检索结果-内蒙古大学图书馆

Detecting energy consumption anomalies with dynamic adaptive encoder-decoder deep learning networks

RENEWABLE & SUSTAINABLE ENERGY REVIEWS 2025年 207卷

作者： Zhang, Limao Guo, Jing Lin, Penghui Tiong, Robert L. K. Huazhong Univ Sci & Technol Sch Civil & Hydraul Engn 1037 Luoyu Rd Wuhan 430074 Hubei Peoples R China Nanyang Technol Univ Sch Civil & Environm Engn 50 Nanyang Ave Singapore 639798 Singapore

Efficient management of building energy consumption is paramount for sustainability and cost-effectiveness, where anomalies in energy usage patterns can signify malfunctions, inefficiencies, or even potential hazards within the building systems. To address this problem, this study introduces an Asymmetric Hybrid encoderdecoder (AHED) anomaly detection architecture, designed to precisely forecast and identify point anomalies and collective anomalies within the domain of building energy usage. This architecture synthesizes both supervised and unsupervised learning approaches and utilizes an advanced decoder-encoder configuration for accurate prediction of energy consumption. Concurrently, the AHED framework applies sliding window techniques and cross-correlation analysis to convert multivariate temporal data into feature matrices, to detect anomalous patterns that manifest collectively within specified time intervals. The results demonstrate that the AHED model outperforms traditional anomaly detection techniques, achieving higher accuracy and improved generalization across diverse building environments, which affirms the efficacy and superiority of the asymmetric model in anomaly detection for building energy consumption. This study underscores the potential of dynamic adaptive deep learning networks in addressing the challenges of anomaly detection in building energy management, paving the way for more efficient and sustainable building operations.

关键词： encoder-decoder Deep learning Anomaly detection Building energy consumption

来源：评论

学校读者我要写书评

暂无评论

ACSF-ED: Adaptive Cross-Scale Fusion encoder-decoder for Spatio-Temporal Action Detection

引用

Computers, Materials & Continua 2025年第2期82卷 2389-2414页

作者： Wenju Wang Zehua Gu Bang Tang Sen Wang Jianfei Hao College of Publishing University of Shanghai for Science and TechnologyShanghai200093China Institute of Information Technology Shanghai Baosight Software Co.Ltd.Shanghai200940China

Current spatio-temporal action detection methods lack sufficient capabilities in extracting and comprehending spatio-temporal information. This paper introduces an end-to-end Adaptive Cross-Scale Fusion encoder-decoder (ACSF-ED) network to predict the action and locate the object efficiently. In the Adaptive Cross-Scale Fusion Spatio-Temporal encoder (ACSF ST-encoder), the Asymptotic Cross-scale Feature-fusion Module (ACCFM) is designed to address the issue of information degradation caused by the propagation of high-level semantic information, thereby extracting high-quality multi-scale features to provide superior features for subsequent spatio-temporal information modeling. Within the Shared-Head decoder structure, a shared classification and regression detection head is constructed. A multi-constraint loss function composed of one-to-one, one-to-many, and contrastive denoising losses is designed to address the problem of insufficient constraint force in predicting results with traditional methods. This loss function enhances the accuracy of model classification predictions and improves the proximity of regression position predictions to ground truth objects. The proposed method model is evaluated on the popular dataset UCF101-24 and JHMDB-21. Experimental results demonstrate that the proposed method achieves an accuracy of 81.52% on the Frame-mAP metric, surpassing current existing methods.

关键词： Spatio-temporal action detection encoder-decoder cross-scale fusion multi-constraint loss function

来源：评论

学校读者我要写书评

暂无评论

Day-Ahead Solar Power Forecasting Using LightGBM and Self-Attention Based encoder-decoder Networks

引用

IEEE TRANSACTIONS ON SUSTAINABLE ENERGY 2025年第2期16卷 866-879页

作者： Hokmabad, Hossein Nourollahi Husev, Oleksandr Belikov, Juri Tallinn Univ Technol Tal Tech Elect Power Engn & Mechatron EE-19086 Tallinn Harjuma Estonia Tallinn Univ Technol TalTech Software Sci EE-19086 Tallinn Harjuma Estonia

The burgeoning trend of integrating renewable energy harvesters into the grid introduces critical issues for its reliability and stability. These issues arise from the stochastic and intermittent nature of renewable energy sources. Data-driven forecasting tools are indispensable in mitigating these challenges with their rugged performance. However, tools relying solely on data-driven methods often underperform when an adequate amount of recorded data is unattainable. To bridge this gap, this paper presents a novel day-ahead hybrid forecasting framework for photovoltaic applications. This framework integrates a physics-based model with Machine Learning (ML) techniques, enhancing prediction reliability in environments with scarce data. Additionally, an innovative ML pipeline is introduced for data-abundant environments. The proposed ML tool comprises two branches: a set of regressors, each tailored for specific weather conditions, and a self-attention-based encoder-decoder network. By fusing the outputs from these branches through a meta-learner, the tool achieves predictions of higher quality, as evidenced by its superior performance over benchmark models in an investigated test dataset.

