检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks

作者： Xue-Qin Huo Wei-Long Zheng Bao-Liang Lu Center for Brain-like Computing and Machine Intelligence Department of Computer Science and Engineering Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Brain Science and Technology Research Center

ISBN: (纸本)9781509006212

In this paper, we fuse EEG and forehead EOG to detect drivers' fatigue level by using discriminative graph regularized extreme learning machine (GELM). Twenty-one healthy subjects including twelve men and nine women participate in our driving simulation experiments. Two fusion strategies are adopted: feature level fusion (FLF) and decision level fusion (DLF). PERCLOS (the percentage of eye closure) is calculated by using the eye movement data recorded by eye tracking glasses as the indicator of drivers' fatigue level. The prediction correlation coefficient and root mean square error (RMSE) between the estimated fatigue level and the real fatigue level are both used to evaluate the performance of single modality and fusion modality. A comparative study on modality performance is conducted between GELM and support vector machine (SVM). The experimental results show that fusion modality can improve the performance of driving fatigue detection with a higher prediction correlation coefficient and a lower RMSE value in comparison with solely using EEG or forehead EOG. And FLF achieves better performance than DLF. GELM is more suitable for driving fatigue detection than SVM. Moreover, feature level fusion with GELM achieves the best performance with the prediction correlation coefficient of 0.8080 and the RMSE value of 0.0712 on average.

关键词： Fatigue Electrooculography Feature extraction Electroencephalography Forehead brain modeling Correlation

来源：评论

学校读者我要写书评

暂无评论

Measuring Sleep Quality from EEG with Machine Learning Approaches

Measuring Sleep Quality from EEG with Machine Learning Appro...

引用

International Joint Conference on Neural Networks

作者： Li-Li Wang Wei-Long Zheng Hai-Wei Ma Bao-Liang Lu Center for Brain-like Computing and Machine Intelligence Department of Computer Science and Engineering Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Brain Science and Technology Research Center

ISBN: (纸本)9781509006212

This study aims at measuring last-night sleep quality from electroencephalography (EEG). We design a sleep experiment to collect waking EEG signals from eight subjects under three different sleep conditions: 8 hours sleep, 6 hours sleep, and 4 hours sleep. We utilize three machine learning approaches, k-Nearest Neighbor (kNN), support vector machine (SVM), and discriminative graph regularized extreme learning machine (GELM), to classify extracted EEG features of power spectral density (PSD). The accuracies of these three classifiers without feature selection are 36.68%, 48.28%, 62.16%, respectively. By using minimal-redundancy-maximal-relevance (MRMR) algorithm and the brain topography, the classification accuracy of GELM with 9 features is improved largely and increased to 83.57% in average. To investigate critical frequency bands for measuring sleep quality, we examine the features of each band and observe their energy changing. The experimental results indicate that Gamma band is more relevant to measuring sleep quality.

关键词： quality of sleep Electroencephalography Sleep Artificial Intelligence Machine Learning Frequency bands Power spectral density Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Phoneme-specific speech separation

Phoneme-specific speech separation

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zhong-Qiu Wang Yan Zhao DeLiang Wang Department of Computer Science and Engineering The Ohio State University USA Center for Cognitive and Brain Sciences The Ohio State University USA

Speech separation or enhancement algorithms seldom exploit information about phoneme identities. In this study, we propose a novel phoneme-specific speech separation method. Rather than training a single global model to enhance all the frames, we train a separate model for each phoneme to process its corresponding frames. A robust ASR system is employed to identify the phoneme identity of each frame. This way, the information from ASR systems and language models can directly influence speech separation by selecting a phoneme-specific model to use at the test stage. In addition, phoneme-specific models have fewer variations to model and do not exhibit the data imbalance problem. The improved enhancement results can in turn help recognition. Experiments on the corpus of the second CHiME speech separation and recognition challenge (task-2) demonstrate the effectiveness of this method in terms of objective measures of speech intelligibility and quality, as well as recognition performance.

