Transportation, Logistics, and Finance

Permanent URI for this collectionhdl:10365/32213

Browse

Now showing 1 - 20 of 71

Unlocking Drone Potential in the Pharma Supply Chain: A Hybrid Machine Learning and GIS Approach
(2023) Bridgelall, Raj; Upper Great Plains Transportation Institute
In major metropolitan areas, the growing levels of congestion pose a significant risk of supply chain disruptions by hindering surface transportation of commodities. To address this challenge, cargo drones are emerging as a potential mode of transport that could improve the reliability of the pharmaceutical supply chain and enhance healthcare. This study proposes a novel hybrid workflow that combines machine learning and a geographic information system to identify the fewest locations where providers can initiate cargo drone services to yield the greatest initial benefits. The results show that by starting a service in only nine metropolitan areas across four regions of the contiguous United States, drones with a robust 400-mile range can initially move more than 28% of the weight of all pharmaceuticals. The medical community, supply chain managers, and policymakers worldwide can use this workflow to make data-driven decisions about where to access the largest opportunities for pharmaceutical transport by drones. The proposed approach can inform policies and standards such as Advanced Air Mobility to help address supply chain disruptions, reduce transportation costs, and improve healthcare outcomes.
Data-Driven Deployment of Cargo Drones: A U.S. Case Study Identifying Key Markets and Routes
(2023) Bridgelall, Raj; Upper Great Plains Transportation Institute
Electric and autonomous aircraft (EAA) are set to disrupt current cargo-shipping models. To maximize the benefits of this technology, investors and logistics managers need information on target commodities, service location establishment, and the distribution of origin–destination pairs within EAA’s range limitations. This research introduces a three-phase data-mining and geographic information system (GIS) algorithm to support data-driven decision-making under uncertainty. Ana- lysts can modify and expand this workflow to scrutinize origin–destination commodity flow datasets representing various locations. The algorithm identifies four commodity categories contributing to more than one-third of the value transported by aircraft across the contiguous United States, yet only 5% of the weight. The workflow highlights 8 out of 129 regional locations that moved more than 20% of the weight of those four commodity categories. A distance band of 400 miles among these eight locations accounts for more than 80% of the transported weight. This study addresses a literature gap, identifying opportunities for supply chain redesign using EAA. The presented methodology can guide planners and investors in identifying prime target markets for emerging EAA technologies using regional datasets.
Identifying Factors Associated with Terrorist Attack Locations by Data Mining and Machine Learning
(2023) Bridgelall, Raj; Upper Great Plains Transportation Institute
While studies typically investigate the socio-economic factors of perpetrators to comprehend terrorism motivations, there was less emphasis placed on factors related to terrorist attack locations. Addressing this knowledge gap, this study conducts a multivariate analysis to determine attributes that are more associated with terrorist attacked locations than others. To tackle the challenge of identifying pertinent attributes, the methodology merges a global terrorism database with relevant socio-economic attributes from the literature. The workflow then trains 11 machine learning models on the combined dataset. Among the 75 attributes assessed, 10 improved the predictability of targeted locations, with population and public transportation infrastructure being key factors. After optimizing hyperparameters, a multi-layer perceptron—a type of artificial neural network—exhibited superior predictive performance, achieving an AUC score of 89.3%, classification accuracy of 88.1%, and a harmonically balanced precision and recall score of 87.3%. In contrast, support vector machines demonstrated the poorest performance. The study also revealed that race, age, gender, marital status, income level, and home values did not improve predictive performance. The machine learning workflow developed can aid policymakers in quantifying risks and making objective decisions regarding resource allocation to safeguard public health.
A Systematic Literature Review of Drone Utility in Railway Condition Monitoring
(2023) Askarzadeh, Taraneh; Bridgelall, Raj; Tolliver, Denver D.; Upper Great Plains Transportation Institute
Drones have recently become a new tool in railway inspection and monitoring (RIM) worldwide, but there is still a lack of information about the specific benefits and costs. This study conducts a systematic literature review (SLR) of the applications, opportunities, and challenges of using drones for RIM. The SLR technique yielded 47 articles filtered from 7,900 publications from 2014 to 2022. The SLR found that key motivations for using drones in RIM are to reduce costs, improve safety, save time, improve mobility, increase flexibility, and enhance reliability. Nearly all the applications fit into the categories of defect identification, situation assessment, rail network mapping, infrastructure asset monitoring, track condition monitoring, and obstruction detection. The authors assessed the open technical, safety, and regulatory challenges. The authors also contributed a cost analysis framework, identified factors that affect drone performance in RIM, and offered implications for new theories, management, and impacts to society.