关键词： Data models Predictive models Forecasting Mathematical models Weather forecasting Photovoltaic cells Renewable energy sources Integrated circuit modeling Accuracy Solar irradiance Solar power forecasting photo voltaic systems physics-based modeling hybrid approach data scarce environments machine learning LightGBM encoder-decoder attention

来源：评论

学校读者我要写书评

暂无评论

Supervised Convolutional encoder-decoder With Gated Linear Units for Detecting Fetal R-Peaks

引用

IEEE ACCESS 2025年 13卷 4290-4303页

作者： Chen, Yao Wang, Jian Zhang, Jing Zhang, Junkun Qin, Zhentao Liu, Xinran Panzhihua Univ Sch Math & Comp Sci Panzhihua 617000 Peoples R China Sichuan Univ Coll Comp Sci Chengdu 610065 Peoples R China Fudan Univ Shanghai Canc Ctr Shanghai 200032 Peoples R China

Noninvasive fetal electrocardiography (ECG) is prevalently used for monitoring fetal heartbeats during pregnancy due to its affordability, ease of use, and constant monitoring capability. A crucial aspect of noninvasive fetal ECG is detecting the R-peak series from the abdominal electrode signal, which is a fundamental baseline for determining fetal heart rate. This paper explores the direct detection of R-peaks by assigning categorical labels to each member of the observed values in the ECG sequence and proposes a convolutional encoder-decoder network and training strategy for processing the sequence annotation task. Specifically, the encoder is a stacked convolutional layer equipped with a gating linear unit (GLU), and the decoder is a recurrent neural network. The GLU convolutional layer can effectively extract and aggregate the features to improve the generalization ability. To address the issue of unbalanced sequence labels, we adopt and fine-tune the focal loss function, promoting superior prediction and faster convergence. The experimental results suggest that the proposed method can achieve promising performance on two benchmark datasets. The versatility of our approach is validated through tests of different label encoding strategies, demonstrating its potential for other complex fetal ECG labeling tasks.

关键词： Fetal R-peak encoder-decoder GLU convolutional layer sequence tagging fetal QRS complexes locations Fetal R-peak encoder-decoder GLU convolutional layer sequence tagging fetal QRS complexes locations

来源：评论

学校读者我要写书评

暂无评论

Rwkv-vg: visual grounding with RWKV-driven encoder-decoder framework

引用

MULTIMEDIA SYSTEMS 2025年第2期31卷 1-12页

作者： Nian, Fudong Gu, Yanhong Wang, Wentao Liu, Aoyu Zhang, Dong Li, Fanding Hefei Univ Sch Adv Mfg Engn Hefei Peoples R China Hefei Univ Anhui Prov Engn Technol Res Ctr Intelligent Vehicl Hefei Peoples R China Unisound AI Technol Co Ltd Beijing Peoples R China Quectel Wireless Solut Co Ltd Shanghai Peoples R China Jilin Univ State Key Lab Automot Simulat & Control Changchun Peoples R China Jiangnan Univ Sch Intelligent Mfg Wuxi Peoples R China

Visual grounding is a fundamental task that bridges vision and language, aiming to accurately associate natural language queries with specific regions in an image. Existing approaches, predominantly based on Transformers or CNNs, struggle with balancing computational efficiency and fine-grained semantic alignment. In this paper, we propose RWKV-VG, the first visual grounding framework entirely built on the RWKV architecture. Leveraging RWKV's unique ability to combine RNN-like sequential modeling with Transformer-like attention, our model efficiently achieves both intra-modal and cross-modal reasoning. The framework consists of a RWKV-based visual encoder, a RWKV-based linguistic encoder, and a RWKV-based visual-linguistic decoder, complemented by a learnable [REG] token designed for box regression. Comprehensive evaluations on benchmark datasets, including ReferItGame and the RefCOCO series, demonstrate the superiority of RWKV-VG, achieving state-of-the-art performance with rapid convergence. Ablation studies further confirm the effectiveness of the RWKV modules and the [REG] token design. Our work establishes RWKV as a compelling alternative to conventional architectures for visual grounding tasks. To facilitate future research, the code and pre-trained models are released at https://***/nianfd/RWKV-VG.

