检索结果-内蒙古大学图书馆

Streamflow modelling and forecasting for Canadian watersheds using LSTM networks with attention mechanism

NEURAL COMPUTING & APPLICATIONS 2022年第22期34卷 19995-20015页

作者： Girihagama, Lakshika Khaliq, Muhammad Naveed Lamontagne, Philippe Perdikaris, John Roy, Rene Sushama, Laxmi Elshorbagy, Amin Natl Res Council Canada Ottawa ON Canada Ontario Power Generat Niagara Falls ON Canada Hydro Meteo Notre Dame Des Prairies PQ Canada McGill Univ Montreal PQ Canada Univ Saskatchewan Saskatoon SK Canada

This study investigates the capability of sequence-to-sequence machine learning (ML) architectures in an effort to develop streamflow forecasting tools for Canadian watersheds. Such tools are useful to inform local and region-specific water management and flood forecasting related activities. Two powerful deep-learning variants of the Recurrent Neural Network were investigated, namely the standard and attention-based encoder-decoder long short-term memory (LSTM) models. Both models were forced with past hydro-meteorological states and daily meteorological data with a look-back time window of several days. These models were tested for 10 different watersheds from the Ottawa River watershed, located within the Great Lakes Saint-Lawrence region of Canada, an economic powerhouse of the country. The results of training and testing phases suggest that both models are able to simulate overall hydrograph patterns well when compared to observational records. Between the two models, the attention model significantly outperforms the standard model in all watersheds, suggesting the importance and usefulness of the attention mechanism in ML architectures, not well explored for hydrological applications. The mean performance accuracy of the attention model on unseen data, when assessed in terms of mean Nash-Sutcliffe Efficiency and Kling-Gupta Efficiency is, respectively, found to be 0.985 and 0.954 for these watersheds. Streamflow forecasts with lead times of up to 5 days with the attention model demonstrate overall skillful performance with well above the benchmark accuracy of 70%. The results of the study suggest that the encoder-decoder LSTM, with attention mechanism, is a powerful modelling choice for developing streamflow forecasting systems for Canadian watersheds.

关键词： Streamflow forecasting LSTM encoder-decoder architecture Attention-based models Deep learning

来源：评论

学校读者我要写书评

暂无评论

MSCFNet: A Lightweight Network With Multi-Scale Context Fusion for Real-Time Semantic Segmentation

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2022年第12期23卷 25489-25499页

作者： Gao, Guangwei Xu, Guoan Yu, Yi Xie, Jin Yang, Jian Yue, Dong Nanjing Univ Posts & Telecommun Inst Adv Technol Nanjing 210023 Peoples R China Natl Inst Informat Digital Content & Media Sci Res Div Tokyo 1018430 Japan Soochow Univ Prov Key Lab Comp Informat Proc Technol Suzhou 215006 Peoples R China Nanjing Univ Posts & Telecommun Coll Automat Nanjing 210023 Peoples R China Nanjing Univ Posts & Telecommun Coll Artificial Intelligence Nanjing 210023 Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Technol Suzhou 210094 Peoples R China Nanjing Univ Posts & Telecommun Coll Automat Inst Adv Technol Nanjing 210023 Peoples R China Nanjing Univ Posts & Telecommun Coll Artificial Intelligence Inst Adv Technol Nanjing 210023 Peoples R China

In recent years, how to strike a good trade-off between accuracy, inference speed, and model size has become the core issue for real-time semantic segmentation applications, which plays a vital role in real-world scenarios such as autonomous driving systems and drones. In this study, we devise a novel lightweight network using a multi-scale context fusion (MSCFNet) scheme, which explores an asymmetric encoder-decoder architecture to alleviate these problems. More specifically, the encoder adopts some developed efficient asymmetric residual (EAR) modules, which are composed of factorization depth-wise convolution and dilation convolution. Meanwhile, instead of complicated computation, simple deconvolution is applied in the decoder to further reduce the amount of parameters while still maintaining the high segmentation accuracy. Also, MSCFNet has branches with efficient attention modules from different stages of the network to well capture multi-scale contextual information. Then we combine them before the final classification to enhance the expression of the features and improve the segmentation efficiency. Comprehensive experiments on challenging datasets have demonstrated that the proposed MSCFNet, which contains only 1.15M parameters, achieves 71.9% Mean IoU on the Cityscapes testing dataset and can run at over 50 FPS on a single Titan XP GPU configuration.

