Sparse coding has been widely applied to learning-based single image super-resolution (SR) and has obtained promising performance by jointly learning effective representations for low-resolution (LR) and high-resoluti...
详细信息
Sparse coding has been widely applied to learning-based single image super-resolution (SR) and has obtained promising performance by jointly learning effective representations for low-resolution (LR) and high-resolution (HR) image patch pairs. However, the resulting HR images often suffer from ringing, jaggy, and blurring artifacts due to the strong yet ad hoc assumptions that the LR image patch representation is equal to, is linear with, lies on a manifold similar to, or has the same support set as the corresponding HR image patch representation. Motivated by the success of deep learning, we develop a data-driven model coupled deep autoencoder (CDA) for single image SR. CDA is based on a new deep architecture and has high representational capability. CDA simultaneously learns the intrinsic representations of LR and HR image patches and a big-data-driven function that precisely maps these LR representations to their corresponding HR representations. Extensive experimentation demonstrates the superior effectiveness and efficiency of CDA for single image SR compared to other state-of-the-art methods on Set5 and Set14 datasets.
Macular edema is a retinal complication that occurs due to the presence of excess fluid between the retinal layers. This might lead to swelling in the retina and cause severe vision impairment if not detected in its e...
详细信息
Macular edema is a retinal complication that occurs due to the presence of excess fluid between the retinal layers. This might lead to swelling in the retina and cause severe vision impairment if not detected in its early stages. This paper presents a robust Edge Attention network (EANet) for segmenting the different retinal fluids like Intraretinal Fluid (IRF), Subretinal Fluid (SRF), and Pigment Epithelial Detachment (PED) from the Spectral Domain - Optical Coherence Tomography (SD-OCT) images. The proposed method employs a novel image enhancement technique by filtering OCT images using a BM3D (Block Matching and 3D Filtering) filter followed by Contrast Limited Adaptive Histogram Equalization (CLAHE) and a linear filter based on multivariate Taylor series to acquire the edge maps of the OCT images. A novel autoencoder based multiscale attention mechanism is incorporated with EANet that feeds on both the OCT image and edge-enhanced OCT image at every level of the encoder. The proposed network, EANet, has been trained and tested for the segmentation of all three types of fluids on the RETOUCH challenge dataset, and the segmentation of the IRF on the OPTIMA challenge and DUKE DME datasets. The average dice coefficient of IRF, SRF, and PED for the RETOUCH dataset is 0.683, 0.873, and 0.756, respectively, whereas it is 0.805, 0.77, and 0.756 for Cirrus, Spectralis, and Topcon vendors, respectively. The proposed method outperformed all the teams that participated in the OPTIMA challenge on all types of vendor images in terms of dice coefficient. The average dice coefficients of IRF on the OPTIMA and DUKE DME datasets are 0.84 and 0.72, respectively.
This paper proposes a novel approach to the portfolio management using an autoencoder. In particular, features learned by an autoencoder with ReLU are directly exploited to portfolio constructions. Since the AutoEncod...
详细信息
This paper proposes a novel approach to the portfolio management using an autoencoder. In particular, features learned by an autoencoder with ReLU are directly exploited to portfolio constructions. Since the autoencoder extracts characteristics of data through a non-linear activation function ReLU, its realization is generally difficult due to the non-linear transformation procedure. In the current paper, we solve this problem by taking full advantage of the similarity of ReLU and an option payoff. Especially, this paper shows that the features are successfully replicated by applying so-called dynamic delta hedging strategy. An out of sample simulation with crypto currency dataset shows the effectiveness of our proposed strategy. (C) 2020 Elsevier Ltd. All rights reserved.
We propose a model for a system with middle temporal neurons and medial superior temporal (MST) neurons by using a three-layered autoencoder. Noise effect is taken into account by using the framework of statistical ph...
