检索结果-内蒙古大学图书馆

IEEE 7th International Conference on Advanced Technologies, Signal and Image Processing (ATSIP)

作者： Benneila, Mahrez Hadji, Salah ben Messouad, Mouhamed Anouar Natl Engineers Sch Tunis Lab Signal Images & Technol Informat LR SITI ENIT Tunis Tunisia CERTn Borj Hamm Lif Lab Nanomat & Energy Lanser Tunis Tunisia

ISBN: (纸本)9798350351491;9798350351484

In this work, we apply an approach based on simultaneous enhancement of the amplitude and phase time-frequency representation of a composite audio signal with two datasets, namely the Voice Bank+Demand and the NTCD TIMIT datasets. The approach is based on an encoder and a decoder connected by transformers having a convolution module. The encoder uses both amplitude and phase spectra as input, while the decoder has two parts one of parallel amplitude mask and the other is a phase decoder. Thus allowing direct recovery of clean amplitude spectra and also clean enveloped phase spectra, its activation function is a sigmoid learnable and it estimates the phase in parallel. Like all neural networks there are losses at several levels such as: amplitude, phase, and short-term complex, without forgetting the temporal waveforms. All these losses are used jointly in training the model implemented, the validation of this model is done on the two datasets and the experimental results gave a PESQ of 3.5 for the Voice Bank+demand and a PESQ of 3.22 for NTCD-TIMIT.

关键词： speech enhancement encoder-decoder parallel denoising magnitude spectra phase spectra

来源：评论

学校读者我要写书评

暂无评论

Retinal vessel segmentation via a Multi-resolution Contextual Network and adversarial learning

引用

NEURAL NETWORKS 2023年第1期165卷 310-320页

作者： Khan, Tariq M. Naqvi, Syed S. Robles-Kelly, Antonio Razzak, Imran Univ New South Wales Sch Comp Sci & Engn Sydney NSW Australia COMSATS Univ Islamabad Dept Elect & Comp Engn Islamabad Pakistan Deakin Univ Fac Sci Engn & Built Environm Sch Informat Technol Locked Bag 20000 Geelong Australia Def Sci & Technol Grp Edinburgh SA 5111 Australia

Timely and affordable computer-aided diagnosis of retinal diseases is pivotal in precluding blindness. Accurate retinal vessel segmentation plays an important role in disease progression and diagnosis of such vision-threatening diseases. To this end, we propose a Multi-resolution Contextual Network (MRC-Net) that addresses these issues by extracting multi-scale features to learn contextual depen-dencies between semantically different features and using bi-directional recurrent learning to model former-latter and latter-former dependencies. Another key idea is training in adversarial settings for foreground segmentation improvement through optimization of the region-based scores. This novel strategy boosts the performance of the segmentation network in terms of the Dice score (and correspondingly Jaccard index) while keeping the number of trainable parameters comparatively low. We have evaluated our method on three benchmark datasets, including DRIVE, STARE, and CHASE, demonstrating its superior performance as compared with competitive approaches elsewhere in the literature.(C) 2023 Elsevier Ltd. All rights reserved.

关键词： Retinal vessel segmentation encoder-decoder Contextual network Adversarial learning Diabetic retinopathy

来源：评论

学校读者我要写书评

暂无评论

A Novel CNN-based Model for Medical Image Registration

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2023年第11期14卷 1125-1136页

作者： Gao, Hui Liang, Mingliang Zhengzhou Railway Vocat & Tech Coll Zhengzhou 451460 Henan Peoples R China

