Papers
Journal articles, conference proceedings, and book chapters in reversed chronological order. generated by jekyll-scholar.
2024
- JournalUnderstanding Electric Vehicle Ownership Using Data Fusion and Spatial ModelingMelrose Pan, Majbah Uddin, and Hyeonsup LimTransportation Research Part D: Transport and Environment 2024
The global shift toward electric vehicles (EVs) for climate sustainability lacks comprehensive insights into the impact of the built environment on EV ownership, especially in varying spatial contexts. This study, focusing on New York State, integrates data fusion techniques across diverse datasets to examine the influence of socioeconomic and built environmental factors on EV ownership. The utilization of spatial regression models reveals consistent coefficient values, highlighting the robustness of the results, with the Spatial Lag model better at capturing spatial autocorrelation. Results underscore the significance of charging stations within a 10-mile radius, indicative of a preference for convenient charging options influencing EV ownership decisions. Factors like higher education levels, lower rental populations, and concentrations of older population align with increased EV ownership. Utilizing publicly available data offers a more accessible avenue for understanding EV ownership across regions, complementing traditional survey approaches.
@article{trd2024, author = {Pan, Melrose and Uddin, Majbah and Lim, Hyeonsup}, title = {Understanding Electric Vehicle Ownership Using Data Fusion and Spatial Modeling}, journal = {Transportation Research Part D: Transport and Environment}, volume = {127}, year = {2024}, number = {}, pages = {104075}, doi = {10.1016/j.trd.2024.104075}, } - JournalImproving the Accuracy of Freight Mode Choice Models: A Case Study Using the 2017 CFS PUF Data Set and Ensemble Learning TechniquesExpert Systems with Applications 2024
The US Census Bureau has collected two rounds of experimental data from the Commodity Flow Survey, providing shipment-level characteristics of nationwide commodity movements, published in 2012 (i.e., Public Use Microdata) and in 2017 (i.e., Public Use File). With this information, data-driven methods have become increasingly valuable for understanding detailed patterns in freight logistics. In this study, we used the 2017 Commodity Flow Survey Public Use File data set to explore building a high-performance freight mode choice model, considering three main improvements: (1) constructing local models for each separate commodity/industry category; (2) extracting useful geographical features, particularly the derived distance of each freight mode between origin/destination zones; and (3) applying additional ensemble learning methods such as stacking or voting to combine results from local and global models for improved performance. The proposed method achieved over 92% accuracy without incorporating external information, outperforming most previously proposed models by a margin of 10%. Furthermore, SHAP (Shapely Additive Explanations) values were computed to explain the outputs and major patterns obtained from the proposed model. The model framework could enhance the performance and interpretability of existing freight mode choice models.
@article{eswa2024, author = {Liu, Diyi and Lim, Hyeonsup and Uddin, Majbah and Liu, Yuandong and Hwang, Ho-Ling and Chin, Shih-Miao}, title = {Improving the Accuracy of Freight Mode Choice Models: A Case Study Using the 2017 CFS PUF Data Set and Ensemble Learning Techniques}, journal = {Expert Systems with Applications}, volume = {240}, year = {2024}, pages = {122478}, doi = {10.1016/j.eswa.2023.122478}, } - JournalOptimizing Hydrogen Fueling Infrastructure Plans on Freight Corridors for Heavy-Duty Fuel Cell Electric VehiclesSAE International Journal of Sustainable Transportation, Energy, Environment, & Policy 2024
The development of a future hydrogen energy economy will require the development of several hydrogen market and industry segments including a hydrogen-based commercial freight transportation ecosystem. For a sustainable freight transportation ecosystem, the supporting fueling infrastructure and the associated vehicle powertrains making use of hydrogen fuel will need to be co-established. This article introduces the OR-AGENT (Optimal Regional Architecture Generation for Electrified National Transportation) tool developed at the Oak Ridge National Laboratory, which has been used to optimize the hydrogen refueling infrastructure requirements on the I-75 corridor for heavy-duty (HD) fuel cell electric commercial vehicles (FCEV). This constraint-based optimization model considers existing fueling locations, regional-specific vehicle fuel economy and weight, vehicle origin and destination (O-D), and vehicle volume by class and infrastructure costs to characterize in-mission refueling requirements for a given freight corridor. The authors applied this framework to determine the ideal public access locations for hydrogen refueling (constrained by existing fueling stations), the minimal viable cost to deploy sufficient hydrogen fuel dispensers, and associated equipment, to accommodate a growing population of hydrogen fuel cell trucks. The framework discussed in this article can be expanded and applied to a larger interstate system, expanded regional corridor, or other transportation network. This article is the third in a series of papers that defined the model development to optimize a national hydrogen refueling infrastructure ecosystem for HD commercial vehicles.
@article{sae2024, author = {Siekmann, Adam and Sujan, Vivek and Uddin, Majbah and Liu, Yuandong and Xie, Fei}, title = {Optimizing Hydrogen Fueling Infrastructure Plans on Freight Corridors for Heavy-Duty Fuel Cell Electric Vehicles}, journal = {SAE International Journal of Sustainable Transportation, Energy, Environment, & Policy}, volume = {5}, year = {2024}, number = {1}, doi = {10.4271/13-05-01-0008}, } - JournalAssignment of Freight Traffic in a Large-Scale Intermodal Network under UncertaintyMajbah Uddin, Nathan Huynh, and Fahim AhmedHighlights of Sustainability 2024
This paper presents a methodology for freight traffic assignment in a large-scale road-rail intermodal network under uncertainty. Network uncertainties caused by natural disasters have dramatically increased in recent years. Several of these disasters (e.g., Hurricane Sandy, Mississippi River Flooding, and Hurricane Harvey) severely disrupted the U.S. freight transportation network, and consequently, the supply chain. To account for these network uncertainties, a stochastic freight traffic assignment model is formulated. An algorithmic framework, involving the sample average approximation and gradient projection algorithm, is proposed to solve this challenging problem. The developed methodology is tested on the U.S. intermodal network with freight flow data from the Freight Analysis Framework. The experiments consider three types of natural disasters that have different risks and impacts on transportation networks: earthquakes, hurricanes, and floods. It is found that for all disaster scenarios, freight ton-miles are higher compared to the base case without uncertainty. The increase in freight ton-miles is the highest under the flooding scenario; this is because there are more states in the flood-risk areas, and they are scattered throughout the U.S.
