VFAST - Virtual Foundation for Advancement of Science and Technology (Pakistan)
Not a member yet
1255 research outputs found
Sort by
Intelligent Hybrid System for Automated Heart Disease Prediction and Identification
Full text linkCardiovascular disorders are major worldwide health concerns that require sophisticated and effective diagnostic instruments. An intelligent hybrid decision support system for the automated diagnosis of cardiac disorders is presented in this research. The suggested system combines the improved predictive power of the Boost Trap method with the durability of the K-fold approach. Effective cross-validation using the K-fold approach guarantees the model\u27s applicability to a variety of datasets. At this stage, the system\u27s reliability is increased as overfitting is decreased, and a thorough assessment of its performance is given. Moreover, by iteratively increasing the system\u27s forecast accuracy, the Boost Trap method strengthens the decision-making process. The total diagnostic precision is increased by this algorithm by combining the strengths of numerous models using ensemble learning techniques. By combining these algorithms, a synergistic decision support system is produced that can identify cardiac diseases with high accuracy and that can also readily adjust to different data settings. The Gradient Boosted Tree algorithm achieves 94.05% accuracy on GitHub and 92.19% on Kaggle datasets. Integrating these algorithms creates a decision support system that identifies cardiac diseases across data settings. When implemented, this model provides doctors a reliable tool for diagnosis, advancing automated healthcare for cardiac conditions. By giving doctors a dependable tool for prompt and precise diagnosis, the suggested method advances automated healthcare solutions and eventually helps with the efficient treatment of cardiac conditions.
Solving Software Project Scheduling Challenges Using a Search-Based Approach
Full text linkEfficient scheduling is a cornerstone of successful software project management, directly influencing delivery timelines, cost control, and resource utilization. However, inadequate scheduling methodologies remain a critical factor behind project delays and budget overruns, particularly in contexts requiring rapid deployment such as the COVID-19 pandemic. This study addresses the Software Project Scheduling Problem (SPSP) through a search-based approach leveraging metaheuristic optimization techniques. Specifically, we investigate the effectiveness of Genetic Algorithms (GA), Tabu Search (TS), and their hybridization, in comparison with alternative metaheuristics such as the Firefly and Dragonfly algorithms. The International Software Benchmarking Standards Group (ISBSG) dataset, comprising over 2,000 global software projects, is employed as the empirical basis for validation. The research design encompasses a comprehensive literature review, formulation of research questions, and systematic application of GA and GA–TS hybrid models. Experimental evaluation reveals that the hybrid approach achieves substantial improvements over standalone GA, with mean fitness values increasing by approximately 40% across 100 iterations (from 0.948 to 1.887 in the final 10 iterations). Furthermore, the hybrid model reduced convergence time by nearly 30%, enhanced resource allocation accuracy, improved project duration estimates by 25%, and lowered projected costs by 20%. These results demonstrate that the GA–TS hybrid consistently provides more robust, efficient, and reliable scheduling solutions. The findings contribute to both theory and practice by validating the superiority of hybrid metaheuristics in addressing the inherent complexity and nonlinearity of SPSP. They further highlight the potential of search-based techniques to improve real-world project management outcomes in dynamic and resource-constrained environments. Future research should extend this work by integrating additional metaheuristic combinations, incorporating uncertainty modeling, and testing across diverse datasets to generalize applicability and strengthen practical adoption
An Explainable Deep Learning Framework for Automated Classification of Ocular Diseases in a Big Data Environment
Full text linkOcular diseases such as cataracts, glaucoma, age-related macular degeneration, and diabetic retinopathy remain major contributors to global visual impairment and blindness, where early detection is critical for effective intervention. While color fundus photography is widely used for retinal screening, manual interpretation is time-consuming and prone to error, highlighting the need for automated, accurate, and interpretable diagnostic solutions. In this study, we propose a deep learning based framework for the automated classification of ocular diseases and normal cases using medical images. The framework incorporates a comprehensive preprocessing pipeline and leverages a scalable Apache-powered big data environment for efficient feature extraction and model training on large-scale datasets. A Convolutional Neural Network (CNN) was proposed and benchmarked against state-of-the-art architectures including VGG19, ResNet50, and GoogLeNet, achieving superior performance with an accuracy of 97%, precision of 93%, recall of 97%, and F1-score of 93%. To enhance interpretability and clinical trust, Gradient-weighted Class Activation Mapping (Grad-CAM) was integrated, generating heatmaps that highlight the most discriminative retinal regions influencing predictions. The proposed approach not only achieves high diagnostic accuracy but also ensures transparency, scalability, and clinical relevance, making it a promising step toward real-world deployment of explainable AI systems in ophthalmology and broader healthcare applications
Deep Learning-Based Predictive Analytics for Weapon Detection: A Fusion of FMR-CNN and YOLOv9 Models
