Semantic segmentation predicts dense pixel-wise semantic labels, which is crucial for autonomous environment perception systems. For applications on mobile devices, current research focuses on energy-efficient segmenters for both frame and event-based cameras. However, there is currently no artificial neural network (ANN) that can perform efficient segmentation on both types of images. This paper introduces spiking neural network (SNN, a bionic model that is energy-efficient when implemented on neuromorphic hardware) and develops a Spiking Context Guided Network (Spiking CGNet) with substantially lower energy consumption and comparable performance for both frame and event-based images. First, this paper proposes a spiking context guided block that can extract local features and context information with spike computations. On this basis, the directly-trained SCGNet-S and SCGNet-L are established for both frame and event-based images. Our method is verified on the frame-based dataset Cityscapes and the event-based dataset DDD17. On the Cityscapes dataset, SCGNet-S achieves comparable results to ANN CGNet with 4.85 × energy efficiency. On the DDD17 dataset, Spiking CGNet outperforms other spiking segmenters by a large margin.
This paper presents a novel approach of radar station intelligence quality evaluation which based on fuzzy Backpropagation neural network (BPNN). Firstly, the index system of the radar station intelligence quality evaluation is established according to the analysis of the process, the characteristics, and the main influencing factors of the radar station intelligence production. And then the factor set, comment set and the membership matrix are structured, the fuzzy BPNN for evaluating the quality of the radar station intelligence is designed referring to the index system. Finally, the experiment shows that the accuracy and stability can be improved effectively by using fuzzy BPNN to evaluate the radar station intelligence quality
IntroductionThe spiking neural network (SNN) is a bionic model that is energy-efficient when implemented on neuromorphic hardwares. The non-differentiability of the spiking signals and the complicated neural dynamics make direct training of high-performance SNNs a great challenge. There are numerous crucial issues to explore for the deployment of direct training SNNs, such as gradient vanishing and explosion, spiking signal decoding, and applications in upstream tasks.MethodsTo address gradient vanishing, we introduce a binary selection gate into the basic residual block and propose spiking gate (SG) ResNet to implement residual learning in SNNs. We propose two appropriate representations of the gate signal and verify that SG ResNet can overcome gradient vanishing or explosion by analyzing the gradient backpropagation. For the spiking signal decoding, a better decoding scheme than rate coding is achieved by our attention spike decoder (ASD), which dynamically assigns weights to spiking signals along the temporal, channel, and spatial dimensions.Results and discussionThe SG ResNet and ASD modules are evaluated on multiple object recognition datasets, including the static ImageNet, CIFAR-100, CIFAR-10, and neuromorphic DVS-CIFAR10 datasets. Superior accuracy is demonstrated with a tiny simulation time step of four, specifically 94.52% top-1 accuracy on CIFAR-10 and 75.64% top-1 accuracy on CIFAR-100. Spiking RetinaNet is proposed using SG ResNet as the backbone and ASD module for information decoding as the first direct-training hybrid SNN-ANN detector for RGB images. Spiking RetinaNet with a SG ResNet34 backbone achieves an mAP of 0.296 on the object detection dataset MSCOCO.
From 21st century, it is hard for traditional storage and algorithm to provide service with high quality because of big data of communication which grows rapidly. Thus, cloud computing technology with relatively low cost of hardware facilities is created. However, to guarantee the quality of service in the situation of the rapid growth of data volume, the energy consumption cost of cloud computing begins to exceed the hardware cost. In order to solve the problems mentioned above, this study briefly introduced the virtual machine and its energy consumption model in the mobile cloud environment, introduced the basic principle of the virtual machine migration strategy based on the artificial bee colony algorithm and then simulated the performance of processing strategy to big data of communication based on artificial bee colony algorithm in mobile cloud computing environment by CloudSim3.0 software, which was compared with the performance of two algorithms, resource management (RM) and genetic algorithm (GA). The results showed that the power consumption of the migration strategy based on the artificial bee colony algorithm was lower than the other two strategies, and there were fewer failed virtual machines under the same number of requests, which meant that the service quality was higher.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.