检索结果-内蒙古大学图书馆

Spatial-temporal learning structure for short-term load forecasting

IET GENERATION TRANSMISSION & DISTRIBUTION 2023年第2期17卷 427-437页

作者： Ganjouri, Mahtab Moattari, Mazda Forouzantabar, Ahmad Azadi, Mohammad Islamic Azad Univ Dept Elect Engn Marvdasht Branch Marvdasht Iran Islamic Azad Univ Mechatron & Artificial Intelligence Res Ctr Dept Engn Marvdasht Branch Marvdasht Iran Islamic Azad Univ Dept Engn Marvdasht Branch Marvdasht Iran Islamic Azad Univ Dept Elect Engn Marvdasht Branch Marvdasht *** Iran

In the power system operational/planning studies, it is a crucial task to provide the load consumption information in the look-ahead times. The huge variation of the power system infrastructure in recent years has led to significant changes in the consumers' consumption pattern. Therefore, short-term load forecasting (STLF) is transformed to a more complicated problem in recent years. To address this issue, this paper proposes a graph-based deep neural network to capture full spatial-temporal features and be able to oversee high volatility time series including load sequence. The proposed spatial deep learning structure benefits from learning the spatial feature using Gabor filter-oriented layers and full understanding the temporal behaviour based on bidirectional networks. The designed learning-based system is developed as a graph-based learning system to improve the accuracy considering the meteorological information behaviour. To verify the performance of the designed deep graph network, the actual load data of Shiraz, Iran, is used. Besides, to demonstrate the superiority and effectiveness of the proposed, the designed deep graph network is compared with three well-known shallow and deep networks in different cases including yearly performance, seasonal performance, and sensitivity analysis on the meteorological data.

关键词： bidirectional gated recurrent unit deep graph network encoder-decoder Gabor convolutional neural network meteorological data short-term load forecasting

来源：评论

学校读者我要写书评

暂无评论

A novel decoder based on Bayesian rules for task-driven object segmentation

引用

IET IMAGE PROCESSING 2023年第3期17卷 832-848页

作者： Cai, Yuxiang Yu, Yuanlong Jiang, Weijie Chen, Rong Zheng, Weitao Wu, Xi Su, Renjie Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn Shanghai Peoples R China State Grid Fujian Infotmat & Telecommun Co Technol Dept Fuzhou Peoples R China Fuzhou Univ Coll Comp & Data Sci Fuzhou 350108 Peoples R China

As a challenging problem in computer vision, salient object segmentation has attracted increasing attention in recent years. Though a lot of works based on encoder-decoder have been made, these methods can only recognize and segment one class of objects, but cannot segment the other classes of objects in the same image. To address this issue, this paper proposes a novel decoder based on Bayesian rules to perform task-driven object segmentation, in which a control signal is added to the decoder to determine which class of objects need to be segmented. What's more, a Bayesian rule is established in the decoder, in which the control signal is set as the prior, and the latent features learned in encoder is transferred to the corresponding layer of decoder as observation, thus the posterior probability of each object with respect to the specific-class can be calculated, and the objects belonging to this class can be segmented. This proposed method is evaluated for task-driven salient object segmentation on several benchmark datasets, including MS COCO, DUT-OMRON, ECSSD etc. Experimental results show that the approach tends to segment accurate, detailed, and complete objects, and improves the performance compared with the previous state-of-the-art.

关键词： image coding image segmentation feature extraction encoder-decoder Machine learning (artificial intelligence) object detection Image and video coding computer vision control signal Other topics in statistics task-driven salient object segmentation complete objects Bayesian rule Image recognition learning (artificial intelligence) Bayes methods Computer vision and image processing techniques

来源：评论

学校读者我要写书评

暂无评论

DRN-VideoSR: a deep recursive network for video super-resolution based on a deformable convolution shared-assignment network

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第9期82卷 14019-14035页

作者： Mu, Shaoshuo Zhang, Yanhua Jiang, Yanbing Commun Univ Zhejiang Hangzhou Peoples R China