Introducing an Efficiency Index to Evaluate eVTOL Designs
(2023) Bridgelall, Raj; Askarzadeh, Taraneh; Tolliver, Denver D.; Upper Great Plains Transportation Institute
The evolution of electric vertical takeoff and landing (eVTOL) aircraft as part of the Advanced Air Mobility initiative will affect our society and the environment in fundamental ways. Technological forecasting suggests that commercial services are fast emerging to transform urban and regional air mobility for people and cargo. However, the complexities of diverse design choices pose a challenge for potential adopters or service providers because there are no objective and simple means to compare designs based on the available set of performance specifications. This analysis defines an aeronautically informed propulsion efficiency index (PEX) to compare the performance of eVTOL designs. Range, payload ratio, and aspect ratio are the minimum set of independent parameters needed to compute a PEX that can distinguish among eVTOL designs. The distribution of the PEX and the range are lognormal in the design space. There is no association between PEX values and the mainstream eVTOL architecture types or the aircraft weight class. A multilinear regression showed that the three independent parameters explained more than 90% of the PEX distribution in the present design space.
Predicting Advanced Air Mobility Adoption by Machine Learning
(2023) Bridgelall, Raj; Upper Great Plains Transportation Institute
Advanced air mobility (AAM) is a sustainable aviation initiative to deliver cargo and passengers in urban and regional locations by electrified drones. The widespread expectation is that AAM adoption worldwide will help to reduce pollution, reduce transport costs, increase accessibility, and enable a more reliable and resilient supply chain. However, most countries lack regulations that legalize AAM. A fragmented regulatory approach hampers the progress of business prospectors and international organizations concerned with human welfare. Therefore, amidst high uncertainty, knowledge of indicators that can predict the propensity for AAM adoption will help nations and organizations plan for drone use. This research finds predictive indicators by assembling a unique dataset of 36 economic, social, environmental, governance, land use, technology, and transportation indicators for 204 nations. Subsequently, the best of 12 different machine learning models ranks the predictive importance of the indicators. The gross domestic product (GDP) and the regulatory quality index (RQI) developed by the Worldwide Governance Indicators (WGI) project were the two top predictors. Just as importantly, the poor predictors were as follows: the social progress index developed by the Social Progress Imperative, the WGI rule-of-law index, land use characteristics such as rural and urban proportions, borders on open waterways, population density, technology accessibility such as electricity and cell phones, carbon dioxide emission level, aviation traffic, port traffic, tourist arrivals, and roadway fatalities.
Perspectives on Securing the Multimodal Transportation System
(2022) Bridgelall, Raj; Upper Great Plains Transportation Institute
The vast, open, and interconnected characteristics of the transportation system make it a prime target for terrorists and hackers. However, there are no standard measures of transport system vulnerability to physical or cyberattacks. The separation of governance over different modes of transport increases the difficulty of coordination in developing and enforcing a common security index. This paper contributes a perspective and roadmap toward developing multimodal security indices that can leverage a variety of existing and emerging connected vehicle, sensing, and computing technologies. The proposed technologies include positive train control (PTC), vehicle-to-everything (V2X), weight-in-motion (WIM), advanced air mobility (AAM), remote sensing, and machine learning with cloud intelligence.
Ranking Risk Factors in Financial Losses From Railroad Incidents: A Machine Learning Approach
(2023) Dhingra, Neeraj; Bridgelall, Raj; Lu, Pan; Szmerekovsky, Joseph; Bhardwaj, Bhavana; Upper Great Plains Transportation Institute
The reported financial losses from railroad accidents since 2009 have been more than US$4.11 billion dollars. This considerable loss is a major concern for the industry, society, and the government. Therefore, identifying and ranking the factors that contribute to financial losses from railroad accidents would inform strategies to minimize them. To achieve that goal, this paper evaluates and compares the results of applying different non-parametric statistical and regression methods to 15 years of railroad Class I freight train accident data. The models compared are random forest, k-nearest neighbors, support vector machines, stochastic gradient boosting, extreme gradient boosting, and stepwise linear regression. The results indicate that these methods are all suitable for analyzing non-linear and heterogeneous railroad incident data. However, the extreme gradient boosting method provided the best performance. Therefore, the analysis used that model to identify and rank factors that contribute to financial losses, based on the gain percentage of the prediction accuracy. The number of derailed freight cars and the absence of territory signalization dominated as contributing factors in more than 57% and 20% of the accidents, respectively. Partial-dependence plots further explore the complex non-linear dependencies of each factor to better visualize and interpret the results.
