Improving the predictive performance of SAFEL: A Situation-Aware FEar Learning model

Rizzi, Caroline; Johnson, Colin G.; Vargas, Patrícia A.

doi:10.1109/roman.2016.7745201

Cited by 3 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The hippocampus is an important part of the limbic system for the formation of associative memories, such as the acquisition of information about the context, especially contextual fear learning. It is based on the concept of situation awareness in the sense of being aware of an entity's variations during a period of time [27]. The process as explored in this work relies on detecting transient and steady states.…”

Section: Hippocampus Modulementioning

confidence: 99%

A new control strategy for harmonic reduction in photovoltaic inverters inspired by the autonomous nervous system

Rahmouni

Gaoui

Aillerie

2022

Journal of Electrical Engineering

View full text Add to dashboard Cite

This paper proposes a new inverter control strategy whose main purpose is to reduce the current harmonic distortion resulting from unnecessary control actions without sacrificing the system’s dynamic response. The brain’s capabilities to learn and react to stress are mimicked to generate control actions based on emotional cues. The model is based on the brain emotional learning based intelligent controller, to which an autonomous nervous system was added. The modified controller aims at separating the strategy during transient states from the one during steady states. The proposed method was compared to the PI controller, the PR controller, and a neural network-based controller on Matlab Simulink. It shows major improvements in terms of harmonic distortion and a complete removal of the inter-harmonics. It provides a good dynamic response in transient states and an immunity to irrelevant signal variations during the steady state, which results in an improvement in the harmonic production.

show abstract

Section: Hippocampus Modulementioning

confidence: 99%

A new control strategy for harmonic reduction in photovoltaic inverters inspired by the autonomous nervous system

Rahmouni

Gaoui

Aillerie

2022

Journal of Electrical Engineering

View full text Add to dashboard Cite

show abstract

“…It is a situation-aware computational system capable of providing robots with fear-learning skills in order to predict threatening situations to their own well-being or to their goals. SAFEL's model has been first proposed by us in [17], partially implemented and tested in [13] and improved in [14]. In this section, we briefly introduce SAFEL's biological inspiration and design.…”

Section: Safelmentioning

confidence: 99%

“…In this section, we briefly introduce SAFEL's biological inspiration and design. For a deeper understanding of SAFEL's model and further details on its implementation and performance analysis, we refer the reader to our previous publications [13,14,17].…”

Section: Safelmentioning

confidence: 99%

“…In this paper, we address RoboCup's stagnation in these areas, discussing the existing approaches and their limitations (Section 2). We propose in Section 3, as potential approach to tackle these limitations, our artificial emotional model named SAFEL (Situation-Aware FEar Learning) [13,14,17], which consists of a hybrid architecture based on the fearlearning mechanisms of the brain. Finally, in Section 4, we suggest RoboCup scenarios where SAFEL could be useful to improve flexible decision making at both individual and multi-agent levels, followed by the conclusions in Section 5.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fear Learning for Flexible Decision Making in RoboCup: A Discussion

Rizzi

Johnson

Vargas³

2018

RoboCup 2017: Robot World Cup XXI

Self Cite

View full text Add to dashboard Cite

show abstract

“…The Basal ganglia and Hippocampus parts of the brain form the basis for the implementation of a-BELBIC. The spike potentiation received from Hippocampus is continuously monitored for changes [18]. For maintaining homeostasis, a steady-state equilibrium in human body, the spike potentiation generally varies constantly.…”

Section: Introductionmentioning

confidence: 99%

Emulating emotional quotient – an augmented BELBIC based strategy for harmonic recession in photovoltaic microgrids

Brislin

Maruthachalam

2023

Preprint

View full text Add to dashboard Cite

For the harmonic suppression in photovoltaic microgrids, two interdependent control loops: primary current control loop and secondary voltage control loop is necessary. In this paper, an intelligent secondary controller depicting brain emotional learning based intelligent controller (BELBIC) is suggested. The primitive nature of mammalian brain to learn using emotional quotient is the underlying theory of BELBIC. The original BELBIC is augmented with state awareness knowledge and an upgraded a-BELBIC is proposed in this paper. The proposed controller acquires intelligence through emotional learning and gives promising results in state detection and harmonics deduction. It is also intended to resolve harmonic surge caused by redundant control actions, without compromising on the dynamic response of system. Additionally, it also remains unaffected by insignificant variations during the steady state and reduces the overwork of the primary current controller due to weather deviations. It is completely model-free and is proved to handle computational complexity, system ambiguity and non-linearity. It is compared with PI and NN controller to prove its excellence in harmonic recession and combating subharmonics Moreover, the primary controller administering current control in the inner loop is carried out by the finite control set based model predictive control (MPC). Comprehensively, the validation of robust primary controller and proposed intelligent secondary controller for diversified test cases is assessed using simulations performed in MATLAB/Simulink mathematical engine and tested for hardware-in-loop efficacy using dSPACE DS1104 RTI. The proposed a-BELBIC is observed to reduce the settling time by 18.75%, overshoot by 17.05% and the execution time by 75% in comparison to NN Controller.

show abstract

Improving the predictive performance of SAFEL: A Situation-Aware FEar Learning model

Cited by 3 publications

References 17 publications

A new control strategy for harmonic reduction in photovoltaic inverters inspired by the autonomous nervous system

A new control strategy for harmonic reduction in photovoltaic inverters inspired by the autonomous nervous system

Fear Learning for Flexible Decision Making in RoboCup: A Discussion

Emulating emotional quotient – an augmented BELBIC based strategy for harmonic recession in photovoltaic microgrids

Contact Info

Product

Resources

About