检索结果-内蒙古大学图书馆

Building Extraction Based on an Optimized stacked sparse autoencoder of Structure and Training Samples Using LIDAR DSM and Optical Images

引用

SENSORS 2017年第9期17卷 1957-1957页

作者： Yan, Yiming Tan, Zhichao Su, Nan Zhao, Chunhui Harbin Engn Univ Dept Informat Engn Harbin 150001 Heilongjiang Peoples R China

In this paper, a building extraction method is proposed based on a stacked sparse autoencoder with an optimized structure and training samples. Building extraction plays an important role in urban construction and planning. However, some negative effects will reduce the accuracy of extraction, such as exceeding resolution, bad correction and terrain influence. Data collected by multiple sensors, as light detection and ranging (LIDAR), optical sensor etc., are used to improve the extraction. Using digital surface model (DSM) obtained from LIDAR data and optical images, traditional method can improve the extraction effect to a certain extent, but there are some defects in feature extraction. Since stacked sparse autoencoder (SSAE) neural network can learn the essential characteristics of the data in depth, SSAE was employed to extract buildings from the combined DSM data and optical image. A better setting strategy of SSAE network structure is given, and an idea of setting the number and proportion of training samples for better training of SSAE was presented. The optical data and DSM were combined as input of the optimized SSAE, and after training by an optimized samples, the appropriate network structure can extract buildings with great accuracy and has good robustness.

关键词： stacked sparse autoencoder LIDAR DSM remote sensing image building extraction

来源：评论

学校读者我要写书评

暂无评论

Weighted time series fault diagnosis based on a stacked sparse autoencoder

引用

JOURNAL OF CHEMOMETRICS 2017年第9期31卷 2912,2-16-2912,2-16页

作者： Lv, Feiya Wen, Chenglin Liu, Meiqin Bao, Zhejing Zhejiang Univ Coll Elect Engn Hangzhou 310027 Zhejiang Peoples R China Hangzhou Dianzi Univ Sch Automat Hangzhou 310018 Zhejiang Peoples R China

Most statistical analysis technologies use detection thresholds for fault diagnosis, which often cannot effectively characterize some specific faults in a statistical manner. However, the details and small changes in the faults can be exploited by deep learning-based feature representation. In this paper, we present a weighted time series fault diagnosis method to learn the deep correlations of faults and reduce the loss of fault information. Our model includes 2 key novel properties: (1) It can learn high-level abstract features of faults and the underlying fault patterns, which is particularly efficient for detecting incipient faults;(2) a mathematical framework of stacked sparse autoencoder-based fault diagnosis, with capabilities of multiple nonlinear mapping and complex function approximation, is presented. The monitoring performance was compared with multivariate statistical methods and conventional artificial intelligence methods on the Tennessee Eastman process data set, which is a well-known chemical industrial benchmark. The experimental results showed its performance gain over existing methods, especially for incipient faults that are difficult to detect with traditional technologies. As the details and small changes in the faults can be exploited by deep learning-based feature representation, we present a weighted time series fault diagnosis method. Our model includes 2 key novel properties: (1) It can learn high-level abstract features of faults and the underlying fault patterns, which is particularly efficient for detecting incipient faults;(2) a mathematical framework of stacked sparse auto-encoder (SSAE) -based fault diagnosis, with capabilities of multiple nonlinear mapping and complex function approximation, is presented.

关键词： fault diagnosis feature representation incipient fault stacked sparse autoencoder weighted time series

来源：评论

学校读者我要写书评

暂无评论

stacked sparse autoencoder (SSAE) for Nuclei Detection on Breast Cancer Histopathology Images

引用

IEEE TRANSACTIONS ON MEDICAL IMAGING 2016年第1期35卷 119-130页

作者： Xu, Jun Xiang, Lei Liu, Qingshan Gilmore, Hannah Wu, Jianzhong Tang, Jinghai Madabhushi, Anant Nanjing Univ Informat Sci & Technol Jiangsu Key Lab Big Data Anal Tech Nanjing 210044 Jiangsu Peoples R China Nanjing Univ Informat Sci & Technol CICAEET Nanjing 210044 Jiangsu Peoples R China Case Western Reserve Univ Univ Hosp Case Med Ctr Dept Pathol Anat Cleveland OH 44106 USA Jiangsu Canc Hosp Nanjing 210000 Jiangsu Peoples R China Case Western Reserve Univ Dept Biomed Engn Cleveland OH 44106 USA

