Machine Learning

Computer process millions of within a second by following the commands given by humans and return the result. It can only perform the task as described by human but cannot take decision by itself.

So, the process of making computer to learn and prepare itself for action is called Machine Learning, Or to make your computer do this task is also known as Machine Learning. In Machine learning we work on data and  the property of data points is Features.

So, machine learning algorithms are smart algorithms which gives you the power of taking decision on the basis of experience.

Machine learning  start with defining the data and ends with the model with some defined level of accuracy.

Machine Learning Process

• Define the problem: Think about the solution more formally.
• Collect the data to build the machine learning classifier.
• Prepare the data in the format which is used by machine learning algorithm.
• Cleaning: Removing the errors.
• Formatting: Make data in predefined format.
• Sampling: Removing similar instances from data.
• Decomposition: Divide the date in day, month and year.
• Scaling: Pre-process and transform the data in a form useful for Machine Learning algorithms.
• Split data in training and testing: Train our algorithm on training data and calculate final accuracy by running them on testing data.
• Algorithm selection
• Training the algorithm
• Evaluation on Test data
• Parameter Tuning
• Start Using your model

 Consider an example:

People apply for loan and on the basis on the income and loan amount bank decides whether to give loan or not. Think, if a person has monthly income of Rs 10,000/- and applied for the loan of Rs 3,00,000/- , bank may reject his application early as bank see that he cannot be able to repay it. And if person with Rs 10,000/- monthly income and applied of loan Rs 20,000/- then bank may approve its application.

 So, based on past defaulter history bank created a data, and this is how we train the system to work.

Internet of Things (IoT)

•  When things or objects are connected to the Internet rather than people.
• Things in IoT is the objects which can be the person or machine with a built-in sensor having IP addresses with the ability to collect and transfer the data over the Internet.

IoT is a platform where:

• devices become smarter
• processing becomes intelligent
• communication becomes informative

IoT is a broader concept which includes Machine-to-Machine (M2M) (technologies that enable machines to interact with human beings) and Machine-to- Human (M2H) (technologies that enable machines to communicate with other machines and drive action).

Definition: Internet of Things (IoT) means accessing and controlling daily usable equipment and devices using Internet.

 IoT enable us to use smart technologies to connect things anytime, anyplace for anything.

The term Internet of Things was first coined by  Kevin Ashton in 1999, which refers the connections between physical devices such as vehicles, home appliances, and other items embedded in electronics such as sensors, software which enables these things to connect, collect and exchange data.

Advantages of IoT:

• You can easily access any information sitting from any part of the globe, in real time.
• IoT encourages better communication between your connected devices and the Internet.
• IoT proves to be very helpful to people in their daily tasks by making the appliances communicate to each other.
• Minimize the human effort.
• It provides the benefit of knowing things in advance.

Disadvantages of IoT:

• IoT systems are interconnected and communicate over networks, so chances are there that the system
• Might get cracked by the hackers and they can steal the information.
• Designing, developing, and maintaining and enabling the large technology to IoT system is quite complicated.
• With automated task there may be a lower need for manpower and eventually loss of jobs.
• Human’s dependability on technology is increasing day by day.

Characteristics of IoT:

• Proper connection between all the things of IoT to IoT platform, server or cloud.
• Anything can be interconnected with the global information and communication infrastructure.
• The devices in the IoT are heterogeneous which supports different hardware platforms and networks.
• Interoperability is the ability of two or more systems or components to exchange data and use information.
• IoT devices and systems should change dynamically based on the context and changing conditions.

 Application of IoT:

• Home Automation
• Smart Water Systems
• Smart Transport
• Smart Cities
• Social Life and Entertainment
• Health and Fitness
• Smart Environment and Agriculture
• Livestock Monitoring
• Smart Greenhouses
• Supply Chain and Logistics
• Energy Conservation