TensorFlow 2.0 Tutorial for Beginners 14 - Human Activity Recognition using Accelerometer and CNN

~~===[Complete Udemy ML Course]===~~
Python for Machine Learning: A Step-by-Step Guide

Learn to build Machine Learning and Deep Learning models using Python and its libraries like Scikit-Learn, Keras, and TensorFlow.
~~=============================~~

In this video we will learn about human activity recognition using Accelerometer and CNN. In this project we are going to use accelerometer data to train the model so that it can predict the human activity. We are going to use 2D Convolutional Neural Networks to build the model. This WISDM dataset contains data collected through controlled, laboratory conditions. The total number of examples is 1,098,207. The dataset contains six different labels (Downstairs, Jogging, Sitting, Standing, Upstairs, Walking).

From the data distribution shown above we can observe that the data is unbalanced. Standing has very less examples compared to Walking and Jogging'. If we use this data directly it will overfit and will be skewed towards Walking and Jogging'. As we saw earlier the data is in string data type. Here we have converted the x, y, z values into floating values using astype('float').

🔊 Watch till last for a detailed description
03:18 Understanding dataset
16:50 Balancing the data
29:52 Standardizing data
33:11 Frame preparation
41:14 Building 2D CNN model
47:50 Plotting the learning curve
48:37 Confusion matrix

👇👇👇👇👇👇👇👇👇👇👇👇👇👇
✍️🏆🏅🎁🎊🎉✌️👌⭐⭐⭐⭐⭐
ENROLL in My Highest Rated Udemy Courses
to 🔑 Unlock Data Science Interviews 🔎 and Tests

📚 📗 NLP: Natural Language Processing ML Model Deployment at AWS
Build & Deploy ML NLP Models with Real-world use Cases.
Multi-Label & Multi-Class Text Classification using BERT.

📊 📈 Data Visualization in Python Masterclass: Beginners to Pro
Visualization in matplotlib, Seaborn, Plotly & Cufflinks,
EDA on Boston Housing, Titanic, IPL, FIFA, Covid-19 Data.

📘 📙 Natural Language Processing (NLP) in Python for Beginners
NLP: Complete Text Processing with Spacy, NLTK, Scikit-Learn,
Deep Learning, word2vec, GloVe, BERT, RoBERTa, DistilBERT

📈 📘 2021 Python for Linear Regression in Machine Learning
Linear & Non-Linear Regression, Lasso & Ridge Regression, SHAP, LIME, Yellowbrick, Feature Selection & Outliers Removal. You will learn how to build a Linear Regression model from scratch.

📙📊 2021 R 4.0 Programming for Data Science || Beginners to Pro
Learn Latest R 4.x Programming. You Will Learn List, DataFrame, Vectors, Matrix, DateTime, DataFrames in R, GGPlot2, Tidyverse, Machine Learning, Deep Learning, NLP, and much more.
---------------------------------------------------------------

💯 Read Full Blog with Code
💬 Leave your comments and doubts in the comment section
📌 Save this channel and video for watch later
👍 Like this video to show your support and love ❤️

~~~~~~~~
🆓 Watch My Top Free Data Science Videos
👉🏻 Python for Data Scientist
👉🏻 Machine Learning for Beginners
👉🏻 Feature Selection in Machine Learning
👉🏻 Text Preprocessing and Mining for NLP
👉🏻 Natural Language Processing (NLP)
👉🏻 Deep Learning with TensorFlow 2.0
👉🏻 COVID 19 Data Analysis and Visualization
👉🏻 Machine Learning Model Deployment Using
👉🏻 Make Your Own Automated Email Marketing

***********
🤝 BE MY FRIEND

🆓🆓🆓🆓🆓🆓🆓🆓🆓🆓🆓🆓🆓🆓
Hello Everyone,
I would like to offer my Udemy courses for FREE.
This offer is for a limited time. The only thing you need to do is thumbs up 👍 the video and Subscribe ✔ to the KGP Talkie YouTube channel.

👇 Fill this form for a free coupon

[timojeverett]

Thanks for putting this together, excellent clear introduction. I spent a little more time on the preprocessing of data and split the lines that had a missing newline so that there were two samples on each line and dealt with another couple of problems with the raw data. This resulted in about 3 times as much data over all (just over a million samples) and using your training model got an accuracy of 94% on test set after 13 epochs.
Thank you again for the time you have put into making everything so clear.

[IgorAherne]

Thank you for these tutorials. Quite hard to find tf 2.0 videos right now, you are doing a great contribution

[muhammadzubairbaloch]

Sir the great. you are highly appreciate-able. I have no words to say thanks. Great lectures.

[nirranjanrasaratnam]

Brother Could you plz tell me how to use this trained model in real time?? I'm looking forward to hear from you. Thanks

[Lucifer-enxc]

You mentioned to get the links from the description but they are not here!

[arunaslipnickas]

you should finish the code with lines to release the GPU memory. For instance:
from numba import cuda
cuda.select_device(0)
cuda.close()

[chiduralalakshmigayathri]

but your github link is showing page not found error

[Rikimkigsck]

This video helped me a lot can't thank enough!

[akashpawar]

Another video has completed sir

I saw cleaning and understanding data very typical

Training data is very easy

[chrisogonas]

Great stuff, and thanks for putting this together.

[michalpesko]

Great video, really helpful, thanks!

[ishitagupta]

Please share the architecture of the CNN model you have used

[bhaumikchaudhari]

Sir after data preprocessing and train model then next how we detect human activity can you give code for demonstration of activity from video

[riti]

Can you please provide blog link
The link that you provided is not working

[YasinShah]

great work. I really appreciate. very detailed and informative tutorial.

[damilareadeyoyin]

Great Video, how can we make predictions considering the train data has been reshaped

[hammadalitariq]

Thankyou Sir,
Can you instruct how to use this model to make predictions?

[shivanigiri]

Thank you so much . Doing great work . Keep it up

[khushboosoni]

Hello, thanks for this video. Would you suggest any videos on instance selection not feature selection?

[ayoige]

The frame segmentation method used, is that a sliding window or a fixed window technique.