RETRACTED ARTICLE: Cataract eye detection by optik image analysis using encoder basis Boltzmann architecture integrated with internet of things and data mining

• Published in: Optical and quantum electronics Vol. 55; no. 10
• Main Authors: Bhat, Wasim Ahmad, Ahmed, Sarfaraz, Khan, Asif Ali, Ahmad, Adeel, Dar, Arshad Ahmad, Reegu, Faheem Ahmad, Arumugam, Mahendran
• Format: Journal Article
• Language: English
• Published: New York Springer US 2023; Springer Nature B.V
• Subjects: Blindness; Cataracts; Characterization and Evaluation of Materials; Coders; Computer Communication Networks; Data mining; Datasets; Electrical Engineering; Eye (anatomy); Image analysis; Internet of Things; Lasers; Machine learning; Optical Devices; Optics; Photonics; Physics; Physics and Astronomy; Public health; Cataract; RDNN; Machine learning; Classification; Prediction; KNN; IOT module
• ISSN: 0306-8919; 1572-817X
• DOI: 10.1007/s11082-023-05038-7

As cataracts are the most common cause of blindness and are responsible for more than half of all occurrences of blindness worldwide, early detection is crucial. It is now recognized that childhood cataract, which was once common among the elderly, is a significant cause of infant and young child blindness and severe visual impairment. The objective of this paper is to develop a machine learning-based optic image-based cataract detection system. The public health dataset has been used to collect the data in this case using the internet of things module. The auto region encoder basis Boltzmann architecture has been used to pre-process and pre-train this data for improved data classification. The detection was carried out using this pre-trained data, and when an image showed signs of cataract in the eye, it was classified using auto region encoder basis Boltzmann architecture. The simulation results show that various optical-based cataract image datasets have the best accuracy, precision, recall, F-1 score, and specificity.