Unsupervised feature selection is one of the efficient approaches to reduce the dimension of unlabeled high-dimensional data. We present a novel adaptive autoencoder with redundancy control (AARC) as an unsupervised f...
详细信息
Unsupervised feature selection is one of the efficient approaches to reduce the dimension of unlabeled high-dimensional data. We present a novel adaptive autoencoder with redundancy control (AARC) as an unsupervised feature selector. By adding two Group Lasso penalties to the objective function, AARC integrates unsupervised feature selection and determination of a compact network structure into a single framework. Besides, a penalty based on a measure of dependency between features (such as Pearson correlation, mutual information) is added to the objective function for controlling the level of redundancy in the selected features. To realize the desired effects of different regularizers in different phases of the training, we introduce adaptive parameters which change with iterations. In addition, a smoothing function is utilized to approximate the three penalties since they are not differentiable at the origin. An ablation study is carried out to validate the capabilities of redundancy control and structure optimization of AARC. Subsequently, comparisons with nine state-of-the-art methods illustrate the efficiency of AARC for unsupervised feature selection. (c) 2022 Elsevier Ltd. All rights reserved.
Dynamic information is a non-negligible part of time-correlated process data, and its full utilization can improve the performance of fault detection. Traditional dynamic methods concatenate the current process data w...
详细信息
Dynamic information is a non-negligible part of time-correlated process data, and its full utilization can improve the performance of fault detection. Traditional dynamic methods concatenate the current process data with a certain number of previous process data into an extended vector before performing feature extraction. However, this simple way of using dynamic information inevitably increases the input dimensionality and it is inappropriate to treat previous process data as equally important. To address these problems, this paper proposes a novel nonlinear dynamic method, called graph dynamic autoencoder (GDAE), for fault detection. GDAE utilizes a graph structure to model the dynamic information between different data points. GDAE firstly embeds the current data point and previous data points as the features of the central node and its neighbors, respectively, then convolves the feature of the central node with the features of its neighbors to derive the updated feature for the central node, and finally, an encoder-decoder structure is adopted to extract the key low-dimensional feature. Due to the utilization of the graph structure, the extended high-dimensional vectors utilized by traditional dynamic fault detection methods are avoided in GDAE. Furthermore, with the dynamically constructed graph, GDAE is able to adaptively assign different weights to its neighbors by updating the adjacency matrix of the graph. Experimental results obtained from a numerical simulation and the Tennessee Eastman process illustrate the superiority of GDAE in terms of missed detection rate (MDR) and false alarm rate (FAR). The source code of GDAE can be found in https://***/luliu-fighting/Graph-Dynamic-autoencoder. (c) 2022 Elsevier Ltd. All rights reserved.
Document digitization has an important role in helping the company's activities be more efficient, such as detecting text in invoice document images using optical character recognition (OCR). However, writing in i...
详细信息
ISBN:
(纸本)9798350334449
Document digitization has an important role in helping the company's activities be more efficient, such as detecting text in invoice document images using optical character recognition (OCR). However, writing in images has many problems, especially tediously saved documents that can cause noise or interference in the picture, resulting in difficultly recognized writing. Our research aims to build an autoencoder for denoising text images and evaluate the OCR's performance in converting the denoised image into text. The first step in the research is to test the OCR characteristics on the original text image and the text image given Gaussian noise. The next step is to build the optimal autoencoder model for denoising by studying the effect of dataset size and optimizer type. The last step is to test the OCR performance on the denoised text image produced by the optimum autoencoder model. The test results show that datasetsize affects denoising performance and OCR performance. From several autoencoder models compared, the autoencoder with dataset size = 40 has the optimum performance, where the MSE values of the model for train and validation are 1277 and 1385, respectively. With images denoised from the optimum model, the OCR performance in converting images into text is 100%.
In today's industrial processes, data-driven soft sensors are a frequently used tool for predicting quality variables. autoencoder (AE) is an unsupervised algorithm which can extract latent features from initial d...
详细信息
ISBN:
(纸本)9798350321050
In today's industrial processes, data-driven soft sensors are a frequently used tool for predicting quality variables. autoencoder (AE) is an unsupervised algorithm which can extract latent features from initial data. However, during the feature extraction process, the traditional autoencoder does not consider the correlation between modeling input variables and quality variables to be predicted. To solve this issue, a novel autoencoder based on variable correlation analysis (VCA-AE) is proposed. In VCA-AE, the correlation of modeling input variables and quality variables to be predicted is performed by correlation analysis, and input variables are divided into two parts, which are input to the sub-autoencoder to extract latent features, respectively. In each sub-autoencoder, input variables and quality variables have the same correlation. Next, a feedforward neural network Extreme Learning Machine (ELM) is used to develop soft sensor model based on the extracted latent feature variables and quality variables. Finally, the effectiveness of the proposed soft sensor model combining VCA-AE and ELM is illustrated by an experiment of the industrial PTA process.
Nuclear Magnetic Resonance (NMR) spectroscopy is crucial for molecular structure analysis but poses challenges due to high dimensionality and noise. We propose a deep learning approach that combines autoencoders and C...
详细信息
ISBN:
(纸本)9798350350661;9798350350654
Nuclear Magnetic Resonance (NMR) spectroscopy is crucial for molecular structure analysis but poses challenges due to high dimensionality and noise. We propose a deep learning approach that combines autoencoders and Convolutional Neural Networks (CNNs) for improved NMR spectra classification. An autoencoder reduces the data to compact latent representations, which a CNN then classifies. Our method, evaluated on a comprehensive NMR dataset, shows significant accuracy improvements over direct CNN classification on raw spectra and other baselines. The autoencoder effectively captures essential features, enhancing the CNN's performance. This framework addresses NMR classification challenges, offering a robust tool for researchers and practitioners. NMR Classification which mainly is dealt manually for now and classified by the spectra peaks as case or control, can be now classified using our proposed framework. In this we are achieving 80.9% accuracy on NMR Spectra dataset. This framework is an improved solution for NMR spectroscopy with least human intervention.