Automated nuclear detection is a critical step for a number of computer assisted pathology related image analysis algorithms such as for automated grading of breast cancer tissue specimens. The Nottingham Histologic Score system is highly correlated with the shape and appearance of breast cancer nuclei in histopathological images. However, automated nucleus detection is complicated by 1) the large number of nuclei and the size of high resolution digitized pathology images, and 2) the variability in size, shape, appearance, and texture of the individual nuclei. Recently there has been interest in the application of "Deep Learning" strategies for classification and analysis of big image data. Histopathology, given its size and complexity, represents an excellent use case for application of deep learning strategies. In this paper, a stacked sparse autoencoder (SSAE), an instance of a deep learning strategy, is presented for efficient nuclei detection on high-resolution histopathological images of breast cancer. The SSAE learns high-level features from just pixel intensities alone in order to identify distinguishing features of nuclei. A sliding window operation is applied to each image in order to represent image patches via high-level features obtained via the auto-encoder, which are then subsequently fed to a classifier which categorizes each image patch as nuclear or non-nuclear. Across a cohort of 500 histopathological images (2200 2200) and approximately 3500 manually segmented individual nuclei serving as the groundtruth, SSAE was shown to have an improved F-measure 84.49% and an average area under Precision-Recall curve (AveP) 78.83%. The SSAE approach also out-performed nine other state of the art nuclear detection strategies.

关键词： Terms-Automated nuclei detection breast cancer histopathology feature representation learning stacked sparse autoencoder digital pathology deep learning

来源：评论

学校读者我要写书评

暂无评论

A stacked sparse autoencoder based Architecture for Punjabi and English Spoken Language Classification using MFCC features 3

A Stacked Sparse Autoencoder based Architecture for Punjabi ...

引用

3rd International Conference on Computing for Sustainable Global Development (INDIACom)

作者： Arora, Vaibhav Sood, Pulkit Keshari, Kumar Utkarsh Paxcel Technol Pvt Ltd Phase 8 Mohali India

ISBN: (纸本)9789380544199

Spoken language classification is an important task in speech processing. It can serve as a preprocessing step in the pipeline of automated understanding of the semantics of human speech. The paper proposes a sparse autoencoder based architecture for Punjabi and English spoken language Classification. A number of shallow architectures namely Soft-max classifier, SVM and deep architectures namely Artificial Neural Networks, SVM with sparse Auto encoder and Softmax with sparse auto encoder (with and without fine tuning) have been compared on the same task. For this purpose noisy speech samples of 1 second using frame based MFCC coefficients of speech samples have been considered. Comparison of Principal Component Analysis and sparse autoencoder based features has also been done on the dataset.

关键词： ANN Deep learning English MFCC Spoken Language Classification PCA Punjabi stacked sparse autoencoder SVM

来源：评论

学校读者我要写书评

暂无评论

Nondestructive evaluation of bonding quality of dual-layer coatings based on the multi-feature ultrasonic method

引用

APPLIED ACOUSTICS 2024年 224卷

作者： Fan, Shaorui Yuan, Maodan Xu, Jianlin Song, Yongfeng Chen, Yan Ji, Xuanrong Guangdong Univ Technol State Key Lab Precis Elect Mfg Technol & Equipment Guangzhou 510004 Peoples R China

Ultrasound has been extensively utilized to evaluate the bonding quality of coatings. However, current ultrasonic methods based on single temporal or spectral feature cannot accurately characterize the bonding quality within industrial coatings, especially for potential debonding at different layers. This paper proposed an ultrasonic method with multiple temporal and spectral features to evaluate the bonding condition of dual-layer coatings. Ultrasonic features were automatically extracted based on stacked sparse autoencoder (SSAE) to compare with the conventional selected features. Firstly, numerical simulations were carried out to analyze the variation of ultrasonic signals with different stiffnesses at topcoat and primer interfaces. Two temporal and three spectral features were manually extracted and show high sensitivity to different bonding conditions of the two interfaces. Meanwhile, a SSAE network was designed to automatically extract ultrasonic features. The high correlation between the manually and automatically extracted features demonstrates its effectiveness of automatic feature extraction via SSAE. Then, a 50 MHz ultrasonic pulse-echo system was applied to collect signals from 115 coating samples of laptop shell. Four sets of ultrasonic features were extracted via manual method and SSAE networks. Principal components analysis was then employed to reduce the feature space and support vector machine was applied to distinguish topcoat debonding and primer debonding from the intact coatings. The results show that the feature set including 64 temporal and spectral features extracted by SSAE exhibit the best classification with an accuracy of 95.652 %. This proposed multi-feature ultrasonic method can accurately assess the bonding quality of different interfaces in the multi-layer coatings.

