检索结果-内蒙古大学图书馆

13th International Conference on Intelligent Computing (ICIC)

作者： Li, ChenXing Du, YaJun Wang, SiDa Xihua Univ Sch Comp & Software Engn Chengdu 610039 Sichuan Peoples R China

ISBN: (纸本)9783319633152;9783319633145

Nowadays, people are increasingly inclined to use social tools to express their intentions explicitly and implicitly. Most of the work is dedicated to solving the explicit intention detection, ignoring the implicit intention detection, as the former is relatively easy to solve with the classification method. In this work, we use the Attention-Based encoder-decoder model which is specified for the sequence-to-sequence task for user implicit intention detection. Our key idea is to leverage the model to "translate" the implicit intention into the corresponding explicit intent by using the parallel corpora built on the social data. Specifically, our model has domain adaptability since the way people express implicit intentions for different domain is variable, while the way to express explicit intentions is mostly in the same form, such as "I want to do sth". In order to demonstrate the effectiveness of our method, we conduct experiments in four domains. The results show that our method offers a powerful "translation" for the implicit intentions and consequently identifies them.

关键词： Implicit intent detection Recurrent neural networks Attention encoder-decoder model

来源：评论

学校读者我要写书评

暂无评论

An encoder-decoder model based on deep learning for state of health estimation of lithium-ion battery

引用

JOURNAL OF ENERGY STORAGE 2022年 46卷

作者： Gong, Qingrui Wang, Ping Cheng, Ze Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China

Accurate estimation of state of health (SOH) of lithium-ion batteries is an important guarantee for the safe and stable operation of these batteries, which is a key technology in battery management system (BMS). The charging curves of lithium-ion batteries with different aging degrees are also different. Based on this fact, this paper proposes an encoder-decoder model based on deep learning to establish the mapping relationship between battery charging curves and the value of SOH. The model consists of encoder and decoder. The encoder is a hybrid neural network composed of two-dimensional convolution module, ultra-lightweight subspace attention mechanism (ULSAM) module and simple recurrent unit (SRU) module, which can effectively encode the sampling data of the charging curves and generate the encoding sequence. The decoder is mainly composed of back propagation (BP) neural network, which is responsible for decoding the encoding sequence and output an estimate of the SOH. For long encoding sequence, a decoder with attention mechanism is proposed to improve the estimation accuracy of the model. Experimental results show that the proposed model has good adaptability to different types of batteries, can adapt to various sampling modes of charging curves, and has high estimation accuracy.

关键词： Lithium-ion batteries State of health Charging curves encoder-decoder model Deep learning Simple recurrent unit

来源：评论

学校读者我要写书评

暂无评论

A novel encoder-decoder model based on read-first LSTM for air pollutant prediction

引用

SCIENCE OF THE TOTAL ENVIRONMENT 2021年 765卷 144507-144507页

作者： Zhang, Bo Zou, Guojian Qin, Dongming Lu, Yunjie Jin, Yupeng Wang, Hui Shanghai Normal Univ Coll Informat Mech & Elect Engn Shanghai 200234 Peoples R China Tongji Univ Minist Educ Key Lab Rd & Traff Engn Shanghai 201804 Peoples R China Tongji Univ Coll Elect & Informat Engn Shanghai 201804 Peoples R China 3Clear Beijing 100029 Peoples R China Univ Ulster Sch Comp Coleraine Londonderry North Ireland

Accurate air pollutant prediction allows effective environment management to reduce the impact of pollution and prevent pollution incidents. Existing studies of air pollutant prediction are mostly interdisciplinary involving environmental science and computer science where the problem is formulated as time series prediction. A prevalent recent approach to time series prediction is the encoder-decoder model, which is based on recurrent neural networks (RNN) such as long short-term memory (LSTM), and great potential has been demonstrated. An LSTM network relies on various gate units, but in most existing studies the correlation between gate units is ignored. This correlation is important for establishing the relationship of the random variables in a time series as the stronger is this correlation, the stronger is the relationship between the random variables. In this paper we propose an improved LSTM, named Read-first LSTM or RLSTM for short, which is a more powerful temporal feature extractor than RNN, LSTM and Gated Recurrent Unit (GRU). RLSTM has some useful properties: (1) enables better store and remember capabilities in longer time series and (2) overcomes the problem of dependency between gate units. Since RLSTM is good at long term feature extraction, it is expected to perform well in time series prediction. Therefore, we use RLSTM as the encoder and LSTM as the decoder to build an encoder-decoder model (EDSmodel) for pollutant prediction in this paper. Our experimental results show, for 1 to 24 h prediction, the proposed prediction model performed well with a root mean square error of 30.218. The effectiveness and superiority of RLSTM and the prediction model have been demonstrated. (C) 2020 Elsevier B.V. All rights reserved.

