Vijay K. Gurbani
Research Associate Professor of Computer Science
Illinois Institute of Technology, USA
Email: vgurbani@iit.edu
Mailing address:
Department of Computer Science
Stuart Building
10 West 31st Street, Room 235
Chicago, IL 60616, USA
Phone: +1-312-567-5067
I am a Research Associate Professor of Computer Science at
Illinos Tech, and the co-director of the Real-Time
Communications Laboratory. I teach CS 422 (Introduction to Data
Mining and Machine Learning), CS 597 (Reading and Special Problems), and CS 497 (Special Projects). In the past have
taught CS 401 (Introduction to Advanced Studies I), which is a
required data structures and algorithms course designed to prepare students for graduate study in CS.
In addition to the appointment at Illinois Tech, I am also the Chief Data Scientist at Vail Systems, Inc., where I established and now lead a research group on machine learning, data science and AI activities across the company, from idea inception to conceptual proof to prototype, and finally, a product that gets deployed. My work at Vail Systems includes models that involve affective computing, anomaly detection in large datasets, and AI/ML models in the realm of software engineering and log analysis, among other responsibilities. I also hold an appointment as a Research Fellow at the University of Luxembourg in the SEDAN (Services and Data Management) research group headed by Prof. Radu State. As part of my fellowship appointment, I work with Ph.D. students on selected projects and have appeared on the Ph.D. committee of a number of students.
My primary research interests are multimedia signaling protocols, multimedia networks, applied machine learning in the multimedia communication space, and security in multimedia communications networks. During my tenure at Bell Laboratories, my collaboration with Prof. James Herbsleb at Carnegie Mellon University's Institute for Software Research produced a series of papers on how corporations can develop code using open source development techniques, a phenomenon we coined as "corporate open source" at the time. This work has subsequently proved foundational to the academic research conducted on Inner Source, which examines the adoption and tailoring of open source development practices within commercial organizations. Our early work in this area informed the taxonomy in Inner Source, and helped define roles and responsibilities of specific actors in Inner Source.
I have authored or co-authored over 60 papers in peer reviewed journals, conferences and workshops, five books, 19 Internet Engineering Task Force (IETF) RFCs, and been granted 8 patents by the US Patent Office, many of which are also international patents.
Prior to Vail Systems, Inc., I spent 21 years at Bell Laboratories (owned first by Lucent Technologies, Inc., and then Alcatel-Lucent, and now owned by Nokia). Since 2010 at Bell Labs, I have been involved in the increasing use of machine learning algorithms and techniques to make sense of the data generated by 4G and later, 5G, networks. In a sense, the domain I apply machine learning techniques to is the networking, protocol and security domain. Broadly, at Bell Labs my work explored multimedia signaling protocols, especially Session Initiation Protocol (SIP) and the security and privacy aspects of multimedia protocols. My earlier work proposed the use of SIP as a canonical protocol for executing services both in the Public Switched Telephone Network (PSTN) and the Internet. The results of these efforts was siptrans, a general-purpose SIP transaction layer library used to create SIP user agents, proxies, and registrars. The siptrans library was subsequently used as the basis for the Lucent Common SIP Stack (CSS), which is currently used in service provider networks of national and international companies and powers their VoLTE solutions. A serendipitous side affect of my work on SIP was how I managed the internal development of the project using open source development techniques, the learnings of which provided to be foundational for Inner Source as I discuss above.
Prior to Bell Laboratories, I worked at the Fermi National Accelerator Laboratory. At Fermilab, I was working on the Sloan Digital Sky Survey, providing computing support to astrophysicists as they mapped out a quarter of the universe in five colors. Fascinating project! Contact me for more details or browse the SDSS website for impressive results. Prior to Fermilab, I worked at a Chicago startup, among other appointments.
I received my BSc. and MSc. in Computer Science at Bradley University and a Ph.D. in Computer Science from Illinois Institute of Technology under the guidance of Prof. Xian-He Sun. My masters thesis simulated the OSI Session and Presentation layers in the Internet Protocol protocol stack, while my doctoral dissertation examined information loss when we merge rich protocols with many states (traditional telephony protocols) with the simpler protocols having less number of states (Internet Telephony protocols). It further proposed the creation of joint smart spaces where services could be initiated in one of the networks --- traditional telephone network or the Internet telephony network --- and can readily crossover into the other network while minimizing information loss and maximizing communication utility in novel ways not possible in the absence of such a smart space.
