Gray wolf optimization-extreme learning machine approach for diabetic retinopathy detection

Abstract

Many works have employed Machine Learning (ML) techniques in the detection of Diabetic Retinopathy (DR), a disease that affects the human eye. However, the accuracy of most DR detection methods still need improvement. Gray Wolf Optimization-Extreme Learning Machine (GWO-ELM) is one of the most popular ML algorithms, and can be considered as an accurate algorithm in the process of classification, but has not been used in solving DR detection. Therefore, this work aims to apply the GWO-ELM classifier and employ one of the most popular features extractions, Histogram of Oriented Gradients-Principal Component Analysis (HOG-PCA), to increase the accuracy of DR detection system. Although the HOG-PCA has been tested in many image processing domains including medical domains, it has not yet been tested in DR. The GWO-ELM can prevent overfitting, solve multi and binary classifications problems, and it performs like a kernel-based Support Vector Machine with a Neural Network structure, whilst the HOG-PCA has the ability to extract the most relevant features with low dimensionality. Therefore, the combination of the GWO-ELM classifier and HOG-PCA features might produce an effective technique for DR classification and features extraction. The proposed GWO-ELM is evaluated based on two different datasets, namely APTOS-2019 and Indian Diabetic Retinopathy Image Dataset (IDRiD), in both binary and multi-class classification. The experiment results have shown an excellent performance of the proposed GWO-ELM model where it achieved an accuracy of 96.21% for multi-class and 99.47% for binary using APTOS-2019 dataset as well as 96.15% for multi-class and 99.04% for binary using IDRiD dataset. This demonstrates that the combination of the GWO-ELM and HOG-PCA is an effective classifier for detecting DR and might be applicable in solving other image data types.

An efficient hybrid extreme learning machine and evolutionary framework with applications for medical diagnosis

“…The concept of Opposite‐Based Learning (OBL) was originally introduced in the year 2005 (Arora et al, 2022) and has since gained widespread recognition as an effective technique within swarm‐based approaches. OBL facilitates a balanced combination of core trends and enhanced exploration tendencies (Albadr, Ayob, et al, 2022). The fundamental idea behind OBL revolves around generating opposite points based on the initial data points and subsequently seeking improved positions with superior fitness values compared to the original points.…”

“…As mentioned above, researchers also employ notable evolutionary algorithms such as particle swarm optimization (PSO) (Albadr & Tiun, 2020; Zhu et al, 2020), genetic algorithm (GA) (Albadr et al, 2019; Albadr, Tiun, Ayob, Al‐Dhief, Omar, & Hamzah, 2020; Yang et al, 2013), differential evolution (DE) (Li et al, 2020), competitive swarm optimizer (CSO) (Eshtay et al, 2020), Gray wolf optimizer (GWO) (Albadr, Ayob, et al, 2022) and salp swarm algorithm (SSA) (Yaseen et al, 2020) techniques to improve the performance of the ELM neural network models. In several works that utilized the integration of evolutionary swarm intelligence algorithms with ELM network, the authors showed the excellent outcome of their hybrid algorithms by benchmarking the state of the art datasets.…”

Emotions recognition from human facial images based on fast learning network

“…The matrix of the output weights 𝐖 ̂= [W 𝑜𝑖 W 𝑜ℎ ] can be determined via the inverse of the Moore-Penrose generalization as shown in (5).…”

“…Machine learning (ML) and deep learning (DL) algorithms have been extensively applied due to such algorithms have proved their effectiveness and efficiency in the classification between subjects [4]. Moreover, the algorithms of ML and DL have improved the performance of many recent systems and in different fields such as images classification in the medical domain [5]- [7], language identification [8], [9], fog-cloud network [10], identification of spam emails [11], speech emotion recognition [12], vehicle detection [13] and voice pathology detection [14]- [16]. Additionally, the algorithms of DL and ML have been implemented as the main role in the methods of facial emotion recognition [17], [18].…”

IoT-Based Framework for COVID-19 Detection Using Machine Learning Techniques

“…Furthermore, ML techniques have been used in many medical applications such as COVID-19 detection [18]; lung cancer detection [19]; voice pathology classification [20]; breast cancer detection [21]; and diabetes disease detection [22,23]. One of the most dangerous illnesses facing the world recently is COVID-19 [24].…”