检索结果-内蒙古大学图书馆

3rd International Conference on Pattern Recognition and Machine Learning, PRML 2022

作者： Zeng, Ailing Ablimit, Mijit Hamdulla, Askar School of Information Science and Engineering Xinjiang University of China China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China Xinjiang Key Laboratory of Multilingual Information Technology China

ISBN: (数字)9781665499507

ISBN: (纸本)9781665499507

Language identification process is necessary for the downstream tasks of cross lingual and multi-lingual application. This paper proposes a language recognition method based on ResNet-CA-BiGRU-Attention model. Firstly, the speech signal is converted into the corresponding spectrogram, and then the residual network is used for feature extraction according to the distribution of speech energy on the spectrogram. Coordinate Attention and Attention are used to highlight corelated features and suppress irrelevant features. In this paper, five languages are selected from the Common Voice data set. Experimental results show that the proposed language recognition method based on ResNet-CA-BiGRU-Attention model can effectively improve the performance of language recognition. © 2022 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Language Identification in Overlapped Multi-lingual Speeches 3

Language Identification in Overlapped Multi-lingual Speeches

引用

3rd International Conference on Pattern Recognition and Machine Learning, PRML 2022

作者： Aysa, Zuhragvl Ablimit, Mijit Hamdulla, Askar School of Information Science and Engineering Xinjiang University of China China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China Xinjiang Key Laboratory of Multilingual Information Technology China

ISBN: (数字)9781665499507

ISBN: (纸本)9781665499507

Speech, languages, and background voices are overlapped in the multi-speaker environment. The speech separation process is necessary for downstream applications like language and speaker identification and ASR tasks. A combined speech separation and language recognition approach is proposed in this paper. First, the monolingual information is extracted from a multi-speaker multilingual speech scenario, then fed the separated speech to a language identification model. The speech separation model is trained in a single-channel overlapped speech data, and the language identification model is trained in Oriental language corpus. The combined effect of these two models is evaluated in the task of language identification. When the language recognition network is fed with the audio spectrograms separated by the source separation network, the Chinese and Korean language recognition results are significantly improved in terms of accuracy and recall rate than the mixed audio spectrograms. © 2022 IEEE.

关键词： Source separation

来源：评论

学校读者我要写书评

暂无评论

Autofocus-Coupled UTAMP for Sparse Aperture ISAR Imaging

Autofocus-Coupled UTAMP for Sparse Aperture ISAR Imaging

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Hailong Kang Liang Xu Tuoyu Shen Jun Li Marco Martorella The Hangzhou Institute of Technology Xidian University Hangzhou China The National Key Laboratory of Radar Signal Processing Xidian University Xi’an China Radar and Surveillance Systems (RaSS) Laboratory (CNIT) Pisa Italy Department of Electronic Electrical and Systems Engineering University of Birmingham Birmingham UK

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Autofocusing is an important step for inverse synthetic aperture radar (ISAR) imaging, while traditional autofocusing algorithms often fail in sparse aperture (SA) case. The residual phase error due to the imperfect motion compensation cannot be ignored for the compressive sensing (CS) based SA ISAR imaging. To tackle this issue, an autofocus-coupled approximate message passing with unitary transformation (AFUTAMP) algorithm for SA ISAR imaging is proposed in this paper. The phase error estimation process is introduced to the UTAMP framework for autofocusing, which enable UTAMP to simultaneously complete ISAR image reconstruction and autofocus, thereby leading to excellent performance of imaging and autofocusing. The effectiveness and superiority of the proposed algorithm are verified by the simulation results and experimental results based on measured data.

关键词： Simulation Message passing Imaging Geoscience and remote sensing Apertures radar imaging Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Power Big Data–Based Combination Forecast Method for Medium-Long Term Power 12th

Power Big Data–Based Combination Forecast Method for Medium...

引用

12th International Conference on Computer Engineering and Networks, CENet 2022

作者： Yuan, Zhonghui Lu, Zhiqing Zhao, Jiyuan Lu, Lucong School of Information and Communication Guilin University of Electronic Science and Technology Guilin541004 China Guangxi Key Laboratory of Wireless Broadband Communication and Signal Processing Guilin University of Electronic Science and Technology Guilin541004 China

ISBN: (纸本)9789811969003

The power grid will generate massive data in the process of power generation, transmission, transformation and power consumption. It is directly related to the development of the power grid to make use of power big data to forecast power system in the medium and long term. In the past, many researchers used a single model to predict power. However, in the context of big data, power grid data is generated in many different environments and times, and no single prediction model can guarantee satisfactory prediction results for the big data generated at any time and in any environment. To improve the accuracy of power prediction, a medium and long-term power prediction method based on LSTM, gray scale prediction model and LSSVM is proposed in this paper. The proposed combination method first calculates the weights of the prediction results of different models by means of the variance-covariance method, and then fusions the final prediction results by weighting. To verify the effectiveness of the combined model, a medium- and long-term power prediction experiment is carried out. The experimental result shows that the prediction accuracy of the proposed combined prediction model is higher than the prediction of each single prediction model in accuracy. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

