Where developers grow together

Non-Invasive Blood Glucose Prediction via PPG Signals

An experimental Machine Learning pipeline designed to predict blood glucose levels and blood pressure ranges without needles. By analyzing Photoplethysmography (PPG) datasets, I performed extensive feature engineering and signal categorization to map optical blood volume changes to glucose metrics. A deep-dive into the future of painless health monitoring!

Fincurry: a Flutter app for family group and personal expenses

I'm Siddharth Kajaria, founder of Fincurry, and I'd like to share what our small team at Tailwebs Technology in Bengaluru has been building. Fincurry is a family group and personal expense tracker for iOS and Android. Every account starts solo. When you are ready, you invite family, a partner or roommates over WhatsApp, and the same app becomes a family group of up to 15 people. You can split bills equally, by amount, % or shares, see who owes whom and settle up, set category budgets, and let recurring bills such as rent, EMIs and electricity log themselves. It works in 22 languages, and each group can have its own currency. Why we built it: in many homes several people pay for the same household. One person pays the kirana bill, another the electricity, someone covers school fees, and by the end of the month nobody is sure where things stand. We wanted one calm place where the whole household can see that, without a spreadsheet or a long chat thread. How it is built, at a high level: the app is written in Flutter, so one codebase serves iOS and Android. Firebase handles storage, push notifications and analytics. A Node.js and Express API sits behind it, and the website is built with Next.js. When one member adds an expense, Socket.io and push carry it to every phone in the group in real time. Logging also works offline: entries wait in a local queue on the device and sync once the phone is back online. Feedback I would love from this community: If you run Socket.io and push side by side, how do you stop the same update from being handled twice on the device? Is the solo-to-family flow clear the first time you invite someone, or does it feel confusing? What would you check first in a Flutter app's onboarding before you trust it with household data? Fincurry is free, with no ads, and it is a tracking tool, not financial advice. Thanks for reading; happy to answer questions in the comments.

Solving Medicine Identification: AI Medicine Strip Analyzer using YOLOv8, OCR & Gemini

Brief: An AI solution to scan medicine packaging, recognize the drug, and fetch real-time medical guidelines & safety warnings. Introduction:Illegible handwriting or hard-to-read text on medicine strips can lead to harmful dosing. I built an AI application to instantly analyze medicine strips from photo captures and retrieve easy-to-understand drug information. How It Works:1. Package Detection: Trained a custom YOLOv8 model to detect and isolate medicine strips/foils from various lighting and angles.2. Text Extraction: OCR identifies brand names, drug compounds, and expiration dates on the packaging.3. LLM Reasoning: Extracted text is fed to a FastAPI back-end that queries Gemini API to synthesize patient guidelines (uses, dosage, side effects).4. Safety First: The pipeline generates explicit alerts about allergies and expiry checks. Tech Stack:YOLOv8, OpenCV, OCR (PaddleOCR), Gemini API, FastAPI, Python. Key Results:End-to-end drug identification and explanation in under 3 seconds with critical warnings highlighted.