检索结果-内蒙古大学图书馆

Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence

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

ISBN: (纸本)9781450372619

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 state-of-the-art performance with just 10% of the labeled data.

关键词： LSTM

来源：评论

学校读者我要写书评

暂无评论

Software in the natural world: A computational approach to hierarchical emergence

arXiv

引用

arXiv 2024年

作者： Rosas, Fernando E. Geiger, Bernhard C. Luppi, Andrea I. Seth, Anil K. Polani, Daniel Gastpar, Michael Mediano, Pedro A.M. Department of Informatics University of Sussex United Kingdom Sussex Centre for Consciousness Science and Sussex AI University of Sussex United Kingdom Center for Psychedelic Research and Centre for Complexity Science Department of Brain Science Imperial College London United Kingdom Center for Eudaimonia and Human Flourishing University of Oxford United Kingdom Know-Center GmbH Graz Austria Signal Processing and Speech Communication Laboratory Graz University of Technology Graz Austria Montreal Neurological Institute McGill University Canada Department of Computer Science University of Hertfordshire Hatfield United Kingdom School of Computer and Communication Sciences EPFL Lausanne Switzerland Department of Computing Imperial College London United Kingdom Division of Psychology and Language Sciences University College London United Kingdom

Understanding the functional architecture of complex systems is crucial to illuminate their inner workings and enable effective methods for their prediction and control. Recent advances have introduced tools to characterise emergent macroscopic levels;however, while these approaches are successful in identifying when emergence takes place, they are limited in the extent they can determine how it does. Here we address this important limitation by developing a computational approach to emergence, which characterises macroscopic processes in terms of their computational capabilities. Concretely, we articulate a view on emergence based on how software works, which is rooted on a mathematical formalisation of how macroscopic processes can express self-contained informational, interventional, and computational properties. This framework reveals a hierarchy of nested self-contained processes that determines what computations take place at what level, which in turn delineates the functional architecture of a complex system. This approach is illustrated on paradigmatic models from the statistical physics and computational neuroscience literature, which are shown to exhibit macroscopic processes that are akin to software in human-engineered systems. Overall, this framework enables a deeper understanding of the multi-level structure of complex systems, revealing specific ways in which they can be efficiently simulated, predicted, and controlled. Copyright © 2024, The Authors. All rights reserved.

关键词： Statistical Physics

来源：评论

学校读者我要写书评

暂无评论

Disentangled Generation Network for Enlarged License Plate Recognition and A Unified Dataset

arXiv

引用

arXiv 2022年

作者： Li, Chenglong Yang, Xiaobin Wang, Guohao Zheng, Aihua Tan, Chang Jia, Ruoran Tang, Jin Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Key Lab of Intelligent Computing and Signal Processing Ministry of Education Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China iFLYTEK Co. Ltd. Hefei230088 China

License plate recognition plays a critical role in many practical applications, but license plates of large vehicles are difficult to be recognized due to the factors of low resolution, contamination, low illumination, and occlusion, to name a few. To overcome the above factors, the transportation management department generally introduces the enlarged license plate behind the rear of a vehicle. However, enlarged license plates have high diversity as they are non-standard in position, size, and style. Furthermore, the background regions contain a variety of noisy information which greatly disturbs the recognition of license plate characters. Existing works have not studied this challenging problem. In this work, we first address the enlarged license plate recognition problem and contribute a dataset containing 9342 images, which cover most of the challenges of real scenes. However, the created data are still insufficient to train deep methods of enlarged license plate recognition, and building large-scale training data is very time-consuming and high labor cost. To handle this problem, we propose a novel task-level disentanglement generation framework based on the Disentangled Generation Network (DGNet), which disentangles the generation into the text generation and background generation in an end-to-end manner to effectively ensure diversity and integrity, for robust enlarged license plate recognition. Extensive experiments on the created dataset are conducted, and we demonstrate the effectiveness of the proposed approach in three representative text recognition frameworks. © 2022, CC BY.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

On Error Performance and Concatenated Coding of Polar Codes in AWGN Channels

On Error Performance and Concatenated Coding of Polar Codes ...