Reducing Risks by Transporting Dangerous Cargo in Drones
(2022) Bridgelall, Raj; Upper Great Plains Transportation Institute
The transportation of dangerous goods by truck or railway multiplies the risk of harm to people and the environment when accidents occur. Many manufacturers are developing autonomous drones that can fly heavy cargo and safely integrate into the national air space. Those developments present an opportunity to not only diminish risk but also to decrease cost and ground traffic congestion by moving certain types of dangerous cargo by air. This work identified a minimal set of metropolitan areas where initial cargo drone deployments would be the most impactful in demonstrating the safety, efficiency, and environmental benefits of this technology. The contribution is a new hybrid data mining workflow that combines unsupervised machine learning (UML) and geospatial information system (GIS) techniques to inform managerial or investment decision making. The data mining and UML techniques transformed comprehensive origin–destination records of more than 40 commodity category movements to identify a minimal set of metropolitan statistical areas (MSAs) with the greatest demand for transporting dangerous goods. The GIS part of the workflow determined the geodesic distances between and within all pairwise combinations of MSAs in the continental United States. The case study of applying the workflow to a commodity category of dangerous goods revealed that cargo drone deployments in only nine MSAs in four U.S. states can transport 38% of those commodities within 400 miles. The analysis concludes that future cargo drone technology has the potential to replace the equivalent of 4.7 million North American semitrailer trucks that currently move dangerous cargo through populated communities.
Perspectives on Using Connected Vehicles for Transportation Infrastructure Condition Monitoring
(2022) Bridgelall, Raj; Upper Great Plains Transportation Institute
The condition of surface transportation infrastructure directly affects the economic health of a nation. However, it is difficult to justify the large sums of money needed to extend current methods to monitor all the multimodal infrastructure. The convergence of connected vehicle and cloud computing technologies presents an opportunity to automate the collection of ride quality and imagery data to continuously assess the condition of all roadways and railways. This paper presents several perspectives to help policy and standardization initiatives promote adoption.
Relating Subjective Ride Quality Ratings to Objective Measures
(2022) Bridgelall, Raj; Upper Great Plains Transportation Institute
Agencies have long used subjective roughness ratings from panels of users to inform policy development on road maintenance strategies. The commoditization of electronics motivated the development of more objective, automated, and cost-effective measurement technologies. Consequently, there has been an explosion of ensemble measurements using smartphones or connected vehicles. Nevertheless, agencies have no means of relating those sensor-based measurements to their customary linguistic scale of human perceived roughness levels. This research relates subjective ratings of roughness from regular passengers of public bus transit to simultaneous smartphone-based objective measures of roughness. The findings are that regular bus riders consistently distinguished between the extreme values of measured roughness but not the intermediate values. Ratings are also less distinguishable for smoother rides than for rougher rides. The experiments also reveal a phenomenon of roughness acclimation that leads to biased ratings from regular users of a road segment.
Remediation Ranking of High Crash Fatality Locations Involving Older Drivers in Florida's Rural Counties
(2022) Dehdari Ebrahimi, Zhila; Momenitabar, Mohsen; Arani, Mohammad; Bridgelall, Raj; Upper Great Plains Transportation Institute
In 2019, Florida's aging road users (65 years or older) accounted for 20% of the population but 37% of all crashes. Florida Department of Transportation has identified aging road users as one of the areas that requires attention in achieving Vision Zero--a strategy to eliminate all traffic fatalities and severe injuries, while increasing safe, healthy, equitable mobility for all. Research has documented that fatality rates in motor vehicle crashes are higher in rural than urban areas. Drivers in rural areas may be more vulnerable because they rely more on driving and consequently are reluctant to stop. This study identifies factors contributing to fatalities among aging drivers in 14 rural Florida counties experiencing high crash rates. The methodology used a multicriteria decision-making model, namely the fuzzy analytic hierarchy process (FAHP), to identify and categorize the causes of fatal crashes among drivers aged 65+, and to rank their 14 rural counties for remediation measures. FAHP methodology calculates crash factor weights and ranks the counties using pairwise comparisons of those factors to compare and quantify them. Results revealed that the top contributing factors to fatal crashes among drivers 65+ were cloudy, foggy, or rainy weather and when roadways were sandy or wet. Driving in the dark and at dawn also increased the risk of fatal crashes within this specified age group. These findings could help policy makers in each location focus on remediation measures such as older driver education and infrastructural improvements to address the most critical factors in fatal accidents.
