VFAST - Virtual Foundation for Advancement of Science and Technology (Pakistan)
Not a member yet
1255 research outputs found
Sort by
Signature Elevation Using Parametric Fusion for Large Convolutional Network for Image Extraction
Get PDFThe image acquisition process involves finding regions of interest and defining feature vectors as visual features of the image. This encompasses local and global delineations for specific areas of interest, enabling the classification of images through the extraction of high-level and low-level information. The proposed approach computes the Harris determinants and Hessian matrix after converting the input image to grayscale. Blob structuring is then performed to identify potential regions of interest that can adequately describe texture, color, and shape at different representation levels and the Harris corner detector is used to identify keypoints within these regions. Moreover, scale adaptation method is applied to the determinants of the Harris matrix and the Laplacian operator to extract scale-invariant features. Meanwhile, the input image undergoes processing through VGG-19, DenseNet, and AlexNet architectures to extract features representing diverse levels of abstraction. Furthermore, the RGB channels of the input image are extracted and their color values are computed. All extracted features local, global, and color are then integrated in feature set and encoded through a bag-of-words model to rank and retrieve images based on their shared visual characteristics. The proposed technique is tested on challenging datasets including Caltech-256, Cifar-10, and Corel-1000. The presented approach shows remarkable precision, recall and f-score rates in most of the image categories. The proposed approach leverages the complementary strengths of multiple feature extraction techniques to achieve high accuracy
Enhancing Traffic Control with AI Blockchain and Dynamic Computation Techniques
Get PDFThe rapid urbanization and increasing vehicular density in modern cities have led to significant challenges in traffic management and control. As urban areas continue to expand, the demand for more efficient and intelligent traffic control systems has become increasingly critical. This paper presents a novel approach to enhancing traffic management by integrating Artificial Intelligence (AI), Blockchain technology, and Dynamic Computation Techniques. AI is utilized to analyze and predict traffic patterns, enabling real-time adjustments to traffic signals and flow management. Blockchain provides a secure, transparent, and decentralized platform for data sharing and coordination among various stakeholders, ensuring data integrity and trust. The incorporation of Dynamic Computation Techniques allows for flexible and scalable processing of complex traffic data, facilitating rapid decision-making and adaptation to changing conditions. This multidisciplinary approach not only improves traffic efficiency and reduces congestion but also paves the way for more resilient and sustainable urban transportation systems. The findings highlight the transformative potential of combining AI, Blockchain, and advanced computation methods in the field of traffic control
Comparative Analysis of Educational Policies of China and Pakistan:A Systematic Literature Review
Get PDFThis paper presents a systematic literature review that offers a comparative analysis of the educational policies of China and Pakistan. The review delves into the historical context, policy formulation, implementation strategies, and outcomes of educational reforms in both countries. To ensure a comprehensive and current analysis, studies published between 2000 and 2023 were included. Data were meticulously extracted from peer-reviewed journal articles, government reports, and policy documents. The selected studies were thoroughly analyzed to identify key themes and patterns, employing a comparative framework to synthesize the data focusing on policy formulation, implementation, and outcomes. This detailed comparative analysis highlights significant differences and similarities between the two nations\u27 educational systems, providing valuable insights into how each country addresses its unique educational challenges and opportunities. By examining these aspects, the review offers a comprehensive understanding of the educational landscapes of China and Pakistan, shedding light on the successes and shortcomings of their respective educational policies. The findings suggest that both countries can learn valuable lessons from each other\u27s experiences, thereby enhancing their educational frameworks. This study contributes to the broader discourse on global educational development, emphasizing the importance of tailored policy responses to meet diverse educational needs
Comparative Analysis of Time Series Forecasting using ARIMA, and GRNNs Models: A Case Study of Death Rate of Diabetic Mellitus in Canada