@article{hsus2024, author = {Uddin, Majbah and Huynh, Nathan and Ahmed, Fahim}, title = {Assignment of Freight Traffic in a Large-Scale Intermodal Network under Uncertainty}, journal = {Highlights of Sustainability}, volume = {3}, year = {2024}, number = {1}, pages = {1--15}, doi = {10.54175/hsustain3010001}, } - ConferenceA Spatial-Temporal Analysis of Travel Time Gap and Inequality Between Public Transportation and Personal VehiclesMelrose Pan, Christa Brelsford, and Majbah UddinInternational Conference on Transportation and Development 2024
The increased use of personal vehicles presents environmental challenges, prompting the exploration of public transportation as an affordable, eco-friendly alternative. However, obstacles like fixed schedules, limited routes, and extended travel times impede widespread adoption. This study investigates the temporal evolution of spatial inequality in the travel time gap between public transportation and personal vehicles, reflecting disparities across states and time periods. Analyzing Census Transportation Planning Program data for six northeastern states in 2010 and 2016 reveals no significant increase in the travel time gap, but notable growth in inequality in a few urban and disadvantaged communities. Comprehending these trends is vital for fostering equitable advancements in transportation infrastructure and enhancing public transportation competitiveness.
@inproceedings{ictd-pan-2024, title = {A Spatial-Temporal Analysis of Travel Time Gap and Inequality Between Public Transportation and Personal Vehicles}, author = {Pan, Melrose and Brelsford, Christa and Uddin, Majbah}, booktitle = {International Conference on Transportation and Development}, year = {2024}, }
2023
- JournalAn Interpretable Machine Learning Framework to Understand Bikeshare Demand before and during the COVID-19 Pandemic in New York CityMajbah Uddin, Ho-Ling Hwang, and Md Sami HasnineTransportation Planning and Technology 2023
In recent years, bikesharing systems have become increasingly popular as affordable and sustainable micromobility solutions. Advanced mathematical models such as machine learning are required to generate good forecasts for bikeshare demand. To this end, this study proposes a machine learning modeling framework to estimate hourly demand in a large-scale bikesharing system. Two Extreme Gradient Boosting models were developed: one using data from before the COVID-19 pandemic (March 2019 to February 2020) and the other using data from during the pandemic (March 2020 to February 2021). Furthermore, a model interpretation framework based on SHapley Additive exPlanations was implemented. Based on the relative importance of the explanatory variables considered in this study, share of female users and hour of day were the two most important explanatory variables in both models. However, the month variable had higher importance in the pandemic model than in the pre-pandemic model.
@article{tpt2023, author = {Uddin, Majbah and Hwang, Ho-Ling and Hasnine, Md Sami}, title = {An Interpretable Machine Learning Framework to Understand Bikeshare Demand before and during the COVID-19 Pandemic in New York City}, journal = {Transportation Planning and Technology}, volume = {}, year = {2023}, number = {}, doi = {10.1080/03081060.2023.2201280}, } - JournalExamining Rail Transportation Route of Crude Oil in the US Using Crowdsourced Social Media DataTransportation Research Record 2023
Safety issues associated with transporting crude oil by rail have been a concern since the boom of US domestic shale oil production in 2012. During the last decade, over 300 crude oil by rail incidents have occurred in the US. Some of them have caused adverse consequences including fire and hazardous materials leakage. However, only limited information on the routes of crude-on-rail and their associated risks is available to the public. To this end, this study proposes an unconventional way to reconstruct the crude-on-rail routes using geotagged photos harvested from the Flickr website. The proposed method links the geotagged photos of crude oil trains posted online with national railway networks to identify potential railway segments those crude oil trains were traveling on. A shortest path-based method was then applied to infer the complete crude-on-rail routes, by utilizing the confirmed railway segments as well as their movement direction information. Validation of the inferred routes was performed using a public map and official crude oil incident data. Results suggested that the inferred routes based on geotagged photos have high coverage, with approximately 96% of the documented crude oil incidents aligned with the reconstructed crude-on-rail network. The inferred crude oil train routes were found to pass through many metropolitan areas with dense populations, who are exposed to potential risk. This finding could improve situation awareness for policymakers and transportation planners. In addition, with the inferred routes, this study establishes a good foundation for future crude oil train risk analysis along the rail route.
@article{trr2023, author = {Liu, Yuandong and Uddin, Majbah and Chin, Shih-Miao and Hwang, Ho-Ling and Chen, Jiaoli}, title = {Examining Rail Transportation Route of Crude Oil in the US Using Crowdsourced Social Media Data}, journal = {Transportation Research Record}, volume = {}, year = {2023}, number = {}, doi = {10.1177/03611981231170632}, } - JournalFactors Influencing Mode Choice of Adults with Travel-Limiting DisabilityMajbah Uddin, Melrose Pan, and Ho-Ling HwangJournal of Transport & Health 2023
Despite the plethora of research devoted to analyzing the impact of disability on travel behavior, not enough studies have investigated the varying impact of social and environmental factors on the mode choice of people with disabilities that restrict their ability to use transportation modes efficiently. This research gap can be addressed by investigating the factors influencing the mode choice behavior of people with travel-limiting disabilities, which can inform the development of accessible and sustainable transportation systems. Additionally, such studies can provide insights into the social and economic barriers faced by this population group, which can help policymakers to promote social inclusion and equity. This study utilized a Random Parameters Logit model to identify the individual, trip, and environmental factors that influence mode selection among people with travel-limiting disabilities. Using the 2017 National Household Travel Survey data for New York State, which included information on respondents with travel-limiting disabilities, the analysis focused on a sample of 8,016 people. In addition, climate data from the National Oceanic and Atmospheric Administration were integrated as additional explanatory variables in the modeling process. The results revealed that people with disabilities may be inclined to travel longer distances walking in the absence of suitable accommodation facilities for other transportation modes. Furthermore, people were less inclined to walk during summer and winter, indicating a need to consider weather conditions as a significant determinant of mode choice. Moreover, low-income people with disabilities were more likely to rely on public transport or walking. Based on this study’s findings, transportation agencies could design infrastructure and plan for future expansions that is more inclusive and accessible, thus catering to the mobility needs of people with travel-limiting disabilities.
