Filters








1,982 Hits in 5.6 sec

Comparison Study of Inertial Sensor Signal Combination for Human Activity Recognition based on Convolutional Neural Networks [article]

Farhad Nazari, Navid Mohajer, Darius Nahavandi, Abbas Khosravi, Saeid Nahavandi
2022 arXiv   pre-print
A model based on Convolutional Neural Networks (CNN) has been proposed and trained on different signal combinations of three Inertial Measurement Units (IMU) that exhibit the movements of the dominant  ...  Human Activity Recognition (HAR) is one of the essential building blocks of so many applications like security, monitoring, the internet of things and human-robot interaction.  ...  We proposed a model based on Deep Convolutional Neural Networks (DCNN) to achieve the best performance. Convolutional layers are capable of extracting the local features of the signal.  ... 
arXiv:2206.04480v1 fatcat:6btfxib4vbh4bkvsdazev5k2ae

Inception-LSTM Human Motion Recognition with Channel Attention Mechanism

Yongtao Xu, Liye Zhao, Naeem Jan
2022 Computational and Mathematical Methods in Medicine  
the LSTM network to further extract the temporal features of the inertial sensor signals to achieve the classification and recognition of human motion posture.  ...  An improved channel attention mechanism Inception-LSTM human motion recognition algorithm for inertial sensor signals is proposed to address the problems of high cost, many blind areas, and susceptibility  ...  The algorithm put forward here is based on the original ECA module and combines the application context of human motion recognition with inertial sensor signals, adding a channel feature extraction module  ... 
doi:10.1155/2022/9173504 pmid:35734775 pmcid:PMC9208947 fatcat:poig2dfcpzdhnf4vndawopkkhm

Human activity recognition with inertial sensors using a deep learning approach

Tahmina Zebin, Patricia J Scully, Krikor B. Ozanyan
2016 2016 IEEE SENSORS  
Our focus in this research is on the use of deep learning approaches for human activity recognition (HAR) scenario, in which inputs are multichannel time series signals acquired from a set of body-worn  ...  inertial sensors and outputs are predefined human activities.  ...  Here, instead of exploring hand-crafted features from time-series sensor signals, we aim to show that signal sequences of accelerometers and gyroscopes can be processed by Deep Convolutional Neural Networks  ... 
doi:10.1109/icsens.2016.7808590 fatcat:7hb6cbh2zfexhbqq6ckwit3gie

A Machine Vision Approach to Human Activity Recognition using Photoplethysmograph Sensor Data

Eoin Brophy, Jose Juan Dominguez, Zhengwei Wang, Tomas E. Ward
2018 2018 29th Irish Signals and Systems Conference (ISSC)  
We adopt a machine vision approach for activity recognition based on plots of the optical signals so as to produce classifications that are easily explainable and interpretable by nontechnical users.  ...  Human activity recognition (HAR) is an active area of research concerned with the classification of human motion.  ...  INTRODUCTION Due to the ubiquitous nature of inertial and physiological sensors in phones and fitness trackers, human activity recognition (HAR) studies have become more frequent [1] , [2] .  ... 
doi:10.1109/issc.2018.8585372 fatcat:ohntcameujctnaqqsgkcz24odu

Towards Improved Human Action Recognition Using Convolutional Neural Networks and Multimodal Fusion of Depth and Inertial Sensor Data [article]

Zeeshan Ahmad, Naimul Khan
2020 arXiv   pre-print
Then, inertial data is converted into Signal Images (SI) and another convolutional neural network (CNN) is trained on these images.  ...  This paper attempts at improving the accuracy of Human Action Recognition (HAR) by fusion of depth and inertial sensor data.  ...  In [23] the performance of state-of-the-art deep learning models, convolutional neural network and recurrent neural network, for human activity recognition using inertial sensors are rigorously explored  ... 
arXiv:2008.09747v1 fatcat:gheuxioiprcura5kvsuqz3em2y

