检索结果-内蒙古大学图书馆

An integrated feature learning approach using deep learning for travel time prediction

EXPERT SYSTEMS WITH APPLICATIONS 2020年 139卷 112864-000页

作者： Abdollahi, Mohammad Khaleghi, Tannaz Yang, Kai Wayne State Univ Dept Ind & Syst Engn Detroit MI 48202 USA

Travel time data is a vital factor for numbers of performance measures in transportation systems. Travel time prediction is both a challenging and interesting problem in ITS, because of the underlying traffic and events' hidden patterns. In this study, we propose a multi-step deep-learning-based algorithm for predicting travel time. Our algorithm starts with data pre-processing. Then, the data is augmented by incorporating external datasets. Moreover, extensive feature learning and engineering such as spatiotemporal feature analysis, feature extraction, and clustering algorithms is applied to improve the feature space. Furthermore, for representing features we used a deep stacked autoencoder with dropout layer as regularizer. Finally, a deep multi-layer perceptron is trained to predict travel times. For testing our predictive accuracy, we used a 5-fold cross validation to test the generalization of our predictive model. As we observed, the performance of the proposed algorithm is on average 4 min better than applying the deep neural network to the initial feature space. Furthermore, we have noticed that representation learning using stacked autoencoders makes our learner robust to overfitting. Moreover, our algorithm is capable of capturing the general dynamics of the traffic, however further works need to be done for some rare events which impact travel time prediction significantly. (C) 2019 Elsevier Ltd. All rights reserved.

关键词： Deep learning stacked autoencoder Transportation Travel time prediction Deep neural network Spatiotemporal analysis

来源：评论

学校读者我要写书评

暂无评论

A data-driven computational framework for non-intrusive reduced-order modelling of turbulent flows passing around bridge piers

引用

OCEAN ENGINEERING 2024年 308卷

作者： Zhu, Chuanhua Xiao, Dunhui Fu, Jinlong Feng, Yuntian Fu, Rui Wang, Jinsheng Anhui Jianzhu Univ Sch Environm & Energy Engn Hefei 230601 Peoples R China Swansea Univ Zienkiewicz Inst Modelling Data & AI Fac Sci & Engn Swansea SA1 8EN Wales Tongji Univ Sch Math Sci Key Lab Intelligent Comp & Applicat Minist Educ Shanghai 200092 Peoples R China Queen Mary Univ London Fac Sci & Engn Dept Mech Engn London E1 4NS England Tongji Univ State Key Lab Disaster Reduct Civil Engn Shanghai 200092 Peoples R China Univ Birmingham Sch Civil Engn Birmingham B15 2TT England

Repetitively conducting high-fidelity numerical simulations under varying conditions is often a crucial requirement in the optimisation design of offshore bridges and structures. Reduced-order modelling (ROM) provides an efficient approach to quickly and reliably obtain solutions by extracting low-dimensional representations from full-order numerical systems. This paper presents a novel data-driven computational framework for non- intrusive ROM of turbulent/unsteady flows passing around bridge piers, consisting of two interconnected components: the stacked autoencoder (SAE) and the Dynamic Mode Decomposition (DMD). The novelty lies in utilising SAE to achieve nonlinear dimensionality reduction by projecting the full-order dynamical system onto a low-dimensional latent space, followed by constructing reduced-order models through data-driven DMD to represent fluid dynamics in the latent feature space. This new SAE-DMD-based method is applied to develop reduced-order models for two unsteady flow problems, and it is also compared with classical DMD and highfidelity numerical simulations in terms of modelling accuracy, forecasting efficiency and memory requirements. The results demonstrate that the proposed method can rapidly offer reliable predictions while significantly reducing memory usage and it exhibits excellent extrapolation capability by accurately preserving primary nonlinear characteristics of fluid dynamics. This new method shows potential to overcome computational challenges associated with high-resolution numerical modelling for complex large-scale flow problems.

