Pub Date : 2023-06-20DOI: 10.1177/03611981231170008
Shi Ye, Qun Chen, Yi Tang
Conflicts often occur between bus drivers and passengers or among passengers, leading to dangerous situations while driving. However, tools to explore drivers’ and passengers’ forms of anger expression are lacking. This paper describes the development of a bus passenger anger expression inventory (BPAX) and a bus driver anger expression inventory (BDAX) based on a 402 passenger sample and a 414 driver sample. Exploratory principal component analysis revealed five factors in the BPAX: verbal aggressive expression, verbal positive expression, personal physical aggressive expression, adaptive/constructive expression, and displaced aggression. Similarly, six factors were identified in the BDAX: verbal positive expression, use of the vehicle to express anger, verbal aggressive expression, adaptive/constructive expression, personal physical aggressive expression, and displaced aggression. Overall, gender showed a difference only in aggressive expressions of passenger anger, not in drivers’ anger expressions. Older, less educated, and lower-income passengers preferred to express anger aggressively and rarely relieved conflicts in a positive verbal way. For driver groups, differences in age, anger level, and city grade were reflected in their forms of anger expression. The results of this paper are significant for strengthening driver safety training, improving safety facilities in buses, enhancing passenger education on civilized riding, and perfecting laws and regulations.
{"title":"Anger Expressions of Bus Drivers and Passengers during Conflicts on the Bus","authors":"Shi Ye, Qun Chen, Yi Tang","doi":"10.1177/03611981231170008","DOIUrl":"https://doi.org/10.1177/03611981231170008","url":null,"abstract":"Conflicts often occur between bus drivers and passengers or among passengers, leading to dangerous situations while driving. However, tools to explore drivers’ and passengers’ forms of anger expression are lacking. This paper describes the development of a bus passenger anger expression inventory (BPAX) and a bus driver anger expression inventory (BDAX) based on a 402 passenger sample and a 414 driver sample. Exploratory principal component analysis revealed five factors in the BPAX: verbal aggressive expression, verbal positive expression, personal physical aggressive expression, adaptive/constructive expression, and displaced aggression. Similarly, six factors were identified in the BDAX: verbal positive expression, use of the vehicle to express anger, verbal aggressive expression, adaptive/constructive expression, personal physical aggressive expression, and displaced aggression. Overall, gender showed a difference only in aggressive expressions of passenger anger, not in drivers’ anger expressions. Older, less educated, and lower-income passengers preferred to express anger aggressively and rarely relieved conflicts in a positive verbal way. For driver groups, differences in age, anger level, and city grade were reflected in their forms of anger expression. The results of this paper are significant for strengthening driver safety training, improving safety facilities in buses, enhancing passenger education on civilized riding, and perfecting laws and regulations.","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135139822","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-15DOI: 10.1177/03611981231174240
Mofeng Yang, Weiyu Luo, Mohammad Ashoori, Jina Mahmoudi, Chenfeng Xiong, Jiawei Lu, Guangchen Zhao, Saeed Saleh Namadi, Songhua Hu, Aliakbar Kabiri, Ya Ji
Vehicle volume serves as a critical metric and the fundamental basis for traffic signal control, transportation project prioritization, road maintenance planning, and more. Traditional methods of quantifying vehicle volume rely on manual counting, video cameras, and loop detectors at a limited number of locations. These efforts require significant labor and cost for expansions. Researchers and private sector companies have also explored alternative solutions, such as probe vehicle data, although this still suffers from a low penetration rate. In recent years, along with the technological advancement in mobile sensors and mobile networks, the quantity of mobile device location data (MDLD) has been growing dramatically in spatiotemporal coverage of the population and its mobility. This paper presents a big-data driven framework that can ingest terabytes of MDLD and estimate vehicle volume over a larger geographical area with a larger sample size. The proposed framework first employs a series of cloud-based computational algorithms to extract multimodal trajectories and trip rosters. A scalable map matching and routing algorithm is then applied to snap and route vehicle trajectories to the roadway network. The observed vehicle counts on each roadway segment are weighted and calibrated against ground truth control totals, that is, annual vehicle-miles traveled and annual average daily traffic. The proposed framework is implemented on the all-street network in the State of Maryland using MDLD for the entire year of 2019. The results demonstrate that our proposed framework produces reliable vehicle volume and also its transferability and generalization ability.
