Shiyamala

Security Auditing & Malicious Client Blocking in Federated EEG Seizure Detection

Presented at IEEE ICCIDS 2026. (Acceptance Rate: ∼17.8%)

Shiyamaladevi R S, Swaroop S Kaimal, Jeetashree Aparajeeta. Security Auditing and Ultra-Strict Malicious Client Blocking in Federated EEG Seizure Detection.

• Engineered a three-tier attestation-based federated learning framework integrating HMAC-SHA256 for secure client verification.
• Achieved 97.5% accuracy in no-attack and 95.2% accuracy under 30% malicious clients, with 98.7% attack detection rate.
• Optimized lightweight CNN models for Raspberry Pi deployment, achieving 18 ms inference latency with 99% validation accuracy.
• Established a HIPAA/GDPR-compliant architecture enabling secure, privacy-preserving clinical AI for distributed seizure detection.

Swara-Net: A Deep Learning Baseline for Under-Represented Carnatic Ragas

Presented at Dec IEEEINDICON’2025

Shiyamaladevi R S. Swara-Net: A Deep Learning Baseline and Curated Dataset for Five Under-Represented Carnatic Ragas. TechRxiv. October 31, 2025. DOI: 10.36227/techrxiv.176281084.44193627/v1

• Curated a diverse dataset of 638 audio snippets across five ragas (Shankarabharanam, Revathi, Abheri, Brindavanasaranga, Mayamalavagowla).
• Designed Swara-Net, a 3-layer Deep Neural Network achieving 99.0% classification accuracy, outperforming SVM by 42%.
• Conducted detailed musicological error analysis of the model’s misclassification patterns and published the open-source dataset for reproducibility.
• Pioneered the first computational baseline for these five ragas, contributing to computational ethnomusicology research in Indian classical music.

Alleviating Muscle Fatigue in Robotic Prosthetic Arms via Multi-Sensor Fusion

Completed - Published in IEEE

Manimaran, P., Ashwin, J. B., Swaroop, S. K., & Shiyamaladevi, R. S. (2024, December). Alleviating Muscle Fatigue in Robotic Prosthetic Arms Through Multi-Sensor Fusion and Adaptive Real-Time Grip Assistance. In 2024 International Conference on Communication, Computing, Smart Materials and Devices (ICCCSMD) (pp. 1-12). IEEE. DOI: 10.1109/ICCCSMD63546.2024.11015135

• Designed a multi-sensor adaptive control system integrating EMG signals, computer vision, and pressure feedback to optimize grip force.
• Proposed a real-time fatigue detection algorithm reducing muscle strain and improving prosthetic control comfort.
• Validated feasibility for hardware-level integration with existing prosthetic arms, enhancing long-term usability and efficiency.

Automated Classification of E-Commerce Packaging for Open Box Delivery

Shiyamaladevi R S, Jeetashree Aparajeeta. Automated Classification of E-Commerce Packaging for Open Box Delivery: A Transfer Learning Solution. TechRxiv. November 10, 2025. DOI: 10.36227/techrxiv.176281084.44193627/v1

• Developed a transfer learning–based image classification pipeline to detect poor-quality packaging images (Blur/Dark/Random, Primary/Secondary Package).
• Achieved 89% overall accuracy and 96% recall for low-quality images using fine-tuned CNN architectures (ResNet50 + augmentation).
• Deployed an end-to-end automated workflow integrated with Google Sheets—allowing non-technical operators to run real-time OBD quality checks without coding.
• Reduced manual inspection overhead by 60%, improving packaging integrity assurance across last-mile delivery systems.

Research Assistant

Center for Neuroinformatics (Vellore Institute of Technology) | May 2025 - Aug 2025

• Designed a cryptographically secured federated learning framework using HMAC-SHA256 and AES-256, enabling privacy-preserving model training across 25 simulated medical devices.
• Developed an ultra-lightweight CNN (0.54 MB, 140K parameters) optimized for Raspberry Pi, achieving <15 ms inference latency and 98%+ clinical accuracy in real-time seizure detection.
• Implemented a Byzantine fault-tolerant aggregation system with dynamic trust scoring to ensure robustness against adversarial and faulty nodes.

Supply Chain Machine Learning Intern

FLIPKART | Feb 2025 – Jun 2025 | Chennai, India

• Engineered Python tool processing 1.3M records across multiple hubs, reducing time from 5 hours to 200 seconds—a 99.8% reduction (432× efficiency boost).
• Developed and deployed ML algorithms for Open Box delivery with 90%+ accuracy, improving fault detection and cutting operational downtime.
• Built a prototype Chrome extension identifying and mitigating last-mile delivery risks, ensuring improved reliability.

Section Leader

STANFORD CODE IN PLACE | Apr 2025 - June 2025

• Led a 6-week Python programming section, teaching 15 students core concepts including variables, control flow, functions, lists, and dictionaries.
• Facilitated weekly interactive coding sessions, provided personalized feedback, and supported student learning through hands-on exercises.

AWS Project Intern

ETHNUS | Aug 2023 – Dec 2023 | Remote

• Implemented Amazon EC2 and Elastic Beanstalk to host and scale an E-Health Record Management System, enhancing performance and responsiveness.
• Utilized Amazon S3 for efficient storage of diagnostic images, established role-based access control, and leveraged AWS RDS, Lambda, and CloudWatch for a robust system.

Instrumentation Intern

SAIPEM INDIA PROJECTS PVT LTD | Sept 2023 – Oct 2023 | Chennai, India

• Ensured compliance with engineering specifications through P&ID checks and streamlined data sheet validation.
• Built a foundation in oil & gas operations, control systems, and instrumentation using SmartPlant software.