Ideaz

The Problem:

In hostels, residents share rooms and common areas, making it difficult to maintain consistent routines for study, sleep, and wellness. Daily issues include:

• Irregular sleep schedules due to noise, social activities, or roommates’ habits.

• Difficulty identifying optimal study times and maintaining focus.

• Stress and reduced productivity caused by poor time management.

• Health issues from disrupted routines, such as sleep deprivation or missed meals.

This situation leads to decreased academic performance, higher stress levels, and general dissatisfaction among residents.

Gaps in Current Solutions:

• Habit-tracking apps or planners are generic and require manual input, rarely reflecting real-life patterns.

• Noise-canceling devices or study spaces only partially address environmental distractions.

• Wellness guides don’t leverage data or predictive insights to recommend personalized schedules.

• Hostel management rarely has tools to support residents in optimizing their routines.

Who Benefits:

• Users (students and residents): Gain personalized insights, improved productivity, better sleep, and reduced stress.

• Buyers (parents and management): Enjoy higher resident satisfaction, fewer complaints about conflicts or poor performance, and improved hostel reputation.

• Community: Creates a culture of accountability, healthy routines, and mutual respect in shared living spaces.

Why This Matters to Me:

As a hostel resident, I’ve struggled with disrupted routines, late-night study sessions, and poor sleep. Using data and ML to optimize personal schedules can improve academic performance, well-being, and overall harmony in shared living environments.

Optional Technical Details:

• Uses smartphone sensors, wearables, and IoT-enabled hostel rooms to collect data on sleep, study, and environmental conditions.

• ML algorithms predict optimal study periods, sleep windows, and wellness activities based on past behavior and environment.

• Residents receive real-time, personalized recommendations through a mobile app, and can view analytics dashboards to track improvements over time.

The Problem Managing bills and expenses today is scattered and stressful. We get paper bills, PDFs, email invoices, and app notifications, often losing track of spending patterns. Existing apps either focus on banking or are too complex for everyday users. There’s a need for a single, simple system to track, organise, and understand all expenses from daily bills to subscriptions.

What GreenBill Does GreenBill is a mobile-first solution that uses OCR (Optical Character Recognition) and lightweight ML models to scan bills, extract key details (amount, date, category, merchant), and automatically log them. It goes beyond storage by acting as a personal financial assistant, connecting with apps we already use.

How it Works

1. Smart Scanning – Snap a photo of any bill; OCR extracts details accurately.

2. Automatic Categorisation – ML tags expenses (food, transport, utilities, shopping).

3. Cross-App Integration – Syncs with UPI apps (GPay, PhonePe), food delivery, ride apps, and email receipts.

4. Unified Dashboard – Displays monthly spend, recurring payments, and category breakdowns.

5. Smart Reminders – Calendar alerts for bill due dates.

6. Secure Cloud Storage – Backups via Google Drive/Dropbox.

Why GreenBill Matters Instead of juggling multiple apps, GreenBill gives users a single source of truth for spending. It’s useful for students, professionals, and families, helping them track, save, and plan effortlessly.

Future Vision

• AI Insights – Personalised suggestions like “Reduce dining expenses by 20% next month.”

• Smart Saving Goals – Set targets for gadgets, trips, or emergencies.

• Shared Expenses – Split costs with friends/flatmates.

• Green Impact Tracking – Track eco-friendly purchases to encourage sustainable spending.

Why I’m Building This As a student, I’ve struggled to manage personal expenses. Using my CS skills (OCR, APIs, ML), I can prototype GreenBill and test it with peers before scaling.

Next Steps

• Prototype OCR + logging pipeline

• Build a minimal Android app (Flutter/React Native)

• Pilot with students for UX & accuracy feedback

Proactive treatment and prevention remain some of the biggest challenges in modern healthcare. Why must we wait for something to go wrong before addressing it? Why must we wait for our bodies to scar before knowing we are allergic to something? While test kits, blood panels, and health apps exist, they lack integration and do not predict interactions between lifestyle, environment, and genetics.
My idea Gen-Dub would create a digital twin of a person, and it is built from biological tests, genetic data, lifestyle inputs which would involve sleep, meals, and location tracking. This AI model is meant to simulate an individual's unique biology and hence allows it to predict outcomes such as potential side effects to drugs or food (allergic reaction) and in the long run it can predict health risks much before symptoms even appear. Unlike the health trackers that currently exist, Gen-Dub is a solution that moved beyond passive monitoring to active forecasting.
The benefits are almost never ending. Users gain peace of mind, predictive health advice and majorly, fewer emergency situations. Doctors can make safer treatment decisions and avoid trial and error prescriptions. Gen-Dub will help change the definition of healthcare and should help us prevent suffering and not just mange it afterward.
Gen-Dub leverages genomics, machine learning, and real-time data to produce unique digital models of each individual. Over time, as new data accumulates, these models continuously evolve and improve in accuracy alongside the user.
Initially, Gen-Dub will be expensive due to the level of testing and tech required to build a complex model for each individual. However, as technology advances and processes become more efficient, costs will decrease, making Gen-Dub accessible to everyone. Ultimately, Gen-Dub has the potential to make proactive, personalized healthcare the standard, transforming how we understand and manage our well-being for generations to come.

One of the biggest problems in cities today is inefficient waste management. Overflowing garbage bins, uncollected trash, and littered streets are common scenes that affect not just cleanliness but also public health and the environment. Despite multiple efforts from municipalities, the systems in place often fail to handle waste efficiently. I thought—what if there was a way to use technology to manage waste more intelligently, ensuring that bins are cleaned before they overflow and resources are used optimally? That’s how the idea of “Smart Waste Management System” came to me.

The idea is to equip waste bins with sensors that measure how full they are in real time. These sensors would send data to a central system that maps all bins in the city. Garbage collection trucks would then be directed only to the bins that need emptying, avoiding unnecessary trips and reducing fuel consumption. The system could also predict peak waste times in different areas, helping the authorities deploy staff more efficiently.

The gap in current solutions is that most cities rely on fixed schedules, which lead to inefficiencies. Bins are emptied when they are not full, wasting time and resources, while some areas remain unclean because bins overflow before the next scheduled collection.

The beneficiaries are many:

• Residents, because streets will be cleaner and healthier.

• Municipalities, which can save money and reduce pollution by optimizing routes.

• Businesses and tourists, who will benefit from a cleaner environment.

• The planet, as better waste management reduces landfill overflow and harmful emissions.

This problem matters to me because I live in an urban environment where waste is a constant challenge. Seeing garbage piling up not only looks unpleasant but also leads to diseases and discomfort. Efficient waste management improves quality of life and reflects responsible governance.

From a technical perspective, the system could use low-cost IoT sensors, cloud-based analytics, and route optimization algorithms powered by machine learning. Data privacy can be ensured by only tracking bins and collection schedules without personal information.

Though there will be challenges like sensor maintenance, connectivity, and funding, the long-term benefits far outweigh the initial investment. By making waste management smarter, cities can become healthier, safer, and more sustainable for everyone. This is not just about garbage—it’s about dignity, health, and responsible living.