{"title":"Big-Data Driven Framework to Estimate Vehicle Volume Based on Mobile Device Location Data","authors":"Mofeng Yang, Weiyu Luo, Mohammad Ashoori, Jina Mahmoudi, Chenfeng Xiong, Jiawei Lu, Guangchen Zhao, Saeed Saleh Namadi, Songhua Hu, Aliakbar Kabiri, Ya Ji","doi":"10.1177/03611981231174240","DOIUrl":"https://doi.org/10.1177/03611981231174240","url":null,"abstract":"Vehicle volume serves as a critical metric and the fundamental basis for traffic signal control, transportation project prioritization, road maintenance planning, and more. Traditional methods of quantifying vehicle volume rely on manual counting, video cameras, and loop detectors at a limited number of locations. These efforts require significant labor and cost for expansions. Researchers and private sector companies have also explored alternative solutions, such as probe vehicle data, although this still suffers from a low penetration rate. In recent years, along with the technological advancement in mobile sensors and mobile networks, the quantity of mobile device location data (MDLD) has been growing dramatically in spatiotemporal coverage of the population and its mobility. This paper presents a big-data driven framework that can ingest terabytes of MDLD and estimate vehicle volume over a larger geographical area with a larger sample size. The proposed framework first employs a series of cloud-based computational algorithms to extract multimodal trajectories and trip rosters. A scalable map matching and routing algorithm is then applied to snap and route vehicle trajectories to the roadway network. The observed vehicle counts on each roadway segment are weighted and calibrated against ground truth control totals, that is, annual vehicle-miles traveled and annual average daily traffic. The proposed framework is implemented on the all-street network in the State of Maryland using MDLD for the entire year of 2019. The results demonstrate that our proposed framework produces reliable vehicle volume and also its transferability and generalization ability.","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135711090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-14DOI: 10.1177/03611981231174239
M. Paköz, N. Kaya
A forced and rapid increase in remote working because of the COVID-19 pandemic has afforded today’s megacities several important opportunities for reducing traffic congestion, energy consumption, greenhouse gas emissions, and certain threats such as the promotion of urban sprawl. The way in which employees have adapted to working remotely during the pandemic and the potential it offers for improving their work/life balance provide indicators for developing urban policies in the post-pandemic city. The present study aims to examine the potential impact the increase in remote working during the first phase of the COVID-19 pandemic has had on residential relocations in Istanbul by investigating how employees have adapted to remote working and their thoughts about leaving the city after the pandemic. To do so, an online survey was conducted between June 1 and June 5, 2020 with 186 employees living in the city of Istanbul. The survey consisted of investigations into changes in work life during the pandemic. The differences between participants’ responses were analyzed and interpreted with respect to their personal characteristics and leisure-time preferences using Pearson’s chi-squared test and the Mantel–Haenszel test of trends (linear-by-linear association). The study finds significant relationships between personal/social characteristics and how people adapt to remote working and provides important indicators of the effects these adaptation processes have on residential relocations.