关键词： Model order reduction Unsteady/turbulent flow Computational fluid dynamics stacked autoencoder Dynamic mode decomposition Non-intrusive

来源：评论

学校读者我要写书评

暂无评论

An Efficient Deep Learning Approach To IoT Intrusion Detection

引用

COMPUTER JOURNAL 2022年第11期65卷 2870-2879页

作者： Cao, Jin Lin, Liwei Ma, Ruhui Guan, Haibing Tian, Mengke Wang, Yong Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn Shanghai 200240 Peoples R China FuJian Univ Technol Sch Comp Sci & Math Fuzhou 350028 Fujian Peoples R China Peking Univ Sch Integrated Circuits Beijing 100871 Peoples R China Beijing Microelect Technol Inst Beijing 100076 Peoples R China

With the rapid development of the Internet of Things (IoT), network security challenges are becoming more and more complex, and the scale of intrusion attacks against the network is gradually increasing. Therefore, researchers have proposed Intrusion Detection Systems and constantly designed more effective systems to defend against attacks. One issue to consider is using limited computing power to process complex network data efficiently. In this paper, we take the AWID dataset as an example, propose an efficient data processing method to mitigate the interference caused by redundant data and design a lightweight deep learning-based model to analyze and predict the data category. Finally, we achieve an overall accuracy of 99.77% and an accuracy of 97.95% for attacks on the AWID dataset, with a detection rate of 99.98% for the injection attack. Our model has low computational overhead and a fast response time after training, ensuring the feasibility of applying to edge nodes with weak computational power in the IoT.

关键词： IoT security intrusion detection system attack classification stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

An enhanced swarm optimization-based deep neural network for diabetic retinopathy classification in fundus images

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2022年第15期81卷 20611-20642页

作者： Dayana, A. Mary Emmanuel, W. R. Sam Nesamony Mem Christian Coll Dept Comp Sci Marthandam India Manonmaniam Sundaranar Univ Tirunelveli 627012 Tamil Nadu India Nesamony Mem Christian Coll Dept PG Comp Sci Marthandam India

Diabetic Retinopathy (DR) is one of the long-lasting Diabetic retinal disorders that leads to vision impairment eventually blindness in most of the working-age population. The process of classifying the severity level of DR has been a great challenging task as the lesion features are hard to analyze. The screening process requires an effective detection method to classify the subtle pathologies of the retina. Deep neural architectures play a vital role in diagnosing eye disease and helps ophthalmologists to provide timely treatment. This paper proposes an efficient, optimized deep neural network with Chronological Tunicate Swarm Algorithm (CTSA) for classifying the severity of DR. Initially, the retinal images captured through the low-quality fundus photography are preprocessed and then subjected to the segmentation process. First, the optic disc and the blood vasculatures are segmented using a U-Net and sparse Fuzzy C-means-based hybrid entropy model. The lesion area is then detected using the Gabor filter banks, and then the features are extracted. The final classification process takes place using a deep stacked autoencoder (SAE) jointly optimized with a bio-inspired Tunicate Swarm Algorithm based on the chronological concept. The presented model achieved an average accuracy, sensitivity, specificity and F1-Score values of 95.9%, 88.07%, 96.80% and 85.26% for the DIARETDB0 database and 95.48%, 93.29%, 91.89% and 90.53% for the DIARETDB1 database. The experimental outcome demonstrates the effectiveness and the robustness of the proposed method in the DR classification task.

关键词： Diabetic retinopathy Deep neural network Classification Chronological tunicate swarm algorithm stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Deep multi-view representation learning for social images

引用

APPLIED SOFT COMPUTING 2018年 73卷 106-118页

作者： Huang, Feiran Zhang, Xiaoming Zhao, Zhonghua Li, Zhoujun He, Yueying Beihang Univ State Key Lab Software Dev Environm Beijing 100191 Peoples R China Beihang Univ Sch Cyber Sci & Technol Beijing 100191 Peoples R China Coordinat Ctr China Natl Comp Network Emergency Response Tech Team Beijing 100029 Peoples R China

Multi-view representation learning for social images has recently made remarkable achievements in many tasks, such as cross-view classification and cross-modal retrieval. Since social images usually contain link information besides the multi-modal contents (e.g., text description, and visual content), simply employing the data content may result in sub-optimal multi-view representation of the social images. In this paper, we propose a Deep Multi-View Embedding Model (DMVEM) to learn joint embeddings for the three views including the visual content, the associated text descriptions, and their relations. To effectively encode the link information, a weighted relation network is built based on the linkages between social images, which is then embedded into a low dimensional vector space using the Skip-Gram model. The learned vector is regarded as the third view besides the visual content and text description. To learn a joint representation from the three views, a deep learning model with three-branch nonlinear neural network is proposed. A three-view bi-directional loss function is used to capture the correlation between the three views. The stacked autoencoder is adopted to preserve the self-structure and reconstructability of the learned representation for each view. Comprehensive experiments are conducted in the tasks of image-to-text, text-to-image, and image-to-image searches. Compared to the state-of-the-art multi-view embedding methods, our approach achieves significant improvement of performance. (C) 2018 Elsevier B.V. All rights reserved.

