eScholar-UMT
eScholar is the institutional repository for research conducted at UMT and maintains a large collection of theses, dissertations and projects produced by UMT graduates as part of their respective degree programs. It includes (but not limited to):
- PhD/MS Theses
- Graduate Program Research Projects
- Undergraduate Program Reports and Final Year Projects
- Full-text articles/research work of faculty and students
Join eScholar and sign-up to get the access of above mentuobed digital resources at your desktop.
Communities in DSpace
Select a community to browse its collections.
Recent Submissions
Classification of Pathogenic Bacteria Using Machine Learning and Deep Learning
(UMT, Lahore, 2024) Mahmood Ahmad
The present study has been designed for the classification of pathogenic bacteria species by using machine learning (ML) and deep learning (DL). The fourteen different pathogenic bacterial species included Porphyromonas gingivalis, Enterococcus faecium, Eschericia coli, Listera monocytogenes, Neisseria Gonorrhoea, Propionibacterium acnes, Clostridium perfringens, Proteus spp., streptococcus agalactiae, Staphylococcus epidermidis, Staphylococcus saprophyticus, Enterococcus faecalis, Pseudomonas aeruginosa, and Staphylococcus aureus. About of 10 thousand images of pathogenic bacteria were includedin the study with 80% training images and 20% testing images extracted from DIBaS dataset. From machine learning, Random forest, Decision tree, Naïve bayes and Support vector machinewere used, while from deep learning, VGG19, Resnet 101, Resnet, 34, Resnet 50, and Densenet 201 were used for classification purpose. For the training and testing purposes of the presented models, CNN architecture and PyTorch libraries based on Python programming language were used. All of the algorithms from machine learning and deep learningwere applied to bacteria images one by one and accuracies were recorded along with the number of iterations and average time taken by each algorithm during training and testing procedures. The results from both machine learning and deep learning architectures were then compared to find out the best method for classification purposes. In deep learning, we achieved 98.6%, 99.3%, 98.9%, 98.5%, and 98.6% accuracy produced by VGG19, Resnet 101, Resnet 34, Resnet 50 and Densenet 201 respectively. While we obtained the accuracy of 71.68%, 58.63%, 49.31%, 63.18% by using Support vector machine, Naïve bayes classifier, Decision tree, and random forest models respectively, form machine learning framework. The results depict that deep learning algorithms provided much higher accuracies than that of machine learning models. Here, deep learning architecture i.e. Resnet 101 is regarded as the best technique for automated identification of bacterial species. In addition, this is the first enhanced study on classification of pathogenic bacteria images using machine learning and deep learning.
PREDICTION OF HYPERTENSION RISK IN HUMAN USING FEDERATED LEARNING
(UMT, Lahore, 2024) HAFSA MANZOOR
Hypertension, commonly known as high blood pressure, when the force of the blood on the artery walls is continuously too great, it is referred to as hypertension. This research employs federated learning along with machine learning techniques. Predictive models based on a large dataset of various blood pressure metrics from hypertensive patients are developed and evaluated. The study thoroughly evaluates the performance of federated learning techniques when paired with traditional machine learning approaches in order to predict patterns of hypertension. Federated learning in particular, with its accuracy rate of 99.4%, has great potential for healthcare applications. With a heavy focus on privacy and the use of decentralized data sources, the federated learning methodology shows promising results, improving the accuracy and generality of hypertension prediction significantly. The results emphasize how important it is to incorporate information into models that forecast hypertension. They also show how related literacy has revolutionary potential in healthcare applications, especially when it comes to enhancing prediction accuracy and protecting privacy. This research provides important new understandings of hypertension, providing a solid basis for improving public health initiatives and guiding policy choices.
URDU ABSTRACTIVE TEXT SUMMARIZATION USING DEEP LEARNING APPROACHES
(UMT, Lahore, 2024) HAMZA SAEED
One of the most experimental profound learning challenges is text summarization, which reduces the amount of text while retaining its essential and core information. Earlier research in this field will produce impressive outcomes by utilizing highly reliant data. Works about natural language processing is becoming more popular due to implementation issues. In addition to being a key concept in NLP, abstractive text summarization is a popular and challenging topic with variable solutions or outcomes depending on the dataset. The goal of the study is to reformat critical information that has been collected from files, documents, or datasets into a well-simplified text format. The methodology we will use in our study is RNN-based abstractive text summarization. This approach helps the model perform better and is applied to troubleshoot complex issues. One of this paper's features is keyword extraction. Modern technology will be employed to confirm the model's effectiveness. The model's accuracy will be determined and validated using BLEU and ROUGE. The dataset's most prominent feature is how independent each column's relationship is from the others. The paper aims to create condensed text from enormous amounts of data (text format). Sequence-to-sequence and LSTM models are common methods for solving these kinds of problems.
A Proposed Framework for the prediction of Breast cancer by using Federated Learning
(UMT, Lahore, 2024) MEHREEN ILYAS
The leading cause of death for women is breast cancer. Although genetic factors substantially assist in the growth of breast cancer, recent studies show that environmental factors are also essential in the occurrence and spread of the disease. The escalation of environmental factors has become a noteworthy worldwide concern that carries substantial consequences for human health, specifically in connection with breast cancer, resulting in a rise in the incidence and intensity of breast cancer. This study aims to assess Federated Learning's predictive accuracy for breast cancer. Several machine learning techniques, such as XG Boost, Random Forest, Support Vector Classifier, Artificial Neural Network, and stacking classifier, have been studied by researchers to forecast breast cancer issues. Facilitating local data collecting and analysis while maintaining privacy and eliminating the need for centralized data aggregation is one of FL's competitive advantages. Given its capacity to evaluate a variety of locally stored data without jeopardizing patient privacy, FL is the suggested approach for breast cancer prediction. The unique features of FL include privacy protection, local data collecting and analysis, and the removal of the requirement for a centralized data repository.
STORE SALES FORECASTING WITH COMPARATIVE ANALYSIS
(UMT, Lahore, 2024) MUHAMMAD JUNAID KHAN
Sales forecasting or prediction are essential for businesses to make informed decisions about resource allocation, budgeting, and marketing strategies. Sales prediction involves predicting future sales of a product or service. There are several methods that businesses can use to forecast sales, including statistical analysis, market research, and expert opinion. Key factors that can impact sales predictions include market conditions, economic trends, competition, and customer behavior. Literature review shows that forecasting sales can be challenging tasks, as they require businesses to accurately forecast future demand and predict future sales in the face of changing market conditions and unpredictable customer behavior. There are also several uncertainties that businesses may face when forecasting or predicting sales, such as economic conditions, competition, customer behavior, product life cycles, and external events. This research uses the data given by the Rossmann supply chain, which is the second largest drugstore chain in Europe, their dataset contains 3 years of the sales record from the 1115 stores out of 3000+ stores, that we utilize to predict the future sale. This research does the sales prediction and provide a comparative analysis of three widely used techniques in the field of forecasting, namely: statistical modeling, machine learning, and deep learning. In our analysis, after performing extensive feature engineering and get the better results with machine learning algorithm XGboost with an RMSE score of 0.10.