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.
Deep Convolutional Neural Networks (CNN) enforce supervised information only at the output layer, and hidden layers are trained by back propagating the prediction error from the output layer without explicit supervision. We propose a supervised feature learning approach, Label Consistent Neural Network, which enforces direct supervision in late hidden layers in a novel way. We associate each neuron...
Fine-grained classification involves distinguishing between similar sub-categories based on subtle differences in highly localized regions, therefore, accurate localization of discriminative regions remains a major challenge. We describe a patch-based framework to address this problem. We introduce triplets of patches with geometric constraints to improve the accuracy of patch localization, and automatically...
Participants in the restructured power market are seeking effective generation resource bidding strategies. This paper proposes a methodology to obtain the optimal bidding strategy for generation companies (GENCOs) participating in electric power markets. Supply function like model, which chooses to strategically bid generation prices of bid curves, is used here for the day-ahead market auction. Different...
Latent Low-Rank Representation (Lat LRR) has the empirical capability of identifying "salient" features. However, the reason behind this feature extraction effect is still not understood. Its optimization leads to non-unique solutions and has high computational complexity, limiting its potential in practice. We show that Lat LRR learns a transformation matrix which suppresses the most significant...
Due to the high dimensionality of hyperspectral data, dimension reduction is becoming an important problem in hyperspectral image classification. Band selection can retain the information which is capable of keeping the original meaning of the data, and thus has attracted more attention. This paper tackles the band selection problem from the perspective of multiple classifiers combination, which can...
The up-to-date researches focused on compressive sensing (CS) have indicated that a CS-based system could be very sensitive to signal noise which contaminates the input signal prior to measurement. In this paper, it is demonstrated that the SNR loss of the recovered signal can be estimated by the subsampling rate. The conditions based on which the proposed estimator is applied are theoretical analyzed...
A novel extreme rainfall prediction model combined with data mining is proposed in this paper. Because of the special nature of hydrological data, our model uses the clustering method to group the next year's average extreme rainfall and then establish a hybrid extreme rainfall prediction model based on building neural networks for each group. Furthermore discriminant analysis is employed to classify...
Support Vector Machine, a statistic procedure, is robust and has good performance when applied to farmland image segmentation. It can effectively identify the crop rows, even though they have some intersection at some points because of weeds of the leaves growth of the crops. However, the Support Vector Machine has relatively high time complexity and cannot meet the requirements of real-time processing...
A novel compact bandstop filter (BSF) based on signal interference technique is presented in this paper. The designed structure consists of two bilateral transmission lines and one central series capacitor. Bandwidth and rejection level of the filter can be controlled by changing the circuit parameters. The equivalent model and a set of analytical formulas for the design of the new BSFs are provided...
A compact and novel lowpass filter using three-order corner-cutting TCMRC (T-shaped compact microstrip resonator cells) is presented. Such a structure decreases the unnecessary coupling between the microstrip transmission lines and presents a good impedance matching and less spurious responses. Based on this theory, the proposed filter has been designed, fabricated and measured. From the measurements,...
The Modulated Wideband Converter (MWC) is a recently proposed analogv-to-digital converter (ADC) based on Compressive Sensing (CS) theory. Unlike conventional ADCs, its quantization reference voltage, which is important to the system performance, does not equal the maximum amplitude of original analog signal. In this paper, the quantization reference voltage of the MWC is theoretically analyzed and...
In this paper, we address the problem of estimating the 3D structure and motion of a non-rigid object based on feature points throughout a image sequence. The main limitation of existing factorization methods is that they are difficult to provide correct structure and motion estimates: the motion matrix has a repetitive structure which is not represented by these methods. In order to cope with this...
In this paper, we deal with a cross-layer optimization problem in Ad Hoc networks. Based on network utility maximization framework, we formulate the joint congestion and power control problem providing SINR guarantee and energy saving. We adopt dual decomposition technique to deduce two maximization sub problem, and then design the optimal distributed congestion control algorithm at the transport...
Ad Hoc networks are characterized as fast time-varying. Thus, fast distributed algorithm to implement self-management is indispensable, especially for QoS support. In this paper, we propose rate control with QoS support in Ad Hoc networks based on primal-dual interior-point method. We apply Gaussian belief propagation algorithm to compute the Newton step. For implementing distributed computation in...
Human motion tracking is crucial for many important applications. In this paper we propose an approach to human motion tracking from monocular image sequences. First, a system is developed for solving the occlusion problems. The system is based on recursive least square (RLS) and genetic algorithm (GA) that introduced a new way to eliminate occlusion. Then, in order to reduce the noise of position...
The knowledge discovery of driver behavior in traffic accident database is implemented based on multi-agent technology. The multi-agent technology helps to solve the complexity problems of both discovery and driver's behavior, and achieve more intelligence for driver behavior knowledge discovery. The application of pair-database-coordination mechanism and heuristic algorithm makes the knowledge discovery...
In the past decades of years the systematic research on pain mechanisms has been the focus of scientists. The traditional Chinese medicine such as acupuncture has shown great potential in pain relief. Transcutaneous Electrical Acupoint Stimulation (TEAS) has been used and bicoherence of EEG has been extracted and used as evaluation criterion of pain relief in the research. In this study 12 volunteers...
An adaptive learning rate Backpropagation Neural Network (BPNN) is proposed to image segmentation of rice disease spots. Rice blast is a common disease of rice and is tested in this paper. Firstly, the combination of different color feature parameters is selected as the input of the BPNN. Secondly, a BPNN with 5 input, 10 hidden neurons and 1 output is constructed to rice blast spots segmentation...
In this paper we propose an approach to estimating the deformation degree of a non-rigid shape from monocular image sequence with uncertainty and missing data. The non-rigid shape can be represented as a weighted combination of K rigid basis shapes. Since K denotes the number of basis shapes that can represent the shape sequence, it provides a measure of deformation degree of the shape sequence. K...
This paper concerns the problem of automatic image stitching which mainly applies to the image sequence even those including noise images. And it uses a method based on invariant features to realize fully automatic image stitching, in which it includes two main parts: image matching and image blending. As the noises images have large differences between the other images, when using SIFT features to...
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.