Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 21
Filtrar
Mais filtros










Base de dados
Intervalo de ano de publicação
1.
Comput Methods Programs Biomed ; 212: 106464, 2021 Nov.
Artigo em Inglês | MEDLINE | ID: mdl-34736166

RESUMO

BACKGROUND AND OBJECTIVE: Recognizing different tissue components is one of the most fundamental and essential works in digital pathology. Current methods are often based on convolutional neural networks (CNNs), which need numerous annotated samples for training. Creating large-scale histopathological datasets is labor-intensive, where interactive data annotation is a potential solution. METHODS: We propose DELR (Deep Embedding-based Logistic Regression) to enable rapid model training and inference for histopathological image analysis. DELR utilizes a pretrained CNN to encode images as compact embeddings with low computational cost. The embeddings are then used to train a Logistic Regression model efficiently. We implemented DELR in an active learning framework, and validated it on three histopathological problems (binary, 4-category, and 8-category classification challenge for lung, breast, and colorectal cancer, respectively). We also investigated the influence of active learning strategy and type of the encoder. RESULTS: On all the three datasets, DELR can achieve an area under curve (AUC) metric higher than 0.95 with only 100 image patches per class. Although its AUC is slightly lower than a fine-tuned CNN counterpart, DELR can be 536, 316, and 1481 times faster after pre-encoding. Moreover, DELR is proved to be compatible with a variety of active learning strategies and encoders. CONCLUSIONS: DELR can achieve comparable accuracy to CNN with rapid running speed. These advantages make it a potential solution for real-time interactive data annotation.


Assuntos
Redes Neurais de Computação , Área Sob a Curva , Processamento de Imagem Assistida por Computador , Modelos Logísticos
3.
Comput Methods Programs Biomed ; 204: 106047, 2021 Jun.
Artigo em Inglês | MEDLINE | ID: mdl-33789213

RESUMO

BACKGROUND AND OBJECTIVE: Colon cancer is a fatal disease, and a comprehensive understanding of the tumor microenvironment (TME) could lead to better risk stratification, prognosis prediction, and therapy management. In this paper, we focused on the automatic evaluation of TME in giga-pixel digital histopathology whole-slide images. METHODS: A convolutional neural network is used to recognize nine different content presented in colon cancer whole-slide images. Several implementation details, including the foreground filtering and stain normalization are discussed. Based on the whole-slide segmentation, several TME descriptors are quantified and correlated with the clinical outcome by Kaplan-Meier analysis and Cox regression. Specifically, the stroma, tumor, necrosis, and lymphocyte components are discussed. RESULTS: We validated the method on colon adenocarcinoma cases from The Cancer Genome Atlas project. The result shows that the stroma is an independent predictor of progression-free interval (PFI) after corrected by age and pathological stage, with a hazard ratio of 1.665 (95%CI: 1.110~2.495, p = 0.014). High-level necrosis component and lymphocytes component tend to be correlated with poor PFI, with a hazard ratio of 1.552 (95%CI: 0.943~2.554, p = 0.084) and 1.512 (95%CI: 0.979~2.336, p = 0.062), respectively. CONCLUSIONS: The result reveals the complex role of the tumor microenvironment in colon adenocarcinoma, and the quantified descriptors are potential predictors of disease progression. The method could be considered for risk stratification and targeted therapy and extend to other types of cancer, leading to a better understanding of the tumor microenvironment.


Assuntos
Adenocarcinoma , Neoplasias do Colo , Aprendizado Profundo , Adenocarcinoma/diagnóstico por imagem , Humanos , Microambiente Tumoral
4.
IEEE Trans Cybern ; PP2021 Feb 26.
Artigo em Inglês | MEDLINE | ID: mdl-33635815

RESUMO

This article investigates the issue of observer-based security control for the interconnected semi-Markovian jump systems with completely unknown and uncertain bounded transition probabilities (TPs). Considering the limited bandwidth of communication network in each subsystem, an adaptive event-triggered mechanism (AETM) is developed to relieve more network burden than the conventional event-triggered mechanism (ETM), where the designed adaptive law can dynamically adjust the triggering threshold. In addition, two Bernoulli distributed variables are utilized to describe the influence of denial-of-service (DoS) attacks and false-data injection (FDI) attacks in the proposed observer-based security control strategy. Moreover, some sufficient criterions are derived for the stochastic stability with an H∞ attenuation level of augmented systems. Meanwhile, the observer and controller gain matrices can be attained simultaneously with the help of linear matrix inequalities (LMIs). Finally, we provide a practical example to demonstrate the effectiveness of theoretical results.

