As an effective tool for monitoring surface irregularities in remote sensing, hyperspectral anomaly detection (HAD) has garnered increasing attention. However, how to improve the detection accuracy remains a formidabl...
详细信息
ISBN:
(纸本)9798350360332;9798350360325
As an effective tool for monitoring surface irregularities in remote sensing, hyperspectral anomaly detection (HAD) has garnered increasing attention. However, how to improve the detection accuracy remains a formidable challenge, due mainly to the noise and variations in the spectral domain, especially when there is lack of the labelled data for training. To tackle these difficulties, a novel unsupervised HAD method is proposed. First, 1-D Singular Spectrum Analysis (SSA) is employed to eliminate outliers in the spectral domain. Second, the SSA-smoothed hypercube undergoes a sparse autoencoder for background reconstruction, where the reconstruction error is used to extract anomalous pixels. Finally, the RX algorithm is employed to segment anomalous pixels from the background. Comprehensive experiments on four publicly available datasets have validated the superior performance of our method in effectively enhancing the separability between anomaly pixels and their respective backgrounds, outperforming a few state-of-the-art methods, particularly in terms of the detection accuracy.
High Efficiency Video Coding (HEVC) is designed to deliver a video communication with better quality at reduced bit rate. For intra coding, HEVC employs an effective hierarchical quad tree partitioning and an exhausti...
详细信息
High Efficiency Video Coding (HEVC) is designed to deliver a video communication with better quality at reduced bit rate. For intra coding, HEVC employs an effective hierarchical quad tree partitioning and an exhaustive optimal mode search which increases the time complexity. Aiming this issue, we propose a Support Vector Machine (SVM)-based method to effectively predict the intra mode. Compared to the standard HEVC encoder HM-15.0, the proposed method could reduce 57.6% of encoding time at a bit-rate penalty of 3.3% at an average PSNR decline of only around 0.09 dB.
The function of most multi-objective algorithms (MOEAs) is to provide an overall trade-off Pareto front to the decision makers (DMs). But DMs actually tend to have a preference for a specific subset of the Pareto fron...
详细信息
The function of most multi-objective algorithms (MOEAs) is to provide an overall trade-off Pareto front to the decision makers (DMs). But DMs actually tend to have a preference for a specific subset of the Pareto front. So combing decision makers' preference information with many-objective optimization methods has recently been a hot survey topic in the research field of many-objective optimization. The preference-inspired coevolutionary algorithms using goal vectors (PICEA-g) coevolve a family of decision makers' preferences called preference set together with a population of candidate solutions. It is a classic and effective algorithm, but it has shortcomings in distribution and there is a waste of computing resources. So we use a sparse autoencoder as a controller to perform feature processing on the target solution set in the process of coordinated evolution and modify the fitness assignment formula to improve the diversity. The combination of PICEA-g and sparse autoencoder framework enhance the convergence and expand the ability of the PICEA-g algorithm. The preference-inspired coevolutionary algorithm with sparse autoencoder (PICEA-g/SAE) is evaluated by three widely used benchmark suites and compared with nine classic multi-objective evolutionary algorithms to prove the advantages of the sparse autoencoder framework. The experimental results show that PICEA-g/SAE could have a good performance on many DTLZ test problems. Moreover, PICEA-g/SAE on UF1-9 and WFG1-9 test problems in low dimensions could have good convergence, diversity, and spread compared with other algorithms.
Since December 2019, the world has been intensely affected by the COVID-19 pandemic, caused by the SARS-CoV-2. In the case of a novel virus identification, the early elucidation of taxonomic classification and origin ...
详细信息
Since December 2019, the world has been intensely affected by the COVID-19 pandemic, caused by the SARS-CoV-2. In the case of a novel virus identification, the early elucidation of taxonomic classification and origin of the virus genomic sequence is essential for strategic planning, containment, and treatments. Deep learning techniques have been successfully used in many viral classification problems associated with viral infection diagnosis, metagenomics, phylogenetics, and analysis. Considering that motivation, the authors proposed an efficient viral genome classifier for the SARS-CoV-2 using the deep neural net-work based on the stacked sparse autoencoder (SSAE). For the best performance of the model, we explored the utilization of image representations of the complete genome sequences as the SSAE input to provide a classification of the SARS-CoV-2. For that, a dataset based on k-mers image representation was applied. We performed four experiments to provide different levels of taxonomic classification of the SARS-CoV-2. The SSAE technique provided great performance results in all experiments, achieving classification accuracy between 92% and 100% for the validation set and between 98.9% and 100% when the SARS-CoV-2 samples were applied for the test set. In this work, samples of the SARS-CoV-2 were not used during the training process, only during subsequent tests, in which the model was able to infer the correct classification of the samples in the vast majority of cases. This indicates that our model can be adapted to classify other emerging viruses. Finally, the results indicated the applicability of this deep learning technique in genome classification problems.(c) 2022 The Author(s). Published by Elsevier B.V. on behalf of Research Network of Computational and Structural Biotechnology. This is an open access article under the CC BY license (http://creativecommons. org/licenses/by/4.0/).
