As of more recently, deep learning-based models have demonstrated considerable potential, as they have outperformed all traditional practices. When data becomes high dimensional, extraction of features and compression...
详细信息
Health assessment of pipeline systems is of deep significance for improving pipeline reliability and integrity. Traditional health assessment methods may be difficult or costly to perform on pipeline systems due to th...
详细信息
Health assessment of pipeline systems is of deep significance for improving pipeline reliability and integrity. Traditional health assessment methods may be difficult or costly to perform on pipeline systems due to the long distances and environmental constraints of pipelines. This paper incorporates the distributed optical fiber sensor (DOFS) technique and the semi-supervised learning algorithm into the pipeline health assessment framework. Three critical problems that limit the application of DOFS in pipeline health assessments are addressed. First, an applicable damage monitoring experiment of a pipeline system is designed, which is effective in obtaining the necessary base data for data-driven modeling. Second, the correspondence between the pipeline health status and the monitored strain features is established. The experimental data are shared for public research, which is expected to solve the problem of the lack of benchmark research data in related fields. Third, considering the scarcity of labeled degradation data in pipelines, a semi-supervised denoising autoencoder model is proposed specifically for pipeline health assessment. The proposed method is demonstrated and validated using a comparative experimental case study.
The Growing Hierarchical Self-Organising Representation Map (GHSORM) is a model fusing the denoising autoencoder, used to better represent a dataset, and the Growing Hierarchical Self -Organising Map, used for organiz...
详细信息
The Growing Hierarchical Self-Organising Representation Map (GHSORM) is a model fusing the denoising autoencoder, used to better represent a dataset, and the Growing Hierarchical Self -Organising Map, used for organizing and projecting the input data in clusters of varying detail. It is shown here that the GHSORM is instrumental in sub-grouping clusters that are not fully separable by a single SOM. This combined approach is first tested and illustrated on the problem of clustering handwritten digits where a modification of the Activation Maximisation method for use at the SOM output layer demonstrates the benefit of hierarchical growth in the GHSORM. In particular, the SOM Node Activation Maximisation method is used to visually represent the best approximation of each of the SOM nodes at the output layer. This demonstrates the improvement in representing difficult to separate digits in the hierarchical case. To test and measure the effi-cacy of the GHSORM hierarchical model in class and sub-class separation the method is applied to complex digital gene expression data. A cancer dataset, comprising of gene expression data that has samples of different classes and sub-classes, is used for this purpose. The GHSORM demon-strates robust capabilities to cluster and sub-cluster the different classes and subclasses of cancer, where the results are superior to both linear methods, currently in use, as well as the methods of its constituent algorithms.
To reduce noise in the lidar return signal, an improved deep belief network (DBN) denoising algorithm is proposed in this study. In the traditional implementation process of DBN, a multi-layer fully connected network ...
详细信息
To reduce noise in the lidar return signal, an improved deep belief network (DBN) denoising algorithm is proposed in this study. In the traditional implementation process of DBN, a multi-layer fully connected network is realized by stacking restricted Boltzmann machines (RBMs). However, the RBM is an undirected graph model, and there is no clear causal relationship between random variable nodes. The denoising autoencoder (DAE) can avoid this problem and produce field generalization performance by adding random contamination during training and stacking, thereby achieving better performance than the traditional DBN. In this study, a new multi-layer DBN called DADBN is implemented by stacking DAE and RBM. First, the multi-layer DAE is placed in the beginning layer of the network as the primary filter of the signal to provide data dimensionality reduction and feature extraction. Then, the RBM is used as the lower layer, the hidden layer is calculated according to the initial value of the visible layer by the contrast of the divergence algorithm, and the visible layer is reconstructed from the samples of the hidden layer. And the sparse representation penalty is added to the RBM model to solve the assimilation phenomenon of hidden layer nodes in the RBM model. It not only optimizes the log-likelihood function when training data, but also makes the probability of each hidden layer node being activated tend to a minimum value, so as to sparsely activate the sparse hidden layer nodes. The weight matrix W is obtained by computing the results of the hidden layer twice. Finally, the original input signal was reconstructed by Gibbs sampling layer and the reconstructed signal was decoded by the decoder to achieve the purpose of noise reduction. To verify its effectiveness, this method is compared with four other denoising methods: wavelet packet algorithm, complete ensemble empirical modal decomposition (CEEMDAN), wavelet transform and empirical mode decomposition (WT-EMD), and
Image analysis and classification perform well in pre-processed noise-free images than in corrupted images. Synthetic aperture radar (SAR) images, Ultrasound (US) medical images, etc. exhibit speckle noise, which has ...
详细信息
Image analysis and classification perform well in pre-processed noise-free images than in corrupted images. Synthetic aperture radar (SAR) images, Ultrasound (US) medical images, etc. exhibit speckle noise, which has a multiplicative and granular behavior. In the existing techniques, the autoencoders are used to implement a deep learning-based denoising method specifically for US images. The traditional image denoising techniques as well as deep learning techniques for image denoising. In this paper, we have proposed a deep learning-based model called, Convolutional-based improved despeckling autoencoder (CIDAE) for denoising transthoracic echocardiographic images. The dataset for the network has been collected from patients having Regional Wall Motion Abnormality (RWMA). There were 294 subjects with routine transthoracic examinations, consisting of 151 RWMA and 143 normal hearts (55.7 percent female, ages 20-75 years). The potential of the proposed DL algorithms was evaluated visually and quantitatively using the Structural Similarity Index Measure (SSIM), Peak Signal Noise Ratio (PSNR), and Mean Squared Error (MSE). Our results demonstrate the significance of the proposed CIDAE for denoising echo images of patients with RWMA and structurally normal hearts with a promising p-value < 0.0001.