@article{jth2023, author = {Uddin, Majbah and Pan, Melrose and Hwang, Ho-Ling}, title = {Factors Influencing Mode Choice of Adults with Travel-Limiting Disability}, journal = {Journal of Transport & Health}, volume = {33}, year = {2023}, number = {101714}, doi = {10.1016/j.jth.2023.101714}, } - ConferenceExploring the Effects of Population and Employment Characteristics on Truck Flows: An Anlysis of NextGen NHTS Origin-Destination DataMajbah Uddin, Yuandong Liu, and Hyeonsup LimInternational Conference on Transportation and Development 2023
Truck transportation remains the dominant mode of US freight transportation because of its advantages, such as the flexibility of accessing pickup and drop-off points and faster delivery. Because of the massive freight volume transported by trucks, understanding the effects of population and employment characteristics on truck flows is critical for better transportation planning and investment decisions. The US Federal Highway Administration published a truck travel origin-destination data set as part of the Next Generation National Household Travel Survey program. This data set contains the total number of truck trips in 2020 within and between 583 predefined zones encompassing metropolitan and nonmetropolitan statistical areas within each state and Washington, DC. In this study, origin-destination-level truck trip flow data was augmented to include zone-level population and employment characteristics from the US Census Bureau. Census population and County Business Patterns data were included. The final data set was used to train a machine learning algorithm-based model, Extreme Gradient Boosting (XGBoost), where the target variable is the number of total truck trips. Shapley Additive ExPlanation (SHAP) was adopted to explain the model results. Results showed that the distance between the zones was the most important variable and had a nonlinear relationship with truck flows.
@inproceedings{ictd-uddin-2023, title = {Exploring the Effects of Population and Employment Characteristics on Truck Flows: An Anlysis of NextGen NHTS Origin-Destination Data}, author = {Uddin, Majbah and Liu, Yuandong and Lim, Hyeonsup}, booktitle = {International Conference on Transportation and Development}, year = {2023}, } - ConferenceMobility Gaps between Low-Income and Not Low-Income Households: A Case Study in New York StateYuandong Liu, and Majbah UddinInternational Conference on Transportation and Development 2023
Understanding the travel challenges faced by low-income residents has always been and continues to be one of the most important transportation equity topics. This study aims to explore the mobility gaps between low-income households (HHs) and not low-income HHs, and how the gaps vary within different socio-demographic population groups in New York State (NYS). The latest National Household Travel Survey data was used as the primary data source for the analysis. The study first employed the K-prototype clustering algorithm to categorize the HHs in NYS based on their socio-demographic attributes. Five population groups were identified based on nine different household (HH) features such as HH size, vehicle ownership, and elderly status of its members. Then, the mobility differences, measured by trip frequency, trip distance, travel time, and person miles traveled, were examined among the five population groups. Results suggest that the individuals in low-income HHs consistently took fewer trips and made shorter trips compared to their not low-income counterparts in NYS. The travel distance gaps were most obvious among white HHs with more vehicles than drivers. In addition, while the population from low-income HHs made shorter trips on average (2.7 mi shorter per trip), they experienced longer travel time than those from not low-income HHs (1.8 min longer per trip). These key findings provide a deeper understanding of the travel behavior disparities between low-income and not low-income households. The findings could also support policymakers and transportation planners in addressing the critical needs of residents in low-income households in NYS and provide inputs for designing a more equitable transportation system.
@inproceedings{ictd-liu-2023, title = {Mobility Gaps between Low-Income and Not Low-Income Households: A Case Study in New York State}, author = {Liu, Yuandong and Uddin, Majbah}, booktitle = {International Conference on Transportation and Development}, year = {2023}, }
2022
- JournalA Comparative Study of Machine Learning Algorithms for Industry-Specific Freight Generation ModelSustainability 2022
According to Bureau of Transportation Statistics, the U.S. transportation system handled 14,329 million ton-miles of freight per day in 2020. Understanding the generation of these freight shipments is crucial for transportation researchers, planners, and policymakers to design and plan for a more efficient and connected freight transportation system. Traditionally, the freight generation modeling has been based on Ordinary Least Square (OLS) regression, although more advanced Machine Learning (ML) algorithms have been evaluated and proven to have excellent performance in various transportation applications in recent years. Furthermore, one modeling approach applied for one industry might not always be applicable for another as their freight generation logics can be quite different. The objective of this study is to apply and evaluate alternative ML algorithms in the estimation of freight generation for each of 45 industry types. Seven alternative ML algorithms, along with the base OLS regression, were evaluated and compared. In addition, the study considered different combinations of variables in both the original and logarithmic form as well as hyperparameters of those ML algorithms in the model selection for each industry type. The results showed statistically significant improvements in the root mean square error reduction by the alternative ML algorithms over the OLS for over 80% of cases. The study suggests utilizing the alternative ML algorithms can reduce the root mean square error by about 30%, depending on industry types.
@article{su142215367, author = {Lim, Hyeonsup and Uddin, Majbah and Liu, Yuandong and Chin, Shih-Miao and Hwang, Ho-Ling}, title = {A Comparative Study of Machine Learning Algorithms for Industry-Specific Freight Generation Model}, journal = {Sustainability}, volume = {14}, year = {2022}, number = {22}, article-number = {15367}, issn = {2071-1050}, doi = {10.3390/su142215367}, } - ConferenceModeling Freight Traffic Demand and Highway Networks for Hydrogen Fueling Station Planning: A Case Study of U.S. Interstate 75 CorridorAnnual International Green Energy Conference 2022
The use of hydrogen as an alternative transportation fuel has gained much interest in recent years. Hydrogen can be utilized in electric vehicles equipped with hydrogen powertrains (including hydrogen internal combustion engines or fuel cells). Given that most of the freight in the U.S. is transported via diesel trucks, transition to hydrogen fuel would help achieve significant environmental benefits as well as accelerate the decarbonization of the freight transportation sector. This paper presents the methodology and results of a case study on modeling freight traffic demand and highway networks based on publicly available data for the Interstate 75 freight corridor. The purpose of this study is to prepare input traffic and network data that can support the planning of a hydrogen fueling station infrastructure. In particular, the data can be used for siting and characterizing an optimized framework of hydrogen fueling stations from candidate diesel stations along the Interstate 75 corridor. The methodologies developed and presented in this paper may be readily expanded and applied to any transport corridor given the data availability. This paper is the first in a series that will build out a comprehensive model to optimize a consolidated national hydrogen refueling infrastructure eco-system targeted at commercial vehicles.
