检索结果-内蒙古大学图书馆

Visual saliency detection via invariant feature constrained stacked denoising autoencoder

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第18期82卷 27451-27472页

作者： Ma, Yunpeng Yu, Zhihong Zhou, Yaqin Xu, Chang Yu, Dabing Hohai Univ Key Lab Sensor Networks & Environm Sensing Changzhou 213022 Peoples R China Hohai Univ Jiangsu Key Lab Power Transmiss & Distribut Equipm Changzhou 213022 Peoples R China Hohai Univ Coll Internet Things Engn Changzhou 213022 Peoples R China

Visual saliency detection is usually regarded as an image pre-processing method to predict and locate the position and shape of saliency regions. However, many existing saliency detection methods can only obtain the local or even incorrect position and shape of saliency regions, resulting in incomplete detection and segmentation of the salient target region. In order to solve this problem, a visual saliency detection method based on scale invariant feature and stacked denoising autoencoder is proposed. Firstly, the deep belief network would be pretrained to initialize the parameters of stacked denoising autoencoder network. Secondly, different from traditional features, scale invariant feature is not limited to the size, resolution, and content of original images. At the same time, it can help the network to restore important features of original images more accurately in multi-scale space. So, scale invariant feature is adopted to design the loss function of the network to complete self-training and update the parameters. Finally, the difference between the final reconstructed image obtained by stacked denoising autoencoder and the original is regarded as the final saliency map. In the experiment, we test the performance of the proposed method in both saliency prediction and saliency object segmentation. The experimental results show that the proposed method has good ability in saliency prediction and has the best performance in saliency object segmentation than other comparison saliency prediction methods and saliency object detection methods.

关键词： Visual saliency detection Saliency prediction Saliency object segmentation stacked denoising autoencoder Reconstruction network Scale invariant feature

来源：评论

学校读者我要写书评

暂无评论

HFO Detection in Epilepsy: A stacked denoising autoencoder and Sample Weight Adjusting Factors-Based Method

引用

IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING 2021年 29卷 1965-1976页

作者： Wu, Min Qin, Hongzhen Wan, Xiongbo Du, Yuxiao China Univ Geosci Sch Automat Wuhan 430074 Peoples R China Hubei Key Lab Adv Control & Intelligent Automat C Wuhan 430074 Peoples R China Minist Educ Engn Res Ctr Intelligent Technol Geoexplorat Wuhan 430074 Peoples R China Guangdong Univ Technol Sch Automat Guangzhou 510006 Guangdong Peoples R China

High-frequency oscillations (HFOs) recorded by the intracranial electroencephalography (iEEG) are the promising biomarkers of epileptogenic zones. Accurate detection of HFOs is the key to pre-operative assessment for epilepsy. Due to the subjective bias caused by manual features and the class imbalance between HFOs and false HFOs, it is difficult to obtain satisfactory detection performance by the existing methods. To solve these problems, we put forward a novel method to accurately detect HFOs based on the stacked denoising autoencoder (SDAE) and the ensemble classifier with sample weight adjusting factors. First, the adjustable threshold of Hilbert envelopes is proposed to isolate the events of interest (EoIs) from background activities. Then, the SDAE network is utilized to automatically extract features of EoIs in the time-frequency domain. Finally, the AdaBoost-based support vector machine ensemble classifier with sample weight adjusting factors is devised to separate HFOs from EoIs by using the extracted features. These adjusting factors are used to solve the class imbalance problem by adjusting sample weights when learning the base classifiers. Our HFO detection method is evaluated by using clinical iEEG data recorded from 20 patients with medically refractory epilepsy. The experimental results show that our detection method outperforms some existing methods in terms of sensitivity and false discovery rate. In addition, the HFOs detected by our method are effective for localizing seizure onset zones.

