Machine_learning_2

Biomedical robot Cancer Detection (PEPPER ROBOT-APPLICATION)

TEAM MEMBERS

Ginne Vikas Reddy (5061211)

Yeshwanth Guru krishnakumar (5059111)

Elham mohammadi (5073904)

ABSTRACT

Breast cancer has become one of the prevalent diseases in this era. Many cases are getting resulted as False Negatives which means that the patients without cancer are sent to diagnostic mammography, which uses a high dose of X-ray to screen for cancer which may be harmful to the women, on the other hand, patients with breast cancer are sent back saying that there is no cancer growth due to the inaccuracy which results in cancer enormously. In order to overcome this problem, we have designed a machine learning-based system that can analyze the mammogram output and can predict whether the patient is developing cancer or not. Unlike the conventional CNN methods, we have used a unique texture descriptor called LNIP and Radial Basis Function kernel of the SVM classifier.

CLASSIFIERS USED

MLP Classifier
Linear SVM
Random Forest
XG BOOST Classifier
Naive Baye’s
MLP Classifier
Optimized RBF kernel

PACKAGE DESCRIPTIION

CODE EXECUTION PROCESS

Download the dataset fom the given link

https://unigeit-my.sharepoint.com/:f:/r/personal/s5061211_studenti_unige_it/Documents/ml2/Dataset_DDSM_database?csf=1&web=1&e=9i1Gm3

instead of entire training you can use the pre trained data set which is in the main package addressed LNIP_super_all.csv. Clone the complete package from the github link

https://github.com/vikasreddy636/machine_learning_2

.git which would have the complete package of the application which we have developed using the python. To run the code we should give the command

                                      python3 classification.py

Once the code input is given for further execution have included the screenshot for reference.

And for the graphical interface output attached the screenshot for reference

RESULT

We have developed this and it can be implemented in the pepper robot architecture that would be helpful for the doctors and technician to give and get feedback of cancer detection by scanned images.