检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Zhang, Chenjiao Wang, Lulu Wu, Xing He, Zhongshi Chongqing Univ Coll Comp Sci Chongqing Peoples R China

ISBN: (纸本)9780738133669

Pulmonary nodule detection in low-dose computed tomography (CT) images is essential for early screening and treatment of lung cancer. Previous related researches based on deep convolutional neural networks generally rely on 2D or 2.5D components and only focus on the output feature information under a single receptive field. Considering the 3D nature of lung CT images and the performance limitation of state-of-the-art nodule detection methods, we develop a novel 3D multi-branch region proposal network with an encoder-decoder structure. Specifically, each parallel branch is designed with 3D residual blocks and U-Net-like structure to effectively extract multi-scale fusion features based on 3D spatial information of CT scans, and the strategies of varying receptive fields and sharing weight parameters are used to improve the sensitivity of the detection network to nodules with scale variation and maintain the original parameters. Besides, we propose a multi-scale attentional feature fusion module to better fuse high-resolution and semantically strong features and adaptively learn the inter-dependency information of different feature maps. Finally, we compare a dynamically scaled cross entropy loss and online hard example mining (OHEM) to combat the imbalance of positive and negative samples during training, which is aimed at assisting with network optimization. Our extensive experiments on publicly available CT scans obtained from LUNA16 and TianChi(1) competition dataset demonstrate that our method outperform state-of-the-art pulmonary nodule detection models.

关键词： pulmonary nodule detection 3d convolutional neural network encoder-decoder multi-scale attentional feature fusion

来源：评论

学校读者我要写书评

暂无评论

Constrained Image Splicing Detection and Localization With Attention-Aware encoder-decoder and Atrous Convolution

引用

IEEE ACCESS 2020年 8卷 6729-6741页

作者： Liu, Yaqi Zhao, Xianfeng Chinese Acad Sci Inst Informat Engn State Key Lab Informat Secur Beijing 100093 Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing 100093 Peoples R China

Constrained image splicing detection and localization (CISDL) is a newly formulated image forensics task and plays an important role in verifying the generating process of a forged image. CISDL conducts dense matching between two investigated images and detects whether one image has forged regions pasted from the other. In this work, we introduce a novel attention-aware encoder-decoder deep matching network named as AttentionDM for CISDL. An encoder-decoder with atrous convolution is newly designed for hierarchical features dense matching and fine-grained masks generation. A novel attention-aware correlation computation module is built on normalization operations and informative features recalibration with channel attention blocks. Last but not least, VGG and ResNets are respectively formulated as feature extractors for comprehensive comparisons in CISDL. Extensive experiments demonstrate the superior performance of AttentionDM over the state-of-the-art methods.

关键词： encoder-decoder atrous convolution normalization channel attention

来源：评论

学校读者我要写书评

暂无评论

Pedestrian behavior prediction model with a convolutional LSTM encoder-decoder

引用

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS 2020年 560卷 125132-125132页

作者： Chen, Kai Song, Xiao Han, Daolin Sun, Jinghan Cui, Yong Ren, Xiaoxiang Beihang Univ BUAA Beijing Peoples R China Univ Illinois Urbana IL USA Nanan Primary Sch Xian Shanxi Peoples R China

Pedestrian behavior modeling is a challenging problem especially in crowded transportation scenarios. Some recent studies have addressed this problem using deep neural network, but the accuracy of trajectory prediction is still not high because the internal structure of the typical deep neural network with long short-term memory (LSTM) is a one-dimensional vector, which destroys the spatial information around a pedestrian. Therefore, these models cannot fully learn spatial sensing behavior of pedestrians. To solve this, we recommend using multi-channel tensors to represent the environmental information of pedestrians. Meanwhile, the spatiotemporal interactions among the pedestrians are represented by convolution operations of these tensors. Then, an end-to-end fully convolutional LSTM encoder-decoder is designed, trained and tested. Finally, our approach is compared with existing LSTM-based methods using five crowded video sequences with public datasets. The results show that our method reduces the displacement offset error and provides more realistic trajectory prediction in manifold cases. (c) 2020 Published by Elsevier B.V.

