Shaniya T.

Key Skills

Software

Other

Top Subject Matter

Computer Vision (Hand Gesture Translation)

Safety Monitoring Simulation

Inventory Data Organization (Simulation)

Top Data Types

Image

Top Task Types

Tracking

Classification

Freelancer Overview

Hand Gesture Translation Web App (Streamlit & Python). Core strengths include MediaPipe (Computer Vision) and Other. Education includes Integrated Master of Science, VIT Vellore (2030). AI-training focus includes data types such as Computer Code and Programming and labeling workflows including Tracking and Classification.

Labeling Experience

E-Commerce Inventory Simulator (Python)

OtherClassification

Developed a terminal-based inventory simulator that organizes products using structured records. Implemented user account verification flows and maintained organized data tables for dynamic sorting of products. Used programmatic rules to assign and manage categorical product organization states within the simulated dataset. • Built login/logout verification logic for user sessions • Created structured tables for product organization and sorting • Added logic for dynamic ordering of inventory entries • Ensured correctness of table operations and execution flow

Not specified

Smart LPG Gas Monitoring Simulator (C Programming)

OtherTracking

Implemented a real-time gas safety monitoring simulation that interprets incoming readings against defined safety thresholds. Created conditional warning triggers when simulated levels cross safe limits. Treated the alert outputs as labeled classification states derived from streaming numerical data. • Authored algorithms to ingest and evaluate incoming gas data • Defined safety-limit logic for automated warning generation • Verified conditional branches and edge cases in execution • Debugged simulation behavior to ensure correct label transitions

Not specified

Hand Gesture Translation Web App (Streamlit & Python)

Tracking

Built real-time hand-movement translation logic for an app using spatial hand landmark coordinates. Mapped detected landmark positions to corresponding text output via custom algorithms. Focused on transforming sensor/vision-derived data streams into labeled text events suitable for AI-driven interpretation. • Implemented MediaPipe hand landmark extraction and coordinate processing • Designed position-to-text mapping rules for consistent translation outputs • Optimized backend logic for low-latency, reliable real-time inference • Validated execution by checking for logic and processing errors during development

Not specified

Education

Work History