HNet: A Loss Rate Robust ISAR Imaging Framework Based on Hypernetwork

引用

IEEE Transactions on Aerospace and Electronic Systems 2025年

作者： Li, Xiaoyong Liu, Lei Huang, Jiale Li, Lei Bai, Xueru Zhou, Feng Xidian University Hangzhou Institute of Technology Hangzhou311231 China Xidian University Key Laboratory of Electronic Information Countermeasure and Simulation Technology of Ministry of Education Xi'an710071 China Xidian University National Key Lab of Radar Signal Processing Xi'an710071 China Xidian University School of Aerospace Science and Technology Xi'an710071 China

Deep learning has significantly advanced the field of sparse inverse synthetic aperture radar (ISAR) imaging. Nonetheless, current methodologies often face constraints due to their reliance on fixed loss rates and types, which can limit practical applicability and result in elevated computational demands both spatially and temporally, as well as diminished generalizability. In tackle to these challenges, this paper introduces a resilient ISAR imaging architecture grounded in hypernetwork technology capable of accommodating diverse loss rates. Initially, we devise a sparse signal reconstruction technique that functions irrespective of the loss rate or matrix dimensions. Subsequently, a methodology for producing arbitrary loss rates is outlined. Building upon this foundation, we present a hypernetwork framework that harnesses hypernetworks to derive defocus characteristics from range-Doppler (RD) imagery across varying loss rates, subsequently transforming these insights into ideal parameters for the sparse signal reconstruction process. By executing the iterative algorithm with these optimized parameters, we achieve loss rate robust ISAR imaging. Comprehensive evaluations conducted on point simulated data, electromagnetic simulated data and measured data confirm the superiority of our proposed approach in terms of reconstruction accuracy and generalization capabilities. This advancement facilitates reliable ISAR imaging across a spectrum of loss rates. 1965-2011 IEEE.

关键词： radar imaging

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Classifiers for the Identification of Multiple Sclerosis Lesions in Neural MRI Scans with Attributes Extracted from Pre-trained Neural Networks 9th

Evaluation of Classifiers for the Identification of Multiple...

引用

9th Latin American Congress on Biomedical Engineering, CLAIB 2022 and 28th Brazilian Congress on Biomedical Engineering, CBEB 2022

作者： Vital, D.A. Kudo, M.S. Marconatto, L.P. Moraes, M.C. Abdala, N. Department of Diagnostic Imaging Paulista School of Medicine Federal University of São Paulo UNIFESP São Paulo Brazil Laboratory of Image and Signal Processing Institute of Science and Technology Federal University of São Paulo UNIFESP São José dos Campos Brazil

ISBN: (纸本)9783031494031

About 2.8 million people worldwide have multiple sclerosis, and around 250,000 new cases are diagnosed annually. This disease damages the myelin sheath of neurons, injuring electrical signal conduction, and causing impairment and loss of senses, movement, and other neurological functions. Although the disease has no cure, early diagnosis is essential for the initiation of adequate treatment, controlling eventual outbreaks, delaying the advance, and improving the quality of life of patients. Neuroaxis magnetic resonance imaging is used to investigate this disease, identifying and following up lesions in the brain and spinal cord tissues;however, the diagnosis only through the visual evaluation of these exams may lack information for a quick and accurate analysis. Recent studies present computational methods based on artificial intelligence that allow the identification of lesions caused by the disease, aiming to overcome these visual limitations, but still have limitations in terms of accuracy and scope. The objective of this work was to evaluate the potential of classifiers based on machine learning algorithms in the identification of multiple sclerosis lesions in brain tissue. Axial FLAIR MRI brain exams were used from two databases combining filtering, normalization, and enhancement image pre-processing methods to extract the exam attributes. The algorithms evaluated were Decision Tree, Random Forest, K-Nearest Neighbors, Support Vector Machine and Logistic Regression, through training with attributes extracted from 3 pre-trained neural models: SqueezeNet, Inception V3 and VGG-19. The classifiers were evaluated by the classification of images from the studies as "with lesion" and "without lesion", and the SVM classifier trained with attributes extracted from the pre-trained neural model Inception V3 provided the best result, obtaining AUC = 0.988, accuracy = 0.980, sensitivity = 0.990 and F1-Score = 0.979. © The Author(s), under exclusive license to Springer Natur

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Convergence Analysis of Whale Optimization Algorithm

Convergence Analysis of Whale Optimization Algorithm

引用

2020 International Conference on Computer Big Data and Artificial Intelligence, ICCBDAI 2020

作者： Feng, Wentao National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu Sichuan610041 China

The whale optimization algorithm (WOA) has been widely used in different applications. It has simple control parameters and novel population updating mechanism. However, there is few theoretical analysis of WOA and the convergence property of WOA is ambiguity. This paper analyzes the convergence property of WOA by using the Markov chain of the stochastic process theory. The Markov chain model of the WOA algorithm is established. The one step transition probabilities and convergence properties of different population updating mechanisms in WOA are given. It's proved that the convergence property of WOA is determined by its shrinking encircling mechanism. Finally, three algorithms with different population updating mechanisms are tested with thirteen benchmark functions on accuracy and convergence speed. The simulation results on benchmark functions verify the validity of the theoretical analysis of WOA. © Published under licence by IOP Publishing Ltd.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Robust adaptive beamformer based on minimum dispersion with a broad null by linear programming

Robust adaptive beamformer based on minimum dispersion with ...

