Journal articles: 'Convolutional Deep Belief Networks'

1

Chu, Joseph Lin, and Adam Krzyźak. "The Recognition Of Partially Occluded Objects with Support Vector Machines, Convolutional Neural Networks and Deep Belief Networks." Journal of Artificial Intelligence and Soft Computing Research 4, no. 1 (January 1, 2014): 5–19. http://dx.doi.org/10.2478/jaiscr-2014-0021.

Full text

Abstract:

Abstract Biologically inspired artificial neural networks have been widely used for machine learning tasks such as object recognition. Deep architectures, such as the Convolutional Neural Network, and the Deep Belief Network have recently been implemented successfully for object recognition tasks. We conduct experiments to test the hypothesis that certain primarily generative models such as the Deep Belief Network should perform better on the occluded object recognition task than purely discriminative models such as Convolutional Neural Networks and Support Vector Machines. When the generative models are run in a partially discriminative manner, the data does not support the hypothesis. It is also found that the implementation of Gaussian visible units in a Deep Belief Network trained on occluded image data allows it to also learn to effectively classify non-occluded images

APA, Harvard, Vancouver, ISO, and other styles

2

Guang Huo, Qi Zhang, Yangrui Zhang, Yuanning Liu, Huan Guo, and Wenyu Li. "Multi-Source Heterogeneous Iris Recognition Using Stacked Convolutional Deep Belief Networks-Deep Belief Network Model." Pattern Recognition and Image Analysis 31, no. 1 (January 2021): 81–90. http://dx.doi.org/10.1134/s1054661821010119.

Full text

APA, Harvard, Vancouver, ISO, and other styles

3

Li, Yang, and Chu Li. "Singer Recognition Based on Convolutional Deep Belief Networks." IOP Conference Series: Materials Science and Engineering 435 (November 5, 2018): 012005. http://dx.doi.org/10.1088/1757-899x/435/1/012005.

Full text

APA, Harvard, Vancouver, ISO, and other styles

4

Phan, NhatHai, Xintao Wu, and Dejing Dou. "Preserving differential privacy in convolutional deep belief networks." Machine Learning 106, no. 9-10 (July 13, 2017): 1681–704. http://dx.doi.org/10.1007/s10994-017-5656-2.

Full text

APA, Harvard, Vancouver, ISO, and other styles

5

Tang, Binbin, Xiao Liu, Jie Lei, Mingli Song, Dapeng Tao, Shuifa Sun, and Fangmin Dong. "DeepChart: Combining deep convolutional networks and deep belief networks in chart classification." Signal Processing 124 (July 2016): 156–61. http://dx.doi.org/10.1016/j.sigpro.2015.09.027.

Full text

APA, Harvard, Vancouver, ISO, and other styles

6

Rakhmanenko, I. A., A. A. Shelupanov, and E. Y. Kostyuchenko. "Automatic text-independent speaker verification using convolutional deep belief network." Computer Optics 44, no. 4 (August 2020): 596–605. http://dx.doi.org/10.18287/2412-6179-co-621.

Full text

Abstract:

This paper is devoted to the use of the convolutional deep belief network as a speech feature extractor for automatic text-independent speaker verification. The paper describes the scope and problems of automatic speaker verification systems. Types of modern speaker verification systems and types of speech features used in speaker verification systems are considered. The structure and learning algorithm of convolutional deep belief networks is described. The use of speech features extracted from three layers of a trained convolution deep belief network is proposed. Experimental studies of the proposed features were performed on two speech corpora: own speech corpus including audio recordings of 50 speakers and TIMIT speech corpus including audio recordings of 630 speakers. The accuracy of the proposed features was assessed using different types of classifiers. Direct use of these features did not increase the accuracy compared to the use of traditional spectral speech features, such as mel-frequency cepstral coefficients. However, the use of these features in the classifiers ensemble made it possible to achieve a reduction of the equal error rate to 0.21% on 50-speaker speech corpus and to 0.23% on the TIMIT speech corpus.

APA, Harvard, Vancouver, ISO, and other styles

7

Wang, Haibo, and Xiaojun Bi. "Contractive Slab and Spike Convolutional Deep Belief Network." Neural Processing Letters 49, no. 3 (August 9, 2018): 1697–722. http://dx.doi.org/10.1007/s11063-018-9897-2.

Full text

APA, Harvard, Vancouver, ISO, and other styles

8

Nizami Huseyn, Elcin. "APPLICATION OF DEEP LEARNING TECHNOLOGY IN DISEASE DIAGNOSIS." NATURE AND SCIENCE 04, no. 05 (December 28, 2020): 4–11. http://dx.doi.org/10.36719/2707-1146/05/4-11.

Full text

Abstract:

The rapid development of deep learning technology provides new methods and ideas for assisting physicians in high-precision disease diagnosis. This article reviews the principles and features of deep learning models commonly used in medical disease diagnosis, namely convolutional neural networks, deep belief networks, restricted Boltzmann machines, and recurrent neural network models. Based on several typical diseases, the application of deep learning technology in the field of disease diagnosis is introduced; finally, the future development direction is proposed based on the limitations of current deep learning technology in disease diagnosis. Keywords: Artificial Intelligence; Deep Learning; Disease Diagnosis; Neural Network

APA, Harvard, Vancouver, ISO, and other styles

9

Brosch, Tom, and Roger Tam. "Efficient Training of Convolutional Deep Belief Networks in the Frequency Domain for Application to High-Resolution 2D and 3D Images." Neural Computation 27, no. 1 (January 2015): 211–27. http://dx.doi.org/10.1162/neco_a_00682.

Full text

Abstract:

Deep learning has traditionally been computationally expensive, and advances in training methods have been the prerequisite for improving its efficiency in order to expand its application to a variety of image classification problems. In this letter, we address the problem of efficient training of convolutional deep belief networks by learning the weights in the frequency domain, which eliminates the time-consuming calculation of convolutions. An essential consideration in the design of the algorithm is to minimize the number of transformations to and from frequency space. We have evaluated the running time improvements using two standard benchmark data sets, showing a speed-up of up to 8 times on 2D images and up to 200 times on 3D volumes. Our training algorithm makes training of convolutional deep belief networks on 3D medical images with a resolution of up to 128 × 128 × 128 voxels practical, which opens new directions for using deep learning for medical image analysis.

