research-article

One Size Does Not Fit All: Multi-Scale, Cascaded RNNs for Radar Classification

Authors:

Dhrubojyoti Roy,

Sangeeta Srivastava,

Aditya Kusupati,

Anish AroraAuthors Info & Claims

BuildSys '19: Proceedings of the 6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation

Pages 1 - 10

https://doi.org/10.1145/3360322.3360860

Published: 13 November 2019 Publication History

Abstract

Edge sensing with micro-power pulse-Doppler radars is an emergent domain in monitoring and surveillance with several smart city applications. Existing solutions for the clutter versus multi-source radar classification task are limited in terms of either accuracy or efficiency, and in some cases, struggle with a trade-off between false alarms and recall of sources. We find that this problem can be resolved by learning the classifier across multiple time-scales. We propose a multi-scale, cascaded recurrent neural network architecture, MSC-RNN, comprised of an efficient multi-instance learning (MIL) Recurrent Neural Network (RNN) for clutter discrimination at a lower tier, and a more complex RNN classifier for source classification at the upper tier. By controlling the invocation of the upper RNN with the help of the lower tier conditionally, MSC-RNN achieves an overall accuracy of 0.972. Our approach holistically improves the accuracy and per-class recalls over machine learning models suitable for radar inferencing. Notably, we outperform cross-domain handcrafted feature engineering with purely time-domain deep feature learning, while also being up to ~3X more efficient than a competitive solution.

References

[1]

[n. d.]. CMSIS-DSP Software Library. http://www.keil.com/pack/doc/CMSIS/DSP/html/index.html.

[2]

[n. d.]. Olentangy Trail usage, Columbus, OH. https://www.columbus.gov/recreationandparks/trails/Future-Trails-(Updated)/.

[3]

Joshua Adkins, Branden Ghena, et al. 2018. The signpost platform for city-scale sensing. In IPSN. IEEE, 188--199.

[4]

Shaojie Bai, J Zico Kolter, et al. 2018. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271 (2018).

[5]

Juan P. Bello, Claudio Silva, et al. 2019. SONYC: A system for monitoring, analyzing, and mitigating urban noise pollution. CACM 62, 2 (Jan. 2019), 68--77.

Digital Library

[6]

Charles E Catlett, Peter H Beckman, et al. 2017. Array of things: A scientific research instrument in the public way: platform design and early lessons learned. In SCOPE. ACM, 26--33.

[7]

Ohio Supercomputer Center. 1987. Ohio Supercomputer Center. http://osc.edu/ark:/19495/f5s1ph73

[8]

Kyunghyun Cho, Bart Van Merriënboer, et al. 2014. On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259 (2014).

[9]

Junyoung Chung, Sungjin Ahn, et al. 2016. Hierarchical multiscale recurrent neural networks. arXiv preprint arXiv:1609.01704 (2016).

[10]

Don Dennis, Chirag Pabbaraju, et al. 2018. Multiple instance learning for efficient sequential data classification on resource-constrained devices. In NIPS. Curran Associates, Inc, 10975--10986.

[11]

Don Kurian Dennis, Sridhar Gopinath, et al. [n. d.]. EdgeML: Machine learning for resource-constrained edge devices. https://github.com/Microsoft/EdgeML

[12]

Richard M Goldstein, Howard A Zebker, et al. 1988. Satellite radar interferometry: Two-dimensional phase unwrapping. Radio science 23, 4 (1988), 713--720.

[13]

Song Han, Huizi Mao, et al. 2016. Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding. ICLR (2016).

[14]

Jin He and Anish Arora. 2014. A regression-based radar-mote system for people counting. In PerCom. IEEE, 95--102.

[15]

Jin He, Dhrubojyoti Roy, et al. 2014. Mote-scale human-animal classification via micropower radar. In SenSys. ACM, 328--329.

[16]

Geoffrey E Hinton. 1990. Mapping part-whole hierarchies into connectionist networks. Artificial Intelligence 46, 1-2 (1990), 47--75.

[17]

Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735--1780.

Digital Library

[18]

Rios Jesus Javier and Youngwook Kim. 2014. Application of linear predictive coding for human activity classification based on micro-Doppler signatures. GRSL, IEEE 11 (10 2014), 1831--1834.

[19]

Branka Jokanovic, Moeness Amin, et al. 2016. Radar fall motion detection using deep learning. In RADAR. IEEE, 1--6.

