Professional Documents
Culture Documents
Submitted by:
Ms.K.G.Jagtap
1
Institute Code: 0141
CERTIFICATE
Certified that this micro project report titled “Application of SVM Algorithm for cancer
detection ” is the bonafide work of Sarang Jagdale, Roll no 2609 of year Diploma in Artificial
intelligence and machine learning for the Course: Advanced Algorithms in AI & ML Course
code: 22683 during the Academic Year 2023-2024 , who carried out the micro project work under
my supervision.
Ms.K.G.Jagtap
2
ACKNOWLEDGEMENT
We would like to express our special thanks of gratitude to our teachers, who gave us opportunity
to do this wonderful micro project on the topic “ Application of SVM Algorithm for cancer
detection ” which also helped us in doing a lot of Research and we came to know about so many
new things we all really thankful to all who help us doing this micro project.
Secondly we would also like to thank our parents and friends who helped us a lot in
finalizing this project within the limited time frame.
Name Signature
Sarang Jagdale
3
ALL INDIA SHRI SHIVAJI MEMORIAL SOCIETY’S POLYTECHNIC, PUNE -1
4
ALL INDIA SHRI SHIVAJI MEMORIAL SOCIETY’S POLYTECHNIC, PUNE -1
PO2 Problem analysis: Identify and analyze well-defined engineering problems using
codified standard methods.
PO7 Life-long learning: Ability to Analyze individual needs and engage in updating in
the context of technological changes.
5
INDEX
1. Title 1
2. Certificate 2
3. Acknowledgement 3
4. Annexure I 7
5. Annexure II 10
6. Annexure III 17
7. Annexure IV 19
8. Log Book 20
6
Annexure-I
Micro-Project Proposal
Title of the Project: “ Application of SVM Algorithm for cancer detection ”
Benefits :
Overall, SVM is a powerful tool for cancer detection due to its ability to handle high-dimensional
data, robustness to overfitting, effectiveness in handling non-linear relationships, optimal margin
properties, implicit feature selection, and well-established theoretical foundations. However, like any
machine learning algorithm, its performance depends on the quality of the data, feature selection, and
appropriate parameter tuning.
1. Arrangement of groups and representatives for groups that are not usually represented
aspartners in main projects.
2. Capacity building and networking in relation to the role as partners in micro projects.
3. Collected materials related to project.
4. Support development of more need and user driven projects.
5. Contribute to the maximum requirements of project.
6. An eligible project idea addressing one of the four Priority Axes and a work plan for a
micro project including a description of how the capacity building and networking should
take place.
7. The project involves maximum three partners. From three partners, the contributions of
micro project are distributed.
8. An eligible Lead member who will guide the group members and analyzed the data.
9. Eligible match finding the proper information.
10. Softcopy corrections by respective teachers.
11. Completion of the micro project properly.
12. Final copy and submission.
7
4.0 Action Plan
8
Resources Required
9
Annexure-II
Micro-Project Report
Rationale:
Overall, SVM is a powerful algorithm for classification tasks, especially when the data
is high-dimensional or when there's a need for a clear separation between classes.
However, SVM may not perform well on very large datasets due to its computational
complexity, and parameter tuning can be crucial for achieving optimal performance.
Benefits:
Overall, SVM is a powerful tool for cancer detection due to its ability to handle high-dimensional data,
robustness to overfitting, effectiveness in handling non-linear relationships, optimal margin properties,
implicit feature selection, and well-established theoretical foundations. However, like any machine
learning algorithm, its performance depends on the quality of the data, feature selection, and
appropriate parameter tuning.
Literature Review:
1. https://www.geeksforgeeks.org/support-vector-machine-algorithm/
2. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5822181/
1
ABSTRACT
Support Vector Machine (SVM) is a powerful machine learning algorithm used for linear or nonlinear
classification, regression, and even outlier detection tasks. SVMs can be used for a variety of tasks, such as
text classification, image classification, spam detection, handwriting identification, gene expression analysis,
face detection, and anomaly detection. SVMs are adaptable and efficient in a variety of applications because
they can manage high-dimensional data and nonlinear relationships.