@inproceedings{uddin2022modeling, title = {Modeling Freight Traffic Demand and Highway Networks for Hydrogen Fueling Station Planning: A Case Study of U.S. Interstate 75 Corridor}, author = {Uddin, Majbah and Liu, Yuandong and Xie, Fei and Sujan, Vivek and Siekmann, Adam}, booktitle = {Annual International Green Energy Conference}, year = {2022}, } - ConferenceProviding Levelized Cost and Waiting Time Inputs for HDV Hydrogen Refueling Station Planning: A Case Study of U.S. I-75 CorridorAnnual International Green Energy Conference 2022
The use of hydrogen as an alternative transportation fuel has gained much interest in recent years. Hydrogen can be utilized in electric vehicles equipped with hydrogen powertrains (including hydrogen internal combustion engines or fuel cells). Given that most of the freight in the U.S. is transported via diesel trucks, transition to hydrogen fuel would help achieve significant environmental benefits as well as accelerate the decarbonization of the freight transportation sector. This paper presents the methodology and results of a case study on modeling freight traffic demand and highway networks based on publicly available data for the Interstate 75 freight corridor. The purpose of this study is to prepare input traffic and network data that can support the planning of a hydrogen fueling station infrastructure. In particular, the data can be used for siting and characterizing an optimized framework of hydrogen fueling stations from candidate diesel stations along the Interstate 75 corridor. The methodologies developed and presented in this paper may be readily expanded and applied to any transport corridor given the data availability. This paper is the first in a series that will build out a comprehensive model to optimize a consolidated national hydrogen refueling infrastructure eco-system targeted at commercial vehicles.
@inproceedings{liu2022providing, title = {Providing Levelized Cost and Waiting Time Inputs for HDV Hydrogen Refueling Station Planning: A Case Study of U.S. I-75 Corridor}, author = {Liu, Yuandong and Siekmann, Adam and Sujan, Vivek and Uddin, Majbah and Xie, Fei and Ou, Shawn}, booktitle = {Annual International Green Energy Conference}, year = {2022}, }
2021
- JournalModeling Freight Mode Choice Using Machine Learning Classifiers: A Comparative Study Using the Commodity Flow Survey (CFS) DataMajbah Uddin, Sabreena Anowar, and Naveen EluruTransportation Planning and Technology 2021
This study explores the usefulness of machine learning classifiers for modeling freight mode choice. We investigate eight commonly used machine learning classifiers, namely Naïve Bayes, Support Vector Machine, Artificial Neural Network, K-Nearest Neighbors, Classification and Regression Tree, Random Forest, Boosting and Bagging, along with the classical Multinomial Logit model. US 2012 Commodity Flow Survey data are used as the primary data source; we augment it with spatial attributes from secondary data sources. The performance of the classifiers is compared based on prediction accuracy results. The current research also examines the role of sample size and training-testing data split ratios on the predictive ability of the various approaches. In addition, the importance of variables is estimated to determine how the variables influence freight mode choice. The results show that the tree-based ensemble classifiers perform the best. Specifically, Random Forest produces the most accurate predictions, closely followed by Boosting and Bagging. With regard to variable importance, shipment characteristics, such as shipment distance, industry classification of the shipper and shipment size, are the most significant factors for freight mode choice decisions.
@article{uddin2021modeling, title = {Modeling Freight Mode Choice Using Machine Learning Classifiers: A Comparative Study Using the Commodity Flow Survey (CFS) Data}, author = {Uddin, Majbah and Anowar, Sabreena and Eluru, Naveen}, journal = {Transportation Planning and Technology}, volume = {44}, number = {5}, pages = {543--559}, year = {2021}, }
2020
- JournalInjury Severity Analysis of Truck-Involved Crashes under Different Weather ConditionsMajbah Uddin, and Nathan HuynhAccident Analysis & Prevention 2020
This paper investigates truck-involved crashes to determine the statistically significant factors that contribute to injury severity under different weather conditions. The analysis uses crash data from the state of Ohio between 2011 and 2015 available from the Highway Safety Information System. To determine if weather conditions should be considered separately for truck safety analyses, parameter transferability tests are conducted; the results suggest that weather conditions should be modeled separately with a high level of statistical confidence. To this end, three separate mixed logit models are estimated for three different weather conditions: normal, rain and snow. The estimated models identify a variety of statistically significant factors influencing the injury severity. Different weather conditions are found to have different contributing effects on injury severity in truck-involved crashes. Rural, rear-end and sideswipe crash parameters were found to have significantly different levels of impact on injury severity. Based on the findings of this study, several countermeasures are suggested: 1) safety and enforcement programs should focus on female truck drivers, 2) a variable speed limit sign should be used to lower speeds of trucks during rainy condition, and 3) trucks should be restricted or prohibited on non-interstates during rainy and snowy conditions. These countermeasures could reduce the number and severity of truck-involved crashes under different weather conditions.
@article{uddin2020injury, title = {Injury Severity Analysis of Truck-Involved Crashes under Different Weather Conditions}, author = {Uddin, Majbah and Huynh, Nathan}, journal = {Accident Analysis \& Prevention}, volume = {141}, pages = {105529}, year = {2020}, publisher = {Pergamon}, } - JournalModel for Collaboration among Carriers to Reduce Empty Container Truck TripsMajbah Uddin, and Nathan HuynhInformation 2020
In recent years, intermodal transport has become an increasingly attractive alternative to freight shippers. However, the current intermodal freight transport is not as efficient as it could be. Oftentimes an empty container needs to be transported from the empty container depot to the shipper, and conversely, an empty container needs to be transported from the receiver to the empty container depot. These empty container movements decrease the freight carrier’s profit, as well as increase traffic congestion, decrease roadway safety, and add unnecessary emissions to the environment. To this end, our study evaluates a potential collaboration strategy to be used by carriers for domestic intermodal freight transport based on an optimization approach to reduce the number of empty container trips. A binary integer-linear programming model is developed to determine each freight carrier’s optimal schedule while minimizing its operating cost. The model ensures that the cost for each carrier with collaboration is less than or equal to its cost without collaboration. It also ensures that average savings from the collaboration are shared equally among all participating carriers. Additionally, two stochastic models are provided to account for uncertainty in truck travel times. The proposed collaboration strategy is tested using empirical data and is demonstrated to be effective in meeting all of the shipment constraints.