引用

第四届遥感与无线通信国际会议

作者： Jing Jin Rui Deng Tiansheng Liu Liping Li Key Laboratory of Intelligent Computing and Signal Processing (Ministry of Education) Anhui University Department of Electronic Engineering and Information Science University of Science and Technology

In additive white Gaussian noise（AWGN） channels, construction of polar codes is needed for every operating signal-to-noise ratio（SNR）. Recently, the proposal of the design-SNR reduces the computation effort in constructing polar codes. In this paper, we prove that although the BER performance of the design-SNR construction is not affected, the packet-error-rate（PER） performance is degraded compared with the point-by-point construction. Therefore, a concatenation scheme is proposed to improve the degraded PER performance. Results show the validity of the proposed concatenation scheme when employing the design-SNR construction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Joint multi-task cascade for instance segmentation

Joint multi-task cascade for instance segmentation

引用

作者： Wen, Yaole Hu, Fuyuan Ren, Jinchang Shang, Xinru Li, Linyan Xi, Xuefeng School of Electronic & Information Engineering Suzhou University of Science and Technology SuzhouJiangsu215009 China Centre for Signal and Image Processing University of Strathclyde Glasgow United Kingdom Suzhou Institute of Trade & Commerce SuzhouJiangsu215009 China Virtual Reality Key Laboratory of Intelligent Interaction and Application Technology of Suzhou Suzhou University of Science and Technology SuzhouJiangsu215009 China Suzhou Key Laboratory for Big Data and Information Service Suzhou University of Science and Technology SuzhouJiangsu215009 China

Instance segmentation requires both pixel-level classification accuracy and high-level semantic features at the target instance level, which is very challenging, and the cascade structure can effectively improve both of these problems. To make full use of the relationship between detection and segmentation, this paper proposes a joint multi-tasking cascade structure, which is not simply to cascade the two tasks of detection and segmentation, but to unitedly put them into multi-stage processing, and especially to integrate the information at different stages of the mask branch. The entire structure can effectively utilize the superior characteristics of each stage in the matter of detection and segmentation, thus improving the quality of mask prediction. The feature fusion process is introduced in the full convolution networks (FCN) branch, and the high-level and low-level features are effectively fused to enhance the contextual information of the picture semantic features. The experiments demonstrate the better results on the COCO dataset. © 2020, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Uncertainty estimation by boosting with Gaussian process for expensive optimization problems

引用

Applied Soft Computing 2025年 180卷

作者： Zou, Hanhua Zeng, Sanyou Li, Changhe Jiao, Ruwang Zhao, Fei School of Mechanical Engineering and Electronic Information China University of Geosciences Wuhan China School of Artificial Intelligence Anhui University of Science & Technology Hefei China School of Future Science and Engineering Soochow University Suzhou China National Key Laboratory of Blind Signal Processing Chengdu China

In surrogate-assisted evolutionary algorithms (SAEAs), uncertainty measures the confidence level of the predicted fitness and plays an important role in selecting candidate points for expensive evaluation, as evaluating those with a large degree of uncertainty can enhance the exploration ability of algorithms and significantly improve model reliability. Gaussian process (GP) gains great popularity with a predictive variance to estimate uncertainty. However, the performance of GP-assisted SAEAs is still limited with weakened predictions and underutilized uncertainty. In this paper, we propose a novel SAEA that leverages a boosting ensemble with GP as the base learner to enhance optimization performance. First, GP is leveraged to boost a weak learner that captures global trends, refining its prediction in guiding the search. Then, the uncertainty provided by GP is integrated into boosting ensemble model to estimate its overall ensemble uncertainty, enhancing the model reliability and promoting the exploration capabilities. Moreover, a mechanism study is performed through standardized residual and a distance-based metric to have deep insights into search behaviors, demonstrating that the migrated uncertainty basically covers the statistical boundary of Gaussian distribution and contributes to exploitation and exploration trade-off. Experimental results across multiple benchmark problems and an antenna design problem demonstrate that the proposed method significantly enhanced GP-assisted SAEAs in statistical results of the best fitness value and convergence profile without increasing too much running time, particularly in high-dimensional problems. © 2025 Elsevier B.V.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Precise irrigation of dryland cotton under canal irrigation system constraints based on the CERES-CROPGRO-Cotton model

引用

Agricultural Water Management 2025年 317卷

作者： Lei Wang Liang He Weihong Sun Chen Gao Zhenxiang Han Meiwei Lin School of Computer Science and Technology Xinjiang University Urumqi 830017 China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi 830017 China Department of Electronic Engineering and Beijing National Research Center for Information Science and Technology Tsinghua University Beijing 100084 China School of Agricultural Engineering Jiangsu University Zhenjiang 212013 China

Xinjiang agriculture faces significant challenges due to water resource scarcity and uneven distribution, making accurate predictions of irrigation's impact on cotton yield crucial for decision-making. Existing studies primarily examine the relationship between irrigation and soil but often overlook the combined effects of irrigation networks, time constraints, and the interactions between crop growth patterns, weather, soil, and irrigation strategies. This study integrates the Decision Support System for Agrotechnology Transfer (DSSAT) model with machine learning models, accounting for weather, soil, crop conditions, and irrigation time constraints, to propose an intelligent irrigation decision-making framework. Meteorological data from 1980 to 2024, 13 sets of soil data, and field experiments conducted in 2023 and 2024 were used to calibrate the DSSAT model (with a calibration rate of 0.856). Additionally, water channel quota time constraints were established to determine the optimal irrigation timing. The framework analyzes the interactions between weather, soil, irrigation strategies, and other factors, enhancing cotton yield prediction. The results indicate that the intelligent decision-making algorithm outperforms traditional methods under data limitations, reducing the irrigation water consumption-yield ratio ( U i ) by 3.99 %, while increasing yield by 8.5 % to 9724 kg/ha, thus achieving both water-saving and yield-enhancing objectives. This research offers a refined solution for intelligent irrigation decision-making in cotton cultivation in arid regions and paves the way for the application of intelligent agricultural decision systems.

