检索结果-内蒙古大学图书馆

Efficient encoder-decoder Network With Estimated Direction for SAR Ship Detection

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2022年 19卷

作者： Niu, Yuzhen Li, Yuezhou Huang, Jiangyi Chen, Yuzhong Fuzhou Univ Coll Comp & Data Sci Fujian Prov Key Lab Networking Comp & Intelligent Fuzhou 350116 Peoples R China Minist Educ Key Lab Spatial Data Min & Informat Sharing Fuzhou 350108 Fujian Peoples R China

Synthetic aperture radar (SAR) image ship detection has important applications in marine surveillance. There are two limitations when applying advanced detection methods naively for SAR ship detection. First, most detectors construct the model as an encoder and rely on the feature pyramid network (FPN) head for accurate prediction, which may lead to high computational costs. Second, the background noises in the ground truth (annotated as rectangular bounding boxes) of angular ships bring difficulties for model training. To meet these challenges, we propose an efficient encoder-decoder network with estimated direction for ship detection in SAR images. First, we present an anchor-free encoder-decoder model that can efficiently extract multiple-level features. Second, we formulate ship detection as a multitask learning problem, including a bounding box prediction and a ship direction regression. The estimated ship direction can weakly supervise and benefit ship detection. Furthermore, we develop a center-weighted labeling method for overlapped annotations. Comprehensive experiments on SAR-Ship-Detection and SSDD datasets show that our method achieves state-of-the-art performance with a high running speed.

关键词： Marine vehicles Radar polarimetry Synthetic aperture radar Decoding Feature extraction Task analysis Background noise encoder-decoder multitask learning ship detection in SAR image synthetic aperture radar (SAR) image

来源：评论

学校读者我要写书评

暂无评论

ED-DRAP: encoder-decoder Deep Residual Attention Prediction Network for Radar Echoes

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2022年 19卷

作者： Che, Hongshu Niu, Dan Zang, Zengliang Cao, Yichao Chen, Xisong Southeast Univ Key Lab Measurement & Control CSE Minist Educ Nanjing 210096 Peoples R China Southeast Univ Sch Automat Nanjing 210096 Peoples R China PLA Univ Sci & Technol Inst Meteorol & Oceanog Nanjing 211101 Peoples R China

Precipitation nowcasting is quite important and fundamental. It underlies various public services ranging from rainstorm warnings to flight safety. In order to further improve the prediction accuracy for the spatiotemporal sequence forecasting problem, we propose an encoder-decoder deep residual attention prediction network, which adaptively rescales the multiscale sequence- and spatial-wise features and achieves very deep trainable residual prediction by integrating global residual learning and local deep residual sequence and spatial attention blocks (RSSABs). Experiments in a real-world radar echo map dataset of South China show that compared with the ingenious PredRNN++, TrajGRU methods, and newly proposed Unet-based methods, our ED-DRAP network performs better on the precipitation nowcasting metrics, as well as occupies small GPU memory.

关键词： Feature extraction Spatiotemporal phenomena Radar Decoding Forecasting Three-dimensional displays Radar remote sensing Deep residual prediction encoder-decoder precipitation nowcasting sequence and spatial attention

来源：评论

学校读者我要写书评

暂无评论

A Multi-Head Self-Attention-based on GRU encoder-decoder Framework for Predicting Molten Iron Silicon Content 12

A Multi-Head Self-Attention-based on GRU Encoder-Decoder Fra...

引用

IEEE 12th Data Driven Control and Learning Systems Conference (DDCLS)

作者： Cai, Yu Yang, Chunjie Lou, Siwei Zeng, Zhenyu Liao, Huanyu Zhang, Bing Zhejiang Univ Coll Control Sci & Engn Hangzhou 310013 Peoples R China Alibaba Grp Hangzhou 311121 Peoples R China

ISBN: (纸本)9798350321050

Silicon content is a significant index in the process of blast furnace ironmaking. It is used to measure the quality of molten iron *** only meets the requirements if it is too high or too low. In the production process,the silicon content in molten iron needs to be controlled within a stable *** the same time,due to the time lag, nonlinear and dynamic characteristics of blast furnace itself, it is difficult to predict the silicon content accurately. This paper proposes a multi-head self-attention-based gate recurrent unit encoder-decoder framework that can better extract global dynamic features and local features, improve prediction accuracy and pass the experimental verification.

