Olcay Sahin

Dr. Olcay Sahin

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 May 2019 in Journal of Big Data Analytics in Transportation
Verified
Journal Article
Closed access
PDF file
RNReza Vatani Nezafat
Reza Vatani Nezafat
OSOlcay Sahin
Olcay Sahin
MCMecit Cetin
Mecit Cetin

6 March 2020 in Journal of Intelligent Transportation Systems
Verified
Journal Article
Closed access
OSOlcay Sahin
Olcay Sahin
RNReza Vatani Nezafat
Reza Vatani Nezafat
MCMecit Cetin
Mecit Cetin
Classification of vehicles into distinct groups is critical for a number of applications including freight and commodity flow modeling, pavement management and design, tolling, air quality monitoring, and intelligent transportation systems. The main goal of this paper is to demonstrate how data from Light Detection and Ranging (LiDAR) sensors could be leveraged to distinguish between specific types of truck trailers beyond what is generally possible by the traditional vehicle classification sensors (e.g., piezoelectric sensors and inductive loop detectors). A multi-array LiDAR sensor enables the construction of 3D-profiles of vehicles since it measures the distance to the object reflecting its emitted light. This paper shows how point-cloud data from a 16-beam LiDAR sensor are processed to extract useful information and features to classify semi-trailer trucks hauling ten different types of trailers: a reefer and non-reefer dry van, 20 ft and 40 ft intermodal containers, 40 ft reefer intermodal container, platforms, tanks, car transporter, open-top van/dump and aggregated other types (i.e., livestock, logging). K-Nearest Neighbors (KNN), Multilayer Perceptron (MLP), Adaptive Boosting (AdaBoost.M2), and Support Vector Machines (SVM) supervised machine learning algorithms are implemented on the field data collected on a freeway segment that includes over seven-thousand trucks. The results show that with the SVM model, different trailer body types can be distinguished with a very high level of accuracy ranging from 85% to 98%.

6 October 2022 in Transportation Research Record: Journal of the Transportation Research Board
Verified
Journal Article
Closed access
TCTaner Cokyasar
Taner Cokyasar
ASAnirudh Subramanyam
Anirudh Subramanyam
JLJeffrey Larson
Jeffrey Larson
MSMonique Stinson
Monique Stinson
OSOlcay Sahin
Olcay Sahin
Electric vehicle routing problems can be particularly complex when recharging must be performed mid-route. In some applications, such as e-commerce parcel delivery truck routing, however, mid-route recharging may not be necessary because of constraints on vehicle capacities and the maximum allowed time for delivery. In this study, we develop a mixed-integer optimization model that exactly solves such a time-constrained capacitated vehicle routing problem, especially of interest for e-commerce parcel delivery vehicles. We compare our solution method with an existing metaheuristic and carry out exhaustive case studies considering four U.S. cities—Austin, TX; Bloomington, IL; Chicago, IL; and Detroit, MI—and two vehicle types: conventional vehicles and battery electric vehicles (BEVs). In these studies we examine the impact of vehicle capacity, maximum allowed travel time, service time (dwelling time to physically deliver the parcel), and BEV range on system-level performance metrics, including vehicle miles traveled (VMT). We find that the service time followed by the vehicle capacity plays a key role in the performance of our approach. We assume an 80-mi BEV range as a baseline without mid-route recharging. Our results show that the BEV range has a minimal impact on performance metrics because the VMT per vehicle averages around 72 mi. In a case study for shared-economy parcel deliveries, we observe that VMT could be reduced by 38.8% in Austin if service providers were to operate their distribution centers jointly.

12 January 2023 in Transportation Research Record: Journal of the Transportation Research Board
Verified
Journal Article
Closed access
TCTaner Cokyasar
Taner Cokyasar
MSMonique Stinson
Monique Stinson
OSOlcay Sahin
Olcay Sahin
Nirmit PrabhakarNirmit Prabhakar
Nirmit Prabhakar
DKDominik Karbowski
Dominik Karbowski
Drone delivery, once thought of as fictitious, is becoming a reality with the efforts of both forward-looking enterprises and supportive government policies. This emerging mode of e-commerce delivery raises many concerns. One important concern is the energy efficiency of direct delivery drones compared with conventional delivery trucks at a regional systems level. In this study, we develop and apply methods to quantify the regional energy impacts of drone delivery, then we assess these impacts and compare them with the impacts of truck delivery. To study this problem, we develop an optimization model that determines an optimal set of fulfillment centers (FCs) with variable service capacities that allow drones to make direct e-commerce deliveries. We adopt two drone delivery energy estimation models from the literature and use them as inputs to demonstrate the potential range of energy needs. We also develop another optimization model to account for the energy consumption of diesel trucks (DTs) and battery electric vehicles (BEVs). We test the models using validated simulation data for the Chicago metropolitan area in the U.S. to quantify the energy implications of these three delivery modes. For drone delivery, we further extend our analyses by considering the impact of wind speed and flight patterns. Our results show that direct delivery drones require 15.8% more energy than BEVs on an average windy day, and they need 15% more energy than DTs on a very windy day. We provide essential parameter values for reproducibility and list relevant open problems.

