Frank Ngeni

Deep learning (DL)-based image classification models are essential for autonomous vehicle (AV) perception modules since incorrect categorization might have severe repercussions. Adversarial attacks are widely studied cyberattacks that can lead DL models to predict inaccurate output, such as incorrectly classified traffic signs by the perception module of an autonomous vehicle. In this study, we create and compare hybrid classical-quantum deep learning (HCQ-DL) models with classical deep learning (C-DL) models to demonstrate robustness against adversarial attacks for perception modules. Before feeding them into the quantum system, we used transfer learning models, alexnet and vgg-16, as feature extractors. We tested over 1000 quantum circuits in our HCQ-DL models for projected gradient descent (PGD), fast gradient sign attack (FGSA), and gradient attack (GA), which are three well-known untargeted adversarial approaches. We evaluated the performance of all models during adversarial attacks and no-attack scenarios. Our HCQ-DL models maintain accuracy above 95\% during a no-attack scenario and above 91\% for GA and FGSA attacks, which is higher than C-DL models. During the PGD attack, our alexnet-based HCQ-DL model maintained an accuracy of 85\% compared to C-DL models that achieved accuracies below 21\%. Our results highlight that the HCQ-DL models provide improved accuracy for traffic sign classification under adversarial settings compared to their classical counterparts.

Recent technological developments have attracted the use of machine learning technologies and sensors in various pavement maintenance and rehabilitation studies. To avoid excessive road damages, which cause high road maintenance costs, reduced mobility, vehicle damages, and safety concerns, the periodic maintenance of roads is necessary. As part of maintenance works, road pavement conditions should be monitored continuously. This monitoring is possible using modern distress detection methods that are simple to use, comparatively cheap, less labor-intensive, faster, safer, and able to provide data on a real-time basis. This paper proposed and developed two models: computer vision and sensor-based. The computer vision model was developed using the You Only Look Once (YOLOv5) algorithm for detecting and classifying pavement distresses into nine classes. The sensor-based model combined eight Controller Area Network (CAN) bus sensors available in most new vehicles to predict pavement distress. This research employed an extreme gradient boosting model (XGBoost) to train the sensor-based model. The results showed that the model achieved 98.42% and 97.99% area under the curve (AUC) metrics for training and validation datasets, respectively. The computer vision model attained an accuracy of 81.28% and an F1-score of 76.40%, which agree with past studies. The results indicated that both computer vision and sensor-based models proved highly efficient in predicting pavement distress and can be used to complement each other. Overall, computer vision and sensor-based tools provide cheap and practical road condition monitoring compared to traditional manual instruments.

Illegal removal of road barricades without the notice of road emergency officials and road users has resulted in fatalities, injuries, and property damages. It is only after an incident has occurred or someone noticed the removal and alerted the authorities for the barricade to be placed back at its intended location. There is a need for traditional barricades to be equipped with mechanisms that would alert officials on illegal road barricade removal and warn road users of a road/lane(s) closure to prevent fatalities, injuries, and property damages to the traveling public. This research has used the Global Positioning System (GPS) module to implement the detection of barricade displacement and an alerting system for emergency officials and road users. The barricade displacement was estimated from the haversine distance formula, corrected for errors, and interfaced with the displacement threshold value for the road users within a geofenced area to be alerted. The geofenced area radius was estimated to be 1.04 miles from the barricade location using AASHTO, NSC, and TransGuide ITS manuals. The non-parametric bootstrapping method estimated the GPS position error to 10.5 feet and corrected the measured distances. Data from a clear sunny day shows the best response to barricade movements compared to a cloudy day where movements can’t be explained easily. The proposed monitoring and warning systems would warn road users and alert emergency officials of the danger when the physical barricades have been removed illegally hence saving lives and reducing property damages.