Get PDFThis research aims to compare ARIMA and GRNN models alone. For this comparison the death rate for diabetes mellitus time series data of Canada is used. Autoregressive Integrated Moving Average (ARIMA), and Generalized Regression Neural Networks (GRNN) models were applied for time series prediction of the death rate for diabetes mellitus—trained data for two models from 2000 to 2015. Test data was used to compare the precision through data from 2016 to 2021. The ARIMA model was applied using the auto-command through R package which provided the least BIC and AIC values. The mean absolute deviation (MAD), root mean squared error (RMSE), and mean absolute percentage error (MAPE) were employed to measure the forecasting efficiency of the models. The ARIMA model had the highest prediction accuracy as compared to the GRNN model. ARIMA predicts the death rate for diabetes mellitus more accurately and robustly compared to the GRNNs model
Generic Moves and Move Strategies in Job Application Letters Written by Pakistani Graduates
Get PDFThis study investigated the generic moves and move strategies in the job application letters of Pakistani graduates. In order to analyze the generic moves, by following Bhatia’s (1993) and Al-Ali’s (2004) frameworks, a model containing eleven moves was developed. Using this model, ten job application letters written by Pakistani graduates were manually examined. The findings of the present study revealed that Pakistani applicants frequently used nine moves out of 11 moves. In their job application letters, Pakistani graduates frequently used straight forward and direct strategies to provide explicit information in their job application letters while keeping professional tone and still follow courtly expressions. It also observed that Pakistani graduates also use the techniques to grab the attention of the potential employer. The results of present study were mostly agreed with previous studies (Bhatia, 1993; Henry and Roseberry, 2001; Al-Ali, 2004; Khan and Bee, 2012). The results of the present study will be helpful for fresh graduates to write an effective job application letter. It is advised that to conduct further study to create a genre-based syllabus.
Keywords: Generic, lexico-grammatical, job application letters, moves, move strategy 
IoT Intrusion Detection with Deep Learning Techniques
Get PDFIt must be argued that the rising number of IoT devices has latest features they got cybersecurity threats and further robust techniques to detect and prevent these threats are needed. This paper aims to propose a novel solution to IoT cybersecurity by using the BoTNeTIoT-L01 dataset and advanced artificial neural networks. The work enhances the classification and categorization of IoT cyber threats using models such as Decision Trees, Logistic regression, LightGBM, and Deep learning. Data pre-processing is been done comprehensively by feature selection and by encoding. A specific enhancement from previous models is the further enhancement of the model performance through the inclusion of T-scores, Leaky ReLU, and Ordinal Encoder. LightGBM and Decision Trees showed superiority in the basic fields of measure such as F1 score, precision, and recall, and the study achieved high accuracy and a high recall rate in threat detection. Specifically, the proposed method achieved an accuracy of 98.76 percent and a loss of 0.034 percent, demonstrating its effectiveness. Comparing LightGBM and Decision Trees with deep learning models, it was found that while both sets of models offered the right balance of testing accuracy with computational amenities, the deep learning models were superior in terms of complexity and pattern discovery. The present study proves that using machine learning algorithms can significantly enhance IoT security; however, the information suggests that updates and changes need to be made constantly and frequently to address the emerging risks
Leveraging Machine Learning And Deep Learning Models for Proactive Churn Customer Retention
Get PDFCustomer attrition is especially an issue in industries such as retail, banking, and telecommunications where customer acquisition costs are significantly higher than the costs of retaining repeat customers. The customer lack of interest is now predictable through machine learning models, and deep learning has become instrumental in early intervention for retention. In order to assess the quality of churn prediction, the study tests six basic machine learning techniques: random forest, logistic regression, and the k-nearest neighbors method, as well as four deep learning techniques: long short term memory (LSTM), bidirectional LSTM, convolutional neural networks (CNN), and artificial neural networks (ANN). The performance of the model is then assessed via the evaluation matrices, including the accuracy, precision, recall, and F1-score from the customer\u27s behavioral data after feature extraction from large datasets. The study reveals that DL models offer improved handling of the churn and non-churn customer classification and Random Forest as well as other ML models comparable accuracy. This research can conclude that LSTM and ANN models outshine in actual-world churn prediction circumstances, especially when long-term consumer behavior evaluation is required. To enhance the current outcomes of a given prediction model, this research focuses on data preprocessing and the utilization of bootstrapping, feature extraction, and the combination of multiple models. The implications of the study provide specific practical recommendations for firms to effectively manage customer churn and increase customer retention by employing data-dealing techniques
