Abstract-To find an efficient and valid alternative of polysomnography (PSG), this paper investigates real-time sleep apnea and hypopnea syndrome (SAHS) detection based on electrocardiograph (ECG) and saturation of peripheral oxygen (SpO 2 ) signals, individually and in combination. We include ten machinelearning algorithms in our classification experiment. It is shown that our proposed SpO 2 features outperform the ECG features in terms of diagnostic ability. More importantly, we propose classifier combination to further enhance the classification performance by harnessing the complementary information provided by individual classifiers. With our selected SpO 2 and ECG features, the classifier combination using AdaBoost with Decision Stump, Bagging with REPTree, and either kNN or Decision Table achieves sensitivity, specificity, and accuracy all around 82% for a minute-based realtime SAHS detection over 25 sleep-disordered-breathing suspects' full overnight recordings.Index Terms-Classifier combination, electrocardiograph (ECG), feature selection, hypopnea, machine learning, saturation of peripheral oxygen (SpO 2 ), sleep apnea.
In this paper, we propose an improved image dehazing algorithm using dark channel prior and Multi-Scale Retinex. Main improvement lies in automatic and fast acquisition of transmission map of the scene. We implement the Multi-scale Retinex algorithm on the luminance component in YCbCr space, obtain a pseudo transmission map whose function is similar to the transmission map in original approach. Combining with the haze image model and the dark channel prior, we can recover a high quality haze-free image. Compared with the original method, our algorithm has two main advantages: (i) no user interaction is needed, and (ii) restoring the image much faster while maintaining comparable dehazing performance.
A method for determination of the complete set of physical, geometrical, and interfacial properties of an isotropic layer embedded between two known solids is discussed. These properties are: Lamé elastic moduli, density and thickness of the layer, and complex normal and transverse interfacial stiffnesses between the layer and the substrates. The properties are combined in the form of eight nondimensional parameters, which are determined from experimental reflection spectra at two incident angles: normal and oblique. The conditions for simultaneous determination of bulk layer properties and the interface normal and transverse springs with losses and the stability of the inversion method against data scatter are addressed. The inversion model is validated by experiment on normal and angular ultrasonic reflectivity from a layer between two semispaces in dry mechanical contact and from an environmentally degraded adhesive joint. The layer properties were measured independently, showing good agreement with the reconstructed results.
This study was structured to challenge the hypothesis that nano-sized particulates could be molecularly targeted and bound to the prognostic and predictive HER-2/neu cell membrane receptor to elicit detectable changes in ultrasound response from human breast cancer cells. SKBR-3 human breast cancer cells were enlisted to test the efficacy of the particle conjugation strategy used in this study and ultimately, to provide conclusive remarks regarding the validity of the stated hypothesis. A characterization-mode ultrasound (CMUS) system was used to apply a continuum mechanics based, two-step inversion algorithm to reconstruct the mechanical material properties of four cell/agarose test conditions upon three independent test samples. The four test conditions include: Herceptin conjugated iron oxide nanoparticles bound to cells (HER-con), Herceptin bound to cells (HER), iso-type matched antibody conjugated iron oxide nanoparticles bound to cells (ISO-con), and Cold Flow Buffer mixed with agarose (CFB). The statistical analysis of these ultrasound results supported the ability to differentiate between HER-2/neu positive SKBR-3 cells that have been successfully tagged with Herceptin(R) conjugated iron oxide particles to those that have not demonstrated particle binding. These findings serve as promising proof-of-concept data for the development of a quantitative histopathologic evaluation tool directed towards both in situ and in vivo applications. The ultimate goal of this research is to exploit the molecular expression of the HER-2/neu protein to offer rapid, quantitative ultrasound information concerning the malignancy rating of human breast tissue employing tumor targeting nanoparticle based ultrasound contrast agents. When fully developed, this could potentially help 32,000-63,000 women efficiently find their proper treatment strategy to fight and win their battle against breast cancer.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.