VFAST - Virtual Foundation for Advancement of Science and Technology (Pakistan)
Not a member yet
1255 research outputs found
Sort by
Towards Improved Assistive Technologies: Classification and Evaluation of Object Detection Techniques for Users with Visual Impairments
Get PDFEven though millions of people struggle to interact with the outside world due to visual impairments, vision is an essential part of our daily lives. Because of its ability to identify and navigate around objects in their surroundings, object detection a crucial component of computer vision has become a potentially helpful solution. This study offers a thorough analysis of object detection techniques utilizing a dual classification system that combines traditional and deep learning methods. In addition, we analyze the most popular evaluation metrics and datasets for these systems\u27 training and evaluation. Unlike previous surveys, our work provides a unique perspective by carefully examining the latest advancements in both innovative deep learning models and traditional approaches. The survey\u27s conclusion highlights current problems and recommends future research directions, highlighting the need for more effective models, diverse datasets, and multi-modal data integration to improve assistive technologies for the visually impaired
Optimized Music Classification with a Hybrid VGG16-RNN Using Mel-Spectrogram and MFCC Features
Get PDFMusic classification using deep neural networks has gained a lot of attention in recent years. This is due to the difficult task of capturing every essential aspect of music in features and interpretability of classifiers. There is limited research on the integration of VGG16 and RNNs, but the researchers found that few classifiers accurately capture intrinsic musical characteristics. Previous work in this field has primarily focused on spectral features, which has constrained overall performance. To address this issue, we proposed a novel hybrid neural architecture based on Visual Geometry Group 16 (VGG16), which is highly effective in extracting important features from musical variations. We combined VGG16 with several recurrent neural network (RNN) variants, including Gated Recurrent Unit (GRU), Bidirectional GRU (BiGRU), Long Short-Term Memory (LSTM), and Bidirectional LSTM (BiLSTM). Additionally, we compared their performance for the GTZAN dataset using both Mel-Spectrogram and Mel-Frequency Cepstral Coefficients (MFCC) features. Our results indicate that the VGG16+GRU model achieved the highest accuracy of 89. 60% with Mel spectrograms and 82. 70% with MFCC features. These findings demonstrate the effectiveness of combining advanced feature extraction techniques with deep learning models for music genre classification
Towards Secure Identification: A Comparative Analysis of Biometric Authentication Techniques
Get PDFThis paper provides an overview and analysis of existing biometric authentication methods. Biometric authentication enhances the security of traditional authentication methods by utilizing unique biological characteristics of individuals, such as fingerprints, facial features, or iris patterns, to verify identity. However, implementing biometric authentication may involve initial setup costs for service providers due to the need for specialized hardware and software. Additionally, users may experience some initial inconvenience during the enrollment process to register their biometric data. This paper presents a comparative analysis of the usability of biometric authentication techniques. Initially, a survey of existing work is conducted by comparing techniques, algorithms, and metrics used in research. Later the challenges of the distinct types of authentication techniques are discussed, and their problems are discovered. Subsequently, the findings of a quantitative study based on a are presented, aimed at assessing the usability of those techniques. The findings indicate that authentic biometric techniques are perceived as usable
Evaluating the Performance of Machine Learning Classifier Algorithms for Software Estimation in Software Development Projects
Get PDFThe major aim of this research is to rank the best performing features in order to classify the Software estimation dataset using SVM, Naïve Bayes, Random forest, Decision tree, and KNN classifiers and evaluate their accuracy. Two steps are involved in the classification process: first, the dataset with all attributes is analyzed; second, the information gain methodology is used to rank the attributes, and only the highly rated ones are used to generate the model of classification. Using several folds of cross-validation, we assess the accuracy rank of SVM, Naïve Bayes, Decision tree, Random forest, and KNN classifie
Investigation the Stochastic behaviour of the Traffic Flow: A Case Study of a Section of a Road
Get PDFThe stochastic behavior is one of the key for the current state of vehicles flow for the real time traffic behavior. This paper describe the study to investigate the stochastic behavior of real time traffic flow for a section of road using probability distribution fit over the section of road, the traffic data was collected for a week from 7:00 to 19:00 at the location Nawabshah Pakistan. The different distribution such as Normal, Lognormal, Weibull, Gamma, Exponential distribution was fit using MATLAB distribution fit by probability plot of traffic flow data. The same distribution was used for the goodness-of-fit tests by considering Kolmogorov-Smirnov, Kolmogorov-Smirnov modified, Anderson-Darling were used with p-values at 95% of confidence level and justification to accept the hypothesis test are accepted or rejects. The hypothesis accept for Normal, Weibull and Gamma distribution which accept the all hypothesis test and among these three accepted fit distribution the Normal probability distribution fit is most fitted distribution using the rank by p-value of the hypothesis tests.
