The integration of artificial intelligence into autonomous vehicles (AVs) raises transparency challenges that can hinder user acceptance and experience. To address when users need AV explanations, we created a large-scale dataset of 3327 diverse driving scenarios, each paired with a user-friendly explanation, and conducted an online study to survey when users need explanations. Using both scenario and user-related factors, our best-performing tree-ensemble models predicted explanation need with great performance (F1=0.72, AUC=0.82). SHAP analyses revealed that while both user- and scenario-related factors matter, factors directly related to driving (AV driving style, AV action, event cause, annual mileage, human driving style) were more contributive than general demographics and environmental factors. Our study delivers a comprehensively annotated dataset that underpins future human-AV interaction research, an explainable model that reliably predicts explanation needs, and valuable insights to inform the design of adaptive AV interfaces for superior user experiences.

This paper introduces a new framework, Drive-Blip2, built upon the BLIP2-OPT architecture, to generate accurate and contextually relevant explanations for emerging driving scenarios. While existing vision-language models perform well in general tasks, they encounter difficulties in understanding complex, multi-object environments, particularly in real-time applications such as autonomous driving, where the rapid identification of key objects is crucial. To address this limitation, an Attention Map Generator is proposed to highlight significant objects relevant to driving decisions within critical video frames. By directing the model’s focus to these key regions, the generated attention map helps produce clear and relevant explanations, enabling drivers to better understand the vehicle’s decision-making process in critical situations. Evaluations on the DRAMA dataset reveal significant improvements in explanation quality, as indicated by higher BLEU, ROUGE, CIDEr, and SPICE scores compared to baseline models. These findings underscore the potential of targeted attention mechanisms in vision-language models for enhancing explainability in real-time autonomous driving.

The rapid evolution of automated vehicles (AVs) has the potential to provide safer, more efficient, and comfortable travel options. However, these systems face challenges regarding reliability in complex driving scenarios. Recent explainable AV architectures neglect crucial information related to inherent uncertainties while providing explanations for actions. To overcome such challenges, our study builds upon the "object-induced" model approach that prioritizes the role of objects in scenes for decision-making and integrates uncertainty assessment into the decision-making process using an evidential deep learning paradigm with a Beta prior. Additionally, we explore several advanced training strategies guided by uncertainty, including uncertainty-guided data reweighting and augmentation. Leveraging the BDD-OIA dataset, our findings underscore that the model, through these enhancements, not only offers a clearer comprehension of AV decisions and their underlying reasoning but also surpasses existing baselines across a broad range of scenarios.

Fish modeling in complex environments is critical for understanding drivers of population dynamics in aquatic systems. This paper proposes a Bayesian network method for modeling fish survival and growth over multiple connected rivers. Traditional fish survival models capture the effect of multiple environmental drivers (e.g., stream temperature, stream flow) by adding different variables, which increases model complexity and results in very long and impractical run times (i.e., weeks). We propose a coupled survival-growth model that leverages the observations from both sources simultaneously. It also integrates the Bayesian process into the neural network model to efficiently capture complex variable relationships in the system while also conforming to known survival processes used in existing fish models. To further reduce the performance disparity of fish body length across cohorts, we propose two approaches for enforcing fairness by the adjustment of training priorities and data augmentation. The results based on a real-world fish dataset collected in Massachusetts, US demonstrate that the proposed method can greatly improve prediction accuracy in modeling survival and body length compared to independent models on survival and growth, and effectively reduce the performance disparity across cohorts. The fish growth and movement patterns discovered by the proposed model are also consistent with prior studies in the same region, while vastly reducing run times and memory requirements.

Retrosynthesis prediction is one of the fundamental challenges in organic synthesis. The task is to predict the reactants given a core product. With the advancement of machine learning, computer-aided synthesis planning has gained increasing interest. Numerous methods were proposed to solve this problem with different levels of dependency on additional chemical knowledge. In this paper, we propose Retroformer, a novel Transformer-based architecture for retrosynthesis prediction without relying on any cheminformatics tools for molecule editing. Via the proposed local attention head, the model can jointly encode the molecular sequence and graph, and efficiently exchange information between the local reactive region and the global reaction context. Retroformer reaches the new state-of-the-art accuracy for the end-to-end template-free retrosynthesis, and improves over many strong baselines on better molecule and reaction validity. In addition, its generative procedure is highly interpretable and controllable. Overall, Retroformer pushes the limits of the reaction reasoning ability of deep generative models.

The Internet of Vehicles (IoV) is a set of connected vehicles supported with sensors, communication technologies, and software connected by the Internet as an infrastructure. With the evolution of 5G technology, automation, and artificial intelligence, the IoV is expected to replace traditional transportation systems in the near future. On the other hand, with this evolution, the possibility of new cyberattacks has increased. This paper proposes a security framework in which intrusion detection secures the Intra/Inter-Vehicular communications within the IoV network. The proposed framework uses multi-task trans-fer learning to transfer knowledge gained from two different benchmark datasets. To the best of our knowledge, this is the first work that uses transfer learning to transfer the knowledge between two different benchmark datasets. The performance of the intrusion detection engine is evaluated using two different deep learning algorithms, namely Deep Neural Network (DNN) and Convolutional Neural Network (CNN), in terms of accuracy, precision, recall and F1-score. In addition to achieving satisfying performance and reduced training/fine-tuning time for the target domains, our analysis illustrates the computational effectiveness of the proposed model by transferring the knowledge from the smaller to the larger dataset.