A correlation-based binary particle swarm optimization method for feature selection in human activity recognition

Ke, Ruomeng; Li, Junhuai; An, Yang; Wang, Kan; Lei, Yu

doi:10.1177/1550147718772785

Cited by 17 publications

(11 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is a population-oriented method that is inspired by animals and fish social behavior. The standard PSO algorithm [ 20 ] is the one used for basic optimization of parameters. EPSO proposed by Li et al [ 21 ] is considered to be PSO's most renowned variant.…”

Section: Introductionmentioning

confidence: 99%

Optimization of Correlation Filters Using Extended Particle Swarm Optimization Technique

Masood

Zafar

Ali

et al. 2021

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

In the past few decades, the field of image processing has seen a rapid advancement in the correlation filters, which serves as a very promising tool for object detection and recognition. Mostly, complex filter equations are used for deriving the correlation filters, leading to a filter solution in a closed loop. Selection of optimal tradeoff (OT) parameters is crucial for the effectiveness of correlation filters. This paper proposes extended particle swarm optimization (EPSO) technique for the optimal selection of OT parameters. The optimal solution is proposed based on two cost functions. The best result for each target is obtained by applying the optimization technique separately. The obtained results are compared with the conventional particle swarm optimization method for various test images belonging from different state-of-the-art datasets. The obtained results depict the performance of filters improved significantly using the proposed optimization method.

show abstract

Section: Introductionmentioning

confidence: 99%

Optimization of Correlation Filters Using Extended Particle Swarm Optimization Technique

Masood

Zafar

Ali

et al. 2021

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

show abstract

“…Different feature selection approaches can be found in literature (Table 4). Embedded approach-based methods completely remove noise and irrelevant features with filter-based methods, and create an optimal feature set using the wrapper-based method [79]. In this way, the high efficiency of the filter model is combined with the high accuracy of the wrapper model [79].…”

Section: Impact Of Human Activity Recognition (Har) Stages On Enermentioning

confidence: 99%

“…Pattern-based methods are classified as supervised and unsupervised learning techniques. The most known supervised learning techniques include k-Nearest Neighbors (kNN) [4,18,71,91], Decision Tree (DT) [26,87,92,93,94], Decision Table [11], Random Forests (RF) [7,83], Naive Bayes (NB) [15,79,83,87,95,96] and Support Vector Machine (SVM) [2,12,33,34,58,60,76,79,81,83,88,97,98,99,100]. Classification techniques have been summarized in Figure 2.…”

Section: Impact Of Human Activity Recognition (Har) Stages On Enermentioning

confidence: 99%

Step by Step Towards Effective Human Activity Recognition: A Balance between Energy Consumption and Latency in Health and Wellbeing Applications

Dinarevic

Husić

Baraković

2019

Sensors

View full text Add to dashboard Cite

Human activity recognition (HAR) is a classification process that is used for recognizing human motions. A comprehensive review of currently considered approaches in each stage of HAR, as well as the influence of each HAR stage on energy consumption and latency is presented in this paper. It highlights various methods for the optimization of energy consumption and latency in each stage of HAR that has been used in literature and was analyzed in order to provide direction for the implementation of HAR in health and wellbeing applications. This paper analyses if and how each stage of the HAR process affects energy consumption and latency. It shows that data collection and filtering and data segmentation and classification stand out as key stages in achieving a balance between energy consumption and latency. Since latency is only critical for real-time HAR applications, the energy consumption of sensors and devices stands out as a key challenge for HAR implementation in health and wellbeing applications. Most of the approaches in overcoming challenges related to HAR implementation take place in the data collection, filtering and classification stages, while the data segmentation stage needs further exploration. Finally, this paper recommends a balance between energy consumption and latency for HAR in health and wellbeing applications, which takes into account the context and health of the target population.

show abstract

“…[41,42]. Finally, different FS methods were used to reduce the number of variables without any transformation, such as Minimum Redundancy Maximum Relevance [43], recursive feature elimination [34], Information Gain [25], or evolutionary algorithms [44].…”

Section: Related Workmentioning

confidence: 99%

“…Since the aim of a HAR application is to identify the performed activity, a proper learning algorithm must be applied as final step. The great majority of the studies in this fields was based on supervised learning algorithms, ranging from machine learning (support vector machine [33], decision tree [27], random forest [32], multilayer perceptron [44],…) to the emerging deep learning neural networks [45,46,47]. However, sporadic applications of unsupervised learning algorithms were proposed [48].…”

Section: Related Workmentioning

confidence: 99%

Comparison of Different Sets of Features for Human Activity Recognition by Wearable Sensors

Rosati

Balestra

Knaflitz

2018

Sensors

View full text Add to dashboard Cite

Human Activity Recognition (HAR) refers to an emerging area of interest for medical, military, and security applications. However, the identification of the features to be used for activity classification and recognition is still an open point. The aim of this study was to compare two different feature sets for HAR. Particularly, we compared a set including time, frequency, and time-frequency domain features widely used in literature (FeatSet_A) with a set of time-domain features derived by considering the physical meaning of the acquired signals (FeatSet_B). The comparison of the two sets were based on the performances obtained using four machine learning classifiers. Sixty-one healthy subjects were asked to perform seven different daily activities wearing a MIMU-based device. Each signal was segmented using a 5-s window and for each window, 222 and 221 variables were extracted for the FeatSet_A and FeatSet_B respectively. Each set was reduced using a Genetic Algorithm (GA) simultaneously performing feature selection and classifier optimization. Our results showed that Support Vector Machine achieved the highest performances using both sets (97.1% and 96.7% for FeatSet_A and FeatSet_B respectively). However, FeatSet_B allows to better understand alterations of the biomechanical behavior in more complex situations, such as when applied to pathological subjects.

show abstract

A correlation-based binary particle swarm optimization method for feature selection in human activity recognition

Cited by 17 publications

References 53 publications

Optimization of Correlation Filters Using Extended Particle Swarm Optimization Technique

Optimization of Correlation Filters Using Extended Particle Swarm Optimization Technique

Step by Step Towards Effective Human Activity Recognition: A Balance between Energy Consumption and Latency in Health and Wellbeing Applications

Comparison of Different Sets of Features for Human Activity Recognition by Wearable Sensors

Contact Info

Product

Resources

About