APA, Harvard, Vancouver, ISO, and other styles

10

Kumar, P. S. Jagadeesh, Yanmin Yuan, Yang Yung, Mingmin Pan, and Wenli Hu. "Robotic simulation of human brain using convolutional deep belief networks." International Journal of Intelligent Machines and Robotics 1, no. 2 (2018): 180. http://dx.doi.org/10.1504/ijimr.2018.094922.

Full text

APA, Harvard, Vancouver, ISO, and other styles

11

Hu, Wenli, Yang Yung, Mingmin Pan, Yanmin Yuan, and P. S. Jagadeesh Kumar. "Robotic simulation of human brain using convolutional deep belief networks." International Journal of Intelligent Machines and Robotics 1, no. 2 (2018): 180. http://dx.doi.org/10.1504/ijimr.2018.10016324.

Full text

APA, Harvard, Vancouver, ISO, and other styles

12

Lee, Honglak, Roger Grosse, Rajesh Ranganath, and Andrew Y. Ng. "Unsupervised learning of hierarchical representations with convolutional deep belief networks." Communications of the ACM 54, no. 10 (October 2011): 95–103. http://dx.doi.org/10.1145/2001269.2001295.

Full text

APA, Harvard, Vancouver, ISO, and other styles

13

Zhang, Ying, Jinchen Ji, and Bo Ma. "Reciprocating compressor fault diagnosis using an optimized convolutional deep belief network." Journal of Vibration and Control 26, no. 17-18 (January 21, 2020): 1538–48. http://dx.doi.org/10.1177/1077546319900115.

Full text

Abstract:

This article proposes an optimized convolutional deep belief network for fault diagnosis of reciprocating compressors. Sparse filtering is first used to compress raw signal into compact time series by refining the most representative information and to reduce the computational burden. Then, the proposed convolutional deep belief network is adopted to learn the unsupervised features of the compressed signal without the need of feature extraction by human effort. To improve the generalization ability of the network, an optimized probabilistic pooling out is proposed in this article to replace the standard one in the pooling layer of the convolutional deep belief network. Finally, the unsupervised features calculated by the optimized convolutional deep belief network are fed as the input of the softmax regression classifier for fault identification. Four types of vibration signals reflecting different operating conditions are collected from the industry to validate the effectiveness of the proposed method. The obtained results demonstrate that the proposed convolutional deep belief network method can achieve a higher classification accuracy rate of up to 91% for fault diagnosis than the traditional methods and accomplish the fault diagnosis of reciprocating compressor effectively.

APA, Harvard, Vancouver, ISO, and other styles

14

Roy, Diptendu Sinha, Cuijuan Shang, Huan Chao Keh, Zaixiu Dong, and Weimin Wen. "An intrusion detection model using improved convolutional deep belief networks for wireless sensor networks." International Journal of Ad Hoc and Ubiquitous Computing 36, no. 1 (2021): 20. http://dx.doi.org/10.1504/ijahuc.2021.10035247.

Full text

APA, Harvard, Vancouver, ISO, and other styles

15

Wen, Weimin, Cuijuan Shang, Zaixiu Dong, Huan Chao Keh, and Diptendu Sinha Roy. "An intrusion detection model using improved convolutional deep belief networks for wireless sensor networks." International Journal of Ad Hoc and Ubiquitous Computing 36, no. 1 (2021): 20. http://dx.doi.org/10.1504/ijahuc.2021.112980.

Full text

APA, Harvard, Vancouver, ISO, and other styles

16

OYEDOTUN, Oyebade, and Adnan KHASHMAN. "Iris nevus diagnosis: convolutional neural network and deep belief network." TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES 25 (2017): 1106–15. http://dx.doi.org/10.3906/elk-1507-190.

Full text

APA, Harvard, Vancouver, ISO, and other styles

17

Amri, A'inur A'fifah, Amelia Ritahani Ismail, and Abdullah Ahmad Zarir. "Convolutional Neural Networks and Deep Belief Networks for Analysing Imbalanced Class Issue in Handwritten Dataset." International Journal on Advanced Science, Engineering and Information Technology 7, no. 6 (December 29, 2017): 2302. http://dx.doi.org/10.18517/ijaseit.7.6.2632.

Full text

APA, Harvard, Vancouver, ISO, and other styles

18

Li, Ziqiang, Xun Cai, Yun Liu, and Bo Zhu. "A Novel Gaussian–Bernoulli Based Convolutional Deep Belief Networks for Image Feature Extraction." Neural Processing Letters 49, no. 1 (March 12, 2018): 305–19. http://dx.doi.org/10.1007/s11063-017-9751-y.

Full text

APA, Harvard, Vancouver, ISO, and other styles

19

Elleuch, Mohamed, and Monji Kherallah. "Boosting of Deep Convolutional Architectures for Arabic Handwriting Recognition." International Journal of Multimedia Data Engineering and Management 10, no. 4 (October 2019): 26–45. http://dx.doi.org/10.4018/ijmdem.2019100102.

Full text

Abstract:

In recent years, deep learning (DL) based systems have become very popular for constructing hierarchical representations from unlabeled data. Moreover, DL approaches have been shown to exceed foregoing state of the art machine learning models in various areas, by pattern recognition being one of the more important cases. This paper applies Convolutional Deep Belief Networks (CDBN) to textual image data containing Arabic handwritten script (AHS) and evaluated it on two different databases characterized by the low/high-dimension property. In addition to the benefits provided by deep networks, the system is protected against over-fitting. Experimentally, the authors demonstrated that the extracted features are effective for handwritten character recognition and show very good performance comparable to the state of the art on handwritten text recognition. Yet using Dropout, the proposed CDBN architectures achieved a promising accuracy rates of 91.55% and 98.86% when applied to IFN/ENIT and HACDB databases, respectively.

APA, Harvard, Vancouver, ISO, and other styles

20

Han, Bing, Xiaohui Yang, Yafeng Ren, and Wanggui Lan. "Comparisons of different deep learning-based methods on fault diagnosis for geared system." International Journal of Distributed Sensor Networks 15, no. 11 (November 2019): 155014771988816. http://dx.doi.org/10.1177/1550147719888169.

