Title: Compact System-level Models for Design and Synthesis of Smart Sensing Systems

Abstract: This talk discusses the integration of coarse-grain dataflow techniques with Markov decision processes for modeling, synthesis, and optimization of embedded software in smart sensor systems. Dataflow is a powerful formalism for representing a wide variety of applications for signal processing and knowledge extraction from distributed sensing devices. Markov decision processes can be applied to systematically drive the dynamic adaptation of dataflow graph parameters to improve performance in the face of uncertainties or time-varying characteristics in the operating environment or target platform. Software synthesis enables the automated, optimized derivation of embedded software implementations from cooperating dataflow graphs and Markov models. This talk presents foundations underlying this new form of software synthesis, and how they can be applied to address complex challenges facing designers of advanced smart sensing systems.

Brief Biography: Shuvra S. Bhattacharyya is a Professor in the Department of Electrical and Computer Engineering at the University of Maryland, College Park. He holds a joint appointment in the University of Maryland Institute for Advanced Computer Studies (UMIACS). He also holds a part-time position as International Research Chair, joint with INSA/IETR, and INRIA in Rennes, France. His research interests include signal processing, embedded systems, electronic design automation, machine learning, wireless communication, and wireless sensor networks. He received the Ph.D. degree from the University of California at Berkeley. He has held industrial positions as a Researcher at the Hitachi America Semiconductor Research Laboratory (San Jose, California), and Compiler Developer at Kuck & Associates (Champaign, Illinois). He has held a visiting summer research position at AFRL in Rome, New York. From 2015 through 2018, he was a part-time visiting professor in the Department of Pervasive Computing at the Tampere University of Technology, Finland, as part of the Finland Distinguished Professor Programme (FiDiPro). He is a Fellow of the IEEE.

Link: https://cse.iitkgp.ac.in/conf/SmartSensing/keynote.html

Topic: Avoiding Stress Driving: Online Trip Recommendation from Driving Behavior Prediction

Abstract: —The growth in the market for cab companies like Uber has opened the door to high-income options for drivers. However, in order to boost their income, drivers many a time resort to accepting trips which increases their stress resulting in poor driving quality and accidents in serious cases. Every driver handles stress differently and the trip recommendation thus needs to be on a personalized level. In this paper, we explore historical trip data to compute the driving stress and its impact on various driving behavioral features, captured through vehicle-mounted GPS and inertial sensors. We utilize a Multi-task Learning based Neural Network model to learn both the common features and the personalized features from the driving data to predict the stress level of a driver. We further establish a causal relationship between the stress level of a driver and his driving behavior. Finally, we develop a trip recommendation system for cab drivers to avoid stress driving. The models have been tested over both a publicly available dataset with 6 drivers for 500 minutes of driving data and an in-house collected dataset from 8 drivers over 1700 trips for 5 months. We observe that the proposed model gives an average prediction accuracy of 94% with low false-positive rates. We also observed that the driving behavior is improved when a driver takes a recommended trip

Brief Biography:Sandip Chakraborty is working as an Assistant Professor at the Department of Computer Science and Engineering in Indian Institute of Technology (IIT) Kharagpur. He completed his PhD from IIT Guwahati in 2014. He is a member of Complex Network Research Group (CNeRG), an interdisciplinary research group working on cross-domain research covering machine learning, social systems and computer systems. He leads multiple high-valued projects, sponsored by the Government of India as well as various industries like Intel, HPE, and BEL. He is a member of IEEE COMSOC, ACM SIGCOMM and ACM SIGMOBILE. Dr. Chakraborty is one of the founding members of ACM IMOBILE, the ACM SIGMOBILE chapter at India. He is working as an Area Editor of Elsevier Ad Hoc Networks journal. The primary research interests of Dr. Chakraborty are on various aspects of machine learning applications for computer systems, development of assistive technologies for societal well-being and design of distributed, pervasive and ubiquitous technologies over mobile devices and smartphones.