检索结果-内蒙古大学图书馆

2019第二届算法、计算和人工智能国际会议

作者： Zheng Chen Ruiwen Tao Xiaoyang Wu Zhimin Wei Xiao Luo School of Information & Software Engineering University of Electronic Science & Technology of China National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu Sichuan China

Deep learning has yielded state-of-the-art performance on text classification tasks. In this paper, a new neural network based on Long-Short-Term-Memory model is applied to classify spam emails. Using deep learning method to classify spam emails requires large amounts of labeled data. To solve this problem, active learning method is used to reduce labeling cost and increase model adaptability. In this paper, it is found that the new model performs better than standard CNNs and RNNs on email classification task, and active learning methods can match stateof-the-art performance with just 10% of the labeled data.

关键词： Spam email classification active learning LSTM

来源：评论

学校读者我要写书评

暂无评论

Community-Grouping Based Particle Swarm optimisation Algorithm for Feature Selection

Community-Grouping Based Particle Swarm optimisation Algorit...

引用

Congress on Evolutionary Computation

作者： Jianfeng Qiu Jiangchuan Wan Lei Zhang Fan Cheng Yongkang Luo Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University China School of Computer Science and Technology Anhui University Hefei China

ISBN: (数字)9781728169293

ISBN: (纸本)9781728169309

As a frequently-used dimensionality reduction technique in machine learning, feature selection has attracted interests in the last decade. Since feature selection is essentially a combinatorial optimization problem, how to search the valuable feature subset is a challenging optimization task. Particle swarm optimization (PSO) algorithm and its variations have shown their competitiveness in solving feature selection problem. However, they have been proven to be easily trapped into the local optimal in high-dimensional space due to their intrinsic characteristic of quick convergence. To this end, an effective binary particle swarm optimization algorithm, named CBPSOFS, is proposed for feature selection, where a community-grouping based adaptive updating strategy is designed to avoid trapping into the local optimum and enhance the performance of PSO algorithm in feature selection. To be specific, the correlationship among features is used to construct the feature network, where multiple feature groups are obtained by dividing the achieved feature network. Considering that a community usually contains multiple similar features, the proposed adaptive updating strategy utilizes these feature groups to make the similar features not be included in the same particle so as to maintain the diversity of the population in the evolution. In addition, an information gain based initialization strategy and a history information based resetting strategy are also developed to improve the quality of obtained feature subset. Experimental results on several real world datasets have demonstrated the effectiveness of CBPSOFS in feature selection when compared with the several state-of-the-art baselines.

关键词： Feature extraction Sociology Statistics Particle swarm optimization Optimization History signal processing algorithms

来源：评论

学校读者我要写书评

暂无评论

Enhanced Beamforming via Bayesian Postprocessing

Enhanced Beamforming via Bayesian Postprocessing

引用

OCEANS

作者： Chennan Shi Jun Tao Key Laboratory of Underwater Acoustic Signal Processing of the Ministry of Education School of Information Science and Engineering Southeast University Nanjing China Acoustic Science and Technology Laboratory Harbin Engineering University Harbin China

ISBN: (数字)9781728154466

ISBN: (纸本)9781728184098

A Bayesian postprocessing (BP) scheme for improving beamforming performance is proposed. It is implemented as a signal beam power estimator at a beamformer output based on the Bayesian minimum mean square error (BMMSE) criterion, boosting signal components by suppressing noise and interferences. The BMMSE estimation of the signal beam power boils down to the track of the noise-plus-interference power and the signal-to-interference-plus-noise ratio (SINR), which are achieved with the minimum-statistics (MS) method and the decision-directed approach (DDA), respectively. The Bayesian postprocessing scheme is applied to the conventional beamforming (CBF), leading to the BP-CBF. Simulation results showed the BP-CBF significantly outperforms the CBF without sacrificing its robustness to signal mismatch.

关键词： Array signal processing Simulation Estimation Mean square error methods Robustness Bayes methods signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Weakly Supervised Joint Whole-Slide Segmentation and Classification in Prostate Cancer

arXiv

引用

arXiv 2023年

作者： Pati, Pushpak Jaume, Guillaume Ayadi, Zeineb Thandiackal, Kevin Bozorgtabar, Behzad Gabrani, Maria Goksel, Orcun IBM Research Europe Switzerland Department of Pathology Brigham and Women’s Hospital Harvard Medical School United States Department of Pathology Massachusetts General Hospital Harvard Medical School United States Cancer Program Broad Institute of Harvard MIT United States Data Science Program Dana-Farber Harvard Cancer Center United States Computer-Assisted Applications in Medicine ETH Zurich Switzerland Signal Processing Laboratory 5 EPFL Switzerland EPFL Switzerland Department of Information Technology Uppsala University Sweden