The registration of the deformable image is applied widely to image diagnosis, the monitoring of the disease, and the navigation of the surgery with the aim of learning the correspondence of the anatomist among an image of motion and an image of static. The procedure of the registration of an image mainly includes three steps: the creation of a model of the deformation, a function design for the mensuration of the similarity, and the step of learning for the optimization of the parameter. In the current article, 2-stream architecture is designed, which has the ability to sequentially estimate the fields of the registration of the multi-level by a couple of the pyramids of the feature. In this paper, a 3D network of the encoder decoder with the 2-stream is designed, which calculates 2 pyramids of the feature of the convolutional as separately by 2 volumes of the input. Also, the registration of the pyramid of the sequential is proposed, which in it, a trail of the modules of the pyramid registration (PR) for the prediction of the fields of the registration of the multi-level is designed as straight by the pyramids of the feature of the decoding. In addition, the modules of PR can be augmented with the computation of the 3D correlations of the local among the pyramids of the feature, which this work leads to the further improvement of the presented approach. Thus, it is capable of collecting the detailed anatomical structure of the brain. The proposed method is tested in three criterion datasets about the registration of MRI of the brain. The evaluation outcomes display that the presented approach outperforms the advanced approaches with a big value.

关键词： Image registration convolutional neural network Pyramid Registration (PR) encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Ship Trajectory Prediction for Environmental Perception in Multi-ship Interactions Based on Denoising Diffusion Models 30th

Ship Trajectory Prediction for Environmental Perception in M...

引用

30th International Conference on Computational and Experimental Engineering and Sciences

作者： Ma, Kun Han, Qilong Yao, Jingzheng Harbin Engn Univ Coll Comp Sci & Technol Harbin Peoples R China Harbin Engn Univ Yantai Res Inst Yantai Peoples R China

ISBN: (纸本)9783031816758;9783031816734;9783031816727

Ship trajectory prediction plays a crucial role in maritime safety and navigation, especially in complex environments where multiple ships interact simultaneously. In maritime applications, exact single trajectory prediction may not be paramount;rather, balancing accuracy and diversity of trajectories is essential to ensure collision avoidance based on predicted paths during ship interactions. However, due to the stochastic nature of ships' future intentions, resulting in diverse motion patterns and multiple possible paths, predicting trajectories in these regions poses significant challenges. This paper proposes a novel method, Environmental Perception based on Denoising Diffusion Models(EP-DDM), for ship trajectory prediction in multi-ship interaction scenarios, utilizing denoising diffusion models to enhance environmental perception. EP-DDM is based on an encoder-decoder architecture but differs from conventional methods by avoiding the use of latent variables to represent multimodality. The encoder leverages a transformer to extract historical and interactional information, while the decoder, also based on a transformer, adequately captures temporal dependencies. By integrating denoising techniques into the prediction model, this method aims to improve trajectory prediction accuracy while considering trajectory diversity, particularly in scenes involving complex ship interactions. Experimental results on extensive natural ship trajectory data demonstrate that the proposed model achieves excellent prediction performance and robustness compared to baseline methods, highlighting the potential of our approach to enhance maritime trajectory prediction capabilities in dynamic and congested ocean environments.

关键词： Diffusion model encoder-decoder Trajectory prediction Transfomer

来源：评论

学校读者我要写书评

暂无评论

DM-BDD: Real-time Vessel Trajectory Prediction Based on Diffusion Probability Model Balancing Diversity and Determinacy

DM-BDD: Real-time Vessel Trajectory Prediction Based on Diff...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Ma, Kun Han, Qilong Yao, Jingzheng Zhang, Yuntao Harbin Engn Univ Coll Comp Sci & Technol Harbin Peoples R China Harbin Engn Univ Yantai Res Inst Yantai Peoples R China Harbin Engn Univ Coll Shipbuilding Engn Harbin Peoples R China

