{"id":9242,"date":"2024-02-01T12:46:11","date_gmt":"2024-02-01T17:46:11","guid":{"rendered":"https:\/\/cecas.clemson.edu\/C2M2\/?page_id=9242"},"modified":"2025-05-29T20:46:58","modified_gmt":"2025-05-30T00:46:58","slug":"funded-projects-2023","status":"publish","type":"page","link":"https:\/\/cecas.clemson.edu\/C2M2\/funded-projects-2023\/","title":{"rendered":"Funded Projects 2023"},"content":{"rendered":"

C2<\/sup>M2<\/sup> sent out a Call for Proposals to researchers at our five partner institutions, launching our 2023\/24 round of funded projects in August 2023.\u00a0 In continuing with our goal to foster collaboration multi-institution projects were prioritized. The theme for this year’s CFP was Application and Technology Transfer of the Completed Research Projects<\/em><\/strong>.\u00a0 13 research proposals were submitted to C2<\/sup>M2<\/sup> for potential funding, with a mix of new and returning PIs. In keeping with tradition, proposals were then sent out for blind review by industry professionals from academia, and public and private agencies.\u00a0 Each proposal received two blind reviews, which were then used to select projects for funding. C2<\/sup>M2\u00a0<\/sup>Directors, Drs. Chowdhury (Clemson University), Caicedo (University of South Carolina), Comert (Benedict College), Mwakalonge (South Carolina State University), and Michalaka (the Citadel) along with Assistant Director Ghafari, met virtually this year to evaluate proposals and select proposals for funding. In this round, 11 research projects out of the 13 submitted proposals were selected for funding based on their reviews. Projects began in September or early November of 2023.\u00a0 Of these 11 selected projects, four are led by Clemson University, four are led by USC, two led by the Citadel and one led by South Carolina State University. Benedict College are collaborating on multiple selected projects.<\/p>\r\n

\r\n\r\n\r\n
\r\n

Computer-Vision Model for Estimation of Road Sign Retro-Reflectivity Based on Deep Learning Algorithm and Vehicle Built-in Cameras<\/strong><\/p>\r\n

Lead Principal Investigator \u2013 Judith Mwakalonge, South Carolina State University<\/p>\r\n

Co-Principal Investigator(s) \u2013 Gurcan Comert, Benedict College; Saidi Siuhi, South Carolina State University<\/p>\r\n

May 2023 \u2013 September 2024<\/p>\r\n

Project Status \u2013 Completed<\/p>\r\n

Funding Amount \u2013 UTC $48,044; SCSU – $17,023; Benedict College – $7,000<\/p>\r\n

Total Funding – $72,067<\/p>\r\n

Sponsoring Orgs \u2013 OST-R, South Carolina State University, Benedict College<\/p>\r\n

Description: <\/strong>The US Department of Transportation requires road signs transportation agencies maintain sign retro reflectivity such that signs have the same shape and color day and night. Regularly checking road sign retro-reflectivity values ensures timely replacement of road signs with inadequate retro-reflectivity, enhancing road users’ visibility and safety. In this project, The research team address the practical safety and cost concern regarding road sign replacement strategy. We seek to apply deep-learning techniques and computer vision models for retro reflectivity detection using built-in-vehicle technologies. The research team proposes a technique to estimate the amounts of retro-reflectivity from the road signs using deep learning algorithms. This proposed research is part of the team\u2019s agenda to employ affordable methods to improve road safety.<\/p>\r\n<\/div>\r\n

\r\n\r\n\r\n
\r\n

Assessing Transportation Infrastructure Segments for Bike Suitability<\/strong><\/p>\r\n

Lead Principal Investigator \u2013 Dimitra Michalaka, The Citadel<\/p>\r\n

Co-Principal Investigator(s) \u2013 Keweku Brown and William J. Davis, The Citadel; Nathan Huynh and Chun-Hsing Ho, University of Nebraska-Lincoln; Yuche Chen, University of South Carolina<\/p>\r\n