Vehicle Axle Detection from Under-Sampled Signal through Compressed-Sensing-Based Signal Recovery
(2022) Zhang, Zhiming; Huang, Ying; Bridgelall, Raj; Upper Great Plains Transportation Institute
In traffic data collection, sampling design should satisfy the requirements of identifying prominent pulses corresponding to vehicle axle passage. Insufficient measurement leads to signal distortion and attenuation, reducing the quality of signal pulses. This study exploits the value of under-sampled data by applying compressed sensing (CS) methods to recover signal components that are critical for vehicle axle detection. Two CS methods are investigated in this study to recover the strain signal pulses from inside-pavement instrumented sensors at high-speed traversals. The CS methods successfully recovered the signal pulses from all axles of the truck used for testing. A comparison of the measured axle distances with the reference measurements validated the effectiveness of signal recovery methods. Therefore, the CS methods have the potential of reducing the cost, energy consumption, and data storage space, and improving the data transmission efficiency in practical implementations by enabling sampling devices designed for static measurements to achieve dynamic measurements.
Detecting Sources of Ride Roughness by Ensemble Connected Vehicle Signals
(2022) Bridgelall, Raj; Bhardwaj, Bhavana; Lu, Pan; Tolliver, Denver D.; Dhingra, Neeraj; Upper Great Plains Transportation Institute
It is expensive and impractical to scale existing methods of road condition monitoring for more frequent and network-wide coverage. Consequently, defects that increase ride roughness or can cause accidents will go undetected. This paper presents a method to enable network-wide, continuous monitoring by using low-cost GPS receivers and accelerometers on board regular vehicles. The technique leverages the large volume of sensor signals from multiple traversals of a road segment to enhance the signal quality by ensemble averaging. However, ensemble averaging requires position-repeatable signals which is not possible because of the low resolution and low accuracy of GPS receivers and the non-uniform sampling of accelerometers. This research overcame those challenges by integrating methods of interpolation, signal resampling, and correlation alignment. The experiments showed that the approach doubled the peak of the composite signal by decreasing signal misalignment by a factor of 67. The signal-to-noise ratio increased by 10 dBs after combining the signals from only 6 traversals. A probabilistic model developed to estimate a dynamic signal-detection threshold demonstrated that both the false-positive and false-negative rates approached zero after combining the signals from 15 traversals. The method will augment the efficiency of follow-up inspections by focusing resources to locations that consistently produce rough rides.
Using Artificial Intelligence to Derive a Public Transit Risk Index
(2022) Bridgelall, Raj; Upper Great Plains Transportation Institute
A terrorist attack on the public transportation system of a city can cripple its economy. Uninformed investments in countermeasures may result in a waste of resources if the risk is negligible. However, risks are difficult to quantify in an objective manner because of uncertainties, speculations, and subjective assumptions. This study contributes a probabilistic model, validated by ten different machine learning methods applied to the fusion of six heterogeneous datasets, to objectively quantify risks at different jurisdictional scales. The risk index is purposefully simple to quickly inform a proportional prioritization of resources to make fair investment decisions that stakeholders can easily understand, and to guide policy formulation. The main finding is that the risk indices among public transit jurisdictions in the United States distribute normally. This result enables agencies to evaluate the quality of their risk index calculations by detecting an outlier or a large deviation from the expected value.
Applying Unsupervised Machine Learning to Counterterrorism
(2022) Bridgelall, Raj; Upper Great Plains Transportation Institute
To advance the agenda in counterterrorism, this work demonstrates how analysts can combine unsupervised machine learning, exploratory data analysis, and statistical tests to discover features associated with different terrorist motives. A new empirical text mining method created a “motive” field in the Global Terrorism Database to enable associative relationship mining among features that characterize terrorist events. The methodology incorporated K-means co-clustering, three methods of non-linear projection, and two spatial association tests to reveal statistically significant relationships between terrorist motives, tactics, and targets. Planners and investigators can replicate the approach to distill knowledge from big datasets to help advance the state of the art in counterterrorism.