关键词： encoder-decoder model Recurrent neural networks Long short term memory Air pollutant prediction Deep learning Numerical analysis

来源：评论

学校读者我要写书评

暂无评论

Grade prediction of zinc tailings using an encoder-decoder model in froth flotation

引用

MINERALS ENGINEERING 2021年 172卷 107173-107173页

作者： Zhang, Hu Tang, Zhaohui Xie, Yongfang Luo, Jin Chen, Qing Gui, Weihua Cent South Univ Sch Automat Changsha 410083 Peoples R China Hunan Univ Technol Sch Comp Sci Zhuzhou 412007 Peoples R China

Accurate grade prediction is conducive to proper flotation operation or control. Different from grade monitoring, grade prediction needs to obtain the target grade in advance. However, there is usually a time delay between the flotation cell and the predicted grade in froth flotation. This time delay makes it difficult to match the features of the observed flotation cell with the predicted grade. To solve this problem, this article studies the method of zinc tailings grade prediction using encoder-decoder models. The proposed model considers the feature time series of the first rougher and the previously measured tailings grades. First, according to the sample ratio between froth video and X-ray fluorescence (XRF) analyser, the feature time series of the first rougher can be automatically extracted by finding the nearest available feature vectors. Next, the feature time series of the first rougher is fed into the encoder to generate a context vector, and then the context vector and previously measured grades are sent into the decoder to predict the current tailings grade. The proposed model effectively captures the dynamic consistency between the feature time series and previously measured grades. The effectiveness of the proposed model in the froth flotation has been verified by experiments. Compared with the traditional recurrent neural network (RNN)-based models, the root mean squared error (RMSE) and mean absolute percentage error (MAPE) of the proposed model decrease by about 17.8% and 1.9%. respectively, and the R-squared (R2) score of the proposed model increases by about 13.8%.

关键词： Grade prediction Machine vision Froth video Time series Recurrent neural network encoder-decoder model

来源：评论

学校读者我要写书评

暂无评论

A deep learning based encoder-decoder model for speed planning of autonomous electric truck platoons

引用

HELIYON 2024年第11期10卷 e31836页

作者： Karthik, S. Rohith, G. Devika, K. B. Subramanian, Shankar C. Indian Inst Technol Madras Dept Mech Engn Chennai 600036 India Orbital Astronaut Thames CourtGoring Reading RG8 9AQ Oxon England Univ Exeter Fac Environm Sci & Econ Exeter EX4 4QF England Indian Inst Technol Madras Dept Engn Design Chennai 600036 India

Electric truck platooning offers a promising solution to extend the range of electric vehicles during long -haul operations. However, optimizing the platoon speed to ensure efficient energy utilization remains a critical challenge. The existing research on implementing data -driven solutions for truck platooning remains limited and implementing first principles solution is still a challenge. However, recognizing the resemblance of truck platoon data to a time series serves as a compelling motivation to explore suitable analytical techniques to address the problem. This paper presents a novel deep learning approach using a sequence -to -sequence encoder -decoder model to obtain the speed profile to be followed by an autonomous electric truck platoon considering various constraints such as the available state of charge (SOC) in the batteries along with other vehicles and road conditions while ensuring that the platoon is string stable. To ensure that the framework is suitable for long -haul highway operation, the model has been trained using various known highway drive cycles. encoder -decoder models were trained and hyperparameter tuning was performed for the same. Finally, the most suitable model has been chosen for the application. For testing the entire framework, drive cycle/speed prediction corresponding to different desired SOC profiles has been presented. A case study showing the relevance of the proposed framework in predicting the drive cycle on various routes and its impact on taking critical policy decisions during the planning of electric truck platoons has also been presented. This study would help to efficiently plan the feasible routes for electric trucks considering multiple constraints such as battery capacity, expected discharge rate, charging infrastructure availability, route length/travel time, and other on -road operating conditions while also maintaining stability.