May 2023 \u2013 September 2024<\/p>\r\n

Project Status \u2013 Completed<\/p>\r\n

Funding Amount \u2013 UTC $157,330; Citadel – $28,344; USC – $50,322<\/p>\r\n

Total Funding – $235,996<\/p>\r\n

Sponsoring Orgs \u2013 OST-R, The Citadel, University of South Carolina<\/p>\r\n

Description: <\/strong>There is need for research and empirical measurements to assess how the built transportation infrastructure accommodates bike trips in urbanized communities across the US. This project will focus on assessing transportation infrastructure segments for bike suitability using motion and vibration sensors. This effort will supplement the previously completed C2M2 project \u201cAssessing Potential of Bike Share Networks and Active Transportation to Improve Urban Mobility, Physical Activity and Public Health Outcomes in South Carolina\u201d. Data will be collected in Charleston, SC, Columbia, SC, and Lincoln, NE to provide a case study location for exploring insightful relationships that will be informative to other communities. The data will be analyzed to investigate route conditions to better understand how built environment infrastructure is meeting the users\u2019 needs. This research focuses on evaluating the built environment infrastructure by collecting data that will help determine cyclist riding quality. Qualitative, quantitative, and geospatial methods will be used to evaluate cycling paths.<\/p>\r\n<\/div>\r\n

\r\n\r\n\r\n
\r\n

Transfer of Unmanned Aircraft Systems Technology to SCDOT for Enhanced Bridge Inspections<\/strong><\/p>\r\n

Lead Principal Investigator \u2013 Joseph Burgett, Clemson University<\/p>\r\n

Co-Principal Investigator(s) \u2013 Gurcan Comert, Benedict College<\/p>\r\n

October 2023 \u2013 September 2024<\/p>\r\n

Project Status \u2013 Completed<\/p>\r\n

Funding Amount \u2013 UTC $181,208; Clemson – $85,680; Benedict College – $27,297<\/p>\r\n

Total Funding – $294,185<\/p>\r\n

Sponsoring Orgs \u2013 OST-R, Clemson University, Benedict College<\/p>\r\n

Description: <\/strong>To operate a UAS for commercial purposes, pilots must pass the FAA\u2019s Part 107 knowledge test and earn their remote pilot certificate. The examination assesses a pilot\u2019s knowledge of weather, airspace, and regulations. Part 107 only tests general knowledge and does not have a practical component. \u201cASTM F3266: Standard Guide for Training for Remote Pilots in Command of UAS Endorsement\u201d is the industry standard for assessing flight proficiency. ASTM F3266 defines flight proficiency as having sufficient general knowledge, field operations, and aircraft control. The standard indicates that UAS general knowledge can be assessed with the Part 107 knowledge test. However, individual agencies must assess field operations and aircraft control. The standard indicates specific field operations and aircraft control topics that should be assessed but does not stipulate a specific assessment tool. This is a gap in the literature that this project seeks to fill. There is no standardized assessment tool that DOTs can use that measures field operation and aircraft control ability. This project will create and pilot test this assessment tool as part of a comprehensive training program. At the end of the project, DOTs will have an assessment tool that complements the FAA\u2019s general knowledge test and the ability to assess UAS flight proficiency comprehensively.<\/p>\r\n<\/div>\r\n

\r\n\r\n\r\n
\r\n

A Web-Based Tool for Cross Dock Trailer Scheduling<\/strong><\/p>\r\n

Lead Principal Investigator \u2013 William G. Ferrell, Clemson University<\/p>\r\n

Co-Principal Investigator(s) \u2013 Nathan Huynh, University of Nebraska-Lincoln<\/p>\r\n

