检索结果-内蒙古大学图书馆

Optimization of RLS Algorithm for Hybrid Method ICA-RLS

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2019年第27期52卷 530-535页

作者： Rene Jaros Radek Martinek Radana Kahankova Lukas Danys Jan Baros Martina Ladrova Michaela Sidikova Department of Cybernetics and Biomedical Engineering Faculty of Electrical Engineering and Computer Science VSB-Technical University of Ostrava 17. listopadu 15 708 33 Ostrava Czech Republic

This paper deals with a design and implementation of a new approach to the extraction of fetal electrocardiography (fECG) signal by hybrid method combining independent component analysis (ICA) and adaptive algorithm based on recursive optimal adaptation (Recursive Least Square, RLS). The abdominal and direct fetal electrocardiogram database (ADFECGDB) was selected for the validation based on estimation of detection accuracy (ACC) relative to the reference signal recorded by means of fetal scalp electrode. The paper provides the tests of the RLS-based filter order setting in the range of 2 to 100 as well as optimization of the input channel combination to achieve the most accurate detection. In total, 11 electrode combinations were created out of 4 abdominal channels, and tested as the inputs of the ICA-RLS hybrid method. The results show that the method is very promising. The highest score was achieved for recording r0l ACC = 99.228 % with combination of input channels 1, 2, and 3 along with the RLS algorithm filter order 4.

关键词： Noninvasive fetal electrocardiography independent component analysis (ICA) recursive least square (RLS) hybrid methods fetal heart rate variability monitoring extraction systems

Overground gait patterns changed by modulating hip stiffness with a robotic exoskeleton*

学校读者我要写书评

暂无评论

Overground gait patterns changed by modulating hip stiffness...

IEEE/RAS-EMBS International Conference on biomedical Robotics and Biomechatronics (BioRob)

作者： Meghan E. Huber Jongwoo Lee Vibha Agarwal Haley Warren Neville Hogan Department of Mechanical Engineering Massachusetts Institute of Technology Cambridge MA USA Department of Mechanical and Industrial Engineering University of Massachusetts Amherst Amherst MA USA Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge MA USA Department of Biomedical Engineering University of Vermont Burlington VT USA Department of Brain and Cognitive Sciences Massachusetts Institute of Technology Cambridge MA USA

ISBN: (数字)9781728159072

ISBN: (纸本)9781728159089

Lower-limb exoskeletons have shown great potential to assist human locomotion. However, effective methods for modulating aspects of gait behavior beyond reducing metabolic effort, such as stride time and gait kinematics, are still needed, especially for individuals with impaired gait. Using the Samsung GEMS-H exoskeleton, we studied the effect on healthy gait behavior of applying hip stiffness during overground walking. We found that applying positive stiffness did not affect stride time, but it did reduce hip range of motion. We also found that applying negative stiffness increased both stride time and hip range of motion. Additional analyses showed that the effect of applied hip stiffness on hip range of motion during overground walking was similar to that observed during treadmill walking. The effect of positive stiffness on stride time was similar during overground and treadmill walking, but the increase in stride time in response to the application of negative stiffness was greater during treadmill walking than in overground walking. Lastly, we found no evidence to indicate that neural adaptation or learning occurred when hip stiffness was applied. These results suggest that applying joint stiffness may be a promising approach to restoring healthy gait kinematics.

关键词： Legged locomotion Hip Exoskeletons Robots Read only memory Time measurement Analysis of variance

Correction To: Combining functional near-infrared spectroscopy and EEG measurements for the diagnosis of attention-deficit hyperactivity disorder

学校读者我要写书评

暂无评论

Neural Computing and Applications 2022年第8期34卷 6581-6581页

作者： Güven, Ayşegül Altınkaynak, Miray Dolu, Nazan İzzetoğlu, Meltem Pektaş, Ferhat Özmen, Sevgi Demirci, Esra Batbat, Turgay Department of Biomedical Engineering Engineering Faculty Erciyes University Kayseri Turkey Department of Physiology Medical Faculty Başkent University Ankara Turkey Electrical and Computer Engineering Department Villanova University Villanova USA Department of Physiology Medical Faculty Altınbaş University Istanbul Turkey Department of Child and Adolescent Psychiatry Medical Faculty Erciyes University Kayseri Turkey

Multiple faults detection in low voltage inverter-fed induction motors

学校读者我要写书评

暂无评论

Multiple faults detection in low voltage inverter-fed induct...

IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives (SDEMPED)

作者： Lucia Frosini Marcello Minervini Luca Ciceri Andrea Albini Department of Electrical Computer and Biomedical Engineering University of Pavia Pavia Italy CESI SpA Italy

ISBN: (纸本)9781728118338

This paper presents a novel procedure to detect the most frequent faults in inverter-fed induction motors, i.e. stator short circuits and bearing defects, even in case of simultaneous presence. The procedure is based only on the analysis in the frequency domain of electromagnetic signals (one-phase stator current and stray flux around the motor), by evaluating in the experimental measurements the amplitude of the harmonic components at characteristic fault frequencies. A methodology based on high sampling frequency and filtering process allowed to distinguish not only the presence of single and multiple faults, but also the progression of these faults, from an early stage to a more serious condition.

关键词： Circuit faults Rotors Induction motors Stator windings Vibrations Electromagnetics

A review of hidden markov models and recurrent neural networks for event detection and localization in biomedical signals

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Khalifa, Yassin Mandic, Danilo Sejdić, Ervin Department of Electrical and Computer Engineering University of Pittsburgh PittsburghPA United States Department of Electrical and Computer Engineering Imperial College LondonSW7 2BT United Kingdom Department of Bioengineering University of Pittsburgh PittsburghPA United States Department of Biomedical Informatics University of Pittsburgh PittsburghPA United States Intelligent Systems Program University of Pittsburgh PittsburghPA United States

biomedical signals carry signature rhythms of complex physiological processes that control our daily bodily activity. The properties of these rhythms indicate the nature of interaction dynamics among physiological processes that maintain a homeostasis. Abnormalities associated with diseases or disorders usually appear as disruptions in the structure of the rhythms which makes isolating these rhythms and the ability to differentiate between them, indispensable. computer aided diagnosis systems are ubiquitous nowadays in almost every medical facility and more closely in wearable technology, and rhythm or event detection is the first of many intelligent steps that they perform. How these rhythms are isolated? How to develop a model that can describe the transition between processes in time? Many methods exist in the literature that address these questions and perform the decoding of biomedical signals into separate rhythms. In here, we demystify the most effective methods that are used for detection and isolation of rhythms or events in time series and highlight the way in which they were applied to different biomedical signals and how they contribute to information fusion. The key strengths and limitations of these methods are also discussed as well as the challenges encountered with application in biomedical signals. Copyright © 2020, The Authors. All rights reserved.

关键词： biomedical signal processing

Reinforcement learning control of robotic knee with human in the loop by flexible policy iteration

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Gao, Xiang Si, Jennie Wen, Yue Li, Minhan Huang, He Department of Electrical Computer and Energy Engineering Arizona State University TempeAZ85287 United States Department of Biomedical Engineering North Carolina State University RaleighNC27695 United States University of North Carolina at Chapel Hill Chapel HillNC27599 United States

—This study is motivated by a new class of challenging control problems described by automatic tuning of robotic knee control parameters with human in the loop. In addition to inter-person and intra-person variances inherent in such human-robot systems, human user safety and stability, as well as data and time efficiency should also be taken into design consideration. Here by data and time efficiency we mean learning and adaptation of device configurations takes place within countable gait cycles or within minutes of time. As solutions to this problem is not readily available, we therefore propose a new policy iteration based adaptive dynamic programming algorithm, namely the flexible policy iteration (FPI). We show that the FPI solves the control parameters via (weighted) least-squares while it incorporates data flexibly and utilizes prior knowledge. We provide analyses on stable control policies, non-increasing and converging value functions to Bellman optimality, and error bounds on the iterative value functions subject to approximation errors. We extensively evaluated the performance of FPI in a well-established locomotion simulator, the OpenSim under realistic conditions. By inspecting FPI with three other comparable algorithms, we demonstrate the FPI as a feasible data and time efficient design approach for adapting the control parameters of the prosthetic knee to co-adapt with the human user who also places control on the prosthesis. As the proposed FPI algorithm does not require stringent constraints or peculiar assumptions, we expect this reinforcement learning controller can potentially be applied to other challenging adaptive optimal control problems. Copyright © 2020, The Authors. All rights reserved.