关键词： Feature extraction Hafnium oxide Time-frequency analysis Support vector machines Sensitivity Oscillators Training Epilepsy high-frequency oscillations stacked denoising autoencoder ensemble classifier sample weight adjusting factors

来源：评论

学校读者我要写书评

暂无评论

Research of 3D Face Recognition Algorithm Based on Deep Learning stacked denoising autoencoder Theory 8

Research of 3D Face Recognition Algorithm Based on Deep Lear...

引用

8th IEEE International Conference on Communication Software and Networks (ICCSN)

作者： Zhang, Jian Hou, Zhenjie Wu, Zhuoran Chen, Yongkang Li, Weikang Changzhou Univ Coll Informat Math & Phys Changzhou Peoples R China

ISBN: (纸本)9781509017812

This electronic Due to the fact that the 3D face depth data have more information, the 3D face recognition is attracting more and more attention in the machine learning area. Firstly, this paper selects 30 feature points from the 113 feature points of Candide-3 face model to characterize face, which improves the efficiency of recognition algorithm obviously without affecting the recognition accuracy. With the significant advantage of the characterization of essential features by learning a deep nonlinear network, this paper presents a stacked denoising autoencoder algorithm model based on deep learning which improves neural networks model. This algorithm conducts the unsupervised preliminary training of face depth data and the supervised training to fine-tuning the network which is better than neural network's random initialization. The experiment indicates that compared with real face data, the reconstruction face model has a small matching error by using SDAE algorithm and it achieves an excellent face recognition effect.

关键词： 3D face depth data deep learning neural networks stacked denoising autoencoder unsupervised preliminary training

来源：评论

学校读者我要写书评

暂无评论

A Robust Acoustic Feature Extraction Approach Based On stacked denoising autoencoder 1

A Robust Acoustic Feature Extraction Approach Based On Stack...

引用

IEEE First International Conference on Multimedia Big Data

作者： Liu, J. H. Zheng, W. Q. Zou, Y. X. Peking Univ ADSPLAB ELIP Sch Elect & Comp Engn Shenzhen Peoples R China

ISBN: (纸本)9781479986880

Acoustic feature extraction (AFE) is considered as one of the most challenging techniques for speech applications since the adverse environment noises always cause significant variation on the extracted acoustic features. In this paper, we propose a systematical AFE approach which based on stacked denoising autoencoder (SDAE) aiming at extracting acoustic features automatically. denoising autoencoder (DAE), which is trained to reconstruct a clean "repaired" input from a corrupted version of it, works as the basic building block to form SDAE. Besides, the training set with clean and noisy speech ensures the SDAE has much powerful ability to extract the robust features under different noise conditions. Considering the speaker classification task using features extracted by the proposed approach for evaluation, intensive experiments have been conducted on TIMIT and NIST SRE 2004 to show SDAE with 3 hidden layers (3L-SDAE) gives better performance than shallow layers. The results also show that the features extracted by 3L-SDAE performs better than MFCC features when SNR is lower than 6dB and act more robustly when SNR decreases. What's more, for different types of noises at SNR of 0dB, the accuracy of speaker classification using 3L-SDAE features is higher than about 84% while MFCC features is lower than 77%.

关键词： robust acoustic feature extraction stacked denoising autoencoder noisy environment speaker classification

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis of Multiple Combined Defects in Bearings Using a stacked denoising autoencoder

Fault Diagnosis of Multiple Combined Defects in Bearings Usi...

引用

International Conference on Computer, Communication and Computational Sciences (IC4S)

作者： Duong, Bach Phi Kim, Jong-Myon Univ Ulsan Sch Elect Engn Ulsan 680749 South Korea

ISBN: (纸本)9789811303418;9789811303401

Bearing fault diagnosis is an inevitable process in the maintenance of rotary machines. Multiple combined defects in bearings are more difficult to detect because of the complexity in components of acquired acoustic emission signals. To address this issue, this paper proposes a deep learning method that can effectively detect the combined defects in bearings. The proposed deep neural network (DNN) is based on the stacked denoising autoencoder (SDAE). In this study, the proposed method trains single faulty data while it efficiently classifies multiple combined faults. Experimental results indicate that the proposed method achieves an average accuracy of 91% although it only has single mode fault information.