5.
Artigo em Inglês | MEDLINE | ID: mdl-33587719

RESUMO

For full-state constrained nonlinear systems with input saturation, this article studies the output-feedback tracking control under the condition that the states and external disturbances are both unmeasurable. A novel composite observer consisting of state observer and disturbance observer is designed to deal with the unmeasurable states and disturbances simultaneously. Distinct from the related literature, an auxiliary system with approximate coordinate transformation is used to attenuate the effects generated by input saturation. Then, using radial basis function neural networks (RBF NNs) and the barrier Lyapunov function (BLF), an opportune backstepping design procedure is given with employing the dynamic surface control (DSC) to avoid the problem of ``explosion of complexity.'' Based on the given design procedure, an output-feedback controller is constructed and guarantees all the signals in the closed-loop system are semiglobally uniformly ultimately bounded. It is shown that the tracking error is regulated by the saturated input error and design parameters without the violation of the state constraints. Finally, a simulation example of a robot arm is given to demonstrate the effectiveness of the proposed controller.

6.
ISA Trans ; 117: 303-308, 2021 Nov.
Artigo em Inglês | MEDLINE | ID: mdl-33593485

RESUMO

While actuator rate limit is common and counted in practical engineering, it has not drawn enough attention in control synthesis especially system identification. In this note, it aims to construct a new identification framework for first-order plus time-delay (FOPTD) systems affected by actuator rate limit. It is found that the rate limit can lead to an illusory delay in system reaction curves. Furthermore, necessary quantitative analyses are given to validate that excessively estimated or illusory delay significantly influences estimation accuracy of other parameters and subsequently degrades control performance. Two illustrative examples and experimental results are provided to demonstrate the adverse effect of actuator rate limit on system identification and the effectiveness of the proposed model structure on control performance.

7.
IEEE Trans Neural Netw Learn Syst ; 32(9): 3909-3918, 2021 09.
Artigo em Inglês | MEDLINE | ID: mdl-32822313

RESUMO

This article deals with H∞ state estimation of neural networks with mixed delays. In order to make full use of delay information, novel delay-product Lyapunov-Krasovskii functional (LKF) by using parameterized delay interval is first constructed. Then, generalized free-weighting-matrix integral inequality is used to estimate the derivative of LKF to reduce the conservatism. Also, a more general activation function is further applied by combining with parameterized delay interval in order to obtain a more accurate estimator model. Finally, sufficient conditions are derived to confirm that the estimation error system is asymptotically stable with a prescribed H∞ performance. Numerical examples are simulated to show the benefits of our proposed method.

8.
Sensors (Basel) ; 20(5)2020 Mar 04.
Artigo em Inglês | MEDLINE | ID: mdl-32143360

RESUMO

Data collection is one of the key technologies in wireless sensor networks. Due to the limited battery resources of sensors, mobile collectors are introduced to collect data instead of multi-hop data relay. However, how to decrease the data delay based on the cooperation of mobile collectors is a main problem. To solve this problem, a matching game-based data collection algorithm is proposed. First, some high-level cluster heads are elected. Second, by introducing a matching game model, the data collection problem is modeled as a one to one matching problem. Then, according to the preferences of mobile collectors and cluster heads, the benefit matrices are established. Based on the proposed matching algorithm, each mobile collector selects a cluster head to collect the data packets. Performance analysis proves that the matching result is stable, optimal, and unique. Simulation results show that the proposed algorithm is superior to other existing approach in terms of the reduction in data delay.

9.
ISA Trans ; 104: 15-25, 2020 Sep.
Artigo em Inglês | MEDLINE | ID: mdl-31822362

RESUMO

This paper is engaged in investigating the observer-based event-triggered output feedback control issue for fractional-order cyber-physical systems with stochastic network attacks, where the order scale of the fractional derivative used is 0<α<1. An event-triggered scheme (ETS) with output-independent threshold is proposed to renew the observer input so as to reduce the redundant data communications. Considering the effects of the ETS and network attacks, a novel closed-loop fractional-order control system model is constructed. By making use of fractional-order Lyapunov indirect approach, sufficient conditions that can insure the global stochastic asymptotic stability of the established closed-loop control system are obtained. Moreover, according to the singular value decomposition (SVD) of matrix, the co-design of the gains of the desired observer and controller is addressed by finding the solution of the linear matrix inequalities (LMIs). Finally, a numerical example and a diesel engine control system are provided to validate the feasibility of the adopted observer-based control method.

10.
ISA Trans ; 96: 132-142, 2020 Jan.
Artigo em Inglês | MEDLINE | ID: mdl-31200925

RESUMO

This paper is primarily concerned with the event-triggered adaptive containment control for the second-order linear multi-agent systems (MASs) subject to time-varying input delays. Different from traditional methods, the triggering thresholds can be time-variable and achieved online, which are regulated by the triggering error. Then the number of transmitted data is modulated by two adaptive laws that play a crucial role in deciding whether to release the current data or not. By selecting two augmented types of Lyapunov-Krasovskii functionals (LKFs) and applying three effective inequalities, these earlier ignored information can be recollected and the field of application can be greatly enlarged. Moreover, the issues on delay-dependence respectively take uniform input delay and nonuniform input ones into consideration, in which the inter-relationship among time-delays can be involved. Finally, two MAS examples are exploited to illustrate our theoretical results.

11.
ISA Trans ; 81: 63-75, 2018 Oct.
Artigo em Inglês | MEDLINE | ID: mdl-30078519

RESUMO

This paper investigates the problem of distributed event-triggered H∞ filtering over sensor networks with sensor saturations and cyber-attacks. By taking the effects of sensor saturations existing in spatially distributed sensors and randomly occurring cyber-attacks into consideration, a distributed event-triggered filtering error system is firstly established. Then, sufficient conditions guaranteeing the system asymptotically stable with H∞ performance are obtained by means of Lyapunov stability theory. Moreover, the explicit expressions of distributed H∞ filters and the weighting matrices of distributed event-triggered scheme are achieved by solving a set of linear matrix inequalities (LMIs). Finally, two examples are given to illustrate the usefulness of the designed distributed event-triggered H∞ filters.

12.
ISA Trans ; 72: 122-137, 2018 Jan.
Artigo em Inglês | MEDLINE | ID: mdl-29157873

RESUMO

This paper addresses the problem of H∞ filter design for T-S fuzzy systems with saturation nonlinearities. For the purpose of reducing network burden, an output-dependent triggering scheme and a quantizer are introduced at the same time. The output-dependent triggering scheme is applied to determine whether or not the current instant information should be transmitted to the quantizer. Saturation nonlinearities, as a common phenomenon in networked systems due to the physical or technological constraints, is also considered here. Then a filtering error model with aforementioned characteristics is established. By using Lyapunov functional approach and stochastic analysis techniques, some matrix inequality-based sufficient conditions for the existence of the fuzzy filter are obtained. Moreover, a co-design algorithm for solving the suitable filter and the event generator is derived. Finally, a numerical example is provided to demonstrate the effectiveness of the proposed approach.

13.
ISA Trans ; 70: 116-124, 2017 Sep.
Artigo em Inglês | MEDLINE | ID: mdl-28571756

RESUMO

This paper studies the asymptotic stability for a class of neutral systems with mixed time-varying delays. Through utilizing some Wirtinger-based integral inequalities and extending the convex combination technique, the upper bound on derivative of Lyapunov-Krasovskii (L-K) functional can be estimated more tightly and three mixed-delay-dependent criteria are proposed in terms of linear matrix inequalities (LMIs), in which the nonlinearity and parameter uncertainties are also involved, respectively. Different from those existent works, based on the interconnected relationship between neutral delay and state one, some novel triple integral functional terms are constructed and the conservatism can be effectively reduced. Finally, two numerical examples are given to show the benefits of the proposed criteria.

14.
ISA Trans ; 65: 44-50, 2016 Nov.
Artigo em Inglês | MEDLINE | ID: mdl-27665144

RESUMO

This paper investigates the output feedback control problem of a class of nonlinear systems with sensor noise and actuator degradation. Firstly, by using the descriptor observer approach, the origin system is transformed into a descriptor system. On the basis of the descriptor system, a novel Proportional Derivative (PD) observer is developed to asymptotically estimate sensor noise and system state simultaneously. Then, by designing an adaptive law to estimate the effectiveness of actuator, an adaptive observer-based controller is constructed to ensure that system state can be regulated to the origin asymptotically. Finally, the design scheme is applied to address a flexible joint robot link problem.

15.
Neural Netw ; 82: 39-48, 2016 Oct.
Artigo em Inglês | MEDLINE | ID: mdl-27459409

RESUMO

This paper is concerned with H∞ filter design for a class of neural network systems with event-triggered communication scheme and quantization. Firstly, a new event-triggered communication scheme is introduced to determine whether or not the current sampled sensor data should be broadcasted and transmitted to quantizer, which can save the limited communication resource. Secondly, a logarithmic quantizer is used to quantify the sampled data, which can reduce the data transmission rate in the network. Thirdly, considering the influence of the constrained network resource, we investigate the problem of H∞ filter design for a class of event-triggered neural network systems with quantization. By using Lyapunov functional and linear matrix inequality (LMI) techniques, some delay-dependent stability conditions for the existence of the desired filter are obtained. Furthermore, the explicit expression is given for the designed filter parameters in terms of LMIs. Finally, a numerical example is given to show the usefulness of the obtained theoretical results.


Assuntos
Algoritmos , Redes Neurais de Computação , Simulação por Computador/tendências , Fatores de Tempo
16.
ScientificWorldJournal ; 2014: 840185, 2014.
Artigo em Inglês | MEDLINE | ID: mdl-25110747

RESUMO

Synchronization control of stochastic neural networks with time-varying discrete and continuous delays has been investigated. A novel control scheme is proposed using the Lyapunov functional method and linear matrix inequality (LMI) approach. Sufficient conditions have been derived to ensure the global asymptotical mean-square stability for the error system, and thus the drive system synchronizes with the response system. Also, the control gain matrix can be obtained. With these effective methods, synchronization can be achieved. Simulation results are presented to show the effectiveness of the theoretical results.


Assuntos
Modelos Teóricos , Redes Neurais de Computação , Algoritmos
17.
ISA Trans ; 53(3): 709-16, 2014 May.
Artigo em Inglês | MEDLINE | ID: mdl-24530195

RESUMO

This paper investigates the problem of global finite-time stabilization in probability for a class of stochastic nonlinear systems. The drift and diffusion terms satisfy lower-triangular or upper-triangular homogeneous growth conditions. By adding one power integrator technique, an output feedback controller is first designed for the nominal system without perturbing nonlinearities. Based on homogeneous domination approach and stochastic finite-time stability theorem, it is proved that the solution of the closed-loop system will converge to the origin in finite time and stay at the origin thereafter with probability one. Two simulation examples are presented to illustrate the effectiveness of the proposed design procedure.


Assuntos
Algoritmos , Retroalimentação , Modelos Estatísticos , Dinâmica não Linear , Processos Estocásticos , Simulação por Computador
18.
ISA Trans ; 52(4): 494-500, 2013 Jul.
Artigo em Inglês | MEDLINE | ID: mdl-23664204

RESUMO

This paper investigates the problem of output feedback stabilization for a class of high-order feedforward nonlinear systems with time-varying input delay. First, a scaling gain is introduced into the system under a set of coordinate transformations. Then, the authors construct an observer and controller to make the nominal system globally asymptotically stable. Based on homogeneous domination approach and Lyapunov-Krasovskii functional, it is shown that the closed-loop system can be rendered globally asymptotically stable by the scaling gain. Finally, two simulation examples are provided to illustrate the effectiveness of the proposed scheme.


Assuntos
Algoritmos , Retroalimentação , Modelos Teóricos , Dinâmica não Linear , Simulação por Computador
19.
IEEE Trans Neural Netw Learn Syst ; 24(9): 1459-66, 2013 Sep.
Artigo em Inglês | MEDLINE | ID: mdl-24808582

RESUMO

In this brief, by employing an improved Lyapunov-Krasovskii functional (LKF) and combining the reciprocal convex technique with the convex one, a new sufficient condition is derived to guarantee a class of delayed neural networks (DNNs) to be globally asymptotically stable. Since some previously ignored terms can be considered during the estimation of the derivative of LKF, a less conservative stability criterion is derived in the forms of linear matrix inequalities, whose solvability heavily depends on the information of addressed DNNs. Finally, we demonstrate by two numerical examples that our results reduce the conservatism more efficiently than some currently used methods.


Assuntos
Modelos Neurológicos , Rede Nervosa/fisiologia , Redes Neurais de Computação , Neurônios/fisiologia , Algoritmos , Animais , Simulação por Computador , Humanos , Fatores de Tempo
20.
IEEE Trans Neural Netw ; 21(8): 1365-71, 2010 Aug.
Artigo em Inglês | MEDLINE | ID: mdl-20667811

RESUMO

In this brief, based on Lyapunov-Krasovskii functional approach and appropriate integral inequality, a new sufficient condition is derived to guarantee the global stability for delayed neural networks with unbounded distributed delay, in which the improved delay-partitioning technique and general convex combination are employed. The LMI-based criterion heavily depends on both the upper and lower bounds on time delay and its derivative, which is different from the existent ones and has wider application fields than some present results. Finally, three numerical examples can illustrate the efficiency of the new method based on the reduced conservatism which can be achieved by thinning the delay interval.


Assuntos
Inteligência Artificial , Modelos Teóricos , Redes Neurais de Computação , Reconhecimento Automatizado de Padrão/métodos , Processamento de Sinais Assistido por Computador , Algoritmos , Animais , Humanos , Fatores de Tempo
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA
...