关键词： Convolution Semantics Ear Real-time systems Image segmentation Feature extraction Task analysis Real-time semantic segmentation lightweight network encoder-decoder architecture context fusion

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Multiscale Fusion Network Based on Regional Attention for Remote Sensing Images

引用

IEEE ACCESS 2020年 8卷 107802-107813页

作者： Lu, Wanzhen Liang, Longxue Wu, Xiaosuo Wang, Xiaoyu Cai, Jiali Lanzhou Jiaotong Univ Elect & Informat Engn Dept Lanzhou 730073 Peoples R China Gansu Acad Sci Inst Sensor Technol Lanzhou 730070 Peoples R China Lanzhou Jiaotong Univ Key Lab Opt Technol & Intelligent Control Minist Educ Lanzhou 730070 Peoples R China

With the widespread application of semantic segmentation in remote sensing images with high-resolution, how to improve the accuracy of segmentation becomes a research goal in the remote sensing field. An innovative Fully Convolutional Network (FCN) is proposed based on regional attention for improving the performance of the semantic segmentation framework for remote sensing images. The proposed network follows the encoder-decoder architecture of semantic segmentation and includes the following three strategies to improve segmentation accuracy. The enhanced GCN module is applied to capture the semantic features of remote sensing images. MGFM is proposed to capture different contexts by sampling at different densities. Furthermore, RAM is offered to assign large weights to high-value information in different regions of the feature map. Our method is assessed on two datasets: ISPRS Potsdam dataset and CCF dataset. The results indicate that our model with those strategies outperforms baseline models (DCED50) concerning F1, mean IoU and PA, 10.81%,19.11%, and 11.36% on the Potsdam dataset and 29.26%, 27.64% and 13.57% on the CCF dataset.

关键词： Convolution Feature extraction Remote sensing Image segmentation Semantics Random access memory Kernel Remote sensing fully convolutional networks semantic segmentation encoder-decoder architecture regional attention Potsdam dataset CCF dataset

来源：评论

学校读者我要写书评

暂无评论

Convolutional Edge Constraint-Based U-Net for Salient Object Detection

引用

IEEE ACCESS 2019年 7卷 48890-48900页

作者： Han, Le Li, Xuelong Dong, Yongsheng Chinese Acad Sci Xian Inst Opt & Precis Mech Key Lab Spectral Imaging Technol CAS Xian 710119 Shaanxi Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Northwestern Polytech Univ Sch Comp Sci Xian 710072 Shaanxi Peoples R China Northwestern Polytech Univ Ctr OPT IMagery Anal & Learning OPTIMAL Xian 710072 Shaanxi Peoples R China Henan Univ Sci & Technol Sch Informat Engn Luoyang 471023 Peoples R China

The salient object detection is receiving more and more attention from researchers. An accurate saliency map will be useful for subsequent tasks. However, in most saliency maps predicted by existing models, the objects regions are very blurred and the edges of objects are irregular. The reason is that the hand-crafted features are the main basis for existing traditional methods to predict salient objects, which results in different pixels belonging to the same object often being predicted different saliency scores. Besides, the convolutional neural network (CNN)-based models predict saliency maps at patch scale, which causes the objects edges of the output to be fuzzy. In this paper, we attempt to add an edge convolution constraint to a modified U-Net to predict the saliency map of the image. The network structure we adopt can fuse the features of different layers to reduce the loss of information. Our SalNet predicts the saliency map pixel-by-pixel, rather than at the patch scale as the CNN-based models do. Moreover, in order to better guide the network mining the information of objects edges, we design a new loss function based on image convolution, which adds an L1 constraint to the edge information of saliency map and ground-truth. Finally, experimental results reveal that our SalNet is effective in salient object detection task and is also competitive when compared with 11 state-of-the-art models.

关键词： encoder-decoder architecture image convolution edge extraction salient object detection skip connection U-Net

来源：评论

学校读者我要写书评

暂无评论

Video description: A comprehensive survey of deep learning approaches

引用

ARTIFICIAL INTELLIGENCE REVIEW 2023年第11期56卷 13293-13372页

作者： Rafiq, Ghazala Rafiq, Muhammad Choi, Gyu Sang Yeungnam Univ Dept Informat & Commun Engn Gyongsan 38541 South Korea Keimyung Univ Dept Game & Mobile Engn 1095 Dalgubeol Daero Daegu 42601 South Korea