I have an Erdos number of 4 and a Dijkstra number of 4.
In addition to the appointment at Illinois Tech, I am also the Chief Data Scientist at Vail Systems, Inc., where I established and now lead a research group on machine learning, data science and AI activities across the company, from idea inception to conceptual proof to prototype, and finally, a product that gets deployed. My work at Vail Systems includes models that involve affective computing, anomaly detection in large datasets, and AI/ML models in the realm of software engineering and log analysis, among other responsibilities. I also hold an appointment as a Research Fellow at the University of Luxembourg in the SEDAN (Services and Data Management) research group headed by Prof. Radu State. As part of my fellowship appointment, I work with Ph.D. students on selected projects and have appeared on the Ph.D. committee of a number of students.
My primary research interests are multimedia signaling protocols, multimedia networks, applied machine learning in the multimedia communication space, and security in multimedia communications networks. During my tenure at Bell Laboratories, my collaboration with Prof. James Herbsleb at Carnegie Mellon University's Institute for Software Research produced a series of papers on how corporations can develop code using open source development techniques, a phenomenon we coined as "corporate open source" at the time. This work has subsequently proved foundational to the academic research conducted on Inner Source, which examines the adoption and tailoring of open source development practices within commercial organizations. Our early work in this area informed the taxonomy in Inner Source, and helped define roles and responsibilities of specific actors in Inner Source.
I have authored or co-authored over 60 papers in peer reviewed journals, conferences and workshops, five books, 19 Internet Engineering Task Force (IETF) RFCs, and been granted 8 patents by the US Patent Office, many of which are also international patents.
Prior to Vail Systems, Inc., I spent 21 years at Bell Laboratories (owned first by Lucent Technologies, Inc., and then Alcatel-Lucent, and now owned by Nokia). Since 2010 at Bell Labs, I have been involved in the increasing use of machine learning algorithms and techniques to make sense of the data generated by 4G and later, 5G, networks. In a sense, the domain I apply machine learning techniques to is the networking, protocol and security domain. Broadly, at Bell Labs my work explored multimedia signaling protocols, especially Session Initiation Protocol (SIP) and the security and privacy aspects of multimedia protocols. My earlier work proposed the use of SIP as a canonical protocol for executing services both in the Public Switched Telephone Network (PSTN) and the Internet. The results of these efforts was siptrans, a general-purpose SIP transaction layer library used to create SIP user agents, proxies, and registrars. The siptrans library was subsequently used as the basis for the Lucent Common SIP Stack (CSS), which is currently used in service provider networks of national and international companies and powers their VoLTE solutions. A serendipitous side affect of my work on SIP was how I managed the internal development of the project using open source development techniques, the learnings of which provided to be foundational for Inner Source as I discuss above.
Prior to Bell Laboratories, I worked at the Fermi National Accelerator Laboratory. At Fermilab, I was working on the Sloan Digital Sky Survey, providing computing support to astrophysicists as they mapped out a quarter of the universe in five colors. Fascinating project! Contact me for more details or browse the SDSS website for impressive results. Prior to Fermilab, I worked at a Chicago startup, among other appointments.
I received my BSc. and MSc. in Computer Science at Bradley University and a Ph.D. in Computer Science from Illinois Institute of Technology under the guidance of Prof. Xian-He Sun. My masters thesis simulated the OSI Session and Presentation layers in the Internet Protocol protocol stack, while my doctoral dissertation examined information loss when we merge rich protocols with many states (traditional telephony protocols) with the simpler protocols having less number of states (Internet Telephony protocols). It further proposed the creation of joint smart spaces where services could be initiated in one of the networks --- traditional telephone network or the Internet telephony network --- and can readily crossover into the other network while minimizing information loss and maximizing communication utility in novel ways not possible in the absence of such a smart space.
I have an Erdos number of 4 and a Dijkstra number of 4.