[20]

Youngwook Kim and Hao Ling. 2008. Human activity classification based on micro-Doppler signatures using an artificial neural network. In AP-S. IEEE, 1--4.

[21]

Youngwook Kim and Brian Toomajian. 2016. Hand gesture recognition using micro-Doppler signatures with convolutional neural network. IEEE Access 4 (01 2016), 1--1.

[22]

Dimitrios Kotzias, Misha Denil, et al. 2014. Deep multi-instance transfer learning. arXiv preprint arXiv:1411.3128 (2014).

[23]

Alex Krizhevsky, Ilya Sutskever, et al. 2012. Imagenet classification with deep convolutional neural networks. In NIPS. 1097--1105.

[24]

Ashish Kumar, Saurabh Goyal, et al. 2017. Resource-efficient machine learning in 2 KB RAM for the Internet of Things. In ICML. ACM, 1935--1944.

[25]

Sangeeta Kumari, Dhrubojyoti Roy, et al. 2019. EdgeL3: Compressing L3-Net for mote scale urban noise monitoring. In IPDPSW. IEEE, 877--884.

[26]

Aditya Kusupati, Manish Singh, et al. 2018. FastGRNN: A fast, accurate, stable and tiny kilobyte sized gated recurrent neural network. In NIPS. Curran Associates, Inc., 9030--9041.

[27]

Liang Liu, Mihail Popescu, et al. 2011. Automatic fall detection based on Doppler radar motion signature. In PervasiveHealth, Vol. 222. 222--225.

[28]

Gihan Mendis, Tharindu Randeny, et al. 2016. Deep learning based Doppler radar for micro UAS detection and classification. In MILCOM. IEEE, 924--929.

[29]

Michael C Mozer. 1992. Induction of multiscale temporal structure. In NIPS. Morgan-Kaufmann, 275--282.

[30]

Dustin P. Fairchild and Ram Narayanan. 2014. Classification of human motions using empirical mode decomposition of human micro-Doppler signatures. Radar, Sonar & Navigation, IET 8 (06 2014), 425--434.

[31]

Razvan Pascanu, Tomas Mikolov, et al. 2013. On the difficulty of training recurrent neural networks. In ICML. ACM, 1310--1318.

[32]

Hanchuan Peng, Fuhui Long, et al. 2005. Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. IEEE Transactions on pattern analysis and machine intelligence 27, 8 (2005), 1226--1238.

Digital Library

[33]

Dhrubojyoti Roy, Sangeeta Kumari, et al. [n. d.]. MSC-RNN: Multi-Scale, Cascaded RNNs for Radar Classification. https://github.com/dhruboroy29/MSCRNN

[34]

Dhrubojyoti Roy, Christopher Morse, et al. 2017. Cross-environmentally robust intruder discrimination in radar motes. In MASS. IEEE, 426--434.

[35]

Dhrubojyoti Roy, Sangeeta Srivastava, et al. [n. d.]. Micro-power pulse-Doppler radar clutter and displacement source classification dataset. https://doi.org/10.5281/zenodo.3451407

[36]

Jürgen Schmidhuber. 1992. Learning complex, extended sequences using the principle of history compression. Neural Computation 4, 2 (1992), 234--242.

Digital Library

[37]

The Samraksh Company. [n. d.]. NOW with eMote. https://goo.gl/C4CCv4.

[38]

UrbanCCD. [n. d.]. Array of Things. https://medium.com/array-of-things/five-years-100-nodes-and-more-to-come-d3802653db9f.

[39]

Zhisheng Wang, Jun Lin, et al. 2017. Accelerating recurrent neural networks: A memory-efficient approach. IEEE Transactions on VLSI Systems 25, 10 (2017), 2763--2775.

[40]

Jiajun Wu, Yinan Yu, et al. 2015. Deep multiple instance learning for image classification and auto-annotation. In CVPR. 3460--3469.

[41]

Jinmian Ye, Linnan Wang, et al. 2018. Learning compact recurrent neural networks with block-term tensor decomposition. In CVPR. IEEE, 9378--9387.

