Pedestrian detection plays a critical role in intelligent perception systems in autonomous vehicles, which directly influences the reliability and safety of the overall system. Advanced in-vehicle sensor technology has enabled the continuous evolution of pedestrian detection systems by leveraging heterogeneous multimodal inputs such as RGB, infrared, depth, Light Detection And Ranging, and event data. Nevertheless, establishing a robust pedestrian detection system that is capable of integrating and processing such heterogeneous multimodal data effectively remains a significant challenge. At the same time, growing concerns about data privacy among automobile manufacturers have hindered further advances in detection model performance by restricting the sharing of private data within the industry. In this paper, a novel personalised federated learning framework, Kolmogorov-Arnold network-based Dual Expert Transformer Heterogeneous Personalized Federated Learning (KDET-HPFL), is proposed for multimodal pedestrian detection. To be specific, the KDET pedestrian detector is developed based on an expert feature selection module (which is designed to adaptively choose essential features from multimodal data) and a Group-Rational Kolmogorov-Arnold Network module, which enhances the feature extraction capabilities and improves the detection performance effectively. The HPFL framework is proposed for data privacy protection on heterogeneous multimodal data, where a cross-client aggregation (CCA) method is put forward by integrating different aggregation methods for certain layers in the KDET detector. With CCA, the HPFL framework achieves personalised feature retention of multimodal data pairs on multiple clients and improved model aggregation effect for each client. Experimental findings reveal that the proposed KDET-HPFL framework outperforms some existing personalised federated learning frameworks for pedestrian detection on four public datasets (i.e., LLVIP, STCrowd, InOutDoor, and EventPed) with mAP scores of 73.74%, 75.39%, 66.14%, and 79.57%, respectively.

Accurate prediction of material removal depth and averaged surface roughness is crucial for evaluating the performance of robotic belt grinding (RBG). Nevertheless, the machining parameters of RBG across different spaces exhibit various data distributions, which often results in prediction shifts on unseen machining parameters when using conventional approaches. In this article, we introduce a pairwise domain adaptation-assisted dual-task learning (PW-DA-DTL) method for copredicting material removal depth and averaged surface roughness with regard to new RBG machining parameter spaces. The multigate mixture-of-experts method is employed as the foundational framework for dual-task learning, effectively capturing and modeling the relationships between material removal depth and average surface roughness by leveraging their inherent task interdependencies. The pairwise domain adaptation strategy is put forward to simultaneously enhance sample diversity and mitigate cross-domain data distribution discrepancy between the existing and new RBG machining parameter spaces. Comparative experiments are presented to demonstrate the effectiveness and superiority of the proposed PW-DA-DTL method.

The application of artificial intelligence (AI) systems has surged in the high-risk area of medicine, and these systems must explain their decisions to different users. However, existing explainable AI (XAI) design practices in the medical domain are mostly focused on domain experts, such as physicians, and there is a lack of XAI design practices for consumer users. Therefore, we developed a library of XAI user needs in the medical domain, which can be used as an auxiliary tool for the development of user-centered XAI design solutions in this domain. Moreover, through empirical research, based on our XAI user Needs Library, we designed an XAI-based electrocardiogram diagnostic system prototype for consumer users and conducted a user evaluation. The results provide the empirical experience of the design space of XAI and promote consumer user-centered XAI practices.

In this paper, the torus-event-based fault detection and isolation (FDI) problem is investigated for a class of time-varying multirate systems. An ellipsoidal constraint is first adopted to describe the fault in a more practical pattern, and a novel torus-event-triggering scheme is proposed to improve the unilateral triggering mechanism. The aim is to design the torus-event-based fault detection filter and fault isolation estimators such that both the prescribed variance constraint on the estimation error and the desired H∞performance on the disturbance are guaranteed over the finite horizon. Especially, the residual evaluation function is employed to detect the fault, and the residual matching function is developed to isolate the fault. Furthermore, three optimization problems are provided to seek separately the minimal parameters on the H∞performance level, the upper bound of the estimation error variance, and the triggering torus. Finally, two simulation examples are utilized to show the effectiveness of the FDI scheme proposed in this paper.