Hi, I’m Sastha Srinivas!
As a graduate researcher, pursuing a Ph.D. in Computer Science at the IIIT-Delhi, in the department of Computer Science at the Melange Lab under the guidance of Prof. Pushpendra Singh and Prof. Mohan Kumar. I bring 3+ years of hands-on experience specializing in AI/ML and IoT through my prior work, graduate education, and internships. As a researcher, my focus is on leveraging existing technologies and upcoming ML/AI technologies and tools for social impact.
Prior to this, I spent two years as a Programmer Analyst at Sara’s Inc. and Unanu, spearheading cloud products and analytics dashboards that saved time and money for clients from various domains. My involvement was not limited but included cloud API deployment, testing, and maintenance, analytics dashboard design, and deployment, & working on producing ML/AI pipelines for production environments.
Preceding that, I was pursuing a Master’s degree in Computer Systems Engineering with a specialization in IoT at the College of Engineering at Northeastern University (currently renamed as the Master of Science in Cyber-Physical Systems with a concentration in the Internet of Things (IoT)), under the guidance of Prof.Peter O’Reilly. In the final year of my graduate degree, I had the opportunity to complete my 6 month Co-op at Bose Corporation in the smart home sound systems division, as a Product Security Engineer Co-op, where I developed an automated testing suite for the embedded and network security of smart speakers using some deductive algorithms to be integrated in the Sec-DevOps pipeline. I was also the treassuer of the IoTConnect graduate club at Northeastern University involved in the design and development of IoT systems and applications by graduate students.
My work and passion involve utilizing concepts from multi-disciplinary fields for affective computing. My side projects include advancements in computer science education, including but not limited to improving teaching methods, analyzing the impact of AI on education, and more. I also like playing strategic games (board and online), RPGs (table-top DnD and online), and delving into interesting books (based on recommendations and reviews) with a cup of hot cocoa to relax when I do not explore the nature.
Featured Projects
Tested the hypothesis of making a compressed model to detect diabetic retinopathy without compromising on evaluation metrics on various memory-efficient deep learning models and performed a comparative evaluation. The codes for the evaluated models are available here.
Trained various DL classification models for the Herbarium2022 Dataset having 15004 classes. To improve the model’s performance, trained the classes to classify based on coarser labels using different hierarchy levels. The codes for the evaluated models are available here.
Designed and developed an air quality monitoring system with the raspberry pi and senseHAT as a system model to explain different levels of an Embedded IoT framework. Improved privacy and efficiency of the framework by using OTA alerts and remote-control options. The code and instructions are available here.
Evaluated differences in the performance of Deep Neural Networks on different processing modules available on Nvidia Tegra Jetson Xavier System on Module (SoM) using Mask R-CNN, Faster R-CNN, and TensorRT models. Delivered a report on profile-specific competencies for different processing units present in the SoM for an image classification/detection algorithm. The repositories used for evaluation can be found in the following links: Mask-RCNN, Realtime-object-detection, and Jetson-inference
Developed a couple of games to test the understanding of SFML framework and C++ using various concepts like sprite background changes, registering keystrokes, refreshing spawns, registering mouse clicks, and incorporating randomness to coordinates hit. The code for Timber and Zombie Arena is available in Timber, and Zombie Arena respectively.
Designed and evaluated a correlation experiment to quantify the effect of music tempo on heart rate during exercise. Derived a regression curve for the effect of music tempo on heart rate by clustering data from various people.
Featured Publications
Latest News
- Position Paper on analyzing missing physiological data for health management accepted at PhysioCHI 24 Workshop at CHI 24.
- Position Paper on generating synthetic physiological data for health management accepted at LLMCHI 24 Workshop at CHI 24.
- Poster on hybrid teaching accepted at SIGCSE TS 24.
- Poster on Ble IPS accepted at MLSS 2024, Okinawa, Japan. Also received the travel grant to attend the summer school.
- Poster on Positive Aging at ACM SIGCHI Symposium for HCI & Friends 2022, Mumbai, India. Also received the travel grant to attend the symposium.
- Joined Ph.D. at IIIT Delhi, under the guidance of Prof. Pushpendra Singh and Prof. Mohan Kumar.
- Started vocational work as Lead Programmer Analyst at Unanu.
- Joined as Programmer Analyst at Sara’s Inc.
Latest Travel
Mar 20–23, '24 | SIGCSE TS 24, Portland, Oregon, United States (Attended Online) |
Mar 3–15, '24 | MLSS 2024, Okinawa, Japan, Okinawa, Japan |
May 11–12, '23 | RIISE 2023, New Delhi, Delhi, India |
Dec 9–11, '22 | ACM SIGCHI Symposium for HCI & Friends, Mumbai, India |
Oct 16–18, '22 | Winter School on Cognitive Computing, IIT Mandi (Attended Online) |
–>