IRO Journals

Journal of Electrical Engineering and Automation

Comparative analysis of Direct and Indirect Model Reference Adaptive Control by Extended Kalman Filter
Volume-3 | Issue-3

Integrated Renewable Energy Management System for Reduced Hydrogen Consumption using Fuel Cell
Volume-3 | Issue-1

Design of Effective Smart Communication System for Impaired People
Volume-2 | Issue-4

Artificial Intelligence based Business Process Automation for Enhanced Knowledge Management
Volume-3 | Issue-2

Unmanned Aerial Vehicle with Thermal Imaging for Automating Water Status in Vineyard
Volume-3 | Issue-2

A Survey on Digital Fraud Risk Control Management by Automatic Case Management System
Volume-3 | Issue-1

Wireless Power Transfer Device Based on RF Energy Circuit and Transformer Coupling Procedure
Volume-3 | Issue-3

Prediction of Energy Consumption by Ships at the port using Deep Learning
Volume-3 | Issue-2

A Novel Adaptive Fuzzy MPPT Algorithm under Changing Atmospheric Conditions
Volume-3 | Issue-4

Flexibility Management in Renewable Energy Source Operated Power Systems using Decision Support System
Volume-2 | Issue-1

Power Transfer Capability Recognition in Deregulated System under Line Outage Condition Using Power World Simulator
Volume-3 | Issue-4

Transformer Oil Diagnostic Tests Analysis using Statistical Correlation Technique
Volume-4 | Issue-3

Wireless Power Transfer Device Based on RF Energy Circuit and Transformer Coupling Procedure
Volume-3 | Issue-3

Prediction of Energy Consumption by Ships at the port using Deep Learning
Volume-3 | Issue-2

A Novel Adaptive Fuzzy MPPT Algorithm under Changing Atmospheric Conditions
Volume-3 | Issue-4

Performance Analysis of Multiple Pico Hydro Power Generation
Volume-2 | Issue-2

Energy Efficient Data Mining Approach for Estimating the Diabetes
Volume-3 | Issue-2

Design of Inverter Voltage Mode Controller by Backstepping Technique for Nonlinear Power System Model
Volume-3 | Issue-4

Intelligent Automation System for Smart Grid Renewable Energy Generation on Climatic Changes
Volume-3 | Issue-3

Automated Multimodal Fusion Technique for the Classification of Human Brain on Alzheimer’s Disorder
Volume-3 | Issue-3

Home / Archives / Volume-3 / Issue-3 / Article-5

Volume - 3 | Issue - 3 | september 2021

Automated Multimodal Fusion Technique for the Classification of Human Brain on Alzheimer’s Disorder
B. Vivekanandam   242  191
Pages: 214-229
Cite this article
Vivekanandam, B. (2021). Automated Multimodal Fusion Technique for the Classification of Human Brain on Alzheimer’s Disorder. Journal of Electrical Engineering and Automation, 3(3), 214-229. doi:10.36548/jeea.2021.3.005
Published
16 November, 2021
Abstract

Alzheimer's Disorder (AD) may permanently impair memory cells, resulting in dementia. Researchers say that early Alzheimer's disease diagnosis is difficult. MRI is used to detect AD in clinical trials. It requires high discriminative MRI characteristics to accurately classify dementia stages. Due to the large extraction of features, improved deep CNN-based models have recently proven accurate. With fewer picture samples in the datasets, over-fitting issues arise, limiting the effectiveness of deep learning algorithms. This research article minimizes the overfitting error due to fusion techniques. This hybrid approach is used to classify Alzheimer's disease more accurately than other traditional approaches. Besides, the Convolutional Neural Network (CNN) provides more minute features of small changes in MRI scan images than any other algorithm. Therefore, the proposed algorithm provides great accuracy in the region of sagittal, coronal, and axial Mild Cognitive Impairments (MCI) in the brain segment classification. Moreover, this research article compares the proposed algorithm with previous research output that is used to help prove its superiority. The performance metrics uses Health Subject (HS), MCI, and Mini-Mental State Evaluation (MMSE) to evaluate the proposed research algorithm.

Keywords

Alzheimer disease convolutional neural network multimodal fusion deep learning batch normalization group normalization human brain classification

Full Article PDF Download Article PDF 
×

Currently, subscription is the only source of revenue. The subscription resource covers the operating expenses such as web presence, online version, pre-press preparations, and staff wages.

Subscription Payment Details

payumoney (INR): https://pmny.in/Er7GXftJ2HVB

paypal (USD): https://www.paypal.me/InventiveResOrg

Subscription Fee

Quarterly Subscription 2000 INR / 30 USD
Annual Subscription 5000 INR / 100 USD
Subscription form: click here