{"title":"Personal Adaptations to Remote Working in the Post-Pandemic City and Its Potential Impact on Residential Relocations: The Case of Istanbul","authors":"M. Paköz, N. Kaya","doi":"10.1177/03611981231174239","DOIUrl":"https://doi.org/10.1177/03611981231174239","url":null,"abstract":"A forced and rapid increase in remote working because of the COVID-19 pandemic has afforded today’s megacities several important opportunities for reducing traffic congestion, energy consumption, greenhouse gas emissions, and certain threats such as the promotion of urban sprawl. The way in which employees have adapted to working remotely during the pandemic and the potential it offers for improving their work/life balance provide indicators for developing urban policies in the post-pandemic city. The present study aims to examine the potential impact the increase in remote working during the first phase of the COVID-19 pandemic has had on residential relocations in Istanbul by investigating how employees have adapted to remote working and their thoughts about leaving the city after the pandemic. To do so, an online survey was conducted between June 1 and June 5, 2020 with 186 employees living in the city of Istanbul. The survey consisted of investigations into changes in work life during the pandemic. The differences between participants’ responses were analyzed and interpreted with respect to their personal characteristics and leisure-time preferences using Pearson’s chi-squared test and the Mantel–Haenszel test of trends (linear-by-linear association). The study finds significant relationships between personal/social characteristics and how people adapt to remote working and provides important indicators of the effects these adaptation processes have on residential relocations.","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47888714","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-13DOI: 10.1177/03611981231173649
Agnimitra Sengupta, Hoda Azari, S. Ilgin Guler, Parisa Shokouhi
Impact echo (IE) is capable of locating subsurface defects in concrete slabs from the vibrational response of the slab to a mechanical impact. For an intact slab (“good” condition), the frequency spectrum of the IE is dominated by a single peak corresponding to the slab’s “thickness resonance frequency,” whereas the presence of subsurface defects (“fair” or “poor” conditions) could manifest in various ways such as multiple distinct peaks at frequencies higher, or lower, than the thickness resonance. In previous research, the authors have proposed a frequency partitioning of the spectrum for IE signal classification. Firstly, the thickness resonance frequency band is identified using a data-driven approach and then the IE signals are represented by their energy distribution in three bands—frequencies less than, within, and greater than the thickness resonance. Following this feature extraction, an unsupervised clustering approach is used to identify the centroids for each signal class—good, fair, and poor—which are further used to classify any test signal into one of the three aforementioned classes. The classification is developed by training on unlabeled IE signals from real bridge deck data (the Federal Highway Administration’s [FHWA’s] InfoBridge dataset) without making use of any labeled data. This study aims to validate the proposed methodology on a labeled dataset of eight reinforced concrete specimens constructed at the FHWA Advanced Sensing Technology Nondestructive Evaluation laboratory having known artificial defects. Our findings indicate that the physics-based feature definition and the method developed on real bridge data are robust and can classify IE signals in the labeled data with moderate accuracy.
{"title":"Validating a Physics-Based Automatic Classification Scheme for Impact Echo Signals on Data Using a Concrete Slab with Known Defects","authors":"Agnimitra Sengupta, Hoda Azari, S. Ilgin Guler, Parisa Shokouhi","doi":"10.1177/03611981231173649","DOIUrl":"https://doi.org/10.1177/03611981231173649","url":null,"abstract":"Impact echo (IE) is capable of locating subsurface defects in concrete slabs from the vibrational response of the slab to a mechanical impact. For an intact slab (“good” condition), the frequency spectrum of the IE is dominated by a single peak corresponding to the slab’s “thickness resonance frequency,” whereas the presence of subsurface defects (“fair” or “poor” conditions) could manifest in various ways such as multiple distinct peaks at frequencies higher, or lower, than the thickness resonance. In previous research, the authors have proposed a frequency partitioning of the spectrum for IE signal classification. Firstly, the thickness resonance frequency band is identified using a data-driven approach and then the IE signals are represented by their energy distribution in three bands—frequencies less than, within, and greater than the thickness resonance. Following this feature extraction, an unsupervised clustering approach is used to identify the centroids for each signal class—good, fair, and poor—which are further used to classify any test signal into one of the three aforementioned classes. The classification is developed by training on unlabeled IE signals from real bridge deck data (the Federal Highway Administration’s [FHWA’s] InfoBridge dataset) without making use of any labeled data. This study aims to validate the proposed methodology on a labeled dataset of eight reinforced concrete specimens constructed at the FHWA Advanced Sensing Technology Nondestructive Evaluation laboratory having known artificial defects. Our findings indicate that the physics-based feature definition and the method developed on real bridge data are robust and can classify IE signals in the labeled data with moderate accuracy.","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136101474","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-09DOI: 10.1177/03611981231179168
K. Dönmez
The increasing demand for air traffic at airports necessitates the efficient utilization of ground facilities such as runways and taxiways. Intersecting departures, in which one or more aircraft take off from intersecting points on the runway, is a commonly used approach to increase runway capacity and reduce ground delays and taxi times, as well as noise and air pollution. However, the procedure carries potential risks such as runway incursion and excursion. This creates a trade-off between minimizing the number of intersecting departures and minimizing ground delays. In practice, the decision to perform an intersecting departure is ultimately up to the pilot, resulting in uncertainty in the acceptance rate of these types of takeoffs. In this study, a departure sequencing model was developed for a single-runway airport that considers intersecting departures and various pilot acceptance rate scenarios. The primary objective of the model is to minimize total ground delay, including taxi delays, runway holds, and conflict holds. The secondary objective is to minimize the number of intersecting departures by directing the most operationally critical aircraft to the intersection takeoff. The epsilon constraint method—a multi-objective scalarization method—was used to reveal the trade-offs between the objective functions. The results of the model were compared with a traditional scenario that only allows take offs from the beginning of the runway. As a result, average delay savings ranged from 17.1% to 31.5% in various acceptance rate scenarios, as well as average taxi time savings ranging from 4.9% to 8.4% compared with the traditional scenario.
