检索结果-内蒙古大学图书馆

Recurrence quantification analysis of dynamic brain networks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Lopes, Marinho A. Zhang, Jiaxiang Krzemiński, Dominik Hamandi, Khalid Chen, Qi Livi, Lorenzo Masuda, Naoki Department of Engineering Mathematics University of Bristol BS8 1UB United Kingdom Cardiff University Brain Research Imaging Centre School of Psychology Cardiff University CardiffCF24 4HQ United Kingdom Center for Studies of Psychological Application School of Psychology South China Normal University Guangzhou510631 China Departments of Computer Science and Mathematics University of Manitoba WinnipegMBR3T 2N2 Canada Department of Computer Science College of Engineering Mathematics and Physical Sciences University of Exeter ExeterEX4 4QF United Kingdom Department of Mathematics University at Buffalo State University of New York United States Computational and Data-Enabled Science and Engineering Program University at Buffalo State University of New York United States

Evidence suggests that brain network dynamics is a key determinant of brain function and dysfunction. Here we propose a new framework to assess the dynamics of brain networks based on recurrence analysis. Our framework uses recurrence plots and recurrence quantification analysis to characterize dynamic networks. For resting-state magnetoencephalographic dynamic functional networks (dFNs), we have found that functional networks recur more quickly in people with epilepsy than healthy controls. This suggests that recurrence of dFNs may be used as a biomarker of epilepsy. For stereo electroencephalography data, we have found that dFNs involved in epileptic seizures emerge before seizure onset, and recurrence analysis allows us to detect seizures. We further observe distinct dFNs before and after seizures, which may inform neurostimulation strategies to prevent seizures. Our framework can also be used for understanding dFNs in brain function in health and other neurological disorders. Copyright © 2020, The Authors. All rights reserved.

关键词： Electroencephalography

SVM-based deep stacking networks

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Wang, Jingyuan Feng, Kai Wu, Junjie MOE Engineering Research Center of Advanced Computer Application Technology School of Computer Science Engineering Beihang University Beijing100191 China Beijing Key Laboratory of Emergency Support Simulation Technologies for City Operations School of Economics and Management Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China

The deep network model, with the majority built on neural networks, has been proved to be a powerful framework to represent complex data for high performance machine learning. In recent years, more and more studies turn to nonneural network approaches to build diverse deep structures, and the Deep Stacking Network (DSN) model is one of such approaches that uses stacked easy-to-learn blocks to build a parameter-training-parallelizable deep network. In this paper, we propose a novel SVM-based Deep Stacking Network (SVM-DSN), which uses the DSN architecture to organize linear SVM classifiers for deep learning. A BP-like layer tuning scheme is also proposed to ensure holistic and local optimizations of stacked SVMs simultaneously. Some good math properties of SVM, such as the convex optimization, is introduced into the DSN framework by our model. From a global view, SVM-DSN can iteratively extract data representations layer by layer as a deep neural network but with parallelizability, and from a local view, each stacked SVM can converge to its optimal solution and obtain the support vectors, which compared with neural networks could lead to interesting improvements in anti-saturation and interpretability. Experimental results on both image and text data sets demonstrate the excellent performances of SVM-DSN compared with some competitive benchmark models. Copyright © 2019, The Authors. All rights reserved.

关键词： Convex optimization

Comparative Study Between Classification Algorithms Based on Prediction Performance 52nd

学校读者我要写书评

暂无评论

Comparative Study Between Classification Algorithms Based on...

52nd Annual Convention of the computer Society of India: Social Transformation - Digital Way, CSI 2017

作者： Hari Narayanan, A.G. Prabhakar, Megha Lakshmi Priya, B. Amar Pratap Singh, J. Department of Computer Application Noorul Isalm Centre for Higher Education Kumaracoil Thucklay KanyakumariTamilnadu629 180 India Department of Computer Science and IT Amrita School of Arts and Sciences Kochi Amrita Vishwa Vidyapeetham Kochi India Department of Computer Science and Engineering Noorul Isalm Centre for Higher Education Kumaracoil Thucklay KanyakumariTamilnadu629 180 India

