- This event has passed.
IoT-based Fire and Smoke Detection in Smart Cities using Deep Learning
September 17, 2019 @ 6:30 pm - 9:00 pm
IEEE Consumer Electronics Society Santa Clara Valley chapter brings to you exciting talks on IoT-based Fire and Smoke Detection in Smart Cities using Deep Learning
Date and Time
Tue, September 17, 2019
6:30 PM – 9:00 PM PDT
Location
Nvidia Building E
2800 Scott Boulevard
Santa Clara, CA 95050
Eventbrite link:
Agenda:
6:30 pm – 7:00 pm: Registration, Food, Networking
7:00 pm – 8:00 pm: Talk
8:00 pm – 9 pm: Q&A and Networking
Speaker: Subhankar Dhar, Dev Bhattacharya and Avid Farhoodfar
Subhankar Dhar
Bio:
Subhankar Dhar is a Professor with the School of Information Systems and Technology at San José State University. He is also an affiliate faculty member of the Center for Smart Technology, Computing, and Complex Systems (STCCS) and Silicon Valley Center for Entrepreneurship.
He advises early stage high tech startups and mentors entrepreneurs. Subhankar’s research interests are data science, big data analytics, mobile, and cloud computing as well as wireless networks. In addition, he is also interested in smart cities. He teaches a variety of courses including computer networks, distributed systems, database systems, and web-based computing. His publications have appeared in reputed international journals and gave presentations to various international conferences. He serves as a member of the editorial board of International Journal of Business Data Communications and Networking. He is a reviewer of papers for various international journals, conferences and scholarly publications. He also served as a member of the organizing committee of various international conferences including IEEE ANTS, IEEE Smart World Congress, Workshop on Large Scale Complex Network Analysis. Subhankar has several years of industrial experience in software development, consulting for high-tech industries including product planning, design, and information systems management. Subhankar has a Ph.D. in Statistics from the Univesity of South Florida and is a senior member of IEEE.
nidianDev Bhattacharya
Bio:
Dev Bhattacharya, is currently a chair of Consumer Electronics Society of IEEE section of Santa Clara Valley. He is a technical leader in various IoT systems and has over 20 years of experience in leading the system, hardware and firmware development of complex IoTs and embedded systems based on various sensors and devices.
Dev has a master’s degree of Science in computer and systems engineering from Rensselaer Polytechnic Institute and has successfully led and managed development of system architecture, system hardware, firmware of consumer grade, IoT and complex embedded system products with sensors, networking, wireless and multi-media from concept to volume production at various companies including Cisco, Intel, Logitech, Moog Crossbow and Rockwell Collins.
Avid Farhoodfar
Bio:
Avid Farhoodfar, PhD, is currently a Faculty in the Computer Science Department at Sofia University at Palo Alto, California. Formerly an Assistant chair in the Engineering Management Department, as well as Faculty in the Electrical and Computer Engineering Department at the International Technological University (ITU) in San Jose.
For her doctorate in Condensed Matter Physics and Material Sciences at Queen’s University, Dr. Farhoodfar modeled matter in quantum size, developing a modeling system using Quantum Monte Carlo approximation and Sherman Morrison optimization techniques.
Abstract: In this talk, we focus on designing an IoT-based fire and smoke detection system using edge and cloud computing infrastructure along with deep learning. First, an overview of IoT-based fire and smoke detection in smart cities will be discussed. Then a framework of an IoT-based system for fire and smoke detection is presented. An efficient model using deep learning for the IoT framework is proposed. This presentation covers applicability of our proposed model in detection of fire and smoke for edge and cloud computing.
Finally, we discuss the effectiveness of the proposed model and make recommendations using industry best practices.