检索结果-内蒙古大学图书馆

International Conference on Image and Vision Computing New Zealand, IVCNZ

作者： Akmal-Jahan Mohamed-Abdul-Cader Watcharapong Chaidee Jasmine Banks Vinod Chandran Vision and Signal Processing Lab School of Electrical Engineering and Computer Science Queensland University of Technology Brisbane Australia Signal and Image Processing Laboratory Kasetsart University Bangkok Thailand

A new algorithm for matching finger or palm prints is presented for use where the full hand is considered as a biometric and only parts may be available in images for comparison. The algorithm uses an extended version of the minutiae-based approach treating the pattern as a graph of minutiae-like points. The procedure to identify minutiae-like points uses Gabor filtering, edge detection and thinning and following line patterns. A set of such points is subjected to Delaunay triangulation yielding a starting set of base-triangles for matching. There can be multiple matches of such triangles between the template and test - as similar triangles with a tolerance in the angles. Graphs are then grown to 5 and more nodes as long as a match can be found, until the maximum size matching graph is obtained. If the test matches a significant part of the template, the maximum order of graph matched will be high. The matching process is robust to transformations such as rotation, translation and scale changes. It can be applied to any part of the hand provided minutiae-like points are identifiable prior to the matching steps. The algorithm is tested using 158 fingerprint images from FVC 2002 DB1. 100 genuine and 5048 impostor scores are generated from 46 templates and 112 testing images. It had an EER of about 6%. It proves the principle behind the methodology and demonstrates that the method can be effective with degraded fingerprint images and is robust to similarity transformations present in the data. It can be applied for forensic fingerprint matching from the palm or parts other than the fingertips. By using multiple parts and multiple templates, the accuracy of the method will be improved with fusion in future versions of the algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Network completion via deep metric learning

引用

Journal of Physics: Conference Series 2020年第1期1656卷

作者： Qiang Wei School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu 611731 China National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu 610041 China

Completing networks is often a necessary step when dealing with problems arising from applications in incomplete network data mining. This paper investigates the network completion problem with node attributes. We proposed a new method called DeepMetricNC by exploiting the correlation between node attributes and the underlying network structure. In DeepMetricNC, the correlation is modeled as a nonlinear mapping from node attributes to the probability of edge existence. To obtain the mapping, deep metric learning is applied with batch training and random negative sampling. DeepMetricNC has linear training time complexity and can adapt to large-scale network completion tasks. Experiments of real networks show that DeepMetricNC completes network structures better than other methods, and is more suitable when the portion of the observed part is small.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Novel deep hybrid model for electricity price prediction based on dual decomposition

引用

Applied Energy 2025年 395卷

作者： Ghimire, Sujan Nguyen-Huy, Thong Deo, Ravinesh C. Casillas-Pérez, David Masrur Ahmed, A.A. Salcedo-Sanz, Sancho Artificial Intelligence Applications Laboratory School of Mathematics Physics and Computing University of Southern Queensland SpringfieldQLD4300 Australia Centre for Applied Climate Sciences University of Southern Queensland ToowoombaQLD4350 Australia Faculty of Information Technology Thanh Do University Kim Chung Hoai Duc Ha Noi100000 Viet Nam Department of Signal Processing and Communications Universidad Rey Juan Carlos Madrid Fuenlabrada28942 Spain Science Economics and Insights Division Department of Climate Change Energy the Environment and Water NSW Government SydneyNSW2141 Australia Department of Signal Processing and Communications Universidad de Alcalá Alcalá de Henares Madrid 28805 Spain

Electricity price (EP) forecasting is vital for effective market operation, strategic planning, and risk management in deregulated energy systems. However, the inherent volatility and complexity of electricity prices, shaped by demand supply dynamics, weather variability, and regulatory interventions, pose substantial challenges to accurate prediction. This study introduces a novel hybrid framework designed to improve forecasting accuracy by leveraging both signal decomposition and deep learning techniques. Specifically, the method integrates Variational Mode Decomposition (VMD) and Empirical Wavelet Transform (EWT) for noise reduction and feature extraction, followed by a Multi Resolution Convolution (MRC) layer and a Bidirectional Long Short Term Memory (BiLSTM) network to capture multiscale temporal patterns in electricity price data. The model is applied to half hourly electricity price data from South Australia spanning January 2018 to December 2022. Its performance is benchmarked against a suite of traditional and hybrid models using a comprehensive set of twelve evaluation metrics. The results reveal that the proposed hybrid model consistently outperforms all baselines across seasons and forecast horizons. Notably, during the spring period, it achieved a Normalized Root Mean Square Error of ≈4.87%, a Mean Absolute Percentage Error of ≈12.09%, and a Global Performance Index of ≈3.22. These improvements demonstrate the model's ability to effectively handle the non-linear and nonstationary nature of EP. Overall, the findings underscore the potential of combining advanced decomposition methods with deep learning architectures to deliver more accurate and robust EP forecasts, thereby offering valuable support for decision making in complex and evolving energy markets. © 2025 The Author(s)