{"title":"Evaluation of the Trade-Off between Ground Delays and Intersecting Departures under Various Pilot Acceptance Rate Scenarios","authors":"K. Dönmez","doi":"10.1177/03611981231179168","DOIUrl":"https://doi.org/10.1177/03611981231179168","url":null,"abstract":"The increasing demand for air traffic at airports necessitates the efficient utilization of ground facilities such as runways and taxiways. Intersecting departures, in which one or more aircraft take off from intersecting points on the runway, is a commonly used approach to increase runway capacity and reduce ground delays and taxi times, as well as noise and air pollution. However, the procedure carries potential risks such as runway incursion and excursion. This creates a trade-off between minimizing the number of intersecting departures and minimizing ground delays. In practice, the decision to perform an intersecting departure is ultimately up to the pilot, resulting in uncertainty in the acceptance rate of these types of takeoffs. In this study, a departure sequencing model was developed for a single-runway airport that considers intersecting departures and various pilot acceptance rate scenarios. The primary objective of the model is to minimize total ground delay, including taxi delays, runway holds, and conflict holds. The secondary objective is to minimize the number of intersecting departures by directing the most operationally critical aircraft to the intersection takeoff. The epsilon constraint method—a multi-objective scalarization method—was used to reveal the trade-offs between the objective functions. The results of the model were compared with a traditional scenario that only allows take offs from the beginning of the runway. As a result, average delay savings ranged from 17.1% to 31.5% in various acceptance rate scenarios, as well as average taxi time savings ranging from 4.9% to 8.4% compared with the traditional scenario.","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":"2677 1","pages":"733 - 746"},"PeriodicalIF":1.7,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46818970","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Many studies have explored the impact of the COVID-19 pandemic on work-from-home (WFH) behavior from different perspectives. However, it is rare to find studies focusing on how the newly adopted WFH practices will affect commuting patterns in the post-pandemic era. This study defines two mediation factors to capture the perceptions of pandemic severity and work environment at home and further investigates their impacts on future WFH adoption. This study utilizes a comprehensive survey and a path analysis method known as structural equation modeling (SEM) to explore the association between demographic factors, perception of COVID-related issues, and WFH behavior before, during, and after the pandemic. The results show that motherhood negatively affected WFH experiences in the before, during, and after periods of the pandemic. It was also found that being forced to WFH and mixing the working environment with their children made mothers less likely to WFH in the post-pandemic era. The results also show that older workers are less appreciative of the WFH approach and are less likely to continue to WFH in the post-pandemic era. The findings also confirmed the association between WFH during and after the pandemic with other factors, such as age and education. The positive or negative experiences with WFH during the pandemic will significantly shape workers’ decisions on continuing to WFH in the post-pandemic era. These findings could help transportation agencies understand the impacts of these factors on the choices of WFH during and, more importantly, after the pandemic era.
