← Home

A little more about me

I’m a Master’s student in Electrical and Computer Engineering at the University of Southern California, specializing in Machine Learning and Data Science. My research sits at the intersection of neurotechnology, biosignal processing, and artificial intelligence.

Currently, I work as a graduate researcher at USC’s COOR Lab, where I develop ML tools for clinical biomechanics and biosignal processing. My work focuses on making complex data analysis accessible and practical for real-world applications.

Education

University of Southern California

M.S. in Electrical and Computer Engineering (ML/DS Track)
Aug 2024 - May 2026 (expected) · Los Angeles, CA

Indian Institute of Information Technology Sri City

B.Tech (Honours) in Electronics and Communications Engineering
Aug 2020 - May 2024 · Sri City, India

Experience

USC Information Sciences Institute — Project Alexandria

Graduate Researcher · Aug 2025 - Present

  • Built a PDF-to-structured-record service in Python (2,910 lines across 8 modules) with cloud and fully local model backends interchangeable behind one interface, cutting extraction cost per page to zero on the local path.
  • Added semantic retrieval over ChromaDB with sentence-transformer embeddings, plus a Neo4j layer that resolves repeated entities across documents via MERGE on (name, type) — a cross-document node/edge graph instead of per-file silos.
  • Built a four-family automated evaluation harness (information retention, n-gram overlap, LLM-as-judge, graph topology) instrumented with Weights & Biases, so every run emits reproducible quality signals.
  • Engineered the Python signal-processing pipeline for multi-channel surface EMG: 2 kHz across 7 muscles and 54 patients — notch and Butterworth filtering, TKEO onset detection, MVIC normalization into a QC-gated dataset.
  • Showed force and neuromuscular timing recover independently (r = -0.012, p = 0.938) with linear mixed-effects models under Bonferroni correction and leave-one-out cross-validated logistic regression.
  • Result carried by two APTA CSM abstracts and a manuscript.

BrainSightAI

Machine Learning Intern · Jan 2024 - Jun 2024

  • Processed clinical 3T patient MRI scans with UNet3D models (VoxelBox) to extract DTI metrics and 3D white-matter tractography, running visual QC on FA maps to eliminate spatial artifacts and false fiber streamlines.
  • Caught a denoising failure that aggregate SNR and RMSE both passed — blocky spatial artifacts visible only on rendered FA maps — and changed the production default on that evidence.

Human Movement Analysis Lab, IIIT Sri City

Honours Student Researcher · May 2022 - May 2024

  • Led collection and public release of four surface EMG datasets (EMAHA-DB4 to DB7, 70 subjects).
  • Trained CNN and BiLSTM classifiers over a filter, rectify, normalize, feature-extract pipeline — producing three peer-reviewed IEEE publications (EMBC, BIOSIGNALS, ISPA).

Publications

Impact of Measurement Conditions on Classification of ADL using Surface EMG signals ↗

Vidya Sagar, Anish Turlapaty, Surya Naidu
ISPA 2023

Classification of Fine-ADL using sEMG signals under different measurement conditions ↗

Surya Naidu, Anish Turlapaty, Vidya Sagar
BIOSIGNALS 2024

Impact of Activity Pace and Arm Position on Classification of ADLs ↗

Sayee G B, Anish Turlapaty, Surya Naidu, Vidya Sagar
EMBC 2024

Nanomagnetic Logic Simulation of Digital Design

Vidya Sagar (co-author)
2023

Projects

Explore the project collection for selected work in neural decoding, biosignals, and ML systems.

Technical Skills

Languages: Python, C++, SQL, MATLAB, JavaScript, R

ML & AI: PyTorch, TensorFlow, scikit-learn, XGBoost, JAX, ONNX, OpenCV, Hugging Face

LLM & Retrieval: LangChain, ChromaDB, Neo4j, Hybrid retrieval (RRF), Sentence transformers, Ollama (local inference)

Signals & Time-Series: Surface EMG, TKEO onset detection, Kalman / PSID, Wavelets, Mixed-effects models, Bootstrap CIs

Systems & MLOps: Docker, FastAPI, GitHub Actions, pytest, MLflow, Weights & Biases, Git, Linux

Cloud & Data: Azure, GCP, Spark

Biomedical & Neuroimaging: BIDS, FSL, sEMG processing, Motion capture, HIPAA compliance

Beyond Research

When I’m not working on research, I enjoy exploring new technologies, contributing to open-source projects, and staying active. I’m particularly interested in the potential of AI to transform healthcare and make advanced medical technologies more accessible.

I’m currently seeking full-time ML / signal-processing roles (2026), particularly in sensor ML, neurotechnology, or applied-ML positions.

Contact

Email: vvenna@usc.edu GitHub: ViSaReVe LinkedIn: vidyasagarvenna Scholar: Google Scholar