关键词： Deep learning Drive cycle Electric trucks encoder-decoder model Platoon State-of-charge

来源：评论

学校读者我要写书评

暂无评论

SEQUENCE TRAINING OF encoder-decoder model USING POLICY GRADIENT FOR END- TO-END SPEECH RECOGNITION

SEQUENCE TRAINING OF ENCODER-DECODER MODEL USING POLICY GRAD...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Shigeki Karita Atsunori Ogawa Marc Delcroix Tomohiro Nakatani NTT Communication Science Laboratories NTT Corporation Kyoto Japan

ISBN: (纸本)9781538646595

The standard evaluation metric of automatic speech recognition (ASR) is the word error rate (WER), which measures the dissimilarity between recognized word sequences and their ground truth. Many training algorithms designed to reduce sequence-level errors such as WER have been proposed for hidden Markov model (HMM)-based ASR, e.g., state-level minimum Bayes risk (sMBR). However, these approaches cannot be used directly for encoder-decoder model based end-to-end ASR, because the encoder-decoder model employs very different mechanisms from HMM-based approaches. In this paper, we propose a new method for optimizing the encoder-decoder model based on a sequence-level evaluation metric. Since the WER is not directly differentiable, we adopt a policy gradient objective function to train the encoder-decoder model, which enables us to minimize the expected WER of the model predictions. This training method employs the scoring of multiple hypotheses as in the decoding stage while usual cross entropy training uses only the ground truth. Therefore, we can expect it to improve the decoding results of the encoder-decoder model. We perform experiments using the Tedlium corpus to demonstrate the potential of our proposed method for improving the recognition performance of the encoder-decoder model.

关键词： end-to-end speech recognition encoder-decoder model policy gradient sequence training Tedlium Speech recognition Hidden Markov models aquifer storage and recovery ground truth Scoring Training

来源：评论

学校读者我要写书评

暂无评论

Multi-step prediction model enhanced by adaptive denoising and encoder-decoder for shield machine cutterhead torque in complex conditions

引用

TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY 2025年 158卷

作者： Xu, Deming Wang, Yuan Huang, Jingqi Xu, Shujun Zhou, Kun Univ Sci & Technol Beijing Sch Civil & Resources Engn Beijing Key Lab Urban Underground Space Engn Beijing 100083 Peoples R China Hohai Univ Coll Water Conservancy & Hydropower Engn Nanjing 210024 Peoples R China China Railway 14th Bur Grp Co Ltd Nanjing 210098 Jiangsu Peoples R China

Cutterhead torque reflects the obstruction extent of geological environment on the shield machine, and its prediction can assist operators to adjust control parameters to improve construction efficiency and avoid machine jamming. However, tunneling in complex geological or working conditions often results in high cutterhead torque fluctuations and noise, which seriously affects the accuracy of torque prediction. This study proposes a multi-step prediction model for cutterhead torque enhanced by adaptive denoising and encoder-decoder. In this model, a novel adaptive denoising method for cutterhead torque is employed to improve prediction accuracy under complex conditions. Moreover, by introducing encoder-decoder method, the processing capability for multi-time dimensional data and multi-step prediction performance of LSTM neural networks are further improved. The effectiveness of proposed model is verified through an application to the Heyan Road River Crossing project. The results of this study can assist operators in achieving precise adjustment of control parameters under complex conditions.

关键词： Shield machine Cutterhead torque Multi-step prediction Long short-term memory encoder-decoder model

来源：评论

学校读者我要写书评

暂无评论

85-GHz photonics W-band IM/DD PAM4 wireless transmission over 300 m based on nonlinear U-net symmetrical encoder-decoder equalizer

引用

OPTICS COMMUNICATIONS 2025年 577卷

作者： Zhang, Jie Zhou, Wen Bian, Chengzhen Ge, Jingtao Xu, Sicong Ma, Yuan Wang, Qihang Wang, Siqi Ou, Zhihang Hu, Sheng Fudan Univ Key Lab Informat Sci Electromagnet Waves MoE Shanghai 200433 Peoples R China