关键词： Blast Furnace Si Content Prediction encoder-decoder Multi-Head Attention Mechanism Gate Recurrent Unit

来源：评论

学校读者我要写书评

暂无评论

Utilizing Attention-Based Multi-encoder-decoder Neural Networks for Freeway Traffic Speed Prediction

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2022年第8期23卷 11960-11969页

作者： Abdelraouf, Amr Abdel-Aty, Mohamed Yuan, Jinghui Univ Cent Florida Dept Civil Environm & Construct Engn Orlando FL 32816 USA

Speed prediction is a crucial yet complicated task for intelligent transportation systems. The challenge derives from the complex spatiotemporal dependencies of traffic parameters. In the past few years, deep neural networks have achieved the best traffic speed prediction performance. However, most models depend on short-term input sequences to predict short/long-term traffic speed (e.g., predicting speed for the next hour using data from the past hour). These models fail to consider the daily and weekly periodic behavior of traffic. Another problem posed by neural networks is the lack of interpretability as they often operate as ``black boxes''. In this paper, an attention-based multi-encoder-decoder (Att-MED) model is proposed to predict traffic speed. The model uses convolutional-LSTMs to capture the spatiotemporal relationship of multiple input sequences, namely short-term, daily and weekly traffic patterns. The model also employs an LSTM to model the output predictions sequentially. Furthermore, attention mechanism is used to weigh the contribution of each traffic sequence towards the output predictions. The proposed network architecture, when trained end-to-end, results in a superior prediction accuracy compared to baseline models. In addition to contributing towards performance, the attention mechanism creates weight values, which when visualized, provide insights into the decision-making process of the neural network, and consequently produce explainable outputs. Att-MED's extracted attention weights highlight the contribution of daily and weekly periodic input towards speed prediction.

关键词： Predictive models Feature extraction Roads Decoding Computational modeling Traffic control Data mining Traffic forecasting multi-sequence encoder-decoder attention explainable neural networks

来源：评论

学校读者我要写书评

暂无评论

EDChannel: channel prediction of backscatter communication network based on encoder-decoder

引用

TELECOMMUNICATION SYSTEMS 2022年第1期81卷 99-114页

作者： Li, Dengao Wen, Yongxin Xu, Shuang Wang, Qiang Bai, Ruiqin Zhao, Jumin Taiyuan Univ Technol Coll Data Sci Jinzhong 030600 Shanxi Peoples R China Taiyuan Univ Technol Coll Informat & Comp Jinzhong 030600 Shanxi Peoples R China Technol Res Ctr Spatial Informat Network Engn Sha Jinzhong 030600 Peoples R China Intelligent Percept Engn Technol Ctr Shanxi Jinzhong 030600 Peoples R China

Backscatter communication networks have attracted much attention due to their small size and low power waste, but their spectrum resources are very limited and are often affected by link bursts. Channel prediction is a method to effectively utilize the spectrum resources and improve communication quality. Most channel prediction methods have failed to consider both spatial and frequency diversity. Meanwhile, there are still deficiencies in the existing channel detection methods in terms of overhead and hardware dependency. For the above reasons, we design a sequence-to-sequence channel prediction scheme. Our scheme is designed with three modules. The channel prediction module uses an encoder-decoder based deep learning model (EDChannel) to predict the sequence of channel indicator measurements. The channel detection module decides whether to perform a channel detection by a trigger that reflects the prediction effect. The channel selection module performs channel selection based on the channel coefficients of the prediction results. We use a commercial reader to collect data in a real environment, and build an EDChannel model based on the deep learning module of Tensorflow and Keras. As a result, we have implemented the channel prediction module and completed the overall channel selection process. The experimental results show that the EDChannel algorithm has higher prediction accuracy than the previous state-of-the-art methods. The overall throughput of our scheme is improved by approximately 2.9% and 14.1% over Zhao's scheme in both stable and unstable environments.

