Machine Learning or Predictive Models in IoT - Energy Prediction Use Case

Machine Learning or Predictive Models in IoT - Energy Prediction Use Case

In this machine learning and IoT project, we are going to test out the experimental data using various predictive models and train the models and break the energy usage.

Videos

Each project comes with 2-5 hours of micro-videos explaining the solution.

Code & Dataset

Get access to 50+ solved projects with iPython notebooks and datasets.

Project Experience

Add project experience to your Linkedin/Github profiles.

Customer Love

Read All Reviews

Arvind Sodhi

VP - Data Architect, CDO at Deutsche Bank

I have extensive experience in data management and data processing. Over the past few years I saw the data management technology transition into the Big Data ecosystem and I needed to follow suit. I... Read More

Ray Han

Tech Leader | Stanford / Yale University

I think that they are fantastic. I attended Yale and Stanford and have worked at Honeywell,Oracle, and Arthur Andersen(Accenture) in the US. I have taken Big Data and Hadoop,NoSQL, Spark, Hadoop... Read More

What will you learn

Understanding the problem statement
Importing Dataset directly from AWS
Understanding the attributes and their datatypes
Importing important libraries and understanding its significance
Using the summary function in R and interpreting its result
Time stamping the column with time attributes
Visualizing and understanding density plot
Plotting a time series plot
Understanding seasonality and trends
Plotting box plot and whiskers plot for visualizing outliers
Visualizing ggplot and Barplot
Filling out null values and feature engineering
Visualizing variables using panel graphs
Selecting the best feature using RFE(Recursive Feature Elimination)
Converting categorical into numerical vectors
Applying Boosting model Gradient Boosting Model for training
Applying linear model Linear Regression
Applying SVM using different Kernels
Selecting best evaluation metrics
Plotting graphs for visualizing the results
Selecting the best model for hyper-parameter tuning
Using Grid Search CV to extract the best features
Making final predictions and Saving them in form of CSV

Project Description

This IoT project presents and discusses data-driven predictive models for the energy use of appliances. Data used include measurements of temperature and humidity sensors from a wireless network, whether from a nearby airport station and recorded energy use of lighting fixtures. The machine learning project discusses data filtering to remove non-predictive parameters and feature ranking. The data set is at 10 min for about 4.5 months. The house temperature and humidity conditions were monitored with a ZigBee wireless sensor network. Each wireless node transmitted the temperature and humidity conditions around 3.3 min. Then, the wireless data was averaged for 10 minutes periods. The energy data was logged every 10 minutes with m-bus energy meters. Weather from the nearest airport weather station (Chievres Airport, Belgium) was downloaded from a public data set from Reliable Prognosis (rp5.ru) and merged together with the experimental data sets using the date and time column. Two random variables have been included in the data set for testing the regression models and to filter out non-predictive attributes (parameters). 

Similar Projects

IoT Project-Learn to design an IoT Ready Infrastructure 

The goal of this IoT project is to build an argument for generalized streaming architecture for reactive data ingestion based on a microservice architecture. 

View Project Details

Curriculum For This Mini Project

Introduction to Problem Statement
05m
Dataset Overview
08m
Data PreProcessing
00m
Import Libraries
02m
Format Date
14m
Identify Missing Values
02m
Plotting univariate features
09m
Plotting bivariate features
06m
Identify Outliers
12m
Visualize energy usage
16m
Summary statistics using DPLYR
10m
Heat map for usage pattern
33m
Recap
02m
Model Data Preparation
03m
Correlations Table
07m
Feature Selection using Boruta
09m
Adding Dummy Variables to model
01m
Create Model using RFE control
08m
List chosen Features for prediction
02m
Training the Model
04m
Training the SVM and RF Model
03m
Conclusion
01m