检索结果-内蒙古大学图书馆

deep autoencoder-like non-negative matrix factorization with graph regularized for link prediction in dynamic networks

引用

APPLIED SOFT COMPUTING 2023年 148卷

作者： Lv, Laishui Bardou, Dalal Liu, Yanqiu Hu, Peng China Jiliang Univ Coll Informat Engn Hangzhou 310018 Peoples R China Univ Abbes Laghrour Dept Comp Sci & Math ICOSI Lab Khenchela Algeria Anhui Normal Univ Sch Comp & Informat Wuhu 241002 Peoples R China

Link prediction in dynamic(temporal) networks refers to predicting future edges by analyzing the available network information. Among the existing temporal link prediction approaches, non-negative matrix factorization(NMF) is a kind of competitive algorithm and has attracted extensive attention. However, traditional NMF-based prediction methods are shallow methods and cannot fully mine the dynamic network, which may lead to a decrease in performance of algorithms. To overcome these shortcomings, inspired by deep autoencoder, we propose two novel deep autoencoder-like NMF with graph regularized prediction methods for dynamic networks. By fusing encoder component with deep structure into deep NMF model, our algorithms can sufficiently exploit the complex hierarchical information hidden in dynamic networks. To further extract the abundant information hidden in dynamic networks, graph regularization and PageRank are utilized to exploit the local and global topology information of each snapshot, respectively. By jointly optimizing them in deep autoencoder-like NMF model, our model is able to preserve the local and global information hidden in dynamic networks, simultaneously. Moreover, an effective alternating iterative method with convergence guarantee is developed for minimizing the established model. Finally, we test our proposed prediction methods on several synthetic and real world datasets to demonstrate that our approaches outperform the state-of-the-art prediction approaches.

关键词： Temporal networks Temporal link prediction deep NMF Graph regularization deep autoencoder

来源：评论

学校读者我要写书评

暂无评论

deep autoencoder Neural Networks for Short-Term Traffic Congestion Prediction of Transportation Networks

引用

SENSORS 2019年第10期19卷 2229页

作者： Zhang, Sen Yao, Yong Hu, Jie Zhao, Yong Li, Shaobo Hu, Jianjun Chinese Acad Sci Chengdu Inst Comp Applicat Chengdu 610041 Sichuan Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Guizhou Inst Technol Sch Big Data Guiyang 550003 Guizhou Peoples R China Guizhou Univ Sch Mech Engn Guiyang 550003 Guizhou Peoples R China GuiZhou Univ Finance & Econ Coll Big Data Stat Guiyang 550025 Guizhou Peoples R China Univ South Carolina Dept Comp Sci & Engn Columbia SC 29201 USA

Traffic congestion prediction is critical for implementing intelligent transportation systems for improving the efficiency and capacity of transportation networks. However, despite its importance, traffic congestion prediction is severely less investigated compared to traffic flow prediction, which is partially due to the severe lack of large-scale high-quality traffic congestion data and advanced algorithms. This paper proposes an accessible and general workflow to acquire large-scale traffic congestion data and to create traffic congestion datasets based on image analysis. With this workflow we create a dataset named Seattle Area Traffic Congestion Status (SATCS) based on traffic congestion map snapshots from a publicly available online traffic service provider Washington State Department of Transportation. We then propose a deep autoencoder-based neural network model with symmetrical layers for the encoder and the decoder to learn temporal correlations of a transportation network and predicting traffic congestion. Our experimental results on the SATCS dataset show that the proposed DCPN model can efficiently and effectively learn temporal relationships of congestion levels of the transportation network for traffic congestion forecasting. Our method outperforms two other state-of-the-art neural network models in prediction performance, generalization capability, and computation efficiency.

关键词： transportation network traffic congestion forecasting spatial-temporal correlation deep learning end-to-end deep autoencoder convolutional neural network long short-term memory

来源：评论

学校读者我要写书评

暂无评论

A Data Compression Method for Wellbore Stability Monitoring Based on deep autoencoder

引用

SENSORS 2024年第12期24卷 4006页

作者： Song, Shan Zhao, Xiaoyong Zhang, Zhengbing Luo, Mingzhang Yangtze Univ Sch Elect Informat & Elect Engn Jingzhou 434023 Peoples R China China Natl Petr Corp Bohai Drilling Engn Co Ltd Direct Drilling Branch Tianjin 300280 Peoples R China

The compression method for wellbore trajectory data is crucial for monitoring wellbore stability. However, classical methods like methods based on Huffman coding, compressed sensing, and Differential Pulse Code Modulation (DPCM) suffer from low real-time performance, low compression ratios, and large errors between the reconstructed data and the source data. To address these issues, a new compression method is proposed, leveraging a deep autoencoder for the first time to significantly improve the compression ratio. Additionally, the method reduces error by compressing and transmitting residual data from the feature extraction process using quantization coding and Huffman coding. Furthermore, a mean filter based on the optimal standard deviation threshold is applied to further minimize error. Experimental results show that the proposed method achieves an average compression ratio of 4.05 for inclination and azimuth data;compared to the DPCM method, it is improved by 118.54%. Meanwhile, the average mean square error of the proposed method is 76.88, which is decreased by 82.46% when compared to the DPCM method. Ablation studies confirm the effectiveness of the proposed improvements. These findings highlight the efficacy of the proposed method in enhancing wellbore stability monitoring performance.