ISBN: (纸本)9789811313424

In todays "data-centric" world, the prevalence of vast and immeasurable amount of data pertaining to various fields of study has led to the need for properly analyzing and apprehending this information to yield knowledge that becomes useful in decision making. Among the many procedures for handling this multitude of data, "classification" is the one that aids in making decisions based on categorization of data and "feature selection" is the process of picking out attributes relevant to the study. Keeping classification as the central idea of our study, we aim at presenting a comparative analysis of prediction accuracies obtained by two chosen classification algorithms, namely, SVM and RBFN. We proceed to introduce feature selection using both filter and wrapper methods along with SVM and RBFN to showcase a detailed analytical report on variations in performance when using classification algorithms alone, and with application of feature selection. The four approaches used for feature selection in our study are;Information Gain, Correlation, Particle Swarm Optimization (PSO) and Greedy method. Performance of the algorithms under study is evaluated based on time, accuracy of prediction and area under ROC curve. Although time and accuracy are effective parameters for comparison, we propose to consider ROC area as the criterion for performance evaluation. An optimal solution will have the area under ROC curve value approaching 1. © 2018, Springer Nature Singapore Pte Ltd.

关键词： Feature Selection

From digitized whole-slide histology images to biomarker discovery: A protocol for handcrafted feature analysis in brain cancer pathology

学校读者我要写书评

暂无评论

Brain-X

Brain-X 2025年第2期3卷

作者： Lu, Xuanjun Ying, Yawen Chen, Jing Chen, Zhiyang Wu, Yuxin Prasanna, Prateek Chen, Xin Jing, Mingli Liu, Zaiyi Lu, Cheng School of Electronic Engineering Xi'an Shiyou University Shaanxi Xi'an China Department of Medical Research Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences) Southern Medical University Guangdong Guangzhou China Department of Radiology Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences) Southern Medical University Guangdong Guangzhou China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangdong Guangzhou China School of Clinical Dentistry University of Sheffield Sheffield United Kingdom Wallace H. Coulter Department of Biomedical Engineering Georgia Institute of Technology and Emory University Atlanta GA United States Department of Computer Science & Informatics Emory University Atlanta GA United States Department of Biomedical Informatics Stony Brook University Stony Brook NY United States Department of Radiology School of Medicine Guangzhou First People's Hospital South China University of Technology Guangdong Guangzhou China

Hematoxylin and eosin (H&E)-stained histopathological slides contain abundant information about cellular and tissue morphology and have been the cornerstone of tumor diagnosis for decades. In recent years, advancements in digital pathology have made whole-slide images (WSIs) widely applicable for diagnosis, prognosis, and prediction in brain cancer. However, there remains a lack of systematic tools and standardized protocols for using handcrafted features in brain cancer histological analysis. In this study, we present a protocol for handcrafted feature analysis in brain cancer pathology (PHBCP) to systematically extract, analyze, model, and visualize handcrafted features from WSIs. The protocol enabled the discovery of biomarkers from WSIs through a series of well-defined steps. The PHBCP comprises seven main steps: (1) problem definition, (2) data quality control, (3) image preprocessing, (4) feature extraction, (5) feature filtering, (6) modeling, and (7) performance analysis. As an exemplary application, we collected pathological data of 589 patients from two cohorts and applied the PHBCP to predict the 2-year survival of glioblastoma multiforme (GBM) patients. Among the 72 models combining nine feature selection methods and eight machine learning classifiers, the optimal model combination achieved discriminative performance with an average area under the curve (AUC) of 0.615 over 100 iterations under five-fold cross-validation. In the external validation cohort, the optimal model combination achieved a generalization performance with an AUC of 0.594. We provide an open-source code repository (GitHub website: https://***/XuanjunLu/PHBCP) to facilitate effective collaboration between medical and technical experts, thereby advancing the field of computational pathology in brain cancer. © 2025 The Author(s). Brain-X published by John Wiley & Sons Australia, Ltd on behalf of Ainuohui Medical Technology.

