检索结果-内蒙古大学图书馆

Convolutional Neural Networks for Epileptic Seizure Prediction

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Eberlein, Matthias Hildebrand, Raphael Tetzlaff, Ronald Hoffmann, Nico Kuhlmann, Levin Brinkmann, Benjamin Müller, Jens Technische Universität Dresden Faculty of Electrical and Computer Engineering Institute of Circuits and Systems Dresden01062 Germany Technische Universität Dresden Faculty of Computer Science Computer Graphics and Visualisation Dresden01062 Germany Faculty of Information Technology Monash University VIC Clayton3800 Australia Department of Medicine St Vincent's Hospital Melbourne VIC Fitzroy3065 Australia Mayo Systems Electrophysiology Laboratory Departments of Neurology and Biomedical Engineering Mayo Clinic RochesterMN55905 United States

Epilepsy is the most common neurological disorder and an accurate forecast of seizures would help to overcome the patient's uncertainty and helplessness. In this contribution, we present and discuss a novel methodology for the classification of intracranial electroencephalography (iEEG) for seizure prediction. Contrary to previous approaches, we categorically refrain from an extraction of hand-crafted features and use a convolutional neural network (CNN) topology instead for both the determination of suitable signal characteristics and the binary classification of preictal and interictal segments. Three different models have been evaluated on public datasets with long-term recordings from four dogs and three patients. Overall, our findings demonstrate the general applicability. In this work we discuss the strengths and limitations of our methodology. Copyright © 2018, The Authors. All rights reserved.

关键词： Electroencephalography

Contrastive functional connectivity defines neurophysiology-informed symptom dimensions in major depression

学校读者我要写书评

暂无评论

Cell reports. Medicine

Cell reports. Medicine 2025年 102151页

作者： Hao Zhu Xiaoyu Tong Nancy B Carlisle Hua Xie Corey J Keller Desmond J Oathes Feng Liu Charles B Nemeroff Gregory A Fonzo Yu Zhang Department of Bioengineering Lehigh University Bethlehem PA USA. Department of Psychology Lehigh University Bethlehem PA USA. Center for Neuroscience Research Children's National Hospital Washington DC USA. Wu Tsai Neuroscience Institute Stanford University Stanford CA USA Department of Psychiatry and Behavioral Sciences Stanford University School of Medicine Stanford CA USA Veterans Affairs Palo Alto Healthcare System and the Sierra Pacific Mental Illness Research Education and Clinical Center (MIRECC) Palo Alto CA USA. Center for Brain Imaging and Stimulation Department of Psychiatry University of Pennsylvania Perelman School of Medicine Philadelphia PA USA Center for Neuromodulation in Depression and Stress Department of Psychiatry University of Pennsylvania Perelman School of Medicine Philadelphia PA USA Penn Brain Science Translation Innovation and Modulation Center University of Pennsylvania Perelman School of Medicine Philadelphia PA USA Departments of Neurology Neurosurgery Bioengineering and Neuroscience University of Pennsylvania Perelman School of Medicine Philadelphia PA USA. Department of Systems and Enterprises Stevens Institute of Technology Hoboken NJ USA. Center for Psychedelic Research and Therapy Department of Psychiatry and Behavioral Sciences Dell Medical School The University of Texas at Austin Austin TX USA. Department of Bioengineering Lehigh University Bethlehem PA USA Department of Electrical and Computer Engineering Lehigh University Bethlehem PA USA. Electronic address: yuzi20@lehigh.edu.

Major depressive disorder (MDD) is highly heterogeneous, posing challenges for effective treatment due to complex interactions between clinical symptoms and neurobiological features. To address this, we apply contrastive principal-component analysis to fMRI-based resting-state functional connectivity, isolating disorder-specific variations by contrasting data from 233 MDD patients and 285 healthy controls. Subsequently, we use sparse canonical correlation analysis to identify two significant dimensions linking distinct brain circuits with clinical profiles. One dimension relates to an internalizing-externalizing symptom spectrum involving visual and limbic networks and is associated with cognitive task reaction times. The other dimension, linked to personality traits protective against depression (e.g., extraversion), is driven by dorsal attention network connections and correlates with cognitive control and psychomotor performance. This approach illuminates stable symptom dimensions and their neurophysiological underpinnings, aiding in precision phenotyping for MDD and supporting the development of targeted, individualized therapeutic strategies for mental health care.