Human Activity Recognition with Convolutional Neural Networks [chapter]

Antonio Bevilacqua, Kyle MacDonald, Aamina Rangarej, Venessa Widjaya, Brian Caulfield, Tahar Kechadi
2019 Lecture Notes in Computer Science  
In this paper, we propose to use Convolutional Neural Networks (CNNs) to classify human activities. Our models use raw data obtained from a set of inertial sensors.  ...  We explore several combinations of activities and sensors, showing how motion signals can be adapted to be fed into CNNs by using different network architectures.  ...  [2] introduce a first approach to HAR based on deep learning models. They generate a spectrogram image from an inertial signal, in order to feed real images to a convolutional neural network.  ... 
doi:10.1007/978-3-030-10997-4_33 fatcat:uf3t7dgrwfbefiktpbjgwtrxwe

An Efficient and Lightweight Deep Learning Model for Human Activity Recognition Using Smartphones

Ankita, Shalli Rani, Himanshi Babbar, Sonya Coleman, Aman Singh, Hani Moaiteq Aljahdali
2021 Sensors  
In this paper, convolutional layers are combined with long short-term memory (LSTM), along with the deep learning neural network for human activities recognition (HAR).  ...  In general, LSTM is alternative form of recurrent neural network (RNN) which is famous for temporal sequences' processing.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s21113845 fatcat:jrkcvtqckfd4dgazehigzg2e5e

Gait Neural Network for Human-Exoskeleton Interaction

Bin Fang, Quan Zhou, Fuchun Sun, Jianhua Shan, Ming Wang, Cheng Xiang, Qin Zhang
2020 Frontiers in Neurorobotics  
To optimize human-exoskeleton interaction, this article proposes a gait recognition and prediction model, called the gait neural network (GNN), which is based on the temporal convolutional network.  ...  The performance of the GNN is evaluated based on the publicly available HuGaDB dataset, as well as on data collected by an inertial-based wearable motion capture device.  ...  Further, recent works have reported the use of convolutional neural networks (CNNs) for human activity recognition.  ... 
doi:10.3389/fnbot.2020.00058 pmid:33192431 pmcid:PMC7658381 fatcat:vbspn7tvdbd3dkxxenc5y7b2oy

Improving the Ambient Intelligence Living Using Deep Learning Classifier

Yazeed Yasin Ghadi, Mouazma Batool, Munkhjargal Gochoo, Suliman A. Alsuhibany, Tamara al Shloul, Ahmad Jalal, Jeongmin Park
2022 Computers Materials & Continua  
We assessed the performance of our proposed system on the publicly accessible human gait database (HuGaDB) benchmark dataset and achieved an accuracy rates of 93.95 percent, respectively.  ...  In this paper, we have proposed a novel AAL solution using a hybrid bidirectional long-term and short-term memory networks (BiLSTM) and convolutional neural network (CNN) classifier.  ...  [23] utilized long shortterm memory and convolutional neural network (LSTM-CNN) based architecture for recognition of human activities.  ... 
doi:10.32604/cmc.2022.027422 fatcat:b2hmpl5hlndpnk25zptkqympna

Iss2Image: A Novel Signal-Encoding Technique for CNN-Based Human Activity Recognition

Taeho Hur, Jaehun Bang, Thien Huynh-The, Jongwon Lee, Jee-In Kim, Sungyoung Lee
2018 Sensors  
In this paper, we propose an efficient human activity recognition method, namely Iss2Image (Inertial sensor signal to Image), a novel encoding technique for transforming an inertial sensor signal into  ...  Among the various deep learning methods, convolutional neural networks (CNNs) have the advantages of local dependency and scale invariance and are suitable for temporal data such as accelerometer (ACC)  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s18113910 fatcat:557hm24lnjgozcwip7aom6tpiy