详细信息
We propose a model for a system with middle temporal neurons and medial superior temporal (MST) neurons by using a three-layered autoencoder. Noise effect is taken into account by using the framework of statistical physics. We define a cost function of the autoencoder, from which a learning rule is derived by a gradient descent method, within a mean-field approximation. We find a pair of values of two noise levels at which a minimum value of the cost function is attained. We investigate response properties of the MST neurons to optical flows for various types of motion at the pair of optimal values of two noise levels. We obtain that the response properties of the MST neurons are similar to those obtained from neurophysiological experiments. (C) 2002 Elsevier Science B.V. All rights reserved.
In technical systems the analysis of similar situations is a promising technique to gain information about the system's state, its health or wearing. Very often, situations cannot be defined but need to be discove...
详细信息
In technical systems the analysis of similar situations is a promising technique to gain information about the system's state, its health or wearing. Very often, situations cannot be defined but need to be discovered as recurrent patterns within time series data of the system under consideration. This paper addresses the assessment of different approaches to discover frequent variable-length patterns in time series. Because of the success of artificial neural networks (NN) in various research fields, a special issue of this work is the applicability of NNs to the problem of pattern discovery in time series. Therefore we applied and adapted a Convolutional autoencoder and compared it to classical nonlearning approaches based on Dynamic Time Warping, based on time series discretization as well as based on the Matrix Profile. These nonlearning approaches have also been adapted, to fulfill our requirements like the discovery of potentially time scaled patterns from noisy time series. We showed the performance (quality, computing time, effort of parametrization) of those approaches in an extensive test with synthetic data sets. Additionally the transferability to other data sets is tested by using real life vehicle data. We demonstrated the ability of Convolutional autoencoders to discover patterns in an unsupervised way. Furthermore the tests showed, that the autoencoder is able to discover patterns with a similar quality like classical nonlearning approaches.
In the past decades, personalized recommendation systems have attracted a vast amount of attention and researches from multiple disciplines. Recently, for the powerful ability of feature representation learning, deep ...
详细信息
In the past decades, personalized recommendation systems have attracted a vast amount of attention and researches from multiple disciplines. Recently, for the powerful ability of feature representation learning, deep neural networks have achieved sound performance in the recommendation. However, most of the existing deep recommendation approaches require a large number of labeled data, which is often expensive and labor-some in applications. Meanwhile, the side information of users and items that can extend the feature space effectively is usually scarce. To address these problems, we propose a Personalized Recommendation method, which extends items' feature representations with Knowledge Graph via dual-autoencoder (short for PRKG). More specifically, we first extract items' side information from open knowledge graph like DBpedia as items' feature extension. Secondly, we learn the low-dimensional representations of additional features collected from DBpedia via the autoencoder module and then integrate the processed features into the original feature space. Finally, the reconstructed features is incorporated into the semi-autoencoder for personalized recommendations. Extensive experiments conducted on several real-world datasets validate the effectiveness of our proposed methods compared to several state-of-the-art models.
Achieving carbon neutrality in the pulp and paper industry necessitates effectively recycling pulp and papermaking wastewater, where continuous monitoring of effluent quality indices is crucial. This study suggests a ...
详细信息
Achieving carbon neutrality in the pulp and paper industry necessitates effectively recycling pulp and papermaking wastewater, where continuous monitoring of effluent quality indices is crucial. This study suggests a novel machine learning-based model named LSTMAE-XGBOOST that integrates the feature extraction capabilities of autoencoder, the sequential feature learning capabilities of LSTM, and the high prediction accuracy of XGBOOST. This model is capable of extracting the complex relationships, non-Gaussian characteristics, and time series features from the papermaking wastewater data, and it demonstrates superior predictive performance. Compared to traditional machine learning models, the proposed model exhibits higher prediction accuracy. Specifically, when contrasted with partial least squares regression, LSTMAE-XGBOOST achieves a 40% increase in R-2 and a 35% reduction in RMSE. Further comparative assessments against other machine learning-based hybrid models with similar structures confirm the superiority of integrating LSTM and XGBOOST within the hybrid model approach. This study contributes a compelling methodology for modeling effluent quality indices, offering significant implications for environmental management in the pulp and paper industry.