Video super-resolution(videoSR) usually involves several steps: motion estimation, motion compensation, fusion, and upsampling. Here, we propose a novel architecture for video SR. First, in place of motion estimation and compensation, this architecture is based on a specially designed deformable convolution shared-assignment network. The model does not require warp operation and uses a three-layer pyramid deformable convolution network. Second, inspired by the idea of back-projection and encoder-decoder structure, we propose a deep recursive fusion network that fuses multi-frame information for the target frame. The fusion network adopts a decoder-encoder structure with shared weights to construct the back-projection network, and concatenates the output of each back-projection layer. This design not only reduces the network requirements, but also deepens the network structure so that it can extract deeper image features and achieve fusion. Extensive evaluations and comparisons with previous methods validate the strengths of this approach and demonstrate that the proposed framework is able to significantly outperform the current state of the art.

关键词： Video super-resolution Deformable convolution Pyramid encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Neural machine translation for Indian language pair using hybrid attention mechanism

引用

INNOVATIONS IN SYSTEMS AND SOFTWARE ENGINEERING 2024年第2期20卷 175-183页

作者： Nath, Basab Sarkar, Sunita Das, Surajeet Mukhopadhyay, Somnath Assam Univ Comp Sci & Engn Silchar India

Machine translation is an effective way of achieving suitable translations for a given language pair without human intervention. Machine translation can be a very tedious task when the resources for the concerned language pair are low, and the English-Assamese language pair is one such. Neural machine translation is among the different machine translation techniques that use artificial neural networks to learn the nonlinear relationship between bilingual sentence pairs. In this paper, a neural machine translation model is implemented, which uses our proposed hybrid attention mechanism. This hybrid attention mechanism consists of additive and multiplicative attention mechanisms. The proposed attention mechanism is not only capable of selecting an optimal attention mechanism, but also gives the average loss value per epoch to be minimal. The model with our proposed hybrid attention mechanism outperforms the other two models with additive and multiplicative attention by achieving a BLEU score of 27.20 on English-Assamese and a BLEU score of 25.88 on the Assamese-English language pair.

关键词： Neural machine translation encoder-decoder Attention mechanism Gated recurrent unit Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

PERSONALIZING LARGE SEQUENCE-TO-SEQUENCE SPEECH FOUNDATION MODELS WITH SPEAKER REPRESENTATIONS

PERSONALIZING LARGE SEQUENCE-TO-SEQUENCE SPEECH FOUNDATION M...

引用

2024 Spoken Language Technology Workshop

作者： Wagner, Dominik Baumann, Ilja Ranzenberger, Thomas Riedhammer, Korbinian Bocklet, Tobias TH Nurnberg Georg Simon Ohm Nurnberg Germany

ISBN: (纸本)9798350392265;9798350392258

We present a method to personalize large transformer-based encoder-decoder speech foundation models without the need for changes in the underlying model structure or training from scratch. This is achieved by projecting speaker-specific information into the latent space of the transformer decoder via a small neural network and learning to process the speaker information along with domain-specific information via parameter-efficient finetuning. We use this method to improve the automatic speech recognition results of spoken academic German and English. Our approach yields average relative word error rate (WER) improvements of approximately 29% on German academic speech and 25% on English academic speech. It also translates well to conversational speech, achieving relative WER improvements of up to 36%, and demonstrates modest gains of up to 5% on read speech. Moreover, we observe that incorporating utterances from the recent past as personalization context yields the most significant overall improvements and that changes in voice characteristics resulting from prolonged speaking have a minimal effect on the personalization quality of academic lectures.

关键词： automatic speech recognition speaker adaptation personalization adalora encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

MGB-Unet: An Improved Multiscale Unet with Bottleneck Transformer for Myositis Segmentation from Ultrasound Images

引用

JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2025年第1期38卷 217-228页

作者： Hussein, Allaa Youssef, Sherin Ahmed, Magdy A. Ghatwary, Noha Pharos Univ Comp Engn Pharos Egypt Arab Acad Sci & Technol Comp Engn Alexandria Egypt Fac Engn Comp Engn Alexandria Egypt