关键词： brain-symptom dimension contrastive machine learning disease heterogeneity fMRI functional connectivity major depressive disorder

Wireless surveillance of two-hop communications

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Ma, Ganggang Xu, Jie Duan, Lingjie Zhang, Rui School of Information Engineering Guangdong University of Technology Engineering Systems and Design Pillar Singapore University of Technology and Design Department of Electrical and Computer Engineering National University of Singapore

Wireless surveillance is becoming increasingly important to protect the public security by legitimately eavesdropping suspicious wireless communications. This paper studies the wireless surveillance of a two-hop suspicious communication link by a half-duplex legitimate monitor. By exploring the suspicious link's two-hop nature, the monitor can adaptively choose among the following three eavesdropping modes to improve the eavesdropping performance: (I) passive eavesdropping to intercept both hops to decode the message collectively, (II) proactive eavesdropping via noise jamming over the first hop, and (III) proactive eavesdropping via hybrid jamming over the second hop. In both proactive eavesdropping modes, the (noise/hybrid) jamming over one hop is for the purpose of reducing the end-toend communication rate of the suspicious link and accordingly making the interception more easily over the other hop. Under this setup, we maximize the eavesdropping rate at the monitor by jointly optimizing the eavesdropping mode selection as well as the transmit power for noise and hybrid jamming. Numerical results show that the eavesdropping mode selection significantly improves the eavesdropping rate as compared to each individual eavesdropping mode. Copyright © 2017, The Authors. All rights reserved.

关键词： Jamming

Proactive eavesdropping via jamming over HARQ-based communications

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Xu, Jie Li, Kai Duan, Lingjie Zhang, Rui School of Information Engineering Guangdong University of Technology Engineering Systems and Design Pillar Singapore University of Technology and Design Department of Electrical & Computer Engineering National University of Singapore

This paper studies the wireless surveillance of a hybrid automatic repeat request (HARQ) based suspicious communication link over Rayleigh fading channels. We propose a proactive eavesdropping approach, where a half-duplex monitor can opportunistically jam the suspicious link to exploit its potential retransmissions for overhearing more efficiently. In particular, we consider that the suspicious link uses at most two HARQ rounds for transmitting the same data packet, and we focus on two cases without and with HARQ combining at the monitor receiver. In both cases, we aim to maximize the successful eavesdropping probability at the monitor, by adaptively allocating the jamming power in the first HARQ round according to fading channel conditions, subject to an average jamming power constraint. For both cases, we show that the optimal jamming power allocation follows a thresholdbased policy, and the monitor jams with constant power when the eavesdropping channel gain is less than the threshold. Numerical results show that the proposed proactive eavesdropping scheme achieves higher successful eavesdropping probability than the conventional passive eavesdropping, and HARQ combining can help further improve the eavesdropping performance. Copyright © 2017, The Authors. All rights reserved.

关键词： Error correction

Enhanced IC Modeling Methodology for System-level ESD Simulation

学校读者我要写书评

暂无评论

Enhanced IC Modeling Methodology for System-level ESD Simula...

electrical Overstress/Electrostatic Discharge Symposium (EOS/ESD)

作者： Jie Xiong Zaichen Chen Yang Xiu Zhen Mu Maxim Raginsky Elyse Rosenbaum Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign 1308 West Main St. Urbana IL USA Texas Instruments Inc 12500 TI Blvd. UIUC Dallas TX USA Cadence Design Systems Inc 270 Billerica Rd Chelmsford MA USA

To enable accurate system-level ESD simulation, the quasi-static I-V model of an IC is enhanced through kernel regression to reflect its circuit board dependency; alternatively, a recurrent neural network may be used to generate a non-quasi-static transient model. Hybrid electromagnetic and circuit simulation is demonstrated for ESD-induced noise coupling analysis.

关键词： Integrated circuit modeling Pins Electrostatic discharges Kernel Partial discharges Computational modeling

Amyloid-independent vascular contributions to cortical atrophy and cognition in a multi-center mixed cohort with low to severe small vessel disease

学校读者我要写书评

暂无评论

Alzheimer's & Dementia 2021年第S1期17卷

作者： Julie Ottoy Miracle Ozzoude Katherine Zukotynski Sabrina M. Adamo Christopher J. M. Scott Vincent Gaudet Joel Ramirez Walter Swardfager Benjamin Lam Aparna Bhan Alex Kiss Stephen C. Strother Christian Bocti Michael Borrie Howard Chertkow Richard Frayne Ging-Yuek Robin Hsiung Robert Laforce Jr. Michael D. Noseworthy Frank S. Prato Demetrios J. Sahlas Eric E. Smith Vesna Sossi Alexander Thiel Jean-Paul Soucy Jean-Claude Tardif Maged Goubran Sandra E. Black LC Campbell Cognitive Neurology Research Unit Sunnybrook Research Institute University of Toronto Toronto ON Canada Departments of Medicine and Radiology McMaster University Hamilton ON Canada LC Campbell Cognitive Neurology Research Unit Sunnybrook Research Institute Toronto ON Canada Department of Electrical and Computer Engineering University of Waterloo Waterloo ON Canada Department of Pharmacology & Toxicology University of Toronto Toronto ON Canada Department of Research Design and Biostatistics Sunnybrook Research Institute University of Toronto Toronto ON Canada Rotman Research Institute Baycrest University of Toronto Toronto ON Canada Département de Médecine Université de Sherbrooke Sherbrooke QC Canada Lawson Health Research Institute Western University London ON Canada Jewish General Hospital Montreal QC Canada Departments of Radiology and Clinical Neuroscience University of Calgary Calgary AB Canada Djavad Mowafaghian Centre for Brain Health University of British Colombia Vancouver BC Canada Clinique Interdisciplinaire de Mémoire CHU de Québec/Université Laval/Hôpital de l’Enfant-Jésus Quebec City QC Canada Department of Electrical and Computer Engineering McMaster University Hamilton ON Canada Department of Medicine McMaster University Hamilton ON Canada Hotchkiss Brain Institute University of Calgary Calgary AB Canada Physics and Astronomy Department and DM Center for Brain Health University of British Columbia Vancouver BC Canada Jewish General Hospital McGill University Montreal QC Canada Montreal Neurological Institute McGill University Montreal QC Canada Montreal Heart Institute McGill University Montreal QC Canada

Background Small vessel disease (SVD) often co-exists with Alzheimer’s disease (AD) pathology (up to 60%) and may facilitate AD progression. However, SVD is currently not integrated as a pathological factor within the ATN research criteria. Up to now, the majority of studies that investigated effects of SVD on brain atrophy and cognition were limited to either AD cohorts with low SVD burden (e.g., ADNI) or cognitively normal elderly with high SVD burden. Thus, there is a need to investigate the effects of SVD in a cohort spanning low to severe SVD and amyloid-beta pathology. Method Our study included 118 subjects in total. Fifty-nine subjects were recruited in a multi-site study (MITNEC) from dementia and SVD-stroke clinics (64% amyloid-beta+) who had severe SVD burden as quantified by white matter hyperintensity volumes [WMH; median(IQR): 30.2(22.2)cm 3 ] and Fazekas score 2.5-3. In addition, we included 59 cognitively normal/early-MCI subjects from ADNI (44% amyloid-beta+) with low-to-moderate WMH [median(IQR): 5.8(9.1)cm 3 ]. We performed vertex-wise regressions, investigating associations of cortical thickness with amyloid-beta (18F-florbetapir-SUVR pons ) or vascular burden (WMH), corrected for WMH or amyloid-beta, respectively, and age, sex, education. Further, mediation analyses investigated whether the effects of amyloid-beta or vascular burden on cognition (MMSE, MoCA, Trails-B, semantic fluency, ANART, and Boston-naming) were mediated by cortical thickness. Result We observed a significant effect of vascular burden on cortical thickness independent of amyloid-beta. This effect was stronger than the vascular-independent effect of amyloid-beta on thickness (Fig. 1). Furthermore, we observed additive effects of vascular burden and amyloid-beta on cognition (semantic fluency: ß=-0.29 [p=0.002] and ß=-0.27 [p=0.001], respectively; Trails-B: ß=+0.18 [p=0.03] and ß=+0.22 [p=0.02], respectively). Here, the effects on semantic fluency were significantly mediated by

关键词：

Tissue disorder for label-free diagnosis of biopsies using quantitative phase imaging

学校读者我要写书评

暂无评论

Tissue disorder for label-free diagnosis of biopsies using q...

Optics and Photonics Japan, OFJ 2017

作者： Takabayashi, Masanori Majeed, Hassaan Kajdacsy-Balla, Andre Popescu, Gabriel Department of Systems Design and Informatics Kyushu Institute of Technology Japan Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign Japan Department of Bioengineering University of Illinois at Urbana-Champaign United States Department of Pathology University of Illinois at Chicago United States

ISBN: (纸本)9781557528209

Using quantitative phase imaging, we measured the tissue disorder strength, which is known as one of the effective markers of early carcinogenesis. We retrieved the disorder parameter from local refractive index fluctuation map obtained by spatial light interference microscopy (SLIM). We show that SLIM imaging combined with the disorder analysis is a valuable approach for screening of benign and malignant breast tissue biopsies. © 2017 OSA - The Optical Society. All rights reserved.

关键词： Tissue

A novel decomposition for control of dc circuits and grid models with heterogeneous energy sources

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Wang, Shuai Baillieul, John Division of Systems Engineering Boston University BostonMA02115 United States Departments of Mechanical Engineering Electrical and Computer Engineering Boston University BostonMA02115 United States

The way in which electric power depends on the topology of circuits with mixed voltage and current sources is examined. The power flowing in any steady-state DC circuit is shown to depend on a minimal set of key variables called fundamental node voltages and fundamental edge currents. Every steady-state DC circuit can be decomposed into a voltage controlled subcircuit and a current controlled subcircuit. In terms of such a decomposition, the I2R losses of a mixed source circuit are always the sum of losses on the voltage controlled subcircuit and the current controlled subcircuit. The paper concludes by showing that the total power flowing in a mixed source circuit can be found as critical points of the power expressed in terms of the key voltage and current variables mentioned above. The possible relationship to topology control of electric grid operations is discussed. Copyright © 2017, The Authors. All rights reserved.

关键词： Electric load flow

Can a universal quantum cloner be used to design an experimentally feasible near-deterministic CNOT gate?

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Gueddana, Amor Gholami, Peyman Lakshminarayanan, Vasudevan Theoretical and Experimental Epistemology Lab TEEL School of Optometry and Vision Science University of Waterloo 200 University Avenue West WaterlooONN2l 3G1 Canada Green and Smart Communication Systems Lab Gres'Com Engineering School of Communication of Tunis Sup'Com University of Carthage Ghazela Technopark Ariana2083 Tunisia Department of Physics Department of Electrical and Computer Engineering Department of Systems Design Engineering University of Waterloo 200 University Avenue West WaterlooONN2l 3G1 Canada

We propose a non-deterministic CNOT gate based on a quantum cloner, a quantum switch based on all optical routing of single photon by single photon, a quantum-dot spin in a double-sided optical microcavity with two photonic qubits, delay lines and other linear optical photonic devices. Our CNOT provides a fidelity of 78% with directly useful outputs for a quantum computing circuit and requires no ancillary qubits or electron spin measurements. Copyright © 2018, The Authors. All rights reserved.

关键词： Particle beams