Real Time Home Automation using Google assistant
(IoT).
1
Presented By Supervised By
Zihadur Rahman
ID: 20141201041
Dept. of CSE, BSMRSTU
F.M. Rahat Hasan Robi
Lecturer, Dept. of CSE, BSMRSTU
• Home automation or domotics is building automation for a home, called a smart home or
smart house.
• A home automation system will control lighting, climate, entertainment systems, and
appliances.
• It may also include home security such as access control and alarm systems.
• Home automation is developed by using wireless technology.
• Wireless technology in home automation starts with bluetooth, wi-fi, and zigbee
communication.
2
Introduction:
• Managing all of your home devices from one place.
• Reduce Energy Consumption.
• Maximizing home security.
• Mobile phone Monitoring & Controlled System.
• Improved appliance functionality. Smart homes can also help you run your appliances better.
3
Motivation:
Methodology
Ok,Google
Google Assistant
condition
Input
Action
If(Turn On AC)then(send data 1 to AC feed)
Output
AC feed=1
On
1
MQTT client
AC feed=1
Sensor
ESP8266
ADC
Multiplexer
• Automatic light and Camera on/off by motion sensor.
Main door open/close detection by magnetic door sensor.
• Automatic AC on/off by temperature sensor.
• Alarm when smoke detected by smoke sensor.
• Appliance controlled through mobile phone.
• Notification via Email & SMS.
5
Objectives:
Reference Paper 1.Clickbait detection , M.Potthast,S.Kopsel,B.stein and M Hagen
Methodology: Random forest classifier
Limitations : The problem with fixed rule set approaches is that clickbaits are prevalent not only on particular social media sites,
but also on many other reputed websites across the web.
Reference Paper 2.Stop Clickbait:Detecting and Preventing Clickbaits in Online News Media ,Abhijnan Chakraborty ,Bhargavi
Paranjape,Sourya Karakal,Niloy Ganguly
Methodology : Word N-grams, Part of Speech Tags and Syntactic N-grams
Limitations: These methods identify clickbait with the context of the articles that they represent, but not clickbait headlines in
isolation.
Reference Paper 3.Thai Clickbait Detection Algorithms using Natural Language Processing with Machine Learning Techniques
Methodology: Corpus,Feed-Forward Neural Network,Long-Short Term Memory,Embedding layers,The Keras framework.
Limitations :Word segmentation problems in Thai language.
4.Clickbait Detection using Deep Learning, Amol Agarwal
Methodology :CNN, Word Embeddings
6
Related Works:
Proposed Model:
Bangla Text
Document
Bengali-Word-
Embedding
Feature
Engineering
Splitting data
into training and
test sets
Data Training
Text
Classification
Model
Data Testing Results Evaluation

Real Time Home Automation using Google assistant Iot project presentation

  • 1.
    Real Time HomeAutomation using Google assistant (IoT). 1 Presented By Supervised By Zihadur Rahman ID: 20141201041 Dept. of CSE, BSMRSTU F.M. Rahat Hasan Robi Lecturer, Dept. of CSE, BSMRSTU
  • 2.
    • Home automationor domotics is building automation for a home, called a smart home or smart house. • A home automation system will control lighting, climate, entertainment systems, and appliances. • It may also include home security such as access control and alarm systems. • Home automation is developed by using wireless technology. • Wireless technology in home automation starts with bluetooth, wi-fi, and zigbee communication. 2 Introduction:
  • 3.
    • Managing allof your home devices from one place. • Reduce Energy Consumption. • Maximizing home security. • Mobile phone Monitoring & Controlled System. • Improved appliance functionality. Smart homes can also help you run your appliances better. 3 Motivation:
  • 4.
    Methodology Ok,Google Google Assistant condition Input Action If(Turn OnAC)then(send data 1 to AC feed) Output AC feed=1 On 1 MQTT client AC feed=1 Sensor ESP8266 ADC Multiplexer
  • 5.
    • Automatic lightand Camera on/off by motion sensor. Main door open/close detection by magnetic door sensor. • Automatic AC on/off by temperature sensor. • Alarm when smoke detected by smoke sensor. • Appliance controlled through mobile phone. • Notification via Email & SMS. 5 Objectives:
  • 6.
    Reference Paper 1.Clickbaitdetection , M.Potthast,S.Kopsel,B.stein and M Hagen Methodology: Random forest classifier Limitations : The problem with fixed rule set approaches is that clickbaits are prevalent not only on particular social media sites, but also on many other reputed websites across the web. Reference Paper 2.Stop Clickbait:Detecting and Preventing Clickbaits in Online News Media ,Abhijnan Chakraborty ,Bhargavi Paranjape,Sourya Karakal,Niloy Ganguly Methodology : Word N-grams, Part of Speech Tags and Syntactic N-grams Limitations: These methods identify clickbait with the context of the articles that they represent, but not clickbait headlines in isolation. Reference Paper 3.Thai Clickbait Detection Algorithms using Natural Language Processing with Machine Learning Techniques Methodology: Corpus,Feed-Forward Neural Network,Long-Short Term Memory,Embedding layers,The Keras framework. Limitations :Word segmentation problems in Thai language. 4.Clickbait Detection using Deep Learning, Amol Agarwal Methodology :CNN, Word Embeddings 6 Related Works:
  • 7.
    Proposed Model: Bangla Text Document Bengali-Word- Embedding Feature Engineering Splittingdata into training and test sets Data Training Text Classification Model Data Testing Results Evaluation