Traffic sensing system requires to periodically collect spatial-temporal traffic data distributed among road networks, which results in overhigh bandwidth consumption and storage cost in a large-scale road network. Se...
详细信息
Traffic sensing system requires to periodically collect spatial-temporal traffic data distributed among road networks, which results in overhigh bandwidth consumption and storage cost in a large-scale road network. Several compressive sensing-based algorithms are proposed to reconstruct missing traffic data with limited traffic observation. However, there still exist great challenges to be addressed. First, these existing algorithms are always iteration-based, whose time complexity will explosively increase with the growth of network scale. Furthermore, these algorithms have to be re-executed even if only a small fraction of data changes, which is not suitable for dynamic traffic environments. To overcome these issues, we investigate a novel service architecture of traffic sensing based on mobile edge computing where collected data is pre-processed at the edge node and reconstructed at cloud servers, respectively. On this basis, we formulate the problem of Missing Traffic Data reconstruction (MTDR), which aims at maximizing data reconstruction accuracy within limited observation data. Further, we develop a deep-learning-based algorithm called stacked denoising autoencoder for MTDR (SDAE-MTDR), where three denoisingautoencoders are trained in order and then stacked together for parameter fine-tuning based on cross-entropy-based loss function. Finally, we conduct comprehensive performance evaluation based on realistic vehicular traces and the simulation results demonstrate the superiority of the proposed algorithm compared with competitive solutions.
Centrifugal blowers are easy to get faults due to the harsh working environment, and appropriate fault early warning is of great significance for predictive maintenance. Traditional fault early warning methods have po...
详细信息
Centrifugal blowers are easy to get faults due to the harsh working environment, and appropriate fault early warning is of great significance for predictive maintenance. Traditional fault early warning methods have poor resistance and feature learning ability in dealing with multivariate data with noise, and cannot achieve domain adaptation in different working environments. Aimed at solving these problems, this paper proposes a novel fault early warning method for centrifugal blowers based on stacked denoising autoencoder with sliding window (SWSDAE) and transfer learning. The developed SW-SDAE model can effectively learn representative degradation features and temporal dependence from multivariate time-series data with noise. The reconstruction errors of SW-SDAE are used to construct the health indicators, which accurately characterizes the health status of the centrifugal blower. Meanwhile, transfer learning is employed to solve the problem of domain adaptation for different working environments. The established source domain warning model is successfully transferred to the target domain by minimizing the maximum mean discrepancy. When the health indicator exceeds the warning threshold, a fault early warning is performed. Experimental results demonstrate that the developed SW-SDAE warning model integrating transfer learning significantly resists the interference of noise and improves the domain adaptability for different working conditions. The proposed method achieves fault early warning 5.67 h without false alarms before failure and shows superior warning performance compared with traditional warning methods.
Visual saliency detection is usually regarded as an image pre-processing method to predict and locate the position and shape of saliency regions. However, many existing saliency detection methods can only obtain the l...
详细信息
Visual saliency detection is usually regarded as an image pre-processing method to predict and locate the position and shape of saliency regions. However, many existing saliency detection methods can only obtain the local or even incorrect position and shape of saliency regions, resulting in incomplete detection and segmentation of the salient target region. In order to solve this problem, a visual saliency detection method based on scale invariant feature and stacked denoising autoencoder is proposed. Firstly, the deep belief network would be pretrained to initialize the parameters of stacked denoising autoencoder network. Secondly, different from traditional features, scale invariant feature is not limited to the size, resolution, and content of original images. At the same time, it can help the network to restore important features of original images more accurately in multi-scale space. So, scale invariant feature is adopted to design the loss function of the network to complete self-training and update the parameters. Finally, the difference between the final reconstructed image obtained by stacked denoising autoencoder and the original is regarded as the final saliency map. In the experiment, we test the performance of the proposed method in both saliency prediction and saliency object segmentation. The experimental results show that the proposed method has good ability in saliency prediction and has the best performance in saliency object segmentation than other comparison saliency prediction methods and saliency object detection methods.
