http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Safa M.,Pandian A.,Mohammad Gouse Baig,Reddy Sadda Bharath,Kumar K. Satish,Banu A. S. Gousia,Srihari K.,Chandragandhi S. 대한전기학회 2024 Journal of Electrical Engineering & Technology Vol.19 No.4
Cardiac disease analysis in big data is an emerging factor for human health protection against heart attacks. Most cardiovascular diseases lead to heart failure due to an imbalance of immunity and attention in health conditions. Hence, immunity-based feature analysis of patients’ records is essential to predict accurate results. The machine learning methods make predictions depending on the extended-lasting features to analyze the health data. But the marginal features expose non-relational feature observation to reduce the classifi cation prediction accuracy. We propose a Deep Spectral Time-Variant Feature Analytic Model (DSTV-FAM) using SoftMax Recurrent Neural Network (SMRNN) in a wireless sensor network to improve cardiac disease prediction accuracy. Initially, the IoT sensor devices collect the data from patient observation to validate the data transmission in route propagation. The collected data is organized as features in the collective dataset. The parts are initially preprocessed into the redundant dataset and estimate the Cardiac Immunity Infl uence Rate (CIIR) depending on the time-variant feature selection model. The estimated weights are marginalized as spectral features trained into the classifi ers. Further, Soft-Max Activation Function (SMAF) creates a logical function depending on the Cardiac Aff ection Rate (CAR). Then the trained, rational neurons are constructed into a Recurrent Neural Network (RNN) Feed-forward feature values using a classifi er and Rate of Disease Aff ection (RDA) by Class Type. The proposed structure yields high prescient exactness concerning order, accuracy, and review to help early treatment for early cardiovascular gamble expectation.
M. Safa,M. Shariati,Z. Ibrahim,A. Toghroli,Shahrizan Bin Baharom,Norazman M. Nor,Dalibor Petković 국제구조공학회 2016 Steel and Composite Structures, An International J Vol.21 No.3
Structural design of a composite beam is influenced by two main factors, strength and ductility. For the design to be effective for a composite beam, say an RC slab and a steel I beam, the shear strength of the composite beam and ductility have to carefully estimate with the help of displacements between the two members. In this investigation the shear strengths of steel-concrete composite beams was analyzed based on the respective variable parameters. The methodology used by ANFIS (Adaptive Neuro Fuzzy Inference System) has been adopted for this purpose. The detection of the predominant factors affecting the shear strength steel-concrete composite beam was achieved by use of ANFIS process for variable selection. The results show that concrete compression strength has the highest influence on the shear strength capacity of composite beam.
Strength prediction of rotary brace damper using MLR and MARS
I. Mansouri,M. Safa,Z. Ibrahim,O. Kisi,M.M. Tahir,S. Baharom,M. Azimi 국제구조공학회 2016 Structural Engineering and Mechanics, An Int'l Jou Vol.60 No.3
This study predicts the strength of rotary brace damper by analyzing a new set of probabilistic models using the usual method of multiple linear regressions (MLR) and advanced machine-learning methods of multivariate adaptive regression splines (MARS), Rotary brace damper can be easily assembled with high energy-dissipation capability. To investigate the behavior of this damper in structures, a steel frame is modeled with this device subjected to monotonic and cyclic loading. Several response parameters are considered, and the performance of damper in reducing each response is evaluated. MLR and MARS methods were used to predict the strength of this damper. Displacement was determined to be the most effective parameter of damper strength, whereas the thickness did not exhibit any effect. Adding thickness parameter as inputs to MARS and MLR models did not increase the accuracies of the models in predicting the strength of this damper. The MARS model with a root mean square error (RMSE) of 0.127 and mean absolute error (MAE) of 0.090 performed better than the MLR model with an RMSE of 0.221 and MAE of 0.181.