Keywords: Traffic flow, Goodness-of-fit, Probability Distributions, Nawabsha
Geometric Modelling of a Family of 4-Point Ternary Approximating Subdivision Scheme U_φ with Visual Performance
Get PDFMaking signals better than noise in communication has always been challenging for scientists. Researchers have been working on it in different ways. The computer-aided geometric design is a new research field emerging from the collaboration of computer algorithms and mathematical logic towards curve designing, in which the subdivision schemes used have a key position due to their flexible and smooth behaviour. Using parameters in these schemes allows for increased control over designing. A parameterized framework for generating a wide range of subdivision surfaces with tunable degrees of shape control is presented in the family of schemes. The properties of the proposed family make it suitable for use in isogeometric analysis, computer animation, and geometric modelling. The purpose of this paper is to construct and analyze a family of 4-point ternary subdivision schemes to smooth the curves based on the Laurant polynomial. This family is generated by tuning the weight parameter. The scheme is analysed for its different properties. The scheme has continuity. Visual performance of the subdivision scheme is also provided as an application of this proposed study
Numerical Simulation Model of the Infectious Diseases by Comparing Backward Euler Method and Adams-Bash forth 2-Step Method
Get PDFIn this work, the Backward Euler technique and the Adams-Bashforth 2-step method—two numerical approaches for solving the SIR model of epidemiology are compared for performance. An essential resource for comprehending the transmission of infectious illnesses like COVID-19 in the SIR model. While the explicit Adams-Bash forth 2-step approach is well known for its computing efficiency, the implicit Backward Euler method is noted for its stability. The study evaluates the accuracy, strength, and computing cost of the two approaches to determine which approach is best for simulating the spread of infectious illnesses. The SIR Model was easily solved using the Adams Bashforth 2-step analysis and the Backward Euler method. The approaches\u27 solutions are close to the exact requirements. There are important distinctions between the two-step Adams Bashforth and backward Euler procedures. The running time of the Adams Bashforth 2-step backward Euler method is shorter than that of the backward Euler method
The Analysis the Performance of SDN Controller and AI System for Future Network
No full textthe SDN is new network controller concept and it provide faster packet data receiving and dynamic path in large network. It can work with old systems via creating new nodes. It can monitor activities of traffic routing, flowing and congestion and on the basis of these updated from all routers in the network. It can provide best shortest route to data packet in few seconds. But the main issue is that its location and controlling of huge data. The network controller can be track and data can be hack by hackers. The AI (artificial intelligence) system can help SDN controller to work batter, improve speed of the system and provide security to control network. In this paper, the methods working of AI with SDN controller will be analyzed to make system faster and save from cyber-attack and a solution will be proposed based on analyses of SDN Network.  
Practices of critical challenges during requirements implementation in global software development:A systematic literature review
Get PDFContext: Finding practices of critical challenges are essential in global software development (GSD).Practices of different challenges have discussed in literature in dispersed form that need a proper method to make them useful.Objective: To find out the practices of critical challenges in GSD. New practices helps team to work collaboratively with new products and features and to improve the overall quality of the development process. Some challenges have different background with unique practices which can be find out through a proper process. Method: Systematic literature review (SLR) is used to find out the practices of critical challenges in GSD.Result: Some common practices are ‘Use of synchronous and asynchronous communication technologies’, ‘Use of modern tools and technologies for GSD’, ‘Frequent/regular agile meetings’, ‘Role of effective management’, ‘Process maturity’, ‘Role of liaison’ and ‘Clear roles and responsibilities of duty’
Promoting Learner Autonomy in English Language Classrooms in Pakistan: The Role of Self-Regulated Learning and Technology Integration
Get PDFThe present study investigates the development of learner autonomy and technology-enhanced language learning (TELL) practices in English classrooms at Shaikh Ayaz University Shikarpur (SAUS) highlighting both self-regulated learning strategies/behaviors. Learner autonomy is a key concept in contemporary language teaching, as it requires our learners to be responsible for their learning. However, in Pakistan teacher centered and traditional approaches are generally dominant that hinder students to become an efficient controller of their own learning. Taking SAUS as a case study, this research seeks to investigate how SRL strategies that are supported by digital tools can foster learner-autonomy in an elite academic institution of Pakistan. In particular, this study looks at the impact of digital platforms and mobile applications on online learning. Study design involves gathering data through classroom observations, student and teacher interviews, surveys. The research highlights the major challenges and opportunities for promoting learner autonomy in university, suggesting that these strategies could be applied to similar processes of change at other institutions around Pakistan. The results reveal that the role of technology is quite supportive in SRL but without institutional support, teacher training and student motivation, self-directed learning may not highly function within ELT context