TBA
IISA2017 | MLSA: Machine Learning for Sensor Applications
8341
singular,single,single-post,postid-8341,single-format-standard,ajax_fade,page_not_loaded,,qode-child-theme-ver-1.0.0,qode-theme-ver-3.1,wpb-js-composer js-comp-ver-4.11.1,vc_responsive
 

Blog

MLSA: Machine Learning for Sensor Applications

  |   Tutorials   |   No comment
sensors

Andreas Spanias, ASU SenSIP

Uday Shankar Shanthamallu, ASU SenSIP

Michael Stanley, NXP

This tutorial provides an introduction to the principles and applications of machine learning algorithms with the emphasis on sensor related applications. The tutorial begins with an introduction to the basics of pattern matching, feature extraction, and supervised and unsupervised learning. The instructors then cover basic methods such as the kmeans, support vector machines, neural nets and deep learning. The coverage of topics is at a high level and features qualitative descriptions and software examples. The session connects algorithms with sensor applications including health monitoring, IoT, and security applications.

The tutorial is designed for students, faculty, engineers and managers who need to understand the basics of machine learning and their utility in various sensor applications

andreas

Andreas Spanias, SenSIP Director

Andreas Spanias is Professor in the School of ECEE and the director of the SenSIP center and industry consortium.

His research interests are in the areas of adaptive signal processing, speech processing, and sensor systems. He is author of two text books. He served as Associate Editor in IEEE Signal
Processing and as General Co-chair of IEEE ICASSP-99. He also served as the
IEEE Signal Processing Vice-President for Conferences. Andreas Spanias is corecipient
of the 2002 IEEE Donald G.

Fink paper prize award and was elected Fellow of the IEEE in 2003. He served as Distinguished lecturer for the IEEE Signal processing society in 2004. He received the Meritorious service award from the IEEE Signal Processing society in 2005.

uday

Uday Shankar, SenSIP Researcher

Uday Shankar Shanthamallu joined the Sensor, Signal & Information Processing
Center (SenSIP) at ASU in January 2016. His research interests lie at the
overlap of Sensors and Machine learning. In 2016, he worked as a research associate and intern at NXP on sensor data analytics and more specifically on integrating machine learning algorithms on an embedded sensor board for Internet of Things (IoT) applications. Before joining Arizona State University, he worked as a Systems engineer for 4 years at the Hewlett Packard Research and Development laboratory in Bangalore, India. He received the IEEE Phoenix Section scholarship in 2016. He collaborates with scientists in Lawrence Livermore Labs on deep learning.

mike

Mike Stanley, NXP

Mike Stanley designed MCU & sensor devices and served as speaker in
national conferences. His recent focus is on machine learning algorithms for use in automotive and IoT applications. He authored the detailed functional specifications for the MMA9550L and provided technical leadership for all
56800/E Digital Signal Controller devices. He developed the Freescale Sensor
Fusion Toolbox for Kinetis MCUs where multiple sensors such as accelerometer,
magnetometer, and gyroscope can be integrated to perform tasks that a single
sensor could not handle. He contributed a chapter in the “Measurement,
Instrumentation & Sensors Handbook” He also contributed to the “IEEE
Standard for Sensor Performance Parameter Definitions.” He received the
2017 IEEE Phoenix Section Corporate Award.

Description

This tutorial provides an introduction to the principles and applications of machine learning algorithms with the emphasis on sensor related applications. The tutorial begins with an introduction to the basics of pattern matching, feature extraction, and supervised and unsupervised learning. The instructors then cover basic methods such as the kmeans, support vector machines, neural nets and deep learning. The coverage of topics is at a high level and features qualitative descriptions and software examples. The session connects algorithms with sensor applications including health monitoring, IoT, and security applications.

The tutorial is designed for students, faculty, engineers and managers who need to understand the basics of machine learning and their utility in various sensor applications

Topics of Interests
  • Qualitative Overview,
  • what is machine learning?,
  • Use in Sensors and Big Data,
  • Algorithms and Software,
  • Beginings from Vector Quantization and Cell Phones,
  • Feature Extraction,
  • Kmeans,
  • Adaptive Neural Nets,
  • Support Vector Machines,
  • Bayesian Methods,
  • Deep Learning,
  • Embedding machine learning on sensor boards,
  • Applications;
  • IoT,
  • health monitoring,
  • security;
  • smart campus,
  • smart cities;
  • social implications
Call for Papers
Important Dates
Chairs
Program Committee
Instructions for Authors