关键词： Dual -layer coating Topcoat debonding Primer debonding Ultrasonic features stacked sparse autoencoder Support vector machine

来源：评论

学校读者我要写书评

暂无评论

A Time Series Intrusion Detection Method Based on SSAE,TCN and Bi-LSTM

引用

Computers, Materials & Continua 2024年第1期78卷 845-871页

作者： Zhenxiang He Xunxi Wang Chunwei Li School of Cyberspace Security Gansu University of Political Science and LawLanzhou730000China

In the fast-evolving landscape of digital networks,the incidence of network intrusions has escalated ***,the crucial role of time series data in intrusion detection remains largely underappreciated,with most systems failing to capture the time-bound nuances of network *** leads to compromised detection accuracy and overlooked temporal *** this gap,we introduce a novel SSAE-TCN-BiLSTM(STL)model that integrates time series analysis,significantly enhancing detection *** approach reduces feature dimensionalitywith a stacked sparse autoencoder(SSAE)and extracts temporally relevant features through a Temporal Convolutional Network(TCN)and Bidirectional Long Short-term Memory Network(Bi-LSTM).By meticulously adjusting time steps,we underscore the significance of temporal data in bolstering detection *** the UNSW-NB15 dataset,ourmodel achieved an F1-score of 99.49%,Accuracy of 99.43%,Precision of 99.38%,Recall of 99.60%,and an inference time of 4.24 *** the CICDS2017 dataset,we recorded an F1-score of 99.53%,Accuracy of 99.62%,Precision of 99.27%,Recall of 99.79%,and an inference time of 5.72 *** findings not only confirm the STL model’s superior performance but also its operational efficiency,underpinning its significance in real-world cybersecurity scenarios where rapid response is *** contribution represents a significant advance in cybersecurity,proposing a model that excels in accuracy and adaptability to the dynamic nature of network traffic,setting a new benchmark for intrusion detection systems.

关键词： Network intrusion detection bidirectional long short-term memory network time series stacked sparse autoencoder temporal convolutional network time steps

来源：评论

学校读者我要写书评

暂无评论

Optimizing Big Data Retrieval and Job Scheduling Using Deep Learning Approaches

引用

Computer Modeling in Engineering & Sciences 2023年第2期134卷 783-815页

作者： Bao Rong Chang Hsiu-Fen Tsai Yu-Chieh Lin Department of Computer Science and Information Engineering National University of KaohsiungKaohsiungTaiwan Department of Fragrance and Cosmetic Science Kaohsiung Medical UniversityKaohsiungTaiwan

Big data analytics in business intelligence do not provide effective data retrieval methods and job scheduling that will cause execution inefficiency and low system *** paper aims to enhance the capability of data retrieval and job scheduling to speed up the operation of big data analytics to overcome inefficiency and low throughput ***,integrating stacked sparse autoencoder and Elasticsearch indexing explored fast data searching and distributed indexing,which reduces the search scope of the database and dramatically speeds up data ***,exploiting a deep neural network to predict the approximate execution time of a job gives prioritized job scheduling based on the shortest job first,which reduces the average waiting time of job *** a result,the proposed data retrieval approach outperforms the previous method using a deep autoencoder and Solr indexing,significantly improving the speed of data retrieval up to 53%and increasing system throughput by 53%.On the other hand,the proposed job scheduling algorithmdefeats both first-in-first-out andmemory-sensitive heterogeneous early finish time scheduling algorithms,effectively shortening the average waiting time up to 5%and average weighted turnaround time by 19%,respectively.

关键词： stacked sparse autoencoder Elasticsearch distributed indexing data retrieval deep neural network job scheduling

来源：评论

学校读者我要写书评

暂无评论

Deep network approach with stacked sparse autoencoders in detection of DDoS attacks on SDN-based VANET

引用

IET COMMUNICATIONS 2020年第22期14卷 4089-4100页

作者： Polat, Huseyin Turkoglu, Muammer Polat, Onur Gazi Univ Fac Technol Dept Comp Engn TR-06500 Ankara Turkey Bingol Univ Dept Comp Engn TR-12400 Bingol Turkey

