Sudershan Boovaraghavan

Publications | Google Scholar

Kirigami: Lightweight Speech Filtering for Privacy-Preserving Activity Recognition using Audio
Sudershan Boovaraghavan, Haozhe Zhou, Mayank Goel, Yuvraj Agarwal.
IMWUT 2023

Paper

                            @article{10.1145/3643502,
                            author = {Boovaraghavan, Sudershan and Zhou, Haozhe and Goel, Mayank and Agarwal, Yuvraj},
                            title = {Kirigami: Lightweight Speech Filtering for Privacy-Preserving Activity Recognition using Audio},
                            year = {2024},
                            issue_date = {March 2024},
                            publisher = {Association for Computing Machinery},
                            address = {New York, NY, USA},
                            volume = {8},
                            number = {1},
                            url = {https://doi.org/10.1145/3643502},
                            doi = {10.1145/3643502},
                            abstract = {Audio-based human activity recognition (HAR) is very popular because many human activities have unique sound signatures that can be detected using machine learning (ML) approaches. These audio-based ML HAR pipelines often use common featurization techniques, such as extracting various statistical and spectral features by converting time domain signals to the frequency domain (using an FFT) and using them to train ML models. Some of these approaches also claim privacy benefits by preventing the identification of human speech. However, recent deep learning-based automatic speech recognition (ASR) models pose new privacy challenges to these featurization techniques. In this paper, we systematically evaluate various featurization approaches for audio data, assessing their privacy risks through metrics like speech intelligibility (PER and WER) while considering the utility tradeoff in terms of ML-based activity recognition accuracy. Our findings reveal the susceptibility of these approaches to speech content recovery when exposed to recent ASR models, especially under re-tuning or retraining conditions. Notably, fine-tuned ASR models achieved an average Phoneme Error Rate (PER) of 39.99\% and Word Error Rate (WER) of 44.43\% in speech recognition for these approaches. To overcome these privacy concerns, we propose Kirigami, a lightweight machine learning-based audio speech filter that removes human speech segments reducing the efficacy of ASR models (70.48\% PER and 101.40\% WER) while also maintaining HAR accuracy (76.0\% accuracy). We show that Kirigami can be implemented on common edge microcontrollers with limited computational capabilities and memory, providing a path to deployment on a variety of IoT devices. Finally, we conducted a real-world user study and showed the robustness of Kirigami on a laptop and an ARM Cortex-M4F microcontroller under three different background noises.},
                            journal = {Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.},
                            month = {mar},
                            articleno = {36},
                            numpages = {28},
                            keywords = {Acoustics, Internet of Things, Privacy, Ubiquitous Sensing}
                            }

TAO: Context Detection from Daily Activity Patterns using Temporal Analysis and Ontology
Sudershan Boovaraghavan, Prasoon Patidar, Yuvraj Agarwal
IMWUT 2023

Paper Video

                                    @article{10.1145/3610896,
                                    author = {Boovaraghavan, Sudershan and Patidar, Prasoon and Agarwal, Yuvraj},
                                    title = {TAO: Context Detection from Daily Activity Patterns Using Temporal Analysis and Ontology},
                                    year = {2023},
                                    issue_date = {September 2023},
                                    publisher = {Association for Computing Machinery},
                                    address = {New York, NY, USA},
                                    volume = {7},
                                    number = {3},
                                    url = {https://doi.org/10.1145/3610896},
                                    doi = {10.1145/3610896},
                                    journal = {Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.},
                                    month = {sep},
                                    articleno = {87},
                                    numpages = {32},
                                    keywords = {Behavioral context recognition, ontology, deep Learning, activity recognition}
                                    }

Mites: Design and Deployment of a General-Purpose Sensing Infrastructure for Buildings
Sudershan Boovaraghavan, Chen Chen, Anurag Maravi, Mike Czapik, Yang Zhang, Chris Harrison, and Yuvraj Agarwal.
IMWUT 2023

Paper Video

                                @article{10.1145/3580865,
                                author = {Boovaraghavan, Sudershan and Chen, Chen and Maravi, Anurag and Czapik, Mike and Zhang, Yang and Harrison, Chris and Agarwal, Yuvraj},
                                title = {Mites: Design and Deployment of a General-Purpose Sensing Infrastructure for Buildings},
                                year = {2023},
                                issue_date = {March 2023},
                                publisher = {Association for Computing Machinery},
                                address = {New York, NY, USA},
                                volume = {7},
                                number = {1},
                                url = {https://doi.org/10.1145/3580865},
                                doi = {10.1145/3580865},
                                journal = {Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.},
                                month = {mar},
                                articleno = {2},
                                numpages = {32},
                                keywords = {Real-World Deployment, Distributed Sensor Network, Sensing and Sensor Technologies}
                                }

FitNibble: A Field Study to Evaluate the Utility and Usability of Automatic Diet Monitoring in Food Journaling Using an Eyeglasses-based Wearable.
Abdelkareem Bedri, Yuchen Liang, Sudershan Boovaraghavan, Geoff Kaufman, and Mayank Goel.
IUI 2022