关键词： Precise agricultural water management Intelligent irrigation decision-making Production forecasts DSSAT

来源：评论

学校读者我要写书评

暂无评论

Active learning for spam email classification 2

Active learning for spam email classification

引用

2nd International Conference on Algorithms, Computing and Artificial Intelligence, ACAI 2019

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

ISBN: (纸本)9781450372619

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

In-Silico Trained AI for Enhanced T2 Spectrum Imaging and Myelin Water Fraction Mapping in Preclinical 7T MRI

In-Silico Trained AI for Enhanced T2 Spectrum Imaging and My...

引用

IEEE International Symposium on Biomedical Imaging

作者： Daniel Vallejo-Aldana Alonso Ramírez-Manzanares Erick J. Canales-Rodríguez Thomas Yu Abraham Cisneros-Mejorado Luis Concha Jonathan Rafael-Patiño Jean-Philippe Thiran Computer Science Department Centro de Investigación en Matemáticas A.C Guanajuato México Signal Processing Laboratory (LTS5) École Polytechnique Fédérale de Lausanne (EPFL) Lausanne Switzerland Advanced Clinical Imaging Technology Siemens Healthineers International AG Lausanne Switzerland Instituto de Neurobiología Universidad Nacional Autónoma de México Juriquilla México Radiology Department Centre Hospitalier Universitaire Vaudois and University of Lausanne Lausanne Switzerland CIBM Center for Biomedical Imaging Switzerland

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

This study introduces a Machine Learning (ML) approach for estimating the T 2 spectrum and myelin water fraction (MWF) using multi-echo T 2 (MET 2 ) data from preclinical 7T Magnetic Resonance Imaging (MRI) scanners. ML methods have shown promise in MWF estimation, outperforming Regularized Non-Negative Least Squares (RNNLS). However, existing ML methods were optimized for high signal-to-noise ratios (SNR) typical of 3T clinical MET 2 data with larger voxel sizes. We adapted the Model-Informed Machine Learning (MIML) method to handle challenges in preclinical 7T MRI, including reduced voxel sizes, elevated noise levels (SNR=30-60), and shifts in T 2 lobes. Results from in-silico simulated data demonstrate the superior performance of the proposed multi-layer-perceptron-based solution over RNNLS. Validation with ME T 2 data from two mice—a healthy control and a cuprizone-exposed pathological mouse—confirms the ML method’s success in identifying cuprizone-induced demyelination. Our study showcases the adaptability and enhanced performance of the MIML approach under challenging preclinical 7T MRI conditions, contributing to the advancement of MWF estimation methods in high-field MRI settings.

关键词： Maximum likelihood estimation Pathology Adaptation models Magnetic resonance imaging Machine learning Brain modeling signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Kalmannet: Data-Driven Kalman Filtering

Kalmannet: Data-Driven Kalman Filtering

引用

IEEE International Conference on Acoustics, Speech and signal processing

作者： Guy Revach Nir Shlezinger Ruud J. G. van Sloun Yonina C. Eldar Signal Processing Laboratory (ISI) ETH Zurich Switzerland School of ECE Ben-Gurion University of the Negev Beer Sheva Israel Eindhoven University of Technology and with Phillips Research Eindhoven The Netherlands Faculty of Math and CS Weizmann Institute of Science Rehovot Israel

ISBN: (纸本)9781728176055;9781728176062

The Kalman filter (KF) is a celebrated signal processing algorithm, implementing optimal state estimation of dynamical systems that are well represented by a linear Gaussian state-space model. The KF is model-based, and therefore relies on full and accurate knowledge of the underlying model. We present KalmanNet, a hybrid data-driven/model-based filter that does not require full knowledge of the underlying model parameters. KalmanNet is inspired by the classical KF flow and implemented by integrating a dedicated and compact neural network for the Kalman gain computation. We present an offline training method, and numerically illustrate that KalmanNet can achieve optimal performance without full knowledge of the model parameters. We demonstrate that when facing inaccurate parameters KalmanNet learns to achieve notably improved performance compared to KF.

关键词： Training Computational modeling signal processing algorithms signal processing Filtering algorithms Numerical models State-space methods

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：