October 2023 \u2013 September 2024<\/p>\r\n

Project Status \u2013 Completed<\/p>\r\n

Funding Amount \u2013 UTC $33,426; Clemson – $16,938<\/p>\r\n

Total Funding – $50,364<\/p>\r\n

Sponsoring Orgs \u2013 OST-R, Clemson University<\/p>\r\n

Description: <\/strong>The overarching goal of this project is to develop a web-based tool that makes the previous research results on cross dock scheduling that was completed though past C2M2 projects accessible to a wider audience by removing the need for specialized knowledge of mathematical programming or computer science. The project aims to achieve success by firstly establishing the desirable characteristics of the web-based tool through comprehensive literature reviews, analysis of similar tools in different domains, and engaging in discussions with potential users. Following this, the scope of the web-based model will be defined by comparing it with existing cross-dock models and solution heuristics, aligning with the characteristics identified earlier, and ensuring technical feasibility based on available computing and interface resources. Specifications and a conceptual design for the user interface will then be developed. Subsequently, the existing model will be adapted for seamless integration into the web-based environment, allowing for easy modification of inputs and accurate model solving. The core focus lies in building a user-friendly web tool that enables intuitive adjustments of model inputs and transparent presentation of results, encompassing both quantitative measures and animated representations. The final step involves providing clear and simple user instructions, ensuring the ease of tool utilization and accurate interpretation of results.<\/p>\r\n<\/div>\r\n

\r\n\r\n\r\n
\r\n

A software Tool for Securing Deep Learning against Adversarial Attacks for CAVs<\/strong><\/p>\r\n

Lead Principal Investigator \u2013 Pierluigi Pisu, Clemson University<\/p>\r\n

Co-Principal Investigator(s) \u2013 Gurcan Comert, and Negash Begashaw Benedict College<\/p>\r\n

October 2023 \u2013 September 2024<\/p>\r\n

Project Status \u2013 Completed<\/p>\r\n

Funding Amount \u2013 UTC $123,907; Clemson – $29,344; Benedict College – $33,009<\/p>\r\n

Total Funding – $186,260<\/p>\r\n

Sponsoring Orgs \u2013 OST-R, Clemson University, Benedict College<\/p>\r\n

Description: <\/strong>The scope of this project is to realize a technology transfer of previously developed adversarial attack resilient perception algorithm for autonomous navigation in connected and automated vehicles. The project will attain its objectives by developing a graphical user interface (GUI) designed for the automatic generation of a robust perception algorithm. This involves utilizing a baseline perception neural network and offering options for training and evaluation using various publicly available image datasets. Furthermore, the initiative includes training students on the utilization of the developed GUI, aiming to cultivate a generation of proficient individuals poised to contribute to the advancement of the United States Department of Transportation (USDOT) and society as a whole. Practical applications and understanding of the proposed technology will be demonstrated through workshops, employing an autonomous F1\/10 car testbed that emulates a Connected and Autonomous Vehicle (CAV) perception module. The technology’s viability will be showcased by implementing it on an autonomous vehicle within the AVL DrivingCube SCENIUS at CU-ICAR, highlighting its real-world applicability and potential impact on autonomous vehicle technology.<\/p>\r\n<\/div>\r\n

\r\n\r\n\r\n
\r\n

Intelligent River\u00ae Bridge Flood Monitoring System to Improve Transportation Mobility<\/strong><\/p>\r\n

Lead Principal Investigator \u2013 Christopher Post, Clemson University<\/p>\r\n

Co-Principal Investigator(s) \u2013 Jeff Allen, and Elena Mikhailova, Clemson University;\u00a0 Gurcan Comert, Benedict College<\/p>\r\n

January 2024 \u2013 September 2024<\/p>\r\n

Project Status \u2013 Completed<\/p>\r\n

Funding Amount \u2013 UTC $194,458; Clemson – $100,000; Benedict College – $47,231<\/p>\r\n

Total Funding – $341,689<\/p>\r\n

Sponsoring Orgs \u2013 OST-R, Clemson University, Benedict College<\/p>\r\n

Description: <\/strong>Bridge flooding can dramatically impact mobility, and climate change impacts are expected to increase flooding frequency in the future. There is an urgent need to develop technology to provide accurate, near real-time water level information from bridges. The Clemson Intelligent River\u00ae project has developed an innovative low-cost platform for water level monitoring from bridges. This \u201cBridgeBox\u201d uses radar technology to measure water level and then sends this data over IoT cellular networks to a cloud-based system that can share water levels and flood alerts with DOT professionals to help improve public safety and vehicle flow to improve mobility during extreme precipitation and flooding events. This proposal supports several key aspects of testing and refining the bridge water level monitoring system. Water level distance accuracy would be validated through careful laboratory and field structures. A GPS would be integrated to help validate installation location. Multiple bridge mounting systems would be developed to enable rapid, non-destructive mounting on various bridge structures. Installation surveying methodology would be developed. Finally, twenty test deployments would be done in collaboration with the SC DOT as well as the South Carolina Office of Resilience (SCOR).<\/p>\r\n<\/div>\r\n