Sanitary sewer overflows caused by excessive rainfall derived infiltration and inflow is the major challenge currently faced by municipal administrations, and therefore, the ability to correctly predict the wastewater...
详细信息
Sanitary sewer overflows caused by excessive rainfall derived infiltration and inflow is the major challenge currently faced by municipal administrations, and therefore, the ability to correctly predict the wastewater state of the sanitary sewage system in advance is especially significant. In this paper, we present the design of the sparse autoencoder-based Bidirectional long short-term memory (SAE-BLSTM) network model, a model built on sparse autoencoder (SAE) and Bidirectional long short-term memory (BLSTM) networks to predict the wastewater flow rate in a sanitary sewer system. This network model consists of a data preprocessing segment, the SAE network segment, and the BLSTM network segment. The SAE is capable of performing data dimensionality reduction on high-dimensional original input feature data from which it can extract sparse potential features from the aforementioned high-dimensional original input feature data. The potential features extracted by the SAE hidden layer are concatenated with the smooth historical wastewater flow rate features to create an augmented previous feature vector that more accurately predicts the wastewater flow rate. These augmented previous features are applied to the BLSTM network to predict the future wastewater flow rate. Thus, this network model combines two kinds of abilities, SAE's low-dimensional nonlinear representation for original input feature data and BLSTM's time series prediction for wastewater flow rate. Then, we conducted extensive experiments on the SAE-BLSTM network model utilizing the real-world hydrological time series datasets and employing advanced SVM, FCN, GRU, LSTM, and BLSTM models as comparison algorithms. The experimental results show that our proposed SAE-BLSTM model consistently outperforms the advanced comparison models. Specifically, we selected a 3 months period training dataset in our dataset to train and test the SAE-BLSTM network model. The SAE-BLSTM network model yielded the lowest RMSE, MAE
Room Response Equalization (RRE) systems play a vital role in enhancing the hearing experience in different real-time application areas such as cinema theatres, home theatres, hearing aid implementation, car hi-fi sys...
详细信息
Room Response Equalization (RRE) systems play a vital role in enhancing the hearing experience in different real-time application areas such as cinema theatres, home theatres, hearing aid implementation, car hi-fi systems, etc. Thenceforth, RRE using digital signal processing techniques has been a matter of great interest to researchers for a long time. RRE is intended to provide a listener with a profound audio experience alike the original audio signal. Conventional filtering approaches have been used by several researchers to perform room equalization. However, this article presents a novel technique by cascading a Kautz filter and a sparse autoencoder in performing room equalization. Kautz filters belong to a category of fixed pole IIR filters that use least-square (LS) minimization to generate orthonormal tap-output impulse responses. This LS approximated signal is further trained by a sparse autoencoder, which provides filter coefficients, iteratively optimized, to minimize a cost function. The cost function is considered here in terms of the reconstruction error function. The performance of this hybrid network of equalization is evaluated in terms of mean square error and spectral deviation measures. Computational results show that this hybrid approach yields better results both qualitatively and quantitatively in comparison with the other filtering techniques.
Complicated geological environments lead to a high risk of drilling incidents. Early warning of loss and kick for the drilling process is essential to ensure process safety. On account of the nonlinear and temporal co...
详细信息
Complicated geological environments lead to a high risk of drilling incidents. Early warning of loss and kick for the drilling process is essential to ensure process safety. On account of the nonlinear and temporal correlation of drilling parameters, an early warning method for loss and kick based on sparse autoencoder with multivariate time series is proposed. The sparse autoencoder is utilized for multivariate time series abnormality detection of the drilling process. Abnormal drilling parameter isolation is performed through contribution analysis. Reconstruction analysis and time series segmentation approaches are integrated for abnormal time series trend evaluation. The characteristic of drilling parameters under normal operation learned by the sparse autoencoder and the property of the original time series are taken into account. The final early warning result can be obtained through expert rules based on the trend evaluation result. Case studies are presented based on the data from an actual drilling project. The experiment result shows the effectiveness of the proposed method.