Video description refers to understanding visual content and transforming that acquired understanding into automatic textual narration. It bridges the key AI fields of computer vision and natural language processing in conjunction with real-time and practical applications. Deep learning-based approaches employed for video description have demonstrated enhanced results compared to conventional approaches. The current literature lacks a thorough interpretation of the recently developed and employed sequence to sequence techniques for video description. This paper fills that gap by focusing mainly on deep learning-enabled approaches to automatic caption generation. Sequence to sequence models follow an encoder-decoder architecture employing a specific composition of CNN, RNN, or the variants LSTM or GRU as an encoder and decoder block. This standard-architecture can be fused with an attention mechanism to focus on a specific distinctiveness, achieving high quality results. Reinforcement learning employed within the encoder-decoder structure can progressively deliver state-of-the-art captions by following exploration and exploitation strategies. The transformer mechanism is a modern and efficient transductive architecture for robust output. Free from recurrence, and solely based on self-attention, it allows parallelization along with training on a massive amount of data. It can fully utilize the available GPUs for most NLP tasks. Recently, with the emergence of several versions of transformers, long term dependency handling is not an issue anymore for researchers engaged in video processing for summarization and description, or for autonomous-vehicle, surveillance, and instructional purposes. They can get auspicious directions from this research.

关键词： Deep learning encoder-decoder architecture Text description Video captioning techniques Video description approaches Video captioning Vision to text

来源：评论

学校读者我要写书评

暂无评论

Transfer learning approach based on satellite image time series for the crop classification problem

引用

JOURNAL OF BIG DATA 2023年第1期10卷 54页

作者： Antonijevic, Ognjen Jelic, Slobodan Bajat, Branislav Kilibarda, Milan Univ Belgrade Fac Civil Engn Dept Geodesy & Geoinformat Belgrade Serbia

This paper presents a transfer learning approach to the crop classification problem based on time series of images from the Sentinel-2 dataset labeled for two regions: Brittany (France) and Vojvodina (Serbia). During preprocessing, cloudy images are removed from the input data, the time series are interpolated over the time dimension, and additional remote sensing indices are calculated. We chose Transformerencoder as the base model for knowledge transfer from source to target domain with French and Serbian data, respectively. Even more, the accuracy of the base model with the preprocessing step is improved by 2% when trained and evaluated on the French dataset. The transfer learning approach with fine-tuning of the pre-trained weights on the French dataset outperformed all other methods in terms of overall accuracy 0.94 and mean class recall 0.907 on the Serbian dataset. Our partially fine-tuned model improved recall of crop types that were poorly classified by the base model. In the case of sugar beet, class recall is improved by 85.71%.

关键词： Transfer learning Remote sensing encoder-decoder architecture Domain adaptation Crop classification Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

A comparative study of LSTM-ED architectures in forecasting day-ahead solar photovoltaic energy using Weather Data

引用

COMPUTING 2024年第5期106卷 1611-1632页

作者： Ekinci, Ekin Sakarya Univ Appl Sci Fac Technol Comp Engn Dept Sakarya Turkiye

Solar photovoltaic (PV) energy, with its clean, local, and renewable features, is an effective complement to traditional energy sources today. However, the photovoltaic power system is highly weather-dependent and therefore has unstable and intermittent characteristics. Despite the negative impact of these features on solar sources, the increase in worldwide installed PV capacity has made solar energy prediction an important research topic. This study compares three encoder-decoder (ED) networks for day-ahead solar PV energy prediction: Long Short-Term Memory ED (LSTM-ED), Convolutional LSTM ED (Conv-LSTM-ED), and Convolutional Neural Network and LSTM ED (CNN-LSTM-ED). The models are tested using 1741-day-long datasets from 26 PV panels in Istanbul, Turkey, considering both power and energy output of the panels and meteorological features. The results show that the Conv-LSTM-ED with 50 iterations is the most successful model, achieving an average prediction score of up to 0.88 over R-square (R2). Evaluation of the iteration counts' effect reveals that the Conv-LSTM-ED with 50 iterations also yields the lowest Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE) values, confirming its success. In addition, the fitness and effectiveness of the models are evaluated, with the Conv-LSTM-ED achieving the lowest Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) values for each iteration. The findings of this work can help researchers build the best data-driven methods for forecasting PV solar energy based on PV features and meteorological features.

