Today,urban traffic,growing populations,and dense transportation networks are contributing to an increase in traffic incidents.These incidents include traffic accidents,vehicle breakdowns,fires,and traffic disputes,re...Today,urban traffic,growing populations,and dense transportation networks are contributing to an increase in traffic incidents.These incidents include traffic accidents,vehicle breakdowns,fires,and traffic disputes,resulting in long waiting times,high carbon emissions,and other undesirable situations.It is vital to estimate incident response times quickly and accurately after traffic incidents occur for the success of incident-related planning and response activities.This study presents a model for forecasting the traffic incident duration of traffic events with high precision.The proposed model goes through a 4-stage process using various features to predict the duration of four different traffic events and presents a feature reduction approach to enable real-time data collection and prediction.In the first stage,the dataset consisting of 24,431 data points and 75 variables is prepared by data collection,merging,missing data processing and data cleaning.In the second stage,models such as Decision Trees(DT),K-Nearest Neighbour(KNN),Random Forest(RF)and Support Vector Machines(SVM)are used and hyperparameter optimisation is performed with GridSearchCV.In the third stage,feature selection and reduction are performed and real-time data are used.In the last stage,model performance with 14 variables is evaluated with metrics such as accuracy,precision,recall,F1-score,MCC,confusion matrix and SHAP.The RF model outperforms other models with an accuracy of 98.5%.The study’s prediction results demonstrate that the proposed dynamic prediction model can achieve a high level of success.展开更多
Purpose-The purpose of this paper is to develop an approach to compare occupational health and safety(OHS)performances of countries.Additionally,another aim is to debate the impacts of using recorded data and ratios f...Purpose-The purpose of this paper is to develop an approach to compare occupational health and safety(OHS)performances of countries.Additionally,another aim is to debate the impacts of using recorded data and ratios for OHS performance evaluations.Design/methodology/approach-The number of fatal accidents(NFAs),fatal accident rates(FARs),numbers of lost days(NLDs)and accident severity rates(ASRs)are determined as main criteria and six economic activity areas(EAAs)are considered as sub-criteria.Two different initial decision matrices are used as the initial decision matrix,the first of which consists of recorded data of countries related to NFAs and NLDs,and the second consists of FAR and ASR values as ratios.Importance weights of main and sub-criteria regarding the recorded data and ratios are determined using four different weighting ways.Countries are ranked via utilizing Multi-Attributive Ideal-Real Comparative Analysis considering two different initial decision matrices.Findings-It can be stated that an evaluation based on ratios for comparison of OHS performance provides more realistic results.Additionally,increasing the effect of the FAR values using the 6,000 equivalent lost days factor is also important in terms of differentiating the data of the countries in question.Originality/value-To the best of the authors’knowledge,there is no study in literature that discusses the ranking of countries by means of recorded data and ratios considering different criteria.Additionally,this study is a first in terms of the number of countries evaluated and the comparison of these countries according to their respective EAAs.展开更多
Ammonia borane is widely used in most areas including fuel cell applications.The present paper describes electrochemical behavior of ammonia borane in alkaline media on the poly(p-aminophenol) film modified with Au an...Ammonia borane is widely used in most areas including fuel cell applications.The present paper describes electrochemical behavior of ammonia borane in alkaline media on the poly(p-aminophenol) film modified with Au and Ag bimetallic nanoparticles.The glassy carbon electrode was firstly covered with polymeric film electrochemically and then,Au,Ag,and Au–Ag nanoparticles were deposited on the polymeric film,respectively.The surface morphology and chemical composition of these electrodes were examined by scanning electron microscopy,transmission electron microscopy,electrochemical impedance spectroscopy,X-ray diffraction,and X-ray photoelectron spectroscopy.It was found that alloyed Au–Ag bimetallic nanoparticles are formed.Electrochemical measurements indicate that the developed electrode modified by Au–Ag bimetallic nanoparticles exhibit the highest electrocatalytic activity for ammonia borane oxidation in alkaline media.The rotating disk electrode voltammetry demonstrates that the developed electrode can catalyze almost six-electron oxidation pathway of ammonia borane.Our results may be attractive for anode materials of ammonia borane fuel cells under alkaline conditions.展开更多