关键词： Optimal control systems

Target detection and segmentation in circular-scan synthetic-aperture-sonar images using semi-supervised convolutional encoder-decoders

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Sledge, Isaac J. Emigh, Matthew S. King, Jonathan L. Woods, Denton L. Tory Cobb, J. Príncipe, José C. The Advanced Signal Processing and Automated Target Recognition Branch Naval Surface Warfare Center Panama CityFL32407 United States The Applied Sensing and Processing Branch Naval Surface Warfare Center Panama CityFL32407 United States The Littoral Acoustics and Target Physics Branch Naval Surface Warfare Center Panama CityFL32407 United States The Department of Electrical and Computer Engineering The Department of Biomedical Engineering University of Florida GainesvilleFL32611 United States

We propose a framework for saliency-based, multi-target detection and segmentation of circular-scan, synthetic-aperture-sonar (CSAS) imagery. Our framework relies on a multi-branch, convolutional encoder-decoder network (MB-CEDN). The encoder portion of the MB-CEDN extracts visual contrast features from CSAS images. These features are fed into dual decoders that perform pixel-level segmentation to mask targets. Each decoder provides different perspectives as to what constitutes a salient target. These opinions are aggregated and cascaded into a deep-parsing network to refine the segmentation. We evaluate our framework using real-world CSAS imagery consisting of five broad target classes. We compare against existing approaches from the computer-vision literature. We show that our framework outperforms supervised, deep-saliency networks designed for natural imagery. It greatly outperforms unsupervised saliency approaches developed for natural imagery. This illustrates that natural-image-based models may need to be altered to be effective for this imaging-sonar modality. © 2021, CC BY.

关键词： Sonar

Experimental realization of Schumacher's information geometric bell inequality

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Rezaei, Tahereh Aslmarand, Shahabeddin M. Snyder, Robert Khajavi, Behzad Alsing, Paul M. Fanto, Michael Ahn, Doyeol Miller, Warner A. Department of Physics Florida Atlantic University Boca RatonFL33431 United States L3Harris 10001 Jack Finney Blvd CBN018 GreenvilleTX75402 United States Dept of Biomedical Engineering University of Houston HoustonTX77204 United States Air Force Research Laboratory Information Directorate RomeNY13441 United States Center Quantum Information Processing Department of Electrical and Computer Engineering University of Seoul Seoul130-743 Korea Republic of

Quantum mechanics can produce correlations that are stronger than classically allowed. This stronger-than-classical correlation is the "fuel" for quantum computing. In 1991 Schumacher forwarded a beautiful geometric approach, analogous to the well-known result of Bell, to capture non-classicality of this correlation for a singlet state. He used well-established information distance defined on an ensemble of identically-prepared states. He calculated that for certain detector settings used to measure the entangled state, the resulting geometry violated a triangle inequality - a violation that is not possible classically. This provided a novel information-based geometric Bell inequality in terms of a "covariance distance." Here we experimentally-reproduce his construction and demonstrate a definitive violation for a Bell state of two photons based on the usual spontaneous parametric down-conversion in a paired BBO crystal. The state we produced had a visibility of Vad = 0.970. We discuss generalizations to higher dimensional multipartite quantum states. © 2021, CC BY.

关键词： Geometry

Compact Convolutional Neural Networks for Ultrasound Beamforming

学校读者我要写书评

暂无评论

Compact Convolutional Neural Networks for Ultrasound Beamfor...

IEEE International Ultrasonics Symposium

作者： Zhanwen Chen Adam Luchies Brett Byram Department of Electrical Engineering and Computer Science Vanderbilt University Nashville USA Department of Biomedical Engineering Vanderbilt University Nashville USA

We trained convolutional neural networks (CNNs) to suppress off-axis scattering in the short-time Fourier Transform (STFT) domain. Our training data were point target responses from simulated anechoic cysts. We used random neural architecture search to build CNN models with variable input formulations, layer sizes, and training hyperparameters. Our results showed that CNNs were easier to train, as they required fewer network weights to match the performance of fully-connected networks (FCNs). The best CNN models achieved comparable phantom CNRs with two to three orders of magnitude fewer weights.

关键词： Kernel Convolutional neural networks Array signal processing Training Apertures Ultrasonic imaging Phantoms