ISBN: (纸本)9798350359329;9798350359312

Accurate ship trajectory prediction is crucial to ensure the safety and interaction efficiency of maritime traffic, especially in areas with dense ships and areas with intersecting waterways. Different from the certainty of short-term trajectory prediction, for long-term trajectory prediction, the uncertainty of direction and speed changes in operation is amplified, and the prediction of ship trajectory is more difficult. To solve this problem, we propose A framework based on a diffusion probability model balancing diversity and determinacy (DMBDD). Inspired by the denoising process in the diffusion model, we gradually reduce the range of trajectories that the ships are navigable, and finally achieve a desired and deterministic trajectory. This process is learned using a parameterized Markov chain based on the currently observed trajectory. The length of the chain is adjusted to control the degree of uncertainty of the running trajectory and the final position, and to balance the diversity and certainty of the prediction results. We design an architecture consisting of a temporal-social encoding network and an LSTM-based decoder network to achieve the purpose of capturing the spatial dependence and social dependence of *** test and compare on the AIS dataset of the real Weihai Port and the Nantong waterway of the Yangtze River estuary. The experimental results show that the short, medium and long-term prediction results of the proposed model on the two data sets achieve the best performance in the field of ship trajectory prediction.

关键词： Diffusion model Markov chain Trajectory prediction LSTM encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

RESIDUAL GROUP ENHANCED GAN FOR REMOTE SENSING IMAGE CLOUD SHADOW REMOVAL

RESIDUAL GROUP ENHANCED GAN FOR REMOTE SENSING IMAGE CLOUD S...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Yang, Jiajun Liu, Chenyang Chen, Keyan Zou, Zhengxia Shi, Zhenwei Beihang Univ Image Proc Ctr Sch Astronaut Beijing 100191 Peoples R China Beihang Univ Sch Astronaut Dept Guidance Nav & Control Beijing 100191 Peoples R China

ISBN: (纸本)9798350360332;9798350360325

Cloud shadow is an unignorable factor affecting the quality of remote sensing images, but there are few researches specifically focusing on cloud shadow removal and its impact on downstream remote sensing tasks. In this paper, we propose a residual group enhanced generative adversarial network (RGE-GAN) for cloud shadow removal. We design an encoder-decoder with residual group enhancement (RGE) module to remove cloud shadows from remote sensing images. RGE module can effectively enhance the deep features extracted by encoder. We further introduce a discriminator network and employ adversarial training strategy to constrain the generator to reconstruct high-quality cloud shadow removed images conforming to the distribution of remote sensing images. The joint experiments of cloud shadow removal and building extraction on real remote sensing dataset show that our cloud shadow removal method can effectively enhance the quality of remote sensing images and improve the performance of downstream remote sensing processing tasks.

关键词： Cloud shadow removal remote sensing encoder-decoder generative adversarial network

来源：评论

学校读者我要写书评

暂无评论

Study of Various Text Summarization Methods 1

引用

International Conference on Artificial Intelligence: Theory and Applications (AITA)

作者： Khan, Sarim Pathak, Abhay Chopra, Rishabh Parihar, Hemant Singh Kaur, Preet Chandan Ramrao Adik Inst Technol Navi Mumbai 400706 Maharashtra India

ISBN: (数字)9789819984763

ISBN: (纸本)9789819984756;9789819984763

This paper presents an analysis of various text summarization methods used to condense lengthy pieces of text into shorter versions while retaining the most relevant information. The study reviews different approaches to text summarization, including extraction-based and abstraction-based methods. These techniques are assessed in terms of accuracy, fluency, and coherence, using a variety of metrics such as ROUGE, BLEU, and F1 measures. The suggested model may efficiently produce a smaller body of text that is both accurate in both the semantic sense and linguistic sense by comprehending the entire text and framing it on its own. The findings of this study can help researchers and practitioners in the field of NLP to choose the most suitable text summarization method for their particular application.

关键词： encoder-decoder RNN Text summarization LSTM Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Adaptive Beamforming Based on Recurrent Deep Learning for GNSS Bands 32

Adaptive Beamforming Based on Recurrent Deep Learning for GN...

引用

32nd IEEE Signal Processing and Communications Applications Conference (SIU)

作者： Aras, Irem Erer, Isin Akdemir, Eren ASELSAN AS REHIS Ankara Turkiye Istanbul Tech Univ Elekt Muh Istanbul Turkiye

ISBN: (纸本)9798350388978;9798350388961

Global Navigation Satellite Systems (GNSS) are undoubtedly the most preferred navigation method in these days. However, GNSS signals can frequently become a target for undesired jammer signals. The most known solution for this problem is beamforming methods. In this study, recurrent neural network (RNN) structures are used to determine the beamforming coefficients of signals with known angle of arrivals. A new encoder-decoder (ED) beamforming approach is presented, which is built with long short-term memory (LSTM) cells. ED beamforming approach is compared with a previously proposed multilayer LSTM network and known null steering beamforming (NSB), which ED beamforming is resulted more successfully in terms of beam and null divergences in directions of signal arrivals and with a shorter response time.