Software is playing a growing role in many safety-critical applications, and software systems dependability is a major concern. Predicting faulty modules of software before the testing phase is one method for enhancin...
详细信息
Software is playing a growing role in many safety-critical applications, and software systems dependability is a major concern. Predicting faulty modules of software before the testing phase is one method for enhancing software reliability. The ability to predict and identify the faulty modules of software can lower software testing costs. Machine learning algorithms can be used to solve software fault prediction problem. Identifying the faulty modules of software with the maximum accuracy, precision, and performance are the main objectives of this study. A hybrid method combining the autoencoder and the K-means algorithm is utilized in this paper to develop a software fault predictor. The autoencoder algorithm, as a preprocessor, is used to select the effective attributes of the training dataset and consequently to reduce its size. Using an autoencoder with the K-means clustering method results in lower clustering error and time. Tests conducted on the standard NASA PROMIS data sets demonstrate that by removing the inefficient elements from the training data set, the proposed fault predictor has increased accuracy (96%) and precision (93%). The recall criteria provided by the proposed method is about 87%. Also, reducing the time necessary to create the software fault predictor is the other merit of this study.
Link prediction aims to predict missing links or eliminate spurious links by employing known complex network information. As an unsupervised linear feature representation method, matrix factorization (MF)-based autoen...
详细信息
Link prediction aims to predict missing links or eliminate spurious links by employing known complex network information. As an unsupervised linear feature representation method, matrix factorization (MF)-based autoencoder (AE) can project the high-dimensional data matrix into the low-dimensional latent space. However, most of the traditional link prediction methods based on MF or AE adopt shallow models and single adjacency matrices, which cannot adequately learn and represent network features and are susceptible to noise. In addition, because some methods require the input of symmetric data matrix, they can only be used in undirected networks. Therefore, we propose a deep manifold matrix factorization autoencoder model using global connectivity matrix, called DM-MFAE-G. The model utilizes PageRank algorithm to get the global connectivity matrix between nodes for the complex network. DM-MFAE-G performs deep matrix factorization on the local adjacency matrix and global connectivity matrix, respectively, to obtain global and local multi-layer feature representations, which contains the rich structural information. In this paper, the model is solved by alternating iterative optimization method, and the convergence of the algorithm is proved. Comprehensive experiments on different real networks demonstrate that the global connectivity matrix and manifold constraints introduced by DM-MFAE-G significantly improve the link prediction performance on directed and undirected networks.
Synthesizing talking face from text and audio is increasingly becoming a direction in human-machine and face-to-face interactions. Although progress has been made, several existing methods either have unsatisfactory c...
详细信息
Synthesizing talking face from text and audio is increasingly becoming a direction in human-machine and face-to-face interactions. Although progress has been made, several existing methods either have unsatisfactory co-articulation modeling effects or ignore relations between adjacent inputs. Moreover, some of these methods often train models on shaky head videos or utilize linear-based face parameterization strategies, which further decrease synthesized quality. To address the above issues, this study proposes a sequence-to-sequence convolutional neural network to automatically synthesize talking face video with accurate lip sync. First, an advanced landmark location pipeline is used to accurately locate the facial landmarks, which can effectively reduce landmark shake. Then, a part-based autoencoder is presented to encode face images into a low-dimensional space and obtain compact representations. A sequence-to-sequence network is also presented to encode the relation of neighboring frames with multiple loss functions, and talking faces are synthesized through a reconstruction strategy with a decoder. Experiments on two public audio-visual datasets and a new dataset called CCTV news demonstrate the effectiveness of the proposed method against other state-of-the-art methods. (C) 2020 Elsevier Ltd. All rights reserved.
暂无评论