• 한국컴퓨터정보학회논문지
• /
• 제26권3호
• /
• pp.1-7
• /
• 2021

본 논문에서는 Hybrid CDN/P2P 구조를 기반으로 최적화된 미디어 데이터 탐색과 전송을 수행하며 사용자의 요청 가능성 예측을 통한 선별적 저장을 통해 사용자로의 끊김없는 데이터 전송과 불필요한 트래픽의 감소를 가능하게 한다. 또한 전송지연 및 패킷 손실의 가능성을 최소화하여 실시간으로 미디어를 활용할 수 있도록 하는 새로운 미디어 관리 기법을 제안한다. 이를 위해 각 미디어를 논리적인 세그먼트로 나누어 구성하고 각 세그먼트에 대한 가중치를 지속적으로 계산하며 계산된 가중치에 따라 세그먼트 데이터의 저장 여부를 결정하도록 한다. 또한 네트워크상에 산재되어 있는 컴퓨팅 노드들을 거리에 따라 지역적 그룹으로 지정하고 해당 그룹 내에서 저장 공간을 효율적으로 공유하고 활용하도록 한다. 제안하는 기법의 효율성을 검증하기 위해 수행된 실험을 통해 제안하는 방식이 기존의 방법들에 비해 비교적 좋은 성능 평가가 도출되는 것을 확인하였으며 이는 전송과정에서 발생되는 초기 지연시간 감소와 끊김 없는 전송 모두를 가능하게 할 수 있음을 알 수 있다.

• International Journal of Knowledge Content Development & Technology
• /
• 제10권4호
• /
• pp.29-46
• /
• 2020

The paper describes the quantitative and qualitative dimensions of artificial neural networks (ANN) in India in the global context. The study is based on research publications data (8260) as covered in the Scopus database during 1999-2018. ANN research in India registered 24.52% growth, averaged 11.95 citations per paper, and contributed 9.77% share to the global ANN research. ANN research is skewed as the top 10 countries account for 75.15% of global output. India ranks as the third most productive country in the world. The distribution of research by type of ANN networks reveals that Feed Forward Neural Network type accounted for the highest share (10.18% share), followed by Adaptive Weight Neural Network (5.38% share), Feed Backward Neural Network (2.54% share), etc. ANN research applications across subjects were the largest in medical science and environmental science (11.82% and 10.84% share respectively), followed by materials science, energy, chemical engineering and water resources (from 6.36% to 9.12%), etc. The Indian Institute of Technology, Kharagpur and the Indian Institute of Technology, Roorkee lead the country as the most productive organizations (with 289 and 264 papers). Besides, the Indian Institute of Technology, Kanpur (33.04 and 2.76) and Indian Institute of Technology, Madras (24.26 and 2.03) lead the country as the most impactful organizations in terms of citation per paper and relative citation index. P. Samui and T.N. Singh have been the most productive authors and G.P.S.Raghava (86.21 and 7.21) and K.P. Sudheer (84.88 and 7.1) have been the most impactful authors. Neurocomputing, International Journal of Applied Engineering Research and Applied Soft Computing topped the list of most productive journals.

• 한국수자원학회논문집
• /
• 제55권1호
• /
• pp.11-21
• /
• 2022

지난 2019년 말 발생한 COVID-19는 2020년을 기점으로 국내에 본격적으로 확산되기 시작하여, 사회 전반에 커다란 영향을 미치고 있다. COVID-19 확산을 억제하기 위한 방역수칙들은 인간 생활에 많은 변화를 가져왔으며, 사회적 거리두기 등 사회활동 제한에 따른 다양한 영향이 사회 전반에 걸쳐 나타나고 있다. 본 연구에서는 물 분야 COVID-19 위기 대응의 일환으로, COVID-19 확산에 따른 국내 상수도 사용량 변화를 분석하고, 상수도 사용량의 변화가 공급 서비스에 미치는 위협을 알아보고자 하였다. 국내 중소규모 도시인 S시 주거지역을 대상으로 COVID-19 확산 전후 일정기간 동안의 1시간 단위 용수 사용량 자료를 수집하였으며, 먼저 수집 데이터를 분석 목적에 따라 정제하고 전체 용수 사용량의 변화 및 사용 비중 변화, 그리고 시간별 용수 사용 패턴 변화 등을 분석하였다. 분석 결과, 가정용수 및 영업용수 사용량 및 이용패턴이 COVID-19 확산 이후 뚜렷한 변화를 보였으며, 일부 사용량 변화는 상수도 운영관리 차원에서의 검토가 필요한 것으로 나타났다.