关键词： GNSS deep learning long-short term memory (LSTM) encoder-decoder null-steering beamforming

来源：评论

学校读者我要写书评

暂无评论

A Deep-Learning Approach for the Identification of New Subtypes of Lung Cancer 25th

A Deep-Learning Approach for the Identification of New Subty...

引用

25th International Conference on Intelligent Data Engineering and Automated Learning

作者： Banerjee, Tuhin Corradini, Andrea Canon EMEA Amstelveen Netherlands MCI Innsbruck Austria

ISBN: (纸本)9783031777301;9783031777318

Lung cancer is the deadliest cancer in the world. It is caused by unchecked cell division of damaged cells in the lungs forming tumors that eventually prevent the lung from functioning properly. Identification of novel unsupervised subtypes of lung cancer is critical to reveal new insights into the underlying biology of cancer and ensure that patients receive specialized precision treatment based on the subtype of cancer they are suffering from. The ability of modern sequencing tools to produce patient-specific RNA sequencing (RNA-seq) gene expression data has transformed cancer research by offering in-depth understanding of the molecular landscape of cancer. This paper reports on a pipeline that comprise of a Deep Autoencoder (DAE) model coupled with hierarchical agglomerative clustering (H-Clust). It aims to identify new unsupervised lung cancer subtypes from RNA-seq expression samples collected from a publicly available dataset. Further, a deep learning (DL) model, Artificial Neural Network (ANN) is used to classify a patient's data into one of the newly identified subtypes.

关键词： lung cancer subtype TCGA RNA-seq deep learning DAE encoder-decoder agglomerative clustering ANN

来源：评论

学校读者我要写书评

暂无评论

Mask-Guided Joint Single Image Specular Highlight Detection and Removal 6th

Mask-Guided Joint Single Image Specular Highlight Detection ...

引用

6th Chinese Conference on Pattern Recognition and Computer Vision (PRCV)

作者： Chen, Hao Li, Li Yu, Neng Wuhan Textile Univ Sch Comp Sci & Artificial Intelligence Wuhan 430200 Peoples R China Engn Res Ctr Hubei Prov Clothing Informat Wuhan 430200 Peoples R China Hubei Prov Engn Res Ctr Intelligent Textile & Fas Wuhan 430200 Peoples R China

ISBN: (纸本)9789819985456;9789819985463

Detecting and removing specular highlights is a highly challenging task that can effectively enhance the performance of other computer vision tasks in real-world scenarios. Traditional highlight removal algorithms struggle to accurately distinguish the differences between pure white or nearly white materials and highlights, while recent deep learning-based highlight removal algorithms suffer from complex network architectures, lack of flexibility, and limited object adaptability. To address these issues, we propose an end-to-end framework for single-image highlight detection and removal that utilizes mask guidance. Our framework adopts an encoder-decoder structure, with EfficientNet serving as the backbone network for feature extraction in the encoder. The decoder gradually restores the feature map to its original size through upsampling. In the highlight detection module, the network layers are deepened, and residual modules are introduced to extract more feature information and improve detection accuracy. In the highlight removal module, we introduce the Convolutional Block Attention Module, which dynamically learns the importance of each channel and spatial position in the input feature map. This helps the model better distinguish foreground and background and improve adaptability and accuracy in complex *** results demonstrate that our proposed method outperforms existing methods, as evaluated on the public SHIQ dataset through comparative experiments. Our method achieves superior performance in highlight detection and removal.

关键词： Highlight detection Highlight removal Attention End to End encoder-decoder

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：