Using FPGA to accelerate the application of convolutional neural networks has attracted more and more attention. However, the design technology of the FPGA accelerator cannot follow up the latest achievements of the convolutional neural networks, nor can it consider optimizing the complex network structure combined with the characteristics of hardware to improve the accuracy of the network and simplify the implementation of hardware. To address these issues, in this paper, we adopt the development idea of algorithm-hardware co-design, compress the structure and optimize the operator for a state-of-the-art lightweight person re-identification network, and design a new network model SGCNet (Shift Gaussian Convolution Network). Specifically, SGCNet is obtained by structure optimization and operator replacement according to the optimization degree of the operator in the FPGA hardware environment. For convolution operation, only 1 × 1 kernel convolution operator is adopted in SGCNet, while spatial convolution is replaced by a more effective shift operation. SGCNet is more concise and clear in the operation types and complex structure of the network. Experimental evaluations demonstrate that SGCNet’s top-5 accuracy of 92.7% on ImageNet and R1 accuracy of 74.6% on CUHK03 of person re-identification data set, is higher than CMSNet network.
Trajectory data contains rich spatio-temporal information of moving objects. Directly publishing it for mining and analysis will result in severe privacy disclosure problems. Most existing clustering-anonymity methods cluster trajectories according to either distance- or direction-based similarities, leading to a high information loss. To bridge this gap, in this paper, we present a clustering-anonymity approach considering both these two types of similarities. As trajectories may not be synchronized, we first design a trajectory synchronization algorithm to synchronize them. Then, two similarity metrics between trajectories are quantitatively defined, followed by a comprehensive one. Furthermore, a clustering-anonymity algorithm for trajectory data publishing with privacy-preserving is proposed. It groups trajectories into clusters according to the comprehensive similarity metric. These clusters are finally anonymized. Experimental results show that our algorithm is effective in preserving privacy with low information loss.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.