Deep convolutional neural networks (CNNs) have become one of the state-of-the-art methods for image classification in various domains. For biomedical image classification where the number of training ...images is generally limited, transfer learning using CNNs is often applied. Such technique extracts generic image features from nature image datasets and these features can be directly adopted for feature extraction in smaller datasets. In this paper, we propose a novel deep neural network architecture based on transfer learning for microscopic image classification. In our proposed network, we concatenate the features extracted from three pretrained deep CNNs. The concatenated features are then used to train two fully-connected layers to perform classification. In the experiments on both the 2D-Hela and the PAP-smear datasets, our proposed network architecture produces significant performance gains comparing to the neural network structure that uses only features extracted from single CNN and several traditional classification methods.
This paper investigates the composite nonlinear feedback (CNF) control technique for linear singular systems with input saturation. First, a linear feedback control law is designed for the step ...tracking control problem of linear singular systems subject to input saturation. Then, based on this linear feedback gain, a CNF control law is constructed to improve the transient performance of the closed-loop system. By introducing a generalized Lyapunov equation, this paper develops a design procedure for constructing the CNF control law for linear singular systems with input saturation. After decomposing the closed-loop system into fast subsystem and slow subsystem, it can be shown that the nonlinear part of the CNF control law only relies on slow subsystem. The improvement of transient performance by the proposed design method is demonstrated by an illustrative example.
Endosomes are subcellular organelles which serve as important transport compartments in eukaryotic cells. Fluorescence microscopy is a widely applied technology to study endosomes at the subcellular ...level. In general, a microscopy image can contain a large number of organelles and endosomes in particular. Detecting and annotating endosomes in fluorescence microscopy images is a critical part in the study of subcellular trafficking processes. Such annotation is usually performed by human inspection, which is time-consuming and prone to inaccuracy if carried out by inexperienced analysts. This paper proposes a two-stage method for automated detection of ring-like endosomes. The method consists of a localization stage cascaded by an identification stage. Given a test microscopy image, the localization stage generates a voting-map by locally comparing the query endosome patches and the test image based on a bag-of-words model. Using the voting-map, a number of candidate patches of endosomes are determined. Subsequently, in the identification stage, a support vector machine (SVM) is trained using the endosome patches and the background pattern patches. Each of the candidate patches is classified by the SVM to rule out those patches of endosome-like background patterns. The performance of the proposed method is evaluated with real microscopy images of human myeloid endothelial cells. It is shown that the proposed method significantly outperforms several state-of-the-art competing methods using multiple performance metrics.
Composite nonlinear feedback (CNF) control technique for tracking control problems is extended to the output regulation problem of singular linear systems with input saturation. A state feedback CNF ...control law and an output feedback CNF control law are constructed respectively for the output regulation problem of singular linear systems with input saturation. It is shown that the output regulation problem by CNF control is solvable under the same solvability conditions of the output regulation problem by linear control. However, with the virtue of the CNF control, the transient performance of the closed-loop system can be improved by carefully designing the linear part and the nonlinear part of the CNF control law. The design procedure and the improvement of the transient performance of the closed-loop system are illustrated with a numerical simulation.
Earth surface vibration signals source classification and propagation distance estimation attract increasing attention in recent years due to the wide applications in many areas. In this study, the ...authors develop a hybrid classification and propagation distance estimation algorithm for general earth surface vibration sources. The spectrogram (SPEC) feature characterising the energy distribution of vibrations is first developed for signal representation in this study. The kernel-based extreme learning machine (KELM) algorithm is then adopted for the vibration source classification and propagation distance estimation. Comparing with the conventional approaches, the proposed KELM + SPEC algorithm is not only effective in characterising the time- and frequency-domain features of vibrations, but also superior in accuracy and efficiency. To test the effectiveness of the proposed KELM + SPEC algorithm, experiments on real collected vibration signals are presented, where simulations on both periodic and aperiodic vibrations are carried out in the study. Comparisons to various existing vibration signal extraction and classification algorithms are provided to show the advantages of the proposed KELM + SPEC algorithm.
An important problem in artificial intelligence is to develop an efficient system that can adapt to new knowledge in an incremental manner without forgetting previously learned knowledge. Although ...Convolutional Neural Networks (CNNs) are good at learning strong classifier and discriminative features, CNNs can not perform well in incremental classifier learning due to the catastrophic forgetting problem in the retraining process. In this paper, we propose a novel yet extremely simple approach to enhance the discriminative property of features for incremental classifier learning. We build a network for the universal feature space in which a group of image classes have intra-class compactness and inter-class separability. And, we model each incremental class to have a maximum margin from the rest of the models in universal space. Experiments are conducted on CIFAR-100 dataset and IMage Database for Context Aware Advertisement (IMDB-CAA) we collected. The results demonstrate the superiority of our approach, improving performance on CIFAR-100 dataset over state-of-the-art incremental learning systems. Furthermore, experiments on few-short incremental learning setting show very promising performance although we use only 4% of training samples on CIFAR-100 dataset.
This paper tackles the issue of global stabilization for a class of delayed switched inertial neural networks (SINN). Distinct from the frequently employed reduced-order technique, this paper studies ...SINN directly through non-reduced order method. By constructing a novel Lyapunov functional and using Barbalat Lemma, sufficient conditions for the global asymptotic stabilization issue and global exponential stabilization issue of the considered SINN are established. Numerical simulations further confirm the feasibility of the main results. The comparative research shows that global stabilization results of this paper complement and improve some existing work.
This paper addresses the passivity problem for delayed non-autonomous discrete-time inertial neural networks (NDINN), including the discrete-time switched inertial neural networks (DSINN) with ...state-dependent discontinuous right-hand side as its special case. First, we take a linear transformation to transform the original network into first-order difference equations. Second, by utilizing the Lyapunov direct method and with the help of the property of maximum singular value, we present a passivity criterion for the NDINN with delay-dependent linear matrix inequalities. Combining with the characteristic function method, the proposed analytical approach for NDINN is further extended to the DSINN. Finally, two simulation examples validate the efficacy of the analytical results.
This paper addresses the output feedback composite nonlinear feedback (CNF) controller design for a tracking control problem of single-input single-output (SISO) singular linear systems with input ...saturation. The output feedback CNF control law is constructed based on a state feedback CNF control law for the tracking control problem and a state observer. The stability of the closed-loop system under the output feedback CNF control law is established for an output feedback CNF control law with a singular full state observer. The design procedure and the improvement of the transient performance of the closed-loop system are illustrated with an example.
This paper addresses global dissipativity for a class of delayed discrete-time inertial neural networks (DINN). With a newly developed discrete-time Halanay inequality, a novel criterion of the ...global dissipativity for the DINN is established. Moreover, the global robust dissipativity of DINN with bounded parameter uncertainties is also investigated. Meanwhile, some specific estimates of global attractive sets and positive invariant sets are derived. Finally, two simulation examples validate the efficacy of the proposed results.