检索结果-内蒙古大学图书馆

2019 International Conference on Intelligent Computing, Automation and Systems, ICICAS 2019

作者： Li, Weihao Wang, Keren Information Engineering University Zhengzhou China National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu China

ISBN: (纸本)9781728161068

The current automatic decoding method of the Morse telegram has limited accuracy, and can't adapt to signal distortion and code length deviation of the manual telegram. This paper introduces the deep learning method and constructs an automatic decoding model, which integrates feature extraction, sequence modeling and transcription into an end-to-end training neural network. The time-frequency diagrams of signals are used for training and testing. Experimental results show that the decoding system has strong adaptability to manual deviation and frequency drift, and is robust in a noisy environment. © 2019 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

A Long Synthetic Aperture Passive Localization Method Using Two Planes

A Long Synthetic Aperture Passive Localization Method Using ...

引用

IEEE International Conference on Radar

作者： Bowei Chen Yuqi Wang Guang-Cai Sun Mengdao Xing Zijing Zhang Xiaoniu Yang National Laboratory of Radar Signal Processing Xidian University Xi'an China Science and Technology on Communication Information Security Control Laboratory Jiaxing China

ISBN: (纸本)9781665468893

A long synthetic aperture passive localization algorithm is proposed in this paper. First of all, the Doppler change rate of signal can be measured by the image contrast and then, grid points are divided within the maximum possible latitude and longitude of the emitter location, the Doppler change rate at each grid point can be calculated by using known position and velocity of the receiver. The grid points at which the calculated Doppler change rate is equal to the value measured by the received signal form an isoline. Two receivers can draw two isolines on the ground and the intersection of the isolines gives estimate of the emitter location.

关键词： Location awareness Passive radar Chirp Estimation Receivers Apertures Position measurement

来源：评论

学校读者我要写书评

暂无评论

Tablet Identification Using Ensemble Convolutional Neural Networks and Vibrational Spectroscopy

SSRN

引用

SSRN 2023年

作者： Sun, Penghui Wang, Jiajia Liu, Pei Dong, Zhilin School of Computer Science and Technology Xinjiang University Urumqi China The Key Laboratory of Signal Detection and Processing Xinjiang Uygur Autonomous Region Xinjiang University China Post-doctoral workstation of Xinjiang Xinjiang Uygur Autonomous Region Product Quality Supervision and Inspection Institute Urumqi China

Vibrational spectroscopy reflects molecular vibrational data, facilitating tablet identification. This paper introduces the DCNN-EL model, which integrates vibrational spectroscopy to accurately discern tablet categories. The DCNN-EL model is built upon the Alexnet framework, starting with the proposal of the Alexnet-BN model, enhancing model training speed and robustness by iteratively applying the BN layer in lieu of the pooling layer. Subsequently, by adjusting the parameters of Alexnet-BN, five deep convolutional neural network (DCNN) models are established and combined using an integrated machine learning approach to form the DCNN-EL model. Evaluating the DCNN-EL model with two public datasets (Tablets_Nir and Tablets_Raman) demonstrates its 100% and 91.67% accuracy, affirming its efficacy and generalizability in tablet identification. Consequently, the amalgamation of convolutional neural networks and vibrational spectroscopy bears significant practical relevance in the qualitative detection of tablets. © 2023, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Pyramid Convolution and Multi-Frequency Spatial Attention for Fine-Grained Visual Categorization

SSRN

引用

SSRN 2022年

作者： Xu, Qin Li, Yun Zhang, Mengquan Tao, Zhifu Luo, Bin Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei230601 China School of Big Data and Statistics Anhui University Hefei230601 China