关键词： Backscatter communication Channel prediction Deep learning encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Skeleton-Based Human Action Recognition with A Physics-Augmented encoder-decoder Network 13

Skeleton-Based Human Action Recognition with A Physics-Augme...

引用

Conference on Geospatial Informatics XIII

作者： Guo, Hongji Aved, Alexander Roller, Collen Ardiles-Cruz, Erika Ji, Qiang Rensselaer Polytech Inst Troy NY 12180 USA Air Force Res Lab Rome NY 13441 USA

ISBN: (数字)9781510661653

ISBN: (纸本)9781510661646;9781510661653

Human action recognition is important for many applications such as surveillance monitoring, safety, and health-care. As 3D body skeletons can accurately characterize body actions and are robust to camera views, we propose a 3D skeleton-based human action method. Different from the existing skeleton-based methods that use only geometric features for action recognition, we propose a physics-augmented encoder and decoder model that produces physically plausible geometric features for human action recognition. Specifically, given the input skeleton sequence, the encoder performs a spatiotemporal graph convolution to produce spatiotemporal features for both predicting human actions and estimating the generalized positions and forces of body joints. The decoder, implemented as an ODE solver, takes the joint forces and solves the Euler-Lagrangian equation to reconstruct the skeletons in the next frame. By training the model to simultaneously minimize the action classification and the 3D skeleton reconstruction errors, the encoder is ensured to produce features that are consistent with both body skeletons and the underlying body dynamics as well as being discriminative. The physics-augmented spatiotemporal features are used for human action classification. We evaluate the proposed method on NTU-RGB+D, a large-scale dataset for skeleton-based action recognition. Compared with existing methods, our method achieves higher accuracy and better generalization ability.

关键词： Skeleton-based action recognition physics encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

encoder-decoder Architecture for 3D Seismic Inversion

引用

SENSORS 2023年第1期23卷 61-61页

作者： Gelboim, Maayan Adler, Amir Sun, Yen Araya-Polo, Mauricio Braude Coll Engn Elect Engn Dept IL-2161002 Karmiel Israel TotalEnergies EP R&T Houston TX 77002 USA

Inverting seismic data to build 3D geological structures is a challenging task due to the overwhelming amount of acquired seismic data, and the very-high computational load due to iterative numerical solutions of the wave equation, as required by industry-standard tools such as Full Waveform Inversion (FWI). For example, in an area with surface dimensions of 4.5 km x 4.5 km, hundreds of seismic shot-gather cubes are required for 3D model reconstruction, leading to Terabytes of recorded data. This paper presents a deep learning solution for the reconstruction of realistic 3D models in the presence of field noise recorded in seismic surveys. We implement and analyze a convolutional encoder-decoder architecture that efficiently processes the entire collection of hundreds of seismic shot-gather cubes. The proposed solution demonstrates that realistic 3D models can be reconstructed with a structural similarity index measure (SSIM) of 0.9143 (out of 1.0) in the presence of field noise at 10 dB signal-to-noise ratio.

关键词： 3D reconstruction seismic inversion seismic velocity inverse problems deep learning transfer learning encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

CapNet: An encoder-decoder based Neural Network Model for Automatic Bangla Image Caption Generation

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2022年第8期13卷 752-759页

作者： Rahman, Rashik Saha, Aloke Kumar Murad, Hasan Al Masud, Shah Murtaza Rashid Rahman, Nakiba Nuren Momtaz, A. S. Zaforullah Univ Asia Pacific Comp Sci & Engn Dhaka Bangladesh Chittagong Univ Engn & Technol Comp Sci & Engn Chattogram Bangladesh