关键词： Bearing fault diagnosis Combined fault classification Deep neural networks stacked denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

Detecting Web Attacks using stacked denoising autoencoder and Ensemble Learning Methods 19

Detecting Web Attacks using Stacked Denoising Autoencoder an...

引用

10th International Symposium on Information and Communication Technology (SoICT)

作者： Truong, Dung Tran, Due Nguyen, Lam Mac, Hieu Tran, Hai Anh Bui, Tung HUST Bach Khoa Cybersecur Ctr Hanoi Vietnam

ISBN: (纸本)9781450372459

Web-based anomalies remains a serious security threat on the Internet. This paper proposes the use of Sum Rule and Xgboost to combine the outputs related to various stacked denoising autoencoders (SDAEs) in order to detect abnormal HTTP queries. Sum Rule and Xgboost inherit the distinct advantage of SDAE that does not require handcrafted features to be extracted. Furthermore, these methods can cope with the changing web vulnerabilities, where malicious code is added into different parts of the request header and body. Experiments were carried out on the DVWA dataset and the dataset that obtained from a real-world application. Sum Rule and Xgboost demonstrate to achieve higher F1-score as compared to the state-of-the-art Regularized Deep autoencoders, Isolation Forest, C4.5 decision tree and Long Short-term Memory network.

关键词： Anomaly Detection stacked denoising autoencoder Web attack detection Sum Rule Xgboost

来源：评论

学校读者我要写书评

暂无评论

An integrated scheme based on stacked denoising autoencoder and deep feature fusion for fault diagnosis of helicopter planetary gear train 10

An integrated scheme based on stacked denoising autoencoder ...

引用

10th IEEE Prognostics and System Health Management Conference (PHM-Qingdao)

作者： Sun, Canfei Wang, Youren Cao, Liang Nanjing Univ Aeronaut & Astronaut Coll Automat Engn Aviat Key Lab Sci & Technol Fault Diag & Hlth Man Nanjing Peoples R China Nanjing Univ Aeronaut & Astronaut Coll Automat Engn Nanjing Peoples R China Shanghai Aero Measurement & Control Technol Res I Res Ctr Shanghai Peoples R China

ISBN: (纸本)9781728108612

Planetary gear train plays a critical role in the helicopter transmission system. Fault diagnosis of the planetary gear train has long been a research topic in the health monitoring and maintenance of the helicopter. However, due to the intricate kinematics and severe operating conditions, the vibration signals of the planetary gear train are highly complex, dominated by various coupling disturbances and ambient noise. Aiming to address these challenges, an integrated health state identification scheme (IHSIS) is proposed for fault diagnosis of helicopter planetary gear train. Firstly, IHSIS utilizes multiple sensors to collecting vibration signals for sufficient fault information under multi-mode faults and fluctuating working conditions. Secondly, stacked denoising automatic encoder (SDAE) is adopted to explore deep features from frequency spectrum of each individual sensor. Finally, deep features derived from measured signals of all sensors are fused together and input to a softmax classifier for fault diagnosis. The superiority of IHSIS is validated by analyzing results of a few comparative experiments conducted on a helicopter main-rotor testbed with intentionally created localized gear faults of a planetary gear train under different noise levels.

关键词： Helicopter Planetary gear train Fault diagnosis stacked denoising autoencoder Feature fusion

来源：评论

学校读者我要写书评

暂无评论

Using stacked denoising autoencoder for the Student Dropout Prediction 19

Using Stacked Denoising Autoencoder for the Student Dropout ...