关键词： wellbore safety monitoring deep autoencoder well trajectory data compression logging while drilling (LWD)

来源：评论

学校读者我要写书评

暂无评论

Wavelet-based extended morphological profile and deep autoencoder for hyperspectral image classification

引用

INTERNATIONAL JOURNAL OF WAVELETS MULTIRESOLUTION AND INFORMATION PROCESSING 2018年第3期16卷

作者： Luo, Huiwu Tani, Yuan Yan Biuk-Aghai, Robert P. Yang, Xu Yang, Lina Wang, Yi Univ Macau Fac Sci & Technol Macau 999078 Peoples R China Guangxi Univ Sch Comp Elect & Informat Nanning 530004 Peoples R China Chongqing Univ Coll Comp Sci Chongqing 400030 Peoples R China

In this paper, we propose a novel scheme to learn high-level representative features and conduct classification for hyperspectral image (HSI) data in an automatic fashion. The proposed method is a collaboration of a wavelet-based extended morphological profile (WTEMP) and a deep autoencoder (DAE) ("WTEMP-DAE"), with the aim of exploiting the discriminative capability of DAE when using WTEMP features as the input. Each part of WTEMP-DAE is ingenious and contributes to the final classification performance. Specifically, in WTEMP-DAE, the spatial information is extracted from the WTEMP, which is then joined with the wavelet denoised spectral information to form the spectral-spatial description of HSI data. The obtained features are fed into DAE as the original input, where the good weights and bias of the network are initialized through unsupervised pre-training. Once the pro-training is completed, the reconstruction layers are discarded and a logistic regression (LR) layer is added to the top of the network to perform supervised fine-tuning and classification. Experimental results on two real HSI data sets demonstrate that the proposed strategy improves classification performance in comparison with other state-of-the-art hand-crafted feature extractors and their combinations.

关键词： Wavelet transform deep autoencoder neuronal network mathematical morphology feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Combination of deep autoencoder and Multi-Scale Residual Network for Landslide Susceptibility Evaluation

引用

REMOTE SENSING 2023年第3期15卷

作者： Wang, Zhuolu Xu, Shenghua Liu, Jiping Wang, Yong Ma, Xinrui Jiang, Tao He, Xuan Han, Zeya Liaoning Tech Univ Sch Mapping & Geog Sci Fuxin 123000 Peoples R China Chinese Acad Surveying & Mapping Beijing 100830 Peoples R China Wuhan Univ Sch Resources & Environm Sci Wuhan 430072 Peoples R China

Landslide susceptibility evaluation can accurately predict the spatial distribution of potential landslides, which offers great usefulness for disaster prevention, disaster reduction, and land resource management. Aiming at the problems of insufficient samples for landslide compilation, difficulty in expanding landslide samples, and insufficient expression of nonlinear relationships among evaluation factors, this paper proposes a new evaluation method of landslide susceptibility combining deep autoencoder and multi-scale residual network (DAE-MRCNN). In the first step, a deep autoencoder network was used to learn the feature expression of the original landslide data in order to acquire effective features in the data. Next, a multi-scale residual network was constructed;specifically, the model was improved into a deep residual network model by adding skip connections in the convolutional layer. In addition, the multi-scale idea was utilized to fully extract the scale characteristics of the evaluation factors. Finally, the model was used for feature training, and the results were input into the Softmax classifier to complete the prediction of landslide susceptibility. For this purpose, a machine learning method and two state-of-the-art deep learning methods, namely SVM, CPCNN-ML, and 2D-CNN, were utilized to model landslide susceptibility in Hanzhong City, Shaanxi Province. The proposed method produced the highest model performance of 0.891, followed by 0.842, 0.869, and 0.873. The experimental results show that the DAE-MRCNN method can fully express the complex nonlinear relationships among the evaluation factors, alleviate the problem of insufficient samples in convolutional neural networks (CNN) training, and significantly improve the accuracy of susceptibility prediction.

