New Criteria for Stability of Generalized Neural Networks Including Markov Jump Parameters and Additive Time Delays

Samidurai, Rajendran; Manivannan, R.; Ahn, Choon Ki; Karimi, Hamid Reza

doi:10.1109/tsmc.2016.2609147

Cited by 85 publications

(29 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, our results have an important significance in theory and in practical applications of NNs with time delays. In addition, the proposed method in this paper can be extendable to many famous dynamical systems, such as cellular NNs [8], state estimation problem [14,15], filtering problem [48], impulsive problem [49,50], Markovian jump NNs [34], and sampled data control problem [47]. This will occur in the near future.…”

Section: Discussionmentioning

confidence: 92%

“…Tank 1 and tank 2 are placed below tank 3 and tank 4 to receive water flow by the action of gravity. As shown in Figure 1, the QTPS can be expressed clearly using the NN model (see, e.g., [31,33,34,46,47]). The differential equation for the mass balances in the QTPS can be expressed as follows: The differential equations describing the mass balances in the delayed equations.…”

Section: Numerical Examplesmentioning

confidence: 99%

“…To develop a more interesting realistic problem, leakage delay can be easily added in QTPS by the inlet of water to the tanks and are meaningful in our practical life. However, until now, this has not been explored in the previous literature (see, e.g., [31,33,34,46,47]). Moreover, in this example, transport delays between valves and tanks being interval timevarying, the following aspects are also taken into account.…”

Section: Numerical Examplesmentioning

confidence: 99%

“…More recently, the authors in [11,12] investigated the delay-dependent stability criteria for NNs with interval timevarying delays via an augmented LKF and RCC approach. More recently, the authors in [31][32][33][34] investigated the stability problems of NNs with time-varying delays, based on the integral inequality technique and also demonstrated that the proposed criteria are applied to the practical application, showing how to derive efficient stability criteria for a real-world problem. The main contributions of this paper are highlighted in the following viewpoints:…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Delay-dependent stability criteria for neutral-type neural networks with interval time-varying delay signals under the effects of leakage delay

et al. 2018

Self Cite

View full text Add to dashboard Cite

We examine the stability problem for delayed neutral-type neural networks (NNs) with interval time-varying delay signals under the effects of leakage term by constructing a suitable Lyapunov-Krasovskii functionals (LKFs) with the triple-and four-integral terms and using the famous Jensen inequality, Wirtinger single integral inequality (WSII), and Wirtinger double integral inequality (WDII), combined with the reciprocally convex approach (RCC) for the stability of addressing NNs. Therefore, the major contribution of this study lies in a consideration of new integral inequalities and improved LKFs, fully taking the relationship between the terms in the Leibniz-Newton formula within the framework of linear matrix inequalities (LMIs). Moreover, we assume that the lower bound of interval time-varying delay is not restricted to zero. Using several examples, we show that the proposed stability criterion is less conservative than previous results. Also, the proposed technique is applied to benchmark problem that is associated with reasonable issues to showing feasibility on a real-world problem, including transporting time delay signals and leakage delay as a process variable in the quadruple-tank process system.

show abstract

Section: Discussionmentioning

confidence: 92%

Section: Numerical Examplesmentioning

confidence: 99%

Section: Numerical Examplesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Delay-dependent stability criteria for neutral-type neural networks with interval time-varying delay signals under the effects of leakage delay

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…Once the data is collected from the three different compounds an approach is created in the MATLAB toolbox (R2010a, Mathworks, Natick, MA, USA) with the following characteristics specified in Table 4: There are five units in the input phase because there are five gas sensors; in this way a five-unit hidden phase is chosen to reduce complexity and because three organic compounds are selected, three outputs are required for the output phase, which means that three units are required in the output phase [20].…”

Section: Mq-2 Mq-135mentioning

confidence: 99%

Classification via an Embedded Approach

Rubio

Avila

Melendez

et al. 2017

Designs

View full text Add to dashboard Cite

This paper presents the results of an automated volatile organic compound (VOC) classification process implemented by embedding a machine learning algorithm into an Arduino Uno board. An electronic nose prototype is constructed to detect VOCs from three different fruits. The electronic nose is constructed using an array of five tin dioxide (SnO 2 ) gas sensors, an Arduino Uno board used as a data acquisition section, as well as an intelligent classification module by embedding an approach function which receives data signals from the electronic nose. For the intelligent classification module, a training algorithm is also implemented to create the base of a portable, automated, fast-response, and economical electronic nose device. This solution proposes a portable system to identify and classify VOCs without using a personal computer (PC). Results show an acceptable precision for the embedded approach in comparison with the performance of a toolbox used in a PC. This constitutes an embedded solution able to recognize VOCs in a reliable way to create application products for a wide variety of industries, which are able to classify data acquired by an electronic nose, as VOCs. With this proposed and implemented algorithm, a precision of 99% for classification was achieved into the embedded solution.

show abstract

Non‐Fragile Extended Dissipativity Control Design for Generalized Neural Networks with Interval Time‐Delay Signals

Manivannan

Samidurai

Cao

et al. 2018

Asian Journal of Control

Self Cite

View full text Add to dashboard Cite

The problem of non-fragile extended dissipative control design for a class of generalized neural networks (GNNs) with interval time-delay signals is investigated in this paper. By constructing a suitable Lyapunov-Krasovskii functional (LKF) with double and triple integral terms, and estimating their derivative by using the Wirtinger single integral inequality (WSII) and Wirtinger double integral inequality (WDII) technique respectively, and that is mixed with the reciprocally convex combination (RCC) approach. A new delay-dependent non-fragile extended dissipative control design for GNNs are expressed in terms of the linear matrix inequalities (LMIs). Then, the desired non-fragile extended dissipative controller can be obtained by solving the linear matrix inequalities (LMIs). Furthermore, a non-fragile state feedback controller is designed for GNNs such that the closed-loop system is extended dissiptive. Thus, the non-fragile extended dissipative controller can be adopted to deal with the non-fragile  2 − ∞ performance, non-fragile  ∞ performance, non-fragile passive performance, non-fragile mixed  ∞ and passivity performance, and non-fragile dissipative performance for GNNs by selecting the weighting matrices. Finally, simulation studies are demonstrated for showing the feasibility of the proposed method. Among them, one example was supported by the real-life application of the quadruple tank process system.

show abstract

New Criteria for Stability of Generalized Neural Networks Including Markov Jump Parameters and Additive Time Delays

Cited by 85 publications

References 53 publications

Delay-dependent stability criteria for neutral-type neural networks with interval time-varying delay signals under the effects of leakage delay

Delay-dependent stability criteria for neutral-type neural networks with interval time-varying delay signals under the effects of leakage delay

Classification via an Embedded Approach

Non‐Fragile Extended Dissipativity Control Design for Generalized Neural Networks with Interval Time‐Delay Signals

Contact Info

Product

Resources

About