https://github.com/am-i-groot/summer-intern-iitguwahati-spml
Developed an automated Water Quality Monitoring System (WQMS) at IIT Guwahati, using the pH-W218 sensor and K-Means Clustering to assess water potability. The project enhances water quality evaluation through machine learning-based classification.
https://github.com/am-i-groot/summer-intern-iitguwahati-spml
algorithm data data-visualization kmeans-clustering machine-learning python report sensor signal-processing
Last synced: 8 months ago
JSON representation
Developed an automated Water Quality Monitoring System (WQMS) at IIT Guwahati, using the pH-W218 sensor and K-Means Clustering to assess water potability. The project enhances water quality evaluation through machine learning-based classification.
- Host: GitHub
- URL: https://github.com/am-i-groot/summer-intern-iitguwahati-spml
- Owner: am-i-groot
- License: mit
- Created: 2025-02-28T15:43:25.000Z (8 months ago)
- Default Branch: main
- Last Pushed: 2025-02-28T18:41:42.000Z (8 months ago)
- Last Synced: 2025-02-28T20:17:20.160Z (8 months ago)
- Topics: algorithm, data, data-visualization, kmeans-clustering, machine-learning, python, report, sensor, signal-processing
- Language: Jupyter Notebook
- Homepage: https://colab.research.google.com/drive/1erbYYJE07cYVroKDOOXY2fJe5cDsawUQ
- Size: 20.7 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Water Quality Monitoring System (WQMS) – Summer Internship @ IIT Guwahati
This repository contains my work from the Summer Internship 2024 at IIT Guwahati, where I developed an advanced Water Quality Monitoring System (WQMS) under the mentorship of Dr. Hanumant Singh Shekhawat.
## 🚀 Project Overview
- Developed a Water Quality Monitoring System to enhance the accuracy of water quality assessments.
- Utilized the pH-W218 (8-in-1) sensor to collect and transfer data for multiple water samples.
- Applied Unsupervised Machine Learning (K-Means Clustering) to analyze water potability and interpret cluster centroids.
- Evaluated water quality by assessing key parameters: pH, TDS, EC, ORP, salinity, and temperature.
- Successfully completed the internship and received a certificate upon submitting the final report.
## 📌 Technologies & Tools Used
- Hardware: pH-W218 Sensor
- Programming: Python
- Machine Learning: K-Means Clustering, Elbow Method, Silhouette Analysis
- Data Analysis: Pandas, NumPy, Matplotlib
- Visualization: Seaborn, PCA for dimensionality reduction
## 📂 Repository Structure
`/data` – Collected water quality datasets
`/notebooks` – Jupyter Notebooks for data preprocessing, clustering, and visualization
`/reports` – Final report and presentation materials
## 🔗 Additional Resources
- Dataset: [Google Sheets Data](https://docs.google.com/spreadsheets/d/1D85inHHH68qjMXMPlr5uXc2Dmc4UB307/edit?usp=sharing)
- Colab Notebook: [K-Means Clustering Implementation](https://colab.research.google.com/drive/1erbYYJE07cYVroKDOOXY2fJe5cDsawUQ)
- Google Drive: [Complete Project Files](https://drive.google.com/drive/folders/1sj3jEUk8HoelCwrdG9mpSNwWmGAgawXJ?usp=sharing)
## 📊 Key Findings
### Cluster 1:
High-quality potable water with minimal impurities and balanced pH.
### Cluster 2:
Poor water quality with high levels of dissolved solids, salinity, and contaminants.
### Cluster 3:
Moderate water quality, requiring treatment for drinking purposes.
## 📢 Get in Touch
For any queries, discussions, or collaborations, feel free to connect! 🚀