BRAIN ANEURYSM CLASSIFICATION VIA WHALE OPTIMIZED DENSE NEURAL NETWORK
Journal Title: International Journal of Data Science and Artificial Intelligence - Year 2024, Vol 2, Issue 02
Abstract
A brain aneurysm is caused by faulty blood vessel walls. When a brain aneurysm ruptures or leaks, it can cause bleeding in the brain. It is common for brain aneurysms to not burst but to damage the body and cause symptoms. In this paper, a novel WHO-DNN model (Dense neural network optimized with Whale optimization algorithm) has been proposed to identify the types of aneurysms classes. For this classification, the segmented MRI images are used as input to advance the survival rate of patients. Initially, the segmented MRI images are pre-processed by Adaptive Median Filter (AMF) to remove the noise from the input images. Then, the textural features are extracted to generate the feature sets. The Dense Neural Network (DNN) is utilized to identify and classify the input images to discriminate types of aneurysms classes namely normal, Fusiform aneurysn, and Pseudo aneurysm. Finally, the Whale Optimization Algorithm (WHO) to improve the parameters of the DNN to attain better classification results. The competence of the proposed WHO-DNN model was determined through specific network metrics. The proposed WHO-DNN model attains a total accuracy of 98.69%, which is comparatively better than the existing techniques.
Authors and Affiliations
Ghazanfar Ali Safdar, Xiaochun Cheng
Keywords
Related Articles
- EP ID EP734882
- DOI -
- Views 67
- Downloads 0
SEMANTIC FEATURE ENABLED AGGLOMERATIVE CLUSTERING FOR INFORMATION TECHNOLOGY JOB PROFILE ANALYSIS
The maintenance and implementation of computer systems are the core activities of information technology. Database administration and network architecture are also included in information technology. Professionals have a...
DETECTION OF VIOLENCE IN FOOTBALL STADIUM THROUGH BIG DATA FRAMEWORK AND DEEP LEARNING APPROACH
Football is the most famous game in the world, with over 4 billion supporters worldwide. Football hooliganism refers to the aggressive or destructive actions of a supporter or player in a stadium while watching or partic...
CHICKEN SWARM OPTIMIZATION BASED ENSEMBLED LEARNING CLASSIFIER FOR BLACK HOLE ATTACK IN WIRELESS SENSOR NETWORK
Wireless Sensor Networks (WSNs) are an inevitable technology prevalently used in various critical and remote monitoring applications. The security of WSNs is compromised by various attacks in wireless mediums. Even thoug...
SAFE-ACID: A NOVEL SECURITY ASSESSMENT FRAMEWORK FOR IOT INTRUSION DETECTION VIA DEEP LEARNING
Internet of Things (IoT) intrusion detection is crucial for ensuring the security of interconnected devices in our digital world. With diverse devices communicating in complex networks, IoT environments face vulnerabilit...
DINGO OPTIMIZED FUZZY CNN TECHNIQUE FOR EFFICIENT PROTEIN STRUCTURE PREDICTION
Protein is made up of a variety of molecules that are required by living organisms, such as enzymes, hormones, and antibodies. In step 2, the max-pooling layer and the convolutional layer evaluate the input data to creat...