@article{uddin2020model, title = {Model for Collaboration among Carriers to Reduce Empty Container Truck Trips}, author = {Uddin, Majbah and Huynh, Nathan}, journal = {Information}, volume = {11}, number = {8}, pages = {377}, year = {2020}, publisher = {MDPI}, } - ConferenceDelivering Contextual Knowledge and Critical Skills of Disruptive Technologies through Problem-Based Learning in Research Experiences for Undergraduates Setting127th ASEE Annual Conference 2020
The recent development in transportation, such as energy-efficient and autonomous vehicles, defines a condition for the students in transportation engineering. Students in the field of transportation engineering should be ready upon their graduation with new knowledge and skills that are compatible with the need of the industry and sustainable engineering practices.During summers of 2018 and 2019, we developed and implemented an eight-week program to increase the knowledge and skills of students coming from multidisciplinary fields related to autonomous vehicles. Problem of “How much will platooning reduce fuel consumption and emissions per vehicle mile traveled?” was instrumentalized in subsequent activities to introduce the comprehensive knowledge structure of autonomous vehicles.The engineering concept of reducing the cost and sustainability was embedded in the leading research question that helped us to develop and implement activities on an overall knowledge structure in autonomous vehicles. The goal of using problem-based learning activities was not to encourage the students to focus on reaching the solution merely. We aimed to introduce the multidisciplinary knowledge and critical skills aspects of learning about disruptive technologies.In this paper, we will discuss how a multidisciplinary research approach was incorporated into a problem-based learning activity. The students were introduced the subjects related to math, physics, computer science, and biology as the integration of the knowledge structure of autonomous vehicles. We will also present the results on students’ use of critical skills such as machine learning and computer programming.
@inproceedings{comert2020delivering, title = {Delivering Contextual Knowledge and Critical Skills of Disruptive Technologies through Problem-Based Learning in Research Experiences for Undergraduates Setting}, author = {Comert, Gurcan and Pierce, Charles and Berk, Zulfikar and Huynh, Nathan and Petrulis, Robert and Uddin, Majbah}, booktitle = {127th ASEE Annual Conference}, year = {2020}, } - PreprintDeterminants of Surgical Case On-Time Start and On-Time Finish in Perioperative Services2020
Efficient use of the operating room (OR) is crucial for any hospital. One of the major inefficiencies in the OR is surgical cases not starting or finishing on time as scheduled. When a case is delayed, it affects all subsequent cases in that OR. This study uses discrete choice analysis to determine the significant factors, including team familiarity, that influence OR case on-time start and finish. A case is considered on-time if the documented procedure start and finish times are no more than 10 minutes after the scheduled start and finish times. The analysis uses surgical case data from a large tertiary referral hospital and academic center in Greenville, South Carolina. The case data includes all surgical cases (15,091) performed during regular workdays in 2013. Two binary logit models are developed: one for case on-time start and one for case on-time finish. Results indicate that higher team familiarity between surgeon and anesthesiologist, surgeon and circulating nurse, surgeon and scrub nurse, and surgeon and CRNA improve the likelihood of an OR case on-time start and on-time finish. This finding indicates that the OR scheduling staff in the study hospital make a concerted effort to schedule the surgical teams with members who have worked well together in the past.
@article{uddin2020determinants, title = {Determinants of Surgical Case On-Time Start and On-Time Finish in Perioperative Services}, author = {Uddin, Majbah and Fredendall, Lawrence and Huynh, Nathan and Taaffe, Kevin and Allen, Robert}, year = {2020}, publisher = {Preprints}, }
2019
- JournalReliable Routing of Road–Rail Intermodal Freight under UncertaintyMajbah Uddin, and Nathan HuynhNetworks and Spatial Economics 2019
Transportation infrastructures, particularly those supporting intermodal freight, are vulnerable to natural disasters and man-made disasters that could lead to severe service disruptions. These disruptions can drastically degrade the capacity of a transportation mode and consequently have adverse impacts on intermodal freight transport and freight supply chain. To address service disruption, this paper develops a model to reliably route freight in a road-rail intermodal network. Specifically, the model seeks to provide the optimal route via road segments (highway links), rail segments (rail lines), and intermodal terminals for freight when the network is subject to capacity uncertainties. To ensure reliability, the model plans for reduced network link, node, and intermodal terminal capacity. A major contribution of this work is that a framework is provided to allow decision makers to determine the amount of capacity reduction to consider in planning routes to obtain a user-specified reliability level. The proposed methodology is demonstrated using a real-world intermodal network in the Gulf Coast, Southeastern, and Mid-Atlantic regions of the United States. It is found that the total system cost increases with the level of capacity uncertainty and with increased confidence levels for disruptions at links, nodes, and intermodal terminals.
@article{uddin2019reliable, title = {Reliable Routing of Road--Rail Intermodal Freight under Uncertainty}, author = {Uddin, Majbah and Huynh, Nathan}, journal = {Networks and Spatial Economics}, volume = {19}, number = {3}, pages = {929--952}, year = {2019}, publisher = {Springer US}, } - DissertationDevelopment of Models for Road-Rail Intermodal Freight Network under UncertaintyMajbah Uddin2019
Freight activities are directly related to a country’s Gross Domestic Product and economic viability. In recent years, the U.S. transportation system supports a growing volume of freight, and it is anticipated that this trend will continue in the coming years. To support the projected increase in freight volume, an efficient, reliable, and low-cost freight logistics system is necessary to keep the U.S. competitive in the global market. In addition, intermodal transport is becoming an increasingly attractive alternative to shippers, and this trend is likely to continue as state and federal agencies are considering policies to induce a freight modal shift from road to intermodal to alleviate highway congestion and emissions. However, the U.S. intermodal freight transport network is vulnerable to various disruptions. A disruptive event can be a natural disaster or a man- made disaster. A number of such disasters have occurred recently that severely impacted the freight transport network. To this end, this dissertation presents four studies where mathematical models are developed for the road-rail intermodal freight transport considering the network uncertainties. The first study proposes a methodology for freight traffic assignment in large- scale road-rail intermodal networks. To obtain the user-equilibrium freight flows, gradient projection (GP) algorithm is proposed. The developed methodology is tested on the U.S. intermodal network using the 2007 freight demands for truck, rail, and road-rail intermodal from the Freight Analysis Framework, version 3, (FAF3). The results indicate that the proposed methodology’s projected flow pattern is similar to the FAF3 assignment. The second study formulates a stochastic model for the aforementioned freight traffic assignment problem under uncertainty. To solve this challenging problem, an algorithmic framework, involving the sample average approximation and GP algorithm, is proposed. The experiments consider four types of natural disasters that have different risks and impacts on the transportation network: earthquake, hurricane, tornado, and flood. The results demonstrate the feasibility of the model and algorithmic framework to obtain freight flows for a realistic-sized network in reasonable time. The third study presents a model for the routing of multicommodity freight in an intermodal network under disruptions. A stochastic mixed integer program is formulated, which minimizes not only operational costs of different modes and transfer costs at terminals but also penalty costs associated with unsatisfied demands. The routes generated by the model are found to be more robust than those typically used by freight carriers. Lastly, the fourth study develops a model to reliably route freight in a road-rail intermodal network. Specifically, the model seeks to provide the optimal route via road segments, rail segments, and intermodal terminals for freight when the network is subject to capacity uncertainties. The proposed methodology is demonstrated using a real-world intermodal network in the Gulf Coast, Southeastern, and Mid-Atlantic regions of the U.S.
