A Deep Neuro-Fuzzy Network for Image Classification

Yazdanbakhsh, Omolbanin; Dick, Scott

doi:10.48550/arxiv.2001.01686

Cited by 6 publications

(7 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Basically the network extracts local as well as global features for analyzing the images and for image classification; they deliver the extracted features to the fully connected layers for performing classification task. Then, trained the network by gradient descent in end to end, such that it provided the parameters of filters in fuzzy interface and fuzzy pooling operations along with it provided the fully connected layer parameters [35]. The learnable parameters are categorization based on the fuzzy interface operation.…”

Section: Facial Expression Recognition Using Dnfnmentioning

confidence: 99%

Deep Hunting Social Optimization Algorithm Enabled Deep Neuro Fuzzy Network for Facial Expression Recognition

Komala,

Jayadevappa,

2024

Preprint

View full text Add to dashboard Cite

Recently, a number of researchers have been able to identify human emotions from facial expressions. Realistically speaking, emotion communication is a transient and multimodal process, which makes identifying human emotions difficult. This paper proposes an effective model for multimodal facial expression recognition using the Deer Hunting Social Optimization Algorithm (DHSOA) based Deep Neuro Fuzzy Network (DNFN) in order to overcome such problems in the existing models and achieve outstanding performance in the field of human facial expression recognition. In this work, input video and input electroencephalogram (EEG) signals are considered for additional processing. The feature selection stage uses DHSOA to select appropriate features from input video and EEG signal phases. In contrast, the suggested DHSOA-based DNFN for facial video has a maximum accuracy of 0.910, a precision of 0.899, and a recall of 0.900.

show abstract

Section: Facial Expression Recognition Using Dnfnmentioning

confidence: 99%

Deep Hunting Social Optimization Algorithm Enabled Deep Neuro Fuzzy Network for Facial Expression Recognition

Komala,

Jayadevappa,

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Yazdanbakhsh and Dick 37 suggested the first end-to-end deep neuro-fuzzy network and look into its use for image classification. Fuzzy inference and fuzzy pooling are two novel operations created based on definitions of the Takagi-Sugeno-Kang (TSK) fuzzy model; stacks of these operations make up the layers of this network.…”

Section: Literature Reviewmentioning

confidence: 99%

Reinforcement learning and neuro‐fuzzy GNN‐based vertical handover decision on internet of vehicles

Kumar

Sagar

2023

Concurrency and Computation

View full text Add to dashboard Cite

The Internet of Vehicles (IoV) has become a lot of concern for scientific society because of its rising importance in creating an intelligent transportation system. However, the existing systems addressed handover and network selection difficulties, but they did not solve the necessity for frequent handover problems.Hence, in this research, handover decision difficulties are removed by using a novel state-action-reward-state-action reinforcement learning method in which it learns the current policy action to determine whether a handover decision is required in the fast-moving vehicle therefore the handover failure problem is reduced. Moreover, the existing fuzzy rules do not consider non-line-of-sight and the learning capabilities of the neural networks to select the suitable network therefore it creates network selection difficulty. Hence, the network selection difficulties are removed by using a novel fuzzy-based graph neural network in which the fuzzy logic is connected to the graph hierarchical structure to select the right network therefore the efficient and suitable network is selected on the internet of vehicle communication. Moreover, the existing process is to select the routes completely established on the ancient broadcast history of the vehicles and their channel metrics which causes the frequent handover and poor performance of the network. Hence, the routing selection problem is eliminated by using a novel cluster-based routing algorithm in which the vehicle was divided into clusters to select the efficient route of the internet of the vehicle therefore the best routing path is carried out. As a result, the proposed system is improving the quality of the service and reducing the handover failure and delay of the system.

show abstract

“…Recently, the use of deep fuzzy network for FER system is evolving, which uses fuzzy network for the optimization of CNN and deep learning models given in [33,34]. In [33] novel approach WCHGSO-DNFN for detecting compound emotions showing comparatively good performance when tested using Compound Facial Expressions of Emotion (CFEE) Database and same methodology is applied for pain intensity measurement on UNBC-McMaster Shoulder Pain Expression Archive Database.…”

Section: Related Workmentioning

confidence: 99%

Hybrid learning framework for compound facial emotion recognition

Borgalli

Surve

2022

Preprint

View full text Add to dashboard Cite

Facial emotion recognition (FER) is a vital research area in machine vision and artificial intelligence due to its application in academics and industry. Although FER can primarily be conducted using multiple sensors, research shows that using facial images/videos to recognize facial expressions is a better way to convey emotions because visual expressions carry essential information. This paper focuses on implementing various learning frameworks one of them is to combine machine learning and deep learning and other one is water cycle Henry Gas solubility optimization-based deep neuro fuzzy network (WCHGSO-DNFN) for detecting compound emotions using the iCV Multi-Emotion Facial Expression Dataset (iCV-MEFED). In the first proposed methodology, we used a deep learning CNN-based model to extract features for each image, and a Multi-Class Support Vector Machine (mSVM) classifier was used to detect the corresponding emotions. This proposed learning framework for the iCV-MEFED dataset got an accuracy of 26%, outperforming the state-of-the-art results. Moreover, a comparison with competition results in terms of misclassification results shows that our methodology gives the best result of 74.00%. In the second proposed methodology, we used a deep learning CNN-based model with WCHGSO-DNFN for optimization. This proposed learning framework for the iCV-MEFED dataset got an accuracy of 28%, outperforming the state-of-the-art results. Moreover, a comparison with competition results in terms of misclassification results shows that our methodology gives the best result of 72.00%.

show abstract

A Deep Neuro-Fuzzy Network for Image Classification

Cited by 6 publications

References 32 publications

Deep Hunting Social Optimization Algorithm Enabled Deep Neuro Fuzzy Network for Facial Expression Recognition

Deep Hunting Social Optimization Algorithm Enabled Deep Neuro Fuzzy Network for Facial Expression Recognition

Reinforcement learning and neuro‐fuzzy GNN‐based vertical handover decision on internet of vehicles

Hybrid learning framework for compound facial emotion recognition

Contact Info

Product

Resources

About