• 대한한의학방제학회지
• /
• 제31권1호
• /
• pp.21-28
• /
• 2023

Objective : Scolopendra, a dried body of Scolopendra subspinipes mutilans, is one of Korean medicine. Several reports revealed that Scolopendra has therapeutic effects for arthritis, neuroinflammatory diseases and neuropathic pain. However, the fetal adaptive response or teratogenicity associated with administration of Scolopendra is unclear. Therefore, this study aimed to investigate the fetal toxicity effects that were induced following oral administration of Scolopendra water extract (SWE) in pregnant mice. Methods : The pregnant mice were administrated SWE at dosed of 0, 100, 500 and 1000 mg/kg/day during gestation day 0-18. The mortality, body weight and clinical signs of pregnant mice were observed throughout experimental period. Also, the mortality and malformations in foetus were examined. Results : No meaningful changes were observed in the mortality and clinical signs of pregnant mice between the normal control group and SWE administrated groups. Additionally, there are no significant changes in fetal mortalities, and malformations by SWE administration. conclusion : These results suggest that oral exposure to SWE during pregnancy at oral dosages up to 1000 mg/kg/day did not induce teratogenic toxicity in regard to fetal mortality and morphology.

• Geomechanics and Engineering
• /
• 제33권3호
• /
• pp.279-289
• /
• 2023

Brittleness index (BI) is an important property of rocks because it is a good index to predict rockburst. Due to its importance, several empirical and soft computing (SC) models have been proposed in the literature based on the punch penetration test (PPT) results. These models are very important as there is no clear-cut experimental means for measuring BI asides the PPT which is very costly and time consuming to perform. This study used a novel Multivariate Adaptive regression spline (MARS), M5P, and white-box ANN to predict the BI of rocks using the available data in the literature for an improved BI prediction. The rock density, uniaxial compressive strength (σ_c) and tensile strength (σ_t) were used as the input parameters into the models while the BI was the targeted output. The models were implemented in the MATLAB software. The results of the proposed models were compared with those from existing multilinear regression, linear and nonlinear particle swarm optimization (PSO) and genetic algorithm (GA) based models using similar datasets. The coefficient of determination (R²), adjusted R² (Adj R²), root-mean squared error (RMSE) and mean absolute percentage error (MAPE) were the indices used for the comparison. The outcomes of the comparison revealed that the proposed ANN and MARS models performed better than the other models with R² and Adj R² values above 0.9 and least error values while the M5P gave similar performance to those of the existing models. Weight partitioning method was also used to examine the percentage contribution of model predictors to the predicted BI and tensile strength was found to have the highest influence on the predicted BI.

• Geomechanics and Engineering
• /
• 제31권2호
• /
• pp.129-147
• /
• 2022

The properties of soil are naturally highly variable and thus, to ensure proper safety and reliability, we need to test a large number of samples across the length and depth. In pile foundations, conducting field tests are highly expensive and the traditional empirical relations too have been proven to be poor in performance. The study proposes a state-of-art Particle Swarm Optimization (PSO) hybridized Artificial Neural Network (ANN), Extreme Learning Machine (ELM) and Adaptive Neuro Fuzzy Inference System (ANFIS); and comparative analysis of metaheuristic models (ANN-PSO, ELM-PSO, ANFIS-PSO) for prediction of bearing capacity of pile foundation trained and tested on dataset of nearly 300 dynamic pile tests from the literature. A novel ensemble model of three hybrid models is constructed to combine and enhance the predictions of the individual models effectively. The authenticity of the dataset is confirmed using descriptive statistics, correlation matrix and sensitivity analysis. Ram weight and diameter of pile are found to be most influential input parameter. The comparative analysis reveals that ANFIS-PSO is the best performing model in testing phase (R² = 0.85, RMSE = 0.01) while ELM-PSO performs best in training phase (R² = 0.88, RMSE = 0.08); while the ensemble provided overall best performance based on the rank score. The performance of ANN-PSO is least satisfactory compared to the other two models. The findings were confirmed using Taylor diagram, error matrix and uncertainty analysis. Based on the results ELM-PSO and ANFIS-PSO is proposed to be used for the prediction of bearing capacity of piles and ensemble learning method of joining the outputs of individual models should be encouraged. The study possesses the potential to assist geotechnical engineers in the design phase of civil engineering projects.