Full text

Abstract:

The running state of a geared transmission system affects the stability and reliability of the whole mechanical system. It will greatly reduce the maintenance cost of a mechanical system to identify the faulty state of the geared transmission system. Based on the measured gear fault vibration signals and the deep learning theory, four fault diagnosis neural network models including fast Fourier transform–deep belief network model, wavelet transform–convolutional neural network model, Hilbert-Huang transform–convolutional neural network model, and comprehensive deep neural network model are developed and trained respectively. The results show that the gear fault diagnosis method based on deep learning theory can effectively identify various gear faults under real test conditions. The comprehensive deep neural network model is the most effective one in gear fault recognition.

APA, Harvard, Vancouver, ISO, and other styles

21

Liu, Shuangjie, Jiaqi Xie, Changqing Shen, Xiaofeng Shang, Dong Wang, and Zhongkui Zhu. "Bearing Fault Diagnosis Based on Improved Convolutional Deep Belief Network." Applied Sciences 10, no. 18 (September 12, 2020): 6359. http://dx.doi.org/10.3390/app10186359.

Full text

Abstract:

Mechanical equipment fault detection is critical in industrial applications. Based on vibration signal processing and analysis, the traditional fault diagnosis method relies on rich professional knowledge and artificial experience. Achieving accurate feature extraction and fault diagnosis is difficult using such an approach. To learn the characteristics of features from data automatically, a deep learning method is used. A qualitative and quantitative method for rolling bearing faults diagnosis based on an improved convolutional deep belief network (CDBN) is proposed in this study. First, the original vibration signal is converted to the frequency signal with the fast Fourier transform to improve shallow inputs. Second, the Adam optimizer is introduced to accelerate model training and convergence speed. Finally, the model structure is optimized. A multi-layer feature fusion learning structure is put forward wherein the characterization capabilities of each layer can be fully used to improve the generalization ability of the model. In the experimental verification, a laboratory self-made bearing vibration signal dataset was used. The dataset included healthy bearings, nine single faults of different types and sizes, and three different types of composite fault signals. The results of load 0 kN and 1 kN both indicate that the proposed model has better diagnostic accuracy, with an average of 98.15% and 96.15%, compared with the traditional stacked autoencoder, artificial neural network, deep belief network, and standard CDBN. With improved diagnostic accuracy, the proposed model realizes reliable and effective qualitative and quantitative diagnosis of bearing faults.

APA, Harvard, Vancouver, ISO, and other styles

22

Zhai, Hao, and Yi Zhuang. "Multifocus Image Fusion Method Based on Convolutional Deep Belief Network." IEEJ Transactions on Electrical and Electronic Engineering 16, no. 1 (November 4, 2020): 85–97. http://dx.doi.org/10.1002/tee.23271.

Full text

APA, Harvard, Vancouver, ISO, and other styles

23

Sarkar, Kamal. "Sentiment Polarity Detection in Bengali Tweets Using Deep Convolutional Neural Networks." Journal of Intelligent Systems 28, no. 3 (July 26, 2019): 377–86. http://dx.doi.org/10.1515/jisys-2017-0418.

Full text

Abstract:

Abstract Sentiment polarity detection is one of the most popular sentiment analysis tasks. Sentiment polarity detection in tweets is a more difficult task than sentiment polarity detection in review documents, because tweets are relatively short and they contain limited contextual information. Although the amount of blog posts, tweets and comments in Indian languages is rapidly increasing on the web, research on sentiment analysis in Indian languages is at the early stage. In this paper, we present an approach that classifies the sentiment polarity of Bengali tweets using deep neural networks which consist of one convolutional layer, one hidden layer and one output layer, which is a soft-max layer. Our proposed approach has been tested on the Bengali tweet dataset released for Sentiment Analysis in Indian Languages contest 2015. We have compared the performance of our proposed convolutional neural networks (CNN)-based model with a sentiment polarity detection model that uses deep belief networks (DBN). Our experiments reveal that the performance of our proposed CNN-based system is better than our implemented DBN-based system and some existing Bengali sentiment polarity detection systems.

APA, Harvard, Vancouver, ISO, and other styles

24

Zhong, P., Z. Q. Gong, and C. Schönlieb. "A DIVERSIFIED DEEP BELIEF NETWORK FOR HYPERSPECTRAL IMAGE CLASSIFICATION." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLI-B7 (June 21, 2016): 443–49. http://dx.doi.org/10.5194/isprsarchives-xli-b7-443-2016.

Full text

Abstract:

In recent years, researches in remote sensing demonstrated that deep architectures with multiple layers can potentially extract abstract and invariant features for better hyperspectral image classification. Since the usual real-world hyperspectral image classification task cannot provide enough training samples for a supervised deep model, such as convolutional neural networks (CNNs), this work turns to investigate the deep belief networks (DBNs), which allow unsupervised training. The DBN trained over limited training samples usually has many “dead” (never responding) or “potential over-tolerant” (always responding) latent factors (neurons), which decrease the DBN’s description ability and thus finally decrease the hyperspectral image classification performance. This work proposes a new diversified DBN through introducing a diversity promoting prior over the latent factors during the DBN pre-training and fine-tuning procedures. The diversity promoting prior in the training procedures will encourage the latent factors to be uncorrelated, such that each latent factor focuses on modelling unique information, and all factors will be summed up to capture a large proportion of information and thus increase description ability and classification performance of the diversified DBNs. The proposed method was evaluated over the well-known real-world hyperspectral image dataset. The experiments demonstrate that the diversified DBNs can obtain much better results than original DBNs and comparable or even better performances compared with other recent hyperspectral image classification methods.

APA, Harvard, Vancouver, ISO, and other styles

25

Zhong, P., Z. Q. Gong, and C. Schönlieb. "A DIVERSIFIED DEEP BELIEF NETWORK FOR HYPERSPECTRAL IMAGE CLASSIFICATION." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLI-B7 (June 21, 2016): 443–49. http://dx.doi.org/10.5194/isprs-archives-xli-b7-443-2016.