关键词： Pedestrian behavior model Trajectory prediction Long short-term memory Convolution encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

An encoder-decoder based thermo-visible image translation for disguised and undisguised faces

引用

IMAGE AND VISION COMPUTING 2022年 119卷 104376-104376页

作者： Kumar, Sumit Singh, Satish Kumar Mishra, Nayaneesh Kumar Dutta, Mainak Indian Inst Informat Technol Jhalwa 211012 Prayagraj India Qualcomm Hyderabad Telangana India

Thermal cameras can capture images even in low light conditions. However, humans cannot recognize human faces in thermal images. Translation of thermal images to visible domain is one solution to the problem of face recognition in thermal images. Most of the research works have proposed Generative Adversarial Networks (GANs) based solutions for thermal to visible image translation. However, GAN is a heavy network that consumes huge amount of resource for thermal to visible image translation. In this paper, we propose an encoder-decoder architecture for thermal to visible image translation of human faces. Since our proposed architecture is not based on GANs, it is lightweight. The proposed method works well for both disguised and non-disguised thermal facial images. Standard comparison parameters such as Peak Signal-to-noise Ratio (PSNR), Structural Similarity Index (SSIM), and Multiscale Structural Similarity Index (MS-SSIM) are used to evaluate the quality of the generated visible images with respect to the ground truth. It has been found that our proposed architecture outperforms the current state-of-the-art image translator architectures namely pix2pix, Cycle-GAN, modified thermal to visible GAN and Dual GAN by a considerable margin for both disguised as well as non-disguised dataset. (c) 2022 Elsevier B.V. All rights reserved.

关键词： Image translation Generative Adversarial Networks (GAN) Pix2Pix Cycle-GAN encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

LSTM enhanced by dual-attention-based encoder-decoder for daily peak load forecasting

引用

ELECTRIC POWER SYSTEMS RESEARCH 2022年第0期208卷 1页

作者： Zhu, Kedong Li, Yaping Mao, Wenbo Li, Feng Yan, Jiahao China Elect Power Res Inst Power Automat Dept Nanrui 8 Nanjing 210003 Jiangsu Peoples R China

Daily peak load forecasting is a challenging problem in the filed of electric power load forecasting. Since the nonlinear and dynamic of influence factors and their sequential dependencies are significant for modeling daily peak load, a prediction model based on long short-term memory (LSTM) enhanced by dual-attention-based encoder-decoder is presented. Functioned as the specific encoder and decoder, LSTM is utilized to participate in the nonlinear dynamic temporal modeling. The encoder-decoder is used for information utilization of both the influence factors and daily peak load. Moreover, a dual-attention mechanism, which is inserted into the encoder decoder, is designed to take into account the effects of different influence factors and time nodes on the daily peak load simultaneously. It is benefit for the above mechanism design to analyze the characteristics of daily peak load precisely and to achieve more accurate prediction results. Comprehensive experiments are performed based on a real set of one provincial capital city in eastern China. The case study shows that the proposed methodology provides the most accurate results with an average MAPE 2.07%, an average RMSE 133 MW and an average MAE 326.6 MW.

关键词： Dual-attention mechanism Daily peak load forecasting encoder-decoder Long short-term memory (LSTM)

来源：评论

学校读者我要写书评

暂无评论

A fully-convolutional residual encoder-decoder neural network to localize breast cancer on histopathology images

引用

COMPUTERS IN BIOLOGY AND MEDICINE 2022年 147卷 105698-105698页

作者： Farajzadeh, Nacer Sadeghzadeh, Nima Hashemzadeh, Mahdi Azarbaijan Shahid Madani Univ Fac Informat Technol & Comp Engn Tabriz Iran Azarbaijan Shahid Madani Univ Artificial Intelligence & Machine Learning Res Lab Tabriz Iran Azarbaijan Shahid Madani Univ Azarshahr Rd Tabriz *** Iran