关键词： Risk perception

来源：评论

学校读者我要写书评

暂无评论

A review on InSAR phase denoising

arXiv

引用

arXiv 2020年

作者： Xu, Gang Gao, Yandong Li, Jinwei Xing, Mengdao State Key Laboratory of Millimeter Waves Southeast University Nanjing210096 China School of Environment Science and Spatial Informatics China University of Mining and Technology Xuzhou China Xi'an Institute of Space Radio Technology Xi'an710071 China National Laboratory of Radar Signal Processing Xidian University Xi'an710071 China

Nowadays, interferometric synthetic aperture radar (InSAR) has been a powerful tool in remote sensing by enhancing the information acquisition. During the InSAR processing, phase denoising of interferogram is a mandatory step for topography mapping and deformation monitoring. Over the last three decades, a large number of effective algorithms have been developed to do efforts on this topic. In this paper, we give a comprehensive overview of InSAR phase denoising methods, classifying the established and emerging algorithms into four main categories. The first two parts refer to the categories of traditional local filters and transformed-domain filters, respectively. The third part focuses on the category of nonlocal (NL) filters, considering their outstanding performances. Latter, some advanced methods based on new concept of signal processing are also introduced to show their potentials in this field. Moreover, several popular phase denoising methods are illustrated and compared by performing the numerical experiments using both simulated and measured data. The purpose of this paper is intended to provide necessary guideline and inspiration to related researchers by promoting the architecture development of InSAR signal processing. Copyright © 2020, The Authors. All rights reserved.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Infrared small-dim target detection with transformer under complex backgrounds

arXiv

引用

arXiv 2021年

作者： Liu, Fangcen Gao, Chenqiang Chen, Fang Meng, Deyu Zuo, Wangmeng Gao, Xinbo The School of Communication and Information Engineering Chongqing University of Posts and Telecommunications Chongqing400065 China Chongqing Key Laboratory of Signal and Information Processing Chongqing University of Posts and Telecommunications Chongqing400065 China The Viterbi School of Engineering University of Southern California California90089 United States School of Mathematics and Statistics Xi’an Jiaotong University Shanxi Xi’an710049 China Macau Institute of Systems Engineering Macau University of Science and Technology Taipa999078 China School of Computer Science and Technology Harbin Institute of Techonlogy Heilongjiang Harbin47822 China

The infrared small-dim target detection is one of the key techniques in the infrared search and tracking system. Since the local regions similar to infrared small-dim targets spread over the whole background, exploring the interaction information amongst image features in large-range dependencies to mine the difference between the target and background is crucial for robust detection. However, existing deep learning-based methods are limited by the locality of convolutional neural networks, which impairs the ability to capture large-range dependencies. Additionally, the small-dim appearance of the infrared target makes the detection model highly possible to miss detection. To this end, we propose a robust and general infrared small-dim target detection method with the transformer. We adopt the self-attention mechanism of the transformer to learn the interaction information of image features in a larger range. Moreover, we design a feature enhancement module to learn discriminative features of small-dim targets to avoid miss detection. After that, to avoid the loss of the target information, we adopt a decoder with the U-Net-like skip connection operation to contain more information of small-dim targets. Finally, we get the detection result by a segmentation head. Extensive experiments on two public datasets show the obvious superiority of the proposed method over state-of-the-art methods and the proposed method has stronger cross-scene generalization and anti-noise performance. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

An Improved Particle Filter Based Track-Before-Detect Method for Underwater Target Bearing Tracking

An Improved Particle Filter Based Track-Before-Detect Method...

引用

OCEANS - Europe

作者： Shenglong Jin Haining Huang Yu Li Yufei Ren Yujie Wang Rongxing Zhong Key Laboratory of Science and Technology on Advanced Underwater Acoustic Signal Processing Chinese Academy of Sciences Beijing China

Track-before-detect (TBD) methods have been shown to greatly abate measurement-to-track association (MTA) challenges which could cost plenty of operator workload in many detection systems. In the field of underwater acoustic signal processing, the low signal-to-noise ratio, random missing measurements, multiple interference scenarios, and merging-splitting contacts in measurement space are challenging for common target tracking algorithms. As a result, particle filter (PF) based track-before-detect methods that compute posterior density distribution directly using beamformer output instead of bearing measurements are effective in these cases. However, the general PF always suffers from the particle impoverishment problem which can lead to the misleading state estimation results due to system process error. To cope with above problems, an improved particle filter based track-before-detect method is proposed in this paper. The proposed PF-TBD method adopts crossover and mutation operators from genetic algorithm to evolve particles with small weight. And the quasi-Monte Carlo method is applied into resampling procedure of particle filter. The effectiveness of the method is verified by using experimental data obtained at sea, which can continuously and accurately track target bearings in the case of temporary signal disappearance and multi-target intersection. The estimated result is close to the real value even when the motion model suffers mismatch.