Myositis is the inflammation of the muscles that can arise from various sources with diverse symptoms and require different treatments. For treatment to achieve optimal results, it is essential to obtain an accurate diagnosis promptly. This paper presents a new supervised segmentation architecture that can efficiently perform precise segmentation and classification of myositis from ultrasound images with few computational resources. The architecture of our model includes a unique encoder-decoder structure that integrates the Bottleneck Transformer (BOT) with a newly developed Residual block named Multi-Conv Ghost switchable bottleneck Residual Block (MCG_RB). This block effectively captures and analyzes ultrasound image input inside the encoder segment at several resolutions. Moreover, the BOT module is a transformer-style attention module designed to bridge the feature gap between the encoding and decoding stages. Furthermore, multi-level features are retrieved using the MCG-RB module, which combines multi-convolution with ghost switchable residual connections of convolutions for both the encoding and decoding stages. The suggested method attains state-of-the-art performance on a benchmark set of myositis ultrasound images across all parameters, including accuracy, precision, recall, dice coefficient, and Jaccard index. Despite its limited training data, the suggested approach demonstrates remarkable generalizability by yielding exceptional results. The proposed model showed a substantial enhancement in accuracy when compared to segmentation state-of-the-art methods such as Unet++, DeepLabV3, and the Duck-Net. The dice coefficient and Jaccard index obtained improvements of up to 3%, 6%, and 7%, respectively, surpassing the other methods.

关键词： Myositis Segmentation Unet Classification encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Multi-step ahead wind power forecasting based on dual-attention mechanism

引用

ENERGY REPORTS 2023年 9卷 239-251页

作者： Aslam, Muhammad Kim, Jun-Sung Jung, Jaesung Sejong Univ Dept Artificial Intelligence Seoul 05006 South Korea Korea Elect Power Res Inst Digital Solut Lab Daejeon 34056 South Korea Ajou Univ Dept Elect & Comp Engn Suwon 16499 Gyeonggi Do South Korea

Accurate forecasting is essential for the economic benefits and efficient operation of intermittent wind power systems. Multi-step ahead wind power forecasting provides multiple benefits in the planning and operation of the power systems. This study proposes a deep learning model based on a dual -attention mechanism for multi-step ahead wind power forecasting. Both the attention mechanisms are applied over the encoder-decoder based sequence-to-sequence model consisting of long short-term memory (LSTM) blocks. The Bayesian optimization algorithm is applied to the proposed model to obtain the optimal combination of hyper-parameters. To evaluate its effectiveness, the proposed model has been compared with the persistence model, and state-of-the-art models such as simple LSTM, LSTM-attention, ensemble model, and neural basis expansion analysis for time series (N-BEATS) model. Furthermore, the performance of the attention mechanism with respect to impactful input features, such as wind speed and air pressure, was analyzed. The forecasting skill score of the proposed model was the highest among all other models in comparison, which indicates the effectiveness of the proposed model. Similarly, the proposed model outperformed the traditional methods in terms of other evaluating criteria, including mean absolute error (MAE), and root mean square error (RMSE) among others, hence, proving its efficacy. The average RMSE score of the proposed model for multi horizon forecasting was 0.04995, whereas that of N-BEATS was 0.0876, ensemble method was 0.1132 and LSTM-attention was around 0.101375. Similarly, the average forecasting skill score of proposed method was 0.6625, whereas that of N-BEATS was 0.3975 and LSTM-attention achieved 0.3775 skill score. (c) 2022 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).

关键词： Attention mechanism Bayesian optimization encoder-decoder LSTM Renewable energy Wind power forecasting

来源：评论

学校读者我要写书评

暂无评论

A multi-scale inputs and labels model for background subtraction

引用

SIGNAL IMAGE AND VIDEO PROCESSING 2023年第8期17卷 4133-4141页

作者： Yang, Yizhong Li, Dajin Li, Xiang Zhang, Zhang Xie, Guangjun Hefei Univ Technol Sch Microelect Hefei Peoples R China

