[Quantum-ms] [Seminar] DSI X EE: 4/24 2:30pm, EE Conference Room

[Columbia EE Events]

*“Sense, Collect and Move Data” Data Science Institute Center *

*X*

* Electrical Engineering Department Seminar*


*Speaker:* Homayoon Beigi
*Title: *Structural and Machine Health Monitoring Derived from Speaker
Recognition Techniques

*Time: **2:30 pm, Thursday, April 24*

*Location:* EE Conference Room, Mudd 1300 (also via* zoom
<https://columbiauniversity.zoom.us/j/95258817687?pwd=lfsGRZPqAP0NQHphYbA5CmDVhg99kq.1 >*;
Passcode: 061263)

*Host*: Debasis Mitra


*Abstract:* The latest advancements in structural health monitoring of
bridges and machinery have a lot of in common with speaker recognition
techniques.  Starting out as a mechanical engineer and having done
considerable amount of machine health monitoring and prognosis in the
mid-1980s, as well as neural network learning, control and signal
processing, the speaker moved on to work in the handwriting, speaker,
speech recognition fields, making a connection among these fields and
health monitoring.  The similarities of these fields are explored and a
summary of the research of the last decade in conjunction with the civil
engineering department of Columbia University are discussed.  Cepstral
analysis and deep neural networks originally designed for speaker and
speech recognition are at the heart of the techniques that are in this
research effort that began over a decade ago.  Realizing the similarities
in the vibration of structures, such as bridges and buildings, machinery,
such as gear-meshes and bearings, and the human vocal tract kicked off this
multi-disciplinary effort. Some techniques developed in this approach are
shown together with results for health monitoring and structural damage
detection. The current affiliates in this research, Raimondo Betti (Prof.
of Civil Eng.), Azin Mehrjoo (PostDoc), and Kyle Hom (4th year Doctoral
Student) will be at the seminar and available for discussions.



*Bio:* Homayoon Beigi is a Professor of Professional Practice in the
departments of mechanical engineering and electrical engineering.  He
earned his BS, MS, and Doctorate from Columbia in 1984, 1985 and 1991
respectively.  The author of the first and only comprehensive textbook on
Speaker Recognition, for over three decades he has been involved in
research and development in learning-adaptive control, neural network
learning, biometrics, speech, speaker, face, object, emotion, and language
recognition, as well as Internet-Commerce, and more.  As the president of
Recognition Technologies, Inc. for 22 years, he developed the multiple
award-winning RecoMadeEasy®  Recognition Engine and CommerceMadeEasy®
software.  As an Adjunct Professor at Columbia for thirty years, he taught
in the ME, EE, and CS departments and advised PhD students in civil. In
2023, he was selected as one of only 11 finalists for the 5 Presidential
Awards for Outstanding Teaching.  He was a Research Staff Member at the IBM
T.J. Watson Research Center from 1991 to 2001, working on handwriting,
speaker and speech recognition. He is the recipient of three best paper
awards from IEEE and Society of Experimental Mechanics, 13 issued patents
and over 120 peer-reviewed publications.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.ee.columbia.edu/pipermail/quantum-ms/attachments/20250421/e70a7305/attachment-0001.htm>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: 4:24 seminar.pdf
Type: application/pdf
Size: 15353166 bytes
Desc: not available
URL: <http://lists.ee.columbia.edu/pipermail/quantum-ms/attachments/20250421/e70a7305/attachment-0001.pdf>