• Steel and Composite Structures
• /
• 제51권1호
• /
• pp.25-41
• /
• 2024

The measurement of pile bearing capacity is crucial for the design of pile foundations, where in-situ tests could be costly and time needed. The primary objective of this research was to investigate the potential use of fuzzy-based techniques to anticipate the maximum weight that concrete driven piles might bear. Despite the existence of several suggested designs, there is a scarcity of specialized studies on the exploration of adaptive neuro-fuzzy inference systems (ANFIS) for the estimation of pile bearing capacity. This paper presents the introduction and validation of a novel technique that integrates the fire hawk optimizer (FHO) and equilibrium optimizer (EO) with the ANFIS, referred to as ANFIS_FHO and ANFIS_EO, respectively. A comprehensive compilation of 472 static load test results for driven piles was located within the database. The recommended framework was built, validated, and tested using the training set (70%), validation set (15%), and testing set (15%) of the dataset, accordingly. Moreover, the sensitivity analysis is performed in order to determine the impact of each input on the output. The results show that ANFIS_FHO and ANFIS_EO both have amazing potential for precisely calculating pile bearing capacity. The R² values obtained for ANFIS_FHO were 0.9817, 0.9753, and 0.9823 for the training, validating, and testing phases. The findings of the examination of uncertainty showed that the ANFIS_FHO system had less uncertainty than the ANFIS_EO model. The research found that the ANFIS_FHO model provides a more satisfactory estimation of the bearing capacity of concrete driven piles when considering various performance evaluations and comparing it with existing literature.

• 대한수의학회지
• /
• 제1권1호
• /
• pp.1-29
• /
• 1961

A routine hematological observation in the course of starvation was carried out on eight experimentel1y starved rabbits. They were strictly selected and restricted all of food intake with the exception of optional water intake until death. The body weight of each rabbit on the day before starvation was about 2 kilograms. The results are summarized as follows. 1. The average decrememt ratio of body weight on the terminal day before death was $34.3{\pm}7.5$ per cent with the range from 24.5 to 46.3 per cent. The average life duration until death was $10.25{\pm}2.6$ days, the range being from 6 to 14 days. 2. The decrease in number of reticulocytes with a parallel disappearance of polychromatic erythrocytes in peripheral blood in the course of starvation Was the most remarkable change in erythrocytic series, an evidence suggesting marked restriction of the erythropoietic function on 3rd to 4th day and almost complete suspension in about a week of starvation. 3. Erythrocyte count, hemoglobin content and haematocrit value of peripheral blood, were normal or indicative of slight hemoconcentration. 4. Mean Corpuscular Hemogloin Concentration was slightly higher than normal and Mean Corpuscular Volume tended to be low and no appreciable shifts were observed in Mean Corpuscular Diameter and Price-Jones curve of erythrocytes, while fewer macrocytes than normal were seen. These changes were considered to have resulted from a marked decrease in young erythrocytes in peripheral blood in the course of starvation. 5. Neither poikilccytoses or anisosytosis was observed. 6. Leukopenia was observed in all of 8 starved rabbits. The decrement ratio on the terminal day of starvation was between 13 to 64 per cent. The leukopenia was mainly due to fall of lymphocytes in 6 cases and to fall of neutrophilic leukocytes in the other 2 cases. In many cases, irregular fluctuation of neutrophilic leukocytes in its biological curve were seen in contrast to the relatively smooth changes of lymphocytes. Eosinophilic leukocytes tended to decrease in absolute number especially in later stage of starvation. Little significance in regard to monocytes and basophilic leukocytes in this study was discussed. 7. Proplasma cells, rarely plasma cells, appeared with a tendency to increase in number at later stage of starvation. 8. The most characteristic changes on circulating blood cells in complete starvation of rabbits were the leukoponia and failure of regeneration of erythroctes. These changes were considered as adaptive phenomena in response to the catabolic consumption of body constituents.