Automatic detection of human-related anomalous events in surveillance videos is challenging, owing to unclear definition of anomalies and insufficiency of training data. Generally, the irregular human motion patterns ...
详细信息
Automatic detection of human-related anomalous events in surveillance videos is challenging, owing to unclear definition of anomalies and insufficiency of training data. Generally, the irregular human motion patterns can be regarded as human-related abnormal events. Therefore, we propose a novel method to operate directly on sequences of human skeleton graphs for discovering the normal patterns of human motion. The sequence of skeleton graphs is decomposed into two sub-components: global movement and local posture sequences. The global component is utilized to compute local component. The local component sequences are then input to our network for capturing normal spatial-temporal motion patterns of human skeleton. Our network is established on a Spatial-temporal Graph Convolutional autoencoder (ST-GCAE) and embedded with Long Short-Term Memory (LSTM) network in hidden layers for exploring the temporal cues, which is thus called Spatial-temporal Graph Convolutional autoencoder with Embedded Long Short-Term Memory Network (STGCAE-LSTM). Different from traditional autoencoder, STGCAE-LSTM owns a single-encoder-dual-decoder architecture, which is capable of reconstructing the input and predicting the unseen future simultaneously. Then, samples that deviate from normal patterns are detected as anomalies with fusion of reconstruction and prediction errors. Experimental results on four challenging datasets demonstrate advantages of our method over other state-of-the-art algorithms. (c) 2021 Elsevier B.V. All rights reserved.
Domain adaptation aims to facilitate the learning task in an unlabeled target domain by leveraging the auxiliary knowledge in a well-labeled source domain from a different distribution. Almost existing autoencoder-bas...
详细信息
Domain adaptation aims to facilitate the learning task in an unlabeled target domain by leveraging the auxiliary knowledge in a well-labeled source domain from a different distribution. Almost existing autoencoder-based domain adaptation approaches focus on learning domain-invariant representations to reduce the distribution discrepancy between source and target domains. However, there is still a weakness existing in these approaches: the class-discriminative information of the two domains may be damaged while aligning the distributions of the source and target domains, which makes the samples with different classes close to each other, leading to performance degradation. To tackle this issue, we propose a novel dual-representation autoencoder (DRAE) to learn dual-domain-invariant representations for domain adaptation. Specifically, DRAE consists of three learning phases. First, DRAE learns global representations of all source and target data to maximize the interclass distance in each domain and minimize the marginal distribution and conditional distribution of both domains simultaneously. Second, DRAE extracts local representations of instances sharing the same label in both domains to maintain class-discriminative information in each class. Finally, DRAE constructs dual representations by aligning the global and local representations with different weights. Using three text and two image datasets and 12 state-of-the-art domain adaptation methods, the extensive experiments have demonstrated the effectiveness of DRAE.
With the development of several services, traffic signal preemption is carried out for emergency tasks. For performing workflow intent, cloud systems offer unlimited virtual resources for designing the traffic signal ...
详细信息
The anomaly detection for multimode industrial process is a challenging problem, because the multiple operation modes present various main distributions of monitored variables, and the dynamic sequential characteristi...
详细信息
The anomaly detection for multimode industrial process is a challenging problem, because the multiple operation modes present various main distributions of monitored variables, and the dynamic sequential characteristics exist within each operation mode. This paper proposes an anomaly detection method based on sequence-to-sequence gated recurrent units (SGRU). First, to better model both the cross-mode trends and mode-specific sequential characteristics, a main reconstruction module and residual reconstruction module are integrated to improve the ability to represent complex process. Both modules are implemented by SGRUs. Second, a reconstruction error prediction module is designed to estimate the mean values of mode-specific reconstruction errors, which helps to determine the more reliable alarm thresholds. Third, the two anomaly indicators are utilized to represent the deviation degree of monitored variables against the normal conditions, according to the statistical errors and biases of reconstructions, respectively. The effectiveness of the proposed method is validated on simulations with multimode process, and on the practical data set collected from the Cleaning-in-Place multimode process of an aseptic beverage filling line in a real factory.
Great achievements have been made during the last decades in the field of Electrical Capacitance Tomography(ECT)image ***,there is still a need to make these image reconstruction results faster and of better ***,Deep ...
详细信息
Great achievements have been made during the last decades in the field of Electrical Capacitance Tomography(ECT)image ***,there is still a need to make these image reconstruction results faster and of better ***,Deep Learning(DL)is flourishing and is adopted in many *** DL is very good at dealing with complex nonlinear functions and it is built using several series of Artificial Neural Networks(ANNs).An ECT image reconstruction model using DNN is proposed in this *** proposed model mainly uses Residual autoencoder called(ECT_ResAE).Alarge-scale dataset of 320 k instances have been generated to train and test the proposed ECT_ResAE *** instance contains two vectors;a distinct permittivity distribution and its corresponding capacitance *** capacitance vector has been modulated to generate a 66×66 image,and represented to the ECT_ResAE as an *** scalability and practicability of the ECT_ResAE network are tested using noisy data,new samples,and experimental *** experimental results show that the proposed ECT_ResAE image reconstruction model provides accurate reconstructed *** achieved an average image Correlation Coefficient(CC)of more than 99%and an averageRelative ImageError(IE)around 8.5%.
暂无评论