Full text

Abstract:

In recent years, researches in remote sensing demonstrated that deep architectures with multiple layers can potentially extract abstract and invariant features for better hyperspectral image classification. Since the usual real-world hyperspectral image classification task cannot provide enough training samples for a supervised deep model, such as convolutional neural networks (CNNs), this work turns to investigate the deep belief networks (DBNs), which allow unsupervised training. The DBN trained over limited training samples usually has many “dead” (never responding) or “potential over-tolerant” (always responding) latent factors (neurons), which decrease the DBN’s description ability and thus finally decrease the hyperspectral image classification performance. This work proposes a new diversified DBN through introducing a diversity promoting prior over the latent factors during the DBN pre-training and fine-tuning procedures. The diversity promoting prior in the training procedures will encourage the latent factors to be uncorrelated, such that each latent factor focuses on modelling unique information, and all factors will be summed up to capture a large proportion of information and thus increase description ability and classification performance of the diversified DBNs. The proposed method was evaluated over the well-known real-world hyperspectral image dataset. The experiments demonstrate that the diversified DBNs can obtain much better results than original DBNs and comparable or even better performances compared with other recent hyperspectral image classification methods.

APA, Harvard, Vancouver, ISO, and other styles

26

Zhong, Bineng, Shengnan Pan, Hongbo Zhang, Tian Wang, Jixiang Du, Duansheng Chen, and Liujuan Cao. "Convolutional Deep Belief Networks for Single-Cell/Object Tracking in Computational Biology and Computer Vision." BioMed Research International 2016 (2016): 1–14. http://dx.doi.org/10.1155/2016/9406259.

Full text

Abstract:

In this paper, we propose deep architecture to dynamically learn the most discriminative features from data for both single-cell and object tracking in computational biology and computer vision. Firstly, the discriminative features are automatically learned via a convolutional deep belief network (CDBN). Secondly, we design a simple yet effective method to transfer features learned from CDBNs on the source tasks for generic purpose to the object tracking tasks using only limited amount of training data. Finally, to alleviate the tracker drifting problem caused by model updating, we jointly consider three different types of positive samples. Extensive experiments validate the robustness and effectiveness of the proposed method.

APA, Harvard, Vancouver, ISO, and other styles

27

Sheng, Dali, Jinlian Deng, Wei Zhang, Jie Cai, Weisheng Zhao, and Jiawei Xiang. "A Statistical Image Feature-Based Deep Belief Network for Fire Detection." Complexity 2021 (August 5, 2021): 1–12. http://dx.doi.org/10.1155/2021/5554316.

Full text

Abstract:

Detecting fires is of significance to guarantee the security of buildings and forests. However, it is difficult to fast and accurately detect fire stages in complex environment because of the large variations of the fire features of color, texture, and shapes for flame and smoke images. In this paper, a statistic image feature-based deep belief network (DBN) is proposed for fire detections. Firstly, for each individual image, all the statistic image features extracted from a flame and smoke image in time domain, frequency domain, and time-frequency domain are calculated to construct training and testing samples. Then, the constructed samples are fed into DBN to classify the multiple fire stages in complex environment. DBN can automatically learn fault features layer by layer using restricted Boltzmann machine (RBM). Experiments using the benchmark data of three groups of fire and fire-like images are classified by the present method, and the classification results are also compared with those commonly used support vector machine (SVM) and convolutional deep belief networks (CDBNs) to manifest the superiority of the classification accuracy.

APA, Harvard, Vancouver, ISO, and other styles

28

Li, Chenming, Yongchang Wang, Xiaoke Zhang, Hongmin Gao, Yao Yang, and Jiawei Wang. "Deep Belief Network for Spectral–Spatial Classification of Hyperspectral Remote Sensor Data." Sensors 19, no. 1 (January 8, 2019): 204. http://dx.doi.org/10.3390/s19010204.

Full text

Abstract:

With the development of high-resolution optical sensors, the classification of ground objects combined with multivariate optical sensors is a hot topic at present. Deep learning methods, such as convolutional neural networks, are applied to feature extraction and classification. In this work, a novel deep belief network (DBN) hyperspectral image classification method based on multivariate optical sensors and stacked by restricted Boltzmann machines is proposed. We introduced the DBN framework to classify spatial hyperspectral sensor data on the basis of DBN. Then, the improved method (combination of spectral and spatial information) was verified. After unsupervised pretraining and supervised fine-tuning, the DBN model could successfully learn features. Additionally, we added a logistic regression layer that could classify the hyperspectral images. Moreover, the proposed training method, which fuses spectral and spatial information, was tested over the Indian Pines and Pavia University datasets. The advantages of this method over traditional methods are as follows: (1) the network has deep structure and the ability of feature extraction is stronger than traditional classifiers; (2) experimental results indicate that our method outperforms traditional classification and other deep learning approaches.

APA, Harvard, Vancouver, ISO, and other styles

29

Long, Leijin, Feng He, and Hongjiang Liu. "The use of remote sensing satellite using deep learning in emergency monitoring of high-level landslides disaster in Jinsha River." Journal of Supercomputing 77, no. 8 (January 26, 2021): 8728–44. http://dx.doi.org/10.1007/s11227-020-03604-4.

Full text

Abstract:

AbstractIn order to monitor the high-level landslides frequently occurring in Jinsha River area of Southwest China, and protect the lives and property safety of people in mountainous areas, the data of satellite remote sensing images are combined with various factors inducing landslides and transformed into landslide influence factors, which provides data basis for the establishment of landslide detection model. Then, based on the deep belief networks (DBN) and convolutional neural network (CNN) algorithm, two landslide detection models DBN and convolutional neural-deep belief network (CDN) are established to monitor the high-level landslide in Jinsha River. The influence of the model parameters on the landslide detection results is analyzed, and the accuracy of DBN and CDN models in dealing with actual landslide problems is compared. The results show that when the number of neurons in the DBN is 100, the overall error is the minimum, and when the number of learning layers is 3, the classification error is the minimum. The detection accuracy of DBN and CDN is 97.56% and 97.63%, respectively, which indicates that both DBN and CDN models are feasible in dealing with landslides from remote sensing images. This exploration provides a reference for the study of high-level landslide disasters in Jinsha River.

APA, Harvard, Vancouver, ISO, and other styles

30

Latha, Charlyn Pushpa, and Mohana Priya. "A Review on Deep Learning Algorithms for Speech and Facial Emotion Recognition." APTIKOM Journal on Computer Science and Information Technologies 1, no. 3 (November 1, 2016): 92–108. http://dx.doi.org/10.11591/aptikom.j.csit.118.