关键词： Target tracking Sea measurements Radar tracking Atmospheric measurements Particle measurements Trajectory

来源：评论

学校读者我要写书评

暂无评论

Facial feature embedded CycleGAN for VIS-NIR translation

arXiv

引用

arXiv 2019年

作者： Wang, Huijiao Wang, Li Yang, Xulei Yu, Lei Zhang, Haijian Signal Processing Laboratory School of Electronic Information Wuhan University China Agency for Science Technology and Research Singapore

VIS-NIR face recognition remains a challenging task due to the distinction between spectral components of two modalities and insufficient paired training data. Inspired by the CycleGAN, this paper presents a method aiming to translate VIS face images into fake NIR images whose distributions are intended to approximate those of true NIR images, which is achieved by proposing a new facial feature embedded CycleGAN. Firstly, to learn the particular feature of NIR domain while preserving common facial representation between VIS and NIR domains, we employ a general facial feature extractor (FFE) to replace the encoder in the original generator of CycleGAN. For implementing the facial feature extractor, herein the MobileFaceNet is pretrained on a VIS face database, and is able to extract effective features. Secondly, the domain-invariant feature learning is enhanced by considering a new pixel consistency loss. Lastly, we establish a new WHU VIS-NIR database which varies in face rotation and expressions to enrich the training data. Experimental results on the Oulu-CASIA NIR-VIS database and the WHU VIS-NIR database show that the proposed FFE-based CycleGAN (FFE-CycleGAN) outperforms state-of-the-art VISNIR face recognition methods and achieves 96.5% accuracy. Copyright © 2019, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Multi-node Cooperative MAC Protocol Joint with Space-time Encoding for Underwater Acoustic Communication Networks

A Multi-node Cooperative MAC Protocol Joint with Space-time ...

引用

OCEANS - Europe

作者： Jing Huang Wei Wang Yu Li Zhanqing Pu Haining Huang Key Laboratory of Science and Technology on Advanced Underwater Acoustic Signal Processing Chinese Academy of Sciences Beijing China

It is a great challenge to design effective protocols for underwater acoustic communication networks due to the specific characteristics of underwater acoustic channel, such as long propagation delay and limited available bandwidth. In order to reduce the average end-to-end delay and improve the network throughput, a multi-node cooperative MAC protocol joint with space-time encoding of physical layer for multi-user MIMO centralized network is proposed in this paper. It is receiver-initiated, where the receiver groups the reserved nodes into a series of cells according to the propagation delay between individual reserved node and itself. By scheduling the transmission time, the data packets sent by the nodes in the same cell are guaranteed to reach the receiver within a predetermined time deviation, realizing cooperative parallel transmission of multiple nodes. Simulation results show that the proposed MAC protocol achieves the shortest end-to-end delay and optimal normalized network throughput under different network sizes, traffic loads and data packet lengths compared with other three existing protocols. The performance improvement is significant especially when the data packet length is longer and the load is heavier.

关键词： Receivers Media Access Protocol Delays Throughput Propagation delay MIMO communication

来源：评论

学校读者我要写书评

暂无评论

dense feature aggregation and pruning for RGBT tracking

arXiv

引用

arXiv 2019年

作者： Zhu, Yabin Li, Chenglong Luo, Bin Tang, Jin Wang, Xiao Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei Anhui China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Institute of Physical Science and Information Technology Anhui University Hefei Anhui China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Key Laboratory of Industrial Image Processing and Analysis of Anhui Province Hefei Anhui China

How to perform effective information fusion of different modalities is a core factor in boosting the performance of RGBT tracking. This paper presents a novel deep fusion algorithm based on the representations from an end-to-end trained convolutional neural network. To deploy the complementarity of features of all layers, we propose a recursive strategy to densely aggregate these features that yield robust representations of target objects in each modality. In different modalities, we propose to prune the densely aggregated features of all modalities in a collaborative way. In a specific, we employ the operations of global average pooling and weighted random selection to perform channel scoring and selection, which could remove redundant and noisy features to achieve more robust feature representation. Experimental results on two RGBT tracking benchmark datasets suggest that our tracker achieves clear state-of-the-art against other RGB and RGBT tracking methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

3R: Word and Phoneme Edition based Data Augmentation for Lexical Punctuation Prediction

3R: Word and Phoneme Edition based Data Augmentation for Lex...

引用

International Conference on Computational Intelligence and Security

作者： Aihua Zheng Naipeng Ye Xiao Wang Xiao Song Key Lab of Intelligent Computing and Signal Processing of Ministry of Education Hefei China Peking University Shenzhen Institute Shenzhen China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei China

Existing Lexical Punctuation Prediction methods are mainly trained on the standard clean data while losing the generalization in practical automatic speech recognition (ASR) system with ubiquitous transcription errors. To bridge the gap between clean training data and noisy testing data, we propose three random (3R) data augmentation strategies: random word deletion (RWD), random word substitution (RWS), and random phoneme edition (RPE) in both word and phoneme levels on the training dataset. Specifically, we contribute an acoustically similar vocabulary with phoneme level editions for acoustically similar word substitution. In addition, we first introduce the RoBERTa-large model into a punctuation prediction task to capture the semantics and the long-distance dependencies in language. Extensive experiments on the English dataset IWSLT2011 yield to a new state-of-the-art comparing to the prevalent punctuation prediction methods.

关键词： Training Vocabulary Semantics Training data Predictive models Noise measurement Security

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：