The segmentation and automatic identification of histological regions of diagnostic interest offer a valuable aid to pathologists. However, segmentation methods are hampered by the difficulty of obtaining pixel-level annotations, which are tedious and expensive to obtain for Whole-Slide images (WSI). To remedy this, weakly supervised methods have been developed to exploit the annotations directly available at the image level. However, to our knowledge, none of these techniques is adapted to deal with WSIs. In this paper, we propose WHOLESIGHT, a weakly-supervised method, to simultaneously segment and classify WSIs of arbitrary shapes and sizes. Formally, WHOLESIGHT first constructs a tissue-graph representation of the WSI, where the nodes and edges depict tissue regions and their interactions, respectively. During training, a graph classification head classifies the WSI and produces node-level pseudo labels via post-hoc feature attribution. These pseudo labels are then used to train a node classification head for WSI segmentation. During testing, both heads simultaneously render class prediction and segmentation for an input WSI. We evaluated WHOLESIGHT on three public prostate cancer WSI datasets. Our method achieved state-of-the-art weakly-supervised segmentation performance on all datasets while resulting in better or comparable classification with respect to state-of-the-art weakly-supervised WSI classification methods. Additionally, we quantify the generalization capability of our method in terms of segmentation and classification performance, uncertainty estimation, and model calibration. © 2023, CC BY-NC-ND.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Dynamic Compressive Sensing Based Adaptive Equalization for Underwater Acoustic Communications

Dynamic Compressive Sensing Based Adaptive Equalization for ...

引用

OCEANS

作者： Zhen Qin Jun Tao Xiao Han Key Laboratory of Underwater Acoustic Signal Processing of the Ministry of Education School of Information Science and Engineering Southeast University Nanjing China Acoustic Science and Technology Laboratory Harbin Engineering University Harbin China

ISBN: (数字)9781728154466

ISBN: (纸本)9781728184098

The wide-sense sparsity of a direct adaptive equalizer (DAE) for single-carrier underwater acoustic (UWA) communications has been recognized and utilized to reduce the equalization complexity via the idea of partial tap updating (PTU). Existing PTU schemes run in a batch mode so positions of the partial taps to be updated, once chosen, remain unchanged over a block. Under harsh channel conditions, however, the sparse structure of a DAE may change even within one block and existing PTU schemes will fail. This fact motivates us to seek a way to track also the dynamics of the DAE structure, in addition to its coefficients. In this paper, we propose to adopt the dynamic compressed sensing (DCS) technique to achieve the aforementioned goal. Specifically, the sparse adaptive orthogonal matching pursuit (SpAdOMP) as a typical greedy-type DCS algorithm, is employed. The taps of the resulting SpAdOMP DAE are updated with the affine projection algorithm (APA), leading to the SpAdOMP-APA-DAE. The SpAdOMP-APA-DAE was tested by experimental data collected in an at-sea UWA communication trial. Experimental results showed it significantly outperformed existing DAEs attributed to tracking only significant DAE taps while dropping negligible ones.

关键词： Heuristic algorithms Matching pursuit algorithms Adaptive equalizers Complexity theory Underwater acoustics Projection algorithms Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Multi-compartment diffusion MRI, T2 relaxometry and myelin water imaging as neuroimaging descriptors for anomalous tissue detection

arXiv

引用

arXiv 2021年

作者： Fischi-Gomez, Elda Rafael-Patino, Jonathan Pizzolato, Marco Piredda, Gian Franco Hilbert, Tom Kober, Tobias Canales-Rodriguez, Erick J. Thiran, Jean-Philippe Signal Processing Laboratory 5 Swiss Federal Institute of Technology Lausanne Lausanne Switzerland Department of Applied Mathematics and Computer Science Technical University of Denmark Kongens Lyngby Denmark Advanced Clinical Imaging Technology Siemens Healthcare AG Lausanne Switzerland Department of Radiology Lausanne University Hospital University of Lausanne Switzerland

Multiple sclerosis (MS) is an inflammatory and neurodegenerative disease characterized by diffuse and focal areas of tissue loss. Conventional MRI techniques such as T1-weighted and T2-weighted scans are generally used in the diagnosis and prognosis of the disease. Yet, these methods are limited by the lack of specificity between lesions, its perilesional area and non-lesional tissue. Alternative MRI techniques exhibit a higher level of sensitivity to focal and diffuse MS pathology than conventional MRI acquisitions. However, they still suffer from limited specificity when considered alone. In this work, we have combined tissue microstructure information derived from multicompartment diffusion MRI and T2 relaxometry models to explore the voxel-based prediction power of a machine learning model in a cohort of MS patients and healthy controls. Our results show that the combination of multi-modal features, together with a boosting enhanced decision-tree based classifier, which combines a set of weak classifiers to form a strong classifier via a voting mechanism, is able to utilise the complementary information for the classification of abnormal tissue. Copyright © 2021, The Authors. All rights reserved.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

Sparse Bayesian Learning for Distributed Passive Radar Imaging via Covariance Sparse Representation

Sparse Bayesian Learning for Distributed Passive Radar Imagi...