Full text

Abstract:

Deep Learning is the recent machine learning technique that tries to model high level abstractions in data by using multiple processing layers with complex structures. It is also known as deep structured learning, hierarchical learning or deep machine learning. The term “deep learning" indicates the method used in training multi-layered neural networks. Deep Learning technique has obtained remarkable success in the field of face recognition with 97.5% accuracy. Facial Electromyogram (FEMG) signals are used to detect the different emotions of humans. Some of the deep learning techniques discussed in this paper are Deep Boltzmann Machine (DBM), Deep Belief Networks (DBN), Convolutional Neural Networks (CNN) and Stacked Auto Encoders respectively. This paper focuses on the review of some of the deep learning techniques used by various researchers which paved the way to improve the classification accuracy of the FEMG signals as well as the speech signals.

APA, Harvard, Vancouver, ISO, and other styles

31

Pang, Shan, and Xinyi Yang. "Deep Convolutional Extreme Learning Machine and Its Application in Handwritten Digit Classification." Computational Intelligence and Neuroscience 2016 (2016): 1–10. http://dx.doi.org/10.1155/2016/3049632.

Full text

Abstract:

In recent years, some deep learning methods have been developed and applied to image classification applications, such as convolutional neuron network (CNN) and deep belief network (DBN). However they are suffering from some problems like local minima, slow convergence rate, and intensive human intervention. In this paper, we propose a rapid learning method, namely, deep convolutional extreme learning machine (DC-ELM), which combines the power of CNN and fast training of ELM. It uses multiple alternate convolution layers and pooling layers to effectively abstract high level features from input images. Then the abstracted features are fed to an ELM classifier, which leads to better generalization performance with faster learning speed. DC-ELM also introduces stochastic pooling in the last hidden layer to reduce dimensionality of features greatly, thus saving much training time and computation resources. We systematically evaluated the performance of DC-ELM on two handwritten digit data sets: MNIST and USPS. Experimental results show that our method achieved better testing accuracy with significantly shorter training time in comparison with deep learning methods and other ELM methods.

APA, Harvard, Vancouver, ISO, and other styles

32

Voulodimos, Athanasios, Nikolaos Doulamis, Anastasios Doulamis, and Eftychios Protopapadakis. "Deep Learning for Computer Vision: A Brief Review." Computational Intelligence and Neuroscience 2018 (2018): 1–13. http://dx.doi.org/10.1155/2018/7068349.

Full text

Abstract:

Over the last years deep learning methods have been shown to outperform previous state-of-the-art machine learning techniques in several fields, with computer vision being one of the most prominent cases. This review paper provides a brief overview of some of the most significant deep learning schemes used in computer vision problems, that is, Convolutional Neural Networks, Deep Boltzmann Machines and Deep Belief Networks, and Stacked Denoising Autoencoders. A brief account of their history, structure, advantages, and limitations is given, followed by a description of their applications in various computer vision tasks, such as object detection, face recognition, action and activity recognition, and human pose estimation. Finally, a brief overview is given of future directions in designing deep learning schemes for computer vision problems and the challenges involved therein.

APA, Harvard, Vancouver, ISO, and other styles

33

El-Ashmony, E., M. El-Dosuky, and Samir Elmougy. "CLASSIFICATION OF LOW QUALITY IMAGES USING CONVOLUTIONAL NEURAL NETWORK AND DEEP BELIEF NETWORK." International Journal of Intelligent Computing and Information Sciences 16, no. 4 (October 1, 2016): 19–28. http://dx.doi.org/10.21608/ijicis.2016.19822.

Full text

APA, Harvard, Vancouver, ISO, and other styles

34

Mushtaq, Shiza, M. M. Manjurul Islam, and Muhammad Sohaib. "Deep Learning Aided Data-Driven Fault Diagnosis of Rotatory Machine: A Comprehensive Review." Energies 14, no. 16 (August 20, 2021): 5150. http://dx.doi.org/10.3390/en14165150.

Full text

Abstract:

This paper presents a comprehensive review of the developments made in rotating bearing fault diagnosis, a crucial component of a rotatory machine, during the past decade. A data-driven fault diagnosis framework consists of data acquisition, feature extraction/feature learning, and decision making based on shallow/deep learning algorithms. In this review paper, various signal processing techniques, classical machine learning approaches, and deep learning algorithms used for bearing fault diagnosis have been discussed. Moreover, highlights of the available public datasets that have been widely used in bearing fault diagnosis experiments, such as Case Western Reserve University (CWRU), Paderborn University Bearing, PRONOSTIA, and Intelligent Maintenance Systems (IMS), are discussed in this paper. A comparison of machine learning techniques, such as support vector machines, k-nearest neighbors, artificial neural networks, etc., deep learning algorithms such as a deep convolutional network (CNN), auto-encoder-based deep neural network (AE-DNN), deep belief network (DBN), deep recurrent neural network (RNN), and other deep learning methods that have been utilized for the diagnosis of rotary machines bearing fault, is presented.

APA, Harvard, Vancouver, ISO, and other styles

35

Kaabi, Rabeb, Moez Bouchouicha, Aymen Mouelhi, Mounir Sayadi, and Eric Moreau. "An Efficient Smoke Detection Algorithm Based on Deep Belief Network Classifier Using Energy and Intensity Features." Electronics 9, no. 9 (August 27, 2020): 1390. http://dx.doi.org/10.3390/electronics9091390.