关键词： brain cancer pathology handcrafted features protocol whole-slide images

High Speed Wireless Internet Using LiFi

学校读者我要写书评

暂无评论

SSRN

SSRN 2018年

作者： Agarwal, Chinmay M., Kulshrestha H., Rathore J., Kamalakannan Department of Computer Application Vellore Institute of Technology Vellore India School of Computer Science and Engineering Department of Computer Application Vellore India Vellore Institute of Technology Vellore India

The internet has become a basic necessity, so with the advancement in technology, people are demanding something faster than WI-FI. Since light is the only medium that can travel fastest than any other source of data transmission else so if we use this medium for internet, it will be the best utilization of medium with a higher data transmission rate. This technology was implemented over and came out with concept of LI-FI Technology. Li-Fi in known for Light-Fidelity, Li-Fi uses an idea of visible light communication (VLC) technology that uses light as a medium to convey fast high-speed communication in a manner like Wi-Fi. Since visible light is present everywhere, the main idea of our review paper is how LI-FI technology can help in security, speed and reliability of internet and even can change our life style. This innovation is actualized utilizing white LED bulbs matched with the Downlink transmitter that can give a higher information transmission rate up to 10Gbps. The main prospective of this paper demonstrates the forthcoming routine of Li-Fi technology innovation and its highlights to expand the execution of information transmission and different applications where Li-Fi has been put to utilize. © 2018, The Authors. All rights reserved.

关键词： Visible light communication

AlphaStock: A buying-winners-and-selling-losers investment strategy using interpretable deep reinforcement attention networks

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Wang, Jingyuan Zhang, Yang Tang, Ke Wu, Junjie Xiong, Zhang MOE Engineering Research Center of Advanced Computer Application Technology School of Computer Science Engineering Beihang University Beijing China Institute of Economics School of Social Sciences Tsinghua University Beijing China Beijing Key Laboratory of Emergency Support Simulation Technologies for City Operations School of Economics and Management Beihang University Beijing China Beijing Advanced Innovation Center for BDBC Beihang University Beijing China

Recent years have witnessed the successful marriage of finance innovations and AI techniques in various finance applications including quantitative trading (QT). Despite great research efforts devoted to leveraging deep learning (DL) methods for building better QT strategies, existing studies still face serious challenges especially from the side of finance, such as the balance of risk and return, the resistance to extreme loss, and the interpretability of strategies, which limit the application of DL-based strategies in real-life financial markets. In this work, we propose AlphaStock, a novel reinforcement learning (RL) based investment strategy enhanced by interpretable deep attention networks, to address the above challenges. Our main contributions are summarized as follows: i) We integrate deep attention networks with a Sharpe ratio-oriented reinforcement learning framework to achieve a risk-return balanced investment strategy;ii) We suggest modeling interrelationships among assets to avoid selection bias and develop a cross-asset attention mechanism;iii) To our best knowledge, this work is among the first to offer an interpretable investment strategy using deep reinforcement learning models. The experiments on long-periodic U.S. and Chinese markets demonstrate the effectiveness and robustness of AlphaStock over diverse market states. It turns out that AlphaStock tends to select the stocks as winners with high long-term growth, low volatility, high intrinsic value, and being undervalued recently. Copyright © 2019, The Authors. All rights reserved.

关键词： Strategic planning

Sympathetic cooling of a radio-frequency LC circuit to its ground state in an optoelectromechanical system

学校读者我要写书评

暂无评论

Physical Review A 2021年第3期103卷 033516-033516页

作者： Nicola Malossi Paolo Piergentili Jie Li Enrico Serra Riccardo Natali Giovanni Di Giuseppe David Vitali Physics Division School of Science and Technology University of Camerino I-62032 Camerino (MC) Italy INFN Sezione di Perugia via A. Pascoli I-06123 Perugia Italy Kavli Institute of Nanoscience Department of Quantum Nanoscience Delft University of Technology 2628CJ Delft The Netherlands Zhejiang Province Key Laboratory of Quantum Technology and Device Department of Physics and State Key Laboratory of Modern Optical Instrumentation Zhejiang University Hangzhou 310027 China Institute of Materials for Electronics and Magnetism Nanoscience-Trento-FBK Division I-38123 Povo Trento Italy INFN Trento Institute for Fundamental Physics and Application I-38123 Povo Trento Italy Department of Microelectronics and Computer Engineering/ECTM/DIMES Delft University of Technology Feldmanweg 17 2628 CT Delft The Netherlands CNR-INO Largo Enrico Fermi 6 I-50125 Firenze Italy

We present a complete theory for laser cooling of a macroscopic radio-frequency LC electrical circuit by means of an optoelectromechanical system, consisting of an optical cavity dispersively coupled to a nanomechanical oscillator, which is in turn capacitively coupled to the LC circuit of interest. The driven optical cavity cools the mechanical resonator, which in turn sympathetically cools the LC circuit. We determine the optimal parameter regime where the LC resonator can be cooled down to its quantum ground state, which requires a large optomechanical cooperativity, and a larger electromechanical cooperativity. Moreover, comparable optomechanical and electromechanical coupling rates are preferable for reaching the quantum ground state.