Cognitive Therapy and Routine Recommendation System (CTRRS): An AI-Driven Approach for Mental Health
Get PDFDepression detection and management is an important research field nowadays. In this research work, Cognitive Therapy and Routine Recommendation System (CTRRS) is proposed. It automates the process of detecting depression and provides personalized mental health recommendations using a Random Forest model for healthcare activities and a Long Short-Term Memory (LSTM) model for sentiment analysis. The LSTM architecture includes dense layers, bidirectional LSTM layers, and embedding layers, with term frequency-inverse document frequency (TF-IDF) vectorization and early stopping to prevent overfitting. Furthermore, a Voting Classifier improves classification performance by combining the advantages of multiple models. The system\u27s evaluation is centered on accuracy, precision, recall, and F1-score, with confusion matrices offering in-depth analysis. Finally, CTRRS uses a cosine similarity algorithm to customize content to user preferences, increasing engagement. The study integrates machine learning and deep learning by employing a Random Forest model for healthcare activity recommendations and an LSTM model for sentiment analysis and depression detection. This combination leverages the strengths of both approaches to enhance the system\u27s overall performance. Additionally, ensemble learning techniques such as bagging, boosting, and stacking are utilized to balance performance trade-offs and improve predictive accuracy. The LSTM model achieved 96.38% accuracy, 98.10% precision, 94.50% recall, and a 96.27% F1-score, which are important findings. Through user-friendly visualizations (PHQ-9 survey responses, word clouds highlighting frequent terms in depression-related texts, bar charts displaying top TF-IDF features, and confusion matrices for model performance evaluation), CTRRS enables users to monitor their progress in terms of mental health and compliance with recommendations. This research advances mental health care by providing a solution that is stigma-free, scalable, and accessible
A Scholarly Review of the Islamic Principles of Parenting and Contemporary Approaches
Get PDFThis research article explores the dual impact of parental involvement on children’s character and behavioral development, drawing on insights from Islamic teachings in the Quran and Hadith. It investigates how parental attitudes, engagement, and role modeling influence various dimensions of a child\u27s upbringing, including mental, emotional, physical, and moral growth. Positive parental interactions, characterized by love, encouragement, and support, are shown to foster children’s self-esteem, resilience, and adaptability, helping them navigate social and personal challenges. Such interactions also facilitate the development of core moral values, religious understanding, social skills, and self-discipline, which are essential for healthy personality formation.However, the study also addresses the adverse effects that arise from parental neglect, harshness, or excessive strictness, which can create feelings of fear, resentment, and inadequacy in children. These negative experiences may inhibit children\u27s potential for positive personality development and social adjustment. This article underscores the importance of a balanced, compassionate, and informed approach to parenting, with parents serving not only as authority figures but as supportive guides, to help their children become constructive and well-integrated members of society
Sindhi Text-Based Students Sentiment Analysis Using Convolutional Neural Network
Get PDFCurrent generation especially the teenager students are using Social Media (SM) platforms at an extreme level even the sentimental angles are too discussed there. In the province Sindh, students mostly prefer to text the message in origin of their mother tongue i.e. Sindhi lexicon for sharing their views regarded politics, religions, sports, education etc.All these sentimental conveys are important for enhancing the academic capabilities.In this research paper, approach is broken down into multiple phases comprising of number of WhatsApp chat, lexicon generation, dataset tokenization, Convolutional Neural Network (CNN); all based on respective sentiments.To validate the experimentation process at standard level. 100 WhatsApp data chats were collected from different levels of students and divided into four categories.The CNN Model is used for sentimental classification. Accuracy, Precision, Recall and F-Score are the four parameters used for model evaluation. The model provides 0.874% accuracy, 0.883% recall, 0.863% precision and 0.745% F-Score