@phdthesis{uddin2019development, title = {Development of Models for Road-Rail Intermodal Freight Network under Uncertainty}, author = {Uddin, Majbah}, year = {2019}, school = {University of South Carolina}, }
2018
- JournalFactors Influencing Injury Severity of Crashes Involving HAZMAT TrucksMajbah Uddin, and Nathan HuynhInternational Journal of Transportation Science and Technology 2018
Most Cited Article Award
This paper investigates factors affecting injury severity of crashes involving HAZMAT large trucks. It uses the crash data in the state of California from the Highway Safety Information System, from 2005 to 2011. The explanatory factors include the occupant, crash, vehicle, roadway, environmental, and temporal characteristics. Both fixed- and random-parameters ordered probit models of injury severity (where possible outcomes are major, minor, and no injury) were estimated; the random-parameters model captures possible unobserved effects related to factors not present in the data. The model results indicate that the occupants being male, truck drivers, crashes occurring in rural locations, under dark-unlighted, under dark-lighted conditions, and on weekdays were associated with increased probability of major injuries. Conversely, the older occupants (age 60 and over), truck making a turn, rear-end collision, collision with an object, crashes occurring on non-interstate highway, higher speed limit highway (≥65 mph), and flat terrain were associated with decreased probability of major injuries. This study has identified factors that explain injury severities of crashes involving HAZMAT, and as such, it could be used by policy makers and transportation agencies to improve HAZMAT transport, and thus, the overall highway safety.
@article{uddin2018factors, title = {Factors Influencing Injury Severity of Crashes Involving HAZMAT Trucks}, author = {Uddin, Majbah and Huynh, Nathan}, journal = {International Journal of Transportation Science and Technology}, volume = {7}, number = {1}, pages = {1--9}, year = {2018}, publisher = {Elsevier B.V.}, note = {Most Cited Article Award}, } - JournalAssessing Operating Room Turnover Time via the Use of Mobile ApplicationMajbah Uddin, Robert Allen, Nathan Huynh, Jose Vidal, Kevin Taaffe, Lawrence Fredendall, and Joel GreensteinmHealth 2018
Background: Improving operating room (OR) utilization is crucial to hospitals. This study examines the effectiveness of a mobile application co-developed with hospital staff to track OR turnover time (TOT). Methods: An Android-based app, named ORTimer, was used by staff in two OR units (GI-Lab and D-Core) of Greenville Memorial Hospital (GMH) in South Carolina. The staff used the app to record milestones and note delay reasons (if applicable). A total of 1,782 turnover observations from the GI-Lab and 694 turnover observations from the D-Core were collected for the study. Using data collected from the app and additional information from GMH’s electronic medical record system, a two-sample proportionality test was conducted to test the hypothesis that the use of the app improved OR turnover performance (i.e., the TOT is equal to or less than the allotted time). Results: The result of the hypothesis test indicates that a higher percentage of observations in the GI-Lab and D-Core met their turnover target time when the ORTimer app was used. Additionally, multiple regression analysis was used to identify significant factors that contribute to prolonged OR TOT and to estimate their impacts. Conclusions: The app serves as both a visual management tool as well as a TOT data collection tool. By identifying barriers to the on-time completion of the turnaround, the app allows for continuous improvement of the turnover process.
@article{uddin2018assessing, title = {Assessing Operating Room Turnover Time via the Use of Mobile Application}, author = {Uddin, Majbah and Allen, Robert and Huynh, Nathan and Vidal, Jose and Taaffe, Kevin and Fredendall, Lawrence and Greenstein, Joel}, journal = {mHealth}, volume = {4}, pages = {12}, year = {2018}, publisher = {AME Publishing Company}, } - JournalOperating Room Turnover Time Autocorrelation while using Mobile ApplicationsMajbah Uddin, Robert Allen, Nathan Huynh, Jose M Vidal, Kevin M Taaffe, Lawrence D Fredendall, and Joel S GreensteinmHealth 2018
@article{uddin2018operating, title = {Operating Room Turnover Time Autocorrelation while using Mobile Applications}, author = {Uddin, Majbah and Allen, Robert and Huynh, Nathan and Vidal, Jose M and Taaffe, Kevin M and Fredendall, Lawrence D and Greenstein, Joel S}, journal = {mHealth}, volume = {4}, pages = {38}, year = {2018}, publisher = {AME Publishing Company}, } - JournalPedestrian Injury Severity Analysis in Motor Vehicle Crashes in OhioMajbah Uddin, and Fahim AhmedSafety 2018
Best Paper Award
According to the National Highway Traffic Safety Administration, 116 pedestrians were killed in motor vehicle crashes in Ohio in 2015. However, no study to date has analyzed crashes in Ohio in order to explore the factors contributing to the pedestrian injury severity resulting from motor vehicle crashes. This study fills this gap by investigating the crashes involving pedestrians exclusively in Ohio. This study uses the crash data from the Highway Safety Information System, from 2009 to 2013. The explanatory factors include the pedestrian, driver, vehicle, crash, and roadway characteristics. Both fixed- and random-parameters ordered probit models of injury severity (where possible outcomes are major, minor, and possible/no injury) were estimated. The model results indicate that older pedestrian (65 and over), younger driver (less than 24), driving under influence (DUI), struck by truck, dark-unlighted roadways, six-lane roadways, and speed limits of 40 mph and 50 mph were all factors associated with more severe injuries to the pedestrians. Conversely, older driver (65 and over), passenger car, crash occurring in urban locations, daytime traffic off-peak (10 a.m. to 3:59 p.m.), weekdays, and daylight condition were all factors associated with less severe injuries. This study provides specific safety recommendations so that effective countermeasures can be developed and implemented by policy makers, which in turn will improve overall highway safety.
