MethaneGuard AI
AI-powered methane leak detection and risk prioritization for faster environmental inspections.
+2 more Machine learning projects
38 students and freshers on Wooble have shown Machine learning in 43 public projects: work you can open, read about and judge for yourself, not a skill ticked on a résumé.
Many of them study at Chennai Institute of Technology, Indian Institute of Technology Roorkee and Rajiv Gandhi Institute of Petroleum Technology.
Some of this work was built for challenges like MemoryVerse AI '26, MethaneGuard AI '26 and Chase the Cloud Challenge '26 (ISRO).
38 builders · 43 projects
AI-powered methane leak detection and risk prioritization for faster environmental inspections.
+2 more Machine learning projects
AI that finds methane plumes in satellite imagery, measures each leak in kg/hr, and ranks them so inspection crews fix the worst first.
Toss advantage creates perception, middle overs create control, and death overs create opportunities for comebacks.
Implemented an Eigenfaces-based face recognition system using Principal Component Analysis (PCA) with 93.75% recognition accuracy.
+1 more Machine learning project
An AI-powered BDR assistant that qualifies inbound leads, researches companies, detects buying signals, and generates sales-ready insights.
An AI-powered spatial archive that transforms scattered files into a structured, searchable timeline of your digital identity.
Replaced a manual updation, token issued in seconds, patient wait times recalculated from real consultation data, zero manual refreshes
Autonomous AI-Agentic Career Intelligence Platform
Digitizes hospital queues with real-time sync, reducing perceived wait times by 60% and improving patient satisfaction by 40% across 500K+ clinics in India.
5-sec patient add · <300 ms multi-screen sync · 0 paper printed · ETA from real data
Built a premium analytics dashboard for the Indian Premier League (IPL) that uncovers toss impact, match-winning phases, batting dominance, bowling efficiency,
+1 more Machine learning project
Built for MemoryVerse AI '26
Built for MemoryVerse AI '26
Pradeepa BV.s.b. Engineering CollegeLate-game speed wins critical moments, but steady middle-overs volume wins match tournaments.
J P Kalpana NayakaM S Ramaiah University of Appied SciencesAnalyzed 1,239 IPL matches and 294,757 deliveries to uncover that middle-over dominance predicts victory more strongly than toss advantage.
+1 more Machine learning project
“IPL victories are influenced far more by death-over performance and finishing strength than by toss advantage alone.”
Analyzed 200K+ IPL ball-by-ball records to uncover how death-over performance, batting consistency, and venue conditions influence match victories.
Analyzed 289,673 ball by ball events to prove that +7.79 middle over run dominance is the strongest predictor of IPL match victory, outperforming toss advantage
Built a high-performance analytics application that processes ball-by-ball IPL records to provide actionable strategic data for franchise match-planning.
289K deliveries → 13 analytics modules, 30+ charts, 7 hidden patterns, 1 ML win-probability model.
This application uses AI-driven data to optimize and significantly reduce patient wait times.
Real-time queue synchronization across receptionist and patient screens with live wait-time estimation and zero page refreshes.
Built a real-time hospital queue system replacing paper tokens with live updates, smart analytics, and emergency queue management.
IPL matches are usually decided before the Death Overs — Powerplay and Middle Overs have the strongest impact on winning, while Death Overs are statistically cl
Discovered a compounding momentum framework proving that winning the Powerplay unlocks an elite 90.00% match-winning probability in the IPL.
Toss-winning teams secured 53.1% of the matches, highlighting a significant advantage in match outcomes.
Death-over scoring showed the strongest correlation with IPL victories, while toss advantage had minimal impact.
Processed 289K+ IPL deliveries across 1200+ matches to uncover tactical match-winning insights using Python analytics.
Analyzed 289K+ deliveries to surface toss impact, phase dominance & player rankings across IPL seasons
Analyzed IPL match data to identify winning patterns using Python, Pandas, and Matplotlib. Explored toss impact, scoring phases, top players, and match-winning
Toss Impact: Winning the toss had almost no effect on overall match outcomes. Match Phases: Strong performance in the death overs showed the highest connection
Every builder here got on this page the same way: a public project on their Wooble profile that uses Machine learning. Enter a hackathon to build one with a brief and a deadline.
Allow analytics and ad cookies? Privacy policy