Browsing by Author "LHR TP 9906"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Heart Disease Detection Based on Machine Learning Algorithms
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2025) Sairish Mushtaq (FA20-BSM-040) : Areej Khan (FA22-BSM-060); Dr. Sana Javed; LHR TP 9906
    Cardiovascular diseases are the first cause of death all over the world. By using artificial intelligence algorithms and, in particular, machine learning approaches it is possible to predict risky situations due to heart disease. Various approaches are investigated in this report such as neural network, support vector machine, decision tree, Naive Bayes, logistic regression and stochastic gradient descent to extract predictive models in order to test for the presence or absence of heart disease. Thanks to the public dataset from UCI, it is possible to take advantage of medical data to train the proposed models. A comparison among the different approaches based on the performance is included in this project. The tests of the proposed models revealed performances in terms of accuracy in the range 77 percent-90.6 percent. The Naive Bayes model has been the model with the highest accuracy (90.6 percent), highest precision (96.4 percent) and shortest time for classification (0.003 seconds).
  • No Thumbnail Available
    Item
    On Topological Indices of Molecular Graph of Copper(II) Flouride
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2025) Irfan Ali (FA20-BSM-050) : Faizan Mustafa (FA20-BSM-070); Dr. Muhammad Kamran Siddiqui; LHR TP 9906
    The utilization of graph theory in multiple branches of research has been vastly enhanced, particularly in the domain of chemical graph theory. Over the past few years, numerous re searchers have been able to pursue a variety of novel avenues. A chemical graph is a named graph where the edges reflect chemical bonds between atoms and the vertices reflect the atoms of a compound. The investigation of topological indices is crucial for determining numerous physical and chemical characteristics of the under-investigation molecular struc tures. Firstly, we focused on degree-based topological indices, namely the Randic index, atom bond connectivity index, geometric arithmetic index, the first and the second Zagreb indices and co-indices, the first and the second multiple Zagreb indices and co-indices, hyper Zagreb index, forgotten index, augmented Zagreb index, Balaban index, redefined Zagreb type indices, of Molecular Graph of Copper(II) Flouride