Learning diverse detailed feature is crucial for fine-grained visual categorization (FGVC). However, most of existing methods for FGVC use the standard convolution for feature extraction which leads to the loss of many subtle but important features. Besides, in the existing attention models for FGVC, the features are aggregated by a simple global average pooling operation, which is unable to characterize complex feature information. To address these problems, we propose pyramid convolution and multi-frequency spatial attention (PCMFSA) for FGVC. To capture spatial context dependencies of different levels and avoid the loss of the subtle features, pyramid convolution, which uses convolution kernels with various sizes, is introduced in the backbone network. To reduce the influence of background noise and obtain diverse fine-grained feature information, we propose multi-frequency spatial attention (MFSA) module, in which two channel-wise grouping operations are designed and discrete cosine transform (DCT) in the frequency domain is adopted to enhance features of different spatial positions. Moreover, to mine more valuable regions, peak suppression is used to suppress high-response regions after MFSA. A large number of experimental results show that our method achieves state-of-the-art results on four popularly FGVC datasets. © 2022, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Measuring the Orbital-Angular-Momentum Complex Spectrum of Light with the Fast Fourier Transform

引用

Physical Review Applied 2023年第1期20卷 014010-014010页

作者： Jialong Zhu Yihua Wu Le Wang Hailong Zhou Shengmei Zhao Institute of Signal Processing and Transmission Nanjing University of Posts and Telecommunications (NUPT) Nanjing 210003 China School of Information Engineering Suqian University Suqian 223800 China Wuhan National Laboratory for Optoelectronics School of Optical and Electronic Information Huazhong University of Science and Technology Wuhan 430074 China Key Lab of Broadband Wireless Communication and Sensor Network Technology (Nanjing University of Posts and Telecommunications) Ministry of Education Nanjing China National Laboratory of Solid State Microstructures Nanjing University Nanjing 210093 China

Measuring the orbital-angular-momentum (OAM) complex spectrum of light is very important in OAM-based applications. In this paper, we propose and experimentally demonstrate a simple scheme to measure the OAM complex spectrum of light with the fast Fourier transform (FFT). The light with input OAM modes coaxially interferes with a Gaussian light beam that is generated locally to achieve the intensity distribution of the interference. By subtracting the intensity distribution of the input OAM light from this interference intensity distribution, the OAM complex spectrum can be extracted by employing the FFT transform on the result of the subtraction. In addition, we also present an approach to enlarge the range of detectable OAM modes (from 1 to 50) and analyze the effects of optical alignment and the number of superimposed OAM modes on the measurement results. The proposed scheme is demonstrated in a proof-of-principle experiment, where six superimposed OAM modes can be measured without error, with their average deviation of amplitude and phase being 0.07 and 0.308, respectively. The proposed scheme can exploit applications in some advanced domains, including OAM sensing, OAM imaging, optical communication decoding, and various other OAM-based systems.

关键词： Angular momentum of light Metrology Spatial profiles of optical beams Optical sources & detectors Optical spectroscopy

来源：评论

学校读者我要写书评

暂无评论

The potential of convolutional neural network diagnosing prostate cancer

引用

Research on Biomedical Engineering 2021年第1期37卷 25-31页

作者： Kudo, Maíra Suzuka de Souza, Vinicius Meneguette Gomes de Souza Amaral, Gabriel de Souza Melo, Petrônio Augusto Estivallet, Carmen Liane Neubarth Santos, Eric Rocha de Amorim, Henrique Alves Moraes, Matheus Cardoso Leite, Katia Ramos Moreira Laboratory of Image and Signal Processing of the Institute of Science and Technology Federal University of São Paulo – UNIFESP 330 Talim St. Room 108 - Jardim Aeroporto Sao Jose dos CamposSP12231-280 Brazil Laboratory of Medical Investigations Number 55 Sao Paulo University Medical School – FMUSP Dr Arnaldo Avenue 455 Room 2145 – Cerqueira Cesar Sao PauloSP01246-903 Brazil

