Sandeep Singh Sandha (Sandeep) [Alum]
image

Amazon

Computer Science

Email:
sandha@cs.ucla.edu

Web Page

Education:

  • Bachelor of Computer Science and Engineering in , Indian Institute of Technology, Roorkee, 2014.
  • Master of Science in Computer Science, UCLA, 2018.
    Thesis: Sensory Substitution Learning
    (done at NESL)
  • Ph.D in Computer Science, UCLA, 2022.
    (done at NESL)

Experience:

  • Amazon AI (2021): Designed a data-driven tool to handle bottlenecks in AWS production databases.
  • ARM Research (2019, 2020): Mango is available: https://github.com/ARM-software/mango
  • Teradata Labs (2018): Patent: https://patents.google.com/patent/US20200151575A1/
  • IBM Research (2015 - 2016): I worked as software engineer in IBM Research, New Delhi. I contributed to the research and development of several projects in the areas of mobile computing, distributed computing, and machine learning.
  • Oracle (2014): I was part of the Oracle database team.
  • IBM Research (2013): Member of the distributed computing team.

Research Interests:

  • Reinforcement Learning
  • Deep Learning Systems
  • Machine Learning
  • Distributed System
  • Databases
  • Mobile Computing
  • Distributed Sensing
  • Time Synchronization

Recent Publications:

  • Machine Learning for Microcontroller-Class Hardware - A Review
    Swapnil Sayan Saha, Sandeep Singh Sandha, and Mani B. Srivastava.
    IEEE Sensors Journal, October 2022. [ Details ]
  • TinyOdom: Hardware-Aware Efficient Neural Inertial Navigation
    Swapnil Sayan Saha, Sandeep Singh Sandha, Luis A. Garcia, and Mani B. Srivastava.
    Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies (IMWUT), May 2022. [ Details ]
  • Auritus: An Open-Source Optimization Toolkit for Training and Deployment of Human Movement Models and Filters using Earables
    Swapnil Sayan Saha, Sandeep Singh Sandha, Siyou Pei, Ziqi Wang, Ankur Sarker, and Mani B. Srivastava.
    Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies (IMWUT), May 2022. [ Details ]
  • THIN-Bayes: Platform-Aware Machine Learning for Low-End IoT Devices
    Swapnil Sayan Saha, Sandeep Singh Sandha, and Mani B. Srivastava.
    TinyML Summit 2022, March 2022. [ Details ]
  • Enabling Hyperparameter Tuning of Machine Learning Classifiers in Production
    Sandeep Singh Sandha, Swapnil Sayan Saha, and Mani B. Srivastava.
    Third IEEE International Conference on Cognitive Machine Intelligence, December 2021. [ Details ]
  • Sim2Real Transfer for Deep Reinforcement Learning with Stochastic State Transition Delays
    Sandeep Singh Sandha, Bharathan Balaji, Fatima M. Anwar, and Mani B. Srivastava.
    CoRL, December 2020. [ Details ]
  • Deep Convolutional Bidirectional LSTM for Complex Activity Recognition with Missing Data
    Swapnil Sayan Saha, Sandeep Singh Sandha, and Mani B. Srivastava.
    Human Activity Recognition Challenge. Smart Innovation, Systems and Technologies, August 2020. [ Details ]
  • Mango: A Python Library for Parallel Hyperparameter Tuning
    Sandeep Singh Sandha, and Mani B. Srivastava.
    ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2020. [ Details ]
  • RadHAR: Human Activity Recognition from Point Clouds Generated through a Millimeter-wave Radar
    Akash Deep Singh, Sandeep Singh Sandha, Luis A. Garcia, and Mani B. Srivastava.
    3rd ACM Workshop on Millimeter-wave Networks and Sensing Systems (co-located with MobiCom), October 2019. [ Details ]
  • Exploiting Smartphone Peripherals for Precise Time Synchronization
    Sandeep Singh Sandha, Joseph Noor, Fatima M. Anwar, and Mani B. Srivastava.
    International Symposium on Precision Clock Synchronization for Measurement, Control, and Communication, September 2019. [ Details ]

Other Publications:

  • "RadHAR: Human Activity Recognition through a Millimeter-wave Radar" mmNets 2019.
  • "Exploiting Smartphone Peripherals for Precise Time Synchronization" ISPCS 2019.
  • "In-Database distributed deep learning: Demonstration using Teradata SQL Engine" VLDB 2019.
  • "Enabling Edge Devices that Learn from Each Other: Cross Modal Training for Activity Recognition" Edge Sys 2018.
  • "A multi-sensor process for in-situ monitoring of water pollution in rivers or lakes for high-resolution quantitative and qualitative water quality data," 14th IEEE International Conference on Embedded and Ubiquitous Computing (EUC), Aug, 2016.
  • “The GangaWatch App and BlueWater Platform to Enable Usage of Water Data in India in Every Day Decisions Integrating Historical and Real-time Sensing Data,” Data Flow: Grand Challenges in Water Systems Modeling, Data Management, and Integration, Louisiana State University, Baton Rouge, May, 2016.
  • "Mobile Health Application for Early Disease Outbreak-Period Detection," 16th IEEE International Conference on E-health Networking, Applications, and Services (Healthcom), Oct, 2014.
  • "CROWD-PAN-360: Crowdsourcing based Context-aware Panoramic Map Generation for Smartphone Users," IEEE Transactions on Parallel and Distributed Systems (TPDS), July 2014.

Awards:

  • UCLA-2021: Outstanding Mentorship Award
  • IoTDI-2019: Best Demo Award
  • IIT Roorkee-2012: Summer Undergraduate Research Award

Secretary: Serving as president of Computer Science Graduate Student Association (2017 - Present)