\r\n\r\n\r\n
\r\n

Transfer of Technologies for Performance Degradation Prediction and Channel Switching in Vehicular Networks under Harsh Weather Conditions and Integration with State-of-the-Art Products<\/span><\/strong><\/p>\r\n

Lead Principal Investigator \u2013 Chin Tser Huang, University of South Carolina<\/p>\r\n

Co-Principal Investigator(s) \u2013 Pierluigi Pisu, Clemson University; Gurcan Comert, and Esmail Abuhdima, Benedict College<\/p>\r\n

October 2023 \u2013 September 2024<\/p>\r\n

Project Status \u2013 Completed<\/p>\r\n

Funding Amount \u2013 UTC $227,991; USC- $52,032; Clemson – $29,344; Benedict College – $33,009<\/p>\r\n

Total Funding – $342,376<\/p>\r\n

Sponsoring Orgs \u2013 OST-R, University of South Carolina, Clemson University, Benedict College<\/p>\r\n

Description: <\/strong>This study promote and realize the transfer of the technologies developed for performance degradation detection and channel switching in vehicular networks under harsh weather conditions. The results of our previous research have shown that harsh weather conditions can pose serious threats on the reliability of vehicular communications and the technologies we developed can effectively mitigate such threats, but the technology we developed must be applied and integrated with practical, usable products to bring substantial benefits to the society. We aim to achieve this by focusing on the integration of our technology with state-of-the-art products in the industry. This effort will be accompanied by student training and workshop activities to foster next-generation researchers who have expertise in this field and enhance social awareness of the threats that harsh weather conditions can cause on transportation safety and the viable solution that our technology can provide.<\/span><\/p>\r\n<\/div>\r\n

\r\n\r\n\r\n
\r\n

Intelligent Asset Management for Improved Mobility:<\/span> Technology Transfer for South Carolina<\/span><\/strong><\/p>\r\n

Lead Principal Investigator \u2013 Paul Ziehl, University of South Carolina<\/p>\r\n

Co-Principal Investigator(s) \u2013 Gurcan Comert, Benedict College<\/p>\r\n

October 2023 \u2013 September 2024<\/p>\r\n

Project Status \u2013 Completed<\/p>\r\n

Funding Amount \u2013 UTC $221,579; USC – $83,495; Benedict College – $27,297<\/p>\r\n

Total Funding – $332,371<\/p>\r\n

Sponsoring Orgs \u2013 OST-R, University of South Carolina, Benedict College<\/p>\r\n

Description: <\/strong>To improve mobility, an asset management system that is capable of autonomously updating the structural status of bridges and resulting networks is needed. The current state of the practice has proven generally effective, however, it comes with high cost, the need for traffic control, and safety risks for inspectors. The extensive needs for mobility in South Carolina, combined with the current state of the infrastructure, require an asset management system that is capable of autonomous evaluation at the network level. This is the opportunity being explored and developed by the project team. To address artificial intelligence for advancing multimodal mobility, we propose leveraging several ongoing research projects in monitoring and bridge evaluation. The algorithms developed in prior projects will be packaged into a graphical user interface (GUI) for autonomous bridge load rating and transitioned to IBM or others through appropriate licensing agreements. Our work will be informed through bi-weekly interactions, and our team is currently working toward this goal. Ongoing SCDOT projects at USC, while somewhat different from the project proposed here, allow access to bridges that is needed for understanding of issues and training of the AI-based bridge load rating system.<\/span><\/p>\r\n<\/div>\r\n

\r\n\r\n\r\n
\r\n

Developing a Portable Railroad Crossing Monitoring System Based on Artificial Intelligence and Image Processing Technology<\/strong><\/p>\r\n

