http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
구조물의 동적 거동예측을 위한 다층퍼셉트론 최적화 방법
타비시알리 ( Tabish Ali ),김은주 ( Kim Robin Eunju ) 한국구조물진단유지관리공학회 2021 한국구조물진단유지관리공학회 학술발표대회 논문집 Vol.25 No.1
The use of Artificial Intelligence (AI) to predict the behavior of any system is common these days. Use of the technology may be economical in terms of both time and cost. The database methods are robust and reliable. The current study is about the application of AI for predicting the dynamic responses of steel frame buildings. To obtain an optimized AI method, different multi-layer perceptron were trained and tested by varying the hyperparameters like number of nodes, layers, algorithms and functions. A multilayer perceptron with 2 hidden layers and 10 nodes showed the most accurate results in terms of regression and root mean square error.
구조물의 동적 거동예측을 위한 다층퍼셉트론 최적화 방법
타비시알리 ( Tabish Ali ),김은주 ( Kim Robin Eunju ) 한국구조물진단유지관리공학회 2021 한국구조물진단유지관리공학회 학술발표대회 논문집 Vol.25 No.1
The use of Artificial Intelligence (AI) to predict the behavior of any system is common these days. Use of the technology may be economical in terms of both time and cost. The database methods are robust and reliable. The current study is about the application of AI for predicting the dynamic responses of steel frame buildings. To obtain an optimized AI method, different multi-layer perceptron were trained and tested by varying the hyperparameters like number of nodes, layers, algorithms and functions. A multilayer perceptron with 2 hidden layers and 10 nodes showed the most accurate results in terms of regression and root mean square error.
지진 상호작용을 고려한 소음 장벽 평가를 위한 기계 학습 프레임워크
알리타비시 ( Ali Tabish ),김은주 ( Kim Robin E. ) 한국구조물진단유지관리공학회 2021 한국구조물진단유지관리공학회 학술발표대회 논문집 Vol.25 No.2
The effectiveness of Noise Barrier (NB) depends on the material and height etc. of the structure. A lot of research has been done on the material of the NB. However, a very little literature is available considering the design and safety of these structures considering the earthquakes. The design guides focus a little on the seismic design and leave it on the engineer’s intuition. Furthermore, in the design of NBs on the bridge structures, the interaction between the NB and bridge is totally ignored. To over come the mentioned research needs, a next generation computer aided framework is proposed to assess the design type and predict the seismic responses of NBs.
Variation of Pull-out Resistance of Geogrid with Degree of Saturation of Soil
Chungsik Yoo,TABISH ALI 한국지반신소재학회 2020 한국지반신소재학회 논문집 Vol.19 No.1
This paper presents the results of experimental investigation on the effect of degree of saturation of soil on the pullout behavior of a geogrid. Different test variables were taken into account while performing the experiment including the soil physical conditions based on water content and external loading applied. The soil used was locally available weathered granite soil. The tests included variations in saturation of about 90%, 80%, 70% and 45% (optimum moisture content). The pullout tests were performed according to ASTM standard D 6706-01. The results indicate that increasing the degree of saturation in the soil decreases the pull-out capacity, which in turn decreases the interface friction angle and interaction coefficient. The decrease in the pullout interface coefficient was observed to be around 12.50% to 33.33% depending on the normal load and degree of saturation of the soil. The test results demonstrated the detrimental effect of increasing the degree of saturation within the reinforce soil on the pullout behavior of reinforcement, thus on the internal stability. The practical inferences of the outcomes are analyzed in detail.
Biocompatibility of cobalt iron oxide magnetic nanoparticles in male rabbits
Furhan Iqbal,Tanveer Ahmad Tabish,Muhammad Naeem Ashiq,Muhammad Azeem Ullah,Shahid Iqbal,Muhammad Latif,Muhammad Ali,Muhammad Fahad Ehsan 한국화학공학회 2016 Korean Journal of Chemical Engineering Vol.33 No.7
Present study was conducted to study the in vivo biocompatibility of cobalt iron oxide magnetic nano-particles (CoFe2O4 MNPs) in rabbits. CoFe2O4 MNPs were synthesized by the conventional micro emulsion technique in crystallite size range of 30 to 50 nm. The lattice constant (a) and cell volume were found to be 8.386 Å and 589.75 Å3, respectively, revealed by XRD. Subject animals were divided in three groups--low dose, high dose and control group without nanoparticles implantation for biocompatibility evaluation. CoFe2O4 was intraperitoneally implanted in rabbits: low dose (1mg CoFe2O4/Kg body weight) and high dose (10mg CoFe2O4/Kg body weight). Blood, serum and histological study of vital organs (liver, heart, kidney and spleen) were carried out in seven days of time protocol after sacrificing of animals. Results indicated that CoFe2O4 had drastically affected the blood chemistry in a dose-dependent manner as RDWa (P=0.01), Platelet (P<0.001) and Plateletcrit (P<0.001) concentrations reduced significantly in low dose and high dose CoFe2O4 treatments as compared to sham treated control group. Histological analysis revealed that CoFe2O4 exposure resulted in disordered and abnormal histology of liver, kidney and that of muscles at surgical site. It is concluded that CoFe2O4 has low biocompatibility and higher toxicity levels in living system at the applied doses.
Development of AI-based Prediction and Assessment Program for Tunnelling Impact
Yoo, Chungsik,HAIDER, SYED AIZAZ,Yang, Jaewon,ALI, TABISH Korean Geosynthetics Society 2019 한국지반신소재학회 논문집 Vol.18 No.4
In this paper the development and implementation of an artificial intelligence (AI)-based Tunnelling Impact prediction and assessment program (SKKU-iTunnel) is presented. Program predicts tunnelling induced surface settlement and groundwater drawdown by utilizing well trained ANNs and uses these predicted values to perform the damage assessment likely to occur in nearby structures and pipelines/utilities for a given tunnel problem. Generalised artificial neural networks (ANNs) were trained, to predict the induced parameters, through databases generated by combining real field data and numerical analysis for cases that represented real field conditions. It is shown that program equipped with carefully trained ANN can predict tunnel impact assessments and perform damage assessments quiet efficiently and comparable accuracy to that of numerical analysis. This paper describes the idea and implementation details of the SKKU-iTunnel with an example for demonstration.
Development of AI-based Prediction and Assessment Program for Tunnelling Impact
유충식,SYED AIZAZ HAIDER2,양재원,TABISH ALI 한국지반신소재학회 2019 한국지반신소재학회 논문집 Vol.18 No.4
In this paper the development and implementation of an artificial intelligence (AI)-based Tunnelling Impact prediction and assessment program (SKKU-iTunnel) is presented. Program predicts tunnelling induced surface settlement and groundwater drawdown by utilizing well trained ANNs and uses these predicted values to perform the damage assessment likely to occur in nearby structures and pipelines/utilities for a given tunnel problem. Generalised artificial neural networks (ANNs) were trained, to predict the induced parameters, through databases generated by combining real field data and numerical analysis for cases that represented real field conditions. It is shown that program equipped with carefully trained ANN can predict tunnel impact assessments and perform damage assessments quiet efficiently and comparable accuracy to that of numerical analysis. This paper describes the idea and implementation details of the SKKU-iTunnel with an example for demonstration.