PSO tuned ANFIS equalizer based on fuzzy C-means clustering algorithm

Çavdar, Tuğrul

doi:10.1016/j.aeue.2016.03.006

Cited by 24 publications

(9 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, there exist many optimization technologies, such as particle swarm algorithm [31], ant colony algorithm [32], artificial bee colony algorithm [33], etc. In our work, the artificial immune algorithm is adopted because of not only preserving the solution diversity and avoiding the local optimal, but also its fast convergence.…”

Section: Optimization Of Synchronous Evolution Process Based On Artifmentioning

confidence: 99%

Enhancing network cluster synchronization capability based on artificial immune algorithm

Chen

Shi

Yang

et al. 2019

Hum. Cent. Comput. Inf. Sci.

View full text Add to dashboard Cite

In recent years, social cluster events (mass events) take place frequently. The contradictions between social groups are gradually exposed, and their conflicts of interests and games are increasingly apparent. It comes with the fact that cluster behaviors are specifically manifested as cluster emergencies. According to statistics in the "Social Blue Book" in China over the past 10 years, mass incidents have occurred frequently. From 1993 to 2006, mass incidents were boosted from 8709 to 90,000, and even increased to more than 100,000 per year after 2010. When facing those events, people normally make decisions by their own opinions and the choices of surrounding people regarding their attitudes and behaviors. At the same time, with the influence of herd behavior, the individual decisions make these group events synchronized. For example, "candle-snatching

show abstract

Section: Optimization Of Synchronous Evolution Process Based On Artifmentioning

confidence: 99%

Enhancing network cluster synchronization capability based on artificial immune algorithm

Chen

Shi

Yang

et al. 2019

Hum. Cent. Comput. Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…ANFIS integrates both advantages of the artificial neural network (ANN) and T-S fuzzy inference system to learn the complex relation between input–output data and construction of a fuzzy model between them. 22 In this paper, ANFIS is trained by error back propagation and gradient descent (GD) optimization method 23 has been used to adjust the linear and nonlinear parameters of the initial fuzzy model. Square error function, which is described in equation (6), has been considered as a performance function where a^r(k) is the estimation of the model for ar(k).…”

Section: Proposed Calibration Algorithmmentioning

confidence: 99%

Calibration of a micro-electro mechanical system-based accelerometer for vehicle navigation

Ghaffari

Khodayari

Nosoudi³

et al. 2018

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

Micro-electro mechanical system-based inertial sensors have broad applications in moving objects including in vehicles for navigation purposes. The low-cost micro-electro mechanical system sensors are normally subject to high dynamic errors such as linear or nonlinear bias, misalignment errors and random noises. In the class of low cost sensors, keeping the accuracy at a reasonable range has always been challenging for engineers. In this paper, a novel method for calibrating low-cost micro-electro mechanical system accelerometers is presented based on soft computing approaches. The method consists of two steps. In the first step, a preliminary model for error sources is presented based on fuzzy subtractive clustering algorithm. This model is then improved using adaptive neuro-fuzzy systems. A Kalman filter is also used to calculate the vehicle velocity and its position based on calibrated measured acceleration. The performance of the presented approach has been validated in the simulated and real experimental driving scenarios. The results show that this method can improve the accuracy of the accelerometer output, measured velocity and position of the vehicle by 79.11%, 97.63% and 99.28%, in the experimental test, respectively. The presented procedure can be used in collision avoidance and emergency brake assist systems.

show abstract

“…Evolutionary meta-heuristic methods are also reported in neuro-fuzzy literature. Particle swarm optimization (PSO) tuned neuro-fuzzy systems have been implemented for financial market price forecasting [16] and channel equalization of wireless communication channels [17]. A new learning scheme based on evolutionary and swarm intelligence algorithms have been employed for improving efficiency and effectiveness of conventional neuro-fuzzy system using fuzzy linguistic hedges which employed to define the flexible shapes of the fuzzy membership functions [18].…”

Section: Introductionmentioning

confidence: 99%

Regularized extreme learning adaptive neuro-fuzzy algorithm for regression and classification

Shihabudheen

Pillai

2017

Knowledge-Based Systems

View full text Add to dashboard Cite

PSO tuned ANFIS equalizer based on fuzzy C-means clustering algorithm

Cited by 24 publications

References 21 publications

Enhancing network cluster synchronization capability based on artificial immune algorithm

Enhancing network cluster synchronization capability based on artificial immune algorithm

Calibration of a micro-electro mechanical system-based accelerometer for vehicle navigation

Regularized extreme learning adaptive neuro-fuzzy algorithm for regression and classification

Contact Info

Product

Resources

About