Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Scott-EBOLO/Classsification-Analysis-of-Some-Cnacer-Types

Domain:

healthcare
Creator:
Sco
Host:
Do you know that cancer is one of the deadliest diseases in africa? According to statistics, in 2018, over 700,000 cases of cancer were recorded with more than 500,000 deaths and this was just in Africa alone. This high death rate is mainly due to the poor and late diagnosis. Building on the works of other researchers, I have used #machinelearning methods to classify four different types of cancer namely prostate, lymphoma, leukemia, and SRBCT. I started the project with a small amount of data with the objective of identifying the best classification method among the five methods I used. To reduce the dimension of the data, I have incorporated a new approach which involves performing PCA our dataset. This new approach led to the discovery that the KNN method was the best, with 90% accuracy for prostate and 100% for others. To see if the #KNN method is still the best, I plan to increase the amount of data used to enable me generalize my results. If successful, these results would help doctors to make better early diagnostics, which will significantly reduce the death rate of this killer disease. # Classsification-Analysis-of-Some-Cnacer-Types Do you know that cancer is one of the deadliest diseases in africa? According to statistics, in 2018, over 700,000 cases of cancer were recorded with more than 500,000 deaths and this was just in Africa alone. This high death rate is mainly due to the poor and late diagnosis. Building on the works of other researchers, I have used #machinelearning methods to classify four different types of cancer namely prostate, lymphoma, leukemia, and SRBCT. I started the project with a small amount of data with the objective of identifying the best classification method among the five methods I used. To reduce the dimension of the data, I have incorporated a new approach which involves performing PCA our dataset. This new approach led to the discovery that the KNN method was the best, with 90% accuracy for prostate and 100% for others. To see if the #KNN method is still the best, I plan to increase the amount of data used to enable me generalize my results. If successful, these results would help doctors to make better early diagnostics, which will significantly reduce the death rate of this killer disease.

Visit

github.com

Tasks

text classification