Chahnasir, E. Sadeghipour,Zandi, Y.,Shariati, M.,Dehghani, E.,Toghroli, A.,Mohamad, E. Tonnizam,Shariati, A.,Safa, M.,Wakil, K.,Khorami, M. 국제구조공학회 2018 Smart Structures and Systems, An International Jou Vol.22 No.4
The factors affecting the shear strength of the angle shear connectors in the steel-concrete composite beams can play an important role to estimate the efficacy of a composite beam. Therefore, the current study has aimed to verify the output of shear capacity of angle shear connector according to the input provided by Support Vector Machine (SVM) coupled with Firefly Algorithm (FFA). SVM parameters have been optimized through the use of FFA, while genetic programming (GP) and artificial neural networks (ANN) have been applied to estimate and predict the SVM-FFA models' results. Following these results, GP and ANN have been applied to develop the prediction accuracy and generalization capability of SVM-FFA. Therefore, SVM-FFA could be performed as a novel model with predictive strategy in the shear capacity estimation of angle shear connectors. According to the results, the Firefly algorithm has produced a generalized performance and be learnt faster than the conventional learning algorithms.
E. Sadeghipour Chahnasir,Y. Zandi,M. Shariati,E. Dehghani,A. Toghroli,E. Tonnizam Mohamad,A. Shariati,M. Safa,K. Wakil,M. Khorami 국제구조공학회 2018 Smart Structures and Systems, An International Jou Vol.22 No.4
The factors affecting the shear strength of the angle shear connectors in the steel-concrete composite beams can play an important role to estimate the efficacy of a composite beam. Therefore, the current study has aimed to verify the output of shear capacity of angle shear connector according to the input provided by Support Vector Machine (SVM) coupled with Firefly Algorithm (FFA). SVM parameters have been optimized through the use of FFA, while genetic programming (GP) and artificial neural networks (ANN) have been applied to estimate and predict the SVM-FFA models' results. Following these results, GP and ANN have been applied to develop the prediction accuracy and generalization capability of SVM-FFA. Therefore, SVM-FFA could be performed as a novel model with predictive strategy in the shear capacity estimation of angle shear connectors. According to the results, the Firefly algorithm has produced a generalized performance and be learnt faster than the conventional learning algorithms.
Ansaruzzaman, M.,Chowdhury, Ashrafuzzaman,Bhuiyan, Nurul A.,Sultana, Marzia,Safa, Ashrafus,Lucas, Marcelino,von Seidlein, Lorenz,Barreto, Avertino,Chaignat, Claire-Lise,Sack, David A.,Clemens, John D. Microbiology Society 2008 Journal of medical microbiology Vol.57 No.12
<P>The genetic characteristics of Vibrio parahaemolyticus strains isolated in 2004 and 2005 in Mozambique were assessed in this study to determine whether the pandemic clone of V. parahaemolyticus O3 : K6 and O4 : K68 serotypes has spread to Mozambique. Fifty-eight V. parahaemolyticus strains isolated from hospitalized diarrhoea patients in Beira, Mozambique, were serotyped for O : K antigens and genotyped for toxR, tdh and trh genes. A group-specific PCR, a PCR that detects the presence of ORF8 of the filamentous phage f237, arbitrarily primed PCR, PFGE and multilocus sequence typing were performed to determine the pandemic status of the strains and their ancestry. All strains of serovars O3 : K6 (n=38) and O4 : K68 (n=4) were identified as a pandemic clonal group by these analyses. These strains are closely related to the pandemic reference strains of O3 : K6 and O4 : K68, which emerged in Asia in 1996 and were later found globally. The pandemic serotypes O3 : K6 and O4 : K68 including reference strains grouped into a single cluster indicating emergence from a common ancestor. The O3 : K58 (n=8), O4 : K13 (n=6), O3 : KUT (n=1) and O8 : K41 (n=1) strains showed unique characteristics different from the pandemic clone.</P>
S. SAFA,M. MOJTAHEDZADEH LARIJANI,V. FATHOLLAHI,O. R. KAKUEE 성균관대학교(자연과학캠퍼스) 성균나노과학기술원 2010 NANO Vol.5 No.6
Hydrogen storage capacity of a carbon nanotube (CNT) sample is investigated using Elastic Recoil Detection Analysis (ERDA) at constant hydrogen uptake pressure of 5 bar and different adsorption temperatures within 30°C–500°C. The results of hydrogen concentration versus temperature revealed three distinct temperature intervals in which a certain adsorption or desorption mechanism is dominant. Moreover, the results showed that hydrogen storage capacity of CNTs at the applied conditions of pressure and temperature is about 0.1 wt.% which is well below the DOE requirements for a viable hydrogen storage system. The physidesorption activation energy is calculated using the Arrhenius plot to be 6 kJmol-1.
