Mansi Gaikwad
Web Developer | Responsive Design & UI/UX Specialist
New to Contra
Mansi is ready for their next project!
Project Title: SteganoTool
1. Established a critical security framework for digital forensics and covert communication, as published in the IJRTI Journal (Vol. 10, Issue 4).
2. Achieved 100% data integrity during extraction by engineering a lossless LSB substitution pipeline for image, audio, and text carriers.
3. Conducted a comparative analysis of LSB vs. advanced transformation methods, proving that my custom noise-reduction heuristics significantly improved the PSNR (Peak Signal-to-Noise Ratio).
4. Optimized for multi-format compatibility, supporting 24-bit RGB and 8-bit grayscale images, making the tool versatile for various enterprise security applications.
0
11
Project Title: Sentix AI: Global Sentiment Intelligence
Results & Impact:
1. Achieved a 92% F1-score by implementing domain-specific fine-tuning on diverse consumer datasets, ensuring high reliability in classification.
2. Engineered an Aspect-Based Sentiment Analysis (ABSA) module that decomposed reviews into granular attributes (performance, pricing, reliability), making trend tracking 15% more precise.
3. Optimized inference performance by 25% through model distillation and Docker-based containerization, enabling the system to handle thousands of concurrent requests.
4. Mitigated data bias by designing a robust pre-processing workflow including lemmatization and custom noise reduction, critical for handling global marketplace jargon.
0
17
Engineered a dynamic, multi-section input engine that optimized the user journey through scalable, real-time block management logic.
Validated a 30% improvement in form-filling efficiency by measuring user interaction speed against traditional static document templates.
Developed and owned a live-preview rendering engine with CSS-optimized print functions to ensure 100% document fidelity and recruiter-ready formatting.
0
36
Architected a high-performance frontend engine using Vanilla JavaScript and Tailwind CSS, resulting in a 40% increase in UI responsiveness compared to standard CSS frameworks. Engineered a client-side recommendation algorithm using Local Storage, dynamically analysing user behavioural data to suggest niche titles with a 100% data persistence rate without a backend.
Optimized user decision-making by implementing a real-time price comparison modal, increasing the application’s utility and simulation accuracy by 30% across mock retail datasets.
1
59