关键词： Decision support systems Indexes

来源：评论

学校读者我要写书评

暂无评论

Phone-Aware LSTM-RNN for Voice Conversion

Phone-Aware LSTM-RNN for Voice Conversion

引用

2016 IEEE 13th International Conference on Signal Processing（ICSP2016）

作者： Jiahao Lai Bo Chen Tian Tan Sibo Tong Kai Yu Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Speech Lab Department of Computer Science and Engineering Brain Science and Technology Research Center Shanghai Jiao Tong University

This paper investigates a new voice conversion technique using phone-aware Long Short-Term Memory Recurrent Neural Networks（LSTM-RNNs）. Most existing voice conversion methods, including Joint Density Gaussian Mixture Models（JDGMMs）, Deep Neural Networks（DNNs）and Bidirectional Long Short-Term Memory Recurrent Neural Networks（BLSTM-RNNs）, only take acoustic information of speech as features to train models. We propose to incorporate linguistic information to build voice conversion system by using monophones generated by a speech recognizer as linguistic features. The monophones and spectral features are combined together to train LSTM-RNN based voice conversion models,reinforcing the context-dependency modelling of *** results of the 1st voice conversion challenge shows our system achieves significantly higher performance than baseline（GMM method） and was found among the most competitive scores in similarity test. Meanwhile, the experimental results show phone-aware LSTM-RNN method obtains lower Melcepstral distortion and higher MOS scores than the baseline LSTM-RNNs.

关键词： voice conversion voice conversion challenge long short-term memory recurrent neural networks phone

来源：评论

学校读者我要写书评

暂无评论

An Investigation on Deep Learning with Beta Stabilizer

An Investigation on Deep Learning with Beta Stabilizer

引用

2016 IEEE 13th International Conference on Signal Processing（ICSP2016）

作者： Qi Liu Tian Tan Kai Yu Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Speech Lab Department of Computer Science and Engineering Brain Science and Technology Research Center Shanghai Jiao Tong University

Artificial neural networks(ANN) have been used in many applications such like handwriting recognition and speech recognition. It is well-known that learning rate is a crucial value in the training procedure for artificial neural networks. It is shown that the initial value of learning rate can confoundedly affect the final result and this value is always set manually in practice. A new parameter called beta stabilizer has been introduced to reduce the sensitivity of the initial learning rate. But this method has only been proposed for deep neural network(DNN) with sigmoid activation function. In this paper we extended beta stabilizer to long short-term memory(LSTM) and investigated the effects of beta stabilizer parameters on different models, including LSTM and DNN with relu activation *** is concluded that beta stabilizer parameters can reduce the sensitivity of learning rate with almost the same performance on DNN with relu activation function and LSTM. However, it is shown that the effects of beta stabilizer on DNN with relu activation function and LSTM are fewer than the effects on DNN with sigmoid activation function.

关键词： DNN An Investigation on Deep Learning with Beta Stabilizer

来源：评论

学校读者我要写书评

暂无评论

Fast High-resolution Miniature Two-photon Microscopy for brain Imaging in Freely-behaving Mice at the Single-spine Level

Fast High-resolution Miniature Two-photon Microscopy for Bra...

引用

中国神经科学学会第十二届全国学术会议

作者： Weijian Zong Runlong Wu Mingli Li Yanhui Hu Yijun Li Jinghang Li Hao Rong Haitao Wu Yangyang Xu Yang Lu Hongbo Jia Ming Fan Zhuan Zhou Yunfeng Zhang Aimin Wang Liangyi Chen Heping Cheng State Key Laboratory of Membrane Biology Institute of Molecular Medicine PekingTsinghua Center for Life Sciences Peking University Department of Cognitive Sciences Institute of Basic Medical Sciences Department of Neurobiology Institute of Basic Medical Sciences Brain Research Instrument Innovation Center Suzhou Institute of Biomedical Engineering and Technology Chinese Academy of Sciences State Key Laboratory of Advanced Optical Communication System and Networks School of Electronics Engineering and Computer Science Peking University

Recent developments in miniaturized microscopes have furthered the quest to visualize brain activities and structural dynamics in animals engaged in self-determined behaviors. However, it remains an unmet challenge to resolve activity at single dendritic spines, the elemental units underlying neuronal computation, in freely-behaving animals. Here, we report the design, testing, and application of a fast, high-resolution, miniaturized two-photon microscope（FIRM-TPM） that accomplishes this goal. With a headpiece weighing 2.15 g and a new type of hollow-core photonic crystal fiber to deliver 920-nm femtosecond laser pulses, the FIRM-TPM is capable of imaging commonly used biosensors at high spatiotemporal resolution（0.64 μm laterally and 3.35 μm axially, 40 Hz at 256 × 256 pixels）. Its micro-electromechanical systems scanner also enables random-access capability and free-line scanning at up to 10,000 Hz. It compares favorably with benchtop two-photon microscopy and miniature wide-field fluorescence microscopy in the structural and functional imaging of Thy1-GFP-or GCa MP6 f-labeled neurons. Further, we demonstrate its unique application and robustness with hour-long recording of neuronal activities down to the level of spines in mice experiencing vigorous body and head movements or engaging in social interaction. Thus, our new generation miniature microscope provides neuroscientists the long-sought tool-of-choice for imaging the brain at the synaptic level in freely-behaving animals.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Methods for interpreting and understanding deep neural networks