Paper Video

                        @inproceedings{10.1145/3490099.3511154,
                        author = {Bedri, Abdelkareem and Liang, Yuchen and Boovaraghavan, Sudershan and Kaufman, Geoff and Goel, Mayank},
                        title = {FitNibble: A Field Study to Evaluate the Utility and Usability of Automatic Diet Monitoring in Food Journaling Using an Eyeglasses-Based Wearable},
                        year = {2022},
                        isbn = {9781450391443},
                        publisher = {Association for Computing Machinery},
                        address = {New York, NY, USA},
                        url = {https://doi.org/10.1145/3490099.3511154},
                        doi = {10.1145/3490099.3511154},
                        booktitle = {27th International Conference on Intelligent User Interfaces},
                        pages = {79–92},
                        numpages = {14},
                        keywords = {usability, food journaling, eating detection, and compliance, diet monitoring, wearable, utility},
                        location = {Helsinki, Finland},
                        series = {IUI '22}
                        }

MLIoT: An End-to-End Machine Learning System for the Internet-of-Things
Sudershan Boovaraghavan, Anurag Maravi, Prahalladha Mallela, Yuvraj Agarwal
IoTDI 2021

Paper Video

                                @inproceedings{10.1145/3450268.3453522,
                                author = {Boovaraghavan, Sudershan and Maravi, Anurag and Mallela, Prahaladha and Agarwal, Yuvraj},
                                title = {MLIoT: An End-to-End Machine Learning System for the Internet-of-Things},
                                year = {2021},
                                isbn = {9781450383547},
                                publisher = {Association for Computing Machinery},
                                address = {New York, NY, USA},
                                url = {https://doi.org/10.1145/3450268.3453522},
                                doi = {10.1145/3450268.3453522},
                                booktitle = {Proceedings of the International Conference on Internet-of-Things Design and Implementation},
                                pages = {169–181},
                                numpages = {13},
                                keywords = {Distributed Machine Learning, Training, Serving, Internet of Things},
                                location = {Charlottesvle, VA, USA},
                                series = {IoTDI '21}
                                }

Vista: Spatial DataRepresentation for Smart Buildings
Matilda Kathryn Ferguson, Sudershan Boovaraghavan, Yuvraj Agarwal
BuildSys 2020

Paper

@inproceedings{10.1145/3408308.3431112,
author = {Ferguson, Matilda Kathryn and Boovaraghavan, Sudershan and Agarwal, Yuvraj},
title = {Vista: Spatial Data Representation for Smart Buildings},
year = {2020},
isbn = {9781450380614},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3408308.3431112},
doi = {10.1145/3408308.3431112},
booktitle = {Proceedings of the 7th ACM International Conference on Systems for Energy-Efficient Buildings,
                            Cities, and Transportation},
pages = {342–343},
numpages = {2},
keywords = {Smart Buildings, Visual Inference, Data Visualization},
location = {Virtual Event, Japan},
series = {BuildSys '20}
}

Who can Access What, and When? Understanding Minimal Access Requirements of Building Applications
Jason Koh, Dezhi Hong, Shreyas Nagare, Sudershan Boovaraghavan, Yuvraj Agarwal, Rajesh Gupta
BuildSys 2019

Paper

@inproceedings{10.1145/3360322.3360868,
author = {Koh, Jason and Hong, Dezhi and Nagare, Shreyas and Boovaraghavan, Sudershan and Agarwal, Yuvraj and Gupta, Rajesh},
title = {Who Can Access What, and When? Understanding Minimal Access Requirements of Building Applications},
year = {2019},
isbn = {9781450370059},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3360322.3360868},
doi = {10.1145/3360322.3360868},
booktitle = {Proceedings of the 6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation},
pages = {121–124},
numpages = {4},
keywords = {smart buildings, IoT, Access control},
location = {New York, NY, USA},
series = {BuildSys '19}
}

Supporting Maintenance Operations for IoT-Based Activity Recognition Using Transfer Learning
Matus Tomlein, Sudershan Boovaraghavan, Yuvraj Agarwal, Anind Dey
arXiv 2018

Paper

@article{tomlein2018,
author = {Tomlein, Matúš and Boovaraghavan, Sudershan and Agarwal, Yuvraj and Dey, Anind},
year = {2018},
month = {06},
pages = {},
title = {Supporting Maintenance Operations for IoT-based Activity Recognition using Transfer Learning},
doi = {10.13140/RG.2.2.11601.43361}
}

CharIoT: An end-user programming environment for the IoT
Matus Tomlein, Sudershan Boovaraghavan, Yuvraj Agarwal, Anind Dey
IoT 2017

Paper

@article{tomlein2018,
author = {Tomlein, Matúš and Boovaraghavan, Sudershan and Agarwal, Yuvraj and Dey, Anind},
year = {2018},
month = {06},
pages = {},
title = {Supporting Maintenance Operations for IoT-based Activity Recognition using Transfer Learning},
doi = {10.13140/RG.2.2.11601.43361}
}

📢 News

08/23: I was awarded the 2023 CyLab Presidential Fellowship

07/23: Paper on TAO-context sensing paper gets accepted to Ubicomp'23

04/23: Completed my Thesis Proposal!

01/23: Mites paper gets accepted to Ubicomp'23, see you in Cancún!

Patents

Virtual sensor system
Yuvraj Agarwal, Christopher Harrison, Gierad Laput, Sudershan Boovaraghavan, Chen Chen, Abhijit Hota, Bo Robert Xiao, and Yang Zhang
U.S. Patent Application 16/591,987,filed January 30, 2020

📢 I'm currently seeking full-time opportunities. If you're aware of any opportunities, please reach out to me. Here is my resume and CV.

Publications | Google Scholar

Patents