Vertical Federated Learning (VFL) enables the construction of models by combining clients with different features without compromising privacy. Existing VFL methods exhibit tightly coupled participant parameters, resu...
详细信息
With the explosive growth of mobile data, Mobile Crowd Sensing (MCS) has become a popular paradigm for large-scale data collection. The difficulty of data collection and the gaps in workers’ sensing capabilities are ...
详细信息
This work proposes a novel multi-robot task allocation framework for robots that can switch between multiple modes, e.g., flying, driving, or walking. We first provide a method to encode the multi-mode property of rob...
详细信息
In recent years, there has been growing interest in multi-view subspace clustering for handling multiple-view data. While current methodologies typically aim to capture both consistency and complementarity between vie...
详细信息
The structure of the rocket-borne model is inherently complex, with processed images exhibiting high resolution and generating substantial amounts of data and calculations. Achieving robust real-time computing on an e...
详细信息
ISBN:
(数字)9798331531881
ISBN:
(纸本)9798331531898
The structure of the rocket-borne model is inherently complex, with processed images exhibiting high resolution and generating substantial amounts of data and calculations. Achieving robust real-time computing on an embedded platform poses significant challenges due to strictly limited resources, power consumption constraints, and size limitations. Our review of rocket-borne applications reveals considerable variability in the design resources of different devices, indicating a need for expanded design approaches. Upon evaluating existing methods, we identified two primary drawbacks. First, certain operators within the high-resolution target detection model are difficult to parallelize, resulting in significant inference delays that hinder the ability to meet task requirements. Although existing methods have been extended, there remains significant potential for performance enhancement in core scheduling for poor acceleration. This paper proposes an optimized architecture for the target detection algorithm accelerator designed for high-resolution images, along with a novel highly parallel data pre-processing and post-processing module implemented on FPGA to address these issues. Compared to the ARM implementation, this architecture demonstrates an improved performance of 24.64x. Furthermore, to ensure flexible application across various rocket launch scenarios, we introduce an optimization structure for convolution, pooling, and fusion operators and a multi-core expansion optimization method. This approach yields a 1.29x improvement in computing unit utilization compared to state-of-the-art multi-core scaling efforts. Finally, we assessed the accelerator architecture across multiple FPGA platforms, achieving a peak processing element utilization rate of 99.71% for a single core and layer. The overall computing efficiency, excluding the first layer, exceeded 90%. The peak computing power for the four cores reached 1638.4 GOPS, and the end-to-end computation time for
Cloud computing has revolutionized the provisioning of computing resources, offering scalable, flexible, and on-demand services to meet the diverse requirements of modern applications. At the heart of efficient cloud ...
详细信息
Dual three-phase permanent magnet synchronous motor drives have gained considerable interest in those applications requiring high levels of reliability. However, they often suffer from high-order harmonic currents and...
详细信息
— Social learning provides a fundamental framework in economics and social sciences for studying interactions among rational agents who observe each other’s actions but lack direct access to individual beliefs. This...
详细信息
Traditional scan-direct absorption spectroscopy (scan-DAS) is susceptible to 1/f noise, limiting its ability to realize high signal-to-noise ratio (SNR) measurements. This study proposes a calibration-free and noise-i...
详细信息
Myocardial Infarction (MI) is a major global health threat, where rapid and accurate diagnosis is essential for improving treatment outcomes. This study proposes MSRC-TransBLSTM, a deep learning-based hierarchical hyb...
详细信息
ISBN:
(纸本)9798400712425
Myocardial Infarction (MI) is a major global health threat, where rapid and accurate diagnosis is essential for improving treatment outcomes. This study proposes MSRC-TransBLSTM, a deep learning-based hierarchical hybrid model for the automatic detection of MI. The model combines spatial and temporal features through a hierarchical modeling strategy: multi-layer convolutional blocks and improved MSRC modules extract and optimize spatial features, strengthening the representation of both local and global features. For temporal modeling, the Transformer Encoder captures global dependencies, while the BLSTM focuses on refining local dynamics features. Experiments on the PTB-XL dataset demonstrated the model's strong performance across key metrics (Acc = 98.68%, Sen = 97.33%, F1 = 97.43%). Compared to other models, it achieves notable improvements in accuracy and feature representation, confirming its effectiveness in MI detection.
暂无评论