Intelligent Computing Techniques for the Detection of Sleep Disorders: A Review

KumarGarg, Vijay; Bansal, R. K.

doi:10.5120/19283-0701

Cited by 4 publications

(3 citation statements)

References 87 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Eye-tracking systems support estimation of the user's gaze behaviors, the data foundation of interaction between humans and computers. Wang et.al (2012) [20] proposed a gaze estimation method that used both neural network and fuzzy rules to describe the relationship between gazes and intention; Neural networks are adaptive to training data, whereas they lack the ability to explain how the networks reach their final decision nodes [21]; On the other hand, fuzzy logics are incapable of automatically acquiring the rules they use [22]. Those hybrid models of neural networks and fuzzy systems can complement each other for improved accuracy.…”

Section: Fuzzy Models Applied To Eye-tracking Datamentioning

confidence: 99%

An Adaptive Fuzzy Modeling of Visual Attention in Real-world Interaction with Health Information System

Sridhar

Kwon

Cho

et al. 2020

Proceedings of the Human Factors and Ergonomics Society Annual

View full text Add to dashboard Cite

Bottom-up and top-down processes are the two mechanisms of visual attention allocation, which allow people to efficiently spot task-relevant stimuli from cluttered and noisy environments, while staying alert to abnormalities within the visual field of view. This paper presents a preliminary study of the physicians’ real-life interaction with Information Communication Technology (ICT) in their own offices, along with extensively analyzing one case of an hour-long interaction of a physician, in which one performs a daily routine of reviewing patient electronic health records (EHRs) and writing diagnostic notes to the system interface. The physician interactions were captured in a time series data by recording display screen, keystrokes and mouse movements, also by simultaneously tracking eye movements. Then, a fuzzy-based model that can distinguish bottom-up and top-down processes were defined by using statistical random variables in terms of eye-movement patterns. The shift between those two attentional processes was detected by tracking the parametric changes of gaze behaviors as input: significant shift of fixation, sustained gazing, and fixation trajectory over time. Based on those gaze metrics, a random variable was assigned to the discrete probability of low (0), medium (0.5), or high (1.0), for a quantified fuzzy output, which was further machine-learned into an Adaptive Neuro-Fuzzy Inference System (ANFIS) model in order to judge how a physician is likely to be dominated by a bottom-up or top-down processes in performing a task at that instance in time. On training the ANFIS model with three different types of fuzzy membership functions (Gaussian, triangular and trapezoidal), the model performed best with the Gaussian function (after 100 iterations, the predicted root mean-square error (RMSE) converged at 0.07%, yielding a smooth linear curve). For a proof-of concept, the model was implemented by using one physician’s gaze behaviors, of which the average, machine-learned fuzzy output probability indicated that the physician was veering toward bottom-up visual attention. This individualized, task-specific pattern of visual attention has implications for the designs of intelligent interface in ICT. Our ANFIS model can scale up to different physicians and tasks to predict the likelihood of bottom-up or top-down information processing based on real-world gaze behaviors.

show abstract

Section: Fuzzy Models Applied To Eye-tracking Datamentioning

confidence: 99%

An Adaptive Fuzzy Modeling of Visual Attention in Real-world Interaction with Health Information System

Sridhar

Kwon

Cho

et al. 2020

Proceedings of the Human Factors and Ergonomics Society Annual

View full text Add to dashboard Cite

show abstract

“…Basically, it is a combo of two or more artificial neurons having their weights, transfer function, inputs and outputs bias. It acquires a flexi adaptive nature to modify its own structure during training; hence, it is beneficial to solve real world problematic relationships [13].The back-propagation (BP) algorithm is mainly used in ANN and also widely used by many researchers in the detection and classification of sleep apnea / hypopnea events. An ANN model can be constructed using the following fundamental steps [8]: (a) Acquisition of data and choose sample to construct ANN (b) Pre-processing of data (c) Take decision related to total number of hidden layers, neurons present at each layer, most important training function, weight function and an activation function (d) Provide training to the network in which adjustment of weights are done in such a way so that predicted output must be closest to desired one (e) Performance testing of the designed model.…”