关键词： Multi-view learning Image embedding Representation learning stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Adaptive EHTARA: An Energy-Efficient and Trust Aware Secure Routing Algorithm for Big Data Classification in IoT Network

引用

WIRELESS PERSONAL COMMUNICATIONS 2021年第1期121卷 621-646页

作者： Mujeeb, S. Md Sam, R. Praveen Madhavi, K. GITAM Deemed Be Univ Dept CSE SOT Hyderabad 502329 Telangana India G Pulla Reddy Engn Coll Autonomous Dept CSE Kurnool 518007 Andhra Pradesh India JNTUA Coll Engn Ananthapuramu Dept CSE Ananthapuramu 515002 Andhra Pradesh India

Due to rapid growth and tremendous advancement, the Internet of Things (IoT) has been considered as a superior technology in recent years and increased its demand over the internet world because of its smart services. IoT has a wide range of applications over the industry, business, and academia. Still, security and routing remain a huge challenging task because of some reasons, such as heterogeneity issues, large energy consumption, and uncontrollable environment. In order to cope up with such security issues, it is essential to develop an energy-efficient routing protocol. Hence, this article presents an Adaptive energy harvesting and Trust aware routing (EHTARA) algorithm for optimal routing such that it prolongs the lifetime of the network. The optimal secure routing path is chosen to exploit the cost metric function. Moreover, the classification of big data is performed at MapReduce framework using stacked autoencoder, which is trained using the proposed Adaptive E-2-Bat algorithm. Moreover, the proposed Adaptive E-2-Bat algorithm is derived by incorporating adaptive principle with E-2-Bat algorithm. The proposed Adaptive EHTARA achieved an energy of 0.948 J that reveals the superiority of the proposed scheme.

关键词： Internet of Things (IoT) Routing Big data MapReduce framework stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

A lightweight 3D-2D convolutional neural network for spectral-spatial classification of hyperspectral images

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2022年第1期43卷 1241-1258页

作者： Haque, Md Rakibul Mishu, Sadia Zaman Uddin, Md Palash Al Mamun, Md Rajshahi Univ Engn & Technol Dept Comp Sci & Engn Rajshahi Bangladesh Hajee Mohammad Danesh Sci & Technol Univ Dept Comp Sci & Engn Rajshahi Bangladesh

Hyperspectral Image (HSI) is usually composed of hundreds of capturing wavelength bands, which not only increase the size of the HSI rapidly but also impose various obstacles in classifying the objects accurately. Moreover, the traditional machine learning schemes utilize only the spectral features for HSI classification, which, therefore, neglect the spatial features that have a significant impact on the classification improvement. To address the aforementioned issues, in this paper, we propose to employ the principal component analysis (PCA), the baseline feature extraction method, and a thoughtfully designed stacked autoencoder, a deep learning-based feature extraction approach, for reducing the high dimensionality of the HSI and then propose a novel lightweight 3D-2D convolutional neural network (CNN) framework to concurrently exploit both spatial and spectral features from the dimensionality-reduced HSI for classification. In particular, PCA and stacked autoencoder are applied to reduce the high dimensionality of the original HSI and then the proposed 3D-2D CNN provides a combination of 3D and 2D convolution operations to extract the subtle spatial and spectral features for efficient classification. We well-adjust the proposed 3D-2D CNN architecture, and perform extensive experiments on three benchmark HSI datasets and compare our approach with the state-of-the-art classical and deep learning methods. Experimental results illustrate that we have achieved an overall accuracy of 99.73%, 99.90%, and 99.32% on Indian Pines, Pavia University, and Kennedy Space Center datasets, respectively, which outperform the classical machine learning and independent 2D and 3D CNN-based state-of-the-art methods.