{"title":"Case Study on the Relationship Between Socio-Demographic Characteristics and Work-from-Home Behavior Before, During, and After the COVID-19 Pandemic","authors":"X. Kong, Zihao Li, Yunlong Zhang, Xun Chen, Subasish Das, Abbas Sheykhfard","doi":"10.1177/03611981231172946","DOIUrl":"https://doi.org/10.1177/03611981231172946","url":null,"abstract":"Many studies have explored the impact of the COVID-19 pandemic on work-from-home (WFH) behavior from different perspectives. However, it is rare to find studies focusing on how the newly adopted WFH practices will affect commuting patterns in the post-pandemic era. This study defines two mediation factors to capture the perceptions of pandemic severity and work environment at home and further investigates their impacts on future WFH adoption. This study utilizes a comprehensive survey and a path analysis method known as structural equation modeling (SEM) to explore the association between demographic factors, perception of COVID-related issues, and WFH behavior before, during, and after the pandemic. The results show that motherhood negatively affected WFH experiences in the before, during, and after periods of the pandemic. It was also found that being forced to WFH and mixing the working environment with their children made mothers less likely to WFH in the post-pandemic era. The results also show that older workers are less appreciative of the WFH approach and are less likely to continue to WFH in the post-pandemic era. The findings also confirmed the association between WFH during and after the pandemic with other factors, such as age and education. The positive or negative experiences with WFH during the pandemic will significantly shape workers’ decisions on continuing to WFH in the post-pandemic era. These findings could help transportation agencies understand the impacts of these factors on the choices of WFH during and, more importantly, after the pandemic era.","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":"1 1","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42731118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-08DOI: 10.1177/03611981231172962
Hiral Patel, Ninad Gore, Said Easa, Shriniwas Arkatkar
The present study proposed a real-time traffic safety evaluation framework using macroscopic flow variables. To this end, open-access extended vehicle trajectories were employed. Rear-end traffic conflicts and macroscopic traffic flow variables were derived from the trajectory data and were integrated for real-time safety evaluation. The Proportion of Stopping distance ( PSD) accounts for all types of interactions (both safe and unsafe) in the traffic stream; therefore, the same was adopted to analyze the rear-end traffic conflicts. A macroscopic indicator termed “time spent in conflict ( TSC)” was derived to evaluate the rear-end traffic conflicts. Machine learning models, namely, Random Forest (RF), Support Vector Machines (SVM), and eXtreme Gradient Boosting (XGB), were employed to predict TSCs using macroscopic traffic flow variables. The results revealed that the TSC computed based on PSD exhibits a reliable and explainable relationship with the macroscopic traffic flow variables. TSC computed based on PSD revealed that intermediately congested traffic flow conditions are critical in traffic safety and can be attributed to complex traffic phenomena such as traffic hysteresis, traffic oscillations, and increased speed variance. Moreover, a stable relation between traffic safety and traffic flow was suggested for varying threshold values. Among different machine learning models, the RF model was observed as the best-fitted model to predict TSC based on macroscopic traffic variables. TSC quantifies the safety status of a given traffic flow condition, where a higher value of TSC for a particular traffic flow condition indicates that vehicles prevail in the conflicting scenario for a longer time and, therefore, reflect higher operational risk. The developed machine learning model can be employed to predict TSC (operational risk) in real time using the macroscopic traffic flow variables and, therefore, facilitate traffic safety monitoring.
{"title":"Novel Traffic Conflict-Based Framework for Real-Time Traffic Safety Evaluation Under Heterogeneous and Weak Lane-Discipline Traffic","authors":"Hiral Patel, Ninad Gore, Said Easa, Shriniwas Arkatkar","doi":"10.1177/03611981231172962","DOIUrl":"https://doi.org/10.1177/03611981231172962","url":null,"abstract":"The present study proposed a real-time traffic safety evaluation framework using macroscopic flow variables. To this end, open-access extended vehicle trajectories were employed. Rear-end traffic conflicts and macroscopic traffic flow variables were derived from the trajectory data and were integrated for real-time safety evaluation. The Proportion of Stopping distance ( PSD) accounts for all types of interactions (both safe and unsafe) in the traffic stream; therefore, the same was adopted to analyze the rear-end traffic conflicts. A macroscopic indicator termed “time spent in conflict ( TSC)” was derived to evaluate the rear-end traffic conflicts. Machine learning models, namely, Random Forest (RF), Support Vector Machines (SVM), and eXtreme Gradient Boosting (XGB), were employed to predict TSCs using macroscopic traffic flow variables. The results revealed that the TSC computed based on PSD exhibits a reliable and explainable relationship with the macroscopic traffic flow variables. TSC computed based on PSD revealed that intermediately congested traffic flow conditions are critical in traffic safety and can be attributed to complex traffic phenomena such as traffic hysteresis, traffic oscillations, and increased speed variance. Moreover, a stable relation between traffic safety and traffic flow was suggested for varying threshold values. Among different machine learning models, the RF model was observed as the best-fitted model to predict TSC based on macroscopic traffic variables. TSC quantifies the safety status of a given traffic flow condition, where a higher value of TSC for a particular traffic flow condition indicates that vehicles prevail in the conflicting scenario for a longer time and, therefore, reflect higher operational risk. The developed machine learning model can be employed to predict TSC (operational risk) in real time using the macroscopic traffic flow variables and, therefore, facilitate traffic safety monitoring.","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135325176","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-03DOI: 10.1177/03611981231172948