A first-principles study of B3O3 monolayer as potential anode materials for calcium-ion batteries
Kadhim Mustafa M.,Majdi Ali,Hachim Safa K.,Abdullaha Sallalh. Ahmed,Taban Taleeb Zedan,Rheima Ahmed Mahdi 한국화학공학회 2023 Korean Journal of Chemical Engineering Vol.40 No.7
Anodic materials with fast kinetics and high capacity are prerequisites for improvement of calcium-ion batteries (CIBs). According to first-principles computations, unique calcium capacity was discovered for B3O3 monolayer. Based on findings, Ca atoms can be adsorbed on B3O3 surface, and the most stable location is the top of the pore center of B3O3 monolayer. Binding energy of B3O3 monolayer is relatively high for Ca atoms. In addition, Ca atoms have been shown to more simple diffuse on B3O3 surface, and lowest diffusion barrier was 65 meV. A more significant finding is that B3O3 monolayer-based nanostructures possess a relatively large capacity of 616.05 mAh/g (as Ca.51BO). These results are expected to support illumination mechanism of Ca storage in boron oxide materials with low-dimensional structures and pave the way for design of CIBs. Therefore, we can utilize the B3O3 anode-based CIBs as alternatives to normal Ca-ion batteries.
Fuzzy modelling approach for shear strength prediction of RC deep beams
Mohammad Mohammadhassani,Aidi MD. Saleh,M Suhatril,M. Safa 국제구조공학회 2015 Smart Structures and Systems, An International Jou Vol.16 No.3
This study discusses the use of Adaptive-Network-Based-Fuzzy-Inference-System (ANFIS) in predicting the shear strength of reinforced-concrete deep beams. 139 experimental data have been collected from renowned publications on simply supported high strength concrete deep beams. The results show that the ANFIS has strong potential as a feasible tool for predicting the shear strength of deep beams within the range of the considered input parameters. ANFIS‟s results are highly accurate, precise and therefore, more satisfactory. Based on the Sensitivity analysis, the shear span to depth ratio (a/d) and concrete cylinder strength ( c f′) have major influence on the shear strength prediction of deep beams. The parametric study confirms the increase in shear strength of deep beams with an equal increase in the concrete strength and decrease in the shear span to-depth-ratio.
Evaluation of the parameters affecting the Schmidt rebound hammer reading using ANFIS method
Ali Toghroli,Ehsan Darvishmoghaddam,Yousef Zandi,Mahdi Parvan,Maryam Safa,Mu’azu Mohammed Abdullahi,Abbas Heydari,Karzan Wakil,Saad A.M. Gebreel,Majid Khorami 사단법인 한국계산역학회 2018 Computers and Concrete, An International Journal Vol.21 No.5
As a nondestructive testing method, the Schmidt rebound hammer is widely used for structural health monitoring. During application, a Schmidt hammer hits the surface of a concrete mass. According to the principle of rebound, concrete strength depends on the hardness of the concrete energy surface. Study aims to identify the main variables affecting the results of Schmidt rebound hammer reading and consequently the results of structural health monitoring of concrete structures using adaptive neuro-fuzzy inference system (ANFIS). The ANFIS process for variable selection was applied for this purpose. This procedure comprises some methods that determine a subsection of the entire set of detailed factors, which present analytical capability. ANFIS was applied to complete a flexible search. Afterward, this method was applied to conclude how the five main factors (namely, age, silica fume, fine aggregate, coarse aggregate, and water) used in designing concrete mixture influence the Schmidt rebound hammer reading and consequently the structural health monitoring accuracy. Results show that water is considered the most significant parameter of the Schmidt rebound hammer reading. The details of this study are discussed thoroughly.