Smart mirror

Project Title

Smart mirror

Project Area of Specialization Artificial IntelligenceProject Summary

A smart mirror is a device that functions as a mirror with additional capability of displaying multimedia data, such as text, images, and videos. This device allows users to access and interact with contextual information, such as weather data, seamlessly as part of their daily routine.

Dialogue Generation or Intelligent Conversational Agent development using Artificial Intelligence or Machine Learning technique is an interesting problem in the field of Natural Language Processing. In many research and development projects, they are using Artificial Intelligence, Machine Learning algorithms and Natural Language Processing techniques for developing conversation/dialogue agent. Their research and development is still under progress and under experimentation.

Chatbot is a program that generates response based on given input to emulate human conversations in text or voice mode. The chatbot we are proposing demonstrates a method of developing chatbot which can follow the context of the conversation. The mirror will be artificially intelligent, providing smart answers to the user’s inquiries, scheduling tasks and reminding the user of his/her appointments. The mirror will provide quick and efficient assistance and access to information.

Project Objectives

The Intelligent Mirror is designed to perform several functionalities. It will mimic a natural mirror interface through a flat LCD monitor used for the display. A two-way acrylic mirror is used in front of the LCD monitor thereby mimicking the function of a regular mirror. For personalized information services the users will be able to obtain minute updates of latest news and public headlines, weather reports as well as get reports of their interests.

The proposed Intelligent Mirror represents an interactive interface that enables access to personalized information and services and will be capable of answering any question by incorporating the concepts of NLP, Machine Learning (supervised and unsupervised learning).

This device allows users to access and interact with contextual information, such as weather data, seamlessly as part of their daily routine. So intelligent mirror brings together two widely used features, that of a Personal Assistant and that of a device which would display the status of an IOT device.

Project Implementation Method

The inception of the Project will be done with configuration of Raspberry Pi. The Raspberry Pi will be configured to load the web pages at boot and display the result in the Landscape mode along with widgets which are a boon of smart devices. So, the first version will simply be a smart mirror with cool widgets and basic applications similar to those of smart phone made using :

1.Rainmeter software.

2. Android Studio

Toolkits and libraries will be used to implement the chatbot functionality of mirror.

Toolkits and softwares that will be used will be:

1. scikit toolkit
2. Open cv-python
3. Tensor flow
4. NLTK
5. Cloud Speech-to-Text

ChatBot will be implemented using TensorFlow as follows:

1. NLP processes turn text into structured data, the machine converts this plain text request into codified commands for itself.
2. Now the chatbot throw this data into a decision engine, since in the bots mind it has certain criteria to meet to exit the conversational loop.
3. Using Natural Language Generation, NLG processes turn structured data into text.
4. This array of responses goes back into the messaging backend and is presented to you in the form of a question. You tell the bot what you want.
5. The bot now analyzes pre-fed data about the text and then answers accordingly.

Benefits of the Project

Our Intelligent Mirror has combined a few features of other Smart Mirrors that have been developed till date, yet it stands out as we have incorporated voice activation to access said features and we have also incorporated the idea of Wikipedia-type chatbot.

So intelligent mirror brings together two widely used features, that of a Personal Assistant and that of a device which would display the status of an IOT device.

The project is intended to improve communication with students in general while catering to the specific needs of freshers. Through the voice interface, students can get information about a range of subjects, from timetables, tutors and department news to any information related to their field. When new students swarm the campus, they have similar questions every year which makes for a perfect application of a chatbot. Using your voice, you can interact with the chatbot and get access to tons of information easily. Some additional advantages are:

• Improved question responsiveness and accuracy.
• Increased ability to track and monitor student queries, highlighting gaps in available information. 
• Enhanced goodwill and affinity with students.

With the addition of wikipedia chatbot, the smart mirror becomes entertaining yet informative, aimed to make students think out of the box to make creative projects.

Technical Details of Final Deliverable The final deliverable will consist of:

1.Final Report

2.Final presentation

3.Complete coding and database

4.Test cases for different functional modules of Intelligent Mirror.The systematic documentation of each test case will include: a serial  number,name of functional module simulated,description of simulation  ,input data and conditions favourable for module simulation.the results section will comprise of simulations based on input data and conditions.

5.Hardware deliverable will comprise of

• Display monitor with support
• Raspberry pi mounted and fixed to experimental setup
• The monitor will have sensors and camera attached to it.
• A speaker and mic will also be attached to the setup for interaction.

5. Voice Assistant

• For obtaining the voice inputs.
• For answering questions
• For Nlp module

6.Smart Mirror interface

· Will display notifications for E-mails, Messages, and Phone calls.

 · Will get general purpose information like the Date, Time, News, etc.

Final Deliverable of the Project Software SystemType of Industry IT Technologies Artificial Intelligence(AI), Internet of Things (IoT), Big DataSustainable Development Goals Industry, Innovation and InfrastructureRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	24750
LCD Screen	Equipment	1	8000	8000
Monitor Screen	Equipment	1	5000	5000
Wooden Frame	Miscellaneous	1	2000	2000
Raspberry Pie	Equipment	1	5500	5500
USB Microphone	Equipment	1	1000	1000
Speaker	Equipment	1	500	500
Proximity Sensor	Equipment	5	150	750
Tools	Miscellaneous	1	2000	2000