Performance evaluation of optimized and adaptive neuro fuzzy inference system for predictive modeling in agriculture

Remya, S; Sasikala, R.

doi:10.1016/j.compeleceng.2020.106718

Cited by 12 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among the investigated optimisers, first-order optimisers, especially Adam, has been the dominant optimiser, used for most DL research. It is the best performing optimiser for training very DNN architectures as validated by numerous researchers [80,81]. However, the gradient descent-based optimisers and other adaptive optimisers have also performed remarkably in different application areas.…”

Section: Discussionmentioning

confidence: 98%

Advances in Optimisation Algorithms and Techniques for Deep Learning

Nwankpa¹

2020

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

In the last decade, deep learning(DL) has witnessed excellent performances on a variety of problems, including speech recognition, object recognition, detection, and natural language processing (NLP) among many others. Of these applications, one common challenge is to obtain ideal parameters during the training of the deep neural networks (DNN). These typical parameters are obtained by some optimisation techniques which have been studied extensively. These research have produced state-of-art(SOTA) results on speed and memory improvements for deep neural networks(NN) architectures. However, the SOTA optimisers have continued to be an active research area with no compilations of the existing optimisers reported in the literature. This paper provides an overview of the recent advances in optimisation algorithms and techniques used in DNN, highlighting the current SOTA optimisers, improvements made on these optimisation algorithms and techniques, alongside the trends in the development of optimisers used in training DL based models. The results of the search of the Scopus database for the optimisers in DL provides the articles reported as the summary of the DL optimisers. From what we can tell, there is no comprehensive compilation of the optimisation algorithms and techniques so far developed and used in DL research and applications, and this paper summarises these facts.

show abstract

Section: Discussionmentioning

confidence: 98%

Advances in Optimisation Algorithms and Techniques for Deep Learning

Nwankpa¹

2020

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

show abstract

“…This leads to an increase in the number of neurons and the number of fuzzy rules in the knowledge base, which implies the need to increase the volume of the training sample for setting up such a system. Neuro-fuzzy systems that use the backpropagation algorithm for training are characterized by a low speed, which makes their application in sequential data processing ineffective [11]. These disadvantages can be avoided by using hybrid systems that combine both the theory of artificial neural networks, which allows obtaining universal approximating properties and the ability to learn, and the theory of fuzzy logic, which makes it possible to provide the system with linguistic interpretability [12].…”

Section: Methods For Processing Non-stationary Multivariate Time Seriesmentioning

confidence: 99%

Framing regional innovation and technology policies for transformative change

Solodov

Mamai

Pronichkin

2022

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

The current state of social and economic development of regions requires new approaches to increasing the efficiency of their activities, and above all scientific approaches to forecasting, as one of the main components of the strategy of transformative changes. It is proposed to use an architecture based on neuro-fuzzy networks for forecasting regional development, which is characterized by a high learning rate due to the linear dependence of outputs on adjustable weights. Scientific and methodological approaches are developed to determine the global minimum of the learning criterion, taking into account the decision rules “if-then”.

show abstract

“…For this purpose, we choose the Adam optimizer instead of stochastic gradient descent to update the model weights when training data. 45 It combines the advantages of Adagrad and RMSprop optimizers which handle respectively with sparse gradients and non-stationary settings. It ensures achieving performant results through a first-order gradient, hence requiring efficient computational complexity and little memory requirement.…”

Section: Transfer Learning and Fine-tuningmentioning

confidence: 99%

“…At the same time, retinal images with different cataract grades correspond to varying noise. For this purpose, we choose the Adam optimizer instead of stochastic gradient descent to update the model weights when training data 45 . It combines the advantages of Adagrad and RMSprop optimizers which handle respectively with sparse gradients and non‐stationary settings.…”

Section: Ensemble Learning Framework For Cataract Severity Gradingmentioning

confidence: 99%

Cataract grading method based on deep convolutional neural networks and stacking ensemble learning

Elloumi

2022

Int J Imaging Syst Tech

View full text Add to dashboard Cite

The cataract is the most common cause of severe vision impairment or blindness worldwide. A periodical diagnosis is recommended in order to prevent cataract severity, where screening might be feasibly ensured through fundus images. In this paper, we propose a CAD system to efficiently grade the cataract from fundus images. For such a need, an ensemble learning framework is put forward where the knowledge of three convolutional deep neural networks is stacked in order to perform an efficient cataract prediction. The main contributions of this work are given as follows: (1) Preprocessing and data augmentation of fundus images are carried out to ensure the robustness of the cataract grading; (2) The well‐known DL architectures (Inception‐V3, MobileNet‐V2 and NasNet‐Mobile) are fine‐tuned and learned as base classifiers; (3) An Extreme Learning Machine (ELM) is performed as a meta classifier to stack the predictions of base classifiers. The evaluation is conducted using a dataset of 590 fundus images selected from two public databases. The suggested framework achieves 94.07% accuracy, 94.37% sensitivity, 93.62% specificity, 95.71% precision and 95.04% F‐measure for cataract grading. The experimentation proves that the proposed framework successfully grades fundus images into cataract severity. Moreover, stacking ensemble learning allows achieving a performance that significantly surpasses the ones realized by each DL architecture, applied separately.

show abstract

Performance evaluation of optimized and adaptive neuro fuzzy inference system for predictive modeling in agriculture

Cited by 12 publications

References 12 publications

Advances in Optimisation Algorithms and Techniques for Deep Learning

Advances in Optimisation Algorithms and Techniques for Deep Learning

Framing regional innovation and technology policies for transformative change

Cataract grading method based on deep convolutional neural networks and stacking ensemble learning

Contact Info

Product

Resources

About