tinyML Talks: ML using micro-electromechanical system (MEMS)

This talk covers a new technology that enables a sensor such as a wearable accelerometer to provide high-level processed information such as step counts or type of activity rather than the simple raw acceleration measurement. This new technology is based on a micro-electromechanical system (MEMS) where a network of them is designed to locally perform advanced algorithms. The algorithms will be coded in the mechanical responses of the sensing elements of these multiple-coupled MEMS devices that simultaneously capture the measurement of interest such as acceleration. As a result, the MEMS network will perform computing at the sensing physical layer and will require very little power, eliminating the need for a microprocessor and eliminating the need for the energy-hungry circuitry for conditioning and reading the output of the traditional sensor. The new sensing/computing technology has been demonstrated in multiple applications such as human activity recognition, simple signal classification, and mobile robot.


May 31, 2022



Contact us



Timezone: PDT

ML using micro-electromechanical system (MEMS)

Fadi ALSALEEM, Assistant Professor

University of Nebraska - Lincoln

Fadi ALSALEEM, Assistant Professor

University of Nebraska - Lincoln

Dr. Alsaleem joined the college of engineering at the University of Nebraska at Lincoln (UNL) in August 2016. Before this assignment, he worked for multiple years in the industry including four years as a Senior Lead Algorithm Engineer at Emerson Electric Inc to develop novel (cloud-based) sensor monitoring and learning algorithms used for fault diagnostics for mechanical systems. His current and future potential research goals are to vertically advance the fields of intelligent wearable sensing technologies and artificial intelligence algorithms and their use in many health and medical applications. In this research area, he has more than 10 awarded patents, more than 100 publications, presentations, and invited talks, and over 6 million total (near 1.5 million to his research team) of active funding to support his research work.

Schedule subject to change without notice.