Deep learning is the new frontier of machine learning research, which has led to many recent breakthroughs in English natural language processing. However, there are inherent differences between Chinese and English, a...
详细信息
ISBN:
(纸本)9783642416439;9783642416446
Deep learning is the new frontier of machine learning research, which has led to many recent breakthroughs in English natural language processing. However, there are inherent differences between Chinese and English, and little work has been done to apply deep learning techniques to Chinese natural language processing. In this paper, we propose a deep neural network model: text window denoising autoencoder, as well as a complete pre-training solution as a new way to solve classical Chinese natural language processing problems. This method does not require any linguistic knowledge or manual feature design, and can be applied to various Chinese natural language processing tasks, such as Chinese word segmentation. On the PKU dataset of Chinese word segmentation bakeoff 2005, applying this method decreases the F1 error rate by 11.9% for deep neural network based models. We are the first to apply deep learning methods to Chinese word segmentation to our best knowledge.
We introduce a novel mathematical formulation for the training of feed-forward neural networks with (potentially non-smooth) proximal maps as activation functions. This formulation is based on Bregman distances and a ...
详细信息
We introduce a novel mathematical formulation for the training of feed-forward neural networks with (potentially non-smooth) proximal maps as activation functions. This formulation is based on Bregman distances and a key advantage is that its partial derivatives with respect to the network's parameters do not require the computation of derivatives of the network's activation functions. Instead of estimating the parameters with a combination of first-order optimisation method and back-propagation (as is the state-of-the-art), we propose the use of non-smooth first-order optimisation methods that exploit the specific structure of the novel formulation. We present several numerical results that demonstrate that these training approaches can be equally well or even better suited for the training of neural network-based classifiers and (denoising) autoencoders with sparse coding compared to more conventional training frameworks.
The Combined Algorithm Selection and Hyperparameter Optimization problem, in short, CASH, seeks the most suitable classifiers and hyperparameters for the underlying classification problems. In current literature, the ...
详细信息
The Combined Algorithm Selection and Hyperparameter Optimization problem, in short, CASH, seeks the most suitable classifiers and hyperparameters for the underlying classification problems. In current literature, the common approaches in dealing with CASH problem are conducted via search-based methods such as sequential model-based optimization (SMBO) along with various active tests. Different from current existing approaches, in this paper, we propose a new method by incorporating the so-called denoising autoencoder (DAE) approach into meta-learning (MtL) for automatic configuration (both algorithms and their hyperparameters) recommendation, which appears to be quite effective compared to standard search-based approaches. More specifically, we set up the configuration search space for CASH and produce the metadata, and generate the classification performance on a set of collected historical datasets. Then both encoder and decoder in the DAE system are trained with the masked metadata as inputs and the unmasked metadata as targets to extract the subtle latent variables of metadata and recover the unmasked inputs subsequently. Under our framework, the performance over the entire configuration space can be predicted effectively through two different settings, and the configuration with the highest predictive performance is thus recommended. The first recommendation approach is by inactivating some inputs and then to recover their entries via the trained encoder and decoder for new problems, while in the second approach, the relationship between the acquired latent variables and the meta-features of historical datasets via kernel multivariate multiple regression (MMR) is enacted, leading to the performance estimation of new datasets being pursued directly through MMR and the decoder of DAE without requiring any new configuration evaluations. An automatic classification configuration recommendation system, including 81 historical problems and 11 common classifiers with
denoising autoencoder is applied to reverberant speech recognition as a noise robust front-end to reconstruct clean speech spectrum from noisy input. In order to capture context effects of speech sounds, a window of m...
详细信息
ISBN:
(纸本)9781629934433
denoising autoencoder is applied to reverberant speech recognition as a noise robust front-end to reconstruct clean speech spectrum from noisy input. In order to capture context effects of speech sounds, a window of multiple short-windowed spectral frames are concatenated to form a single input vector. Additionally, a combination of short and long-term spectra is investigated to properly handle long impulse response of reverberation while keeping necessary time resolution for speech recognition. Experiments are performed using the CENSREC-4 dataset that is designed as an evaluation framework for distant-talking speech recognition. Experimental results show that the proposed denoising autoencoder based front-end using the short-windowed spectra gives better results than conventional methods. By combining the long-term spectra, further improvement is obtained. The recognition accuracy by the proposed method using the short and long-term spectra is 97.0% for the open condition test set of the dataset, whereas it is 87.8% when a multi condition training based baseline is used. As a supplemental experiment, large vocabulary speech recognition is also performed and the effectiveness of the proposed method has been confirmed.
Web requests made by users of web applications are manipulated by hackers to gain control of web servers. Moreover, detecting web attacks has been increasingly important in the distribution of information over the las...
详细信息
Web requests made by users of web applications are manipulated by hackers to gain control of web servers. Moreover, detecting web attacks has been increasingly important in the distribution of information over the last few decades. Also, several existing techniques had been performed on detecting vulnerable web attacks using machine learning and deep learning techniques. However, there is a lack in achieving attack detection ratio owing to the utilization of supervised and semi-supervised learning approaches. Thus to overcome the afore-mentioned issues, this research proposes a hybrid unsupervised detection model a deep learning-based anomaly -based web attack detection. Whereas, the encoded outputs of De-Noising autoencoder (DAE), as well as Stacked autoencoder (SAE), are integrated and given to the Generative adversarial network (GAN) as input to improve the feature representation ability to detect the web attacks. Consequently, for classifying the type of attacks, a novel DBM-Bi LSTM-based classification model has been introduced. Which incorporates DBM for binary clas-sification and Bi-LSTM for multi-class classification to classify the various attacks. Finally, the performance of the classifier in terms of recall, precision, F1-Score, and accuracy are evaluated and compared. The proposed method achieved high accuracy of 98%.
暂无评论