Development of environmental monitoring based on IoT cloud solutions using deep learning
Explore the docs »
·
Report Bug
·
Request Feature
Table of Contents
Initially DHT11 sensor is connected to Raspberry pi zero to mine the temperature and humidity data inside a closed room environment then data is then continuosly fed to thingspeak cloud using APIs.
Project Overview:
- Data is fed from raspberry pi to cloud.
- Creating a machine learning model with the time series data to predict the future temperature and humidity of an environment.
- Model deployment in cloud.
For machine learning model initially, we will use neural networks to buid the model as a starting point since it could be highly efficient for time series data.
These are the programming languages, libraries, frameworks, cloud services and other tools used in this project.
As mentioned in the roadmap the first step is preparing the trained model which is under going now. Further steps will be continuosly updated.
Data visualization of mined data using few samples to get a better insights about the data. data_visualization.ipynb`.
This image can be found under Images/Past humidity reading.png
For now code for forward propagation for the network is alrready written which can be found under forward.py. Soon backpropogation and trained model will be updated.
- Sensor setup using raspberry pi
- Data feeding to cloud
- Data visualization and pre-processing
- Model Creation
- Evaluation and cloud deployment(Ongoing)
- [-] Data improvement
- [-] Model deployment in different platforms(Ongoing)
See the open issues for a full list of proposed features (and known issues).
Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.
If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement". Don't forget to give the project a star! Thanks again!
- Fork the Project
- Create your Feature Branch (
git checkout -b feature/AmazingFeature) - Commit your Changes (
git commit -m 'Add some AmazingFeature') - Push to the Branch (
git push origin feature/AmazingFeature) - Open a Pull Request
Distributed under the MIT License. See LICENSE.txt for more information.
Your Name - @AriharasudhanM - [email protected]
Project Link: IoT-based-environmental-monitoring
Use this space to list resources you find helpful and would like to give credit to. I've included a few of my favorites to kick things off!
- The future of environment monitoring
- An IoT based Environment Monitoring System
- Deep Learning for Time Series Classification
- REVIEW ON - IOT BASED ENVIRONMENT MONITORING SYSTEM
- Advances in Smart Environment Monitoring Systems Using IoT and Sensors
- Design of an IoT based Real Time Environment Monitoring