SVM algorithms are very effective as we try to find the maximum separating hyperplane between the
different classes available in the target feature.
Support Vector Machine (SVM) is a supervised machine learning algorithm used for both classification and
regression. Though we say regression problems as well it’s best suited for classification. The main objective
of the SVM algorithm is to find the optimal hyperplane in an N-dimensional space that can separate the data
points in different classes in the feature space.
1
Applications
Gene Expression Classification:
SVM can be applied to gene expression data for classifying different types of cancer. By analyzing the
expression levels of thousands of genes, SVM can help identify patterns that distinguish between
cancerous and non-cancerous tissues.
Protein Sequence Analysis:
SVM can be used to analyze protein sequences and predict whether certain mutations or variations are
associated with cancer. This is particularly relevant in understanding the role of specific proteins in cancer
development.
Imaging Data Analysis:
SVM is applied to medical imaging data, such as mammograms, CT scans, or MRI images, to assist in the
early detection and classification of tumors. SVM can help in distinguishing between benign and malignant
tumors based on the features extracted from the images.
Classification of Cancer Subtypes:
SVM can be employed to classify different subtypes of cancers. For instance, it can distinguish between
different types of breast cancer, lung cancer, or leukemia based on various molecular markers or clinical
features.
Identification of Biomarkers:
SVM can be used to identify potential biomarkers associated with cancer. By analyzing high-dimensional
biological data, SVM can identify relevant features that contribute to the classification of cancer samples, a
iding in the discovery of new diagnostic markers.
Drug Response Prediction:
SVM can be utilized to predict the response of cancer patients to specific treatments. By analyzing
molecular and clinical data, SVM models can help identify patients who are likely to respond positively or
negatively to certain therapeutic interventions.
Early Detection of Cancer:
SVM models can be trained on diverse datasets to detect cancer at early stages. Early detection is crucial
for improving treatment outcomes, and SVM's ability to handle complex relationships in the data makes it
valuable in this context.
1
2.0 Actual Methodology Followed:
1
INTRODUCTION
cancer_data = datasets.load_breast_cancer()
X = cancer_data.data
y = cancer_data.target
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)
y_pred = svm_classifier.predict(X_test_scaled)
1
Output of the Micro-Project:
1
Skill Developed/Learning outcome of this Micro-Project
6. Problem solving
1
Annexure - III
(The marks may be allotted to the characteristics of the Micro-Project by considering the
suggested rubrics)
1
6. Report Very short, poor Nearly sufficient Detailed, correct Very detailed,
Preparation quality sketches, and correct details and clear
Details about about methods, description of correct, clear
methods, materials, methods, description of
materials, precautions and materials, methods,
Precautions and conclusion. But precautions and materials,
Conclusions clarity is not there conclusion. precautions and
omitted, some in presentation. Sufficient conclusion.
details are But not enough graphic Enough tables,
wrong. graphic description description charts and
sketches
1
Annexure IV
Micro Project Evaluation
Sheet
Name of Student: Sarang Jagdale Enrollment No: 2101410027
Name of Program: AIML Semester: 6th semester
Course Title: Advanced Algorithms in AI & ML Code: 22683
Title of the Micro-project: “Application of SVM Algorithm for cancer detection
”
3.0 Course Outcomes Achieved : C22683
C22683.a. Immplement processing steps on data to make it ready for analysis
C22683.c. Describe Support Vector Machines and K Nearest Neighbors.
2
Annexure IV
Ms.K.G.Jagtap
2
Annexure IV
Rubrics Used for Evaluation of a Micro Project
B) Individual Presentation/Viva(B)
Ms.K.G.Jagtap
2
Evaluation Sheet for the Micro Project
Roll No. Student Name Marks out of (6) Marks out of (4) Total out
for performance for performance in of (10)
in group activity oral / presentation
2609 Sarang Jagdale