关键词： Optomechanics

A Coupled Transformer-CNN Network: Advancing Sea Surface Temperature Forecast Accuracy

学校读者我要写书评

暂无评论

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Zhang, Tao Lin, Pengfei Liu, Hailong Wang, Pengfei Wang, Ya Xu, Kai Zheng, Weipeng Li, Yiwen Jiang, Jinrong Zhao, Lian Chen, Jian State Key Laboratory of Earth System Numerical Modeling and Application Institute of Atmospheric Physics Chinese Academy of Sciences Beijing100029 China College of Earth and Planetary Sciences University of Chinese Academy of Sciences Beijing100049 China Laoshan Laboratory Qingdao266237 China Institute of Atmospheric Physics Chinese Academy of Sciences Beijing100029 China Earth System Numerical Simulation Science Center Institute of Atmospheric Physics Chinese Academy of Sciences Beijing100029 China School of Ocean Sciences China University of Geosciences Beijing100083 China Computer Network Information Center Chinese Academy of Sciences Beijing100190 China State Key Laboratory of Geo-Information Engineering Xi'an710054 China

Sea surface temperature (SST) is critically important for understanding ocean dynamics and supporting various marine activities, making accurate short-term SST forecasting highly significant. However, accurately modeling the multi-scale variability of SST remains challenging for existing deep learning (DL) models. This study introduces the Coupled Transformer-CNN Network (CoTCN), a hybrid architecture designed to leverage the multi-scale variability of SST. The CoTCN combines the strengths of Transformers and convolutional neural networks (CNNs), significantly enhancing SST forecasts' spatial continuity and predictive accuracy. Compared to five state-of-the-art DL models based on Transformer or CNN that include ConvLSTM, ConvGRU, AFNO, PredRNN, and SwinLSTM, CoTCN demonstrates superior performance in global and local areas of SST forecasting. At 1-day lead time, CoTCN reduces the global average root mean square error (RMSE) by over 15%, with forecast errors ranging from 0.20°C to 0.53°C across 1-10 day lead times. Moreover, the CoTCN effectively mitigates the checkerboard artifacts inherent to the Vision Transformer architecture. These findings highlight the effectiveness of CoTCN in capturing SST's multi-scale features and underscore the promising potential of hybrid architectures for future DL models. © 1980-2012 IEEE.

关键词： Convolutional neural networks

A performance evaluation of correspondence grouping methods for 3D rigid data matching

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Yang, Jiaqi Xian, Ke Wang, Peng Zhang, Yanning School of Computer Science Northwestern Polytechnical University National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi'an710129 China National Key Laboratory of Science and Technology on Multi-spectral Information Processing School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

Seeking consistent point-to-point correspondences between 3D rigid data (point clouds, meshes, or depth maps) is a fundamental problem in 3D computer vision. While a number of correspondence selection methods have been proposed in recent years, their advantages and shortcomings remain unclear regarding different applications and perturbations. To fill this gap, this paper gives a comprehensive evaluation of nine state-of-the-art 3D correspondence grouping methods. A good correspondence grouping algorithm is expected to retrieve as many as inliers from initial feature matches, giving a rise in both precision and recall as well as facilitating accurate transformation estimation. Toward this rule, we deploy experiments on three benchmarks with different application contexts including shape retrieval, 3D object recognition, and point cloud registration together with various perturbations such as noise, point density variation, clutter, occlusion, partial overlap, different scales of initial correspondences, and different combinations of keypoint detectors and descriptors. The rich variety of application scenarios and nuisances result in different spatial distributions and inlier ratios of initial feature correspondences, thus enabling a thorough evaluation. Based on the outcomes, we give a summary of the traits, merits, and demerits of evaluated approaches and indicate some potential future research directions. Copyright © 2019, The Authors. All rights reserved.

关键词： Benchmarking