154 research outputs found
Early detection of neurological disorders using machine learning systems Advances in medical technologies and clinical practice book series./ Sudip Paul, Pallab Bhattacharya, and Arindam Bit, editors.
Includes bibliographical references."This book examines the role of machine learning systems in the detection of neurological disorders such as Alzheimer disease, Parkinson's disease, schizophrenia, and depression"--Provided by publisher.Epileptic seizure detection and classification using machine learning -- Rekh Janghel, Yogesh Rathore, Gautam Tiparti -- A study on basal ganglia circuit and its relation with movement disorders / Ankita Tiwari, Raghuvendra Tripathi, Dinesh Bhatia -- Social media analytics to predict depression level in the users / Mohammad Shahid Husain -- Tremor identification using machine learning in Parkinson's disease -- Angana Saikia, Vinayak Majhi, Masaraf Hussain, Sudip Paul, Amitava Datta -- Soft computing based early detection of Parkinson's disease using non-invasive method based on speech analysis / Chandrasekar Ravi -- Neurofeedback -retrain the brain / Meena Gupta, Dinesh Bhatia -- Neurocognitive mechanisms for detecting early phase of depressive disorder analysis of event related potentials in human brain / Shashikanta Tarai -- Intelligent big data analytics in health : big data analytics in health / Ebru Bayrak, Pinar Kirci -- Motor imagery classification using EEG signals for brain computer interface applications / Subrota Mazumdar, Rohit Chaudharya, Suruchi Suruchi, Suman Mohanty, Divya Kumari, Aleena Swetapadma -- Mapping the intellectual structure of the field neurological disorders : a bibliometric analysis / S. Ravikmar -- Medical image segmentation an advanced approach / Ramgopal Kashyapdia.1 online resource
One-bit Compressed Sensing with the k-Support Norm
Abstract In one-bit compressed sensing (1-bit CS), one attempts to estimate a structured parameter (signal) only using the sign of suitable linear measurements. In this paper, we investigate 1-bit CS problems for sparse signals using the recently proposed k-support norm. We show that the new estimator has a closed-form solution, so no optimization is needed. We establish consistency and recovery guarantees of the estimator for both Gaussian and subGaussian random measurements. For Gaussian measurements, our estimator is comparable to the best known in the literature, along with guarantees on support recovery. For sub-Gaussian measurements, our estimator has an irreducible error which, unlike existing results, can be controlled by scaling the measurement vectors. In both cases, our analysis covers the setting of model misspecification, i.e., when the true sparsity is unknown. Experimental results illustrate several strengths of the new estimator
Acute Aneurysm is more Critical than Acute Stenoses in Blood Vessels: a Numerical Investigation Using Stress Markers
Assessment of Influences of Stenoses in Right Carotid Artery on Left Carotid Artery Using Wall Stress Marker
© 2017 Arindam Bit et al.Purpose. Atherosclerosis is a diseased condition of blood vessel. It causes partial blockage in lumen of vessel and affects hemodynamic of localized flowing blood. Complex geometries like region of bifurcation also affects hemodynamic to a larger extent. Complexity further increases in presence of stenoses at region of bifurcation. Such morphological change in vessel largely affects parent as well as corresponding sister and daughter vessels. In this paper, complexity in hemodynamic of blood in pair of carotid arteries (left and right carotid arteries) is evaluated in presence of stenoses at basilar segment of right artery in three-dimensional domain using reconstructed tomographic images of patient. Methods. Transient information of blood flow is obtained using four-dimensional phase-contrast MRI technique. Haematocrit component of blood at diseased condition is considered using Power Law and Quemada model. Numerical techniques are used to solve pressure-coupled governing equations of flowing blood. Results. Dysfunctions of endothelial cells near the wall are characterised by evaluating shear stress markers. Wall shear stress and its gradient based and harmonic based descriptors are calculated over complete geometry during one cardiac cycle. Conclusion. Internal branch of left carotid artery and external branch of right carotid artery are found prone to secondary stenoses in presence of primary stenoses at basilar segment of right carotid artery
Assessment of Influences of Stenoses in Right Carotid Artery on Left Carotid Artery Using Wall Stress Marker
© 2017 Arindam Bit et al.Purpose. Atherosclerosis is a diseased condition of blood vessel. It causes partial blockage in lumen of vessel and affects hemodynamic of localized flowing blood. Complex geometries like region of bifurcation also affects hemodynamic to a larger extent. Complexity further increases in presence of stenoses at region of bifurcation. Such morphological change in vessel largely affects parent as well as corresponding sister and daughter vessels. In this paper, complexity in hemodynamic of blood in pair of carotid arteries (left and right carotid arteries) is evaluated in presence of stenoses at basilar segment of right artery in three-dimensional domain using reconstructed tomographic images of patient. Methods. Transient information of blood flow is obtained using four-dimensional phase-contrast MRI technique. Haematocrit component of blood at diseased condition is considered using Power Law and Quemada model. Numerical techniques are used to solve pressure-coupled governing equations of flowing blood. Results. Dysfunctions of endothelial cells near the wall are characterised by evaluating shear stress markers. Wall shear stress and its gradient based and harmonic based descriptors are calculated over complete geometry during one cardiac cycle. Conclusion. Internal branch of left carotid artery and external branch of right carotid artery are found prone to secondary stenoses in presence of primary stenoses at basilar segment of right carotid artery
- …
