Filters








26,807 Hits in 6.9 sec

Low-Cost and Device-Free Human Activity Recognition Based on Hierarchical Learning Model

Jing Chen, Xinyu Huang, Hao Jiang, Xiren Miao
2021 Sensors  
In this paper, a novel hierarchical deep learning-based methodology equipped with low-cost sensors is proposed for high-accuracy device-free human activity recognition.  ...  The proposed hierarchical learning method provides a low-cost sensor-based HAR framework to enhance the recognition accuracy and modeling efficiency.  ...  System Overview Aiming to produce low-cost, lightweight and high-precision human activity recognition, we proposed a novel hierarchical recognition framework based on WiFi-RSSI wireless sensing information  ... 
doi:10.3390/s21072359 pmid:33800704 fatcat:ohis4uevujc7fptxqnitwhtzey

Activity recognition with smartphone sensors

Xing Su, Hanghang Tong, Ping Ji
2014 Tsinghua Science and Technology  
User, device and orientation independent human activity recognition on mobile phones: challenges and a proposal.[16] J.-g. Park, A. Patel, D. Curtis, S. Teller, and J. Ledlie.  ...  KNN HMM SVM Noise Sensitivity Cross-Person Adaption Model Update Computation Cost Transition Model Hierarchical Structure Other Classifiers  Gaussian Mixed Model  Artificial  ...  Activity Complexity  Multi tasks at the same time Only  ... 
doi:10.1109/tst.2014.6838194 fatcat:yk3rhrspmbg6leesksbydiot2a

Hierarchical Coherent Anomaly Fall Detection Low Bandwidth System with Combination of Wearable Sensors for Identifying Behavioral Abnormalities

Jilan Zhou, Yanmin Zhao
2020 IEEE Access  
This paper introduces Hierarchical Coherent Anomaly Fall Detection Low Bandwidth System (HCAFDLBS) to effectively identify behavioral abnormalities in human life based on data obtained from wearable sensors  ...  This technique relies on a hierarchical analytical network for the detection of complex behavior; the maximum approximate algorithm and the smoothing Laplace method are used to learn anomaly detection  ...  recognition function as threshold and machine-based learning.  ... 
doi:10.1109/access.2020.3012001 fatcat:pywsfijx3vczhatkad6qf2fcly

Hierarchical Deep Learning Architecture For 10K Objects Classification [article]

Atul Laxman Katole, Krishna Prasad Yellapragada, Amish Kumar Bedi, Sehaj Singh Kalra, Mynepalli Siva Chaitanya
2015 arXiv   pre-print
Evolution of visual object recognition architectures based on Convolutional Neural Networks & Convolutional Deep Belief Networks paradigms has revolutionized artificial Vision Science.  ...  We propose a two level hierarchical deep learning architecture inspired by divide & conquer principle that decomposes the large scale recognition architecture into root & leaf level model architectures  ...  ACKNOWLEDGEMENTS We take this opportunity to express gratitude and deep regards to our mentor Dr. Shankar M Venkatesan for his guidance and constant encouragement.  ... 
arXiv:1509.01951v1 fatcat:zm6636eulfgcpgn3qgai36tpke

Harnessing Commodity Wearable Devices to Capture Learner Engagement

Yu Lu, Jingjing Zhang, Baoping Li, Penghe Chen, Zijun Zhuang
2019 IEEE Access  
We thus designed a hassle-free and non-intrusive system running on the latest wrist-worn commodity wearable devices, which adopts the latest activity recognition and sensor data fusion techniques.  ...  fine-grained learning activities (e.g., writing notes or raising the hand in class).  ...  devices, which can be used to conduct human activity recognition and complicated data analytics tasks.  ... 
doi:10.1109/access.2019.2895874 fatcat:7linnmchwneepie4qz7v6z7kma

Examining sensor-based physical activity recognition and monitoring for healthcare using Internet of Things: A systematic review

Jun Qi, Po Yang, Atif Waraich, Zhikun Deng, Youbing Zhao, Yun Yang
2018 Journal of Biomedical Informatics  
A B S T R A C T Due to importantly beneficial effects on physical and mental health and strong association with many rehabilitation programs, Physical Activity Recognition and Monitoring (PARM) have been  ...  Traditional methods for PARM focus on controlled environments with the aim of increasing the types of identifiable activity subjects complete and improving recognition accuracy and system robustness by  ...  It follows a hierarchical structure containing two layers which are HMMs (Hidden Markov Models) and BNs (Bayes Networks) on the bottom and CFGs (Context Free Grammars) on the top.  ... 
doi:10.1016/j.jbi.2018.09.002 fatcat:q3czymzv7vg3nepy2xgtswegn4

A Survey on Ambient-Assisted Living Tools for Older Adults

Parisa Rashidi, Alex Mihailidis
2013 IEEE journal of biomedical and health informatics  
The aging population, the increasing cost of formal health care, the caregiver burden, and the importance that the individuals place on living independently, all motivate development of innovative-assisted  ...  In this survey, we will summarize the emergence of 'ambient-assisted living" (AAL) tools for older adults based on ambient intelligence paradigm.  ...  Syntactic approaches use grammar syntax such as stochastic context-free grammar to model sequential activities, and description-based approaches represent human activities in terms of logical structures  ... 
doi:10.1109/jbhi.2012.2234129 pmid:24592460 fatcat:lrdkh7wgmfgpdbze2up3bk4bxy

Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities [article]