Background subtraction is a challenging and fundamental task in computer vision, which aims at segmenting moving objects from the background. Recently, the attention mechanism has become a hot topic in the neural network. The algorithms based on encoder-decoder and multi-scale type network perform impressive results in the domain of background subtraction. In this paper, we propose a multi-scale inputs and labels (MSIL) model which is based on the encoder-decoder type network and the channel attention. The multi-scale fusion encoding (MSFE) module aims to utilize multi-scale inputs effectively, which can fuse the high-level and low-level features details. The channel attention (CA) module is introduced to connect the encoder and decoder to model channel-wise attentions. The multi-label supervision decoding (MLSD) module helps to learn richer hierarchical features and achieves better performance by the new multi-label supervision. The proposed model is also evaluated on the CDnet-2014 dataset and the LASIESTA dataset, which demonstrate the effectiveness and superiority of the proposed model by an average F-Measure of 0.9851 and 0.9633, respectively. In addition, scene independent evaluation experiments on the CDnet-2014 dataset demonstrate the effectiveness of the model on unseen videos.

关键词： Background subtraction Neural network Multi-scale inputs and labels encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Designing an adaptive cost function for dynamic human pose predictions

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第18期83卷 53201-53219页

作者： Yadav, Gaurav Kumar Puig, Domenec Nandi, G. C. Indian Inst Informat Technol Allahabad Dept Informat Technol Prayagraj Uttar Pradesh India Univ Rovira I Virgili Dept Comp Sci & Math Secur Tarragona Spain

In the modern-day scenario, machines and humans are expected to work together and collaborate in several social and manufacturing environments. The machines should predict humans' next move for effective collaborations by observing their present move. Human motion modelling and prediction are fundamental and challenging problems involving computer vision and graphics. To help solve some of the challenges, in the present investigation, we propose an innovative idea of developing a new cost function as the objective function based on adaptive sampling, which is subsequently used with an 'Adam' optimizer for training and validating a specially configured Deep Learning architecture. Our proposed development produced significantly improved results regarding future pose estimation/predictions. The adaptiveness of the proposed cost function is based on a bell-shaped locally weighted function. It has been observed that the area covered by the cost function plays a vital role during training, and the bell-shaped function's width helps decide the region of importance for the training samples. The proposed cost function has been used for training a gated recurrent unit (GRU) based encoder-decoder architecture. The encoder takes the observed input sequences, extracts the input sequence's significant variability, and passes it to the decoder. The decoder takes it as input, trains using the adaptive sampling-based method, and predicts future poses. We have experimented with this function in various sizes and shapes and compared the results obtained with some state-of-the-art research results. As elaborated in this paper, we obtained much-improved results in almost all the cases.

关键词： Deep sequential networks encoder-decoder Human 3.6M

来源：评论

学校读者我要写书评

暂无评论

End-to-End Handwritten Paragraph Text Recognition Using a Vertical Attention Network

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2023年第1期45卷 508-524页

作者： Coquenet, Denis Chatelain, Clement Paquet, Thierry LITIS EA 4108 F-76800 Saint Etienne Du Rouvray France Univ Rouen Normandy F-76000 Rouen France Normandy Univ F-14032 Caen France INSA Rouen Normandy F-76800 Saint Etienne Du Rouvray France

Unconstrained handwritten text recognition remains challenging for computer vision systems. Paragraph text recognition is traditionally achieved by two models: the first one for line segmentation and the second one for text line recognition. We propose a unified end-to-end model using hybrid attention to tackle this task. This model is designed to iteratively process a paragraph image line by line. It can be split into three modules. An encoder generates feature maps from the whole paragraph image. Then, an attention module recurrently generates a vertical weighted mask enabling to focus on the current text line features. This way, it performs a kind of implicit line segmentation. For each text line features, a decoder module recognizes the character sequence associated, leading to the recognition of a whole paragraph. We achieve state-of-the-art character error rate at paragraph level on three popular datasets: 1.91% for RIMES, 4.45% for IAM and 3.59% for READ 2016. Our code and trained model weights are available at https://***/FactoDeepLearning/VerticalAttentionOCR.

关键词： Seq2Seq model hybrid attention segmentation-free paragraph handwriting recognition fully convolutional network encoder-decoder optical character recognition

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：