Human Activity Recognition (HAR) has become increasingly important due to the widespread use of sensor-equipped devices and large datasets. This paper evaluates the performance of three categories of models: classical machine learning, deep learning architectures, and Restricted Boltzmann Machines (RBMs) using five key benchmark datasets of HAR (UCI-HAR, OPPORTUNITY, PAMAP2, WISDM, and Berkeley MHAD). Various models including Decision Trees, Random Forests, Convolutional Neural Networks (CNN), and Deep Belief Networks (DBNs) are assessed using metrics such as accuracy, precision, recall, and F1-score for a comprehensive comparison. The results indicate that CNN models demonstrate superior performance across all datasets, particularly excelling on the Berkeley MHAD dataset. Classical models like Random Forest perform well on smaller datasets but face challenges with larger and more complex data. RBM-based models show promise for feature learning. This paper offers a detailed comparison to assist researchers in selecting the most suitable model for HAR tasks. The subsequent sections delve into the state-of-the-art in HAR research starting from traditional machine learning techniques to the evolution of deep learning models and recent advancements with generative models. The methodology section details data collection and preparation processes as well as model selection and configuration. Performance evaluations of each model on multiple datasets are presented in detail. Additionally, prior studies related to activity recognition systems are reviewed to provide context on the development of HAR methodologies. Early works focused on classification and recognition using classical machine learning methods while recent studies have explored various machine learning models including Decision Trees, Random Forests, Gradient Boosting DTs, Logistic regression Linear SVCs,and RBF SVM classifiers for identifying human activities in daily life. Furthermore,d eep learning methodologies have been applied for feature extraction in conjunction with traditional machine learning classifiers to enhance activity recognition accuracy. Traditional machine learning algorithms excel in scenarios where interpretability is crucial but may struggle with understanding complex patterns over time. In contrast, deep learning approaches have shown promise in automatically learning from raw data and comprehending intricate patterns that evolve over time. In conclusion, the performance evaluation of various models on multiple benchmark datasets highlights the superiority of CNN models for HAR tasks. However, RBM-based models show potential for feature learning and traditional machine learning algorithms still have their place in scenarios where interpretability is key. The paper provides a comprehensive comparison to aid researchers in selecting the most suitable model for their specific HAR task.
- Human Activity Recognition (HAR) is important due to sensor-equipped devices and large datasets
- Evaluation of three model categories: classical machine learning, deep learning architectures, and Restricted Boltzmann Machines (RBMs)
- Assessment of various models including Decision Trees, Random Forests, CNNs, and DBNs using key benchmark datasets
- CNN models demonstrate superior performance across datasets, especially on the Berkeley MHAD dataset
- RBM-based models show promise for feature learning
- Traditional machine learning models like Random Forest perform well on smaller datasets but struggle with larger and complex data
- Deep learning approaches excel in understanding complex patterns over time
- Paper provides a detailed comparison to help researchers choose the most suitable model for HAR tasks
Summary- Human Activity Recognition (HAR) is about understanding how people move using special devices and lots of information.
- Scientists looked at different types of models to see which one is best for recognizing human activities.
- They tested models like Decision Trees, Random Forests, CNNs, and RBMs on important datasets.
- CNN models did very well in recognizing activities, especially on a specific dataset called Berkeley MHAD.
- RBM-based models also did well in learning important features for recognizing activities.
Definitions
- Human Activity Recognition (HAR): Understanding how people move and what they are doing using technology.
- Datasets: Collections of information or data used for testing and studying.
- Models: Different ways or methods used to understand and analyze data.
- Restricted Boltzmann Machines (RBMs): A type of model used in machine learning to learn patterns in data.
Human Activity Recognition (HAR) has become increasingly important due to the widespread use of sensor-equipped devices and large datasets. This paper evaluates the performance of three categories of models: classical machine learning, deep learning architectures, and Restricted Boltzmann Machines (RBMs) using five key benchmark datasets of HAR.
Introduction:
The introduction section provides an overview of the importance of HAR in today's world and introduces the main focus of this research paper - evaluating the performance of various models for HAR tasks. It also mentions the five benchmark datasets that will be used for comparison.
State-of-the-art in HAR Research:
This section delves into previous studies related to activity recognition systems, providing context on the development of methodologies for HAR. Early works focused on classification and recognition using classical machine learning methods while recent studies have explored various machine learning models including Decision Trees, Random Forests, Gradient Boosting DTs, Logistic regression Linear SVCs,and RBF SVM classifiers for identifying human activities in daily life. Furthermore,d eep learning methodologies have been applied for feature extraction in conjunction with traditional machine learning classifiers to enhance activity recognition accuracy.
Methodology:
The methodology section details data collection and preparation processes as well as model selection and configuration. It explains how each dataset was collected and preprocessed before being used for training and testing different models. The process of selecting appropriate models based on their strengths and weaknesses is also described.
Performance Evaluation:
In this section, the results from evaluating each model on multiple datasets are presented in detail. Metrics such as accuracy, precision, recall, and F1-score are used to compare the performance of different models across all five benchmark datasets. The findings show that CNN models demonstrate superior performance overall but RBM-based models show potential for feature learning.
Comparison between Models:
This section offers a detailed comparison between classical machine learning algorithms like Decision Trees and Random Forests versus deep learning architectures like CNNs and DBNs. It highlights their strengths and weaknesses in terms of performance on HAR tasks. It also discusses the challenges faced by classical models when dealing with larger and more complex data.
Conclusion:
In conclusion, the paper summarizes the key findings from the performance evaluation of various models on multiple benchmark datasets. It highlights the superiority of CNN models for HAR tasks but also acknowledges the potential of RBM-based models for feature learning. The paper emphasizes that traditional machine learning algorithms still have their place in scenarios where interpretability is crucial.
Overall, this research paper provides a comprehensive comparison between different categories of models for HAR tasks. It offers valuable insights into which model may be most suitable for specific HAR applications based on their performance on different datasets. This can aid researchers in selecting an appropriate model for their own projects and contribute to further advancements in HAR research.
