检索结果-内蒙古大学图书馆

Few-shot traffic classification based on autoencoder and deep graph convolutional networks

SCIENTIFIC REPORTS 2025年第1期15卷 1-16页

作者： Xu, Shengwei Han, Jijie Liu, Yilong Liu, Haoran Bai, Yijie Beijing Elect Sci & Technol Inst Informat Secur Res Inst Beijing 100070 Peoples R China Beijing Elect Sci & Technol Inst Dept Cryptog Sci & Technol Beijing 100070 Peoples R China Beijing Univ Posts & Telecommun Sch Cyberspace Secur Beijing 100876 Peoples R China

Traffic classification is a crucial technique in network management that aims to identify and manage data packets to optimize network efficiency, ensure quality of service, enhance network security, and implement policy management. As graph convolutional networks (GCNs) take into account not only the features of the data itself, but also the relationships among sets of data during classification. Many researchers have proposed their own traffic classification methods based on GCN in recent years. However, most of the current approaches use two-layer GCN primarily due to the over-smoothing problem associated with deeper GCN. In scenarios with small samples, a two-layer GCN may not adequately capture relationships among traffic data, leading to limited classification performance. Additionally, during graph construction, traffic usually needs to be trimmed to a uniform length, and for traffic with insufficient length, zero-padding is typically applied to extension. This zero-padding strategy poses significant challenges in traffic classification with small samples. In this paper, we propose a method based on autoencoder (AE) and deep graph convolutional networks (ADGCN) for traffic classification for few-shot datasets. ADGCN first utilizes an AE to reconstruct the traffic. AE enables shorter traffic to learn abstract feature representations from longer traffic of the same class to replace zeros, mitigating the adverse effects of zero-padding. The reconstructed traffic is then classified using GCNII, a deep GCN model that addresses the challenge of insufficient data samples. ADGCN is an end-to-end traffic classification method applicable to various scenarios. According to experimental results, ADGCN can achieve a classification accuracy improvement of 3.5 to 24% compared to existing state-of-the-art methods. The code is available at https://***/han20011019/ADGCN.

关键词： Traffic classification autoencoder Graph convolutional networks Few-shot

来源：评论

学校读者我要写书评

暂无评论

Design of autoencoder Algorithm for Compression of Lightweight EEG Signals Based on 2-D Rhythm Feature Maps

IEEE SENSORS LETTERS

引用

IEEE SENSORS LETTERS 2025年第3期9卷

作者： Ma, Peijun Yao, Cong Shi, Jiangyi Zhao, Gongzhi Ma, Mingyu Xidian Univ Sch MicroElect Xian 710000 Peoples R China

In recent years, with the development of brain science, the value of electroencephalography (EEG) data has become prominent. However, due to the characteristics of real-time transmission and large amounts of data, there is an urgent need for efficient and lightweight EEG compression algorithms. The existing EEG compression methods have many shortcomings, such as limited compression ratio (CR), poor reconstruction signal quality, and too large model scale, which cannot meet the developmental needs of portable wearable EEG detection devices. In this letter, a method of EEG signal compression based on 2-D rhythm feature maps is proposed. Through discrete wavelet transformation (DWT) extraction of the signal rhythm characteristics, the signal is compressed and reconstructed using encoding and reconstruction channels based on an autoencoder network. At the output end of the encoding channel, entropy coding is carried out to further compress the data volume. Through the discussion of several coding algorithms, JPEG2000 is selected as the local optimal coding algorithm. In addition, based on the idea of grouping convolution and void convolution kernel, a lightweight structure is designed to simplify the process of the proposed network and greatly reduce the number of model parameters. Experiments show that, compared with other similar algorithms, the percentage-root-mean-square distortion and mean squared error (MSE) of the proposed algorithm are 14.76% and 2.95%, respectively, at a relatively high CR (CR is about 16). And only 87.9-k parameters are used, which is more suitable for embedded scenarios and wearable devices.