Introduction: There were more than 1,276,106 new cases of prostate cancer (PC) in 2018 worldwide (GLOBOCAN). Early and precise diagnosis leads to cure chances up to 90%. Digital rectal examination and PSA serum levels are employed for prostate cancer screening. If both exams are suspicious for cancer, the patient will be submitted to a prostate biopsy. Histological diagnosis and grading are crucial to the proper manage of the patients and are not always easy to evaluate, demanding experience of pathologists. To test the possibility to adopt artificial intelligent to diagnose PC, we studied a set of prostate biopsy sample images that were input to a specifically constructed convolutional neural network. Purpose: Evaluate the potential of the convolutional neural network for the classification of cancer and non-cancer patches extracted from prostate biopsy images. Methods: Thirty-two prostate cancer biopsy images were obtained and reviewed by a single uropathologist and then transformed into 2594 fragments to feed the CNN. The methodology has been divided into clinical approaches—to extract patches—and computational approaches—the CNN implementation. Results: The k-fold three-way cross-validation method was used, resulting in a 98.3% output accuracy in distinguishing cancer from non-cancer. Conclusion: The presented method proved to be robust and trustworthy comparing with an expert pathologist report. © 2020, Sociedade Brasileira de Engenharia Biomedica.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Urban Environmental Sound Monitoring Network Based on Combination of Mobile and Stationary Nodes 7

Urban Environmental Sound Monitoring Network Based on Combin...

引用

7th International Conference on Information science and Control Engineering, ICISCE 2020

作者： Wei, Jinquan Luo, Liyan Wang, Mei Song, Xiyu Zhang, Liujun Yao, Man Guilin University of Electronic Technology Guangxi Key Laboratory of Wireless Broadband Communication and Signal Processing Guilin541004 China Guangxi Key Laboratory of Wireless Broadband Communication and Signal Processing Guilin University of Electronic Technology Guilin541004 China College of Information Science and Engineering Guilin University of Technology Guilin541007 China

ISBN: (纸本)9781728164069

Urban noise has posed a threat to people's physical and mental health. Significant progress has been made in noise monitoring related projects at home and abroad, but these projects usually utilize stationary monitoring equipment to measure noise whose deployment is susceptible to the cost and complex urban environment and thus they cannot effectively cover the monitored area. In this paper, a kind of joint mobile and stationary nodes based urban environmental sound monitoring network is proposed to achieve low-cost, high-precision, and high-flexibility noise monitoring. The network adopts NETTY framework, which effectively alleviates the impact of high concurrency on server performance in the context of large-scale sensor nodes. In addition, this paper designs a visual monitoring platform for the display of noise distribution and abnormal sound events. In order to verify the performance of the system, 10 mobile nodes and 50 stationary nodes are deployed in the campus environment. The experimental results show that the proposed system can realize urban environmental noise monitoring with high performance in real scenes. © 2020 IEEE.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

An Intelligent SDWN Routing Algorithm Based on Network Situational Awareness and Deep Reinforcement Learning

arXiv

引用

arXiv 2023年

作者： Li, Jinqiang Ye, Miao Huang, Linqiang Deng, Xiaofang Qiu, Hongbing Wang, Yong School of Information and Communication Technology Guilin University of Electronic Technology Guilin541000 China Guangxi Key Laboratory of Wireless Broadband Communication and Signal Processing Guilin541004 China School of Computer Science and Information Security Guilin University of Electronic Technology Guilin541004 China Engineering Technology Research Center of Cloud Security and Cloud Service Guilin University of Electronic Technology Guilin541004 China