Full text linkThe early detection of firearms from surveillance videos is necessary to improve public security and life. Even with the growing advancement of Deep Learning (DL) techniques, difficulties persist in distinguishing generic items from weapons in surveillance footage. While deep learning has significantly advanced generic object identification, weapons detection demands specialized methods that maintain high accuracy and processing efficiency. This study addresses these challenges by presenting a novel hybrid deep learning system that combines the strengths of Faster R-CNN, Mask R-CNN, and the YOLOv9s architecture. The aim is to enhance surveillance systems through predictive analytics and automatic weapon identification for defensive security measures. This research focuses on deep learning to create an intelligent detection system that improves operational effectiveness and recognition accuracy. The testing results indicate that the hybrid technique outperforms the individual models, achieving an overall accuracy of 99.02%, along with comparable precision and recall scores. In contrast, YOLOv9s alone achieved an accuracy of 98.70%, while other standalone models showed lower performance. However, the technique still faces limitations in poorly lit or visually cluttered environments.The proposed framework represents a flexible, scalable, and precise tool for instantaneous weapon spotting, contributing substantially to intelligent monitoring technologies and community protection efforts
Impact of Individual Participation and Their Health Education on the Growth of the Sportsy Population
Full text linkHealth education plays a significant role in promoting health, creating awareness of health issues, and adjusting the focus on the value of physical exercise in enhancing the general health of individuals. This paper focuses on a mathematical model for the interaction between health education, individual involvement, and the growth of the sports population and proposes the best decision solutions. An intelligent approach based on Bayesian Regularization (BR) and neural networks is used to predict the solutions of the presented mathematical model. To verify the accuracy of the predicted solutions for the mathematical model, the RK-4 numerical technique is utilized to generate target points for comparison. Different scenarios and the subsequent variation in parameters are used to determine the solutions of the model and the stability of our utilized technique. This study provides useful information for developing effective evidence-based interventions to promote a healthier and more active population
A Comparative Analysis of Four Navigation Aids on User Performance in Single User Virtual Environment
Full text linkIn virtual environments (VEs), whether collaborative or single-user, numerous interaction strategies have been developed to facilitate task execution. However, due to the diverse nature of tasks and applications in VEs, these interaction techniques often vary significantly and lack standardization. Consequently, there are no universally accepted or well-organized interaction techniques that can be effectively applied across all VEs. This limitation becomes especially evident in Single User Virtual Environments (SUVEs), where effective communication modalities are essential for task execution. Despite their importance, there has been limited research on systematically comparing communication modalities such as arrows-casting, textual guidance, audio cues, and 3D Map-Liner (3DML) to assess their impact on user performance during task completion in SUVEs.This study aims to address the above gap by evaluating user performance with different communication modalities in SUVEs. Specifically, it compares the effectiveness of arrows-casting, textual guidance, audio cues, and 3DML for task execution in a VE designed for assembly tasks. A virtual environment was developed where the Dijkstra algorithm was implemented to calculate the shortest distance, ensuring optimized navigation. To conduct the study, 20 undergraduate students were selected to test these navigational aids. The results highlight that arrows-casting demonstrated the highest user performance among the tested modalities, while audio navigation aids showed the lowest performance.The findings of this study provide valuable insights into the design and selection of communication modalities in SUVEs. The superior performance of arrows-casting suggests that visual navigation aids are particularly effective in guiding users during task execution. On the other hand, the low performance of audio navigation aids indicates the need for further refinement and integration of audio cues in VEs. These results can inform the development of more efficient and user-friendly navigation aids, contributing to improved task completion and overall user experience in VEs. Additionally, the methodology and findings can serve as a foundation for future research on interaction techniques and task optimization in diverse virtual environments
Hybrid Deep Learning Approaches Enable Intrusion Detection System for Zero-Day Phishing Detection
Full text linkThese days, The website Uniform Resource Locator (URL) is widely used for accessing and navigating online information. However, the rise of AI-generated fake content, scams, counterfeit URLs, and other cyberattacks has significantly increased phishing-related threats. These fake URLs are difficult to identify because phishing links often resemble legitimate URLs. Consequently, both known and unknown (zero-day) phishing attacks remain difficult to detect in practice.This paper presents a hybrid deep learning–based intrusion detection system capable of detecting both known and zero-day phishing URLs. The objective is to provide users with absolute URLs while protecting them from fake ones. Another goal is to design an adaptive intrusion detection system (IDS) that combines static analysis, signature-based detection, and heuristic methods to identify phishing URLs. The proposed method, named the Zero-Phishing Convolutional Neural Network and Long Short-Term Memory (ZP-CNN-LSTM) algorithm, consists of three distinct schemes. For instance, static analysis rules are based on regular expressions, signatures for convolutional neural networks (CNNs), and zero-day detection using LSTM and autoencoders. We tested our project in the VR and AR research laboratory on 2 million testbed URLs, determined whether they were real or fake with respect to phishing, and predicted their phishing patterns. Results show that the proposed method achieves 98% higher accuracy than existing phishing detection methods in practice
