapse, human casualties, and loss of farms and fields have more attention from people than indirect damages such as increase of consumer prices. But indirect damages also need to be considered for living. The agricultural products are typical consumer items affected by typhoons and floods. Sudden, powerful typhoons are mostly accompanied by heavy rains and damage agricultural products; this increases the retail price of such products. This study analyzes the influence of natural disasters on the price of agricultural products by using a deep learning algorithm. We decided rice, onion, green onion, spinach, and zucchini as target agricultural products, and used data on variables that influence the price of agricultural products to create a model that predicts the price of agricultural products. The result shows that the model's accuracy was about 0.069 measured by RMSE, which means that it could explain the changes in agricultural product prices. The accurate prediction on the price of agricultural products can be utilized by the government to respond natural disasters by controling amount of supplying agricultural products.

The Development of Protocol for Construction of Smart Factory (스마트 팩토리 구축을 위한 프로토콜 개발)

  • Lee, Yong-Min;Lee, Won-Bog;Lee, Seung-Ho
    • Journal of IKEEE
    • /
    • v.23 no.3
    • /
    • pp.1096-1099
    • /
    • 2019
  • In this paper, we propose the protocol for construction of smart factory. The proposed protocol for construction of smart factory consists of an OPC UA Server/Client, a technology of TSN realtime communication, a NTP & PTP time synchronization protocol, a FieldBus protocol and conversion module, a technology of saving data for data transmit latency and synchronization protocol. OPC UA server/client is a system integration protocol which makes interface industrial hardware device and supports standardization which allows in all around area and also in not independent from any platform. A technology of TSN realtime communication provides an high sensitive time management and control technology in a way of sharing specific time between devices in the field of high speed network. NTP & PTP time synchronization protocol supports IEEE1588 standardization. A fieldbus protocol and conversion module provide an extendable connectivity by converting industrial protocol to OPC. A technology of saving data for data transmit latency and synchronization protocol provide a resolution function for a loss and latency of data. Results from testing agencies to assess the performance of proposed protocol for construction of smart factory, response time was 0.1367ms, synchronization time was 0.404ms, quantity of concurrent access was 100ea, quantity of interacting protocol was 5ea, data saving and synchronization was 1,000 nodes. It produced the same result as the world's highest level.

Direct and Indirect Costs of Chronic Obstructive Pulmonary Disease in Korea

  • Kim, Changhwan;Kim, Younhee;Yang, Dong-Wook;Rhee, Chin Kook;Kim, Sung Kyoung;Hwang, Yong-Il;Park, Yong Bum;Lee, Young Mok;Jin, Seonglim;Park, Jinkyeong;Hahm, Cho-Rom;Park, Chang-Han;Park, So Yeon;Jung, Cheol Kweon;Kim, Yu-Il;Lee, Sang Haak;Yoon, Hyoung Kyu;Lee, Jin Hwa;Lim, Seong Yong;Yoo, Kwang Ha
    • Tuberculosis and Respiratory Diseases
    • /
    • v.82 no.1
    • /
    • pp.27-34
    • /
    • 2019
  • Background: Understanding the burden of disease is important to establish cost-effective treatment strategies and to allocate healthcare resources appropriately. However, little reliable information is available regarding the overall economic burden imposed by chronic obstructive pulmonary disease (COPD) in Korea. Methods: This study is a multicenter observational research on the COPD burden in Korea. Total COPD costs were comprised of three categories: direct medical, direct non-medical, and indirect costs. For direct medical costs, institutional investigation was performed at 13 medical facilities mainly based on the claims data. For direct non-medical and indirect costs, site-based surveys were administered to the COPD patients during routine visits. Total costs were estimated using the COPD population defined in the recent report. Results: The estimated total costs were approximately 1,245 million US dollar (1,408 billion Korean won). Direct medical costs comprised approximately 20% of the total estimated costs. Of these, formal medical costs held more than 80%. As direct non-medical costs, nursing costs made up the largest percentage (39%) of the total estimated costs. Costs for COPD-related loss of productivity formed four fifths of indirect costs, and accounted for up to 33% of the total costs. Conclusion: This study shows for the first time the direct and indirect costs of COPD in Korea. The total costs were enormous, and the costs of nursing and lost productivity comprised approximately 70% of total costs. The results provide insight for an effective allocation of healthcare resources and to inform establishment of strategies to reduce national burden of COPD.