引用

19th IEEE International Symposium on Multimedia (ISM)

作者： Kuo, Jong Yih Pan, Chia Wei Lei, Baiying Natl Taipei Univ Technol Comp Sci & Informat Engn Taipei Taiwan Shenzhen Univ Guangdong Key Lab Biomed Measurements & Ultrasoun Natl Reg Key Technol Engn Lab Med Ultrasound Sch Biomed EngnHlth Sci Ctr Shenzhen 518060 Peoples R China

ISBN: (纸本)9781538629376

This paper extended stacked denoising autoencoder to build a deep neural network which initialized the weight of neural network through the encoder's weight and used Dropout to reduce the error rate in fine-tuning stage. The neural network used the information of students in recent years as input data to train neural network, and predicted the possibility of dropout on the students during the semester. The prediction result can be used to counseling and warning students which be dropout likely and then reduced the unnecessary resource of school.

关键词： Neural Network Deep Learning Unsupervised Feature Learning stacked denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

A Robust WiFi Localization Algorithm Using Data Augmentation and stacked denoising autoencoder 35

A Robust WiFi Localization Algorithm Using Data Augmentation...

引用

35th Chinese Control and Decision Conference (CCDC)

作者： Zhuang, Changsheng Zhang, Dengyin Nanjing Univ Posts & Telecommun Coll Internet Things Nanjing Peoples R China

ISBN: (纸本)9798350334722

based fingerprint localization technology has become one of the most practical methods for localizing mobile users due to its non-intrusive nature, low cost and no additional equipment required. However, the fluctuation of WiFi signal seriously affects the accuracy of WiFi fingerprint localization. To address this problem, this paper proposes a solution using data augmentation combined with stacked denoising autoencoder (SDAE). Data augmentation can facilitate the neural network to learn the mapping relationship between the fluctuating WiFi signals and coordinates. And the SDAE can obtain a robust and time-independent feature from the dynamic WiFi signal. A convolutional neural network is also used to build a floor classification model to determine the height, and a multilayer perceptron (MLP) is used to build a regression model to determine the relative coordinates. Experimental results on public datasets show that the method improves system robustness and localization accuracy.

关键词： indoor positioning data augmentation stacked denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis for Hydraulic Servo System: A stacked denoising autoencoder Method based on Self-Learning of Robustness Features

Fault Diagnosis for Hydraulic Servo System: A Stacked Denois...

引用

Chinese Automation Congress (CAC)

作者： Wang, Zhenya Fan, Jiaxuan Huang, Hu Han, Te China Acad Launch Vehicle Technol Res & Dev Dept Beijing Peoples R China

ISBN: (纸本)9781728176871

The fault diagnosis of hydraulic servo system attracts more attention in complex system prognostics and health management. As the precondition of most fault diagnosis methods, feature extraction could efficiently draw information from the initial data and supply more evidence to the following results. However, traditional time-frequency analysis largely depend on artificial selection and optimization, which are generally limited by the quality of input data and working environment. Thus this paper proposes a stacked deep learning based model to represent robust feature information in terms of the advantage of cognitive computing and pattern classification theory, which is shown to be suitable for certain applications with inevitable ambient noise and working condition fluctuations. To effectively realize feature reconstruction, a stacked denoising autoencoder (SDA) in which multiple encoders are established and trained is used. The employed deep neural network is trained layer by layer to extract high-level features, where the sparsity representation is applied to map the original inputs to better high-level features. Considering better robustness of the learnt features to avoid external interferences, the original input neural parameters of each autoencoder are denoised by randomly assigning some units to be zero. The modified denoising autoencoders are then stacked to initialize the deep hierarchical architecture instead of the original. High-level feature representations of the monitoring data samples are obtained based on unsupervised self-learning, and are set as the inputs of a top fault pattern classifier for final training, followed by a fine-tuning process. Validation data arc collected to facilitate the comparison and evaluation of the fault diagnosis results of the SDA models, of which the denoising proportion is different for each. Experiments show an obvious advantage of the SDA model based on the self-learning of the robustness features for fault patte

关键词： stacked denoising autoencoder deep learning hydraulic servo system fault diagnosis

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：