引用

Asian and Pacific Conference on Synthetic Aperture Radar (APSAR)

作者： Fukang Gong Shunsheng Zhang Qing He Research Institute of Electronic Science and Technology University of Electronic Science and Technology of China Chengdu China National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu China

ISBN: (数字)9781728129129

ISBN: (纸本)9781728129136

Due to low imaging cost and robustness, the distributed passive radars using multiple transmitters and multiple receivers to observe targets have become a hot research. In the case of low SNR, the imaging accuracy of the distributed passive radar imaging model via Orthogonal Matching Pursuit (OMP) sparse reconstruction is low. For this problem, a framework consisting of sparse representation of the received multi-snapshot radar signal covariance matrix, Sparse Bayesian Learning (SBL) based reconstruction algorithm has been built. At the end of paper, through the simulation experiment, the imaging results of the original data and covariance data at low SNR are compared, and the reconstruction errors under different SNR are used to verify the effectiveness of the proposed algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimized Gain of One-Pump Fiber Optical Parametric Amplifier by using Genetic Algorithm with Pump Depletion

Optimized Gain of One-Pump Fiber Optical Parametric Amplifie...

引用

Asia Communications and Photonics Conference and Exhibition (ACP)

作者： Zhenyu Zhu Jinli Zhang Hao Sui Le Cheng Hongna Zhu Xiaorong Gao School of Physical Science and Technology Southwest Jiaotong University Chengdu China National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu Sichuan China

An optimized method to determine the parameters of one-pump fiber optical parametric amplifier with pump depletion is illustrated by using genetic algorithm. The gain with wide bandwidth and high peak gain is obtained.

ISBN: (纸本)9781943580705

关键词： Genetic algorithms Nonlinear optical fibers Nonlinear parametric processes Numerical analysis Optical amplifiers Optical fibers

来源：评论

学校读者我要写书评

暂无评论

Improved Matrix-based Attribute Reduction Algorithm Based on Minimal Elements for Mobile Edge Computing

Improved Matrix-based Attribute Reduction Algorithm Based on...

引用

IEEE/ACM International Symposium on Cluster Computing and the Grid (CCGRID)

作者： Yi Xu Zhiqiang Zheng Yan Cheng Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei China School of Computer Science and Technology Anhui University Hefei China

ISBN: (数字)9781728160955

ISBN: (纸本)9781728196497

With the development of Internet of Thlngs(IoT) technology, the Mobile Edge Computing (MEC) environment plays an important role in different scenarios. This paper focus on the "last-mile" delivery scenario in logistics. In this scenario, due to the limited computation ability of the unmanned aerial vehicle (UAV), high real-time and computational resource-intensive tasks such as obstacle avoidance, route planning, and face recognition are require the assistance by MEC computing resources. However, due to the limited computing power of edge servers, the computing tasks of neural networks has very high delay. It cause the deadline of neural networks computation task may not be satisfied. Besides with the users and environment changed continuously, the neural nework take a long time to update which may affect the work of UAV. Therefore, It is an critical problem to accelerate the calculation and update of neural network on edge server. This paper proposes an attribute reduction algorithm based on rough set, which can reduce redundant attributes and compress the dimensionality of data. The experimental results show that can accelerate the calculation and update of neural network significantly and save the energy consumption.

关键词： Servers Edge computing Task analysis Neural networks Energy consumption Information systems Rough sets

来源：评论

学校读者我要写书评

暂无评论

A Real-Time Dereverberation Algorithm Combined with Echo Cancellation

A Real-Time Dereverberation Algorithm Combined with Echo Can...

引用

International Conference on Measuring technology and Mechatronics Automation, ICMTMA

作者： Xia Wang Shuangshuang Zhu Li Zhao School of Information Science and Technology Nantong University Nantong China Key Laboratory of Underwater Acoustic Signal Processing of Ministry of Education Southeast University Nanjing China

ISBN: (数字)9781728170817

ISBN: (纸本)9781728170824

In order to improve the output speech quality of the near-end signal collected in the real-time communication system, a reverberation suppression algorithm with low computation is proposed. Firstly, the algorithm uses the adaptive filter of the echo canceller to model the room response. Secondly, using the linear fitting method, the reverberation time is estimated according to the modeled impulse. Then, a adaptive filter is used to estimate the echo signal and thus the error signal is obtained. Finally, the spectral subtraction method is used to obtain the estimated pure signal. Experimental results validated the efficiency of the proposed algorithm. The near-end speech can be obtained with less amount of calculation comparing to other similar algorithms.

关键词：

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：