关键词： landslide susceptibility deep autoencoder convolutional neural networks residual learning multiscale

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection of Water Level Using deep autoencoder

引用

SENSORS 2021年第19期21卷 6679页

作者： Nicholaus, Isack Thomas Park, Jun Ryeol Jung, Kyuil Lee, Jun Seoung Kang, Dae-Ki Dongseo Univ Dept Comp Engn Busan 47011 South Korea Buzzni AI Lab Seoul 08788 South Korea JCMEEK Seoul 07591 South Korea Infran R&D Ctr Seoul 07994 South Korea

Anomaly detection is one of the crucial tasks in daily infrastructure operations as it can prevent massive damage to devices or resources, which may then lead to catastrophic outcomes. To address this challenge, we propose an automated solution to detect anomaly pattern(s) of the water levels and report the analysis and time/point(s) of abnormality. This research's motivation is the level difficulty and time-consuming managing facilities responsible for controlling water levels due to the rare occurrence of abnormal patterns. Consequently, we employed deep autoencoder, one of the types of artificial neural network architectures, to learn different patterns from the given sequences of data points and reconstruct them. Then we use the reconstructed patterns from the deep autoencoder together with a threshold to report which patterns are abnormal from the normal ones. We used a stream of time-series data collected from sensors to train the model and then evaluate it, ready for deployment as the anomaly detection system framework. We run extensive experiments on sensor data from water tanks. Our analysis shows why we conclude vanilla deep autoencoder as the most effective solution in this scenario.

关键词： anomaly detection deep autoencoder time-series

来源：评论

学校读者我要写书评

暂无评论

Detection and classification of brain abnormality by a novel hybrid EfficientNet-deep autoencoder (EF-DA) CNN model from MRI brain images in smart health diagnosis

引用

INTERNATIONAL JOURNAL OF NANOTECHNOLOGY 2023年第5-10期20卷 696-718页

作者： Nayak, Dillip Ranjan Padhy, Neelamadhab Singh, Ashish Mallick, Pradeep Kumar GIET Univ Sch Engn & Technol CSE Gunupur 765022 Odisha India Deemed Univ Kalinga Inst Ind Technol Sch Comp Engn Bhubaneswar 751024 India

This paper presents the novel smart hybrid EfficientNet-deep autoencoder (EF-DA) deep Neural Network model to classify brain images. This is the succession of modified EfficientNetB0 with a deep autoencoder to detect tumours. Initially, the feature extraction is done by modified EfficientNet, and then classification is done by the proposed smart deep autoencoder. The images are filtered, cropped by morphological operations, and augmented to train a deep hybrid EF-DA model in the first stage. In the second stage, a modified deep autoencoder is used for classification. The statistical result analysis of the hybrid model is assessed using seven types of degree metrics like F-score, precision, recall, specificity, Kappa score, accuracy, and area under the ROC curve (AUC) score. It is compared with three types of pre-trained models like MobileNet, MobileNetV2, and ResNet50 for analysis. The EF-DA model has achieved an overall accuracy of 99.34% and an AUC score of 99.95%.

关键词： hybrid EfficientNet data augmentation deep autoencoder deep neural network AUC score overfitting recall precision F-score

来源：评论

学校读者我要写书评

暂无评论

DAE-TPGM: A deep autoencoder network based on a two-part-gamma model for analyzing single-cell RNA-seq data

引用

COMPUTERS IN BIOLOGY AND MEDICINE 2022年 146卷 105578-105578页

作者： Zhao, Shuchang Zhang, Li Liu, Xuejun Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol MIIT Key Lab Pattern Anal & Machine Intelligence Nanjing 211106 Peoples R China Collaborat Innovat Ctr Novel Software Technol & In Nanjing 210023 Peoples R China Nanjing Forestry Univ Coll Comp Sci & Technol Nanjing 210037 Peoples R China

Single-cell RNA sequencing (scRNA-seq) can reveal differences in genetic material at the single-cell level and is widely used in biomedical studies. However, the minute RNA content within individual cells often results in a high number of dropouts and introduces random noise of scRNA-seq data, concealing the original gene expression pattern. Therefore, data normalization is critical in the analysis pipeline to adjust for unexpected biological and technical effects, leading to a particular bimodal expression pattern exhibited in the semi continuous normalized data. We further find the positive continuous expression presents a right-skewed distribution, which is still under-explored by mainstream dimensionality reduction and imputation methods. We introduced a deep autoencoder network based on a two-part-gamma model (DAE-TPGM) for joint dimensionality reduction and imputation of scRNA-seq data. DAE-TPGM uses a two-part-gamma model to capture the statistical characteristics of semi-continuous normalized data and adaptively explores the potential relationships between genes for promoting data imputation by deep autoencoder. Just as the classic application scenarios that use an autoencoder in dimensionality reduction, our personalized autoendoer can capture phenotypic information on the peripheral blood mononuclear cells (PBMC) better and clearly infer continuous phenotype information for hematopoiesis in mice. Compared with that of mainstream imputation methods such as MAGIC, SAVER, scImpute and DCA, the new model achieved substantial improvement on the recognition of cellular phenotypes in two real datasets, and the comprehensive analyses on synthetic "ground truth" data demonstrated that our method obtains competitive advantages over other imputation methods in discovering underlying gene expression patterns in time-course data.

关键词： Single-cell RNA sequencing deep autoencoder Two-part model Gamma distribution Dimensionality reduction Imputation

来源：评论

学校读者我要写书评

暂无评论

Fast deep autoencoder for fe derate d learning

引用

PATTERN RECOGNITION 2023年 143卷

作者： Novoa-Paradela, David Fontenla-Romero, Oscar Guijarro-Berdinas, Bertha Univ A Coruna CITIC Campus Elvina s-n La Coruna 15008 Spain

This paper presents a novel, fast and privacy preserving implementation of deep autoencoders. DAEF (deep autoencoder for Federated learning), unlike traditional neural networks, trains a deep autoencoder network in a non-iterative way, which drastically reduces training time. Training can be performed incrementally, in parallel and distributed and, thanks to its mathematical formulation, the information to be exchanged does not endanger the privacy of the training data. The method has been evaluated and compared with other state-of-the-art autoencoders, showing interesting results in terms of accuracy, speed and use of available resources. This makes DAEF a valid method for edge computing and federated learning, in addition to other classic machine learning scenarios.& COPY;2023 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY license ( http://***/licenses/by/4.0/ )

关键词： deep autoencoder Anomaly detection Federated learning Edge computing Machine learning

来源：评论

学校读者我要写书评

暂无评论

Tasmanian devil optimization with deep autoencoder for intrusion detection in IoT assisted unmanned aerial vehicle networks

引用

AIN SHAMS ENGINEERING JOURNAL 2024年第11期15卷

作者： Negm, Noha Alamro, Hayam Allafi, Randa Khalid, Majdi Nouri, Amal M. Marzouk, Radwa Othman, Aladdin Yahya Ahmed, Noura Abdelaziz King Khalid Univ Coll Sci & Art Mahayil Dept Comp Sci Abha Saudi Arabia Princess Nourah Bint Abdulrahman Univ Coll Comp & Informat Sci Dept Informat Syst POB 84428 Riyadh 11671 Saudi Arabia Northern Border Univ Dept Comp & Informat Technol Coll Sci & Arts Ar Ar Saudi Arabia Umm Al Qura Univ Coll Comp & Informat Syst Dept Comp Sci Mecca Saudi Arabia Imam Abdulrahman Bin Faisal Univ Appl Coll Dept Comp Sci Dammam 34212 Saudi Arabia Prince Sattam Bin Abdulaziz Univ Dept Comp & Self Dev Preparatory Year Deanship Alkharj Saudi Arabia

Background: Recently, a developing count of physical objects is linked to the Internet at an unprecedented rate, calcifying the knowledge of the Internet of Things (IoT). In several paradigms of IoT applications, unmanned aerial vehicles (UAVs) and satellites for IoT have concerned much attention and are experiencing quick progress. As for UAVs, because of their superiority in maneuverability and cost, it is established an increasingly extensive consumption in several IoT scenarios like disaster relief, rapid transportation, and environment monitoring. Security remains a main problem in the IoT supported UAV networks that are solved by the employ of intrusion detection system (IDS) methods. Objective: This article aims to present a Tasmanian Devil Optimization with deep autoencoder for Intrusion Detection System (TDODAE-IDS) technique in IoT assisted Unmanned Aerial Vehicle Networks. Methods: The presented TDODAE-IDS technique majorly concentrates on the effectual identification of the intrusions in the IoT based UAV networks. To accomplish this, the presented TDODAE-IDS system designs a new TDO algorithm for the feature subset selection process. Moreover, the DAE model classifies the existence of intrusion in the UAV network and the hyperparameter tuning of the DAE model takes place using the dragonfly algorithm (DFA). Results: The simulation results of the TDODAE-IDS approach were tested on a benchmark IDS dataset and the results are assessed under several measures. Conclusion: The comprehensive comparative analysis highlighted the enhanced outcomes of the TDODAE-IDS algorithm over other recent approaches with maximum accuracy of 99.36%. Therefore, the proposed model can be employed to accomplish security in the IoT assisted UAV networks.

关键词： Internet of things Unmanned aerial vehicles deep autoencoder Intrusion detection Feature selection

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

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

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：