Background: Fault detection and diagnosis technology is of great significance for practical industrial processes. Industrial process characteristics change with time due to various reasons such as changing working con...
详细信息
Background: Fault detection and diagnosis technology is of great significance for practical industrial processes. Industrial process characteristics change with time due to various reasons such as changing working conditions. This will cause false alarm or missing alarm of process monitoring. Methods: In this paper, an adaptive slow feature analysis (SFA) - sparse autoencoder (SAE) algorithm is proposed to establish an adaptive model for time-varying process monitoring. Model update index is built based on timevarying characteristics extracted using SFA model. Process monitoring index is built based on sparse characteristics extracted using SAE model. Through online adaptive update strategy, updated monitoring model is realized to adapt to the time-varying characteristics of the process. Significant findings: The proposed algorithm has good performance on penicillin fermentation process data set and can realize the task of adaptive process monitoring.
Rotating machines (RMs) have vast applicability in almost all the industries in mechanical domain. Rolling element bearings (RBs) are the key elements to ensure that the RMs perform efficiently. RBs are highly prone t...
详细信息
Rotating machines (RMs) have vast applicability in almost all the industries in mechanical domain. Rolling element bearings (RBs) are the key elements to ensure that the RMs perform efficiently. RBs are highly prone to wear and tear which could have devastating consequences such as massive economic losses and accidents. In the past, many time-domain based condition-indicators such as root mean square (RMS), skewness and kurtosis, etc. have been proposed by researchers to diagnose the bearing faults and prevent RM failures. However, they are often insensitive to early stage faults, affected by outliers and possess poor degradation tracking characteristics. To overcome these shortcomings, this paper proposes a novel statistical feature extraction technique called as multiscale statistical moment (MSM) analysis, in combination with sparse autoencoder to detect the incipient faults as well as track the progression of wear. Firstly, the vibration signal are acquired from the bearings to be monitored. Secondly, the MSM features are extracted from the vibration signals. Thirdly, the MSM features corresponding to normal conditions are utilized to train the sparse autoencoder network. Fourthly, the MSM features corresponding to test conditions are supplied to the pre-trained sparse autoencoder model. The MSM technique offers the advantage that it extracts the fault properties contained in multiple time-scales of the vibration signals instead of a single time-scale only. Finally, the dissimilarity between the actual and predicted output is measured to obtain the bearing health indicator (BHI). The experimental results demonstrate that the suggested BHI detects the faults at early stages, possess better sensitivity and trends the bearing degradation more accurately as compared to the traditional techniques such as RMS, kurtosis, and BHI obtained with statistical moment features at single-scale only.
The diagnostic study on single-fault with distinguishing features based on monitoring data analysis is mature and fruitful in recent years. However, the early fault signals collected by practical monitoring systems of...
详细信息
The diagnostic study on single-fault with distinguishing features based on monitoring data analysis is mature and fruitful in recent years. However, the early fault signals collected by practical monitoring systems often possess the following characteristics: 1) Fairly weak signal strength;2) Submerged in powerful background noise;3) Coupling of different fault data. These features not only increase the diagnostic difficulty, but also make the existing methods hardly to get the desired results. Consequently, the early compound faults diagnosis commonly in industrial systems is still a thorny and urgent problem. Therefore, in order to solve this problem and provide technical support for the practical industrial machinery fault diagnosis, a denoising-integrated sparse autoencoder (DISAE) model for early compound faults diagnosis is proposed in this paper. The innovation points of this study mainly include: 1) A feature-enhanced and denoising solution based on fault sensitivity degree (FSD) is designed, and the reconstructed diagnostic signals are acquired. 2) A disassociation framework is formulated, and the data coupling is solved. 3) A weight constraint term of SAE is constructed to improve the effectiveness and diversity of feature learning. 4) An adaptive loss function and a DISAE model is formed, and the early compound faults diagnosis is achieved. Finally, different trials and comparison results display the effectiveness and superiority of the designed DISAE based scheme.
暂无评论