Automatic caption generation from images has become an active research topic in the field of Computer Vision (CV) and Natural Language Processing (NLP). Machine generated image caption plays a vital role for the visually impaired people by converting the caption to speech to have a better understanding of their surrounding. Though significant amount of research has been conducted for automatic caption generation in other languages, far too little effort has been devoted to Bangla image caption generation. In this paper, we propose an encoder-decoder based model which takes an image as input and generates the corresponding Bangla caption as output. The encoder network consists of a pretrained image feature extractor called ResNet-50, while the decoder network consists of Bidirectional LSTMs for caption generation. The model has been trained and evaluated using a Bangla image captioning dataset named BanglaLekhaImageCaptions. The proposed model achieved a training accuracy of 91% and BLEU-1, BLEU-2, BLEU-3, BLEU-4 scores of 0.81, 0.67, 0.57, and 0.51 respectively. Moreover, a comparative study for different pretrained feature extractors such as VGG-16 and Xception is presented. Finally, the proposed model has been deployed on an embedded device for analysing the inference time and power consumption.

关键词： -Bangla image caption generation encoder-decoder bidirectional long short term memory (LSTM) bangla natural language processing (NLP)

来源：评论

学校读者我要写书评

暂无评论

Dynamic energy system modeling using hybrid physics-based and machinelearning encoder–decoder models

引用

Energy and AI 2022年第3期9卷 128-138页

作者： Derek Machalek Jake Tuttle Klas Andersson Kody M.Powell Department of Chemical Engineering University of UtahSalt Lake CityUTUnited States of America Taber International LLCUnited States of America Department of Space Earthand EnvironmentUniversity of ChalmersGothenburgSweden Department of Mechanical Engineering University of UtahSalt Lake CityUTUnited States of America

Three model configurations are presented for multi-step time series predictions of the heat absorbed by thewater and steam in a thermal power plant. The models predict over horizons of 2, 4, and 6 steps into thefuture, where each step is a 5-minute increment. The evaluated models are a pure machine learning model, anovel hybrid machine learning and physics-based model, and the hybrid model with an incomplete dataset. Thehybrid model deconstructs the machine learning into individual boiler heat absorption units: economizer, waterwall, superheater, and reheater. Each configuration uses a gated recurrent unit (GRU) or a GRU-based encoder–decoder as the deep learning architecture. Mean squared error is used to evaluate the models compared totarget values. The encoder–decoder architecture is over 11% more accurate than the GRU only models. Thehybrid model with the incomplete dataset highlights the importance of the manipulated variables to the *** hybrid model, compared to the pure machine learning model, is over 10% more accurate on averageover 20 iterations of each model. Automatic differentiation is applied to the hybrid model to perform a localsensitivity analysis to identify the most impactful of the 72 manipulated variables on the heat absorbed in theboiler. The models and sensitivity analyses are used in a discussion about optimizing the thermal power plant.

关键词： Hybrid model encoder-decoder Time series Automatic differentiation Thermal power plant

来源：评论

学校读者我要写书评

暂无评论

IDM-Net: A Multi-Task Supported encoder-decoder Framework for Magnetic Field Inverse Design

IDM-Net: A Multi-Task Supported Encoder-Decoder Framework fo...

引用

2023 IEEE International Conference on Applied Superconductivity and Electromagnetic Devices, ASEMD 2023

作者： Wang, Jiaqi Zhang, Qiankun Huazhong University of Science and Technology School of Cyber Science and Engineering Wuhan China

ISBN: (纸本)9798350301571

This study presents a novel end-to-end trainable network named IDM-Net (Inverse Design Network for Magnetic Fields) that facilitates multi-task supported inverse design of magnetic fields. Employing the encoder-decoder idea, IDM-Net accomplishes the inverse design of magnet parameters by leveraging magnetic field data for backpropagation. The encoder is harnessed to extract magnetic field features and classify magnet shapes, while the decoder predicts other properties, including magnet size and position. This innovative approach breaks the constraints of single magnet types in existing research, enabling the inverse design of properties for magnets with diverse shapes. Our experimental results demonstrate remarkable performance, with a 95.2% accuracy in magnet shape classification and a mere 0.28% error in magnet property prediction. By introducing the encoder-decoder idea in the field of inverse design for magnetic fields, we showcase significantly enhanced accuracy and pave the way for broader applications of this technology. © 2023 IEEE.

关键词： deep learning design optimization encoder-decoder inverse design magnetic field

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

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

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：