A Random Forest Approach to Body Motion Detection: Multisensory Fusion and Edge Processing

Kianoush, Sanaz; Savazzi, Stefano; Rampa, Vittorio; Costa, Lílian Moreira; Tolochenko, Denis

doi:10.1109/jsen.2022.3232085

Cited by 14 publications

(3 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The RMSE decreases as the RIS area, A, increases. However, since A is inversely proportional to the HPBW of the RIS radiation pattern, an increase of A requires a larger number of rotation angles R to cover the area L and, hence, a higher computational effort for processing the input of the CNN [13].…”

Section: A Ue Localizationmentioning

confidence: 99%

User location uncertainty in RIS-aided channel optimization

Kianoush,

Dossi,

Nebuloni

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Section: A Ue Localizationmentioning

confidence: 99%

User location uncertainty in RIS-aided channel optimization

Kianoush,

Dossi,

Nebuloni

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Recently, it is also used in remote sensing (Belgiu & Drăguţ, 2016), body motion detection (Kianoush et al, 2023), and genetics (Murgas et al, 2023). It is an ensemble learning method where multiple DTs are combined to develop a more accurate and robust model.…”

Section: The Interplay Of Sl Techniques and Optimization Algorithmsmentioning

confidence: 99%

Trends of Optimization Algorithms from Supervised Learning Perspective

Paul

Das

2023

JCCE

View full text Add to dashboard Cite

Machine learning (ML) is rapidly evolving, leading to numerous theoretical advancements and widespread applications across multiple fields. The goal of ML is to enable machines to carry out cognitive tasks by acquiring knowledge from past encounters and resolving intricate issues despite varying circumstances that deviate from previous instances. Supervised Learning (SL) being one of the most popular type of ML has become an area of significant strategic importance due to its practical applications, data collection, and computing power's exponential growth. On the other hand, optimization is a crucial component of ML that has garnered significant attention from researchers. Numerous proposals have been made one after another for solving optimization problems or enhancing optimization techniques in the field of ML. A comprehensive review and application of optimization methods from the perspective of ML is crucial to guide the development of both optimization and ML research. This article presents information specifically on the area of SL and a wide range of optimization methods, applied in conjunction to address various scientific issues. Additionally, this article explores some of the challenges and open problems in optimizing SL models.

show abstract

“…Random Forest (RF) is a popular machine-learning algorithm for classification and regression tasks [31]. RF is an ensemble learning algorithm combining multiple decision trees to make predictions.…”

Section: H Random Forestmentioning

confidence: 99%

Preventing Road Accidents Through Early Detection of Driver Behavior Using Smartphone Motion Sensor Data: An Ensemble Feature Engineering Approach

Raza,

Akhtar,

Abualigah

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Driver behavior refers to the actions and attitudes of individuals behind the wheel of a vehicle. Poor driving behavior can have serious consequences, including accidents, injuries, and fatalities. One of the main disadvantages of poor driving behavior is the increased risk of road accidents, higher insurance premiums, fines, and even criminal charges. The primary aim of our study is to detect driver behavior early with high-performance scores. The publicly available smartphone motion sensor data is utilized to conduct our study experiments. A novel LR-RFC (Logistic Regression Random Forest Classifier) method is proposed for feature engineering. The proposed LR-RFC method combines the logistic regression and random forest classifier for feature engineering from the motion sensor data. The original smartphone motion sensor data is input into the LR-RFC method, generating new probabilistic features. The newly extracted probabilistic features are then input to the applied machine learning methods for predicting driver behavior. The study results show that the proposed LR-RFC approach achieves the highest performance score. Extensive study experiments demonstrate that the random forest achieved the highest performance score of 99% using the proposed LR-RFC method. The performance is validated using k-fold cross-validation and hyperparameter optimization. Our novel proposed study has the potential to revolutionize the early detection of driver behavior to avoid road accidents.INDEX TERMS Machine learning, driver behavior, sensor data, feature engineering, ensemble learning.

show abstract

A Random Forest Approach to Body Motion Detection: Multisensory Fusion and Edge Processing

Cited by 14 publications

References 51 publications

User location uncertainty in RIS-aided channel optimization

User location uncertainty in RIS-aided channel optimization

Trends of Optimization Algorithms from Supervised Learning Perspective

Preventing Road Accidents Through Early Detection of Driver Behavior Using Smartphone Motion Sensor Data: An Ensemble Feature Engineering Approach

Contact Info

Product

Resources

About