Ideaboard – Trivandrum, July 2018
We thought we might help you get started on the hackathon with some ideas and resources. These are however, just some ideas, and while you are free to pick one and work on it, we also encourage you to go out and pick a problem on your own. Jump to the resources by clicking on a stream below:
- Artificial Intelligence
- Computer vision
- Augmented reality
- Virtual reality
- Internet of Things
Natural language processing: NLP is an area concerned with the interactions between computers and human natural languages, in particular how to program computers to process and analyze large amounts of natural language data.
Computer vision: This is a field that deals with how computers can be made for gaining high-level understanding from digital images or videos. From the perspective of engineering, it seeks to automate tasks that a human can do.
Some ideas for you:
- Given an document with pictures embedded in it, predict the sentence in the document closely associated with the picture
- Given a question, extract the main intent.
eg. When is the sunrise tomorrow? – TIme, Sunrise
eg. How much dost the Rado 11.5 Cost? Currency, Rado
- From a corpus of documents, automatically identify the 10 most relevant tags
- Take the commodity price history and predict next months price
- A chat-bot to request space inside Technopark
- Document classification model to get the startup schemes in the state and the country for an aspiring/existing entrepreneur.
- Multi level classification system that automatically assigns tags for questions posted on forums (such as Stack overflow or Quora)
- Develop a model to classify news as fake or real
- Build an application to analyze unstructured data on social media,news and online platforms and identify effective actions to improve customer trust
- Predicting movie success using machine learning
- Diagnosis enablers using computer vision on medical i such as images from radiography and histopathology Sections
- Computer vision & machine learning for accelerated diagnosis and alerting systems based on medical records, data from wearable, medical devices etc.
- Computer vision & machine learning for epidemic predictions and surveillance using public data and satellite imagery
- Computer vision & machine learning for natural environment damage monitoring and urban sprawl surveillance using public data and satellite imagery
- Text Mining Wiki: https://en.wikipedia.org/wiki/Text_mining
- Sci-Kit Learn Tutorial: http://scikit-learn.org/stable/index.html
- Tensorflow Tutorial: https://www.tensorflow.org/tutorials/
- Question tagging Github: https://github.com/erohkohl/question-tagging
- Fake News Github: https://github.com/nishitpatel01/Fake_News_Detection
- Fake News Datacamp : https://www.datacamp.com/community/tutorials/scikit-learn-fake-news
- Fake News: https://towardsdatascience.com/fake-news-classifier-e061b339ad6c
- Sentiment Analysis Github: https://github.com/ayushoriginal/SentimentAnalysis-Twitter/blob/master
- Computer Vision – Stanford University: http://cs231n.github.io/
- NLP – Stanford University Course: http://cs224d.stanford.edu/
- Computer vision and disease outbreak surveillance: https://www.scientificamerican.com/article/satellites-predict-a-cholera-outbreak-weeks-in-advance/
- Computer vision and Histopathology: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5099087/
- Computer vision and urban sprawl: http://streetchange.media.mit.edu/static/pdf/NaikEtAl_Streetchange_PNAS_2017_LowRes.pdf
- Computer vision and urban sprawl: https://www.sciencedirect.com/science/article/pii/S0198971516301831
- Computer vision and urban sprawl: https://arxiv.org/pdf/1802.02668.pdf
A blockchain, is a continuously growing list of records, called blocks, which are linked and secured using cryptography. Each block typically contains a cryptographic hash of the previous block, a timestamp, and transaction data. By design, a blockchain is resistant to modification of the data.
