MACHINE LEARNING BASED FRAMEWORK FOR VERIFICATION AND VALIDATION OF MASSIVE SCALE IMAGE DATA

Computer Science And Engineering

Prostate cancer (PCa) is a severe type of cancer and causes major deaths among men due to its poor diagnostic system. The images obtained from patients with carcinoma consist of complex and necessary features that cannot be extracted readily by traditional diagnostic techniques. Independent of hand-crafted features, and is fine-tuned. The results were compared with hand-crafted features such as texture, morphology, and gray level co-occurrence matrix using non-deep learning classifiers such as support vector machine (SVM) Gaussian Kernel, J48 Algorithm, k-nearest neighbor-Cosine (KNN - Cosine), As of late, explores are focusing on the adequacy of Transfer Learning (TL) also, Ensemble Learning (EL) procedures in prostrate histopathology picture examination. In any case, there have been not many examinations that have depicted the phases of separation of prostrate CT pictures. Accordingly, in this article, we propose an Ensemble Transfer Learning (ETL) structure to order well, moderate and inadequately separated prostrate CT pictures. The existing CMA system focuses on classifying biological cells through advanced software tools and machine learning algorithms. It places great importance on data validation and the verification of software components, utilizing metamorphic testing for scientific software. However, the system encounters challenges with larger datasets, potential resource-intensive computational processes, integration complexities, and the introduction of bias in machine learning algorithms, which can affect the accuracy of cell morphology classification. The proposed system introduces the widely used J48 algorithm, renowned for its recursive divide and conquer strategy, facilitating efficient data classification. Its application in the detection process involves a strategic approach to attribute splitting, ensuring accurate and effective classification, particularly in the context of improving cervical cancer detection.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.