并行物联网传感器分布式推理的分裂卷积神经网络

Jiale Chen, D. V. Le, R. Tan, Daren Ho
{"title":"并行物联网传感器分布式推理的分裂卷积神经网络","authors":"Jiale Chen, D. V. Le, R. Tan, Daren Ho","doi":"10.1109/ICPADS53394.2021.00014","DOIUrl":null,"url":null,"abstract":"Convolutional neural networks (CNNs) are increasingly adopted on resource-constrained sensors for in-situ data analytics in Internet of Things (IoT) applications. This paper presents a model split framework, namely, splitCNN, in order to run a large CNN on a collection of concurrent IoT sensors. Specifically, we adopt CNN filter pruning techniques to split the large CNN into multiple small-size models, each of which is only sensitive to a certain number of data classes. These class-specific models are deployed onto the resource-constrained concurrent sensors which collaboratively perform distributed CNN inference on their same/similar sensing data. The outputs of multiple models are then fused to yield the global inference result. We apply splitCNN to three case studies with different sensing modalities, which include the human voice, industrial vibration signal, and visual sensing data. Extensive evaluation shows the effectiveness of the proposed splitCNN. In particular, the splitCNN achieves significant reduction in the model size and inference time while maintaining similar accuracy, compared with the original CNN model for all three case studies.","PeriodicalId":309508,"journal":{"name":"2021 IEEE 27th International Conference on Parallel and Distributed Systems (ICPADS)","volume":"247 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Split Convolutional Neural Networks for Distributed Inference on Concurrent IoT Sensors\",\"authors\":\"Jiale Chen, D. V. Le, R. Tan, Daren Ho\",\"doi\":\"10.1109/ICPADS53394.2021.00014\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Convolutional neural networks (CNNs) are increasingly adopted on resource-constrained sensors for in-situ data analytics in Internet of Things (IoT) applications. This paper presents a model split framework, namely, splitCNN, in order to run a large CNN on a collection of concurrent IoT sensors. Specifically, we adopt CNN filter pruning techniques to split the large CNN into multiple small-size models, each of which is only sensitive to a certain number of data classes. These class-specific models are deployed onto the resource-constrained concurrent sensors which collaboratively perform distributed CNN inference on their same/similar sensing data. The outputs of multiple models are then fused to yield the global inference result. We apply splitCNN to three case studies with different sensing modalities, which include the human voice, industrial vibration signal, and visual sensing data. Extensive evaluation shows the effectiveness of the proposed splitCNN. In particular, the splitCNN achieves significant reduction in the model size and inference time while maintaining similar accuracy, compared with the original CNN model for all three case studies.\",\"PeriodicalId\":309508,\"journal\":{\"name\":\"2021 IEEE 27th International Conference on Parallel and Distributed Systems (ICPADS)\",\"volume\":\"247 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 IEEE 27th International Conference on Parallel and Distributed Systems (ICPADS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICPADS53394.2021.00014\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE 27th International Conference on Parallel and Distributed Systems (ICPADS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICPADS53394.2021.00014","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

卷积神经网络(cnn)越来越多地应用于资源受限的传感器,用于物联网(IoT)应用中的原位数据分析。为了在一组并发物联网传感器上运行大型CNN,本文提出了一个模型拆分框架,即splitCNN。具体来说,我们采用CNN滤波剪枝技术,将大的CNN拆分成多个小的模型,每个小的模型只对一定数量的数据类敏感。这些类特定的模型被部署到资源受限的并发传感器上,这些传感器协同对它们相同/相似的传感数据执行分布式CNN推理。然后将多个模型的输出融合以产生全局推理结果。我们将splitCNN应用于三个具有不同传感模式的案例研究,包括人声、工业振动信号和视觉传感数据。广泛的评估表明了所提出的splitCNN的有效性。特别是,splitCNN在所有三个案例研究中,与原始CNN模型相比,在保持相似精度的同时,显著减少了模型大小和推理时间。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Split Convolutional Neural Networks for Distributed Inference on Concurrent IoT Sensors
Convolutional neural networks (CNNs) are increasingly adopted on resource-constrained sensors for in-situ data analytics in Internet of Things (IoT) applications. This paper presents a model split framework, namely, splitCNN, in order to run a large CNN on a collection of concurrent IoT sensors. Specifically, we adopt CNN filter pruning techniques to split the large CNN into multiple small-size models, each of which is only sensitive to a certain number of data classes. These class-specific models are deployed onto the resource-constrained concurrent sensors which collaboratively perform distributed CNN inference on their same/similar sensing data. The outputs of multiple models are then fused to yield the global inference result. We apply splitCNN to three case studies with different sensing modalities, which include the human voice, industrial vibration signal, and visual sensing data. Extensive evaluation shows the effectiveness of the proposed splitCNN. In particular, the splitCNN achieves significant reduction in the model size and inference time while maintaining similar accuracy, compared with the original CNN model for all three case studies.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信