An efficient human activity recognition model based on deep learning approaches

Aymen Jalil Abdulelah, Mohannad Al-Kubaisi, Ahmed Muhi Shentaf
2022 Indonesian Journal of Electrical Engineering and Informatics (IJEEI)  
The generic HAR framework for smartphone sensor data is proposed, based on Long Short-Term Memory (LSTM) networks for time-series domains and standard Convolutional Neural Network (CNN) used for classification  ...  Human Activity Recognition (HAR) has gained traction in recent years in diverse areas such as observation, entertainment, teaching and healthcare, using wearable and smartphone sensors.  ...  Another study by Wan et al, aims to present an infrastructure based on a phone inertial sensor for HAR.  ... 
doi:10.52549/ijeei.v10i1.3438 fatcat:fylgzdw7u5ddvcfhmvumyvaimi

Human Daily Activity Recognition Performed Using Wearable Inertial Sensors Combined With Deep Learning Algorithms

Chih-Ta Yen, Jia-Xian Liao, Yi-Kai Huang
2020 IEEE Access  
ACKNOWLEDGMENT This work was supported in part by the Ministry of Science and Technology MOST 108-2221-E-150-022-MY3 and National Formosa University 107AF06.  ...  Wearable devices combining embedded systems and inertial sensors have been developed for activity recognition and are used in daily life and sports activities.  ...  Lee et al. proposed a method based on 1D convolutional neural networks (CNNs); 3-axis accelerometers in users' smartphones were collected to identify walking, running, and no motions.  ... 
doi:10.1109/access.2020.3025938 fatcat:jfmp7wmsxvb2rh75yazwfxxlou

Deep learning for human activity recognition: A resource efficient implementation on low-power devices

Daniele Ravi, Charence Wong, Benny Lo, Guang-Zhong Yang
2016 2016 IEEE 13th International Conference on Wearable and Implantable Body Sensor Networks (BSN)  
In this paper, a human activity recognition technique based on a deep learning methodology is designed to enable accurate and real-time classification for low-power wearable devices.  ...  A systematic analysis of the feature generation parameters and a comparison of activity recognition computation times on mobile devices and sensor nodes are also presented.  ...  For many years, machine learning and pattern recognition techniques for sensor-based classification of human activity have been focused on the design and use of "shallow" features that are task dependent  ... 
doi:10.1109/bsn.2016.7516235 dblp:conf/bsn/RaviWLY16 fatcat:cczyz2r3grdatknepcn7ymu3u4

Adaptive Recognition of Motion Posture in Sports Video Based on Evolution Equation

Rui Yuan, Zhendong Zhang, Yanyan Le, Enqing Chen, Miaochao Chen
2021 Advances in Mathematical Physics  
In this paper, inertial sensor technology is applied to attitude recognition in motion.  ...  The human body movements embodied in sports are more complicated, and the accurate recognition of sports postures plays an active and important role in sports competitions and training.  ...  human body gesture recognition method based on inertial sensor.  ... 
doi:10.1155/2021/2148062 fatcat:4d3zswpasja4zax47knmcuisse

An Efficient ResNetSE Architecture for Smoking Activity Recognition from Smartwatch

Narit Hnoohom, Sakorn Mekruksavanich, Anuchit Jitpattanakul
2023 Intelligent Automation and Soft Computing  
A deep learning framework for smoking activity recognition (SAR) employing smartwatch sensors was proposed together with a deep residual network combined with squeeze-and-excitation modules (ResNetSE)  ...  The proposed model was tested against basic convolutional neural networks (CNNs) and recurrent neural networks (LSTM, BiLSTM, GRU and BiGRU) to recognize smoking and other similar activities such as drinking  ...  Conflicts of Interest: The authors declare that they have no conflicts of interest to report regarding the present study.  ... 
doi:10.32604/iasc.2023.028290 fatcat:pxkcax6najgnzdzjn3qzrqq2h4
« Previous Showing results 1 — 15 out of 1,982 results