IOT and ML Analytics Demo
Hi all,
In this blog, I would like to share information about how to setup ML analytics tool on an IOT cloud platform. Before that, I am writing some basic information about understanding ML and different ML tools.
Understanding ML and different ML analytics tools available
Machine Learning is a type of artificial intelligence that allows software applications to learn from the data and become more accurate in predicting the outcomes without the human intervention. To make this happen, we have lot of machine learning tools available today.
Different Machine Learning Tools
SCIKIT LEARN: It is a simple and efficient tool for data mining and data analysis built on NumPy, SciPy and Matplotlib. It provides a range of Supervised and unsupervised learning algorithms like classification, clustering, regression and much more.
KNIME(Konstanz Information Miner): It is a free and open-source data analytics, reporting, and integration platform built for powerful analytics on a GUI based workflow. The good part of this is we need not know how to code.
TensorFlow: It is a free and open-source library in javascript and the best library for Machine Learning. Created by Google Brain team for numerical computations and large scale machine learning. It provides readable syntax making it easy to use. It also uses keras and other high level api to make things little smoother.
WEKA: It is a open source java software that provides a collection of machine learning algorithms for data mining and data exploration tasks. It is one of the most powerful Machine Learning tools for understanding and visualizing machine learning algorithms on your local machine.
how to set up and use a ML analytics tool on AWS Platform
Login to an AWS account and launch a new EC2 instance which means creating a new virtual machine instance.
Choose an Amazon Machine Image(AMI) from the list you can see. I chose Deep Learning AMI(Amazon Linux 2) version 35.0
Next determine the type of instance this AMI to generate. Since machine learning needs GPU computation power(GPU computing is the use of a GPU, “graphics processing unit” as a co-processor to accelerate CPUs for general-purpose scientific and engineering computing), select an instance from the family. I selected p2.xlarge as shown below.
Then click review and launch where it asks to generate a key pair. Once generated the key pair, we need to download it as .pem file.
After downloading the .pem file, it prompts to view instance. Next, to connect to the instance, click on the connect button as shown below
It will redirect to the following
You can directly connect to the ec2 instance with the connect or use the SSH client to connect. Using SSH, we need to follow the below steps:
Once done, it will prompt to run the commands to work on the interested frameworks as shown below.
Next run the desired command(in our case tensorflow) and open jupyter notebook. That’s it, we are ready to use ML analytics tool on AWS cloud.
In the next blog, I will share about how to setup MQTT flow.