Here are some Ideas:
Blockchain for solving business problems in the broad areas such as:
- Supply chain
- Authenticity/Traceability of items
- Luxury goods Supply/Warranty
- Asset Management and Asset Registry
- Payments and Transactions (Payment System on Blockchain)
- Use Cases: https://www.ibm.com/blockchain/use-cases/
- Smart contracts: https://hackernoon.com/ethereum-development-walkthrough-part-1-smart-contracts-b3979e6e573e
- Ethereum: https://ethereum.org/
- Hello world contract: https://www.ethereum.org/greeter
- HyperLedger: https://www.hyperledger.org/
- HyperLedger Fabric: http://hyperledger-fabric.readthedocs.io/
- HyperLedger Fabric Dev: https://github.com/chainHero/heroes-service/
- HyperLedger Sawtooth: https://www.hyperledger.org/projects/sawtooth
- Ethereum Development Tutorial: https://github.com/ethereum/wiki/wiki/Ethereum-Development-Tutorial
- Solidity Tutorial: https://codeburst.io/build-your-first-ethereum-smart-contract-with-solidity-tutorial-94171d6b1c4b
- GoLang Tutorial: https://gobyexample.com/
- Stellar: Stellar.org (Payments network)
Augmented Reality (AR) is an interactive experience of a real-world environment whose elements are “augmented” by computer-generated perceptual information, sometimes across multiple sensory modalities, including visual, auditory, haptic, somatosensory, and olfactory.
Virtual reality (VR) is an interactive computer-generated experience taking place within a simulated environment, that incorporates mainly auditory and visual, but also other types of sensory feedback like haptic. This immersive environment can be similar to the real world or it can be fantastical, creating an experience that is not possible in ordinary physical reality.
A few ideas for you to try:
- AR/VR based Indoor Navigation for large buildings such as Malls
- AR/VR game based on Indian Culture that would engage Indian audience better.
- AR/VR game based on ground plane detection with auto generated level and complexity
- Bring outdoor games indoor, using Augmented Reality (Example: Football, cricket, golf, hockey)
- AR/VR Game Development using Unit AR RTS/ AR Platformer/ AR Shooter
- Story telling using Unity’s Cinemachine/AR
Make sure Entire pre-build projects shouldn’t be used for development
- Some tools you might want to leverage for computer vision side of AR: ARKit, ARCore or Vuforia
- Free assets could be downloaded from various websites like
- Best 10 AR Games (video): https://www.youtube.com/watch?v=Ki1aN_n-xnU
- Cinemachine https://www.youtube.com/watch?v=GXI0l3yqBrA
- Unity Tutorial: https://docs.unity3d.com/Packagesemail@example.com/manual/index.html
- Cinemachine Tutorial: https://www.youtube.com/watch?v=x6Q5sKXjZOM
The Internet of Things (IoT) is the network of physical devices, vehicles, home appliances, and other items embedded with electronics, software, sensors, actuators, and connectivity which enables these things to connect and exchange data, creating opportunities for more direct integration of the physical world into computer-based systems, resulting in efficiency improvements, economic benefits, and reduced human exertions.
Here Are some Ideas:
- Home/Industrial automation has been there for long, but these systems are getting smarter with progress in Machine Learning, Cloud Computing and declining cost of Sensors and Microcontrollers. There is a lot of opportunity in creating a Home/Industrial Automation system that is smart and can save resources like time, money and energy just to name a few.
- Application of IoT and Robotics in agriculture is making farming more productive, what is your next big idea that would revolutionize farming.
- Farmbots: https://www.youtube.com/watch?v=uNkADHZStDE
- Vertical Farming: https://www.youtube.com/watch?v=-_tvJtUHnmU
- IoT in Farm: https://www.youtube.com/watch?v=wwbZ_2aNhUo
- Innovate with IoT, APIs & Emerging Tech: https://temboo.com/
- App for IoT: https://www.blynk.cc/
- ThingSpeak IoT analytics platform: https://thingspeak.com/
- Open-source IoT platform: https://www.kaaproject.org/
- Robot Operating System: http://www.ros.org/
- Drones in Farming: https://www.ted.com/talks/vijay_kumar_the_future_of_flying_robots
That’s just a few of the many, many ideas that you can try. Feel free to get creative and identify any problem worth solving around you. Once you fix on something, be sure to register for the event too!
Good luck, Pirates!