Analysis of Power System Stability by Deployment of Renewable Energy Resources (재생에너지원 보급에 따른 전력계통 안정도 분석)

  • Kwak, Eun-Sup;Moon, Chae-Joo
    • The Journal of the Korea institute of electronic communication sciences
    • /
    • v.16 no.4
    • /
    • pp.633-642
    • /
    • 2021
  • Growing demand for electricity, when combined with the need to limit carbon emissions, drives a huge increase in renewable energy industry. In the electric power system, electricity supply always needs to be balanced with electricity demand and network losses to maintain safe, dependable, and stable system operation. There are three broad challenges when it comes to a power system with a high penetration of renewable energy: transient stability, small signal stability, and frequency stability. Transient stability analyze the system response to disturbances such as the loss of generation, line-switching operations, faults, and sudden load changes in the first several seconds following the disturbance. Small signal stability refers to the system's ability to maintain synchronization between generators and steady voltages when it is subjected to small perturbations such as incremental changes in system load. Frequency stability refers to the ability of a power system to maintain steady frequency following a severe system upset resulting in significant imbalance between generation and load. In this paper, we discusses these stability using system simulation by renewable energy deployment plan, and also analyses the influence of the renewable energy sources to the grid stability.

A Study on the Awareness and Preparation of the Forth Industrial Revolution of Some Health Department College Students (일부 보건계열학과 대학생의 4차 산업혁명 인식 및 준비도 연구)

  • Cho, Hye-Eun
    • Journal of the Korea Convergence Society
    • /
    • v.11 no.12
    • /
    • pp.291-299
    • /
    • 2020
  • The purpose of this study was to be used as basic data for the development of future-type curriculum in health. The awareness and preparation of the forth industrial revolution were surveyed on 280 college students in health departments preparing medical technicians. A self-written structured questionnaire was used for data collection, and the recognition of the forth industry revolution was 2.74, 3D printing (3.59) was high, and neural network machine learning(2.33) was the lowest. Students majoring in Physiotherapy (3.00) had the highest perception, and those majored in Dental engineering(2.37) had the lowest perception, and there was a difference in the degree of perception of IoT by major (p=0.024). For the forth industrial revolution, 54.5% of students are preparing, and lack of interest (42.9%) is the most difficult reason to prepare, and 50.6% of educational experience and 60.9% of VR&AR game experience have experience. In the era of the forth industrial revolution, job loss (38.7%) was high, and the required competency was creative capacity (50.6%). Therefore, it is necessary to develop a curriculum related to the fourth industrial revolution and apply teaching methods that can increase the awareness and preparation of health college students in the era of the fourth industrial revolution.

A Study on the Changes in Korean Ocean Carriers' Financial Ratios and Profitability Before and After the Bankruptcy of the H-Line Carrier (H선사 파산전후 국적외항선사의 재무비율 차이분석과 영향요인 연구)