We propose a nonlinear U-Net equalizer based on a fully convolutional neural network for radio-over-fiber (ROF) communication systems. The U-Net encoder generates numerous feature channels through multi-layer downsampling, effectively extracting and transmitting deep temporal information. The symmetric decoder side uses corresponding upsampling steps to restore resolution, ensuring that the output has the same size as the input, thus generating equalization for each symbol. To mitigate the spatial information loss caused by downsampling, U-Net introduces skip connections, ensuring that the upsampled feature maps retain more shallow temporal information. The symmetric structure facilitates a more balanced transmission of information, achieving equilibrium between global and local information, as well as deep and shallow features. By using our proposed U-Net equalizer, we experimentally demonstrated single-channel 4G baud 85 GHz PAM4 signal transmission over a 300-m wireless link, and its bit error rate (BER) is below the 7% hard-decision forward error correction (HD-FEC) threshold of 3.8 x 10-3. Experimental results show that compared to Volterra and other neural networks, the UNet equalizer reduces the BER by 42%, reduces computational complexity by 57%, parameters by 13%, and training data size by 8%. To the best of our knowledge, this is the first time such a novel U-Net equalizer in ROF system has been proposed. Its high precision, low complexity, and reduced training data requirements make this equalizer highly promising for future millimeter-wave communication development and applications.

关键词： W -band U -net equalizer encoder-decoder model Photonics aided technology

来源：评论

学校读者我要写书评

暂无评论

A deep learning approach to impact localization and uncertainty assessment in CFRP composites using sparse PZTs: Integrating experiments and simulations

引用

THIN-WALLED STRUCTURES 2025年 212卷

作者： Yan, Huai Xie, Weihua Gao, Bo Yang, Fan Meng, Songhe Harbin Inst Technol Natl Key Lab Sci & Technol Adv Composites Special Harbin 150001 Peoples R China

The propagation of elastic waves in CFRP composites is dispersive and multimodal, making impact localization using wave signals challenging. An end-to-end deep learning model with an encoder-decoder architecture was developed for impact localization in CFRP composites, using sparse piezoelectric ceramic transducer (PZT) arrays and a data-driven approach to enable online impact sensing. The model used a segmented training strategy and transfer learning to capture shared features between experimental and simulated data. According to the piezoelectric equation, it links experimental piezoelectric signals with simulated stress responses. The results show that the feature encoder trained can extract their shared features effectively. Meanwhile, the model successfully applied the laws from simulation data to the localization of experimental impacts based on the fine-tuning strategy, alleviating the challenge of limited experimental data. The prediction results in the test set show that good generalization, and impact localization can be achieved in milliseconds during inference. The average error in localization is only 3.42 mm over a 100 mm x 100 mm monitoring area. Compared to the traditional transfer strategy, the three-stage training proposed shows better generalization by constraining the encoded features. In addition, the Monte-Carlo dropout strategy is used to assess prediction uncertainty, analyzing the effects of dropout rate and repeated predictions on confidence intervals. The study provides a prospective solution for large CFRP structures to achieve fast localization of impacts under sparse PZT arrays.

关键词： encoder-decoder model Impact localization Monte-Carlo dropout CFRP laminates

来源：评论

学校读者我要写书评

暂无评论

Pretrained Network with Vision Transformer for Enhanced Road Extraction from Satellite Imagery

引用

JOURNAL OF THE INDIAN SOCIETY OF REMOTE SENSING 2025年 1-19页

作者： Kumar, K. Madhan Velayudham, A. PET Engn Coll Dept Elect & Commun Engn Vallioor Tamilnadu India Jansons Inst Technol Dept Comp Sci & Engn Coimbatore Tamilnadu India

The extraction of road surfaces and centerlines from the satellite images is the most challenging task in the feature extraction field. In recent years, road extraction has been used for diverse applications such as rescue missions, urban planning, automated map updates and autonomous driving. The previous researches have road region misidentification during complex road conditions, inefficient segmentation of road regions and binary semantic segmentation issues. To address these issues, the novel model named as Pretrained Network with Vision Transformer (Conv-ViT) based encoder-decoder model is proposed that is responsible for predicting accurate road extraction. For road extraction, the satellite images are collected from different datasets and preprocessing is involved in this paper to reduce overfitting issues, eliminate artifacts and avoid distortions present in the images. The Conv-ViT model extracts contextual features to produce feature representation. The high and low-level features in the preprocessed images are extracted by using Inception-V3 and ResNet-50. The relationships between the nearby pixels and long-distance pixels are developed by leveraging the ViT transformer model. The encoder captures the generated feature representation and produces the road extraction output from the extracted feature representation. The Mutation Boosted Whale optimization Algorithm (MBWOA) approach is included in this paper that fine-tunes the parameters of the Conv-ViT model. The comparative analyses are performed with the help of performance evaluation measures and attained the highest accuracy rate of 98.7% from the proposed road extraction model.

关键词： Satellite image Road extraction Contextual features Vision transformer encoder-decoder model Whale optimization

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：