window.dataLayer = window.dataLayer || []; function gtag(){dataLayer.push(arguments);} gtag('js', new Date()); gtag('config', 'UA-70916517-9');


The focus of my research is to understand and enhance the usability and processing capabilities of tiny, energy harvesting, batteryless sensing, and computing devices to realize their full potential in our daily lives. While existing works on batteryless computing systems concentrate preliminary on the lower-level goals, e.g., execution progress and memory consistency, their prospect in the time-sensitive applications are yet to be explored. My work leverages the data processing and control layer of batteryless systems and ensures timely response by (1) developing a unified framework that integrates energy harvesting and real-time systems, and (2) engineering machine learning and computer vision algorithms to allow imprecise computing.

My work exploits the data processing and control layers of the commercially available systems to propose frameworks that enable already deployed systems to become more efficient and adaptive. Time-sensitive batteryless systems open up new application domains including wildlife tracking, infrastructure monitoring, wearables, and healthcare. The interdisciplinary nature of my research involves a blend of diverse domains, including embedded systems, mobile computing, machine learning, mobile health, signal processing, and ubiquitous computing. Along with novel frameworks designing for time-aware intermittent systems, my research explored the sensing potential of tiny intelligent computing devices in various application domains including computer vision, healthcare, pedestrian safety, and infrastructure monitoring with a vision to merge these two paths in future works.


  • Intelligent Embedded Systems
  • Intermittent Computing
  • Energy Efficiency
  • Low Power Network
  • Machine Learning
  • Continuous Monitoring System

Research Projects

  • Time-Aware Intelligent Intermittent Systems

    Execution of computational tasks, including machine learning, in intermittently-powered systems

    Current development of extremely low-power computing devices and efficient energy harvesters led to the creation of computing systems that are powered by intermittently available harvested energy, e.g., solar, piezoelectric, and radio-frequency (RF). Such computing systems go through power-on and off phases due to the lack of adequate harvesting energy. These systems are known as Intermittent Computing Systems. While existing works on intermittent computing systems concentrate preliminary on the lower level goals, e.g., execution progress and memory consistency, the potential of such systems under timing constraints is yet to be explored. Some applications of intermittent systems with timing constraints include monitoring wildlife, health, infrastructure and environmental conditions, pedestrian safety, indoor localization and occupancy detection. We focus on the timely-response and learning capability of intermittent systems by (1) developing unified frameworks that integrate harvesting and real-time systems, (2) engineering machine learning algorithms providing learning capabilities to this intermittent systems with timing-constraints, and (3) designing system framework for life-long learning.


    Zygarde: Time-Sensitive On-Device Deep Inference and Adaptationon Intermittently-Powered Systems, IMWUT/UBICOMP '20
    Scheduling Computational and Energy Harvesting Tasks in Deadline-Aware Intermittent Systems, RTAS '20
    Intermittent Learning: On-Device Machine Learning on Intermittently Powered System, IMWUT/Ubicomp '20
    PhD Forum Abstract: Scheduling Tasks on Intermittently Powered Systems, IPSN '20
    WiP: Time-Aware Deep Intelligence on Batteryless Systems, RTAS '19
    Poster Abstract: On-Device Training from Sensor Data on Batteryless Platforms, IPSN '19
    Differences in Reliability and Predictability of Harvested Energy from Battery-less Intermittently Powered Systems, JEI '20
  • Energy-Efficient Computer Vision on Embedded Systems

    3D reconstruction and augmrnted reality in low-power resource-constraint embedded systems

    Camera is the one of the most usable and common sensors in the current world. With the development of low-power camera and highly efficient embedded processors computer vision is now available in our daily handheld devices including smartphones. In this research, we explore the different computer vision applications, e.g., 3D reconstruction, augmented reality, and provide more energy-efficient solutions by controlling the image acquisition and image processing stages and intergrating other modalities, e.g., inertial measurement units.


    Glimpse.3D: A Motion-Triggered Stereo Body Camera for 3D Experience Capture and Preview, IPSN '18
    MARBLE: Mobile Augmented Reality Using a Distributed BLE Beacon Infrastructure, IoTDi '18
    Demo Abstract: A Motion-Triggered Stereo Camera for 3D Experience Capture, IPSN '18
  • Localization using Low Power Network

    Passive localization of low-power systems using BLE and LORA

    Mobility tracking of internet of things (IoT) devices in smart city infrastructures such as smart buildings, hospitals, shopping centers, warehouses, smart streets, and outdoor spaces has many applications, and BLE is available in almost every IoT device in the market nowadays. Developing an accurate ranging technique for Low powered network-enabled, e.g., Lora, BLE, IoT devices (both battery powered and batterless) is a challenging feat as billions of these devices are already in use, and for pragmatic reasons, we cannot propose to modify the IoT device (a BLE peripheral) itself. While current solutions focuses on active localization, energy-constraint devices are not suitable for this additional computation. Thus we focus on pasive localization by exploit characteristics of netowrk protocols protocol (e.g., frequency hopping and empty control packet transmissions for BLE) and propose a technique to directly estimate the range of a peripheral from a access point by multipath profiling. As timing delay is a significant for localization, we also focus on real-time constraint of the low-power networks.


    Rethinking Ranging of Unmodified BLE Peripherals in Smart City Infrastructure, MMSys '18
    Duty-Cycle-Aware Real-Time Scheduling of Wireless Links in Low Power WANs, DCOSS '18
    WiP: LoRaIn: Making a Case for LoRa in Indoor Localization, PerCom '19
  • Acoustic Sensing for Pedestrian Safety

    Vehicle detection and localization using acoustic sensors

    With the prevalence of smartphones, pedestrians and joggers today often walk or run while listening to music. Since they are deprived of their auditory senses that would have provided important cues to dangers, they are at a much greater risk of being hit by cars or other vehicles. PAWS/SEUS is a wearable system that uses multi-channel audio sensors embedded in a headset to help detect and locate cars from their honks, engine and tire noises, and warn pedestrians of imminent dangers of approaching cars. The system acts as a second pair of ears in situations where the user’s sense of hearing is greatly diminished, such as when the user is taking a phone call or listening to music, and warns users of imminent dangers well in advance, allowing users ample time to react and avoid traffic accidents.


    Paws: A Wearable Acoustic System for Pedestrian Safety, IoTDI '18
    Improving Pedestrian Safety in Cities using Intelligent Wearable Systems, IoTJ '19
    A Smartphone-Based System for Improving Pedestrian Safety, VNC '18
  • Privacy of Acoustic Homehub Devices

    Mitigating overhearing in continuously listening homehub devices, e.g., Google Home, Amazon Echo

    We study the overhearing problem of continuous acoustic sensing devices such as Amazon Echo and Google Home, and develop a smart cover that mitigates personal or contextual information leakage due to the presence of unwanted sound sources in the acoustic environment.


    SoundSifter: Mitigating Overhearing of Continuous Listening Devices, MobiSys '17
  • Intelligent Charger

    Designing intelligent charger to increase battery life-cycles for mobile devices and electronic vehicles

    Battery aging is increasingly becoming a major concern in mobile devices such as laptops or smartphones and often results in premature device replacement. While previous studies have shown that improved charging strategies can increase cycle life, most common chargers do not sufficiently consider battery health. In this perspective paper, we give an overview of recent advances made in battery-health-aware charging and highlight the benefits of making chargers more intelligent to improve the cycle life of different battery-powered devices. In particular, we quantify the potential benefits that intelligent chargers will have and outline possible research directions to make them such.


    Intelligent Chargers will Make Mobile Devices Live Longer, IEEE Design & Test '20