关键词： Solar photovoltaic energy Foecasting Time-series encoder-decoder architecture

来源：评论

学校读者我要写书评

暂无评论

GPCNet: global-context pyramidal and class-balanced network for high-resolution SAR remote sensing image classification

引用

JOURNAL OF APPLIED REMOTE SENSING 2022年第3期16卷

作者： Ni, Kang Yuan, Chunyang Nanjing Univ Posts & Telecommun Sch Comp Sci Nanjing Peoples R China

The description of context information affected by speckle and class imbalance under labeled data makes the pixelwise classification for high-resolution (HR) synthetic aperture radar (SAR) image a challenging task. To address these issues, we propose a global-context pyramidal and class-balanced network (GPCNet) for HR SAR image classification. The proposed structure follows an encoder-decoder architecture. In the encoder module, the multiscale convolutional and global-local cross-channel attention (GCA) blocks are employed to capture the global-context and distinguishable deep feature statistics, while reducing the impacts of the random fluctuation in the homogeneous region. The channel information of different scale convolutional layers is efficiently learned by local cross-channel interaction in the GCA block. Besides, a sampled class-balanced loss, associating with the effective number, is utilized for alleviating the class imbalance of HR SAR images. The experiments carried out on a TerraSAR-X image classification dataset demonstrate GPCNet is able to yield superior performance when compared with other related networks. (C) 2022 Society of Photo-Optical Instrumentation Engineers (SPIE)

关键词： synthetic aperture radar pixelwise classification encoder-decoder architecture context information

来源：评论

学校读者我要写书评

暂无评论

A comprehensive survey on image captioning: from handcrafted to deep learning-based techniques, a taxonomy and open research issues

引用

ARTIFICIAL INTELLIGENCE REVIEW 2023年第11期56卷 13619-13661页

作者： Sharma, Himanshu Padha, Devanand Cent Univ Jammu Dept Comp Sci & Informat Technol Jammu & Kashmir Jammu 181124 India

Image captioning is a pretty modern area of the convergence of computer vision and natural language processing and is widely used in a range of applications such as multi-modal search, robotics, security, remote sensing, medical, and visual aid. The image captioning techniques have witnessed a paradigm shift from classical machine-learning-based approaches to the most contemporary deep learning-based techniques. We present an in-depth investigation of image captioning methodologies in this survey using our proposed taxonomy. Furthermore, the study investigates several eras of image captioning advancements, including template-based, retrieval-based, and encoder-decoder-based models. We also explore captioning in languages other than English. A thorough investigation of benchmark image captioning datasets and assessment measures is also discussed. The effectiveness of real-time image captioning is a severe barrier that prevents its use in sensitive applications such as visual aid, security, and medicine. Another observation from our research is the scarcity of personalized domain datasets that limits its adoption into more advanced issues. Despite influential contributions from several academics, further efforts are required to construct substantially robust and reliable image captioning models.

关键词： Attention-based image captioning encoder-decoder architecture Image captioning Multimodal embedding

来源：评论

学校读者我要写书评

暂无评论

M²: Mixed Models With Preferences, Popularities and Transitions for Next-Basket Recommendation

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2023年第4期35卷 4033-4046页

作者： Peng, Bo Ren, Zhiyun Parthasarathy, Srinivasan Ning, Xia Ohio State Univ Dept Comp Sci & Engn Columbus OH 43210 USA Ohio State Univ Dept Biomed Informat Columbus OH 43210 USA Ohio State Univ Dept Biomed Informat Dept Comp Sci & Engn Columbus OH 43210 USA Ohio State Univ Translat Data Analyt Inst Columbus OH 43210 USA

Next-basket recommendation considers the problem of recommending a set of items into the next basket that users will purchase as a whole. In this paper, we develop a novel mixed model with preferences, popularities and transitions (M-2 ) for the next-basket recommendation. This method models three important factors in next-basket generation process: 1) users' general preferences, 2) items' global popularities and 3) transition patterns among items. Unlike existing recurrent neural network-based approaches, M-2 does not use the complicated networks to model the transitions among items, or generate embeddings for users. Instead, it has a simple encoder-decoder based approach (ed-Trans ) to better model the transition patterns among items. We compared M-2 with different combinations of the factors with 5 state-of-the-art next-basket recommendation methods on 4 public benchmark datasets in recommending the first, second and third next basket. Our experimental results demonstrate that M-2 significantly outperforms the state-of-the-art methods on all the datasets in all the tasks, with an improvement of up to 22.1%. In addition, our ablation study demonstrates that the ed-Trans is more effective than recurrent neural networks in terms of the recommendation performance. We also have a thorough discussion on various experimental protocols and evaluation metrics for next-basket recommendation evaluation.

关键词： Recurrent neural networks Task analysis Benchmark testing Adaptation models Decoding Protocols Markov processes Recommender systems next-basket recommendation encoder-decoder architecture mixed models

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：