VFAST - Virtual Foundation for Advancement of Science and Technology (Pakistan)
Not a member yet
1255 research outputs found
Sort by
Gender-Neutral Education and Its Impact on the Mental Health and Wellbeing of Students in Private Schools in Pakistan
Full text linkThe paper discusses the nature of gender-neutral education in Pakistan, especially in the context of the private schools, and the current conflict of globalisation of ideals and local values of the Pakistani society. The results of thematic analysis of the answers provided by the participants based on an elaborate questionnaire indicates the existence of a complex and subtle terrain. Although a great number of private schools promote gender neutrality and non-discriminatory approaches to education, one can still feel the opposition even in the general community, as the cultural gap between the forward-thinking educational policies and the established societal norms.The effect this has on the mental health of students comes out to be paradoxical, showing positive impacts in school settings, where equality and inclusivity lead to confidence and collaboration but at very high costs once outside the school setting, where the pressures and stereotypes by the society still prevail. The inclusion in policies and the supportive school staff also represent a contrast with the barriers (parental resistance, social stigma, and the lack of policy enforcement) and the necessity to find a complex, community-wide approach.The information given by the focus group discussion would offer group views and practical suggestions of the creation of a balanced and situation-suited approach to gender-neutral education. The ramifications of this research are not limited to the classroom, but affect the policy formulation process and the practice of education and call on the creation of a culturally aware model that would fit the different realities of Pakistan and remain open to international values. The future research opportunities involve longitudinal studies and comparative analyses to gain a deeper insight and evaluate the effects of gender-neutral education on the well-being of students and the community vision and equity in education
Optimization of Feature Selection using Firework Algorithm for Machine Learning Algorithm
Full text linkIn machine learning and deep learning, the optimal feature selection plays an important role in enhancing performance, decreasing computational cost, and improving the interpretability of the algorithm. The performance of the machine learning algorithm is impacted by the noisy, redundant, and meaningless features found in the majority of classification problem datasets. Feature selection is the process of selecting a feature subset and a search method for finding the optimal subset of features from many features using a fitness function to improve the accuracy and execution time. This research focuses on the application of the fireworks algorithm as a useful tool for optimizing feature selection. By navigating the feature space, the recommended technique finds the optimum subset of features that maximize a model\u27s performance. By analyzing the fitness function, which combines the complexity of the model with the predictive ability of the chosen features, the program repeatedly improves the feature subset. The paper makes use of widely known datasets on breast cancer that include a limited number of characteristics. The classification performance of selected feature subsets is evaluated using classification techniques: Support vector machine, logistic regression, and bagging classifier. The proposed algorithms are better than the particle swarm optimization algorithm, ant colony optimization algorithm, principal component analysis, and so on. The results indicate that a certain feature subset may be chosen with higher accuracy through the use of the recommended techniques, as opposed to using all characteristics. An optimal subset of feature selection techniques enhances the accuracy and decreases the number of features. Enhancements in classification accuracy are supported by a substantial decrease in the number of features with a higher weight on the fast reduction of the fitness function
An Efficient Fault Diagnostic Methodology with LWDA and DAGSVM for Industrial Processes
Full text linkince the advent of industry 4.0, many prevalent techniques and processes in the industry have been redesigned, leading to significant advancements in fault diagnosis methods. These methods can generally be categorized into three main categories: model-based, knowledge-based, and data-driven. Among these, data-driven methods are the most preferred due to the abundance of available data. The integration of machine learning into data-driven methods has become an active area of research. Many techniques with well-documented limitations and capabilities have been proposed in this context. However, when working with larger datasets, two critical challenges arise. First, datasets often contain features with high dimensionality, leading to feature redundancy. Second, larger datasets increase complexity, causing machine learning algorithms to perform poorly. To address these challenges, we present an efficient fault diagnostic methodology using LWDA and DAGSVM. The proposed methodology (i) preserves spatial relationships while reducing both dimensionality and data complexity, and (ii) achieves better classification accuracy for non-linear and overlapping data through optimized kernel approaches. We evaluate this methodology on a benchmark dataset, where experimental results demonstrate an accuracy of approximately 97.49%, outperforming existing approaches
