1. SYED PERVEZ HUSSNAIN SHAH - Ph.D. Computer Science from Superior University Lahore, Pakistan, and working as Lecturer IT at Lahore
Leads University, Pakistan.
2. Dr. ARFAN JAFFAR - Dean Computer Science and Information Technology Superior University Lahore, Pakistan.
3. SARFRAZ NAWAZ - Ph.D. (Scholar) Computer Science, Superior University, Lahore, Pakistan, and working as Lecturer CS at
Govt. Graduate College, Kamoke, Gujranwala.
4. WISHAL ARSHAD - Ph.D. (Scholar) Computer Science, Superior University Lahore, Pakistan.
5. MUHAMMAD IZHAR - Ph.D. Scholar computer science, Superior University Lahore, Pakistan and working as a Subject Specialist
(CS) at Govt. Higher Secondary School. Rajunpur, Pakistan.
6. AMNA IQBAL - Ph.D. (Scholar) Computer Science, Superior University Lahore, Pakistan.
In this paper, the researchers have empirically used the various Machine Learning (ML) and Deep Learning (DL) Algorithms and analyze the findings of different Machine Learning and Deep Learning algorithms on the very well-known Wisconsin Diagnostic Breast Cancer Data-Set (WDBC). This study assessed the degree of their capacity to accurately order the sample images as "malignant" or "benign". The separate utilizing of these algorithms was decided on the grounds of different assessment measurements as accuracy is the main factors of datasets. From the trial results, we rational that the deep learning approaches have given preferable outcomes on assessment grounds over the machine learning algorithms. In quantitative terms, CNN performed most reliably among every one of the considered methodologies for the given breast cancer dataset with an accuracy of CNN Deep Learning Model is 99.48 % and MLP 99.45% individually. The ML algorithm SVM has the betters testing accuracy 97.13% and 98.36% training accuracy. In the consequences of finding breast cancer can be predicted on early basis using the Machine Learning and or Deep Learning Models effectively and efficiently. Early detection of breast cancer (BC) will treat well and save many breast cancer patients. As a result, the BC patient’s rate and death rate can be reduced.
Breast Cancer detection, machine learning, deep learning algorithms, classifiers, cancer prediction, convolutional neural network, AlexNet, features extraction, Wisconsin dataset. Benign and malignant images