引用

2021 CIE International Conference on radar, radar 2021

作者： Feng, Yang Wei, Yao Wang, Wenying Yu, Yong Xu, Jingwei Liao, Guisheng Lan, Lan Nanjing Research Institute of Electronics Technology Nanjing210039 China Xidian University National Laboratory of Radar Signal Processing Xi'an710071 China

ISBN: (纸本)9781665498142

The standard minimum dispersion distortionless response (MDDR) beamformer can provide a performance improvement for non-Gaussian signals compared to the minimum variance distortionless response (MVDR) beamformer. However, the variety of the direction of the interference may have a great influence on the performance of the MDDR beamformer. To solve the problem, a robust beamformer with a broad null by linear programming is proposed for sub-Gaussian signals. Unlike the beamformers based on the minimum variance criterion, the proposed beamformer minimizes the p-norm of the output and meanwhile constrains not only the target response to be unity, but also the average power of the interference's dynamic angular sector to zero. The resulting optimization problem is cast as a linear programming and hence can be solved efficiently. Simulation results indicate that the proposed method offers a significant performance improvement if the direction of the interference varies with time. © 2021 IEEE.

关键词： Beamforming interference suppression minimum dispersion ℓp-norm minimization

来源：评论

学校读者我要写书评

暂无评论

LSTM-A: A Cable Partial Discharge Detection Model with Circuit Big Data 12th

LSTM-A: A Cable Partial Discharge Detection Model with Circu...

引用

12th International Conference on Computer Engineering and Networks, CENet 2022

ISBN: (纸本)9789811969003

With the development of smart grid construction and the maturity of the Internet of Things, the application of big data in the smart grid has been further enhanced. Partial discharge is a common problem in cables, especially in aged. It brings a serious threat to power transmission and electricity safety. Using big data to solve the cable partial discharge problem can promote the construction of the smart grid, reduce the cost of human resources, and improve the safety of electricity. In this paper, a cable partial discharge detection method, named LSTM-A, using LSTM and attention mechanism is proposed. Based on LSTM-A, a line fault detection framework with circuit big data is proposed to judge the partial discharge of cables. As the main component of the model, LSTM is skilled in capturing timing features of the electrical signal, and attention mechanism can capture the long-term dependence of the electrical signal. Combining LSTM and attention mechanism, this paper firstly extracts the low-level features of the electrical signal through LSTM, then calculates the dependency relationship using attention structure, and finally output the prediction result after the full connection layer. To verify the effectiveness of the model, Matthews correlation coefficient was used to measure the results. The experiment is compared with common models such as LSTM and CNN, and the results show that LSTM-A is superior to other deep learning models. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Cables

来源：评论

学校读者我要写书评

暂无评论

A Range Ambiguity Resolution Method for High-Resolution and Wide-Swath SAR Imaging Based on Continuous Pulse Coding

A Range Ambiguity Resolution Method for High-Resolution and ...

引用

2021 CIE International Conference on radar, radar 2021

作者： Wei, Jingyi Li, Yachao Sun, Ziyue Xidian University National Laboratory of Radar Signal Processing Xi'an China School of Engineering and Computer Science University of Exeter Exeter United Kingdom

ISBN: (纸本)9781665498142

In synthetic aperture radar (SAR), high-resolution and wide-swath (HRWS) imaging is a challenging problem due to the contradiction between azimuth Doppler ambiguity and range ambiguity. In order to break the limitation of the pulse repetition frequency (PRF) on the radar imaging width, a HRWS SAR imaging method based on continuous pulse coding (CPC) to solve the range ambiguity is proposed in this paper. CPC method requires the radar to transmit multi-pulse signals with varying high PRF in the original pulse repetition period. Because of the small distance between each pulse, the echo will be aliased and blocked. In order to recover the unambiguous echo, we first use the form of CPC signal and the swath width of the radar to construct a linear equation set to mathematically model the aliased echo signal of each receiving window. Next, the established linear equations are split according to the distribution law of the receiving window, and the range ambiguity of the echo is performed by solving the split sub-linear equations. Finally, imaging processing is performed on the decoded unambiguous echo to achieve HRWS SAR imaging. The experimental results have confirmed the effectiveness of the method proposed in this paper. © 2021 IEEE.

关键词： Continuous pulse coding (CPC) high-resolution and wide-swath (HRWS) range ambiguity synthetic aperture radar (SAR)

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：