Time filter

Source Type

Chen B.,Hubei Normal University | Chen J.,Hubei Normal University | Chen J.,Huazhong University of Science and Technology | Chen J.,Key Laboratory of Image Processing
Neural Networks | Year: 2016

The present paper studies global O(t-α) stability and global asymptotical periodicity for a non-autonomous fractional-order neural networks with time-varying delays (FDNN). Firstly, some sufficient conditions are established to ensure that a non-autonomous FDNN is global O(t-α) stable based on a new Lyapunov function method and Leibniz rule for fractional differentiation. Next it is shown that the periodic or autonomous FDNN cannot generate exactly nonconstant periodic solution under any circumstances. Finally, we show that all solutions converge to a same periodic function for a periodic FDNN by using a fractional-order differential inequality technique. Our issues, methods and results are all new. © 2015 Elsevier Ltd. Source

Wu A.,Hubei Normal University | Wu A.,Xian Jiaotong University | Wu A.,Huazhong University of Science and Technology | Zeng Z.,Huazhong University of Science and Technology | Zeng Z.,Key Laboratory of Image Processing
Circuits, Systems, and Signal Processing | Year: 2014

Memristive neural systems are a ground breaking concept that is helping us understand the behavior of electronic brain. In this paper, a general class of memristive neural systems with time delays is formulated and investigated. Several succinct criteria are given to ascertain the input-to-state stability via nonsmooth analysis and control theory. These conditions, which can be directly derived from the parameters of the system, are easily verified. The obtained results extend some previous works on conventional neural systems. A numerical example is provided to show the efficiency of the proposed approach. © 2013 Springer Science+Business Media New York. Source

Pan J.,Key Laboratory of Image Processing | Pan J.,Huazhong University of Science and Technology | Pan J.,Hubei Engineering University | Hu H.,Key Laboratory of Image Processing | And 4 more authors.
Entropy | Year: 2016

By exploiting the statistical analysis method, human dynamics provides new insights to the research of human behavior. In this paper, we analyze the characteristics of the computer operating behavior through a modified multiscale entropy algorithm with both the interval time series and the number series of individuals' operating behavior been investigated. We also discuss the activity of individuals' behavior from the three groups denoted as the retiree group, the student group and the worker group based on the nature of their jobs. We find that the operating behavior of the retiree group exhibits more complex dynamics than the other two groups and further present a reasonable explanation for this phenomenon. Our findings offer new insights for the further understanding of individual behavior at different time scales. © 2015 by the authors. Source

Liu X.,Huazhong University of Science and Technology | Liu X.,Key Laboratory of Image Processing | Liu X.,Wuhan University of Science and Technology | Liu X.,Hubei Province Key Laboratory of Intelligent Information Processing | And 2 more authors.
Neurocomputing | Year: 2015

Mass localization is a crucial problem in computer-aided detection (CAD) system for the diagnosis of suspicious regions in mammograms. In this paper, a new automatic mass detection method for breast cancer in mammographic images is proposed. Firstly, suspicious regions are located with an adaptive region growing method, named multiple concentric layers (MCL) approach. Prior knowledge is utilized by tuning parameters with training data set during the MCL step. Then, the initial regions are further refined with narrow band based active contour (NBAC), which can improve the segmentation accuracy of masses. Texture features and geometry features are extracted from the regions of interest (ROI) containing the segmented suspicious regions and the boundaries of the segmentation. The texture features are computed from gray level co-occurrence matrix (GLCM) and completed local binary pattern (CLBP). Finally, the ROIs are classified by means of support vector machine (SVM), with supervision provided by the radiologist's diagnosis. To deal with the imbalance problem regarding the number of non-masses and masses, supersampling and downsampling are incorporated. The method was evaluated on a dataset with 429 craniocaudal (CC) view images, containing 504 masses. Among them, 219 images containing 260 masses are used to optimize the parameters during MCL step, and are used to train SVM. The remaining 210 images (with 244 masses) are used to test the performance. Masses are detected with 82.4% sensitivity with 5.3 false positives per image (FPsI) with MCL, and after active contour refinement, feature analysis and classification, it obtained 1.48 FPsI at the sensitivity 78.2%. Testing on 164 normal mammographic images showed 5.18 FPsI with MCL and 1.51 FPsI after classification. Experiments on mediolateral oblique (MLO) images have also been performed, the proposed method achieved a sensitivity 75.6% at 1.38 FPsI. The method is also analyzed with free response operating characteristic (FROC) and compared with previous methods. Overall, the proposed method is a promising approach to achieve low FPsI while maintaining a high sensitivity. © 2014 Elsevier B.V. Source

Wu A.,Huazhong University of Science and Technology | Wu A.,Key Laboratory of Image Processing | Zeng Z.,Huazhong University of Science and Technology | Zeng Z.,Key Laboratory of Image Processing
Neural Networks | Year: 2012

The paper introduces a general class of memristor-based recurrent neural networks with time-varying delays. Conditions on the nondivergence and global attractivity are established by using local inhibition, respectively. Moreover, exponential convergence of the networks is studied by using local invariant sets. The analysis in the paper employs results from the theory of differential equations with discontinuous right-hand sides as introduced by Filippov. The obtained results extend some previous works on conventional recurrent neural networks. © 2012. Source

Discover hidden collaborations