Big Data Analytics to Predict Cancer Based on Diagnosed Clinical Data
| dc.contributor.advisor | Beyene, Melkamu (PhD) | |
| dc.contributor.author | Alemayehu, Belay | |
| dc.date.accessioned | 2019-11-13T09:11:54Z | |
| dc.date.accessioned | 2023-11-18T12:44:36Z | |
| dc.date.available | 2019-11-13T09:11:54Z | |
| dc.date.available | 2023-11-18T12:44:36Z | |
| dc.date.issued | 2019-05-03 | |
| dc.description.abstract | These days, vast amount of medical data (i.e. medical images, biomedical signals and handwritten prescriptions) are available that can be utilized for pre-diagnostic tasks on the existence of cancer cells by adopting big data analytic concepts. Hence, the main objective of the study was designing a big data analytics model that predicts the occurrence of cancer cells from medical data (medical images, biomedical signals and handwritten prescriptions) available in St. Paul’s hospital. . A big data analytics model that predict the occurrence of cancer cells from the big medical data that have been collected by different academic and medical imaging departments in the St paul’s hospital millennium medical college is designed. Novel data engineering techniques are applied to ensure the quality of data and integrate data from different sources. Deep learning approach based on a logistic activation function is employed to build the model. The deep learning is implemented on a hadoop framework by configuring five commodity machines in which each of them comprised core i3 processor, 4 GB RAM and 1TB of hard disk storage. | en_US |
| dc.identifier.uri | http://etd.aau.edu.et/handle/12345678/20094 | |
| dc.language.iso | en | en_US |
| dc.publisher | Addis Ababa University | en_US |
| dc.subject | Big Data Analytic | en_US |
| dc.subject | Predict Cancer | en_US |
| dc.subject | Model | en_US |
| dc.subject | Medical Image | en_US |
| dc.subject | Deep Learning | en_US |
| dc.subject | Hadoop | en_US |
| dc.title | Big Data Analytics to Predict Cancer Based on Diagnosed Clinical Data | en_US |
| dc.type | Thesis | en_US |