Quantum Computing (QC) works based on the principle of quantum mechanics, which is different from traditional computers. Heart disease remains the leading cause of mortality worldwide and the development of advanced p...
详细信息
This paper describes a novel virtual platform for university teaching, which in particular allows the creation and use of complex IT infrastructures even for non-experts. Until now, complex network infrastructures in ...
详细信息
This paper introduces a novel approach to enhance privacy-preserving machine learning (PPML) by integrating adversarial techniques with Homomorphic Encryption (HE) and Differential Privacy (DP). Privacy-Preserving mac...
详细信息
Current software evaluation work based on complex networks rarely considers the complexity of nodes themselves and the multiple coupling between nodes, making it difficult to accurately identify high complexity and hi...
详细信息
Heterogeneous Graph Neural networks (HGNNs) have emerged as powerful tools for handling heterogeneous graphs. However, current HGNNs often rely on meta-paths or intricate aggregation operations. In response, we introd...
详细信息
Lip detecion(LD) holds great promise for mobile human-computer interaction(HCI) terminals such as hearing aids, robots, smartphones etc. However they suffer from the massive computation and resource overhead from main...
详细信息
ISBN:
(纸本)9798350387186;9798350387179
Lip detecion(LD) holds great promise for mobile human-computer interaction(HCI) terminals such as hearing aids, robots, smartphones etc. However they suffer from the massive computation and resource overhead from mainstream models as Viola-Jones framework, convolutional neural networks(CNN), recurrent neural networks(RNN) and vision transformer(ViT). To solve this problem, we propose a resource-efficient lip detector(RELD) for mobile HCI applications. For lip region of interest(ROI) detection, a hybrid feature criteria is constructed utilizing the hump-like curve formed by row-summation of lip ROI. And a L-order predictive tracking method is proposed to track the lip bounding box in conitnuous image flows with low computation and latency. For behavioural validation, RELD ahieves test accuracy over 95% on a database of 204000 images generated from GRID dataset. To verify its hardware feasibility, an RTL implementation has been accomplished based on 200 x 200 images read from OV7670 image sensor, showing that RELD requires only 352 bytes of SRAM and <= 5000 MAC operations per frame to perform lip detection task.
Aggregate Computing is an emerging macropro-gramming paradigm, whose validation is often performed by simulation. In this work, we compare the existing JVM-based toolkits from a performance point of view and show that...
详细信息
Community detection is a fundamental operation in graph mining, and by uncovering hidden structures and patterns within complex systems it helps solve fundamental problems pertaining to social networks, such as inform...
详细信息
ISBN:
(纸本)9798350364613;9798350364606
Community detection is a fundamental operation in graph mining, and by uncovering hidden structures and patterns within complex systems it helps solve fundamental problems pertaining to social networks, such as information diffusion, epidemics, and recommender systems. Scaling graph algorithms for massive networks becomes challenging on modern distributed-memory multi-GPU (Graphics Processing Unit) systems due to limitations such as irregular memory access patterns, load imbalances, higher communication-computation ratios, and cross-platform support. We present a novel algorithm HiPDPL-GPU (distributed Parallel Louvain) to address these challenges. We conduct experiments involving different partitioning techniques to achieve an optimized performance of HiPDPL-GPU on the two largest supercomputers: Frontier and Summit. Remarkably, HiPDPL-GPU processes a graph with 4.2 billion edges in less than 3 minutes using 1024 GPUs. Qualitatively, the performance of HiPDPL-GPU is similar or better compared to other state-of-the-art CPU- and GPU-based implementations. While prior GPU implementations have predominantly employed CUDA, our first-of-its-kind implementation for community detection is cross-platform, accommodating both AMD and NVIDIA GPUs.
This article suggests a novel method for protecting corporate cybersecurity systems from malevolent attacks, based on Capsule networks (CapsNets). The enhancement of hierarchical feature learning by Capital networks i...
详细信息
The burgeoning deployment of unmanned aerial vehicles (UAVs) in dynamic environments to perform complicated tasks has engendered significant challenges in UAV networks, predominantly due to unstable communication link...
详细信息
ISBN:
(纸本)9798350350227;9798350350210
The burgeoning deployment of unmanned aerial vehicles (UAVs) in dynamic environments to perform complicated tasks has engendered significant challenges in UAV networks, predominantly due to unstable communication links and changing network topology. This paper proposes a distributed geographic multipath routing strategy based on fountain code, achieving low-latency and reliable routing under dynamic and complex UAV network topologies. We conduct the theoretical analysis of end-to-end latency based on the relationship of distinct encoded packets among the UAVs, and propose an joint optimization model to enhance routing efficiency. Since that the centralized routing with overall joint optimization is not adapt the dynamic topology, we propose a distributed approach based on geographical multipath routing. This approach divides the original problem into multiple sub-problems, which are executed separately at the source UAV and intermediate UAVs, thus achieving distributed routing decisions. Unlike existing work that ignore the differences of encoded packets, we further introduced a cross-entropy-based transmission control model that enables the forwarding of distinct packet groups. Simulation experiments indicate that this solution can effectively reduce overall communication latency and improve route reachability.
暂无评论