Dimensionality Reduction for Human Activity Recognition Using Google Colab

Abstract

Human activity recognition (HAR) is a classification task that involves predicting the movement of a person based on sensor data. As we can see, there has been a huge growth and development of smartphones over the last 10–15 years—they could be used as a medium of mobile sensing to recognize human activity. Nowadays, deep learning methods are in a great demand and we could use those methods to recognize human activity. A great way is to build a convolutional neural network (CNN). HAR using Smartphone dataset has been widely used by researchers to develop machine learning models to recognize human activity. The dataset has two parts: training and testing. In this paper, we propose a hybrid approach to analyze and recognize human activity on the same dataset using deep learning method on cloud-based platform. We have applied principal component analysis on the dataset to get the most important features. Next, we have executed the experiment for all the features as well as the top 48, 92, 138, and 164 features. We have run all the experiments on Google Colab. In the experiment, for the evaluation of our proposed methodology, datasets are split into two different ratios such as 70–10–20% and 80–10–10% for training, validation, and testing, respectively. We have set the performance of CNN (70% training–10% validation–20% testing) with 48 features as a benchmark for our work. In this work, we have achieved maximum accuracy of 98.70% with CNN. On the other hand, we have obtained 96.36% accuracy with the top 92 features of the dataset. We can see from the experimental results that if we could select the features properly then not only could the accuracy be improved but also the training and testing time of the model.

Dynamic and Distributed Intelligence over Smart Devices, Internet of Things Edges, and Cloud Computing for Human Activity Recognition Using Wearable Sensors

“…In our approach, the reduced datasets used fewer entries with the same number of features; the 40,000-entry dataset was enough to capture the required characteristics of the dataset with adequate accuracy. Other researchers, such as the authors of [39], proposed reduced datasets for activity recognition with fewer features and entries, and they achieved 96.36% accuracy using only half the size of the dataset, compared to 98.7% when all the features and entries were used.…”

Performance Comparison K-Nearest Neighbor, Naive Bayes, and Decision Tree Algorithms for Netflix Rating Classification

“…Google Colab is increasingly used in educational and training environments due to its focus on knowledge dissemination and research in the field of machine learning [21]. With Google Collab, developers can create, modify and run code using Python programming languages such as NumPy and Matplotlib for data analysis and visualization [22].…”

3D Convolutional Neural Networks based Movement Evaluation System for Gymnasts in Computer Vision Applications

“…Action Units-based classification proves effective for objective microexpression recognition. In [17], a hybrid approach using deep learning on a smartphone dataset for human activity recognition, achieving 98.70% accuracy with CNN and 96.36% accuracy with top 92 features. Feature selection significantly improves accuracy and model efficiency, demonstrated through experimental results.…”