Technology Developments and Impacts of Connected and Autonomous Vehicles: An Overview
(2022) Ahmed, Hafiz Usman; Huang, Ying; Lu, Pan; Bridgelall, Raj; Upper Great Plains Transportation Institute
The scientific advancements in the vehicle and infrastructure automation industry are progressively improving nowadays to provide benefits for the end-users in terms of traffic congestion reduction, safety enhancements, stress-free travels, fuel cost savings, and smart parking, etc. The advances in connected, autonomous, and connected autonomous vehicles (CV, AV, and CAV) depend on the continuous technology developments in the advanced driving assistance systems (ADAS). A clear view of the technology developments related to the AVs will give the users insights on the evolution of the technology and predict future research needs. In this paper, firstly, a review is performed on the available ADAS technologies, their functions, and the expected benefits in the context of CVs, AVs, and CAVs such as the sensors deployed on the partial or fully automated vehicles (Radar, LiDAR, etc.), the communication systems for vehicle-to-vehicle and vehicle-to-infrastructure networking, and the adaptive and cooperative adaptive cruise control technology (ACC/CACC). Secondly, for any technologies to be applied in practical AVs related applications, this study also includes a detailed review in the state/federal guidance, legislation, and regulations toward AVs related applications. Last but not least, the impacts of CVs, AVs, and CAVs on traffic are also reviewed to evaluate the potential benefits as the AV related technologies penetrating in the market. Based on the extensive reviews in this paper, the future related research gaps in technology development and impact analysis are also discussed.
Characterizing Ride Quality With a Composite Roughness Index
(2022) Bridgelall, Raj; Upper Great Plains Transportation Institute
There are many important applications that require ride quality characterization. However, the only international standard that specifies a roughness index is not suitable for applications beyond assessing the ride quality of paved roads. Other potential applications include automated ride quality characterization of gravel roads, bike or wheelchair paths, railways, rivers, airways, hyperloops, and elevator channels. This work proposes a composite index that characterizes roughness from multidimensional movements along any path. Statistical tests demonstrate two important properties—that the index is consistent based on an ever-decreasing margin-of-error of the mean, and distinguishable among different paths. A low-cost sensor package of accelerometers, gyroscopes, and a speedometer produced the data for spatio-temporal transformation. The experiments conducted on buses revealed that both the consistency and distinguishability of the index improves with the number of measurements. The approach is best suited for applications that can use in-situ sensors or crowdsensing to automate ride quality characterization.
Exploratory Spatial Data Analysis of Traffic Forecasting: A Case Study
(2022) Hungness, Derek; Bridgelall, Raj; Upper Great Plains Transportation Institute
Transportation planning has historically relied on statistical models to analyze travel patterns across space and time. Recently, an urgency has developed in the United States to address outdated policies and approaches to infrastructure planning, design, and construction. Policymakers at the federal, state, and local levels are expressing greater interest in promoting and funding sustainable transportation infrastructure systems to reduce the damaging effects of pollutive emissions. Consequently, there is a growing trend of local agencies transitioning away from the traditional level-of-service measures to vehicle miles of travel (VMT) measures. However, planners are finding it difficult to leverage their investments in their regional travel demand network models and datasets in the transition. This paper evaluates the applicability of VMT forecasting and impact assessment using the current travel demand model for Dane County, Wisconsin. The main finding is that exploratory spatial data analysis of the derived data uncovered statistically significant spatial relationships and interactions that planners cannot sufficiently visualize using other methods. Planners can apply these techniques to identify places where focused VMT remediation measures for sustainable networks and environments can be most cost-effective.
An Application of Natural Language Processing to Classify What Terrorists Say They Want
(2022) Bridgelall, Raj; Upper Great Plains Transportation Institute
Knowing what perpetrators want can inform strategies to achieve safe, secure, and sustainable societies. To help advance the body of knowledge in counterterrorism, this research applied natural language processing and machine learning techniques to a comprehensive database of terrorism events. A specially designed empirical topic modeling technique provided a machine-aided human decision process to glean six categories of perpetrator aims from the motive text narrative. Subsequently, six different machine learning models validated the aim categories based on the accuracy of their association with a different narrative field, the event summary. The ROC-AUC scores of the classification ranged from 86% to 93%. The Extreme Gradient Boosting model provided the best predictive performance. The intelligence community can use the identified aim categories to help understand the incentive structure of terrorist groups and customize strategies for dealing with them.

Browse

Recent Submissions