关键词： Feature extraction principal component analysis deep learning stacked autoencoder classification convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Deep networks in identifying CT brain hemorrhage

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2018年第2期35卷 2215-2228页

作者： Helwan, Abdulkader El-Fakhri, Georges Sasani, Hadi Ozsahin, Dilber Uzun Near East Univ Dept Biomed Engn Near East Blvd TR-99138 Trnc Nicosia Turkey Harvard Med Sch Massachusetts Gen Hosp Gordon Ctr Med Imaging Radiol Boston MA USA

Deep learning algorithms have recently been applied to solving challenging problems in medicine such as medical image classification and analysis. In some areas, those algorithms have outperformed the human medical experts experience in diagnosis. Thus, in this paper we apply three different deep networks to solve the problem of brain hemorrhage identification in CT images. The motivation behind this work is the difficulty that radiologists encounter when diagnosing a hemorrhagic brain CT image, in particularly in the early stages of the brain bleeding. autoencoder (AE), stacked autoencoder (SAE), and convolutional neural network (CNN) are employed and trained to classify the CT images into hemorrhagic or non-hemorrhagic. Experimentally, it was found that all employed networks performed differently in terms of accuracy, error reached, and training time. However, stacked autoencoder has achieved a higher accuracy and lesser error compared to other used networks.

关键词： Deep learning deep networks hemorrhage autoencoder stacked autoencoder convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

The pre-trained explainable deep learning model with stacked denoising autoencoders for slope stability analysis

引用

ENGINEERING ANALYSIS WITH BOUNDARY ELEMENTS 2024年 163卷 406-425页

作者： Lin, Shan Dong, Miao Cao, Xitailang Liang, Zenglong Guo, Hongwei Zheng, Hong Beijing Univ Technol Key Lab Urban Secur & Disaster Engn Minist Educ Beijing 100124 Peoples R China Hong Kong Polytech Univ PolyU Dept Civil & Environm Engn Kowloon Hong Kong Peoples R China

In this work, we proposed a deeply-integrated explainable pre-trained deep learning framework with stacked denoising autoencoders in the assessment of slope stability. The deep learning model consists of a deep neural network as a trunk net for prediction and autoencoders as branch nets for denoising. A comprehensive review of machine learning algorithms in slope stability evaluation is first given in the introduction section. A series of 530 data is then collected from real slope records, which are visualized and investigated in feature engineering and further preprocessed for model training. To ensure reliable and trustworthy model interpretability, a unified model from both local and global perspectives is integrated into the deep learning model, which incorporated the ad hoc back-propagation based Deep SHAP, perturbation based Kernel SHAP and PDPs, and distillation based LIME and Anchors. For a fair evaluation, repeated stratified 10-fold cross-validation is adopted in model evaluation. The obtained results manifest that the constructed model outperforms commonly used machine learning methods in terms of accuracy and stability on the real-world slope data. The explainable model provides a reasonable explanation and validates the capability of the proposed model, and reflects the causes and dependencies of model predictions for a given sample.

关键词： Deep learning stacked autoencoder Slope stability Explainable machine learning DeepLIFT SHAP Anchors Geotechnical engineering

来源：评论

学校读者我要写书评

暂无评论

Pseudo Label-Driven Federated Learning-Based Decentralized Indoor Localization via Mobile Crowdsourcing

引用

IEEE SENSORS JOURNAL 2020年第19期20卷 11556-11565页

作者： Li, Wei Zhang, Cheng Tanaka, Yoshiaki Waseda Univ Dept Comp Sci & Commun Engn Tokyo 1698555 Japan Waseda Univ Dept Commun & Comp Engn Tokyo 1698555 Japan

Received signal strength (RSS) fingerprintbased indoor localization has received increasing popularity over the past decades. However, it suffers from the high calibration effort for fingerprint collection. In this paper, a Centralized indooR localizatioNmethod using Pseudo-label (CRNP) is proposed, which employs a small set of labeled data (RSS fingerprint) along with large volumes of unlabeled data (RSS valueswithout coordinates) to reduce theworkload of labeled data collection and improve the indoor localization performance. However, the rich location data is large in quantity and privacy sensitive, which may lead to high network cost (i. e., data transmission cost, data storage cost) and potential privacy leakage for data transmission to the central server. Therefore, a decentralized indoor localization method incorporating CRNP and federated learning is devised, which keeps the location data on local users' devices and improves the shared CRNP model by aggregating users' updates of the model. The experiment results demonstrate that (i) the proposed CRNP enables to improve the indoor localization accuracy by using unlabeled crowdsourced data;(ii) the designed decentralized scheme is robust to different data distribution and is capable to reduce the network cost and prevent users' privacy leakage.

关键词： Feature extraction Data privacy Data communication Servers Data models Sensors Data collection Indoor localization stacked autoencoder pseudo label federated learning

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：