文摘Today,urban traffic,growing populations,and dense transportation networks are contributing to an increase in traffic incidents.These incidents include traffic accidents,vehicle breakdowns,fires,and traffic disputes,resulting in long waiting times,high carbon emissions,and other undesirable situations.It is vital to estimate incident response times quickly and accurately after traffic incidents occur for the success of incident-related planning and response activities.This study presents a model for forecasting the traffic incident duration of traffic events with high precision.The proposed model goes through a 4-stage process using various features to predict the duration of four different traffic events and presents a feature reduction approach to enable real-time data collection and prediction.In the first stage,the dataset consisting of 24,431 data points and 75 variables is prepared by data collection,merging,missing data processing and data cleaning.In the second stage,models such as Decision Trees(DT),K-Nearest Neighbour(KNN),Random Forest(RF)and Support Vector Machines(SVM)are used and hyperparameter optimisation is performed with GridSearchCV.In the third stage,feature selection and reduction are performed and real-time data are used.In the last stage,model performance with 14 variables is evaluated with metrics such as accuracy,precision,recall,F1-score,MCC,confusion matrix and SHAP.The RF model outperforms other models with an accuracy of 98.5%.The study’s prediction results demonstrate that the proposed dynamic prediction model can achieve a high level of success.
文摘Purpose-The purpose of this paper is to develop an approach to compare occupational health and safety(OHS)performances of countries.Additionally,another aim is to debate the impacts of using recorded data and ratios for OHS performance evaluations.Design/methodology/approach-The number of fatal accidents(NFAs),fatal accident rates(FARs),numbers of lost days(NLDs)and accident severity rates(ASRs)are determined as main criteria and six economic activity areas(EAAs)are considered as sub-criteria.Two different initial decision matrices are used as the initial decision matrix,the first of which consists of recorded data of countries related to NFAs and NLDs,and the second consists of FAR and ASR values as ratios.Importance weights of main and sub-criteria regarding the recorded data and ratios are determined using four different weighting ways.Countries are ranked via utilizing Multi-Attributive Ideal-Real Comparative Analysis considering two different initial decision matrices.Findings-It can be stated that an evaluation based on ratios for comparison of OHS performance provides more realistic results.Additionally,increasing the effect of the FAR values using the 6,000 equivalent lost days factor is also important in terms of differentiating the data of the countries in question.Originality/value-To the best of the authors’knowledge,there is no study in literature that discusses the ranking of countries by means of recorded data and ratios considering different criteria.Additionally,this study is a first in terms of the number of countries evaluated and the comparison of these countries according to their respective EAAs.
基金supported by the Scientific and Technical Research Council of Turkey(TUBITAK) with 110T806 project numberEBILTEM with BIL-012 project numberEge University Research Funds(BAP project,10 FEN/075)
文摘Ammonia borane is widely used in most areas including fuel cell applications.The present paper describes electrochemical behavior of ammonia borane in alkaline media on the poly(p-aminophenol) film modified with Au and Ag bimetallic nanoparticles.The glassy carbon electrode was firstly covered with polymeric film electrochemically and then,Au,Ag,and Au–Ag nanoparticles were deposited on the polymeric film,respectively.The surface morphology and chemical composition of these electrodes were examined by scanning electron microscopy,transmission electron microscopy,electrochemical impedance spectroscopy,X-ray diffraction,and X-ray photoelectron spectroscopy.It was found that alloyed Au–Ag bimetallic nanoparticles are formed.Electrochemical measurements indicate that the developed electrode modified by Au–Ag bimetallic nanoparticles exhibit the highest electrocatalytic activity for ammonia borane oxidation in alkaline media.The rotating disk electrode voltammetry demonstrates that the developed electrode can catalyze almost six-electron oxidation pathway of ammonia borane.Our results may be attractive for anode materials of ammonia borane fuel cells under alkaline conditions.