Shengyang Wu, Yi Gao
As one of the most extensive social networking services, Twitter has more than 300 million active users as of 2022. Among its many functions, Twitter is now one of the go-to platforms for consumers to share their opinions about products or experiences, including flight services provided by commercial airlines. Using a machine learning approach, this study aimed to measure customer satisfaction by analyzing sentiments of tweets that mention airlines. Relevant tweets were retrieved from Twitter’s application programming interface and processed through tokenization and vectorization. After that, these processed vectors were passed into a pretrained machine learning classifier to predict the sentiments. In addition to sentiment analysis, we also performed a lexical analysis on the collected tweets to model keyword frequencies, which provided meaningful context to facilitate interpretation of the sentiments. We then applied time series methods such as Bollinger Bands to detect abnormalities in the sentiment data. Using historical records from January to July 2022, our approach was proven capable of capturing sudden and significant changes in passenger sentiments through the analysis of breakout points on the Bollinger upper and lower bounds. The methodology devised for this study has the potential to be developed into an application that could help airlines, along with other customer-facing businesses, efficiently detect abrupt changes in customer sentiments and consequently take appropriate mitigatory measures.
{"title":"Machine Learning Approach to Analyze the Sentiment of Airline Passengers’ Tweets","authors":"Shengyang Wu, Yi Gao","doi":"10.1177/03611981231172948","DOIUrl":"https://doi.org/10.1177/03611981231172948","url":null,"abstract":"As one of the most extensive social networking services, Twitter has more than 300 million active users as of 2022. Among its many functions, Twitter is now one of the go-to platforms for consumers to share their opinions about products or experiences, including flight services provided by commercial airlines. Using a machine learning approach, this study aimed to measure customer satisfaction by analyzing sentiments of tweets that mention airlines. Relevant tweets were retrieved from Twitter’s application programming interface and processed through tokenization and vectorization. After that, these processed vectors were passed into a pretrained machine learning classifier to predict the sentiments. In addition to sentiment analysis, we also performed a lexical analysis on the collected tweets to model keyword frequencies, which provided meaningful context to facilitate interpretation of the sentiments. We then applied time series methods such as Bollinger Bands to detect abnormalities in the sentiment data. Using historical records from January to July 2022, our approach was proven capable of capturing sudden and significant changes in passenger sentiments through the analysis of breakout points on the Bollinger upper and lower bounds. The methodology devised for this study has the potential to be developed into an application that could help airlines, along with other customer-facing businesses, efficiently detect abrupt changes in customer sentiments and consequently take appropriate mitigatory measures.","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135842280","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-01Epub Date: 2023-01-12DOI: 10.1177/03611981221145133
Patrick Loa, Khandker Nurul Habib
The COVID-19 pandemic had a significant impact on travel mode choices in cities across the world. Driven by perceptions of risk and the fear of infection, the pandemic resulted in an increased preference for private vehicles and active modes and a reduced preference for public transit and ride-sourcing. As travel behavior and modal preferences evolve, a key question is whether the pandemic will result in long-term changes to travel mode choices. This study uses data from a web-based survey to examine the factors influencing mode choices for non-commuting trips in the post-pandemic era. Specifically, it uses stated preference data to develop a random parameter mixed logit model, which is used to compare the elasticity of key variables across different income and age groups. The results of the study highlight the influence of sociodemographic attributes and pre-pandemic travel habits on anticipated post-pandemic mode choices. Additionally, the results suggest that frequent users of private vehicles, public transit, and active modes are likely to continue to use these modes post-pandemic. Furthermore, the results highlight the potential for the perception of shared modes to influence post-pandemic mode choice decisions. The results of the study offer insights into policy measures that could be applied to address the increased use of private vehicles and reduced use of transit during the pandemic, while also emphasizing the need to ensure that certain segments of the population can maintain a sufficient level of mobility and access to transport.