• 지능정보연구
• /
• 제20권3호
• /
• pp.1-18
• /
• 2014

RFID는 유비쿼터스 환경의 다양한 응용분야에서 기본적인 기술로 사용되어 왔다. 특히, 사물 인터넷을 위한 향후 RFID 기술의 폭 넓은 활용의 장애물중의 하나는 태그 리더기에 의한 RFID 데이터의 근본적인 비 신뢰성이다. 특히, 읽기 손실과 잘못된 읽기 같은 읽기오류 문제는 RFID 시스템이 적절히 처리해야 할 필요가 있다. 왜냐하면, 미들웨어 시스템이 전달한 오류 데이터는 궁극적으로 응용 서비스의 품질을 저하시킬 수 있기 때문이다. 따라서 높은 품질의 서비스를 위해서 지능형 RFID 미들웨어 시스템은 응용에 깨끗한 데이터를 전달하기 위해 읽기오류를 상황에 따라 적절하게 처리하여야 한다. 읽기 오류를 해결하기 위한 보편적인 방법 중의 하나는 슬라이딩 윈도우 필터의 사용이다. 따라서 최적의 윈도우 크기를 결정하는 것은 특히 모바일 환경에서는 읽기 오류를 줄이기 위해 쉽지 않은 중요한 일이다. 본 논문에서는 지능형 윈도우 크기 조정을 통해 읽기 오류를 줄이기 위하여 단일 태그를 위한 RFID 데이터 정제 방안을 제안한다. 이항 샘플링을 기반으로 한 기존 연구와 달리, 본 논문에서는 가중치 평균을 사용한다. 이는 최근의 읽기가 더 정확한 현재의 태그 전이를 나타낼 수 있으므로 과거와 현재의 읽기를 차별화하는 일이 필요하다는 것에 기반을 두고 있다. 가중치 평균을 사용하므로 이질적인 읽기 패턴을 갖는 모바일 환경에서도 효율적으로 적응하여 윈도우 크기를 동적으로 조정할 수 있게 된다. 뿐만 아니라, 윈도우 내의 읽음 패턴과 감소되는 윈도우 크기의 효과를 분석함으로서 더욱 효율적이고 정확한 크기 조정 결정을 할 수 있도록 한다. 제안한 방안을 사용하면 RFID 미들웨어 시스템이 응용에 좀 더 정확하고 무결점의 데이터를 제공함으로써 본래의 응용 서비스 품질을 보장할 수 있도록 한다는 궁극적인 목적을 달성할 수 있을 것으로 기대한다.

• 대한의용생체공학회:의공학회지
• /
• 제23권3호
• /
• pp.253-261
• /
• 2002

양전자방출단층촬영기(Positron emission tomography, PET) 영상 개선을 위하여 적응적 공간 필터를 개발하였으며. 개발한 필터의 성능을 시뮬레이션데이터. 모형 PET 영상과 환자 PET 영상을 이용하여 평가하였다. 경계화소로 검출된 화소와 윈도우내의 모든 화소값이 동일한 화소는 보존하고. 그 외 화소에 대하여 2:7:2 비율로 가중치를 주어 정열한 후 중앙의 9개 화소에 대한 평균값으로 대치하였다. 경계화소를 검출하기 위하여 두 개의 임계값(TH7, TH2)을 이용하였으며. 다음의 조건을 만족하면 경계화소로 판단하였다 . THl ($pix_max{\times}0.1/log_2(NPM)$, NPM :주변값중 최상위 값과 최하위 값을 제외한 주변값들의 평균) 보다 작은 ADs (중앙값과 주변값의 차에 대한 절대값) 개수는 8-k이고. TH2 ($NPM{\times}0.1$) 보다 큰 ADs 개수는 k. 여기서 k는 2, 3 ‥‥ 6의 값을 가진다 성능평가 결과 이 연구에서 제안한 필터가 가우시안 필터, 가중메디안 필터, 부분집합평균메디안 필터 등과 비교하여 우수한 성능을 제공하는 것을 관찰하였다. 본 논문에서 개발한 간단한 적응적 공간 필터는 공간 분해능 저하는 최소화하면서 균일도와 대조도를 향상시키는데 효과적 이여서 정확한 PET 영상 해석에 기여할 것으로 기대된다