  • Kim, Myung-Jae;Ahn, Ki-Myung
    • Journal of Navigation and Port Research
    • /
    • v.44 no.6
    • /
    • pp.541-549
    • /
    • 2020
  • This study conducts differential analysis on the financial positions of Korean shipping companies before and after the bankruptcy of the H carrier, looking specifically at their financial ratios, profit and loss patterns, and other factors related to their financial operation. Firstly, it was discovered that major measures of financial health, such as average assets per carrier, were not affected by the bankruptcy of the H carrier. However, despite this, most carriers experienced large changes in profits and losses, with total sales and shipping revenues averaging 424.5 billion won and 381.7 billion won respectively before the bankruptcy, but falling by half to 252.1 billion won and 234.6 billion won after the bankruptcy. Additionally, charter revenues and expenses also dropped by more than half. EBIT/sales and pre-tax revenue margins were also heavily affected after the bankruptcy, with both figures averaging 8% and 3% respectively before the bankruptcy, but falling into the negative range at -2% and -8% post-bankruptcy, resulting in significant deterioration in operational profitability. The study concludes that there is an urgent need to establish a global sales network, improve cost structures, and consistently secure stable cargo in order to increase Korean carriers' profitability. Of all financial measures, liquidity and total asset efficiency were identified as the most severely-impacted by the H carrier bankruptcy, thereby requiring the most pressing policy addressing.

A Multi-Dimensional Node Pairing Scheme for NOMA in Underwater Acoustic Sensor Networks (수중 음향 센서 네트워크에서 비직교 다중 접속을 위한 다차원 노드 페어링 기법)

  • Cheon, Jinyong;Cho, Ho-Shin
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.22 no.6
    • /
    • pp.1-10
    • /
    • 2021
  • The interest in underwater acoustic sensor networks (UWASNs), along with the rapid development of underwater industries, has increased. To operate UWASNs efficiently, it is important to adopt well-designed medium access control (MAC) protocols that prevent collisions and allow the sharing of resources between nodes efficiently. On the other hand, underwater channels suffer from a narrow bandwidth, long propagation delay, and low data rate, so existing terrestrial node pairing schemes for non orthogonal multiple access (NOMA) cannot be applied directly to underwater environments. Therefore, a multi-dimensional node pairing scheme is proposed to consider the unique underwater channel in UWASNs. Conventional NOMA schemes have considered the channel quality only in node pairing. Unlike previous schemes, the proposed scheme considers the channel gain and many other features, such as node fairness, traffic load, and the age of data packets to find the best node-pair. In addition, the sender employs a list of candidates for node-pairs rather than path loss to reduce the computational complexity. The simulation results showed that the proposed scheme outperforms the conventional scheme by considering the fairness factor with 23.8% increases in throughput, 28% decreases in latency, and 5.7% improvements in fairness at best.

Ginseng gintonin alleviates neurological symptoms in the G93A-SOD1 transgenic mouse model of amyotrophic lateral sclerosis through lysophosphatidic acid 1 receptor

  • Nam, Sung Min;Choi, Jong Hee;Choi, Sun-Hye;Cho, Hee-Jung;Cho, Yeon-Jin;Rhim, Hyewhon;Kim, Hyoung-Chun;Cho, Ik-Hyun;Kim, Do-Geun;Nah, Seung-Yeol
    • Journal of Ginseng Research
    • /
    • v.45 no.3
    • /
    • pp.390-400
    • /
    • 2021
  • Background: We recently showed that gintonin, an active ginseng ingredient, exhibits antibrain neurodegenerative disease effects including multiple target mechanisms such as antioxidative stress and antiinflammation via the lysophosphatidic acid (LPA) receptors. Amyotrophic lateral sclerosis (ALS) is a spinal disease characterized by neurodegenerative changes in motor neurons with subsequent skeletal muscle paralysis and death. However, pathophysiological mechanisms of ALS are still elusive, and therapeutic drugs have not yet been developed. We investigate the putative alleviating effects of gintonin in ALS. Methods: The G93A-SOD1 transgenic mouse ALS model was used. Gintonin (50 or 100 mg/kg/day, p.o.) administration started from week seven. We performed histological analyses, immunoblot assays, and behavioral tests. Results: Gintonin extended mouse survival and relieved motor dysfunctions. Histological analyses of spinal cords revealed that gintonin increased the survival of motor neurons, expression of brain-derived neurotrophic factors, choline acetyltransferase, NeuN, and Nissl bodies compared with the vehicle control. Gintonin attenuated elevated spinal NAD(P) quinone oxidoreductase 1 expression and decreased oxidative stress-related ferritin, ionized calcium-binding adapter molecule 1-immunoreactive microglia, S100β-immunoreactive astrocyte, and Olig2-immunoreactive oligodendrocytes compared with the control vehicle. Interestingly, we found that the spinal LPA1 receptor level was decreased, whereas gintonin treatment restored decreased LPA1 receptor expression levels in the G93A-SOD1 transgenic mouse, thereby attenuating neurological symptoms and histological deficits. Conclusion: Gintonin-mediated symptomatic improvements of ALS might be associated with the attenuations of neuronal loss and oxidative stress via the spinal LPA1 receptor regulations. The present results suggest that the spinal LPA1 receptor is engaged in ALS, and gintonin may be useful for relieving ALS symptoms.