The Concept of ʿAqd (Contract) in Islamic Jurisprudence: An Analytical Study with Reference to the Contract Act 1872
Full text linkThe concept of contract forms the foundation of legal, commercial, and social transactions, making its study essential for both jurisprudential and practical purposes. This research explores the concept of ʿaqd (contract) in Islamic jurisprudence and examines its relationship with the modern legal framework of the Contract Act 1872. The study begins with a lexical and juristic analysis of ʿaqd, tracing its Qur’ānic foundations, linguistic dimensions, and scholarly interpretations, with particular emphasis on its essential elements: ījāb (offer), qabūl (acceptance), and irtibāṭ sharʿī (legal binding recognized by Sharīʿah). It further highlights the role of mutual consent (tarāḍī), intention (niyyah), and lawful subject matter as fundamental conditions for the validity of contracts. The research then evaluates the legal definitions of contract under the Contract Act 1872, focusing on the distinctions between promise, agreement, and contract, as well as the requirements of enforceability, consideration, and lawful object. A comparative analysis demonstrates that while the Contract Act 1872 is concerned primarily with enforceability under positive law, Islamic jurisprudence emphasizes both the external act of agreement and the internal dimension of Sharīʿah compliance. Consequently, Islamic law excludes void (bāṭil) contracts that contravene Sharīʿah conditions, whereas the Contract Act recognizes validity if statutory requirements are met, even when Sharīʿah principles are absent. This study concludes that the concept of ʿaqd in Islamic jurisprudence offers a more holistic framework, combining legal enforceability with ethical and spiritual dimensions, thereby providing a balanced approach to justice and accountability in contractual relations
Ecodisaster Imaginaries and Future-Oriented Mental Worlds: An Analysis of Climate Trauma in Nathaniel Rich’s Odds Against Tomorrow
Full text linkThe current study is an attempt to unveil Climate Trauma is Nathaniel Rich’s Odd Against Tomorrow. The field of Climate Trauma is a burgeoning field in ecocriticism which has grabbed the attention of the literary imagination, where text like Odd Against Tomorrow deals with it in a nuanced way. The novel deals with Climate Trauma where fictitious characters suffer the symptoms of Climate Trauma i.e. hallucination, flashforward, pre-anxiety and pre-traumatic stress syndrome. The major selected character, Mitchel Zukor, has severe Climate Trauma and he manifests almost all the symptoms of Climate Trauma. The current study is qualitative in nature where relevant text exhibiting Climate Trauma and its symptoms has been explored and data has been gathered through close reading where then an in-depth textual analysis has been carried out. The research paper finds that pre-traumatic stress syndrome is a real mental phenomenon caused by the anxiety about future ecological calamity in the fictious character in the novel. It unveils that Mitchel Zukor carries pre-traumatic stress syndrome which has been caused by his alienation, isolation and detachment from nature. It also unveils that his mechanistic, reductionistic and materialistic approach towards nature has caused his Climate Trauma. The study is important because it deals with a burgeoning field of Climate Trauma and ecocriticism, and it drags the attention of the researchers in literary studies to engage with this field and explore it in novel ways. The study fills in a very important gap by arguing that E Ann Kaplan’s Climate Trauma theory is largely individualistic focusing on spectacular and episodic events while ignoring the slow gradually unfolding and cumulative nature of ecologically induced mental distresses
From Deterrence to Domination: Contemporary Israeli Aggression and Its Impact on Middle Eastern Geopolitics
Full text linkThis paper evaluates this military paradigm shift in Israel whereby the strategy of deterrence has been changed to domination and its implications on Middle East geopolitics. In the past, Israeli security policy was characterized with existential threats, which have been characterized by deterrence by alliances and military dominance. However, the conquest of Palestine lands, failure of peace efforts, and later ones of Lebanon, Gaza and Syria, were a doctrinal shift of defense to regional hegemony. It aims at achieving three objectives; the first, it aims to examine the evolution of the doctrine of Israel, that is, from deterrence to domination; the second, it will assess the geopolitical interests of Israeli aggression in the contemporary world, including the extent of its penetration in to the countries of the Gulf region, such as Qatar; and, the third, it will determine how far this transformation threatens the international law and the stability of the region. The study uses a descriptive-analytical design, which utilizes only secondary sources, including scholarly books, peer-reviewed journal articles, and policy briefs. The theory is structured realism, which explains how systemic disequilibrium and great-power patronage stimulating states to pursue hegemonic objectives. The study confirms the growing Israeli aggression that undermines the sovereignty, destabilizes the mediation and exacerbates polarization in the Middle East, with the case of Hamas leaders being struck down by a 2025 strike in Doha. The study concludes that the shift of Israel to deterrence to domination is recreating the regional order through the destruction of the international norms and accelerating the instability. It proposes the need to countify collective regional security structures, intensifying international accountability structures, and securing neutral mediators with a view to preserving the de-escalation and conflict resolution channels