关键词： Convolution Electroencephalography Feature extraction Transform coding Rhythm Kernel autoencoders Brain modeling Sleep Signal processing algorithms Sensor signal processing 2-D rhythm profile autoencoder electroencephalography (EEG) JPEG2000 lightweight signal compression

来源：评论

学校读者我要写书评

暂无评论

Localized global models using autoencoder-based clustering to forecast related time series

引用

INTERNATIONAL JOURNAL OF DATA SCIENCE AND ANALYTICS 2025年 1-22页

作者： Abbasimehr, Hossein Noshad, Ali Azarbaijan Shahid Madani Univ Fac Informat Technol & Comp Engn Tabriz Iran Politecn Milan Dept Elect Informat & Bioengn Milan Italy

In many industries, such as banking, retail, medical, and tourism, abundant time series data is generated. Global forecasting methods have emerged to train a single model by leveraging cross-series information. However, the performance of the global models may be decreased when applied to heterogeneous unequal-length time series datasets. To address heterogeneity in time series, this study contributes a comprehensive methodology for time series forecasting, incorporating three key components: (1) automatic feature extraction from unequal-length time series utilizing two novel autoencoder models based on long short-term memory and convolutional neural network methods, (2) time series clustering, (3) and global forecasting. To evaluate the forecasting accuracy of the proposed methodology, we conduct comprehensive experiments across various time series datasets including six datasets of M3, Tourism, and Hospital datasets. Across all datasets with 2620 time series, attained the lowest mean symmetric mean absolute percentage error (sMAPE) of 15.08, surpassing the baseline mean sMAPE of 15.42. It exhibits enhancements of 0.19 and 0.60 in mean sMAPE relative to ETS and ARIMA, respectively. Furthermore, it demonstrates improvements of 1.10, 0.52, and 2.11 compared to DeepAR, N-BEATS, and Transformer, respectively. A comparative analysis of our proposed methodology against clustering-based and ensembling-based models in the existing literature highlights its superiority in global time series forecasting.

关键词： Related time series Global forecasting autoencoder LSTM CNN

来源：评论

学校读者我要写书评

暂无评论

Leveraging autoencoder for laser phase noise compensation in coherent optical OFDM systems

引用

JOURNAL OF OPTICS-INDIA 2025年 1-10页

作者： Al-Saedi, Ibtesam R. K. Alnaseri, Omar Rasool, Jamal Mohammed Li, Hongxiang Univ Technol Iraq Commun Engn Dept Baghdad Iraq DHBW Ravensburg Univ Dept Elect Engn Ravensburg Baden Wuerttemb Germany Univ Louisville Dept Elect & Comp Engn Louisville KY USA

This paper unveils a cutting-edge end-to-end learning approach to tackle laser phase noise in coherent optical orthogonal frequency-division multiplexing (CO-OFDM) fiber communications. Inspired by the autoencoder concept, a powerful deep neural network, the proposed approach tackles this challenge by learning resilient symbol sequences that can withstand laser phase noise impairments, even from low-cost distributed feedback lasers with linewidths up to 2 MHz. This makes it ideally suited for high-order modulation formats and large FFT sizes in CO-OFDM systems, where maximizing spectral efficiency is crucial. By eliminating the need for computationally intensive conventional techniques, this approach opens the door to a simpler, potentially more efficient solution.

关键词： Optical fiber communication Coherent detection OFDM Laser phase noise autoencoder

来源：评论

学校读者我要写书评

暂无评论

Robust biochar yield and composition prediction via uncertainty-aware ResNet-based autoencoder

引用

BIOCHAR 2025年第1期7卷 1-16页

作者： Zhang, Yali Lei, Bowen Mahdaviarab, Amirhossein Wang, Xiao Liu, Zong Texas A&M Univ 375 Olsen Blvd College Stn TX 77845 USA

With growing demand for energy and fossil fuels, biomass and biochar are gaining attention due to their abundance and sustainability. However, there is a crucial need for optimizing production conditions and minimizing environmental risks associated with biochar production. Machine learning is an emerging strategy for predicting biochar yield and composition, optimizing production conditions and minimizing environmental risks. This paper presents a ResNet-based autoencoder model that utilizes biomass properties and pyrolysis conditions to more accurately and robustly predict biochar yield and composition. The developed model has the advantage of addressing the common data uncertainty concerns in training data. Our model outperforms commonly used baseline methods, including MLP-NN (mean R2 = 0.907), Random Forest (RF, mean R2 = 0.798), XGBoost (XGB, mean R2 = 0.826), and Gaussian Process (GP, mean R2 = 0.786), by achieving a mean R2 of 0.974. The performance of the model was further improved by incorporating previously discarded data with high missing rates, achieving an average R2 of 0.983. The addition of the three newly collected covariates resulted in an average R2 of 0.985. Additionally, robust sensitivity analyses of the input covariates revealed the impact of data uncertainty on the performance of the model, emphasizing the robustness of the model. In advancing the application of machine learning in biochar research, this study provides a reliable method to determine optimal production conditions.