Kaixuan Chen, Dalin Zhang, Lina Yao, Bin Guo, Zhiwen Yu, Yunhao Liu
2021 arXiv   pre-print
In this study, we present a survey of the state-of-the-art deep learning methods for sensor-based human activity recognition.  ...  The vast proliferation of sensor devices and Internet of Things enables the applications of sensor-based activity recognition.  ...  Therefore, it is essential and challenging to resolve the issue of high computation cost to realize real-time and reliable human activity recognition on mobile devices by deep learning models. 3.9.1 Layer  ... 
arXiv:2001.07416v2 fatcat:km2b3xn4sngtxgkdck6ymlmu3m

A survey on ontologies for human behavior recognition

Natalia Díaz Rodríguez, M. P. Cuéllar, Johan Lilius, Miguel Delgado Calvo-Flores
2014 ACM Computing Surveys  
new learning and recognition models.  ...  In this work, we review different methods for human activity recognition, classified as data-driven and knowledge-based techniques.  ...  Competitiveness, and the project Development of an Intelligent System for Behaviour Detection and Control in a Tagged World (TIN2009-14538-C02-01).  ... 
doi:10.1145/2523819 fatcat:kvlfg5ghsfgpbewnbebhpakk4i

Mobile big data analytics using deep learning and apache spark

Mohammad Abu Alsheikh, Dusit Niyato, Shaowei Lin, Hwee-pink Tan, Zhu Han
2016 IEEE Network  
This Spark-based framework speeds up the learning of deep models consisting of many hidden layers and millions of parameters.  ...  Each Spark worker learns a partial deep model on a partition of the overall MBD, and a master deep model is then built by averaging the parameters of all partial models.  ...  (a) Accelerometer signal of different human activities. (b) Recognition accuracy of deep learning models under different deep model setups.  ... 
doi:10.1109/mnet.2016.7474340 fatcat:kmt2eywkuzb5fdp3q3biacr4uq

Author Index

2010 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition  
as Feedback Cue in Human-Robot Interaction -A Comparison between Human and Automatic Recognition Performances Lashkari, Danial Workshop: Nonparametric Hierarchical Bayesian Model for Functional Brain  ...  Based Approach Workshop: Learning High-dimensional Image Statistics for Aabnormality Detection on Medical Images Workshop: Application of Trace-Norm and Low-Rank Matrix Decomposition for Computational  ... 
doi:10.1109/cvpr.2010.5539913 fatcat:y6m5knstrzfyfin6jzusc42p54

Prediction of Behavior and Activity of Patients through Wearable Devices Based on Deep Learning

Decheng Zhang, Hengjing Zhang, Chuanxin Zhao, Manuel Aleixandre
2022 Journal of Sensors  
Specifically, in the first step, we developed a wearable device based on ZigBee with low cost and low weight.  ...  In order to help patients with rehabilitation training, it is necessary to monitor their activities in time. We propose a real-time monitoring method based on wearable devices.  ...  Acknowledgments This work was supported in part by the Natural Science Foundation of China (Grant 61871412), in part by the Wuhu City Science and Technology Plan Project (2021cg17), and in part by the  ... 
doi:10.1155/2022/3067840 fatcat:yd7esiub4bc4bcgnwixx7d7aem

An Agricultural Monitoring System Based on Wireless Sensor and Depth Learning Algorithm

Liwei Geng, Tingting Dong
2017 International Journal of Online Engineering (iJOE)  
In addition to cheap cost and low power consumption, the solution has the functions of reminding and recognition due to the adoption of artificial intelligence algorithm.  ...  Second, the classification model based on deep learning algorithm was put forward according to the application of the Wireless Sensor Network (WSN) in continuous monitoring of soil temperature and humidity  ...  Deep learning, also known as deep structured learning or hierarchical learning, is part of a broader family of machine learning methods based on learning data representations, as opposed to task-specific  ... 
doi:10.3991/ijoe.v13i12.7885 fatcat:vvtpwhlvanbzhev5o3gdevjcly

Survey on Deep Neural Networks in Speech and Vision Systems [article]

Mahbubul Alam, Manar D. Samad, Lasitha Vidyaratne, Alexander Glandon,, Khan M. Iftekharuddin
2019 arXiv   pre-print
This survey begins by providing background and evolution of some of the most successful deep learning models for intelligent vision and speech systems to date.  ...  Robust and efficient intelligent systems demand low-latency and high fidelity in resource-constrained hardware platforms such as mobile devices, robots, and automobiles.  ...  Note the views and findings reported in this work completely belong to the authors and not the NSF or NIH.  ... 
arXiv:1908.07656v2 fatcat:7acubicqzzac3dqemkiccoogm4

A Lightweight Hierarchical Model with Frame-Level Joints Adaptive Graph Convolution for Skeleton-Based Action Recognition

Yujian Jiang, Xue Yang, Jingyu Liu, Junming Zhang, Zhenhua Tan
2021 Security and Communication Networks  
It is difficult to deploy previously established models to real-life applications based on low-cost embedded devices.  ...  It also has a simple structure and training process that make it easy to deploy in real-time recognition systems based on low-cost embedded devices.  ...  Acknowledgments is work was supported by Funds for Key Laboratory of Ministry of Culture and Tourism (WLBSYS2005) and the Fundamental Research Funds for the Central Universities (CUC19ZD005).  ... 
doi:10.1155/2021/2290304 fatcat:cxtjpygsqffcxi7xmlhpea2tmu
« Previous Showing results 1 — 15 out of 26,807 results