Operability and Policy Implementation of Blockchain Technology in Distance Learning: A Survey
Full text linkNowadays, due to the advancement of technology, most educational institutions and organizations have focused their attention on e-learning education systems, especially since the COVID-19 pandemic. This is accelerating the use of technology in the education system. However, the organizations also face many challenges in implementing this new mode of education. The existing e- learning systems have some limitations, such as user interactivity, system interoperability, and information Security. Currently, there is no secure and privacy control model implemented that protects the personal learning data, such as learning logs in e-learning systems, and the authenticity of academic credentials. Another challenge in the current e-learning system is verifying the authenticity of academic credentials. Some of the other challenges that affect the distance learning system are fraud detection, decentralized classrooms, and ensuring transparency of scholarships. There are many proposed solutions to tackle these problems, such as client-server architecture, cloud, and big data implementation. However, Blockchain technology can provide a solution to these challenges more effectively. This study is based on the use of blockchain in an e-learning system and aims to analyze the operability and policy implementation of blockchain in the education system. To address the above problems, a conceptual model for e-learning systems is proposed by adopting blockchain technology in the education system to create a trusted online accreditation system globally, which reduces the development cost, standardizes infrastructure, and achieves a higher degree of interoperability
Ontology based Semantic Analysis framework in Sindhi Language
Full text link Sentiment analysis, identifying polarity information (Positive, Negative, or Neutral sentiment) from textual data, is a crucial aspect of natural language understanding. However, its implementation in low resource languages like Sindhi presents significant challenges due to linguistic diversity and a limited amount of labeled data. This work addresses these challenges by proposing an ontology-driven sentiment analysis framework that integrates domain-specific ontological knowledge with the power of the Distil-BERT model for efficient sentiment classification. We constructed a custom Sindhi sentiment dataset, comprising 123 sentences annotated with three sentiment classes: Positive, Negative, and Neutral. The Distil-BERT model was employed for tokenization and sequence classification, leveraging its efficiency and adaptability for resource-constrained settings. Using Pytorch and the Hugging Face Transformers library, we trained the model with supervised pre-training arguments using the Trainer API. Additionally, a domain-specific ontology was developed to capture complex linguistic relationships and enrich the model’s semantic understanding, enabling it to handle diverse sentiment- bearing expressions effectively. Experimental results highlight the efficacy of our approach. The ontology-driven model achieved an impressive accuracy of 93%, significantly outperforming the baseline model, which achieved 82%. This improvement underscores the importance of integrating ontological knowledge, particularly in addressing the nuances of low-resource languages like Sindhi. Performance evaluation metrics, including precision, recall, and F1 Score, further validate the superior performance of the ontology-driven framework. This study presents a robust solution for sentiment analysis in Sindhi, laying the groundwork for future research in Natural Language Processing (NLP) for low-resource languages. Expanding the ontology to include more sentiment contexts and exploring hybrid deep learning approaches for sentiment classification offer promising directions for future work
Advancements in EEG-Based Machine Learning Techniques for Early Autism Spectrum Disorder Diagnosis: A Review
Full text linkAutism Spectrum Disorder (ASD) is a neurodevelopmental condition characterized by impairments in social interaction, communication, and repetitive behaviors. Electroencephalography (EEG) has gained prominence as a reliable tool for ASD diagnosis, capturing critical behavioral patterns. Researchers have applied various Machine Learning (ML) techniques to enhance ASD detection, achieving notable accuracy. Studies using feature selection with ML classifiers have reported up to 100% accuracy in children as young as 6–12 months. Other approaches integrating EEG with behavioral features such as eye gaze, facial gestures, and body movements have attained classification accuracies as high as 87.5%. Additionally, resting-state EEG studies have explored microstate differences between ASD and neurotypical individuals. Several ML models, including Support Vector Machines (SVM), Convolutional Neural Networks (CNNs), and ensemble methods like Random Forest and Naïve Bayes, have demonstrated classification precision between 90% and 99%. However, challenges such as data heterogeneity and limited sample sizes hinder clinical implementation. This review highlights the most notable EEG-based ML studies for ASD diagnosis and emphasizes the need for further research to refine these techniques for broader clinical adoption
Transformative Role of LLMs in Digital Forensic Investigation: Exploring Tools, Challenges, and Emerging Opportunities