In an extensive-scale surveillance system, the quality of the surveillance camera installed varies. This variation of surveillance camera produces different image quality in terms of resolution, illumination, and nois...
详细信息
In an extensive-scale surveillance system, the quality of the surveillance camera installed varies. This variation of surveillance camera produces different image quality in terms of resolution, illumination, and noise. The quality of the captured image depends on the surveillance camera hardware, placement and orientation, and the surrounding light. A pixelated, low illumination and noisy image produced by a low-quality surveillance camera causes critical issues for video surveillance face recognition systems. To address these issues, a deep learning image enhancement (DLIE) model is proposed. By utilizing a deep learning architecture such as a convolutional neural network (CNN) and a denoisingautoencoder, the image quality can be enhanced. The DLIE model is able to improve image resolution and illumination and reduce noise in an image. There are two deep learning blocks (DLB) in the DLIE model, which are DLB1 and DLB2. Both DLBs are arranged in parallel so that all the stated problems can be addressed simultaneously. DLB1 is proposed to address the occurrence of pixelated images by reconstructing a low-resolution image into a high-resolution image using a CNN. DLB2 used the capability of a denoisingautoencoder to reconstruct the corrupted image into a clean image by enhancing the dark and noisy images. The output of each DLB is fused using image fusion to obtain the optimum image quality. The image is evaluated using the peak to signal noise ratio (PSNR) and structural similarity index (SSIM). The enhanced image from the DLIE model exhibits superior quality compared to the original image ranging from 13.3625 to 22.7728 for PSNR and 0.6207 to 0.8155 for SSIM.
Pulsed thermography is one of the most popular thermography inspection methods. During an experiment of pulsed thermography, a specimen is quickly heated, and infrared images are captured to provide information about ...
详细信息
ISBN:
(纸本)9781728143958
Pulsed thermography is one of the most popular thermography inspection methods. During an experiment of pulsed thermography, a specimen is quickly heated, and infrared images are captured to provide information about the specimen's surface and subsurface conditions. Adequate transformations are usually performed to enhance the contrast of the thermal images and to highlight the abnormal regions before these thermal images are visually inspected. Given that deep neural networks have been a success in computer vision in the past few years, a data contrast enhancement approach with stacked denoising autoencoder (DAE) is proposed in this paper to enhance the abnormal regions in the thermal frames gathered by pulsed thermography. Compared to the direct principal component thermography, the proposed method can enhance the abnormalities evidently without weakening important details.
based fingerprint localization technology has become one of the most practical methods for localizing mobile users due to its non-intrusive nature, low cost and no additional equipment required. However, the fluctuati...
详细信息
ISBN:
(纸本)9798350334722
based fingerprint localization technology has become one of the most practical methods for localizing mobile users due to its non-intrusive nature, low cost and no additional equipment required. However, the fluctuation of WiFi signal seriously affects the accuracy of WiFi fingerprint localization. To address this problem, this paper proposes a solution using data augmentation combined with stacked denoising autoencoder (SDAE). Data augmentation can facilitate the neural network to learn the mapping relationship between the fluctuating WiFi signals and coordinates. And the SDAE can obtain a robust and time-independent feature from the dynamic WiFi signal. A convolutional neural network is also used to build a floor classification model to determine the height, and a multilayer perceptron (MLP) is used to build a regression model to determine the relative coordinates. Experimental results on public datasets show that the method improves system robustness and localization accuracy.
Polar codes, with low encoding/decoding complexity and capacity-achieving potential, have drawn much attention recently. It is very critical to study the impact of fading on polar codes implementation into wireless co...
详细信息
Polar codes, with low encoding/decoding complexity and capacity-achieving potential, have drawn much attention recently. It is very critical to study the impact of fading on polar codes implementation into wireless communications. Existing research works on polar codes over the fading channel use simplified fading channel models while further reducing the frame error rate is highly needed. In this letter, using the structure of polar codes we propose the deep learning based scheme for polar codes over Rayleigh fading channels. Simulation results verify that our proposed scheme can significantly decrease the frame error rate for polar codes over Rayleigh fading channels.
Active vision sensing is widely used in intelligent robotic welding for bead detection and tracking. Disturbed by welding noise such as arc light and spatter, it is a hard work to extract the laser stripe and feature ...
详细信息
Active vision sensing is widely used in intelligent robotic welding for bead detection and tracking. Disturbed by welding noise such as arc light and spatter, it is a hard work to extract the laser stripe and feature values. This paper presents a method for denoising and feature extraction of weld seam profiles with strong welding noise in gas metal arc welding (GMAW) process by using stacked denoising autoencoder (SDAE). This algorithm encodes the images of various butt joints with strong welding noise to several useful intermediate representations, which can be decoded to the image of pure laser stripe in 1-pixel width. The results show little deviations when there are large spatters across the laser stripe. A back propagation neural network (BPNN) is developed to verify the reliability of the intermediate representations gotten from the encoder, in which the intermediate representations are input neurons and the weld seam width is output neuron. The average width error in training dataset and testing dataset is 0.042 mm and 0.061 mm. The results show that this algorithm can extract the weld seam profiles with strong welding noise and extract feature values accurately.
High-frequency oscillations (HFOs) recorded by the intracranial electroencephalography (iEEG) are the promising biomarkers of epileptogenic zones. Accurate detection of HFOs is the key to pre-operative assessment for ...
详细信息
High-frequency oscillations (HFOs) recorded by the intracranial electroencephalography (iEEG) are the promising biomarkers of epileptogenic zones. Accurate detection of HFOs is the key to pre-operative assessment for epilepsy. Due to the subjective bias caused by manual features and the class imbalance between HFOs and false HFOs, it is difficult to obtain satisfactory detection performance by the existing methods. To solve these problems, we put forward a novel method to accurately detect HFOs based on the stacked denoising autoencoder (SDAE) and the ensemble classifier with sample weight adjusting factors. First, the adjustable threshold of Hilbert envelopes is proposed to isolate the events of interest (EoIs) from background activities. Then, the SDAE network is utilized to automatically extract features of EoIs in the time-frequency domain. Finally, the AdaBoost-based support vector machine ensemble classifier with sample weight adjusting factors is devised to separate HFOs from EoIs by using the extracted features. These adjusting factors are used to solve the class imbalance problem by adjusting sample weights when learning the base classifiers. Our HFO detection method is evaluated by using clinical iEEG data recorded from 20 patients with medically refractory epilepsy. The experimental results show that our detection method outperforms some existing methods in terms of sensitivity and false discovery rate. In addition, the HFOs detected by our method are effective for localizing seizure onset zones.
In modern plants, industrial processes generally operate under different modes, and reliable monitoring for such processes is highly important. One of the key challenges is how to accurately identify the various modes...
详细信息
In modern plants, industrial processes generally operate under different modes, and reliable monitoring for such processes is highly important. One of the key challenges is how to accurately identify the various modes including steady modes and transitions modes. In this paper, a novel monitoring scheme based on hierarchical mode identification strategy and stacked denoising autoencoder (HMI-SDAE) is proposed for multimode processes. First, a novel mode division strategy called HMI is presented. In HMI, the Gaussian mixture model (GMM) is adopted to realize the preliminary identification of various modes by extracting the global distribution features of the variables. In this way, the whole multimode process is divided into multiple steady modes. An improved density peaks clustering algorithm based on local density relation search (LDRSDPC) is proposed to achieve the transition mode identification by fully utilizing the local distribution features of the process variables involved in any two adjacent steady modes and transition mode between them. A decision criterion combined with local density relation is constructed to automatically determine the clustering center. In this hierarchical way, multiple steady modes and transition modes are divided automatically and accurately. Secondly, the deep nonlinear features embedded in process variables are mined by SDAE, and the robust monitoring model is established for each steady mode. A monitoring statistic is constructed using the reconstruction error for detecting faults. The effectiveness and feasibility of the proposed HMI-SDAE monitoring scheme are illustrated with a numerical example and Tennessee Eastman (TE) process.(c) 2022 Elsevier Ltd. All rights reserved.
暂无评论