Full text

Abstract:

Smoke detection plays an important role in forest safety warning systems and fire prevention. Complicated changes in the shape, texture, and color of smoke remain a substantial challenge to identify smoke in a given image. In this paper, a new algorithm using the deep belief network (DBN) is designed for smoke detection. Unlike popular deep convolutional networks (e.g., Alex-Net, VGG-Net, Res-Net, Dense-Net, and the denoising convolution neural network (DNCNN), specifically devoted to detecting smoke), our proposed end-to-end network is mainly based on DBN. Indeed, most traditional smoke detection algorithms follow the pattern recognition process which consists basically feature extraction and classification. After extracting the candidate regions, the main idea is to perform both smoke recognition and smoke-no-smoke region classification using static and dynamic smoke characteristics. However, manual smoke detection cannot meet the requirements of a high smoke detection rate and has a long processing time. The convolutional neural network (CNN)-based smoke detection methods are significantly slower due to the maxpooling operation. In addition, the training phase can take a lot of time if the computer is not equipped with a powerful graphics processing unit (GPU). Thus, the contribution of this work is the development of a preprocessing step including a new combination of features—smoke color, smoke motion, and energy—to extract the regions of interest which are inserted within a simple architecture with the deep belief network (DBN). Our proposed method is able to classify and localize reliably the smoke regions providing an interesting computation time and improved performance metrics. First, the Gaussian mixture model (GMM) is employed to capture the frames containing a large amount of motion. After applying RGB rules to smoke pixels and analyzing the energy attitude of smoke regions, extracted features are then used to feed a DBN for classification. Experimental results conducted on the publicly available smoke detection database confirm that the DBN has reached a high detection rate that exceeded an average of 96% when tested on different videos containing smoke-like objects, which make smoke recognition more challenging. The proposed methodology provided high detection ratios and low false alarms, and guaranteed robustness verified by evaluations of accuracy, F1-score, and recall for noisy and non-noisy images with and without noise.

APA, Harvard, Vancouver, ISO, and other styles

36

Shao, Haidong, Hongkai Jiang, Haizhou Zhang, and Tianchen Liang. "Electric Locomotive Bearing Fault Diagnosis Using a Novel Convolutional Deep Belief Network." IEEE Transactions on Industrial Electronics 65, no. 3 (March 2018): 2727–36. http://dx.doi.org/10.1109/tie.2017.2745473.

Full text

APA, Harvard, Vancouver, ISO, and other styles

37

Kallipolitis, Athanasios, Kyriakos Revelos, and Ilias Maglogiannis. "Ensembling EfficientNets for the Classification and Interpretation of Histopathology Images." Algorithms 14, no. 10 (September 26, 2021): 278. http://dx.doi.org/10.3390/a14100278.

Full text

Abstract:

The extended utilization of digitized Whole Slide Images is transforming the workflow of traditional clinical histopathology to the digital era. The ongoing transformation has demonstrated major potentials towards the exploitation of Machine Learning and Deep Learning techniques as assistive tools for specialized medical personnel. While the performance of the implemented algorithms is continually boosted by the mass production of generated Whole Slide Images and the development of state-of the-art deep convolutional architectures, ensemble models provide an additional methodology towards the improvement of the prediction accuracy. Despite the earlier belief related to deep convolutional networks being treated as black boxes, important steps for the interpretation of such predictive models have also been proposed recently. However, this trend is not fully unveiled for the ensemble models. The paper investigates the application of an explanation scheme for ensemble classifiers, while providing satisfactory classification results of histopathology breast and colon cancer images in terms of accuracy. The results can be interpreted by the hidden layers’ activation of the included subnetworks and provide more accurate results than single network implementations.

APA, Harvard, Vancouver, ISO, and other styles

38

Zhang Yichao, 张义超, and 孙子文 Sun Ziwen. "Identity Authentication for Smart Phones Based on an Optimized Convolutional Deep Belief Network." Laser & Optoelectronics Progress 57, no. 8 (2020): 081009. http://dx.doi.org/10.3788/lop57.081009.

Full text

APA, Harvard, Vancouver, ISO, and other styles

39

Gheisari, Soheila, DanielR Catchpoole, Amanda Charlton, and PaulJ Kennedy. "Convolutional deep belief network with feature encoding for classification of neuroblastoma histological images." Journal of Pathology Informatics 9, no. 1 (2018): 17. http://dx.doi.org/10.4103/jpi.jpi_73_17.

Full text

APA, Harvard, Vancouver, ISO, and other styles

40

Dai, Jiejie, Yingbing Teng, Zhaoqi Zhang, Zhongmin Yu, Gehao Sheng, and Xiuchen Jiang. "Partial Discharge Data Matching Method for GIS Case-Based Reasoning." Energies 12, no. 19 (September 26, 2019): 3677. http://dx.doi.org/10.3390/en12193677.

Full text

Abstract:

With the accumulation of partial discharge (PD) detection data from substation, case-based reasoning (CBR), which computes the match degree between detected PD data and historical case data provides new ideas for the interpretation and evaluation of partial discharge data. Aiming at the problem of partial discharge data matching, this paper proposes a data matching method based on a variational autoencoder (VAE). A VAE network model for partial discharge data is constructed to extract the deep eigenvalues. Cosine distance is then used to calculate the match degree between different partial discharge data. To verify the advantages of the proposed method, a partial discharge dataset was established through a partial discharge experiment and live detections on substation site. The proposed method was compared with other feature extraction methods and matching methods including statistical features, deep belief networks (DBN), deep convolutional neural networks (CNN), Euclidean distances, and correlation coefficients. The experimental results show that the cosine distance match degree based on the VAE feature vector can effectively detect similar partial discharge data compared with other data matching methods.

APA, Harvard, Vancouver, ISO, and other styles

41

Iorliam, A., S. Agber, MP Dzungwe, DK Kwaghtyo, and S. Bum. "Comparative Analysis of Deep Learning Techniques for the Classification of Hate Speech." NIGERIAN ANNALS OF PURE AND APPLIED SCIENCES 4, no. 1 (August 20, 2021): 121–28. http://dx.doi.org/10.46912/napas.227.

Full text

Abstract:

Social media provides opportunities for individuals to anonymously communicate and express hateful feelings and opinions at the comfort of their rooms. This anonymity has become a shield for many individuals or groups who use social media to express deep hatred for other individuals or groups, tribes or race, religion, gender, as well as belief systems. In this study, a comparative analysis is performed using Long Short-Term Memory and Convolutional Neural Network deep learning techniques for Hate Speech classification. This analysis demonstrates that the Long Short-Term Memory classifier achieved an accuracy of 92.47%, while the Convolutional Neural Network classifier achieved an accuracy of 92.74%. These results showed that deep learning techniques can effectively classify hate speech from normal speech.