Software-defined network (SDN)-based vehicular ad hoc network (VANET) is an outstanding technology for smart transportation as it increases traffic safety, efficiency, comfort, and manageability. However, despite all its benefits and good performance, SDN-based VANET is vulnerable to attack threats such as distributed denial of service (DDoS). When SDN-based VANET systems are exposed to DDoS attacks, this may affect traffic safety, causing traffic accidents and deaths. Therefore, the relevant security threats need to be addressed before integrating the SDN-based VANETs into smart transportation systems. In this study, the stacked sparse autoencoder (SSAE) + Softmax classifier deep network model is proposed to detect DDoS attacks targeting SDN-based VANETs. The features in the dataset obtained from the SDN-based VANET were reduced dimensionally utilising SSAE, and the most significant features were obtained. Then, these features were used as input into the Softmax classifier. According to the experimental results, the best accuracy scores were calculated as 96.9% using the four-layer SSAE + Softmax classifier deep network model proposed. When compared, the results demonstrate the SSAE + Softmax classifier deep network model proposed can obtain better results in the classification of DDoS attacks and is more successful than the other machine learning classifiers.

关键词： computer network security road safety road traffic neural nets vehicular ad hoc networks road accidents intelligent transportation systems software defined networking traffic safety SDN‐ based VANET systems DDoS attacks stacked sparse autoencoder four‐ layer SSAE plus Softmax classifier deep network model software‐ defined network‐ based vehicular ad hoc network deep network approach distributed denial of service attacks smart transportation systems traffic accidents

来源：评论

学校读者我要写书评

暂无评论

DSSAE-BBOA: deep learning-based weather big data analysis and visualization

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2021年第18期80卷 27471-27493页

作者： Rao, Madhukar G. Dharavath, Ramesh Indian Sch Mines Indian Inst Technol Dept Comp Sci & Engn Dhanbad 826004 Jharkhand India

The weather forecasting process is used to predict the future atmospheric condition of a specified location. The evolution of the big data era gives the chances to significantly increase the prediction accuracy of weather conditions. In this paper, a deep learning-based stacked sparse autoencoder (DSSAE) has been proposed for predicting the weather condition of a particular area. This model requires a pre-processing approach to obtain essential data from big weather data and increase the prediction model's speed. For this, the principal component analysis (PCA) is utilized to reduce dimensionality and extraction of features with more significant variance. Also, it integrates the feature selection algorithm based on Binary Butterfly Optimization Algorithm (BBOA) along with a deep stack autoencoder to improve prediction accuracy. The proposed model is validated using the weather data taken from the division of weather underground for short term and long term weather prediction. The simulation consequences illustrate that the proposed model overtakes the existing models in terms of computation time, accuracy and error rate.

关键词： Weather forecasting Feature selection Optimization stacked sparse autoencoder

来源：评论

学校读者我要写书评

暂无评论

Infrared and Visible Image Fusion Based on Deep Decomposition Network and Saliency Analysis

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2021年 24卷 3314-3326页

作者： Jian, Lihua Rayhana, Rakiba Ma, Ling Wu, Shaowu Liu, Zheng Jiang, Huiqin Zhengzhou Univ Sch Informat Engn Zhengzhou 450001 Henan Peoples R China Univ British Columbia Sch Engn Kelowna BC V1V 1V7 Canada Wuhan Univ Sch Comp Sci Wuhan 430072 Hubei Peoples R China

Traditional image fusion focuses on selecting an effective decomposition approach to extract representative features from the source image and attempts to find appropriate fusion rules to merge extracted features respectively. However, the existing image decomposition tools are mostly based on kernels or global energy-optimized functions limiting the performance of the wide range of image contents. This paper proposes a novel infrared and visible image fusion method based on deep decomposition network and saliency analysis (named DDNSA). First, the modified residual dense network (MRDN) is trained with a publicly available dataset to learn the decomposition process. Second, the structure and texture features of source images are separated by the trained decomposition network. Then, according to the characteristics of the above features, we construct the combination of local and global saliency maps by using stacked sparse autoencoder and visual saliency mechanism to fuse the structural features. Besides, we propose a bi-direction edge-strength fusion strategy for merging the texture features. Finally, the resultant image is reconstructed by combining the fused structure and texture features. The experimental results confirm that our proposed method outperforms the state-of-the-art methods in both visual perception and objective evaluation.

关键词： Feature extraction Image fusion Task analysis Fuses Visualization Image edge detection Data mining Bi-direction edge-strength deep decomposition network image fusion stacked sparse autoencoder visual saliency mechanism

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：