关键词： Biochar yield Data uncertainty Robustness ResNet autoencoder

来源：评论

学校读者我要写书评

暂无评论

Seq2Seq-based GRU autoencoder for anomaly detection and failure identification in coal mining hydraulic support systems

引用

SCIENTIFIC REPORTS 2025年第1期15卷 1-19页

作者： Zhan, Kai Wang, Cong Zheng, Xigui Kong, Chao Li, Guangming Xin, Wei Liu, Longhe Shandong Succeed Min Safety Engn Co LTD Jinan Peoples R China Chengdu Univ Technol Chengdu Peoples R China China Univ Min & Technol Sch Mines Xuzhou Peoples R China China Univ Min & Technol State Key Lab Geo Mech & Deep Underground Engn Xuzhou Peoples R China Liupanshui Normal Univ Sch Mines & Civil Engn Liupanshui Peoples R China Guizhou Guineng Investment Co Ltd Guiyang Peoples R China

In coal mining operations, the stable operation of hydraulic supports is crucial for ensuring mine safety. However, the nonlinear, non-stationary characteristics and noise interference in hydraulic support pressure data pose significant challenges for anomaly detection and fault diagnosis. This study proposes an anomaly detection and failure identification method based on Gated Recurrent Unit autoencoder (GRU-AE), aimed at achieving anomaly detection in hydraulic support pressure data and equipment failure early warning. Through in-depth analysis of data from two coal mines in China, we systematically evaluated the model's key parameters. The study revealed that window size had a limited impact on model performance, with a window length of 144 demonstrating optimal comprehensive performance in both anomaly detection and failure mode identification. The study also investigated the effectiveness of teacher forcing techniques. Although this technique can accelerate model convergence, it may lead to training instability and reduced generalization capability, requiring careful consideration in practical applications. Our proposed Recurrent Reconstruction Network model demonstrated excellent performance in complex coal mine hydraulic support data, effectively identifying anomalous regions and potential equipment failure characteristics while revealing potential deviations between model predictions and actual data, demonstrating its superior learning capability for periodic data patterns and equipment failure characteristics. Experimental results validated the effectiveness of the GRU-AE model in hydraulic support pressure anomaly detection and equipment fault diagnosis, providing an innovative technical solution for coal mine safety monitoring.

关键词： Mining engineering Hydraulic support Anomaly detection Gated recurrent unit autoencoder

来源：评论

学校读者我要写书评

暂无评论

AW-CES: adaptively weighted-cumulative error scoring for autoencoder-based anomaly detection on unlabeled data

引用

INTERNATIONAL JOURNAL OF DATA SCIENCE AND ANALYTICS 2025年 1-20页

作者： Park, Cheolsoon Song, Seunghwan Baek, Jun-Geol Korea Univ Dept Ind & Management Engn 145 Anam Ro Seoul 02841 South Korea

autoencoder-based anomaly detectors generally utilize reconstruction error as an anomaly score. However, when both normal and abnormal data are included in train dataset, sufficient training time can lead to the learning of both types of data. Therefore, it becomes difficult to distinguish between the two classes based on reconstruction errors, which degrades the detection performance. To mitigate this, it is necessary to regularize the number of training epochs (NTE). However, this is difficult without labels. Therefore, some studies introduced additional hyperparameters (HPs), arbitrarily selected, to determine the NTE. However, this may degrade the performance and increase its variability. To address this, cumulative error scoring (CES) has been proposed. This method does not determine a single optimal NTE. Instead, to enhance the robustness, it accumulates reconstruction errors from the models trained in the early stages of learning, similar to an ensemble method. Therefore, it showed promising results in the performance robustness. However, it also introduced an additional HP to exclude meaningless reconstruction errors. To improve the limitations of CES, we proposed adaptively weighted-cumulative error scoring (AW-CES). AW-CES utilizes the weighted average of reconstruction errors as an anomaly score. The weights are estimated based on the theoretical characteristic of inlier priority (IP) in deep learning models. Moreover, AW-CES does not require additional HP and the weights are automatically determined during the training without labels. The performance was evaluated using various experiments on real datasets. The results showed an improved average performance. In particular, AW-CES demonstrated a significant improvement in the performance robustness.

