A novel representation in genetic programming for ensemble classification of human motions based on inertial signals

Sepahvand, Majid; Abdali-Mohammadi, Fardin

doi:10.1016/j.eswa.2021.115624

Cited by 14 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They achieved an 80% f1-score on the RealDisp dataset. Sepahvand et al presented a flexible ensemble tree based on genetic programming (ETGP) approach for HAR [59]. To reduce the general complexity in the process of designing the proposed classifier, an initial population of binary trees (genes) is first created and then enhanced through genetic programming to select the best classifier.…”

Section: Confusion Matricesmentioning

confidence: 99%

“…When comparing the experimental results of the proposed CNN-LSTM-LF model with the available research work, it can be noticed that the proposed LF approach gives comparable results. RealDisp CNN CNN with block-wise smoothing [28] 2017 90.1 92.8 Wavelet transform and pooling operator [57] 2019 81.7 SMART [58] 2020 80 ETGP [59] 2021 91 CNN-LSTM-LF (proposed) 92.15…”

Section: Confusion Matricesmentioning

confidence: 99%

“…2L-CNN 3L-CNN [20] 2017 86 85 Attention model [32] 2018 87.5 ETGP [59] 2021 91 3-layer CNN + C3 [60] 2021 91.93 iSPLInception [22] 2021 89 CNN-LSTM-LF (proposed) 93.78…”

Section: Pamap2mentioning

confidence: 99%

See 2 more Smart Citations

CNN-LSTM-Based Late Sensor Fusion for Human Activity Recognition in Big Data Networks

Baloch

Shaikh

Unar

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

The technological advancement in sensor technology and pervasive computing has brought smart devices into our daily life. Due to the continuous connectivity of the internet with our everyday devices, researchers can deploy IoT sensors to health care and other applications, such as human activity recognition. Most of the state-of-the-art sensor-based human activity recognition systems can detect basic activities (such as standing, sitting, and walking), but they cannot accurately distinguish similar activities (ascending stairs or descending stairs). Such systems are not efficient for critical healthcare applications having complex activity sets. This paper proposes two sensor fusion approaches, i.e., position-based early and late sensor fusion using convolutional neural network (CNN) and convolutional long-short-term memory (CNN-LSTM). The performance of our proposed models is evaluated on two publicly available datasets. We also evaluated the effect of different normalization techniques on recognition accuracy. Our results show that the CNN-LSTM-based late sensor fusion model also improves the recognition accuracy of similar activities.

show abstract

Section: Confusion Matricesmentioning

confidence: 99%

Section: Confusion Matricesmentioning

confidence: 99%

See 1 more Smart Citation

CNN-LSTM-Based Late Sensor Fusion for Human Activity Recognition in Big Data Networks

Baloch

Shaikh

Unar

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…EEG has been used for many years as a reliable method to diagnose various brain diseases [8]. However, each patient has a personal and security framework that is not allowed to enter by any research organization [9]- [13]. So, accurate statistics of these patients are needed for a specific classification of their disease type to access the data of different centers and to classify the general patients in a country or province to provide medical services.…”

Section: Introductionmentioning

confidence: 99%

Classification of electroencephalography using cooperative learning based on participating client balancing

Meqdad

Husain

Jawad

et al. 2023

IJECE

View full text Add to dashboard Cite

<span lang="EN-US">Modern technologies are widely used today to diagnose epilepsy, neurological disorders, and brain tumors. Meanwhile, it is not cost-effective in terms of time and money to use a large amount of electroencephalography (EEG) data from different centers and collect them in a central server for processing and analysis. Collecting this data correctly is challenging, and organizations avoid sharing their and client information with others due to data privacy protection. It is difficult to collect these data correctly and it is challenging to transfer them to research centers due to the privacy of the data. In this regard, collaborative learning as an extraordinary approach in this field paves the way for the use of information repositories in research matters without transferring the original data to the centers. This study focuses on the use of a heterogeneous client balancing technique with an interval selection approach and classification of EEG signals with ResNet50 deep architecture. The test results achieved an accuracy of 99.14 compared to similar methods.</span>

show abstract

“…Inertial sensors such as gyroscopes, accelerometers, and magnetometers are widely used in various fields, including human activities and patient monitoring [1], [2], sports activities [3], and Persian character recognition due to the development of their manufacturing technology, cheapness, portability, wearability, and support for various communication protocols, e.g., Wi-Fi and Bluetooth. These sensors have advantages in the field of human activities, including the posiibility of attaching them to certain parts of the body and easily collecting valuable data from people's daily activities such as sitting, walking, jumping, and cycling.…”

Section: Introductionmentioning

confidence: 99%

Human activity recognition method using joint deep learning and acceleration signal

Meqdad

Hussein²,

Husain

et al. 2023

IJ-AI

View full text Add to dashboard Cite

Many studies have been conducted on human activity recognition (HAR) in the last decade. Accordingly, deep learning (DL) algorithms have been given more attention in terms of classification of human daily activities. Deep neural networks (DNNs) compute and extract complex features on voluminous data through some hidden layers that require large memory and powerful graphics processing units (GPUs). So, this study proposes a new joint learning (JL) approach to classify human activities using inertial sensors. To this end, a large complex donor model based on a convolutional neural network (CNN) is used to transfer knowledge to a smaller model based on CNN referred to as the acceptor model. The acceptor model can be deployed on mobile devices and low-power hardware due to decreased computing costs and memory consumption. The wireless sensor data mining (WISDM) dataset is used to test the proposed model. According to the experimental results, the HAR system based on the JL algorithm outperforms than other methods.

show abstract

A novel representation in genetic programming for ensemble classification of human motions based on inertial signals

Cited by 14 publications

References 32 publications

CNN-LSTM-Based Late Sensor Fusion for Human Activity Recognition in Big Data Networks

CNN-LSTM-Based Late Sensor Fusion for Human Activity Recognition in Big Data Networks

Classification of electroencephalography using cooperative learning based on participating client balancing

Human activity recognition method using joint deep learning and acceleration signal

Contact Info

Product

Resources

About