Cancer detection in its early stages may allow patients to receive the proper treatment and save lives along with recovering the routine lifestyles. Breast cancer is of the top leading causes of mortality among women all around the globe. A source to find these cancerous nuclei is through analyzing histopathology images. These images, however, are very complex and large. Thus, locating the cancerous nuclei in them is very challenging. Hence, if an expert fails to diagnose their patients via these images, the situation may be exacerbated. Therefore, this study aims to introduce a method to mask as many cancer nuclei on histopathology images as possible with a high visual aesthetic to make them distinguishable by experts easily. A tailored residual fully convolutional encoderdecoder neural network based on end-to-end learning is proposed to issue the matter. The proposed method is evaluated quantitatively and qualitatively on ER + BCa H&E-stained dataset. The average detection accuracy achieved by the method is 98.61%, which is much better than that of competitors.

关键词： Breast cancer nuclei End-to-End learning Fully convolutional neural networks Image masking encoder-decoder Residual networks

来源：评论

学校读者我要写书评

暂无评论

Establishment of CNN and encoder-decoder Models for the Prediction of Characteristics of Flow and Heat Transfer around NACA Sections

引用

ENERGIES 2022年第23期15卷 9204页

作者： Seo, Janghoon Yoon, Hyun-Sik Kim, Min-Il Pusan Natl Univ Dept Naval Architecture & Ocean Engn 2 Busandaehak Ro 63beon Gil Busan 46241 South Korea

The present study established two different models based on the convolutional neural network (CNN) and the encoder-decoder (ED) to predict the characteristics of the flow and heat transfer around the NACA sections. The established CNN predicts the aerodynamic coefficients and the Nusselt number. The established ED model predicts the velocity, pressure and thermal fields to explain the performances of the aerodynamics and heat transfer. These two models were trained and tested by the dataset extracted from the computational fluid dynamics (CFD) simulations. The predictions mostly matched well with the true data. The contours of the velocity components and the pressure coefficients reasonably explained the variation of the aerodynamic coefficients according to the geometric parameter of the NACA section. In order to physically interpret the heat transfer performance, more quantitative and qualitative information are needed owing to the lack of the correlation and the resolution of the thermal fields. Consequently, the present approaches will be useful to design the NACA section-based shape giving higher aerodynamic and heat transfer performances by quickly predicting the force and heat transfer coefficients. In addition, the predicted flow and thermal fields will provide the physical interpretation of the aerodynamic and heat transfer performances.

关键词： convolutional neural network encoder-decoder aerodynamics heat transfer NACA section computational fluid dynamics

来源：评论

学校读者我要写书评

暂无评论

Three-Dimensional Human Pose Estimation from Sparse IMUs through Temporal encoder and Regression decoder

引用

SENSORS 2023年第7期23卷 3547页

作者： Liao, Xianhua Dong, Jiayan Song, Kangkang Xiao, Jiangjian Ningbo Univ Sch Informat Sci & Engn Ningbo 315211 Peoples R China Chinese Acad Sci Ningbo Inst Mat Technol & Engn Ningbo 315201 Peoples R China

Three-dimensional (3D) pose estimation has been widely used in many three-dimensional human motion analysis applications, where inertia-based path estimation is gradually being adopted. Systems based on commercial inertial measurement units (IMUs) usually rely on dense and complex wearable sensors and time-consuming calibration, causing intrusions to the subject and hindering free body movement. The sparse IMUs-based method has drawn research attention recently. Existing sparse IMUs-based three-dimensional pose estimation methods use neural networks to obtain human poses from temporal feature information. However, these methods still suffer from issues, such as body shaking, body tilt, and movement ambiguity. This paper presents an approach to improve three-dimensional human pose estimation by fusing temporal and spatial features. Based on a multistage encoder-decoder network, a temporal convolutional encoder and human kinematics regression decoder were designed. The final three-dimensional pose was predicted from the temporal feature information and human kinematic feature information. Extensive experiments were conducted on two benchmark datasets for three-dimensional human pose estimation. Compared to state-of-the-art methods, the mean per joint position error was decreased by 13.6% and 19.4% on the total capture and DIP-IMU datasets, respectively. The quantitative comparison demonstrates that the proposed temporal information and human kinematic topology can improve pose accuracy.