Due to the highly dynamic changes in wireless network topologies, efficiently obtaining network status information and flexibly forwarding data to improve communication quality of service are important challenges. This article introduces an intelligent routing algorithm (DRL-PPONSA) based on proximal policy optimization deep reinforcement learning with network situational awareness under a software-defined wireless networking architecture. First, a specific data plane is designed for network topology construction and data forwarding. The control plane collects network traffic information, sends flow tables, and uses a GCN-GRU prediction mechanism to perceive future traffic change trends to achieve network situational awareness. Second, a DRL-based data forwarding mechanism is designed in the knowledge plane. The predicted network traffic matrix and topology information matrix are treated as the environment for DRL agents, while next-hop adjacent nodes are treated as executable actions. Accordingly, action selection strategies are designed for different network conditions to achieve more intelligent, flexible, and efficient routing control. The reward function is designed using network link information and various reward and penalty mechanisms. Additionally, importance sampling and gradient clipping techniques are employed during gradient updating to enhance convergence speed and stability. Experimental results show that DRL-PPONSA outperforms traditional routing methods in network throughput, delay, packet loss rate, and wireless node distance. Compared to value-function-based Dueling DQN routing, the convergence speed is significantly improved, and the convergence effect is more stable. Simultaneously, its consumption of hardware storage space is reduced, and efficient routing decisions can be made in real-time using the current network state information. The source code can be accessed at https://***/GuetYe/DRL-PPONSA. Copyright © 2023, The Authors. All rig

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Layer Visual Perception for No-Reference Image Quality Assessment

Multi-Layer Visual Perception for No-Reference Image Quality...

引用

IEEE International Conference on Electronic Information and Communication technology (ICEICT)

作者： Junwei Qi Yingzhen Wang Qingchun Wang Yingsong Li College of Computer Science and Technology Harbin Engineering University Harbin China College of Information and Communication Engineering Harbin Engineering University Harbin China Shanghai Yanding Information Technology Co. Ltd. Shanghai China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei Anhui China

In this work, we propose a no-reference image quality evaluation approach, aiming to solve the problem that the traditional convolutional neural network is insufficient to express the global information of the image. Therefore, in order to make the captured image features have the coherence of global context information, we combine a Transformer structure widely used in NLP (natural language processing) with the traditional CNN to realize the attention mechanism in the human visual perception characteristics. Firstly, the self-attention mechanism of Transformer is used to learn the global representation of the image from the multi-layer features extracted from different levels of CNN. Additionally, to forecast the ultimate image quality score, the global and local attributes are combined. Finally, the proposed algorithm is evaluated on three public datasets commonly used in CSIQ [1], TID2013 [2] and LIVE [3]. Compared with eight traditional no-reference image quality evaluation algorithms and five methods based on deep learning, the proposed algorithm achieves competitive results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MFUnetr: A Transformer-Based Multi-Task Learning Network for Multi-Organ Segmentation from Partially Labeled Datasets

SSRN

引用

SSRN 2022年

作者： Hao, Qin Tian, Shengwei Yu, Long Wang, Junwen College of Software Xinjiang University Urumqi830000 China Key Laboratory of Software Engineering Technology Xinjiang University Urumqi830000 China College of Network Center Xinjiang University Urumqi830000 China Signal and Signal Processing Laboratory College of Information Science and Engineering Xinjiang University Urumqi830000 China

As multi-organ segmentation of CT images is crucial for clinical applications, most state-of-the-art models rely on a fully annotated dataset with strong supervision to pursue higher accuracy. However, these models have weak generalization when applied to various CT images due to the small scale and single source of training data. To utilize existing partially labeled datasets to obtain full organ segmentation and improve accuracy and robustness, we create a transformer-based multi-task learning network called MFUnetr. By directly feeding a union of datasets, MFUnetr trains an encoder-decoder network on two tasks in parallel. The main task is to produce full organ segmentation by using a particular training strategy. The auxiliary task is to segment organs of each dataset by using labels prior. Additionally, we offer a new weighted combined loss function to optimize the model. Compared to the base model trained on the fully annotated dataset BTCV, our network model, trained on a combination of three datasets, achieved mean Dice on overlapping organs: spleen +2.5%, esophagus +8.9%, and aorta +0.5%. The generalization ability was enhanced, with spleen +4.1%, esophagus +37.4%, and aorta +21.4%. Importantly, without fine-tuning, the mean Dice calculated on 13 organs of BTCV remained +0.6% when all 15 organs were segmented. Experimental results show that our proposed method can effectively use the large existing partially annotated datasets to alleviate the problem of data hunger in multi-organ segmentation. © 2022, The Authors. All rights reserved.

关键词： Image segmentation

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：