APA, Harvard, Vancouver, ISO, and other styles

42

Wang, Shaofei, Ji Zhou, Tianjie Lei, Hua Wu, Xiaodong Zhang, Jin Ma, and Hailing Zhong. "Estimating Land Surface Temperature from Satellite Passive Microwave Observations with the Traditional Neural Network, Deep Belief Network, and Convolutional Neural Network." Remote Sensing 12, no. 17 (August 20, 2020): 2691. http://dx.doi.org/10.3390/rs12172691.

Full text

Abstract:

Neural networks, especially the latest deep learning, have exhibited good ability in estimating surface parameters from satellite remote sensing. However, thorough examinations of neural networks in the estimation of land surface temperature (LST) from satellite passive microwave (MW) observations are still lacking. Here, we examined the performances of the traditional neural network (NN), deep belief network (DBN), and convolutional neural network (CNN) in estimating LST from the AMSR-E and AMSR2 data over the Chinese landmass. The examinations were based on the same training set, validation set, and test set extracted from 2003, 2004, and 2009, respectively, for AMSR-E with a spatial resolution of 0.25°. For AMSR2, the three sets were extracted from 2013, 2014, and 2016 with a spatial resolution of 0.1°, respectively. MODIS LST played the role of “ground truth” in the training, validation, and testing. The examination results show that CNN is better than NN and DBN by 0.1–0.4 K. Different combinations of input parameters were examined to get the best combinations for the daytime and nighttime conditions. The best combinations are the brightness temperatures (BTs), NDVI, air temperature, and day of the year (DOY) for the daytime and BTs and air temperature for the nighttime. By adding three and one easily obtained parameters on the basis of BTs, the accuracies of LST estimates can be improved by 0.8 K and 0.3 K for the daytime and nighttime conditions, respectively. Compared with the MODIS LST, the CNN LST estimates yielded root-mean-square differences (RMSDs) of 2.19–3.58 K for the daytime and 1.43–2.14 K for the nighttime for diverse land cover types for AMSR-E. Validation against the in-situ LSTs showed that the CNN LSTs yielded root-mean-square errors of 2.10–4.72 K for forest and cropland sites. Further intercomparison indicated that ~50% of the CNN LSTs were closer to the MODIS LSTs than ESA’s GlobTemperature AMSR-E LSTs, and the average RMSDs of the CNN LSTs were less than 3 K over dense vegetation compared to NASA’s global land parameter data record air temperatures. This study helps better the understanding of the use of neural networks for estimating LST from satellite MW observations.

APA, Harvard, Vancouver, ISO, and other styles

43

Xiong, Jianbin, Dezheng Yu, Shuangyin Liu, Lei Shu, Xiaochan Wang, and Zhaoke Liu. "A Review of Plant Phenotypic Image Recognition Technology Based on Deep Learning." Electronics 10, no. 1 (January 4, 2021): 81. http://dx.doi.org/10.3390/electronics10010081.

Full text

Abstract:

Plant phenotypic image recognition (PPIR) is an important branch of smart agriculture. In recent years, deep learning has achieved significant breakthroughs in image recognition. Consequently, PPIR technology that is based on deep learning is becoming increasingly popular. First, this paper introduces the development and application of PPIR technology, followed by its classification and analysis. Second, it presents the theory of four types of deep learning methods and their applications in PPIR. These methods include the convolutional neural network, deep belief network, recurrent neural network, and stacked autoencoder, and they are applied to identify plant species, diagnose plant diseases, etc. Finally, the difficulties and challenges of deep learning in PPIR are discussed.

APA, Harvard, Vancouver, ISO, and other styles

44

Shao, Haidong, Hongkai Jiang, Haizhou Zhang, Wenjing Duan, Tianchen Liang, and Shuaipeng Wu. "Rolling bearing fault feature learning using improved convolutional deep belief network with compressed sensing." Mechanical Systems and Signal Processing 100 (February 2018): 743–65. http://dx.doi.org/10.1016/j.ymssp.2017.08.002.

Full text

APA, Harvard, Vancouver, ISO, and other styles

45

Papadomanolaki, M., M. Vakalopoulou, S. Zagoruyko, and K. Karantzalos. "BENCHMARKING DEEP LEARNING FRAMEWORKS FOR THE CLASSIFICATION OF VERY HIGH RESOLUTION SATELLITE MULTISPECTRAL DATA." ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences III-7 (June 7, 2016): 83–88. http://dx.doi.org/10.5194/isprs-annals-iii-7-83-2016.

Full text

Abstract:

In this paper we evaluated deep-learning frameworks based on Convolutional Neural Networks for the accurate classification of multispectral remote sensing data. Certain state-of-the-art models have been tested on the publicly available SAT-4 and SAT-6 high resolution satellite multispectral datasets. In particular, the performed benchmark included the AlexNet, AlexNet-small and VGG models which had been trained and applied to both datasets exploiting all the available spectral information. Deep Belief Networks, Autoencoders and other semi-supervised frameworks have been, also, compared. The high level features that were calculated from the tested models managed to classify the different land cover classes with significantly high accuracy rates i.e., above 99.9%. The experimental results demonstrate the great potentials of advanced deep-learning frameworks for the supervised classification of high resolution multispectral remote sensing data.

APA, Harvard, Vancouver, ISO, and other styles

46

Wang, Hong, Hongbin Wang, Guoqian Jiang, Yueling Wang, and Shuang Ren. "A Multiscale Spatio-Temporal Convolutional Deep Belief Network for Sensor Fault Detection of Wind Turbine." Sensors 20, no. 12 (June 24, 2020): 3580. http://dx.doi.org/10.3390/s20123580.

Full text

Abstract:

Sensor fault detection of wind turbines plays an important role in improving the reliability and stable operation of turbines. The supervisory control and data acquisition (SCADA) system of a wind turbine provides promising insights into sensor fault detection due to the accessibility of the data and the abundance of sensor information. However, SCADA data are essentially multivariate time series with inherent spatio-temporal correlation characteristics, which has not been well considered in the existing wind turbine fault detection research. This paper proposes a novel classification-based fault detection method for wind turbine sensors. To better capture the spatio-temporal characteristics hidden in SCADA data, a multiscale spatio-temporal convolutional deep belief network (MSTCDBN) was developed to perform feature learning and classification to fulfill the sensor fault detection. A major superiority of the proposed method is that it can not only learn the spatial correlation information between several different variables but also capture the temporal characteristics of each variable. Furthermore, this method with multiscale learning capability can excavate interactive characteristics between variables at different scales of filters. A generic wind turbine benchmark model was used to evaluate the proposed approach. The comparative results demonstrate that the proposed method can significantly enhance the fault detection performance.