关键词： Visual grounding RWKV encoder-decoder Cross-modal learning

来源：评论

学校读者我要写书评

暂无评论

Feature-enhanced encoder-decoder model for accurate lithium-ion battery state of health estimation

引用

JOURNAL OF ENERGY STORAGE 2025年 119卷

作者： Wu, Ju Wei, Zheng Wu, Mingwei Shen, Zhonghui He, Qiu Zhao, Yan Wuhan Univ Technol Int Sch Mat Sci & Engn Sch Mat Sci & Engn Wuhan 430070 Peoples R China Sichuan Univ Coll Mat Sci & Engn Chengdu 610065 Peoples R China Karlsruhe Inst Technol Inst Nanotechnol Hermann Von Helmholtz Pl 1 D-76344 Eggenstein Leopoldshafen Germany Wuhan Univ Inst Technol Sci Wuhan 430072 Peoples R China

Accurately estimating the state of health (SOH) of lithium-ion batteries is crucial for optimizing battery management systems, extending battery lifespan, and improving energy efficiency. This study proposes an encoderdecoder model based on feature enhancement to improve estimation accuracy by introducing prior knowledge into directly measured data. Unlike models that rely solely on voltage data, this approach integrates valuable prior information from incremental capacity analysis with the intrinsic characteristics of voltage data, presenting a novel approach for battery SOH estimation. Ablation experiments conducted on three publicly available datasets demonstrate that features enhancement can significantly reduce the estimation error, achieving a remarkably low Root Mean Square Error (RMSE) of 0.19 %, which surpasses traditional models, such as support vector regression (0.35 %) and k-nearest neighbors (1.89 %). The study underscores that this model not only improves SOH estimation accuracy but also validates the effectiveness of feature enhancement technique.

关键词： Lithium-ion batteries State of health estimation Feature enhancement encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Dynamic modeling of post-combustion carbon capture process based on multi-gate mixture-of-experts incorporating dual-stage attention-based encoder-decoder network

引用

APPLIED THERMAL ENGINEERING 2025年 258卷

作者： Zheng, Cheng Sha, Peng Mo, Zhengyang Tang, Zihan Wang, Meihong Wu, Xiao Southeast Univ Natl Engn Res Ctr Power Generat Control & Safety Sch Energy & Environm Nanjing 210096 Peoples R China Univ Sheffield Dept Chem & Biol Engn Sheffield S1 3JD England

Solvent-based post-combustion carbon capture (PCC) technology is a promising, near-term solution for decarbonizing power generation and industrial facilities. Model-based process simulation is crucial for the optimal design and operation of the PCC process. Recently, data-driven models have gained attention due to their adaptability, efficient computation and high accuracy. However, the nonlinearity, strong couplings and multitime scale features of the PCC process pose significant challenges for model identification. To this end, this paper proposes a multi-gate mixture-of-experts incorporating dual-stage attention-based encoder-decoder (MMoE-DAED) network for dynamic modeling of the PCC process under wide operating conditions. An encoder-decoder composed of long short-term memory (LSTM) network is employed to extract features from the time-dependent input data and learn the complex dynamic interactions caused by the inertial and delay properties of the process. Dual-stage attention mechanism is incorporated into the encoder and decoder respectively to select the most relevant input features and their correlations within the time series data. To enhance multioutput prediction accuracy, multi-gate mixture-of-experts (MMoE) framework that considers correlations of multitask learning is implemented. Simulation results using operating data from a PCC experimental setup indicate that the proposed modeling approach accurately predicts the steady-state values and dynamic trends of the CO2 capture rate and stripper bottom temperature over a wide operating range. The RMSE, MAPE and R2 indices for the CO2 capture rate are 2.1592, 0.0295, 0.9641, respectively, and for the stripper bottom temperature are 0.1491, 0.0003, 0.9833, respectively. Validations on a PCC simulator further verify the accuracy and efficiency of the MMoE-DAED model, which enables an 80.87% reduction in computation time compared to the simulator. This paper points to a new direction for the data-driven dyna

关键词： Post-combustion carbon capture Dynamic modeling Multi-output prediction Multi-gate mixture-of-experts encoder-decoder Dual-stage attention mechanism

来源：评论

学校读者我要写书评

暂无评论

A Highly Robust encoder-decoder Network with Multi-Scale Feature Enhancement and Attention Gate for the Reduction of Mixed Gaussian and Salt-and-Pepper Noise in Digital Images

引用

JOURNAL OF IMAGING 2025年第2期11卷 51-51页

作者： Tripathi, Milan Kongprawechnon, Waree Kondo, Toshiaki Thammasat Univ Sirindhorn Int Inst Technol Sch Informat Comp & Commun Technol Pathum Thani 12120 Thailand