arXiv

引用

arXiv 2017年

作者： Montavon, Grégoire Samek, Wojciech Müller, Klaus-Robert Department of Electrical Engineering and Computer Science Technische Universität Berlin Marchstr. 23 Berlin10587 Germany Department of Video Coding and Analytics Fraunhofer Heinrich Hertz Institute Einsteinufer 37 Berlin10587 Germany Department of Brain and Cognitive Engineering Korea University Anam-dong 5ga Seongbuk-gu Seoul136-713 Korea Republic of Max Planck Institute for Informatics Stuhlsatzenhausweg Saarbrucken66123 Germany

This paper provides an entry point to the problem of interpreting a deep neural network model and explaining its predictions. It is based on a tutorial given at ICASSP 2017. It introduces some recently proposed techniques of interpretation, along with theory, tricks and recommendations, to make most efficient use of these techniques on real data. It also discusses a number of practical applications. Copyright © 2017, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Author Correction: Open-access quantitative MRI data of the spinal cord and reproducibility across participants, sites and manufacturers

引用

Scientific data 2021年第1期8卷 242页

作者： Julien Cohen-Adad Eva Alonso-Ortiz Mihael Abramovic Carina Arneitz Nicole Atcheson Laura Barlow Robert L Barry Markus Barth Marco Battiston Christian Büchel Matthew Budde Virginie Callot Anna J E Combes Benjamin De Leener Maxime Descoteaux Paulo Loureiro de Sousa Marek Dostál Julien Doyon Adam Dvorak Falk Eippert Karla R Epperson Kevin S Epperson Patrick Freund Jürgen Finsterbusch Alexandru Foias Michela Fratini Issei Fukunaga Claudia A M Gandini Wheeler-Kingshott Giancarlo Germani Guillaume Gilbert Federico Giove Charley Gros Francesco Grussu Akifumi Hagiwara Pierre-Gilles Henry Tomáš Horák Masaaki Hori James Joers Kouhei Kamiya Haleh Karbasforoushan Miloš Keřkovský Ali Khatibi Joo-Won Kim Nawal Kinany Hagen H Kitzler Shannon Kolind Yazhuo Kong Petr Kudlička Paul Kuntke Nyoman D Kurniawan Slawomir Kusmia René Labounek Maria Marcella Laganà Cornelia Laule Christine S Law Christophe Lenglet Tobias Leutritz Yaou Liu Sara Llufriu Sean Mackey Eloy Martinez-Heras Loan Mattera Igor Nestrasil Kristin P O'Grady Nico Papinutto Daniel Papp Deborah Pareto Todd B Parrish Anna Pichiecchio Ferran Prados Àlex Rovira Marc J Ruitenberg Rebecca S Samson Giovanni Savini Maryam Seif Alan C Seifert Alex K Smith Seth A Smith Zachary A Smith Elisabeth Solana Y Suzuki George Tackley Alexandra Tinnermann Jan Valošek Dimitri Van De Ville Marios C Yiannakas Kenneth A Weber Ii Nikolaus Weiskopf Richard G Wise Patrik O Wyss Junqian Xu NeuroPoly Lab Institute of Biomedical Engineering Polytechnique Montreal Montreal QC Canada. jcohen@polymtl.ca. Functional Neuroimaging Unit CRIUGM Université de Montréal Montreal QC Canada. jcohen@polymtl.ca. Mila - Quebec AI Institute Montreal QC Canada. jcohen@polymtl.ca. NeuroPoly Lab Institute of Biomedical Engineering Polytechnique Montreal Montreal QC Canada. Department of Radiology Swiss Paraplegic Centre Nottwil Switzerland. Centre for Advanced Imaging The University of Queensland Brisbane Australia. Department of Radiology University of British Columbia Vancouver BC Canada. Athinoula A. Martinos Center for Biomedical Imaging Department of Radiology Massachusetts General Hospital Charlestown MA USA. Department of Radiology Harvard Medical School Boston MA USA. Harvard-Massachusetts Institute of Technology Health Sciences & Technology Cambridge MA USA. School of Information Technology and Electrical Engineering The University of Queensland Brisbane Australia. NMR Research Unit Queen Square MS Centre UCL Queen Square Institute of Neurology Faculty of Brain Sciences University College London London UK. Department of Systems Neuroscience University Medical Center Hamburg-Eppendorf Hamburg Germany. Department of Neurosurgery Medical College of Wisconsin Milwaukee WI USA. Aix-Marseille Univ CNRS CRMBM Marseille France. APHM Hopital Universitaire Timone CEMEREM Marseille France. Vanderbilt University Institute of Imaging Science Vanderbilt University Medical Center Nashville TN USA. Department of Computer and Software Engineering Polytechnique Montreal Montreal Canada. CHU Sainte-Justine Research Centre Montreal QC Canada. Centre de Recherche CHUS CIMS Sherbrooke Canada. Sherbrooke Connectivity Imaging Lab (SCIL) Computer Science department Université de Sherbrooke Sherbrooke Canada. Université de Strasbourg CNRS ICube Strasbourg France. UHB - University Hospital Brno and Masaryk University Department of Radiology and Nuclear

