Department of Computer Science
Permanent URI for this communityhttps://repository.cuilahore.edu.pk/handle/123456789/16
Browse
357 results
Search Results
Item Construction Linkooze(Library Information Services, COMSATS University, Lahore Campus, 2021) Saad Munir; , FA17-BSE-025; Ms. Humaira Afzal, Assistant Profesor; LHR TP 7016With the time, the globalization and widespread of internet, people increasingly rely on online services to accomplish most of their tasks. One particular industry in Pakistan which still lack in digitalization is construction industry. As we know that urban construction sector is increasing rapidly. There are many emerging investors in this sector but with all these investments on a huge scale there are many problems arising day by day. The main problem is that there is no such digital platform that provides interaction between different parties. To find a labor is difficult now a days. We have online platforms like Food Delivery apps, Ride booking apps, Online Medical consultant’s apps etc. Just like that we want to develop an online platform to provide interaction between Contractors, Electricians, Plumbers, Carpenters and Customers.Item TRY ON – The Augmented Reality Try Room Final Year(Library Information Services, COMSATS University, Lahore Campus, 2020) Aibak Shahzad , Muhammad Tayyab Hussain,; SP17-BSE-026 , SP17-BSE-008; : Aamer Mehmood, Assistant Profesor; LHR TP 7143Try On – AR Try Room is an augmented-reality fitting room solution that offers convenience to shoppers and customers. Customers can try on clothes virtually without the hassle of getting in and out of clothes. Retailers can gather crucial data about their customers' preferences and shopping behavior. In this app, we are going to have one mobile device in which we have different models of outfits which will be augmented on a human body. The real-world human body will be our target on which the outfit model will be applied by detecting the human body. And on the other side, we have an admin panel from where we can upload pictures of articles (front-side and the back-side), receives orders, and perform several admin activities. The pictures will then be uploaded and available on the customer side (on a mobile device). In short, this project enables users to try different outfits at home using their mobiles and saying ‘goodbye’ to fitting room waiting lines and then order the suit of their choices while on the other side, benefits the firm by increasing their sales.Item Securing Email Communications: Advanced Approaches to Detecting Phishing Through Spam(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2025) Amna Asif; SP23-RCS-006; Dr. Atif Saeed; LHR TP 9484The growing complexity of email-based communication has made it difficult to correctly identify the spam emails which provide significant hazards such as phishing, malware distribution and data breaches. Conventional spam detection algorithms that use static rule-based techniques like Keyword-Based Filtering, Blacklist Filtering, or rely on individual machine learning algorithms like Naïve Bayes, Logistic Regression, K-Nearest Neighbors, usually fall behind in increasing false positive and decreasing accuracy. This study used an optimal ensemble-based approach for spam email identification using Gradient Boosting Machine and Extreme Gradient Boosting algorithms and aims to enhance spam email detection accuracy through efficient hyper parameter tuning of these machine learning algorithms. Primarily, baseline models were trained on default parameters and then performance of these models was improved through randomized search cross validation method to examine the tuning space of hyper-parameters for efficient hyper-parameter values. By using the Enron dataset, a publicly available extensive collection of actual email data containing 33639 labeled emails, models were assessed using key metrics such as accuracy, F1-score, recall, precision, and ROC-AUC. The experimental results of this study presented that the performance of both algorithms was enhanced by the hyper-parameter tuning when contrasted with the baseline models. The modified XGBoost model outperformed the baseline version and other competitive models with an accuracy of 98.65%. Furthermore, on tuned parameters GBM performed well, demonstrating the effectiveness of ensemble algorithm approach. The results highlight the superiority of ensemble algorithms for challenging classification problems and validate the significance of hyper parameters modification in improving model performance. This research offers useful insights for enhancing cybersecurity measures in email communication systems by developing strong spam detection frameworks.Item Semantic Precision: Forecasting Healthy Practices for Diabetic Patients Using Social Media Perspective and Medical Models(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2025) Hina Idrees; SP23-RCS-015; Dr. Abid Sohail; LHR TP 9483Hyperglycemia mellitus is a chronic health condition that affects millions of people globally, posing significant challenges to both individuals and healthcare systems. The condition arises due to the body's inability to produce enough insulin, as seen in Type 1 diabetes, or its inability to effectively utilize insulin, as in Type 2 diabetes [1]. Managing diabetes requires a multifaceted approach, including regular monitoring of blood sugar levels, adherence to medication regimens, maintaining a balanced diet, engaging in physical activity, and being vigilant for potential symptoms [2]. Poor management can lead to severe complications such as cardiovascular diseases, kidney