Integrating machine learning in embedded sensor systems for Internet-of-Things applications

Jongmin Lee; Michael Stanley; Andreas Spanias; Cihan Tepedelenlioglu

doi:10.1109/ISSPIT.2016.7886051

Integrating machine learning in embedded sensor systems for Internet-of-Things applications

Jongmin Lee, Michael Stanley, Andreas Spanias, Cihan Tepedelenlioglu

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

20 Scopus citations

Abstract

Interpreting sensor data in Internet-of-Things applications is a challenging problem particularly in embedded systems. We consider sensor data analytics where machine learning algorithms can be fully implemented on an embedded processor/sensor board. We develop an efficient real-time realization of a Gaussian mixture model (GMM) for execution on the NXP FRDM-K64F embedded sensor board. We demonstrate the design of a customized program and data structure that generates real-time sensor features, and we show details and training/classification results for select IoT applications. The integrated hardware/software system enables real-time data analytics and continuous training and re-training of the machine learning (ML) algorithm. The real-time ML platform can accommodate several applications with lower sensor data traffic.

Original language	English (US)
Title of host publication	2016 IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	290-294
Number of pages	5
ISBN (Electronic)	9781509058440
DOIs	https://doi.org/10.1109/ISSPIT.2016.7886051
State	Published - Mar 23 2017
Event	2016 IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2016 - Limassol, Cyprus Duration: Dec 12 2016 → Dec 14 2016

Other

Other	2016 IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2016
Country	Cyprus
City	Limassol
Period	12/12/16 → 12/14/16

Keywords

condition monitoring
embedded machine learning
Internet-of-Things
sensor data analytics

ASJC Scopus subject areas

Computer Networks and Communications
Computer Science Applications
Signal Processing

Access to Document

10.1109/ISSPIT.2016.7886051

Fingerprint Dive into the research topics of 'Integrating machine learning in embedded sensor systems for Internet-of-Things applications'. Together they form a unique fingerprint.

Cite this

Lee, J., Stanley, M., Spanias, A., & Tepedelenlioglu, C. (2017). Integrating machine learning in embedded sensor systems for Internet-of-Things applications. In 2016 IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2016 (pp. 290-294). [7886051] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISSPIT.2016.7886051

Integrating machine learning in embedded sensor systems for Internet-of-Things applications. / Lee, Jongmin; Stanley, Michael; Spanias, Andreas ; Tepedelenlioglu, Cihan.

2016 IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2016. Institute of Electrical and Electronics Engineers Inc., 2017. p. 290-294 7886051.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Lee, J, Stanley, M, Spanias, A & Tepedelenlioglu, C 2017, Integrating machine learning in embedded sensor systems for Internet-of-Things applications. in 2016 IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2016., 7886051, Institute of Electrical and Electronics Engineers Inc., pp. 290-294, 2016 IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2016, Limassol, Cyprus, 12/12/16. https://doi.org/10.1109/ISSPIT.2016.7886051

@inproceedings{428ca23284394a6bb2dd16dbccf50e2a,

title = "Integrating machine learning in embedded sensor systems for Internet-of-Things applications",

abstract = "Interpreting sensor data in Internet-of-Things applications is a challenging problem particularly in embedded systems. We consider sensor data analytics where machine learning algorithms can be fully implemented on an embedded processor/sensor board. We develop an efficient real-time realization of a Gaussian mixture model (GMM) for execution on the NXP FRDM-K64F embedded sensor board. We demonstrate the design of a customized program and data structure that generates real-time sensor features, and we show details and training/classification results for select IoT applications. The integrated hardware/software system enables real-time data analytics and continuous training and re-training of the machine learning (ML) algorithm. The real-time ML platform can accommodate several applications with lower sensor data traffic.",

keywords = "condition monitoring, embedded machine learning, Internet-of-Things, sensor data analytics",

author = "Jongmin Lee and Michael Stanley and Andreas Spanias and Cihan Tepedelenlioglu",

year = "2017",

month = mar,

day = "23",

doi = "10.1109/ISSPIT.2016.7886051",

language = "English (US)",

pages = "290--294",

booktitle = "2016 IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2016",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "2016 IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2016 ; Conference date: 12-12-2016 Through 14-12-2016",

}

TY - GEN

T1 - Integrating machine learning in embedded sensor systems for Internet-of-Things applications

AU - Lee, Jongmin

AU - Stanley, Michael

AU - Spanias, Andreas

AU - Tepedelenlioglu, Cihan

PY - 2017/3/23

Y1 - 2017/3/23

N2 - Interpreting sensor data in Internet-of-Things applications is a challenging problem particularly in embedded systems. We consider sensor data analytics where machine learning algorithms can be fully implemented on an embedded processor/sensor board. We develop an efficient real-time realization of a Gaussian mixture model (GMM) for execution on the NXP FRDM-K64F embedded sensor board. We demonstrate the design of a customized program and data structure that generates real-time sensor features, and we show details and training/classification results for select IoT applications. The integrated hardware/software system enables real-time data analytics and continuous training and re-training of the machine learning (ML) algorithm. The real-time ML platform can accommodate several applications with lower sensor data traffic.

AB - Interpreting sensor data in Internet-of-Things applications is a challenging problem particularly in embedded systems. We consider sensor data analytics where machine learning algorithms can be fully implemented on an embedded processor/sensor board. We develop an efficient real-time realization of a Gaussian mixture model (GMM) for execution on the NXP FRDM-K64F embedded sensor board. We demonstrate the design of a customized program and data structure that generates real-time sensor features, and we show details and training/classification results for select IoT applications. The integrated hardware/software system enables real-time data analytics and continuous training and re-training of the machine learning (ML) algorithm. The real-time ML platform can accommodate several applications with lower sensor data traffic.

KW - condition monitoring

KW - embedded machine learning

KW - Internet-of-Things

KW - sensor data analytics

UR - http://www.scopus.com/inward/record.url?scp=85006702130&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85006702130&partnerID=8YFLogxK

U2 - 10.1109/ISSPIT.2016.7886051

DO - 10.1109/ISSPIT.2016.7886051

M3 - Conference contribution

AN - SCOPUS:85006702130

SP - 290

EP - 294

BT - 2016 IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2016 IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2016

Y2 - 12 December 2016 through 14 December 2016

ER -