1 January 2017 in Transportation Research Record: Journal of the Transportation Research Board
Verified
Journal Article
Closed access
UAUmama Ahmed
Umama Ahmed
OSOlcay Sahin
Olcay Sahin
MCMecit Cetin
Mecit Cetin
For the past few years, several studies have focused on identifying a vehicle’s trajectory with smartphone data. However, these studies predominantly used GPS coordinate information for that purpose. Considering the known limitations of GPS, such as connectivity issues at urban canyons and underpasses, low precision of localization, and high power consumption of smartphones while GPS is in use, this paper focuses on developing alternative methods for identifying a vehicle’s trajectory at an intersection with sensor data other than GPS to minimize GPS dependency. In particular, accelerometer and gyroscope data collected with smartphone inertial sensors and speed data collected with an onboard diagnostics device are used to develop algorithms for maneuver (i.e., left and right turns and through) and trip direction identification at an intersection. In addition, techniques for noise removal and orientation correction from raw inertial sensor data are described. The effectiveness of the method for trajectory identification is assessed with collected field data. Results demonstrate that the developed method is effective in identifying a vehicle’s trajectory at an intersection. Overall, this research shows the feasibility of using alternative sensor data for trajectory identification and thus eliminating the need for continuous GPS connectivity.

11 December 2025 in World Electric Vehicle Journal
Verified
Journal Article
Open access
PDF file
Charbel MansourCharbel Mansour
Charbel Mansour
AKAmarendra Kancharla
Amarendra Kancharla
JGJulien Bou Gebrael
Julien Bou Gebrael
MAMichel Alhajjar
Michel Alhajjar
OSOlcay Sahin
Olcay Sahin
VFVincent Freyermuth
Vincent Freyermuth
Heavy-duty trucking is central to the U.S. economy, and improving its long-term sustainability requires cost-effective, energy-efficient, and reliable operations. Emerging technologies—advanced powertrains, batteries, and alternative fuels—offer potential solutions, but their economic and operational viability remains uncertain. This study evaluates the performance of Class 8 battery electric (BEV), plug-in hybrid (PHEV), fuel cell electric (FCEV), and diesel trucks in terms of energy use and the levelized cost of driving (LCOD) to determine when these technologies become competitive without compromising operational reliability. The analysis explores how evolving fuel prices and vehicle technology improvements in 2023, 2035, and 2050 influence the cost competitiveness of each powertrain. By comparing the results at both the technology level and the fleet level, the study demonstrates that powertrains that appear cost-effective on individual routes may not always scale to fleet-wide viability, and vice versa. The analysis is based on real-world data from over 15,700 Class 8 truck trips recorded in California in 2022, capturing diverse driving scenarios, payload conditions, and operational constraints. The results show that BEV250 can deliver cost-effective performance in short-haul operations (0–250 miles) under depot electricity prices below USD 0.34/kWh and maintain this advantage through 2050 as battery costs decline. In the 250–500-mile segment, the technology-level analysis indicates that BEV500 often achieves the lowest LCOD on individual tours, particularly under low electricity prices, while the fleet-level results show that FCEVs provide a more consistent cost performance across all tours, especially when the route variability is high. For long-haul operations (>500 miles), where BEVs are assumed to operate without en-route charging, FCEVs emerge as the most cost-effective non-diesel option by 2050, provided hydrogen prices fall below USD 6/kg. PHEVs show a limited long-term competitiveness and are mainly viable under transitional fuel price conditions. Overall, the findings underscore that there is no one-size-fits-all solution. Powertrain adoption must be range-aware, infrastructure-sensitive, and fleet-structured. By integrating technology-level and fleet-level perspectives, this study provides actionable insights for fleet operators, policymakers, and industry stakeholders seeking to balance cost, reliability, and sustainability in heavy-duty freight.