The Effect of Social Capital of Baby Boomers on Practical Well-Being Focused on the Modulating Effect of Psychological Identity (베이비붐 세대의 사회적 자본이 실제적 안녕감에 미치는 영향 심리적 정체성의 조절 효과를 중심으로)

  • Park, Seoung-Tag
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.22 no.1
    • /
    • pp.345-353
    • /
    • 2021
  • This study examined the effects of social capital on psychological identity and practical wellbeing for the Korean baby boom generation. To achieve this, an empirical survey was carried out on baby boomers who use elderly welfare centers and cultural centers living in D City. The overall research results showed that trust (t=6.893, p<.05), participation (t=5.157, p<.05), network (t=8.093, p<.05), and norm and reciprocity (t=4.787, p<.05), as sub-factors of social capital for baby boomers, had a significant effect on their practical wellbeing. Psychological identity was moderated (t=2.023, p<.05) in the effect of trust on practical wellbeing, adopting the hypothesis. This means that the social ties and the strong trust relationship between family members and relatives, which built up amid rapid economic growth, work with positive expectations of social capital and have a major effect on practical wellbeing. Moreover, practical welling also rated high, along with the high trust relationship and psychological identity. Consequently, various exchange programs and group and volunteer activity programs for baby boomers should be established to decrease their psychological identity due to the loss of social roles. Moreover, the decline of activities at a time of retirement can slow practical wellbeing.

Comparative Analysis by Batch Size when Diagnosing Pneumonia on Chest X-Ray Image using Xception Modeling (Xception 모델링을 이용한 흉부 X선 영상 폐렴(pneumonia) 진단 시 배치 사이즈별 비교 분석)

  • Kim, Ji-Yul;Ye, Soo-Young
    • Journal of the Korean Society of Radiology
    • /
    • v.15 no.4
    • /
    • pp.547-554
    • /
    • 2021
  • In order to quickly and accurately diagnose pneumonia on a chest X-ray image, different batch sizes of 4, 8, 16, and 32 were applied to the same Xception deep learning model, and modeling was performed 3 times, respectively. As a result of the performance evaluation of deep learning modeling, in the case of modeling to which batch size 32 was applied, the results of accuracy, loss function value, mean square error, and learning time per epoch showed the best results. And in the accuracy evaluation of the Test Metric, the modeling applied with batch size 8 showed the best results, and the precision evaluation showed excellent results in all batch sizes. In the recall evaluation, modeling applied with batch size 16 showed the best results, and for F1-score, modeling applied with batch size 16 showed the best results. And the AUC score evaluation was the same for all batch sizes. Based on these results, deep learning modeling with batch size 32 showed high accuracy, stable artificial neural network learning, and excellent speed. It is thought that accurate and rapid lesion detection will be possible if a batch size of 32 is applied in an automatic diagnosis study for feature extraction and classification of pneumonia in chest X-ray images using deep learning in the future.