Lead Principal Investigator \u2013 Yu Qian, University of South Carolina<\/p>\r\n

Co-Principal Investigator(s) \u2013 Gurcan Comert, Benedict College; Yuche Chen and Dimitris Rizos, University of South Carolina<\/p>\r\n

October 2023 \u2013 September 2024<\/p>\r\n

Project Status \u2013 Completed<\/p>\r\n

Funding Amount \u2013 UTC $295240; USC – $115,569; Benedict College – $33,009<\/p>\r\n

Total Funding – $443,818<\/p>\r\n

Sponsoring Orgs \u2013 OST-R, University of South Carolina, Benedict College<\/p>\r\n

Description: <\/strong>The objective of this proposal is to create a cost-effective, field-deployable system capable of identifying, counting, and categorizing a diverse range of objects, including vehicles, pedestrians, and other foreign obstructions, at railroad grade crossings. This system also aims to supply crucial data for collision warnings, as well as inform future traffic management and urban planning initiatives. The cornerstone of a successful intelligent railroad grade crossing monitoring system lies in precise object detection, counting, and classification capabilities. To achieve this, we propose the development of a specialized deep neural network (DNN) augmented with a custom detection algorithm. This network will operate in conjunction with an edge computing platform and commercially available cameras to identify potential hazards at grade crossings in real-time. Powered by batteries for enhanced portability, the system can be strategically deployed at specific crossings based on situational needs. Beyond basic detection, the proposed system will also excel in object classification, segregating detected objects into distinct categories such as pedestrian, vehicle, tree, or package. This nuanced classification will enable a shift from current “passive” warning mechanisms to a more “proactive” traffic management strategy. By recognizing and categorizing potential hazards, local agencies will be better equipped to make informed decisions for urban development, thereby mitigating trespassing risks by targeting their sources directly.<\/span><\/p>\r\n<\/div>\r\n

\r\n\r\n\r\n
\r\n

Development of Transportation Air Quality Planning Tool for transportation agencies<\/span><\/strong><\/p>\r\n

Lead Principal Investigator \u2013 Yuche Chen, University of South Carolina<\/p>\r\n

Co-Principal Investigator(s) \u2013 Gurcan Comert, Benedict College; Yu Qian, University of South Carolina<\/p>\r\n

October 2023 \u2013 September 2024<\/p>\r\n

Project Status \u2013 Completed<\/p>\r\n

Funding Amount \u2013 UTC $220,059; USC – $77,506; Benedict College – $33,009<\/p>\r\n

Total Funding – $330,574<\/p>\r\n

Sponsoring Orgs \u2013 OST-R, University of South Carolina, Benedict College<\/p>\r\n

Description: <\/strong>State DOTs, Metropolitan Planning Organizations, and other relevant authorities have crafted several air quality evaluation tools. One noteworthy observation is that the existing tools for air quality assessment don’t encompass the full spectrum of project types within the CMAQ program. Additionally, these tools were formulated before 2014, rendering their emissions rates and other data incongruent with the more recent 2014 version of the MOVES model. To bridge the identified knowledge gap, this project aims to create an Excel-based air quality assessment tool. This tool will enable the computation of emissions ramifications for all eligible transportation project types. The proposed tool will integrate updated parameters and assumptions from the most recent transportation air quality models (such as MOVES) and will incorporate adapted vehicle activity data derived from city-scale microscopic traffic simulations.<\/span><\/p>\r\n<\/div>\r\n

\r\n\r\n\r\n
\r\n

Strategic Development of GUI Tools for Enhancing Transportation Mobility Among Vulnerable Groups During Pandemics<\/span><\/strong><\/p>\r\n

Lead Principal Investigator \u2013 Yuche Chen, University of South Carolina<\/p>\r\n

Co-Principal Investigator(s) \u2013 Xuanke Wu, Juan Caivedo and Yu Qian, University of South Carolina<\/p>\r\n

