💡 Inspiration

  • Mines are some of the most attractive weapons available to any determined adversary and represent one of the most vexing military challenges.
  • Sea mines are perhaps the most lethal form of these weapons, as they are hard to find, difficult to neutralize, and can present a deadly hazard to any vessel.
  • So here we come in with DodgeMine to predict the best possible route while travelling in a marine vehicle.

💻 What it does

  • The machine learning system, which is based on the neural network, needs a training data set that consists of samples of rocks and mines.
  • The training set, which has a distance between the samples, is given to the system, which results in a classification system where each sample has a score that shows its closeness to the other samples.
  • Based on this closeness, the system predicts a safe pathway between the two samples. The system, based on the machine learning model, consists of two parts: one for analysing the sonar radiation and the other for classifying the samples.
  • This system can be easily applied to a variety of applications that require intelligent classification.

⚙️ How we built it

  • The Client end of our website was built by using HTML,CSS and JS.
  • We used Logistic Regression for training the model.
  • We used Flask for our server to integrate an ML model with our website.

🧠 Challenges we ran into

  • Getting datasets for detecting mines or rocks was a bit difficult.
  • Selecting a perfect machine learning algorithm was a hard task.
  • As we are new to flask, We spend more time in integrating our model with our front end.

📖 What we learned

  • We learned to train a model within a short span of time.
  • We learned flask how to integrate a ML model with the client end.
  • We learned about the pickle package in Python, which is used for prediction.

📧 Use of Twilio

  • We used Twilio to send mine vs rock report to our users.
  • Twilio is safe and secure API for sending text messages.

☁️ Use of Google Cloud

  • Google Cloud offers Machine Learning and Deep Learning models.
  • We used google cloud logistic regression machine learning model to train our model.

📖 Use of Deso

  • Deso is a decentralized social application and it is open source & on chain open data
  • We used deso for login, logout purpose and also for transactions occurs in our website.

🚀 What's next for Dodge Mine

  • To upload input data as a file format.
  • To feed the model with more datasets and to increase its accuracy.
  • To test the dataset with different algorithms and to find the optimal algorithm.

🏅 Accomplishments that we're proud of

  • We're glad to sucessfully complete this project!
  • The end goal was met to a satisfactory level, and the outcome would allow help seaman to detect mine accurately and make them to have a safe jorney.

🔨 How to run

  • Fork the repo
  • Clone repo to your local storage
  • Install required packages
  • Run app.py folder
  • Open in your browser
Share this project: