Inferring nonlinear lateral flow immunoassay state-space models via an unscented Kalman filter

Zeng, Nianyin; Wang, Zidong; Zhang, Hong

doi:10.1007/s11432-016-0280-9

Cited by 81 publications

(25 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Future research topics would include the extension of the main results to more complex systems by using more up-to-date techniques. [28][29][30][31][32][33][34][35]…”

Section: Resultsmentioning

confidence: 99%

Sampled‐data consensus of nonlinear multiagent systems subject to cyber attacks

Zhang

Wang

Liu

et al. 2017

Intl J Robust & Nonlinear

Self Cite

View full text Add to dashboard Cite

This paper is concerned with the sampled-data consensus problem for a class of nonlinear multiagent systems subject to cyber attacks. The considered attacks are assumed to be recoverable, which destroy the connectivity of the network topology with directed spanning tree. In light of the designed sampled-data control protocol, a more general switched system is proposed to model both the cyber attacks and the sampled-data mechanism within a unified framework. Then, by using the contradiction methods, the solution of a class of differential equations is provided to deal with the technical challenge resulting from the switching and sampling issues. Furthermore, in terms of such a solution combined with the constructed piecewise Lyapunov function, sufficient conditions are derived under which the nonlinear multiagent systems subject to attacks achieve the consensus exponentially. The relationship between the attack frequency and the sampling period is also revealed through the obtained conditions. Finally, simulations are given to show the effectiveness of the proposed results. KEYWORDSconsensus, cyber attacks, multiagent systems, sampled data, switched systems Corrections added on 3 July 2017, after first online publication: the word 'Equation' had been inserted incorrectly in some cases in the text and has since been removed.Int J Robust Nonlinear Control. 2018;28:53-67.wileyonlinelibrary.com/journal/rnc

show abstract

“…Future research topics would include the extension of the main results to more complex systems by using more up-to-date techniques. [28][29][30][31][32][33][34][35]…”

Section: Resultsmentioning

confidence: 99%

Sampled‐data consensus of nonlinear multiagent systems subject to cyber attacks

Zhang

Wang

Liu

et al. 2017

Intl J Robust & Nonlinear

Self Cite

View full text Add to dashboard Cite

show abstract

“…Finally, a numerical simulation example has been demonstrated to show the effectiveness of the proposed filtering method. The future research topics would include the extensions of the main algorithms developed in this paper to more complicated systems (see, for example, previous works [22][23][24][25][26][27][28][29][30][31][32][33][34][35][36][37] ).…”

Section: Discussionmentioning

confidence: 99%

Recursive filtering for state‐saturated systems with randomly occurring nonlinearities and missing measurements

Chen

Wang

et al. 2017

Intl J Robust & Nonlinear

Self Cite

View full text Add to dashboard Cite

This paper deals with the filtering problem for a class of discrete-time statesaturated systems subject to randomly occurring nonlinearities and missing measurements. A set of mutually independent Bernoulli random variables is used to describe the random occurrence of the missing measurements. Due to the simultaneous consideration of the state saturation, the randomly occurring nonlinearities, and the missing measurements, it is extremely hard to calculate the actual filtering error covariance in a closed form. As such, the objective of this paper is to construct an upper bound for the filtering error covariance and then design the filter parameters to minimize such an upper bound. The performance of the proposed filters is analyzed in terms of boundedness and monotonicity.Specially, we have shown that the minimum upper bound is always bounded under a mild assumption. Moreover, the relationship between the estimator performance and the arrival probability of the measurements is discussed. A numerical simulation is used to demonstrate the effectiveness of the filtering method.

show abstract

“…Figure 2 gives a toy example that consists of two conv layers, two pooling layers, and two fully connected layers. CNN can achieve comparable or even better performance than traditional AI approaches, while it does not need to manual design the features (Zeng et al, 2014 , 2016a , b , 2017a , b ).…”

Section: Methodsmentioning

confidence: 99%

Multiple Sclerosis Identification by 14-Layer Convolutional Neural Network With Batch Normalization, Dropout, and Stochastic Pooling

et al. 2018

View full text Add to dashboard Cite

Aim: Multiple sclerosis is a severe brain and/or spinal cord disease. It may lead to a wide range of symptoms. Hence, the early diagnosis and treatment is quite important.Method: This study proposed a 14-layer convolutional neural network, combined with three advanced techniques: batch normalization, dropout, and stochastic pooling. The output of the stochastic pooling was obtained via sampling from a multinomial distribution formed from the activations of each pooling region. In addition, we used data augmentation method to enhance the training set. In total 10 runs were implemented with the hold-out randomly set for each run.Results: The results showed that our 14-layer CNN secured a sensitivity of 98.77 ± 0.35%, a specificity of 98.76 ± 0.58%, and an accuracy of 98.77 ± 0.39%.Conclusion: Our results were compared with CNN using maximum pooling and average pooling. The comparison shows stochastic pooling gives better performance than other two pooling methods. Furthermore, we compared our proposed method with six state-of-the-art approaches, including five traditional artificial intelligence methods and one deep learning method. The comparison shows our method is superior to all other six state-of-the-art approaches.

show abstract

Inferring nonlinear lateral flow immunoassay state-space models via an unscented Kalman filter

Cited by 81 publications

References 42 publications

Sampled‐data consensus of nonlinear multiagent systems subject to cyber attacks

Sampled‐data consensus of nonlinear multiagent systems subject to cyber attacks

Recursive filtering for state‐saturated systems with randomly occurring nonlinearities and missing measurements

Multiple Sclerosis Identification by 14-Layer Convolutional Neural Network With Batch Normalization, Dropout, and Stochastic Pooling

Contact Info

Product

Resources

About