@article{uddin2018pedestrian, title = {Pedestrian Injury Severity Analysis in Motor Vehicle Crashes in Ohio}, author = {Uddin, Majbah and Ahmed, Fahim}, journal = {Safety}, volume = {4}, number = {2}, pages = {20}, year = {2018}, publisher = {MDPI}, note = {Best Paper Award} }
2017
- JournalTruck-Involved Crashes Injury Severity Analysis for Different Lighting Conditions on Rural and Urban RoadwaysMajbah Uddin, and Nathan HuynhAccident Analysis & Prevention 2017
This paper investigates factors affecting injury severity of crashes involving trucks for different lighting conditions on rural and urban roadways. It uses 2009–2013 Ohio crash data from the Highway Safety Information System. The explanatory factors include the occupant, vehicle, collision, roadway, temporal and environmental characteristics. Six separate mixed logit models were developed considering three lighting conditions (daylight, dark, and dark-lighted) on two area types (rural and urban). A series of log-likelihood ratio tests were conducted to validate that these six separate models by lighting conditions and area types are warranted. The model results suggest major differences in both the combination and the magnitude of impact of variables included in each model. Some variables were significant only in one lighting condition but not in other conditions. Similarly, some variables were found to be significant in one area type but not in other area type. These differences show that the different lighting conditions and area types do in fact have different contributing effects on injury severity in truck-involved crashes, further highlighting the importance of examining crashes based on lighting conditions on rural and urban roadways. Age and gender of occupant (who is the most severely injured in a crash), truck types, AADT, speed, and weather condition were found to be factors that have significantly different levels of impact on injury severity in truck-involved crashes.
@article{uddin2017truck, title = {Truck-Involved Crashes Injury Severity Analysis for Different Lighting Conditions on Rural and Urban Roadways}, author = {Uddin, Majbah and Huynh, Nathan}, journal = {Accident Analysis \& Prevention}, volume = {108}, pages = {44--55}, year = {2017}, publisher = {Elsevier B.V.}, } - JournalPavement Performance Evaluation Models for South CarolinaMd Mostaqur Rahman, Majbah Uddin, and Sarah L GassmanKSCE Journal of Civil Engineering 2017
This paper develops pavement performance evaluation models using data from primary and interstate highway systems in the state of South Carolina, USA. Twenty pavement sections are selected from across the state, and historical pavement performance data of those sections are collected. A total of 8 models were developed based on regression techniques, which include 4 for Asphalt Concrete (AC) pavements and 4 for Jointed Plain Concrete Pavements (JPCP). Four different performance indicators are considered as response variables in the statistical analysis: Present Serviceability Index (PSI), Pavement Distress Index (PDI), Pavement Quality Index (PQI), and International Roughness Index (IRI). Annual Average Daily Traffic (AADT), Free Flow Speed (FFS), precipitation, temperature, and soil type (soil Type A from Blue Ridge and Piedmont Region, and soil Type B from Coastal Plain and Sediment Region) are considered as predictor variables. Results showed that AADT, FFS, and precipitation have statistically significant effects on PSI and IRI for both JPCP and AC pavements. Temperature showed significant effect only on PDI and PQI (p < 0.01) for AC pavements. Considering soil type, Type B soil produced statistically higher PDI and PQI (p < 0.01) compared to Type A soil on AC pavements; whereas, Type B soil produced statistically higher IRI and PSI (p < 0.001) compared to Type A soil on JPCP pavements. Using the developed models, local transportation agencies could estimate future corrective actions, such as maintenance and rehabilitation, as well as future pavement performances.
@article{rahman2017pavement, title = {Pavement Performance Evaluation Models for South Carolina}, author = {Rahman, Md Mostaqur and Uddin, Majbah and Gassman, Sarah L}, journal = {KSCE Journal of Civil Engineering}, volume = {21}, number = {7}, pages = {2695--2706}, year = {2017}, publisher = {Korean Society of Civil Engineers}, } - Book ChapterData Analytics for Intermodal Freight Transportation ApplicationsNathan Huynh, Majbah Uddin, and Chu Cong Minh2017
With the growth of intermodal freight transportation, it is important that transportation planners and decision makers are knowledgeable about freight flow data to make informed decisions. This is particularly true with Intelligent Transportation Systems (ITS) offering new capabilities to intermodal freight transportation. Specifically, ITS enables access to multiple different data sources, but they have different formats, resolution, and timescales. Thus, knowledge of data science is essential to be successful in future ITS-enabled intermodal freight transportation system. This chapter discusses the commonly used descriptive and predictive data analytic techniques in intermodal freight transportation applications. These techniques cover the entire spectrum of univariate, bivariate, and multivariate analyses. In addition to illustrating how to apply these techniques through relatively simple examples, this chapter will also show how to apply them using the statistical software R. Additional exercises are provided for those who wish to apply the described techniques to more complex problems.
@incollection{huynh2017data, title = {Data Analytics for Intermodal Freight Transportation Applications}, author = {Huynh, Nathan and Uddin, Majbah and Minh, Chu Cong}, booktitle = {Data Analytics for Intelligent Transportation Systems}, volume = {1}, pages = {241--262}, year = {2017}, publisher = {Elsevier Science}, } - JournalEffectiveness of a Countdown Timer in Reducing OR Turnover TimeMajbah Uddin, Robert Allen, Nathan Huynh, Jose M Vidal, Kevin M Taaffe, Lawrence D Fredendall, and Joel S GreensteinJournal of Mobile Technology in Medicine 2017
Background: In production environments, a countdown timer is used to report the status of the planned start time and to provide both a communication mechanism and an accountability aid.1 It has been used in the airline industry to remind all personnel of the remaining time until when the aircraft door should be closed. This study explored the effectiveness of a countdown timer in the operating room (OR). Aims: This study was designed to assess the effectiveness of a countdown timer in the OR setting and to determine the factors that contribute to prolonged OR turnover time (TOT) (defined to be from the “procedure finish” time of the preceding case to the “procedure start” time of the following case), as well as the impact each of the significant factors has on TOT. In this study, the term case denotes a surgical procedure. Method: An Android app named ORTimer was developed for the study. The app was installed on Android tablets that were placed at the Certified Registered Nurse Anesthetist (CRNA) workstations in the OR at Greenville Memorial Hospital (GMH) in South Carolina. The CRNAs helped collect the event milestones and record the delay reasons (if applicable). Additional OR case information was extracted from GMH’s electronic medical record. Regression analysis was used to identify significant factors that contribute to prolonged OR TOT and to estimate their impacts. A t-test was conducted to test the hypothesis that the use of a countdown timer is effective in an OR environment. Results: The data from a total of 232 cases where the ORTimer app was used were examined. Among the factors (i.e., delay reasons and case information) considered, an outpatient from a following case had the highest correlation with excessive room idle time, which is the difference between the actual TOT and the allotted TOT. Delays due to patient-related issues added about 12.7 minutes to the turnover time (90% CI: 7.2, 18.3) when other factors were fixed. Delays due to preoperative-related issues added about 27.4 minutes to the turnover time (90% CI: 20.0, 34.7) when other factors were fixed. Conclusions: As is the case with most production environments,1 the use of a visual management tool such as the countdown timer in the OR is found to be effective. Additional research is needed to determine whether this finding is applicable to other hospitals.