APA, Harvard, Vancouver, ISO, and other styles

47

Papadomanolaki, M., M. Vakalopoulou, S. Zagoruyko, and K. Karantzalos. "BENCHMARKING DEEP LEARNING FRAMEWORKS FOR THE CLASSIFICATION OF VERY HIGH RESOLUTION SATELLITE MULTISPECTRAL DATA." ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences III-7 (June 7, 2016): 83–88. http://dx.doi.org/10.5194/isprsannals-iii-7-83-2016.

Full text

Abstract:

In this paper we evaluated deep-learning frameworks based on Convolutional Neural Networks for the accurate classification of multispectral remote sensing data. Certain state-of-the-art models have been tested on the publicly available SAT-4 and SAT-6 high resolution satellite multispectral datasets. In particular, the performed benchmark included the AlexNet, AlexNet-small and VGG models which had been trained and applied to both datasets exploiting all the available spectral information. Deep Belief Networks, Autoencoders and other semi-supervised frameworks have been, also, compared. The high level features that were calculated from the tested models managed to classify the different land cover classes with significantly high accuracy rates i.e., above 99.9%. The experimental results demonstrate the great potentials of advanced deep-learning frameworks for the supervised classification of high resolution multispectral remote sensing data.

APA, Harvard, Vancouver, ISO, and other styles

48

Gao, Dexin, and Xihao Lin. "Fault Diagnosis Method of DC Charging Points for EVs Based on Deep Belief Network." World Electric Vehicle Journal 12, no. 1 (March 20, 2021): 47. http://dx.doi.org/10.3390/wevj12010047.

Full text

Abstract:

According to the complex fault mechanism of direct current (DC) charging points for electric vehicles (EVs) and the poor application effect of traditional fault diagnosis methods, a new kind of fault diagnosis method for DC charging points for EVs based on deep belief network (DBN) is proposed, which combines the advantages of DBN in feature extraction and processing nonlinear data. This method utilizes the actual measurement data of the charging points to realize the unsupervised feature extraction and parameter fine-tuning of the network, and builds the deep network model to complete the accurate fault diagnosis of the charging points. The effectiveness of this method is examined by comparing with the backpropagation neural network, radial basis function neural network, support vector machine, and convolutional neural network in terms of accuracy and model convergence time. The experimental results prove that the proposed method has a higher fault diagnosis accuracy than the above fault diagnosis methods.

APA, Harvard, Vancouver, ISO, and other styles

49

Masud, Mehedi, M. Shamim Hossain, Hesham Alhumyani, Sultan S. Alshamrani, Omar Cheikhrouhou, Saleh Ibrahim, Ghulam Muhammad, Amr E. Eldin Rashed, and B. B. Gupta. "Pre-Trained Convolutional Neural Networks for Breast Cancer Detection Using Ultrasound Images." ACM Transactions on Internet Technology 21, no. 4 (July 16, 2021): 1–17. http://dx.doi.org/10.1145/3418355.

Full text

Abstract:

Volunteer computing based data processing is a new trend in healthcare applications. Researchers are now leveraging volunteer computing power to train deep learning networks consisting of billions of parameters. Breast cancer is the second most common cause of death in women among cancers. The early detection of cancer may diminish the death risk of patients. Since the diagnosis of breast cancer manually takes lengthy time and there is a scarcity of detection systems, development of an automatic diagnosis system is needed for early detection of cancer. Machine learning models are now widely used for cancer detection and prediction research for improving the successive therapy of patients. Considering this need, this study implements pre-trained convolutional neural network based models for detecting breast cancer using ultrasound images. In particular, we tuned the pre-trained models for extracting key features from ultrasound images and included a classifier on the top layer. We measured accuracy of seven popular state-of-the-art pre-trained models using different optimizers and hyper-parameters through fivefold cross validation. Moreover, we consider Grad-CAM and occlusion mapping techniques to examine how well the models extract key features from the ultrasound images to detect cancers. We observe that after fine tuning, DenseNet201 and ResNet50 show 100% accuracy with Adam and RMSprop optimizers. VGG16 shows 100% accuracy using the Stochastic Gradient Descent optimizer. We also develop a custom convolutional neural network model with a smaller number of layers compared to large layers in the pre-trained models. The model also shows 100% accuracy using the Adam optimizer in classifying healthy and breast cancer patients. It is our belief that the model will assist healthcare experts with improved and faster patient screening and pave a way to further breast cancer research.

APA, Harvard, Vancouver, ISO, and other styles

50

Wang, Yuliang, Huiyi Su, and Mingshi Li. "An Improved Model Based Detection of Urban Impervious Surfaces Using Multiple Features Extracted from ROSIS-3 Hyperspectral Images." Remote Sensing 11, no. 2 (January 11, 2019): 136. http://dx.doi.org/10.3390/rs11020136.

Full text

Abstract:

Hyperspectral images (HSIs) provide unique capabilities for urban impervious surfaces (UIS) extraction. This paper proposes a multi-feature extraction model (MFEM) for UIS detection from HSIs. The model is based on a nonlinear dimensionality reduction technique, t-distributed stochastic neighbor embedding (t-SNE), and the deep learning method convolutional deep belief networks (CDBNs). We improved the two methods to create a novel MFEM consisting of improved t-SNE, deep compression CDBNs (d-CDBNs), and a logistic regression classifier. The improved t-SNE method provides dimensionality reduction and spectral feature extraction from the original HSIs and the d-CDBNs algorithm extracts spatial feature and edges using the reduced dimensional datasets. Finally, the extracted features are combined into multi-feature for the impervious surface detection using the logistic regression classifier. After comparing with the commonly used methods, the current experimental results demonstrate that the proposed MFEM model provides better performance for UIS extraction and detection from HSIs.

APA, Harvard, Vancouver, ISO, and other styles

Journal articles on the topic 'Convolutional Deep Belief Networks'

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles