Self-Supervised Learning From Multi-Sensor Data for Sleep Recognition

Zhao, Aite; Dong, Junyu; Zhou, Huiyu

doi:10.1109/access.2020.2994593

Cited by 31 publications

(21 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…34 Zhao et al used a multisensor to obtain lots of data to establish a self-supervised learning model for sleep recognition, increase data capacity through self-supervised pretraining, processing frequency domain information, use the rotational view t-stochastic neighbour embedding to represent multidimensional data features, and use the long short-term memory fusion condition random field, the test proved the effectiveness of the algorithm. 35 Wang et al collected four swimming style data through inertial sensors arranged at the waist, based on the HMM extracted the data fusion information with high recognition rate. 36 In 2019, Feng et al realized multisource information fusion through a multivariate long range system, completed smooth filtering and data denoising by preprocessing sensor data and feature extraction, used sliding windows for stream segmentation and frequency domain feature extraction, and constructed an MRMR-SFS-RF-based pose recognition model, which experimentally proved that in a small number of identification accuracies in the data was 98.9%.…”

Section: Sensor-based Gesture Recognitionmentioning

confidence: 99%

“…Zhao et al used a multisensor to obtain lots of data to establish a self‐supervised learning model for sleep recognition, increase data capacity through self‐supervised pretraining, processing frequency domain information, use the rotational view t‐stochastic neighbour embedding to represent multidimensional data features, and use the long short‐term memory fusion condition random field, the test proved the effectiveness of the algorithm 35 . Wang et al collected four swimming style data through inertial sensors arranged at the waist, based on the HMM extracted the data fusion information with high recognition rate 36 .…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A fully connected deep learning approach to upper limb gesture recognition in a secure FES rehabilitation environment

Liu

Jiang

et al. 2021

Int J Intell Syst

View full text Add to dashboard Cite

Stroke is one of the leading causes of death and disability in the world. The rehabilitation of Patients' limb functions has great medical value, for example, the therapy of functional electrical stimulation (FES) systems, but suffers from effective rehabilitation evaluation. In this paper, six gestures of upper limb rehabilitation were monitored and collected using microelectromechanical systems sensors, where data stability was guaranteed using data preprocessing methods, that is, deweighting, interpolation, and feature extraction. A fully connected neural network has been proposed investigating the effects of different hidden layers, and determining its activation functions and optimizers. Experiments have depicted that a three‐hidden‐layer model with a softmax function and an adaptive gradient descent optimizer can reach an average gesture recognition rate of 97.19%. A stop mechanism has been used via recognition of dangerous gesture to ensure the safety of the system, and the lightweight cryptography has been used via hash to ensure the security of the system. Comparison to the classification models, for example, k‐nearest neighbor, logistic regression, and other random gradient descent algorithms, was conducted to verify the outperformance in recognition of upper limb gesture data. This study also provides an approach to creating health profiles based on large‐scale rehabilitation data and therefore consequent diagnosis of the effects of FES rehabilitation.

show abstract

Section: Sensor-based Gesture Recognitionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

A fully connected deep learning approach to upper limb gesture recognition in a secure FES rehabilitation environment

Liu

Jiang

et al. 2021

Int J Intell Syst

View full text Add to dashboard Cite

show abstract

“…Under the domain of Unsupervised methodologies, "selfsupervised learning" is crucial, and has been widely used in research domains based on computer vision as well as for anomaly detection in several fields. Self-supervised learning formulates new surrogate labels artificially or extract robust feature set through the characteristics or structure of the unlabeled data itself [66]. However, the studies done on effective ham and spam email differentiation using selfsupervised learning is rather scant.…”

Section: Relevant Studiesmentioning

confidence: 99%

Efficient Clustering of Emails Into Spam and Ham: The Foundational Study of a Comprehensive Unsupervised Framework

et al. 2020

View full text Add to dashboard Cite

The spread and adoption of spam emails in malicious activities like information and identity theft, malware propagation, monetary and reputational damage etc. are on the rise with increased effectiveness and diversification. Without doubt these criminal acts endanger the privacy of many users and businesses'. Several research initiatives have taken place to address the issue with no complete solution until now; and we believe an intelligent and automated methodology should be the way forward to tackle the challenges. However, till date limited studies have been conducted on the applications of purely unsupervised frameworks and algorithms in tackling the problem. To explore and investigate the possibilities, we intend to propose an anti-spam framework that fully relies on unsupervised methodologies through a multi-algorithm clustering approach. This paper presents an in-depth analysis on the methodologies of the first component of the framework, examining only the domain and header related information found in email headers. A novel method of feature reduction using an ensemble of 'unsupervised' feature selection algorithms has also been investigated in this study. In addition, a comprehensive novel dataset of 100,000 records of ham and spam emails has been developed and used as the data source. Key findings are summarized as follows: I) out of six different clustering algorithms used -Spectral and K-means demonstrated acceptable performance while OPTICS projected the optimum clustering with an average of 3.5% better efficiency than Spectral and Kmeans, validated through a range of validations processes II) The other three algorithms-BIRCH, HDBSCAN and K-modes, did not fare well enough. III) The average balanced accuracy for the optimum three algorithms has been found to be ≈94.91%, and IV) The proposed feature reduction framework achieved its goal with high confidence.

show abstract

“…KNN linear classifier was used for supervised training using the collected datasets. There are few other recent solutions which make use of the pressure sensors and machine learning for identifying different postures [57][58][59][60][61][62].…”

Section: Introductionmentioning

confidence: 99%

CNN-Based Smart Sleep Posture Recognition System

Tang

Kumar

Nadeem

et al. 2021

IoT

View full text Add to dashboard Cite

Sleep pattern and posture recognition have become of great interest for a diverse range of clinical applications. Autonomous and constant monitoring of sleep postures provides useful information for reducing the health risk. Prevailing systems are designed based on electrocardiograms, cameras, and pressure sensors, which are not only expensive but also intrusive in nature, and uncomfortable to use. We propose an unobtrusive and affordable smart system based on an electronic mat called Sleep Mat-e for monitoring the sleep activity and sleep posture of individuals living in residential care facilities. The system uses a pressure sensing mat constructed using piezo-resistive material to be placed on a mattress. The sensors detect the distribution of the body pressure on the mat during sleep and we use convolution neural network (CNN) to analyze collected data and recognize different sleeping postures. The system is capable of recognizing the four major postures—face-up, face-down, right lateral, and left lateral. A real-time feedback mechanism is also provided through an accompanying smartphone application for keeping a diary of the posture and send alert to the user in case there is a danger of falling from bed. It also produces synopses of postures and activities over a given duration of time. Finally, we conducted experiments to evaluate the accuracy of the prototype, and the proposed system achieved a classification accuracy of around 90%.

show abstract

Self-Supervised Learning From Multi-Sensor Data for Sleep Recognition

Cited by 31 publications

References 31 publications

A fully connected deep learning approach to upper limb gesture recognition in a secure FES rehabilitation environment

A fully connected deep learning approach to upper limb gesture recognition in a secure FES rehabilitation environment

Efficient Clustering of Emails Into Spam and Ham: The Foundational Study of a Comprehensive Unsupervised Framework

CNN-Based Smart Sleep Posture Recognition System

Contact Info

Product

Resources

About