Full text linkIn the evolving realm of digital forensics, the admissible nature of trustworthy digital evidence in a court of law necessitates the application of scientifically validated digital forensic investigative techniques to substantiate a suspected security event. The incorporation of LLMs represents a transformative technology, set to enhance the efficiency and accuracy of digital forensics investigations. A thorough literature analysis is conducted, including current digital forensic models, tools, large language models (LLMs), deep learning methodologies, and the application of LLMs in investigative processes. The review delineates the issues in current digital forensic methodologies and examines the barriers and potential of integrating LLMs. This study emphasizes the need of integrating LLMs into digital forensics, providing insights into their advantages, disadvantages, and wider implications for addressing contemporary cyber threats
An Extended TOPSIS Method for the Multiple Attribute Decision Making Problems Based on double hierarchy linguistic soft sets (DHLSSs)
Full text linkIn this paper, classical soft set theory is extended to develop Double Hierarchy Linguistic Soft Sets (DHLSSs) for addressing multi-attribute decision-making problems. DHLSSs provide an effective framework for handling qualitative information expressed through double hierarchy linguistic terms. Since the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) is a widely accepted method for multi-criteria decision analysis, this study integrates TOPSIS with DHLSSs to propose an extended decision-making approach. The proposed method is designed to handle situations in which attribute weights and attribute values are unknown and represented in the form of double hierarchy linguistic term elements. Background concepts related to DHLTSs, Hamacher t-norms and t-conorms, as well as fuzzy sets, rough sets, soft sets, and fuzzy soft sets are briefly reviewed. Attribute weights are determined using an entropy-based method, and an improved TOPSIS algorithm is employed to rank alternatives. An illustrative example is presented to demonstrate the feasibility and effectiveness of the proposed approach
A Comparative Study on Predictive Modeling of T20 Opener Success in International Cricket Tournaments via Machine Learning Models: Machine Learning Models in Sports Analytics
No full textIn the game of cricket, particularly during high-stakes tournaments, players’ performances have substantial consequences for their teams and energetic crowd. Predicting players’ outcomes is often validated by experts’ territory through mathematical and statistical models. However, due to the intricacies of cricket, player-related features in different sports cannot be evaluated comparatively. De spite these challenges, the rising utilization of Machine Learning (ML) models has proven crucial role in achieving precise predictions. In this research study, the ultimate aim was to predict the performance of T20 opening batters for upcoming T20 tournaments. Player records were compiled from ESPNcricinfo and Cricbuzz. Several ML models are implemented to predict players’ outcomes. The analysis for this study was categorized into two cases: runs scored and strike rate, acknowledging both pre-match and all-match features. For predicting outcomes based on runs scored using pre-match features, Decision Tree and Naïve Bayes outperformed with an accuracy of 0.75, while for strike rate, K-Nearest Neighbor surpassed models with an accuracy of 0.68. Furthermore, assessing players’ performance on runs scored using all-match features, Naïve Bayes and Support Vector Machine achieved exceptional accuracy of 0.98. For strike rate across all-match features, logistic regression beat the models with a leading accuracy of 0.98
Pakistan-Saudi Defense Relations: Strategic, Economic, and Regional Implications
Full text linkThe PakistanSaudi defense agreement of September 2025 is a strategic partnership that is established based on historical collaboration, religious connection, economic interdependence, and mutual interests of security. The qualitative research design discussed in this paper is based on an interpretivist ontological and subjectivist epistemological position and utilizes secondary sources. It examines the multidimensional nature of the benefits and issues of this developing alliance, and the focus should be on the military, economic, and diplomatic benefits of Pakistan and the strategic interests of Saudi Arabia, as well as on the regional security concerns in general.The study, based on the Alliance Theory, specifically the focus on asymmetric alliances, explains how Pakistan capitalizes on its experience in operations, symbolic legitimacy and geostrategic position to enhance Saudi security without becoming overly reliant on Iran. The analysis also establishes the difficulties involved in this association such as domestic political sensibilities, expanding economical dependence, and the possibility of becoming involved in a regional conflict.On the whole, the research adds to the insights into the ways in which current defense collaboration between Pakistan and Saudi Arabia is an indication of a compromise between the conscious approach to ensuring the security and the development of the independent foreign policy. It ends with a set of policy proposals to establish a more balanced, sustained, and win-win defense relationship to enhance the strategic position of both countries in a more complex regional order