@article{uddin2017effectiveness, title = {Effectiveness of a Countdown Timer in Reducing OR Turnover Time}, author = {Uddin, Majbah and Allen, Robert and Huynh, Nathan and Vidal, Jose M and Taaffe, Kevin M and Fredendall, Lawrence D and Greenstein, Joel S}, journal = {Journal of Mobile Technology in Medicine}, volume = {6}, number = {3}, pages = {25--33}, year = {2017}, }
2016
- JournalRouting Model for Multicommodity Freight in an Intermodal Network Under DisruptionsMajbah Uddin, and Nathan HuynhTransportation Research Record: Journal of the Transportation Research Board 2016
This paper presents a mathematical model for the routing of multicommodity freight in an intermodal network under disruptions. A stochastic mixed-integer program was formulated to minimize not only operational costs of various modes and transfer costs at terminals but also penalty costs associated with unsatisfied demands. The sample average approximation algorithm was used to solve this challenging problem. The developed model was then applied to two networks—a hypothetical 15-node network and an actual intermodal network in the Gulf Coast, Southeastern, and Mid-Atlantic regions of the United States—to demonstrate its applicability with explicit consideration of disruptions at links, nodes, and terminals. The model results indicated that during disruptions, goods in the study region should be shipped by road–rail intermodal network because of the built-in redundancy of the freight transport network. Additionally, the routes generated by the model were found to be more robust than those typically used by freight carriers.
@article{uddin2016routing, title = {Routing Model for Multicommodity Freight in an Intermodal Network Under Disruptions}, author = {Uddin, Majbah and Huynh, Nathan}, journal = {Transportation Research Record: Journal of the Transportation Research Board}, volume = {2548}, pages = {71--80}, year = {2016}, publisher = {Transportation Research Board}, }
2015
- JournalFreight Traffic Assignment Methodology for Large-Scale Road–Rail Intermodal NetworksMajbah Uddin, and Nathan HuynhTransportation Research Record 2015
A methodology is proposed for freight traffic assignment in large-scale road–rail intermodal networks. To obtain the user–equilibrium freight flows, a path-based assignment algorithm (gradient projection) was proposed. The developed methodology was tested on the U.S. intermodal network by using the 2007 freight demand for truck, rail, and road–rail intermodal from the Freight Analysis Framework, Version 3 (FAF3). The results indicate that the proposed methodology’s projected flow pattern is similar to the FAF3 assignment. The proposed methodology can be used by transportation planners and decision makers to forecast freight flows and to evaluate strategic network expansion options.
@article{uddin2015freight, title = {Freight Traffic Assignment Methodology for Large-Scale Road--Rail Intermodal Networks}, author = {Uddin, Majbah and Huynh, Nathan}, journal = {Transportation Research Record}, volume = {2477}, number = {1}, pages = {50--57}, year = {2015}, publisher = {SAGE Publications Sage CA: Los Angeles, CA}, } - JournalEvaluation of Google’s Voice Recognition and Sentence Classification for Health Care ApplicationsMajbah Uddin, Nathan Huynh, Jose M Vidal, Kevin M Taaffe, Lawrence D Fredendall, and Joel S GreensteinEngineering Management Journal; EMJ 2015
This study examined the use of voice recognition technology in perioperative services (Periop) to enable Periop staff to record workflow milestones using mobile technology. The use of mobile technology to improve patient flow and quality of care could be facilitated if such voice recognition technology could be made robust. The goal of this experiment was to allow the Periop staff to provide care without being interrupted with data entry and querying tasks. However, the results are generalizable to other situations where an engineering manager attempts to improve communication performance using mobile technology. This study enhanced Google’s voice recognition capability by using post-processing classifiers (i.e., bag-of-sentences, support vector machine, and maximum entropy). The experiments investigated three factors (original phrasing, reduced phrasing, and personalized phrasing) at three levels (zero training repetition, 5 training repetitions, and 10 training repetitions). Results indicated that personal phrasing yielded the highest correctness and that training the device to recognize an individual’s voice improved correctness as well. Although simplistic, the bag-of-sentences classifier significantly improved voice recognition correctness. The classification efficiency of the maximum entropy and support vector machine algorithms was found to be nearly identical. These results suggest that engineering managers could significantly enhance Google’s voice recognition technology by using post-processing techniques, which would facilitate its use in health care and other applications.
@article{uddin2015evaluation, title = {Evaluation of Google’s Voice Recognition and Sentence Classification for Health Care Applications}, author = {Uddin, Majbah and Huynh, Nathan and Vidal, Jose M and Taaffe, Kevin M and Fredendall, Lawrence D and Greenstein, Joel S}, journal = {Engineering Management Journal; EMJ}, volume = {27}, number = {3}, pages = {152--162}, year = {2015}, publisher = {Taylor \& Francis}, } - ThesisAssessment of Classifiers for Potential Voice-Enabled Transportation AppsMajbah Uddin2015
Transportation apps are playing a positive role for today’s technology-driven users. They provide users with a convenient and flexible tool to access transportation data and services, as well as collect and manage data. In many of these apps, such as Google Maps, their operations rely on the effectiveness of the voice recognition system. For the existing and new apps to be truly effective, the built-in voice recognition system needs to be robust (i.e., being able to recognize words spoken in different pitch and tone). The goal of this study is to assess three post-processing classifiers (i.e., bag-of-sentences, support vector machine, and maximum entropy) to enhance the commonly used Google’s voice recognition system. The experiments investigated three factors (original phrasing, reduced phrasing, and personalized phrasing) at three levels (zero training repetition, 5 training repetitions, and 10 training repetitions). Results indicated that personal phrasing yielded the highest correctness and that training the device to recognize an individual’s voice improved correctness as well. Although simplistic, the bag-of-sentences classifier significantly improved voice recognition correctness. The classification efficiency of the maximum entropy and support vector machine algorithms was found to be nearly identical. These results suggest that post-processing techniques could significantly enhance Google’s voice recognition system.
@phdthesis{uddin2015assessment, title = {Assessment of Classifiers for Potential Voice-Enabled Transportation Apps}, author = {Uddin, Majbah}, year = {2015}, school = {University of South Carolina}, }