Image denoising is crucial for correcting distortions caused by environmental factors and technical limitations. We propose a novel and highly robust encoder-decoder network (HREDN) for effectively removing mixed salt-and-pepper and Gaussian noise from digital images. HREDN integrates a multi-scale feature enhancement block in the encoder, allowing the network to capture features at various scales and handle complex noise patterns more effectively. To mitigate information loss during encoding, skip connections transfer essential feature maps from the encoder to the decoder, preserving structural details. However, skip connections can also propagate redundant information. To address this, we incorporate attention gates within the skip connections, ensuring that only relevant features are passed to the decoding layers. We evaluate the robustness of the proposed method across facial, medical, and remote sensing domains. The experimental results demonstrate that HREDN excels in preserving edge details and structural features in denoised images, outperforming state-of-the-art techniques in both qualitative and quantitative measures. Statistical analysis further highlights the model's ability to effectively remove noise in diverse, complex scenarios with images of varying resolutions across multiple domains.

关键词： image denoising Gaussian salt-and-pepper encoder-decoder multi-scale feature enhancement

来源：评论

学校读者我要写书评

暂无评论

Reconstructing 12-lead ECG from reduced lead sets using an encoder-decoder convolutional neural network

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2025年 104卷

作者： Epmoghaddam, Dorsa Banta, Anton Post, Allison Razavi, Mehdi Aazhang, Behnaam Rice Univ Dept Elect & Comp Engn Houston TX 77005 USA Texas Heart Inst Electrophysiol Clin Res & Innovat Houston TX USA Texas Heart Inst Dept Cardiol Houston TX USA

The standard 12-lead electrocardiogram (ECG) is the gold-standard clinical tool for assessing the heart's electrical activity. The primary goal of this study is to reduce the number of recording sites needed to capture the same amount of information as a 12-lead ECG. This approach will simplify monitoring procedures, improve patient comfort, and broaden ECG accessibility across various healthcare settings. In this work, a patient-specific framework is investigated to map a multivariate input to a multivariate output, namely reconstructing the standard 12-lead ECG from any subset of three independent standard ECG leads (i.e. I,II, V 1 : V 6 ). The algorithm is evaluated on two datasets: non-public data from 15 patients and the PTB Diagnostic ECG Database, with models trained and tested individually for each patient. The proposed method involves a series of preprocessing steps aimed at eliminating noise and segmenting the data into heartbeats, followed by Short-Time Fourier Transform (STFT) and an encoder-decoder convolutional neural network (CNN) model. The calculated correlation coefficient (CC) and root mean square error (RMSE) confirm the model's accuracy in reconstructing the 12-lead ECG. The proposed model achieves average correlations of 97.6% for the first dataset and 98.9% for the PTB Database using three leads. With a single lead as input, the average correlations reach 97.3% and 98.4% for the respective datasets. These results demonstrate the effectiveness of the proposed methodology in accurately reconstructing 12-lead ECGs using either any three independent leads or any single lead as input.

关键词： Electrocardiogram (ECG) ECG reconstruction Cardiovascular diseases Convolutional neural network (CNN) Standard 12-lead system encoder-decoder Mutual information

来源：评论

学校读者我要写书评

暂无评论

TSEDNet:Task-specific encoder-decoder network for surface defects of strip steel

引用

MEASUREMENT 2025年 239卷

作者： Guo, Yuyang Wei, Jingliang Feng, Xinglong Shenyang Univ Technol Sch Artificial Intelligence Shenyang 110870 Peoples R China BYD Automobile Ind Co Ltd China 3009 BYD Rd Shenzhen 518118 Guangdong Peoples R China

Deep learning faces challenges in the surface defect segmentation of strip steel. Firstly, insufficient processing of feature maps leads to the loss of task-specific feature information. Secondly, the segmentation of defects with long-tail distributions is not accurate enough. To address these issues, a pixel-level deep segmentation method called task-specific encoder-decoder network (TSEDNet) is proposed to construct an end-to-end defect segmentation model. TSEDNet includes the encoder-multi-decoder structure based on domain knowledge settings tailored to specific tasks, which can achieve effective feature representation and significantly reduce the impact of imbalanced defect quantities. Additionally, a novel metric learning method is introduced to optimize decoder selection. Furthermore, the feature fusion module based on metric learning is proposed to utilize general features for restoring task-specific details, thereby enhancing pixel-level segmentation accuracy. Through experiments and industrial validation, the defect segmentation network demonstrates superior performance compared to other advanced segmentation methods and proves its applicability in practical scenarios.

关键词： encoder-decoder Metric learning Domain knowledge Surface defect 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：