Fuzzy dragon deep belief neural network for activity recognition using hierarchical skeleton features

Sheeba, Paul T; Murugan, S.

doi:10.1007/s12065-019-00245-2

Cited by 9 publications

(4 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…vi. Hierarchical skeleton features Hierarchical skeleton features [36] apply the skeleton pruning technique, which efficiently discards the skeleton branches and offers visually unimportant regions iteratively utilizing the discrete curve evolution (DCE). The expression is given as follows:…”

Section: Oriented Fast and Rotated Brief (Orb)mentioning

confidence: 99%

Deep Q Network Based on a Fractional Political–Smart Flower Optimization Algorithm for Real-World Object Recognition in Federated Learning

Soomro,

Fu,

Aslam

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

An imperative application of artificial intelligence (AI) techniques is visual object detection, and the methods of visual object detection available currently need highly equipped datasets preserved in a centralized unit. This usually results in high transmission and large storage overheads. Federated learning (FL) is an eminent machine learning technique to overcome such limitations, and this enables users to train a model together by processing the data in the local devices. In each round, each local device performs processing independently and updates the weights to the global model, which is the server. After that, the weights are aggregated and updated to the local model. In this research, an innovative framework is designed for real-world object recognition in FL using a proposed Deep Q Network (DQN) based on a Fractional Political–Smart Flower Optimization Algorithm (FP-SFOA). In the training model, object detection is performed by employing SegNet, and this classifier is effectively tuned based on the Political–Smart Flower Optimization Algorithm (PSFOA). Moreover, object recognition is performed based on the DQN, and the biases of the classifier are finely optimized based on the FP-SFOA, which is a hybridization of the Fractional Calculus (FC) concept with a Political Optimizer (PO) and a Smart Flower Optimization Algorithm (SFOA). Finally, the aggregation at the global model is accomplished using the Conditional Autoregressive Value at Risk by Regression Quantiles (CAViaRs) model. The designed FP-SFOA obtained a maximum accuracy of 0.950, minimum loss function of 0.104, minimum MSE of 0.122, minimum RMSE of 0.035, minimum FPR of 0.140, maximum average precision of 0.909, and minimum communication cost of 0.078. The proposed model obtained the highest accuracy of 0.950, which is a 14.11%, 6.42%, 7.37%, and 5.68% improvement compared to the existing methods.

show abstract

Section: Oriented Fast and Rotated Brief (Orb)mentioning

confidence: 99%

Deep Q Network Based on a Fractional Political–Smart Flower Optimization Algorithm for Real-World Object Recognition in Federated Learning

Soomro,

Fu,

Aslam

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…In view of the prevailing congestion situation in major cities, it shows a huge potential for oil saving and emission reduction. Idle start stop technology can be applied to both manual transmission vehicles and automatic transmission vehicles [7][8].…”

Section: Idle Start Stop Systemmentioning

confidence: 99%

Idle Speed Control of Gasoline Engine Based on Fuzzy Neural Network

Zi-ming¹

2021

KME

View full text Add to dashboard Cite

Fuzzy neural network is an intelligent method based on state feedback. In the process of learning and recognition, it has a very high fault tolerance rate and can help people quickly and accurately find the information they need. The engine idle speed and fuel combustion process are measured by using the fuzzy neural network control method. Therefore, in order to improve the idle speed control ability of gasoline engine, this paper studies the application of fuzzy neural network in its control system. This paper mainly uses the experimental method to compare and analyze the fuel economy based on multi-mode through the variables of vehicle idle parking in different periods. The experimental results show that the fuel economy of the start stop system in peak hours is increased by 20.38% on average. The idle start stop control strategy based on multi-mode information can effectively improve the fuel economy of the start stop system.

show abstract

“…This minor change can designate that presence of cancer 5,6 . The most recycled processes to diagnose breast cancer are mammography, biopsy, thermography and ultrasound 7,8 . A biopsy is standard clinic methodology utilized to diagnose early‐stage cancer on microscope 9,10 .…”

Section: Introductionmentioning

confidence: 99%

“…5,6 The most recycled processes to diagnose breast cancer are mammography, biopsy, thermography and ultrasound. 7,8 A biopsy is standard clinic methodology utilized to diagnose early-stage cancer on microscope. 9,10 Based on subjective nature of human clarification, radiologists can have dissimilar opinions about related mammograms.…”

mentioning

confidence: 99%

A Wrapper based feature extraction framework based on AlexNet deep convolutional neural network parameters optimized using gradient‐based optimizer for mammogram images

Sakthivel¹,

Subasree

Malik

et al. 2022

Concurrency and Computation

View full text Add to dashboard Cite

In this manuscript, a Wrapper based feature extraction framework based on AlexNet deep convolutional neural network (ADCNN) with gradient‐based optimizer (GBO) is proposed for early detection of breast cancer. In this input images are occupied as mini‐mammography image analysis society (MIAS) database. Then the images are pre‐processed to eliminate that noises using Markov random field (MRF) method. Image features are extracted by the process of Wrapper based feature extraction framework with ADCNN. Then, the weight parameters of ADCNN are optimizing through the aid of GBO. Then the mammogram images are characterized as normal or abnormal (malignant and benign) with SVM classifier. The simulation process is implemented on MATLAB platform. The proposed ADCNN‐SVM‐GBO attains higher accuracy 34.64%, 28.86%, 19.86%, 24.64%, 32.86%, higher Precision 28.07%, 18.96%, 16.86%, 25.86%, 26.86%, higher recall 27.86%, 32.54%, 27.86%, 23.95%, 19.97%, and the efficiency of the proposed method FE‐ADCNN‐GBO‐SVM is likened with the existing processes. Classification of mammograms depends features removal processes with support vector machine (FE‐LBP‐GLCM‐SVM), breast cancer classification with global discriminate features on mammographic images (FE‐GLCM‐ANN), enhancing breast cancer classification with (SMOTE) technique and pectoral muscle removal on mammographic images (FE‐SMOTE‐RF), application of artificial intelligence depends deep learning on breast cancer screening and imaging diagnosis (FE‐CNN‐CDCNN) respectively.

show abstract

Fuzzy dragon deep belief neural network for activity recognition using hierarchical skeleton features

Cited by 9 publications

References 29 publications

Deep Q Network Based on a Fractional Political–Smart Flower Optimization Algorithm for Real-World Object Recognition in Federated Learning

Deep Q Network Based on a Fractional Political–Smart Flower Optimization Algorithm for Real-World Object Recognition in Federated Learning

Idle Speed Control of Gasoline Engine Based on Fuzzy Neural Network

A Wrapper based feature extraction framework based on AlexNet deep convolutional neural network parameters optimized using gradient‐based optimizer for mammogram images

Contact Info

Product

Resources

About