Publications

Explainable Action Prediction through Self-Supervision on Scene Graphs
This work explores scene graphs as a distille representation of high-level information for autonomous driving, applied to future …
PDF
Explainable Action Prediction through Self-Supervision on Scene Graphs
Textual Explanations for Automated Commentary Driving
The provision of natural language explanations for the predictions of deep-learning-based vehicle controllers is critical as it …
PDF
Textual Explanations for Automated Commentary Driving
From Spoken Thoughts to Automated Driving Commentary: Predicting and Explaining Intelligent Vehicles' Actions
Commentary driving is a technique in which drivers verbalise their observations, assessments and intentions. By speaking out their …
PDF
From Spoken Thoughts to Automated Driving Commentary: Predicting and Explaining Intelligent Vehicles' Actions
Explanations in Autonomous Driving: A Survey
The automotive industry has witnessed an increasing level of development in the past decades; from manufacturing manually operated …
PDF
Explanations in Autonomous Driving: A Survey
Towards Accountability: Providing Intelligible Explanations in Autonomous Driving
The safe deployment of autonomous vehicles (AVs) in real world scenarios requires that AVs are accountable. One way of ensuring …
PDF
Towards Accountability: Providing Intelligible Explanations in Autonomous Driving
Assessing and Explaining Collision Risk in Dynamic Environments forAutonomous Driving Safety
Autonomous vehicles operating in dynamic environments are required to account for other traffic participants. By interpreting sensor …
Assessing and Explaining Collision Risk in Dynamic Environments forAutonomous Driving Safety
Why Not Explain? Effects of Explanations on Human Perceptions of Autonomous Driving
Autonomous vehicles (AVs) have the potential to change the way we commute, travel, and transport our goods. The deployment of AVs in …
PDF
Why Not Explain? Effects of Explanations on Human Perceptions of Autonomous Driving
Context-based Image Explanations for Deep Neural Networks
With the increased use of machine learning in decision-making scenarios, there has been a growing interest in explaining and …
Context-based Image Explanations for Deep Neural Networks
Towards Explainable and Trustworthy Autonomous Physical Systems
The safe deployment of autonomous physical systems in real-world scenarios requires them to be explainable and trustworthy, especially …
PDF
Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Models
Gaining insight into how deep convolutional neural network models perform image classification and how to explain their outputs have …
PDF
Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Models
A Fait Accompli? An Empirical Study into the Absence of Consent to Third-Party Tracking in Android Apps
Third-party tracking allows companies to collect users' behavioural data and track their activity across digital devices. This can put …
PDF
A Fait Accompli? An Empirical Study into the Absence of Consent to Third-Party Tracking in Android Apps
Realizing the Potential of AI in Africa: It All Turns on Trust
Most nations have recognized the disruptive influence of artificial intelligence (AI) on all aspects of their economies, from …
PDF
Efficient Machine Learning for Large-Scale Urban Land-Use Forecasting in Sub-Saharan Africa
Urbanization is a common phenomenon in developing countries and it poses serious challenges when not managed effectively. Lack of …
PDF
Efficient Machine Learning for Large-Scale Urban Land-Use Forecasting in Sub-Saharan Africa
Deep Convolutional Neural Network for Plant Seedlings Classification
Agriculture is vital for human survival and remains a major driver of several economies around the world; more so in underdeveloped and …
PDF
Deep Convolutional Neural Network for Plant Seedlings Classification
EEG-based Communication with a Predictive Text Algorithm
Several changes occur in the brain in response to voluntary and involuntary activities performed by a person. The ability to retrieve …
PDF
EEG-based Communication with a Predictive Text Algorithm