Theses, Dissertations & Reports

Permanent URI for this communityhttp://dspace.iiuc.ac.bd/handle/88203/66

Browse

Subject: search.filters.subject.KNN

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Approach to Improving Machine Learning Models for Intrusion Detection System
    (International Islamic University Chittagong, 2022-07) Labib, Ahmad Ibtisam; Chy, Shamsuddin Ahmmed; Hossain, Md. Shahriar
    In today's digital world, there are several security risks that digital assets must contend with. Systems for detecting intrusions (IDS) are essential security tools that protect digital assets. But their usefulness depends on meeting strict accuracy requirements, and their effectiveness depends on timely alarms. This study offers a novel IDS model that combines deep learning and machine learning methods as a solution to these problems. The study applies several classification techniques, such as Gaussian Naive Bayes (GNB), Random Forest (RF), Decision Tree, K-Nearest Neighbors (KNN), Soft Voting, and Hard Voting, using the well known KDD Cup-1999 dataset. After a large-scale dataset was processed, the Decision Tree method performed better than the others, with a 99.9% accuracy rate. This study aims to investigate the effects of soft voting and hard voting, a novel application in IDS. Decision Tree proved to be the better performance in spite of these efforts. By offering information about algorithmic efficacy, the research advances the field of intrusion detection and helps decision-makers in the design and deployment of intrusion detection systems. These findings have implications for improving digital asset protection against changing cyber threats.
  • No Thumbnail Available
    Item
    Cancer prognosis & Survival rate prediction using machine learning algorithm.
    (Department of Electronic and Telecommunication Engineering, 2022-10) Alif, Borhan Uddin
    Roughly 10 million deaths, or nearly one in six deaths, were caused by cancer in 2020, making it the top cause of death globally. Breast, lung, colon, rectum, and prostate cancers are the most prevalent types of cancer. Any disease that can affect any region of the body is referred to as cancer. Neoplasms and malignant tumors are other words that are used. One characteristic of cancer is the quick development of aberrant cells that expand outside of their normal borders, infiltrate other body components, and eventually move to other organs. This process is known as metastasis. The main reason why cancer patients die is because of widespread metastases [1]. The research was held on two different datasets of breast cancer. To train our model initially we used a primary data set from UCI which includes 569 instances with several attributes [2]. This was for cancer diagnosis prediction/detection. Then we used another dataset that includes 4024 instances with 14 different attributes which we mainly used for death rate prediction with total analysis [3]. Here 6 algorithms were incorporated including KNN, Random Forest, J48, etc., and their results were compared.