Federated learning-based 3D pothole detection, evaluation, and routing for smart transportation

Bad road conditions can cause vehicle damage and create hazardous driving conditions. Auto damages caused by potholes can add up to thousands of dollars per vehicle. Besides, pothole resolution is one of the most expensive street maintenance strategies. Most cities have established social data networks (i.e., Open Data KC 311 in Kansas City) for residents to report potholes to mitigate the problem. However, current reporting methods for bad road conditions are a burden for the reporter, so these conditions might not be reported. Although rudimentary patching policies are defined by the road condition's volume and significance in many cities, it does not provide optimized resolution routes. Some new technologies have been applied to overcome detecting and reporting; however, there are substantial challenges in assessing and reporting methods. Smart cities leverage physical and virtual technologies that rely on sensors and cloud-based communication to improve urban environments. In this matter, this dissertation proposes an Intelligent Real-Time Detection, Reporting, Evaluation, and Routing System of Road Conditions with (MRI) Maintenance Responsiveness Indicator using IoT and Artificial Intelligence technologies. Mainly, this dissertation is formed on three levels. First, we developed an IoT-based road conditions classification System. We used smartphones to collect accelerometer data and analyzed the data to classify road conditions with this system. It can detect potholes, cracks, and smoothness and monitor road parts, such as bridge structures, bumps, and road dips. Secondly, we built a Federated Learning-based 3D Pothole Detection for Smart Transportation to detect road conditions and hazards. This system uses crowd-voting to calculate the city's MRI (Maintenance Responsiveness Indicator). Applying both approaches, we calculate the avoidance score and priority values for road defects. Finally, the third part of this dissertation will cover an important role in road maintenance, optimizing road service routes very efficiently. The work in this dissertation supports cities in transitioning into Smart Transportation in 3 Tiers: 3D detection, comprehensive evaluation (road defects, priority values, and maintenance responsiveness evaluation), and route optimization.

Name thesis:degree_name

Ph.D. (Doctor of Philosophy)

Level thesis:degree_level

Doctoral

Discipline thesis:degree_discipline

Computer Networking and Communication Systems (UMKC)

Grantor

University of Missouri--Kansas City

Year dc:date.issued

2024

Author dc:creator

• Alshammari, Sami A. Q.

Advisor dc:contributor.advisor

• Song, Sejun

Handle dc:identifier.uri

https://hdl.handle.net/10355/98964

OAI identifier oai:identifier

oai:mospace.umsystem.edu:10355/98964