{"title":"Identifying the Determinants of Anticipated Post-Pandemic Mode Choices in the Greater Toronto Area: A Stated Preference Study.","authors":"Patrick Loa, Khandker Nurul Habib","doi":"10.1177/03611981221145133","DOIUrl":"10.1177/03611981221145133","url":null,"abstract":"<p><p>The COVID-19 pandemic had a significant impact on travel mode choices in cities across the world. Driven by perceptions of risk and the fear of infection, the pandemic resulted in an increased preference for private vehicles and active modes and a reduced preference for public transit and ride-sourcing. As travel behavior and modal preferences evolve, a key question is whether the pandemic will result in long-term changes to travel mode choices. This study uses data from a web-based survey to examine the factors influencing mode choices for non-commuting trips in the post-pandemic era. Specifically, it uses stated preference data to develop a random parameter mixed logit model, which is used to compare the elasticity of key variables across different income and age groups. The results of the study highlight the influence of sociodemographic attributes and pre-pandemic travel habits on anticipated post-pandemic mode choices. Additionally, the results suggest that frequent users of private vehicles, public transit, and active modes are likely to continue to use these modes post-pandemic. Furthermore, the results highlight the potential for the perception of shared modes to influence post-pandemic mode choice decisions. The results of the study offer insights into policy measures that could be applied to address the increased use of private vehicles and reduced use of transit during the pandemic, while also emphasizing the need to ensure that certain segments of the population can maintain a sufficient level of mobility and access to transport.</p>","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":"2677 1","pages":"199-217"},"PeriodicalIF":1.6,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10071185/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42975477","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-30DOI: 10.1177/03611981231171923
Martín Scavone, Samer W. Katicha, Gerardo W. Flintsch, Eugene Amarh
Transverse joints are the weakest element of jointed pavements, and when these joints lack structural capacity, the onset of load-related distress is imminent. The most widespread measurement of the joints’ structural performance is the Load Transfer Efficiency Index (LTE), a ratio of the deflection of the two adjoining slabs. LTE can easily be assessed with a falling weight deflectometer, but this test procedure is not advisable for evaluation at the network level because of user safety concerns and because it can be excessively time-consuming. Traffic speed deflection devices like the traffic speed deflectometer (TSD) are suitable devices for network-level pavement structural evaluation. Yet, as of today, no interpretation technique to get structural health metrics for jointed pavements from TSD data has been published. In this paper, a backcalculation scheme based on slab theory is proposed to estimate the joints’ LTE from TSD deflection velocity measurements. The backcalculation problem formulation and its numerical solution using fast procedures are described in detail. The approach is tested with TSD data collected on the MnROAD test track. Overall, it was found that the backcalculation converges to reasonable estimates of the pavement structural properties and can furnish LTE estimates for most transverse joints from 5 cm-resolution TSD data, all at a reasonable computational cost. This allows for corridor-wide LTE assessment of a pavement’s joints using TSD measurements.
{"title":"Estimating Load Transfer Efficiency for Jointed Pavements from TSD Deflection Velocity Measurements","authors":"Martín Scavone, Samer W. Katicha, Gerardo W. Flintsch, Eugene Amarh","doi":"10.1177/03611981231171923","DOIUrl":"https://doi.org/10.1177/03611981231171923","url":null,"abstract":"Transverse joints are the weakest element of jointed pavements, and when these joints lack structural capacity, the onset of load-related distress is imminent. The most widespread measurement of the joints’ structural performance is the Load Transfer Efficiency Index (LTE), a ratio of the deflection of the two adjoining slabs. LTE can easily be assessed with a falling weight deflectometer, but this test procedure is not advisable for evaluation at the network level because of user safety concerns and because it can be excessively time-consuming. Traffic speed deflection devices like the traffic speed deflectometer (TSD) are suitable devices for network-level pavement structural evaluation. Yet, as of today, no interpretation technique to get structural health metrics for jointed pavements from TSD data has been published. In this paper, a backcalculation scheme based on slab theory is proposed to estimate the joints’ LTE from TSD deflection velocity measurements. The backcalculation problem formulation and its numerical solution using fast procedures are described in detail. The approach is tested with TSD data collected on the MnROAD test track. Overall, it was found that the backcalculation converges to reasonable estimates of the pavement structural properties and can furnish LTE estimates for most transverse joints from 5 cm-resolution TSD data, all at a reasonable computational cost. This allows for corridor-wide LTE assessment of a pavement’s joints using TSD measurements.","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135641985","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：