The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Most traditional soft sensor modeling requires the labeled training samples that contain both subsidiary and key variables. However, key variables are difficult to be obtained online due to lack of detection information or high measurement cost. In this paper, a novel semi-supervised learning algorithm, called cotraining-style kernel extreme learning machine, is proposed to exploit unlabeled training...
Crowd counting on still images is very challenging due to heavy occlusions and scale variations. In this paper, we aim to develop a method that can accurately estimate the crowd count from a still image. Recently, convolutional neural networks have been shown effective in many computer vision tasks including crowd counting. To this end, we propose a fully convolutional network (FCN) architecture to...
In this paper, we presented an improved vehicle detection algorithm based on object proposals. In the training part, by using Selective Search algorithm, we firstly segment the vehicle areas in the sample set as positive examples, other regions as negative examples. Then PHOG (Pyramid Histogram of Oriented Gradient) features of the positive samples and negative ones after separately being labeled...
Although Deep Convolutional Neural Networks (CNNs) have liberated their power in various computer vision tasks, the most important components of CNN, convolutional layers and fully connected layers, are still limited to linear transformations. In this paper, we propose a novel Factorized Bilinear (FB) layer to model the pairwise feature interactions by considering the quadratic terms in the transformations...
A two-layer fuzzy kernel regression (TLFKR) model is proposed for understanding human emotional intention in human-robot interaction, where TLFKR model consists of two layers, including fuzzy c-means (FCM) with kernel ridge regression (Kernel 1) for information analysis layer, fuzzy support vector regressions (FSVR) (Kernel 2) for intention understanding layer. TLFKR model represents the weight impact...
Although the existing correlation filter based on trackers has appeared to be more excellent in the visual tracking problem, there is still tremendous space for the improvement of the tracking performance, especially in the occlusion situation which is often ignored due to the difficulty in detection and processing. In this paper, a scale-adaptive tracker is proposed to handle the case of occlusion...
Municipal solid waste incineration (MSWI) becomes the most popular technique to enhance environment protection. This process produces one of the most toxic chemicals in the world, i.e., polychlorinated dibenzo-p-dioxins and polychlorinated dibenzofurans (PCDD/Fs). The dioxin (DXN) production should be restricted rigidly by using operation optimization and control of MSWI process based on present industrial...
In the distillation process, many important process variables are often difficult to be measured online. For example, the aviation kerosene is an important index of operation quality, but current methods cannot obtain the real-time value of the aviation kerosene efficiently. To solve this problem, a method of selecting the input variable based on partial least squares regression (PLS) is proposed...
Inspired by recent work in Optical Character Recognition (OCR) and image captioning, an end-to-end system is utilized which implements the recognition of image formulas. An attention based two-way encoder-decoder structure has been proposed to normal image captioning systems, and it achieves good performance on the recognition of image formulas task. This structure together with a new training method...
Monitoring of dynamic industrial process has been increasingly important due to more and more strict safety and reliability requirements. Popular methods like time lagged arrangement-based and subspace-based approaches exhibit good performance in fault detection, however, they suffer from difficulty in accurately isolating faulty variables and diagnosing fault types. To alleviate this difficulty,...
The contribution of this paper is to bridge the gap on understanding the mathematical structure and the computational implementation of a convolutional neural network (CNN) using a minimal model (Minimal CNN). The proposed minimal CNN is presented using a layering approach. This approach provides a concise and accessible understanding of the main mathematical operations of a CNN. Hence, it benefits...
In this paper, we investigate deep neural networks for blind motion deblurring. Instead of regressing for the motion blur kernel and performing non-blind deblurring outside of the network (as most methods do), we propose a compact and elegant end-to-end deblurring network. Inspired by the data-driven sparse-coding approaches that are capable of capturing linear dependencies in data, we generalize...
Many existing scene parsing methods adopt Convolutional Neural Networks with fixed-size receptive fields, which frequently result in inconsistent predictions of large objects and invisibility of small objects. To tackle this issue, we propose a scale-adaptive convolution to acquire flexiblesize receptive fields during scene parsing. Through adding a new scale regression layer, we can dynamically infer...
In this paper, we introduce a new channel pruning method to accelerate very deep convolutional neural networks. Given a trained CNN model, we propose an iterative two-step algorithm to effectively prune each layer, by a LASSO regression based channel selection and least square reconstruction. We further generalize this algorithm to multi-layer and multi-branch cases. Our method reduces the accumulated...
Most recent CNN architectures use average pooling as a final feature encoding step. In the field of fine-grained recognition, however, recent global representations like bilinear pooling offer improved performance. In this paper, we generalize average and bilinear pooling to “α-pooling”, allowing for learning the pooling strategy during training. In addition, we present a novel way to visualize decisions...
When we use binary tree support vector machine (SVM) to work the multi-classification problems out, we always find that the structure of the binary tree has a large chance and it has a great influence on the classification efficiency of the classification model. To solve this problem, according to the idea of separating the most widely distributed class first, an improved binary tree SVM multiple...
With the rapid development of society and technology, home service robot is becoming cheaper and smarter. Facing with the difficulties of aging and shortage of labor, we can use home service robot (HSR) as a good companion and servant. However, the security and reliability problems have become bottlenecks in this field. It is meaningful to do researches on fault diagnosis of HSR. Due to its excellent...
The low noise amplifier (LNA) is a significant device in RF front-end. In this paper, a straight and efficient modeling method for LNA based on the Volterra series with recursive least squares (RLS) algorithm is proposed. Instead of calculating the high nonlinearity order of Volterra kernels, the proposed method extracts the first three order Volterra kernels characterizing the memory effect to construct...
In this paper the problem of improving the reliability of nonlinear dynamic objects fault diagnosing is presented. Model-based diagnostics nonparametric identification method is used. Diagnostic models are constructed on the base of Volterra kernels wavelet transforms. The effectiveness of the suggested diagnostic models based on Volterra kernels wavelet transforms is analyzed on the basis of simulation...
A novel projection twin support vector machine (PTSVM), termed as NPTSVM, is presented in this paper for binary classification. Although this method determines two projection vectors using the same way as PTSVM, it has more advantages than existing PTSVMs. First, NPTSVM does not have to calculate inverse matrices during the learning process, which makes the training speed of NPTSVM be much faster...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.