Section: Related Workmentioning

confidence: 99%

Comparison of neural network back propagation algorithms for early detection of sleep disorders

Garg

Bansal

2015

2015 International Conference on Advances in Computer Engineering and Applications

View full text Add to dashboard Cite

Sleep is not merely a BREAK from our regular work. It is must to be physically and mentally refreshed every day. Having a sound nights sleep, one can perform best in whatever job in hand. But some time, sleep gets disturbed along with some awkward behaviors known as sleep disorders. The various techniques and practices are followed by numerous researchers for the diagnosis of the unusual behaviors which increase the disturbances in sleep and also encourage other sleep disorders. In this paper, a step has been taken towards the early detection of a few sleep disorders like Sleep Apnea, Insomnia, Parasomnia and Snoring using artificial neural network algorithms. The prior detection of these disorders can reduce the further effects on human body. This paper presents the comparison of four training algorithms gradient descent, quasi newton, conjugate gradient and bayesian regularization by using different training functions such as trainrp, trainlm, trainscg and trainbr respectively. All these algorithms are trained by the data set acquired from various physicians. From the results, it is found that bayesian regularization algorithm which is trained by using trainbr training function provides the best result for early detection of sleep disorders as per chosen sample size of 95 patient records.

show abstract

“…Zhou et al evaluated the performance of a wearable multisensory system compared to polysomnography (PSG) in measuring sleep stages and investigating OSAS [22]. Apart from these studies, compilation studies in the literature on systems that will help classify or detect sleep apnea are also presented in [23,24,25]. The contributions of the study to the literature are as follows.…”

Section: Introductionmentioning

confidence: 99%

Performance Comparison of Standard Polysomnographic Parameters Used in the Diagnosis of Sleep Apnea

Arslan Tuncer,

Çiçek,

Tuncer

2024

Turkish Journal of Science and Technology

View full text Add to dashboard Cite

Obstructive sleep apnea (OSAS), which is one of the leading sleep disorders and can result in death if not diagnosed and treated early, is most often confused with snoring. OSAS disease, the prevalence of which varies between 0.9% and 1.9% in Turkey, is a serious health problem that occurs as a result of complete or partial obstruction of the respiratory tract during sleep, resulting in sleep disruption, poor quality sleep, paralysis and even death in sleep. Polysomnography signal recordings (PSG) obtained from sleep laboratories are used for the diagnosis of OSAS, which is related to factors such as the individual's age, gender, neck diameter, smoking-alcohol consumption, and the occurrence of other sleep disorders. Polysomnography is used in the diagnosis and treatment of sleep disorders such as snoring, sleep apnea, parasomnia (abnormal behaviors during sleep), narcolepsy (sleep attacks that develop during the day) and restless legs syndrome. It allows recording various parameters such as brain waves, eye movements, heart and chest activity measurement, respiratory activities, and the amount of oxygen in the blood with the help of electrodes placed in different parts of the patient's body during night sleep. In this article, the performance of PSG signal data for the diagnosis of sleep apnea was examined on the basis of both signal parameters and the method used. First, feature extraction was made from PSG signals, then the feature vector was classified with artificial neural networks, Support Vector Machine (SVM), K-Nearest Neighbors (k-NN) and Logistic Regression (LR).

show abstract

Intelligent Computing Techniques for the Detection of Sleep Disorders: A Review

Cited by 4 publications

References 87 publications

An Adaptive Fuzzy Modeling of Visual Attention in Real-world Interaction with Health Information System

An Adaptive Fuzzy Modeling of Visual Attention in Real-world Interaction with Health Information System

Comparison of neural network back propagation algorithms for early detection of sleep disorders

Performance Comparison of Standard Polysomnographic Parameters Used in the Diagnosis of Sleep Apnea

Contact Info

Product

Resources

About