Cited By

Chen DChen LZhang YWen BYang C(2022)A Multiscale Interactive Recurrent Network for Time-Series ForecastingIEEE Transactions on Cybernetics10.1109/TCYB.2021.305595152:9(8793-8803)Online publication date: Sep-2022
https://doi.org/10.1109/TCYB.2021.3055951
Roy DSrivastava SKusupati AJain PVarma MArora A(2021)One Size Does Not Fit AllACM Transactions on Sensor Networks10.1145/343995717:2(1-27)Online publication date: 23-Jan-2021
https://dl.acm.org/doi/10.1145/3439957
Kusupati ARamanujan VSomani RWortsman MJain PKakade SFarhadi ADaumé HSingh A(2020)Soft threshold weight reparameterization for learnable sparsityProceedings of the 37th International Conference on Machine Learning10.5555/3524938.3525452(5544-5555)Online publication date: 13-Jul-2020
https://dl.acm.org/doi/10.5555/3524938.3525452
Show More Cited By

Index Terms

One Size Does Not Fit All: Multi-Scale, Cascaded RNNs for Radar Classification
1. Computer systems organization
  1. Embedded and cyber-physical systems
    1. Sensor networks
    2. System on a chip
  2. Real-time systems
    1. Real-time system architecture
2. Computing methodologies
  1. Machine learning
    1. Learning paradigms
      1. Supervised learning
        Supervised learning by classification
    2. Machine learning approaches
      1. Neural networks

Recommendations

One Size Does Not Fit All: Multi-scale, Cascaded RNNs for Radar Classification

Edge sensing with micro-power pulse-Doppler radars is an emergent domain in monitoring and surveillance with several smart city applications. Existing solutions for the clutter versus multi-source radar classification task are limited in terms of either ...
A novel recurrent neural network with one neuron and finite-time convergence for k-winners-take-all operation

In this paper, based on a one-neuron recurrent neural network, a novel k-winners-take-all (k-WTA) network is proposed. Finite time convergence of the proposed neural network is proved using the Lyapunov method. The k-WTA operation is first converted ...
A One-Layer Recurrent Neural Network With a Discontinuous Hard-Limiting Activation Function for Quadratic Programming

In this paper, a one-layer recurrent neural network with a discontinuous hard-limiting activation function is proposed for quadratic programming. This neural network is capable of solving a large class of quadratic programming problems. The state ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

BuildSys '19: Proceedings of the 6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation

November 2019

413 pages

ISBN:9781450370059

DOI:10.1145/3360322

Copyright © 2019 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGEnergy: ACM Special Interest Group on Energy Systems and Informatics

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 13 November 2019

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

BuildSys '19

Sponsor:

SIGEnergy

BuildSys '19: The 6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation

November 13 - 14, 2019

NY, New York, USA

Acceptance Rates

BuildSys '19 Paper Acceptance Rate 40 of 131 submissions, 31%;

Overall Acceptance Rate 148 of 500 submissions, 30%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

4
Total Citations
View Citations
304
Total Downloads

Downloads (Last 12 months)10
Downloads (Last 6 weeks)1

Reflects downloads up to 09 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Chen DChen LZhang YWen BYang C(2022)A Multiscale Interactive Recurrent Network for Time-Series ForecastingIEEE Transactions on Cybernetics10.1109/TCYB.2021.305595152:9(8793-8803)Online publication date: Sep-2022
https://doi.org/10.1109/TCYB.2021.3055951
Roy DSrivastava SKusupati AJain PVarma MArora A(2021)One Size Does Not Fit AllACM Transactions on Sensor Networks10.1145/343995717:2(1-27)Online publication date: 23-Jan-2021
https://dl.acm.org/doi/10.1145/3439957
Kusupati ARamanujan VSomani RWortsman MJain PKakade SFarhadi ADaumé HSingh A(2020)Soft threshold weight reparameterization for learnable sparsityProceedings of the 37th International Conference on Machine Learning10.5555/3524938.3525452(5544-5555)Online publication date: 13-Jul-2020
https://dl.acm.org/doi/10.5555/3524938.3525452
Jain DNgo HPatel PGoodman SFindlater LFroehlich J(2020)SoundWatch: Exploring Smartwatch-based Deep Learning Approaches to Support Sound Awareness for Deaf and Hard of Hearing UsersProceedings of the 22nd International ACM SIGACCESS Conference on Computers and Accessibility10.1145/3373625.3416991(1-13)Online publication date: 26-Oct-2020
https://dl.acm.org/doi/10.1145/3373625.3416991

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents