Multimodal image fusion (MIF) seeks to amalgamate complementary information from various image modalities, offering a more comprehensive and accurate representation of data. Convolutional sparse coding (CSC) based methods have demonstrated effectiveness in this domain. However, they encounter difficulties in adaptively discerning and leveraging cross-modality feature correlations, which essentially presents a multi-objective optimization challenge, such as maximizing information retention while minimizing feature distortion. To address this issue, we introduce a self-attention based multi-objective genetic programming (SA-MOGP) method. SA-MOGP frames the quest for an optimal fusion strategy as a multi-objective optimization problem. By integrating the self-attention mechanism into strongly typed genetic programming (STGP), it enables efficient exploration of associations between sparse features across different modalities. Our approach is structured in three hierarchical layers. The feature extraction (FE) layer automatically generates Q, K, V sub-trees according to a predefined function set. These are then input into the self-attention (SA) layer for computation. Finally, the output layer estimates the fusion weights. We utilize the NSGAII framwork to solve this multi-objective problem, aiming for Pareto front solutions. Experiments on infrared-visible and medical image datasets attest to the superior performance of the SAGP method in multimodal image fusion.

Focusing on the privacy concerns and leakage abuse of sensory data collection in mobile crowdsensing (MCS) environment, we propose a crowdsensed data-oriented distributed and secure spatial query scheme while ensuring data privacy as long as query patterns. To cater to the demands of real-world MCS workloads, we designed a distributed multi-layer architecture and leveraged distributed hash functions(DHT) and broadcast encryption(BE) to achieve load-balancing and enforce access control. Our scheme incorporates a recently developed cryptographic tool–function secret sharing (FSS) to safeguard the query pattern and sensory data from potential compromises at the server layer.The analysis demonstrates that our scheme achieves affordable query complexity while satisfying adaptive $\mathcal{L}$-semantic security. Encouraging experimental results substantiate the efficacy of our scheme, the growth rates of query cost diminishes as the number of records and participants increases. These findings emphasize the suitability of our scheme for crowdsensing applications with fine-grained access control requirements and establish it as an efficient cryptographic tool that holds promise for diverse MCS applications.

A cause-effect chain is a sequence of multi-rate real-time tasks with data dependency. Cause-effect chains are generally subject to end-to-end timing constraints, especially in safety-critical systems. Communication paradigms greatly affect the end-to-end latency of cause-effect chains. This paper compares different communication paradigms (implicit communication, LET, DBP) with regards to the end-to-end latency of cause-effect chains using them, and proposes priority assignment strategies to optimize the end-to-end latency with specific communication paradigm. Experiments with synthesized data based on an automotive benchmark and randomly generated parameters are conducted to evaluate our results.

Real-time systems require locking protocols to coordinate access to shared resources. With the booming revolution of parallel processing technology in real-time systems, there has been some work addressing the problem of extending classic locking protocols for sequential real-time tasks to parallel tasks. However, it may not be most effective to trivially follow the progress mechanisms and queue orders designed for sequential tasks since the intrastructure information within a parallel task is not taken into consideration. This article investigates the design of locking protocols for parallel tasks using a novel mechanism—longest normal Section first (LNSF)—to consider the impact of normal sections on blocking behavior in parallel tasks and further improve real-time performance. LNSF is then implemented in a locking protocol for parallel tasks named POMIP, and associated blocking analysis techniques are presented. Empirical evaluations show that our proposed analysis dominated other state-of-the-art analysis—in best cases, the acceptance ratio of the task set can be improved by around 17%.

Locks are the most widely used mechanisms to coordinate simultaneous accesses to exclusive shared resources. While locking protocols and associated schedulability analysis techniques have been extensively studied for sequential real-time tasks, work for parallel tasks largely lags behind. In the limited existing work on this topic, a common assumption is that a critical section must execute sequentially. However, this is not necessarily the case with parallel programming languages. In this paper, we study the analysis of parallel heavy real-time tasks (the density of which is greater than 1) with critical sections in parallel structures. We show that applying existing analysis techniques directly could be unsafe or much pessimistic for the considered model, and develop new techniques to address these problems. Comprehensive experiments are conducted to evaluate the performance of our method.

ROS (Robot Operating System) is currently one of the most popular development frameworks for robotic software, which is usually subject to hard real-time constraints in safe-critical domains. Designers must formally model and analyze its timing behaviors to guarantee that real-time constraints are always honored at run-time. This paper studies real-time scheduling and analysis under a multi-threaded executor in ROS 2. We present a formal description of the scheduling model of multi-threaded executors, and develop response time analysis techniques for processing chains executing on it. Moreover, we identify a risk of increasing the response time of chains that may be caused by improper design when deploying systems on multi-threaded executors, which provides a useful guidance to designers. We conduct experiments with both randomly generated workloads and case studies on a realistic ROS 2 platform to evaluate and demonstrate our results.

Accurate and efficient segmentation of prostate image plays an important role in the diagnosis of prostate cancer. Since convolutional neural network demonstrates superior performance in computer vision applications, we present a multi-layer deeply supervised deconvolution network (DSDN) which completes end-to-end training to automatically segment magnetic resonance (MR) images. We put additional deeply supervised layers to supervise the performance of hidden layers. During training, the backpropagation process of gradient information in the additional deeply supervised layers accelerates the parameters update for hidden layers, which makes the trained model has strong capacity of features learning as well as passes the extracted features from shallow layers to higher layers effectively. A set of experiments using prostate magnetic resonance (MR) images is carried out to demonstrate that significant segmentation accuracy improvement has been achieved by our proposed method compared to other reported approaches.

Magnetic resonance(MR) imaging has shown to be succeed in detecting and visualizing the prostate location. The accurate segmentation of the prostate gland from MR images is necessary for clinical applications. However, the segmentation of prostate is also a challenging task because of the shape of prostate varies significantly and the inhomogeneous intensity distributions in different scans. In this paper, we present an automatic deep learning method for prostate MR images segmentation using the enhanced holistically-nested framework. The network Holistically-Nested Networks(HNN) was first proposed as an image-to-image solution to extract object edges and boundaries visually. We modify HNN via putting additional skip connections from later stages to early stages in order to combine both low-level features and high-level features. The deeper framework exploits multi-level and multi-scale information for the image-to-image prediction in a holistic manner. Experimental evaluation demonstrates that significant segmentation accuracy has been achieved by our proposed enhanced holistically-nested networks compared to other deep learning approaches.