首页|New Findings from Hindustan Institute of Technology and Science Update Understan ding of Machine Learning (Efficient Retinal Detachment Classification Using Hybr id Machine Learning With Levy Flight-based Optimization)
New Findings from Hindustan Institute of Technology and Science Update Understan ding of Machine Learning (Efficient Retinal Detachment Classification Using Hybr id Machine Learning With Levy Flight-based Optimization)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-A new study on Machine Learning is now available. According to news reporting out of Tamil Nadu, India, by NewsRx edit ors, research stated, "Decreased vision acuity and blindness due to retinal deta chment (RD) are significant concerns, emphasizing the importance of early diagno sis and identification. However, manual screening of RD is labor-intensive and t imeconsuming and faces challenges such as poor quality and low accuracy." Our news journalists obtained a quote from the research from the Hindustan Insti tute of Technology and Science, "A novel hybrid machine learning(ML) algorithm i ncorporating Levy flight-based atom search optimization (LFB-ASO) is proposed to solve the above challenges. The dataset utilized for the experiment is the Reti nal Fundus Multi-disease Image dataset (RFMiD). The data preprocessing pipeline involves image resizing, normalization, data augmentation, masking and segmentat ion. To ensure consistent dimensions, all retinal images are standardized throug h resizing. Performance and convergence are improved using normalization. The da ta augmentation technique enhances diversity, while segmentation focuses on the region of interest (ROI). Then the deep features are extracted from the preproce ssed retinal images using a pre-trained ResNet18 model. LFB-ASO is employed to s elect the most discriminative deep features for RD classification. To achieve su perior accuracy, hybrid ML algorithms, namely Support Vector Machine (SVM), Grad ient Boosting Machine (GBM) and Random Forest (RF) are employed. The proposed mo del achieves remarkable results with accuracy, recall, F1 score and precision of 98.75%, 96.70%, 97.01% and 97.62% ." According to the news editors, the research concluded: "These results outperform existing methods such as HOS-LSDA, LR, NB, PCA and RD-Light-Net." This research has been peer-reviewed.
Tamil NaduIndiaAsiaCyborgsEmergi ng TechnologiesMachine LearningHindustan Institute of Technology and Science
NETL
NSTL