关键词： three-dimensional human pose sparse IMUs encoder-decoder temporal convolutional encoder human kinematics hierarchy regression decoder

来源：评论

学校读者我要写书评

暂无评论

Improving soil moisture prediction using a novel encoder-decoder model with residual learning

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2022年 195卷 106816-106816页

作者： Li, Qingliang Li, Zhongyan Wei Shangguan Wang, Xuezhi Lu Li Yu, Fanhua Changchun Normal Univ Coll Comp Sci & Technol Changchun 130032 Peoples R China Sun Yat Sen Univ Sch Atmospher Sci Guangdong Prov Key Lab Climate Change & Nat Disas Southern Marine Sci & Engn Guangdong Lab Zhuhai Guangzhou Guangdong Peoples R China Jilin Univ Coll Comp Sci & Technol Changchun 130012 Peoples R China

The skillful prediction of soil moisture can provide much help for many practical applications including ecosystem management and precision agriculture. It presents great challenges because the future variation of soil moisture has much uncertainty. Therefore, a novel encoder-decoder deep learning model with residual learning based on Long Short-Term Memory (EDT-LSTM) is developed in this study as an alternative data-intelligence tool. This model includes two layers: the encoder-decoder LSTM layer and LSTM with a fully connected layer, which is used to enhance the prediction ability by considering the intermediate time-series data between the input time step and the predictive time step. We tested EDT-LSTM for soil moisture prediction at the lead time of 1, 3, 5, 7 and 10 days by using data from FLUXNET sites. The result shows that the improvements brought by EDT-LSTM were about 7.95% (1 day), 10.10% (3 days), 12.68% (5 days), 15.49% (7 days) and 19.71% (10 days) in average according to the R-2 taking LSTM as the baseline. Furthermore, the predictability of soil moisture over various conditions (i.e., different hyper-parameters in EDT-LSTM, different predictive models, different climate regions and different sites) has been widely discussed for the understanding of models' behavior in this paper. The proposed EDT-LSTM offered a new tool to predict soil moisture better. The code of EDT-LSTM is publicly available at https://***/ljz1228/CLM-LSTM-soil-moisture-prediction.

关键词： Soil moisture Machine learning LSTM encoder-decoder Residual learning

来源：评论

学校读者我要写书评

暂无评论

encoder-decoder Based CNN Structure for Microscopic Image Identification 27th

Encoder-Decoder Based CNN Structure for Microscopic Image Id...

引用

27th International Conference on Neural Information Processing

作者： Polap, Dawid Wozniak, Marcin Korytkowski, Marcin Scherer, Rafal Silesian Tech Univ Fac Appl Math Kaszubska 23 PL-44100 Gliwice Poland Czestochowa Tech Univ Dept Intelligent Comp Syst Czestochowa Poland

ISBN: (纸本)9783030638290;9783030638306

The significant development of classifiers has made object detection and classification by using neural networks more effective and more straightforward. Unfortunately, there are images where these operations are still difficult due to the overlap of objects or very blurred contours. An example is images obtained from various microscopes, where bacteria or other biological structures can merge, or even have different shapes. To this end, we propose a novel solution based on convolutional auto-encoders and additional two-dimensional image processing techniques to achieve better efficiency in the detection and classification of small objects in such images. In our research, we have included elements such as very weak contours of shapes that may result from the merging of biological objects. The presented method was compared with others, such as a faster recurrent convolutional neural network to indicate the advantages of the proposed solution.

关键词： Convolutional neural networks encoder-decoder Bacteria shape detection

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：