damage, nerve damage, and vision impairment [3]. This thesis proposes a novel framework to simplify and enhance diabetes care by leveraging real world data, process modeling, and advanced machine learning techniques.Item A Methodological Approach for Classifying and Differentiating Business Processes Using Tasks Label(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2025) Sidra Anwar; SP23-RCS-027; Dr. Abid Sohail; LHR TP 9492It is crucial for two organizations to integrate their business process models when one acquires the other or merges with another organization. This research is motivated by the problem of matching processes with semantically similar activity names and similar process maps that make alignment difficult. Introducing a new approach based on the Domain Specification Mapper along with the current state-of-art transformer models, BERT for semantic augmentation and contextual interpretation of activity labels. The method combines semantic analysis, syntactic features and machine learning algorithms to show that DSM does not only increase the effectiveness of the transformer models such as BERT, but also increases the effectiveness of other machine learning models. Although traditional classifiers and semantic syntactic features failed to provide a correct classification of processes, DSM with BERT can successfully address these problems. Furthermore, the integration of DSM with other classifiers also showed good results and improved the classification rate. This approach facilitates integration of process, increases accuracy and aligns operations which makes it ideal for mergers and acquisitions.Item Enhancing Brain Tumor Diagnosis through Deep Feature Learning and Spatial Context Awareness in MRI Scans(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2025) Qasim Ali; FA22-RCS-022; Dr. Muhammad Aksam Iftikhar; LHR TP 9488Brain tumor classification is a critical task in medical diagnostics, where accurate and timely detection significantly influences treatment planning and patient outcomes. In this study, a hybrid deep learning framework which joins Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) is developed to classify brain tumors based on the BRATS 2021 dataset using the FLAIR modality. The CNN part learns local patterns (e.g. edges and textures) while the ViT part captures global dependencies over the whole images, which provides insights of the tumor regions in a holistic way. After performing pre-processing on the dataset, which comprised of 53,610 images, the images were partitioned into tumor and non-tumor groups. The training, validation, and test sets were created with 80%, 10%, and 10%, respectively. The listed model performed two independently trained models for 100 epochs at first, then is applied a feature fusion technique which exploits the complementarity of both architectures. The hybrid model was assessed based on conventional metrics like precision, recall, F1-score, and accuracy. The result confirmed that the hybrid method achieved better performance than the individual CNN and ViT models, with improvements in precision and strengthened classification capability. The study emphasizes how hybrid deep learning techniques can improve clinical applications by alleviating challenges related to data variability, noise, and image complexity. The proposed method combining local and global feature extraction methods ensures valuable typing providing a reliable and scalable implementation of automatic brain tumor classification helping improve the accuracy and efficiency of healthcare related problem solutions and medical diagnostics.Item An Empirical Study of SQA Topics in Tester Discussions on Stack Exchange(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2025) Nimra Ikram; SP22-RCS-004; Dr. Tariq Umer; LHR TP 9491Software quality assurance (SQA) is becoming more and more well-known all over the world since it is crucial to the reliable and efficient implementation of mobile and web applications. Software test engineers can obtain SQA tools and frameworks like Selenium, Automation, Selenium-web driver, and manual-testing etc. Because of the popularity of SQA, software test engineers routinely discuss SQA related application difficulties on social media platforms such as Stack Exchange (SE). This study attempts to identify challenges encountered by software test engineers during the creation of SQA based apps utilizing the SE data set. Understanding software test engineers talks on SE can provide insights into the amount of time, difficulty, and popularity of SQA based difficulties. Throughout this paper, we gathered 10,593 SE postings discussing SQA difficulties. Topics are identified and arranged into categories and subcategories based on their relationships. Each topic's difficulty and popularity have been examined. Our study showed various findings. Software test engineers highlight five SQA related questions on SE: Testing Techniques, SQA Communication and Collaboration, Software Testing, UI Automation Strategies and Best Practices and Defect Management. Secondly, the topic of Test Coverage Analysis of Test Methodology (Fused_Popularity=4.50) is the most popular in the Testing Techniques topic, followed by Cross Browser and Control Handling in Database Design Testing topic (Fused_Popularity=2.57) within the Software Testing category. Thirdly, SQA based issues across all topics are rapidly expanding on SE, with new queries submitted everyday about testing tools, testing challenges, and acceptance. Fourth, Framework support, Test Automation ,and Selenium Python Web driver Best Practices are the most common