March 2024 \u2013 September 2024<\/p>\r\n

Project Status \u2013 Completed<\/p>\r\n

Funding Amount \u2013 UTC $149,474; USC – $74,795<\/p>\r\n

Total Funding – $224,269<\/p>\r\n

Sponsoring Orgs \u2013 OST-R, University of South Carolina<\/p>\r\n

Description: <\/strong>This project aims to improve transportation equality and life quality of voluntary groups with disabilities and the elderly by addressing social exclusion, accessibility, and mobility issues. We propose to develop a strategic GUI application to facilitate the planning, establishment, and life-cycle maintenance and management of ride-sharing vehicle facilities, effectively accommodating their transportation needs. The objective is to develop a user-friendly GUI application using Python Tkinter library to simplify the adoption of the developed algorithms of the car-sharing system for vulnerable groups into practice. Within the GUI application, to streamline all core functions derived from the developed algorithms, encompassing interactive data input processes (such as retrieving city network data and user-defined points of interest (POI) like retirement communities, healthcare centers, grocery stores, entertainment clubs, etc.), automated data processing, calculations, decision-making, and result reporting.<\/span><\/p>\r\n<\/div>\r\n

\r\n\r\n\r\n
\r\n

Safety and Health Impacts of Mobility Alternatives Technology Transfer<\/span><\/strong><\/p>\r\n

Lead Principal Investigator \u2013 Dimitra Michalaka, The Citadel<\/p>\r\n

Co-Principal Investigator(s) \u2013 Kweku Brown, and William J. Davis, The Citadel<\/p>\r\n

October 2023 \u2013 September 2024<\/p>\r\n

Project Status \u2013 Completed<\/p>\r\n

Funding Amount \u2013 UTC $69,661; The Citadel – $34,830<\/p>\r\n

Total Funding – $104,491<\/p>\r\n

Sponsoring Orgs \u2013 OST-R, The Citadel<\/p>\r\n

Description: <\/strong>Conveying new concepts and research results to the general public and professionals can help positively transform our practice and generally our future. This project will center its efforts on extending the technology transfer initiatives from three previously concluded C2M2 projects. These projects include the exploration of potential reductions in fatal crashes in South Carolina attributed to Automated Vehicles, the assessment of the potential of Bike Share Networks and Active Transportation to enhance urban mobility and public health outcomes, and the development of a Cloud-based Quantum Artificial Intelligence-supported Automated Truck Platooning Strategy aimed at reducing energy consumption and improving mobility. The ongoing technology transfer endeavors will be broadened, with the outcomes disseminated in national and international forums, as well as within academic circles. This dissemination aims to share valuable insights and findings derived from the completed research projects, fostering broader understanding and application in relevant fields.<\/span><\/p>\r\n<\/div>\r\n<\/div>\r\n<\/div>","protected":false},"excerpt":{"rendered":"

C2M2 sent out a Call for Proposals to researchers at our five partner institutions, launching our 2023\/24 round of funded projects in August 2023.\u00a0 In continuing with our goal to foster collaboration multi-institution projects were prioritized. The theme for this… Read moreFunded Projects 2023<\/span><\/span><\/a><\/p>\n","protected":false},"author":27,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-9242","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/cecas.clemson.edu\/C2M2\/wp-json\/wp\/v2\/pages\/9242","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cecas.clemson.edu\/C2M2\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/cecas.clemson.edu\/C2M2\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/cecas.clemson.edu\/C2M2\/wp-json\/wp\/v2\/users\/27"}],"replies":[{"embeddable":true,"href":"https:\/\/cecas.clemson.edu\/C2M2\/wp-json\/wp\/v2\/comments?post=9242"}],"version-history":[{"count":23,"href":"https:\/\/cecas.clemson.edu\/C2M2\/wp-json\/wp\/v2\/pages\/9242\/revisions"}],"predecessor-version":[{"id":9540,"href":"https:\/\/cecas.clemson.edu\/C2M2\/wp-json\/wp\/v2\/pages\/9242\/revisions\/9540"}],"wp:attachment":[{"href":"https:\/\/cecas.clemson.edu\/C2M2\/wp-json\/wp\/v2\/media?parent=9242"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}