来源：评论

学校读者我要写书评

暂无评论

Author Correction: Low-dimensional organization of angular momentum during walking on a narrow beam

引用

Scientific reports 2018年第1期8卷 6362页

作者： Enrico Chiovetto Meghan E Huber Dagmar Sternad Martin A Giese Section for Computational Sensomotorics Department of Cognitive Neurology Hertie Institute for Clinical Brain Research Centre for Integrative Neuroscience University Clinic Tübingen Tübingen Germany. enrico.chiovetto@klinikum.uni-tuebingen.de. Department of Mechanical Engineering Massachusetts Institute of Technology Cambridge Massachusetts USA. Departments of Biology Electrical and Computer Engineering Physics and Physical Therapy Movement Science and Rehabilitation Northeastern University Boston Massachusetts USA. Section for Computational Sensomotorics Department of Cognitive Neurology Hertie Institute for Clinical Brain Research Centre for Integrative Neuroscience University Clinic Tübingen Tübingen Germany.

A correction to this article has been published and is linked from the HTML and PDF versions of this paper. The error has been fixed in the paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ZNN -- A Fast and Scalable Algorithm for Training 3D Convolutional Networks on Multi-core and Many-Core Shared Memory Machines

ZNN -- A Fast and Scalable Algorithm for Training 3D Convolu...

引用

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Aleksandar Zlateski Kisuk Lee H. Sebastian Seung Electrical Engineering and Computer Science Dept. Cambridge MA USA Brain and Cognitive Sciences Dept. Massachwsetts Institute of Technology Cambridge MA USA Computer Science Dept. Princeton University Princeton NJ USA

ISBN: (纸本)9781509021413

Convolutional networks (ConvNets) have become a popular approach to computer vision. It is important to accelerate ConvNet training, which is computationally costly. We propose a novel parallel algorithm based on decomposition into a set of tasks, most of which are convolutions or FFTs. Applying Brent's theorem to the task dependency graph implies that linear speedup with the number of processors is attainable within the PRAM model of parallel computation, for wide network architectures. To attain such performance on real shared-memory machines, our algorithm computes convolutions converging on the same node of the network with temporal locality to reduce cache misses, and sums the convergent convolution outputs via an almost wait-free concurrent method to reduce time spent in critical sections. We implement the algorithm with a publicly available software package called ZNN. Benchmarking with multi-core CPUs shows that ZNN can attain speedup roughly equal to the number of physical cores. We also show that ZNN can attain over 90× speedup on a many-core CPU (Xeon Phi™ Knights Corner). These speedups are achieved for network architectures with widths that are in common use. The task parallelism of the ZNN algorithm is suited to CPUs, while the SIMD parallelism of previous algorithms is compatible with GPUs. Through examples, we show that ZNN can be either faster or slower than certain GPU implementations depending on specifics of the network architecture, kernel sizes, and density and size of the output patch. ZNN may be less costly to develop and maintain, due to the relative ease of general-purpose CPU programming.

关键词： Kernel Image edge detection Convolutional codes Transfer functions Training Three-dimensional displays Jacobian matrices

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：