关键词： Anomaly detection Unsupervised learning Unlabeled data autoencoder Cumulative error scoring Inlier priority

来源：评论

学校读者我要写书评

暂无评论

High-precision detection of dibutyl hydroxytoluene in edible oil via convolutional autoencoder compressed Fourier-transform near-infrared spectroscopy

引用

FOOD CONTROL 2025年 167卷

作者： Deng, Jihong Chen, Zhenyu Jiang, Hui Chen, Quansheng Jiangsu Univ Sch Elect & Informat Engn Zhenjiang 212013 Peoples R China Jimei Univ Coll Ocean Food & Biol Engn Xiamen 361021 Peoples R China

The quality of edible oils is closely related to their chemical compositions. Antioxidants have widespread application in edible oil production. In this study, a pioneering detection approach involving the use of a onedimensional convolutional autoencoder (1D-CAE) was introduced to compress spectral data for assessing antioxidant levels in edible oils. Fourier-transform near-infrared (FT-NIR) characterisation of edible oil samples with varying antioxidant concentrations was also conducted. An 1D-CAE model was developed to compress different pre-processed spectra into a condensed representation. These compressed features were then integrated with a support vector machine and partial least squares regression models to establish correlations for each target. The study examined the influence of pre-processing steps and feature engineering methods on near-infrared spectral analysis through independent or combined model analysis. The findings revealed that features derived from the 1D-CAE model demonstrated remarkable repeatability and can be utilised to construct robust detection models. The experimental results showed that the optimal detection model derived based on the 1D-CAE compression features has an average R2, 2 , RPD and RMSE of 0.9953, 15.1664 and 1.2035, respectively, on the prediction set. FT-NIR spectroscopy can be used to accurately detect butylated hydroxytoluene in edible oils. Therefore, autoencoders are an effective tool in spectroscopic analysis, offering promising avenues for future research and application.

关键词： Edible oils Antioxidants Near-infrared Deep learning autoencoder

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Topology Optimization of Synchronous Reluctance Motors Using autoencoder-estimated Flux Barrier Shapes

引用

IEEJ JOURNAL OF INDUSTRY APPLICATIONS 2025年第1期14卷 12-19页

作者： Kishi, Masahiro Wakao, Shinji Murata, Noboru Makino, Hiroaki Takeuchi, Katsutoku Matsushita, Makoto Waseda Univ Dept Elect Engn & Biosci 3-4-1 Ohkubo Tokyo 1698555 Japan Toshiba Infrastructure Syst & Solut Corp Infrastruct Syst R&D Ctr 1 Toshiba Fuchu Tokyo 1838511 Japan

This paper presents a novel topology optimization approach for the design of synchronous reluctance motors based on an autoencoder (AE) combined with the level set (LS) method. As the initial shapes of the LS method, the technique uses the shape generated by the AE, which learns the relationship between the objective function values and the design shapes in the optimization process. The proposed method trains the network parameters such that certain latent variable components represent shape features that are correlated with targeted objective functions. Consequently, shape variations that correspond to changes in multiple objective function values can be independently and continuously visualized. This enables the efficient preparation of new structures that are expected to have high performance. Finally, the AE-generated shapes are used as the initial shapes for LS optimization to derive practical Pareto solutions.

关键词： topology optimization synchronous reluctance motor autoencoder convolutional neural network multi-objective optimization level set method

来源：评论

学校读者我要写书评

暂无评论

Big Data-Driven Control of Nonlinear Processes Through Dynamic Latent Variables Using an autoencoder

引用

IEEE TRANSACTIONS ON CYBERNETICS 2025年第5期55卷 2411-2423页

作者： Tang, Jun Wen Yan, Yitao Bao, Jie Huang, Biao Univ New South Wales Sch Chem Engn Sydney NSW 2052 Australia Univ Alberta Dept Chem & Mat Engn Edmonton AB T6G 2R3 Canada

This article presents a novel data-driven approach to nonlinear system control using a behavioral systems framework. A dynamic latent variable autoencoder (DLVAE) is proposed to project the nonlinear physical variable space onto a linear latent variable space. A data-predictive control approach is developed to control the physical process variables through the latent variables. Based on the behavioral systems theory, the proposed data-driven control framework does not require knowledge of the causality of the latent variables. The stability of the controlled system is ensured by utilizing the concept of trajectory-based dissipativity. The robustness of this control approach is achieved by incorporating the Lipschitz bounds between the latent and physical variables under dissipativity conditions.

关键词： Trajectory Aerospace electronics autoencoders Process control Symmetric matrices Control design Cause effect analysis Nonlinear dynamical systems Linear systems Decoding autoencoder behavioral systems theory data-based control dissipativity nonlinear processes quadratic difference forms

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：