categories for 'how' questions. However, many searches in other categories start with 'What'. Fifthly, SE most popular SQA topics are Software Testing (Fused_Popularity=10.8) and UI Automation Strategies and Best Practices (Fused_Popularity=7.0). Sixth, the questions for Testing Technique (Fused_Difficulty = 11.06) and Software Testing (Fused_Difficulty = 4.4) are particularly difficult than the other classification. Our empirical findings could benefit the number of those who are involved: software test engineers, and SQA researchers. Software Test Engineers and researchers can expand their understanding of new ways and create unique techniques for making difficult SQA issues easier to understandItem Wildfire Detection using Satellite Imagery(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2025) Faisal Saqib; FA22-RCS-007; Dr. Zeeshan Gillani; LHR TP 9494This thesis presents an innovative approach to wildfire detection using satellite imagery, aimed at enhancing detection accuracy and robustness through the fine-tuning of pre trained state-of-the-art deep learning models. Utilizing a dedicated wildfire satellite imagery dataset, our research focused on optimizing these models to better generalize across diverse environmental conditions encountered in satellite data. Key evaluation metrics employed in this study included Dice Loss, Intersection over Union (IoU), and Accuracy, which facilitated comprehensive performance assessments. Our method involved adjusting existing model architectures to improve their efficacy in segmenting and identifying wildfire-affected areas accurately. The results of our experiments indicate significant improvements in model performance, with increased precision in detecting and delineating wildfire boundaries. These findings not only demonstrate the potential of advanced computational techniques in the field of remote sensing for wildfire detection but also provide valuable insights for future applications in environmental monitoring and disaster management. This work underscores the effectiveness of tailored deep learning solutions in enhancing the capabilities of satellite imagery analysis for critical real-world challenges.Item A Benchmark Corpus and Methods for the Urdu Qur’anic Question-Answering System(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2025) Abida Ashraf; SP23-RCS-002; Dr. Rao Muhammad Adeel Nawab; LHR TP 9497Question Answering System aims to provide answers to a question posed in natural language. A question can be factoid and non-factoid. With the rapid increase in technologies, the QA task become one of the most challenging and important tasks of Natural Language Processing (NLP). In previous studies, the problem of the QA system for the Holy Quran has been explored for Arabic, English, and Indonesian languages. Urdu has more than 170 million speakers worldwide yet considered low low-resource language. However, the problem of the QA system for the Holy Quran has not been explored for the Urdu language due to the unavailability of the dataset. To overcome this research gap, this study developed a benchmark corpus of the Holy Quran in the Urdu language. We developed the corpus by carefully mapping the QRCD corpus which was originally in Arabic language into Urdu. For the mapping of answers, we take the expertise of data annotators who have a deep knowledge of the Holy Quran in both Arabic and Urdu language. We conducted experiments in a state-of-the-art BERT based LLMs. We evaluate the proposed techniques using Exact Match, partial Reciprocal Rank, and F1 score, and expert judgment.Item Analysis of Earthquake-Caused Damages Using Multi-temporal Synthetic Aperture Radar (SAR) Imagery for Rapid Mapping(LHR TP 9496, 2025) Uneezeh Habib; FA21-RCS-011; Dr Zeeshan Gillani; LHR TP 9496Automated Earthquake Damage analysis is rapidly becoming a field of interest for researchers due to the huge research gaps and potentials it holds for developments. In addition, the significant losses of life and infrastructure has greatly compelled researchers to work in this domain. Since the latest developments for various disaster responses efforts are taking place using high resolution satellites, these real time images are also used for damage analysis of earthquakes. Satellites have the ability to provide us multi temporal data which is obtained in real time. However, the use of post event imagery obtained from satellites still holds a lot of challenges since there is a large scale shortage of training data that is available for this purpose, making the development of resilient algorithms a challenge. Bearing in mind the challenges and gaps of the previous studies, the current research will make use of SAR as well as Optical based satellite imagery for damage analysis. The performance is then evaluated by comparison with baseline methods and evaluation metrics to show that this research has out-performed the existing researches. The primary motive behind this study will be to identify the damaged buildings in real time from the data acquired from satellites. The dataset in this research makes use of SAR data that is compiled from Capella space dataset while the optical data comes from Maxar’s open space program. We consider this task as an image classification task, where we have two classes of damaged and intact. Machine learning algorithms will be applied on the compiled data so that the efficiency of damage detection of the overall system can be assessed. In this way a damage analysis system will be proposed which can help scientists detect earthquake damages in real time allowing for faster recovery efforts.