As the scale of multiprocessor systems increases, so do the requirements for system reliability and security. Modeling how processors and links are connected in a multiprocessor system through a network topology (or graph) is an effective means to study the reliability of the system. Connectivity, one of the important concepts in graph theory, can be used as an indicator of multiprocessor system’s reliability. However, as classical connectivity is not well suited for practical applications, the concept of$g$-extra connectivity has been proposed to more accurately characterize system’s reliability. The exchanged crossed cube, an innovative network topology derived from the classical hypercube, achieves not only a smaller diameter (improving information transmission efficiency) but also fewer connecting edges (reducing hardware costs when scaling the network). In this article, we derive the$g$-extra connectivity of the exchanged crossed cube and comparatively analyze its advantages in reliability evaluation through simulations.

Deep reinforcement learning (DRL) has gained significant attention in autonomous systems, yet its black-box nature and lack of explainability hinder user trust in safety-critical domains such as autonomous driving. Existing experience replay approaches enhance sample efficiency but often fail to capture the internal causality of training data, leading to a convoluted training process that is difficult for humans to explain. In this work, we introduce Experience Replay with Causal Inference (ERCI), an explainable approach that integrates time series representation and causal inference to offer human-aligned explanations for DRL. Specifically, ERCI 1) introduces a novel multivariate time series representation to extract explainable Time Series Causal Factors (TSCF) from experimental data and 2) leverages internal causality in TSCFs with causal inference as a crucial standard for experience replay in DRL training. We evaluate ERCI using multiple baseline algorithms across diverse environments. Results show that ERCI provides human-aligned explanations and further improves sample efficiency through enhanced explainability. Notably, ERCI outperforms other state-of-the-art approaches by 15% in average performance, highlighting its effectiveness and generalizability.

Salient Object Detection (SOD) aims to identify and segment the most striking elements within an image. Salient object detection methods can be differentiated into several types according to the input data, such as RGB-D (Depth) and RGB-T (Thermal). Previous research primarily focused on saliency detection for single data types. However, forcing an RGB-D SOD model to process RGB-T data will degrade its performance significantly. In addition, current methods still face challenges in detecting fine edge details of salient objects and achieving end-to-end training. To address these issues, we introduce diffSOD, which leverages stable diffusion and cross-modal feature rectification and fusion module for saliency detection by transforming salient object detection into a denoising process from a noisy mask to an object mask. It offers a unified solution for salient object detection that seamlessly spans both RGB-D SOD and RGB-T SOD. Extensive experiments validate the effectiveness of the proposed diffSOD, demonstrating its ability to efficiently detect salient objects across both RGB-D and RGB-T data, while achieving superior performance over state-of-the-art methods.

Imitation learning is a promising approach to acquiring autonomous driving policies by mimicking human driver behaviors. However, a major drawback of existing driving policies derived from imitation learning is their proneness to capturing spurious correlations, owing to the lack of an explicit causal model. Deploying such policies in unpredictable real-world environments poses severe risks, as spurious correlations may result in flawed decisions that compromise safety. To tackle this challenge, we introduce a novel approach called Multi-Task Invariant Representation Imitation Learning (MIRIL). MIRIL combines invariant learning with imitation learning to identify cross-environment invariant causal representations from driving demonstrations in various scenarios. These representations are then fed into multiple downstream branches for multi-task learning, including policy learning, perception prediction, invariant representation learning, and transition dynamics learning. Through the multi-task learning approach, the model not only makes consistent driving decisions across different environments but also perceives the vehicle's surroundings, thereby improving adaptability and robustness in diverse driving conditions. This enables MIRIL to effectively handle a wide range of driving scenarios, ensuring safety and efficiency. Supported by clear metrics, this paper details our comprehensive experimental setup, including datasets, benchmarks, and comparative analyses, underscoring the capability of MIRIL to significantly boost system generalization and excel in decision-making significantly.

We propose an importance sampling method for tractable and efficient estimation of counterfactual expressions in general settings, named Exogenous Matching. By minimizing a common upper bound of counterfactual estimators, we transform the variance minimization problem into a conditional distribution learning problem, enabling its integration with existing conditional distribution modeling approaches. We validate the theoretical results through experiments under various types and settings of Structural Causal Models (SCMs) and demonstrate the outperformance on counterfactual estimation tasks compared to other existing importance sampling methods. We also explore the impact of injecting structural prior knowledge (counterfactual Markov boundaries) on the results. Finally, we apply this method to identifiable proxy SCMs and demonstrate the unbiasedness of the estimates, empirically illustrating the applicability of the method to practical scenarios.

Cardiovascular disease (CVD) is the leading cause of global death. The Electrocardiogram (ECG) is the most widely adopted tool that measures the electrical activities of the heart from the body surface. However, heart rhythm irregularities and other heat attack problems cannot always be detected on a standard resting ECG machine, since they may not occur during an individual's recording session. Common Holter-based portable ECG detection systems lack the capability to provide real-time feedback and has allergic and discomfort problems cased by wet Ag/AgCl electrodes. In this paper, we seek to establish a cell phone-based real-time monitoring system for CVD. To improve the comfort during long term ECG monitoring, a noncontact ECG detection system based on capacitive coupling was designed, fabricated and tested. Capacitive sensing of ECG allows unobtrusively monitoring of the heart, thus has a lot of advantage over the conventional wet Ag/AgCl electrodes, such as zero preparation time, insensitive to skin conditions and has the potential to be embedded in the clothes etc.

We developed and tested the Institute of Electronics, Chinese Academy of Sciences (IECAS) 3AHcare node, a health monitoring device capable of measuring a subject's ECG, blood pressure, blood oxygenation, respiration, temperature and motion - almost equivalent to the feature set of a hospital bedside patient monitor. The main contribution of this paper include: the device has been a highly integrated design incorporating the radio and all associated circuitry on a single PCB; a new noninvasive and cuff-less measurement of blood pressure using pulse wave transit time has been designed and validated. The device stores data locally on microSD flash and /or transmits via Bluetooth and/or Zigbee. We have developed a bandage vest which embeds reusable electrodes for data acquisition as well as a desktop and mobile application for real-time data telemetry. We have evaluated the performance of the device in capturing and recording ambulatory data and found the device easy to use and with high precision.