Artificial Intelligence Based Approach for Classification of Human Activities Using MEMS Sensors Data
| Autor: | Mohamed Abbas, Yash Pratap Singh, Syed Imaduddin, Mohammed Usman, MOHD WAJID, Yusuf Ahmed Khan |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2023 |
| Předmět: |
human activity recognition
deep neural network deep learning Biochemistry Atomic and Molecular Physics and Optics Analytical Chemistry Bi-LSTM network machine learning recurrent neural network Electrical and Electronic Engineering mobile & wearable devices classification algorithm MEMS sensors Instrumentation |
| Zdroj: | Sensors Volume 23 Issue 3 Pages: 1275 |
| ISSN: | 1424-8220 |
| DOI: | 10.3390/s23031275 |
| Popis: | The integration of Micro Electronic Mechanical Systems (MEMS) sensor technology in smartphones has greatly improved the capability for Human Activity Recognition (HAR). By utilizing Machine Learning (ML) techniques and data from these sensors, various human motion activities can be classified. This study performed experiments and compiled a large dataset of nine daily activities, including Laying Down, Stationary, Walking, Brisk Walking, Running, Stairs-Up, Stairs-Down, Squatting, and Cycling. Several ML models, such as Decision Tree Classifier, Random Forest Classifier, K Neighbors Classifier, Multinomial Logistic Regression, Gaussian Naive Bayes, and Support Vector Machine, were trained on sensor data collected from accelerometer, gyroscope, and magnetometer embedded in smartphones and wearable devices. The highest test accuracy of 95% was achieved using the random forest algorithm. Additionally, a custom-built Bidirectional Long-Short-Term Memory (Bi-LSTM) model, a type of Recurrent Neural Network (RNN), was proposed and yielded an improved test accuracy of 98.1%. This approach differs from traditional algorithmic-based human activity detection used in current wearable technologies, resulting in improved accuracy. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
| Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |