检索结果-内蒙古大学图书馆

Contemporary Symbolic Regression Methods and their Relative Performance 35

Contemporary Symbolic Regression Methods and their Relative ...

35th Conference on Neural Information Processing Systems - Track on Datasets and Benchmarks, NeurIPS Datasets and Benchmarks 2021

作者： La Cava, William Orzechowski, Patryk Burlacu, Bogdan de França, Fabrício Olivetti Virgolin, Marco Jin, Ying Kommenda, Michael Moore, Jason H. Boston Children’s Hospital Harvard Medical School United States Institute for Biomedical Informatics University of Pennsylvania United States Josef Ressel Center for Symbolic Regression University of Applied Sciences Upper Austria Austria Federal University of ABC Santo Andre Brazil Life Sciences and Health Group Centrum Wiskunde & Informatica Netherlands Department of Statistics Stanford University United States Department of Automatics and Robotics AGH University of Science and Technology Krakow Poland Center for Mathematics Computation and Cognition | Heuristics Analysis and Learning Laboratory Brazil Chalmers University of Technology Sweden

Many promising approaches to symbolic regression have been presented in recent years, yet progress in the field continues to suffer from a lack of uniform, robust, and transparent benchmarking standards. We address this shortcoming by introducing an open-source, reproducible benchmarking platform for symbolic regression. We assess 14 symbolic regression methods and 7 machine learning methods on a set of 252 diverse regression problems. Our assessment includes both real-world datasets with no known model form as well as ground-truth benchmark problems. For the real-world datasets, we benchmark the ability of each method to learn models with low error and low complexity relative to state-of-the-art machine learning methods. For the synthetic problems, we assess each method’s ability to find exact solutions in the presence of varying levels of noise. Under these controlled experiments, we conclude that the best performing methods for real-world regression combine genetic algorithms with parameter estimation and/or semantic search drivers. When tasked with recovering exact equations in the presence of noise, we find that several approaches perform similarly. We provide a detailed guide to reproducing this experiment and contributing new methods, and encourage other researchers to collaborate with us on a common and living symbolic regression benchmark. © 2021 Neural information processing systems foundation. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent upper-limb exoskeleton integrated with soft wearable bioelectronics and deep-learning for human intention-driven strength augmentation based on sensory feedback

arXiv

引用

arXiv 2023年

作者： Lee, Jinwoo Kwon, Kangkyu Soltis, Ira Matthews, Jared Lee, Yoon-Jae Kim, Hojoong Romero, Lissette Zavanelli, Nathan Kwon, Youngjin Kwon, Shinjae Lee, Jimin Na, Yewon Lee, Sung Hoon Yu, Ki Jun Shinohara, Minoru Hammond, Frank L. Yeo, Woon-Hong Department of Mechanical Robotics and Energy Engineering Dongguk University Seoul04620 Korea Republic of IEN Center for Human-Centric Interfaces and Engineering Institute for Electronics and Nanotechnology Georgia Institute of Technology AtlantaGA30332 United States School of Electrical and Computer Engineering Georgia Institute of Technology AtlantaGA30332 United States George W. Woodruff School of Mechanical Engineering Georgia Institute of Technology AtlantaGA30332 United States School of Industrial Design Georgia Institute of Technology AtlantaGA30332 United States School of Electrical and Electronic Engineering Yonsei University Seoul03722 Korea Republic of School of Biological Sciences Georgia Institute of Technology AtlantaGA30332 United States Wallace H. Coulter Department of Biomedical Engineering Georgia Institute of Technology and Emory University School of Medicine AtlantaGA30332 United States Institute for Materials Parker H. Petit Institute for Bioengineering and Biosciences Neural Engineering Center Institute for Robotics and Intelligent Machines Georgia Institute of Technology AtlantaGA30332 United States

The age and stroke-associated decline in musculoskeletal strength degrades the ability to perform daily human tasks using the upper extremities. Here, we introduce an intelligent upper-limb exoskeleton system that uses cloud-based deep learning to predict human intention for strength augmentation. The embedded soft wearable sensors provide sensory feedback by collecting real-time muscle signals, which are simultaneously computed to determine the user's intended movement. The cloud-based deep-learning predicts four upper-limb joint motions with an average accuracy of 96.2% at a 500-550 millisecond response rate, suggesting that the exoskeleton operates just by human intention. In addition, an array of soft pneumatics assists the intended movements by providing 897 newton of force while generating displacement of 87 millimeter at maximum. Collectively, the intent-driven exoskeleton can reduce human muscle activities by 3.7 times on average compared to the unassisted *** Codes 68T40 (Primary) 92C55, 68T99 (Secondary) Copyright © 2023, The Authors. All rights reserved.

关键词： Sensory feedback

来源：评论

学校读者我要写书评

暂无评论

Analysis of the features of brain neuronal sources during imagery motor activity: MEG study

Analysis of the features of brain neuronal sources during im...

引用

School on Dynamics of Complex Networks and their Application in Intellectual robotics (DCNAIR)

作者： Semen Kurkin Parth Chholak Alexander Pisarchik Alexander Hramov Neuroscience and Cognitive Technology Lab Center for Technologies in Robotics and Mechatronics Components Innopolis University Russia Center for Biomedical Technology Technical University of Madrid Madrid Spain

ISBN: (数字)9781728172866

ISBN: (纸本)9781728172873

We analyzed the features of motor imagery (imagery arms movements) in the source level, applying the Dynamic Imaging of Coherent Sources method to MEG signals. We obtained the results that have confirmed the existence of two types of motor imagery: visual imagery and kinesthetic imagery. We have analyzed averaged distributions of normalized sources power for the visual imagery and kinesthetic imagery subgroups of volunteers and identified the main differences between these types of motor imagery in terms of the excitation of sources of neural activity.

关键词： Visualization Photonics Electroencephalography Optics Robots Magnetic resonance imaging Brain modeling

来源：评论

学校读者我要写书评

暂无评论

Classification of external signal by spiking neural network of bistable Hodgkin-Huxley neurons

Classification of external signal by spiking neural network ...

引用

School on Dynamics of Complex Networks and their Application in Intellectual robotics (DCNAIR)

作者： Andrey Andreev Alexander Pisarchik Neuroscience and Cognivite Technology Laboratory Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia Center for Biomedical Technology Technical University of Madrid Madrid Spain

ISBN: (数字)9781728172866

ISBN: (纸本)9781728172873

We propose a classifier consisting of Hodgkin-Huxley neurons based on the activation of a different number of neurons depending on the external current amplitude. We consider a network with 2 output neurons and train the classifier for 2 external current pulses with different amplitudes by adaptation of the couplings between neurons of the main network and the output neurons.

关键词： Neurons Couplings Neural networks Brain modeling Adaptation models Electroencephalography Neuroscience

来源：评论

学校读者我要写书评

暂无评论

Kinesthetic and visual modes of imaginary movement: MEG studies for BCI development 3

Kinesthetic and visual modes of imaginary movement: MEG stud...

引用

3rd School on Dynamics of Complex Networks and their Application in Intellectual robotics, DCNAIR 2019

作者： Hramov, Alexander E. Pisarchik, Alexander N. Neuroscience and Cognitive Technology Laboratory Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia Center for Biomedical Technology Technical University of Madrid Madrid Spain

ISBN: (纸本)9781728124704

The study of neurophysiological mechanisms responsible for motor imagery is important for the development of brain-computer interfaces (BCI). Here we analyze the results of magnetoencephalographic (MEG) experiments which confirm the existence of two types of motor imagery, kinesthetic and visual imagery, distinguished by activation and inhibition of different brain areas in motor-related alpha (8-12 Hz) and beta (15-30 HZ) frequency ranges. Kinesthetic imagery implies muscular sensation when performing an imaginary moving action that leads to event-related desynchronization (ERD) of motor-associated brain rhythms. By contrast, visual imagery refers to visualization of the corresponding action that results in event-related synchronization (ERS) of alpha/beta activity. A main difference between kinesthetic and visual modes occurs in the frontal brain area. The analysis of evoked responses shows that in all kinesthetic imagery subjects the activity in the frontal cortex is suppressed during motor imagery, while in the visual imagery subjects the frontal cortex is always active. The accuracy in classification of left- and right-arm motor imagery using artificial intelligence methods is similar for kinesthetic and visual imagery modes. The possibility to increase the accuracy for visual imagery is in demand for BCIs. © 2019 IEEE.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Validity of Customized Branched Tissue Engineered Vascular Graft in a Porcine Model

Annals of thoracic surgery short reports

引用

Annals of thoracic surgery short reports 2023年第3期1卷 426-430页

作者： Hidenori Hayashi Jacqueline Contento Hiroshi Matsushita Tatsuya Watanabe Nora Lee Tyler Dunn Katherine Nurminsky Angie Zhu Emmett Reid Paige Mass Vincent Cleveland Seda Aslan Vivian Nguyen Keigo Kawaji Joey Huddle Jed Johnson Yue-Hin Loke Axel Krieger Laura Olivieri Narutoshi Hibino Division of Cardiac Surgery Department of Surgery University of Chicago Chicago Illinois. Department of Cardiology Children's National Hospital Washington DC. Laboratory for Computational Sensing and Robotics Johns Hopkins University Baltimore Maryland. Department of Biomedical Engineering Illinois Institute of Technology Chicago Illinois. Nanofiber Solutions LLC Dublin Ohio. Department of Pediatric Cardiology University of Pittsburgh Medical Center Pittsburgh Pennsylvania. Department of Cardiovascular Surgery Advocate Children's Hospital Oak Lawn Illinois.

Background:Patient-specific, 3-dimensional printed, tissue engineered vascular grafts (3DTEVGs) are manufactured to optimize hemodynamic performance and to accommodate growth. We evaluate growth outcomes of 3DTEVGs compared with standard grafts for pulmonary artery reconstruction in porcine models. Methods:Magnetic resonance imaging (MRI) with 4-dimensional flow data was acquired in porcine models (n = 8). 3DTEVGs guided in design by computational flow dynamics were implanted (n = 4), with polytetrafluorethylene grafts used as controls (n = 4). Postoperative MRI and histologic features of explanted grafts were evaluated after 10 weeks. Results:All pigs survived, with evidence of patent grafts on postoperative MRI. Graft inner diameter changes were 0.47 ± 2.31 mm in 3DTEVGs and -4.61 ± 2.15 mm in controls ( = .018). Mean main pulmonary artery wall shear stress was significantly lower in 3DTEVGs (7.12 ± 4.21 Pa) than in controls (18.15 ± 8.37 Pa; = .0396). Histologic evaluation of 3DTEVGs showed a single layer of endothelial cells, an organized smooth muscle layer, and collagen deposition with a remaining scaffold area of 21.37% ± 20.46%. Conclusions:Our patient-specific 3DTEVGs demonstrated optimal anatomic fit while maintaining ideal flow dynamics and promoting appropriate neovessel formation.

关键词： 3D 3-dimensional 3DTEVG 3-dimensional printed, tissue engineered vascular graft 4D 4-dimensional CFD computational fluid dynamics LPA left pulmonary artery MPA main pulmonary artery MRI magnetic resonance imaging PA pulmonary artery PTFE polytetrafluoroethylene RPA right pulmonary artery WSS wall shear stress

来源：评论

学校读者我要写书评

暂无评论

Neuromorphic system development based on adaptive neuronal network to modulate synaptic transmission in hippocampus 3

Neuromorphic system development based on adaptive neuronal n...

引用

3rd International Conference "Neurotechnologies and Neurointerfaces", CNN 2021

作者： Lebedeva, Albina Gerasimova, Svetlana Fedulina, Anastasiya Mishchenko, Mikhail Beltyukova, Anna Matveeva, Mariya Mikhaylov, Alexey Pisarchik, Alexander Kazantsev, Victor Neurotechnologies Department N.I. Lobachevsky State University of Nizhny Novgorod Nizhny Novgorod Russia Laboratory of Physics and Technology of Thin Films Department of Solid State Electronics and Optoelectronics Research Institute of Physics and Technology N.I. Lobachevsky State University of Nizhny Novgorod Nizhny Novgorod Russia Department of Theory of Oscillations and Automatic Control Faculty of Radiophysics N.I. Lobachevsky State University of Nizhny Novgorod Nizhny Novgorod Russia Center for Biomedical Technology Technical University of Madrid Pozuelo de Alarcón Madrid Spain Center for Technologies in Robotics and Mechatronics Component Innopolis University Innopolis Russia Center for Neurotechnology and Machine Learning Immanuel Kant Baltic Federal University Kaliningrad Russia

ISBN: (纸本)9781665424745

The project presents fundamental research on the development of concept and basic components of physical circuit based on optoelectronic elements (neuromorphic generators, memristors, optical fibers). This network can replace some functions of brain’s neural networks (such as memory) through adaptive stimulation of neural interfaces at the cellular and cellular networks level. Developing learning system will perform the electrical stimulation of brain areas based on the neural activity recorded and will include electronic devices for recording and processing signals. In addition, this system will include electronic devices for generating electrical stimuli based on hardware models of neurons and memristive devices. The basic idea is to integrate an artificial network with living microcircuits of the brain. The artificial network is capable of adaptively generating electrical output signals and can stimulate a given area of the brain according to the recorded pattern of input signals. We suppose that such a network will be able to reproduce the functions of brain systems, based on the use of learning algorithms. It can be used to expand the functionality of these brain systems and to replace lost functions in pathology or trauma. © 2021 IEEE.

关键词： Memristors

来源：评论

学校读者我要写书评

暂无评论

Evaluation of CR2-Haptic Movement Quality Assessment Module for Hand 3rd

Evaluation of CR2-Haptic Movement Quality Assessment Module ...

引用

3rd International Conference for Innovation in biomedical Engineering and Life Sciences, ICIBEL 2020

作者： Khor, Kang Xiang Chin, Patrick Jun Hua Yeong, Che Fai Su, Eileen Lee Ming Narayanan, Aqilah Leela T. Rahman, Hisyam Abdul Abdullah, Najib bin Mustar, Muhammad Farhan bin Khor, Yvonne Yee Woon Latip, Hadafi Fitri Mohd Khan, Qamer Iqbal Silvadorai, Yashitha Devi Chan, Tracy Arumugam, Nimalan Skudai Johor81300 Malaysia Center of Artificial Intelligence and Robotics UTM Kuala Lumpur54100 Malaysia School of Biomedical Engineering and Health Science Faculty of Engineering UTM Skudai Johor81300 Malaysia Universiti Tun Hussein Onn Malaysia Parit Raja Johor86400 Malaysia Sports Innovation and Technology Centre UTM Skudai Johor81300 Malaysia UTM Skudai Johor81310 Malaysia Petaling Jaya Selangor46050 Malaysia

ISBN: (纸本)9783030650919

Objective assessment is crucial in the rehabilitation process for physiotherapists to determine the progress of the patient and to provide the best treatment in therapy. However, current rehabilitations rely heavily on manual labour and lack objective assessments, as well as quantitative diagnosis and evaluation. This project aims to evaluate the movement assessment modules of CR2-Haptic, a portable and reconfigurable rehabilitation robot that can be used to provide an objective assessment for the targeted movement of upper limb. Both wrist and forearm movement performance were assessed in the study. Centre-out-point-to-point (CO-PTP) approach was used in the movement quality assessment module of CR2-Haptic and the proposed coordination score showed high correlation with four kinematic variables of the movement including total trial time which has the strongest relation with r2 value of 0.85, followed by smoothness (r2 = 0.80), mean velocity (r2 = 0.78) and path ratio (r2 = 0.70). © 2021, Springer Nature Switzerland AG.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

The Simulation and Experiment Study of a Wearable, Flexible and Transparent Biomimetic Voltage Source

The Simulation and Experiment Study of a Wearable, Flexible ...

引用

作者： Liang, Zhen Yang, Runhuai Xu, Chenchen Hou, Shaohui Jin, Guoqing Niu, Fuzhou Department of Biomedical Engineering School of Life Science Anhui Medical University Hefei230032 China School of Mechanical and Electric Engineering Robotics and Microsystems Center Soochow University Suzhou215006 China College of Mechanical Engineering Suzhou University of Science and Technology Suzhou215000 China

In this paper, a biomimetic transparent and flexible solid-state electrolytes voltage source was proposed. The ion-transport mechanism was discussed, and finite element method was used to simulate the voltage generated by different parameters. Finally, the experimental study was performed. The generated voltage was measured and compared to the simulation results. Based on the simulation and experiments, a wearable, flexible and transparent voltage source was finally designed and fabricated. © Springer Nature Switzerland AG 2020.

关键词： Biomimetics

来源：评论

学校读者我要写书评

暂无评论

Highest performance requires an optimal effort: A MEG study on visual perception

Highest performance requires an optimal effort: A MEG study ...

引用

School on Dynamics of Complex Networks and their Application in Intellectual robotics (DCNAIR)

作者： Parth Chholak Alexander N. Pisarchik Centre for Biomedical Technology Technical University of Madrid Madrid Spain Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia

ISBN: (数字)9781728172866

ISBN: (纸本)9781728172873

Twelve subjects (6 males; 17-64 years) participated in magnetoencephalography (MEG) experiments designed to study visual response to flickering Necker cubes. Event-related fields in the lateral occipital complex and steady-state response in the visual region V1 and V2 were studied to characterise the early response time durations and attentional capacity during the trial time period of 5-s, respectively. We found that there was an optimal response time duration for which the attention capacity was maximum. The results also support the hypothesis that stimulus detection in brain is driven by coherence resonance.

关键词： Visualization Coherence Electric potential Delays Electroencephalography Magnetic resonance imaging Steady-state

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：