VFAST - Virtual Foundation for Advancement of Science and Technology (Pakistan)
Not a member yet
1255 research outputs found
Sort by
Impact of climatic anomalies and reservoir induced seismicity on earthquake generation using Federated Learning
Get PDFIn this article, impact of climatic anomalies and artificial hydraulic loading on earthquake generation has been studied using federated learning (FL) technique and a model for the prediction of earthquake has been proposed. Federated Learning being one of the most recent techniques of machine learning (ML) guarantees that the proposed model possesses the intrinsic ability to handle all concerns related to data involving data privacy, data availability, data security, and network latency glitches involved in earthquake prediction by restricting data transmission to the network during different stages of model training. The main objective of this study is to determine the impact of artificial stresses and climatic anomalies on increase and decrease in regional seismicity. Experimental verification of proposed model has been carried out within 100 km radial area from 34.708o N, 72.5478o E in Western Himalayan region. Regional data of atmospheric temperature, air pressure, rainfall, water level of reservoir and seismicity has been collected on hourly bases from 1985 till 2022. In this research, four client stations at different points within the selected area have been established to train local models by calculating time lag correlation between multiple data parameters. These local models are transmitted to central server where global model is trained for generating earthquake alert with ten days lead time alarming a specific client that reported high correlation among all selected parameters about expected earthquake
A Contemporary Secure Microservices Discovery Architecture with Service Tags for Smart City Infrastructures
Get PDFThe re-conceptualization of fundamental elements from traditional monolithic structures to the Microservices framework has emerged as a vital vision for the future of IoT systems. This transformation is pivotal in addressing the present and future challenges faced by IoT systems and enhancing their overall operational qualities. The adoption of Microservices in IoT introduces an array of opportunities for innovative research, which collectively contribute to its feasibility and success. The transition from traditional systems to Microservices in IoT brings forth various complex challenges that need to be effectively addressed. Key challenges include ensuring seamless Microservice discovery, efficient API gateway management, scalable distribution services, reliable uniform service discovery, robust containerization, and stringent access control mechanisms. These challenges encompass both technical and security-related aspects, necessitating innovative solutions to overcome them. To overcome these challenges, our research proposes a secure service discovery architecture that integrates security measures at each stage of the discovery process. This methodology employs advanced encryption techniques, authentication protocols, and authorization mechanisms to safeguard Microservices in IoT. A mathematical framework is introduced to formalize and implement these security measures, ensuring a robust and reliable approach to Microservices adoption in the IoT ecosystem. In the experimental phase of our research, we aim to validate the proposed secure service discovery architecture through a series of rigorous tests and simulations. We will assess its performance, scalability, and security efficacy under various real-world scenarios and IoT use cases. Experimental results and performance metrics will be analyzed to provide empirical evidence of the viability and effectiveness of our proposed methodology in addressing Microservices-related challenges in IoT systems
Fingerprint liveness detection using dynamic local ternary pattern (DLTP)
Get PDFNowadays, biometric confirmation systems are utilized for security applications such as verification and identification. There are various biometric modalities such as fingerprints, face recognition, and iris scans. Biometric systems are superior to PIN and password-based systems because the latter can be easily stolen or forgotten, whereas biometric traits are unique and difficult to replicate or forget. Among biometric modalities, fingerprint recognition is widely employed for security purposes due to the distinctiveness of each individual\u27s fingerprint. However, fingerprint biometric systems encounter challenges, such as the reproduction of fake fingerprints using materials like silicon, which can potentially bypass security measures. This issue is considered a significant problem in fingerprint systems.This paper proposes a new software-based method called Dynamic Local Ternary Pattern (DLTP) for fingerprint liveness detection, employing a machine learning classifier, specifically Support Vector Machine (SVM), to distinguish between live and fake fingerprints. Various experiments were conducted using DLTP and state-of-the-art texture descriptors. The results obtained from DLTP demonstrated optimal accuracy, clearly surpassing those achieved by the Local Binary Pattern (LBP) and Local Ternary Pattern (LTP) texture descriptors reported in previous studies
Enhancing MBTI Personality Prediction from Text Data with Advance Word Embedding Technique.
Get PDFUnderstanding human personality traits is crucial for various domains, including psychology, education, and human resources. The Myers-Briggs Type Indicator (MBTI) is a widely recognized psychological assessment tool, categorizing individuals into one of sixteen distinct personality types. The existing methodologies, which primarily relied on Word2Vec embeddings and traditional machine learning models, showed promise but left room for improvement. To address this problem, this research focused on enhancing Myers-Briggs Type Indicator (MBTI) personality prediction from text data through advanced word-embedding techniques, specifically GloVe and BERT. The research investigates the effectiveness of various Machine Learning Classifiers, including Random Forest, XGBoost, LinearSVC, SGD, Logistic Regression, and CatBoost, in predicting MBTI personality types. Additionally, the impact of preprocessing techniques such as text cleaning, tokenization, TF-IDF vectorization, GloVe, and BERT embeddings on classification performance is examined. Furthermore, the research explores strategies for addressing class imbalance through upsampling techniques. Results indicate high accuracy and performance across multiple classifiers, with XGBoost achieving the highest accuracy of 97.33%. The analysis of MBTI dimensions reveals nuanced insights into the classifiers\u27 ability to capture specific personality traits
Machine Learning Techniques for Cyber Security in Internet of Robotic Things
Get PDFRobots are becoming common in domestic, medical, industrial, entertainment, and educational routine activities. The use of robots automates the work processes thus minimizes human labor. The Robots perform complex and repetitive tasks with efficiency and agility, therefore, the conventional industrial manufacturing process are being replaced by smart manufacturing. Robotics encompasses the design and development of robot-based automated systems. It integrates various emerging technologies i.e. operational technology (OT), cloud computing, and artificial intelligence (AI). The Internet of Robotic Things (IoRT) seamlessly combines robots and Internet of Things (IoT) devices, enabling connectivity through the Internet. IoRT enables simple robots to coordinate with each other to achieve well-defined goals by creating a multi-robot system. Cyber security is an inherent challenge for IoRTs because of the interconnected infrastructure and reliance on critical industrial operations on the internet. Any cyber-attack can affect the ongoing operations and compromise the safety of robots. The growing interest among governments, researchers, and industries in robotics and automation demands a dependable cyber-security solution. This paper explores machine learning (ML) based cyber security solutions to mitigate cyber vulnerabilities and threats to IoRT and its dependent systems
Quadratic twist of an elliptic curve in a generalized Weierstrass equation over a function field
Get PDFThis paper mainly focuses on the construction of a quadratic twist for an elliptic curve represented in a generalized Weierstrass equation over the field Fq(t). The specific form of the quadratic twist, presented in the generalized Weierstrass equation, is determined by linear algebra approach and discussed in detail
Series Solution of Unsteady Tank Drainage for Third Order Fluid using Adomian Decomposition Method
Get PDFIn this research study the tank model of isothermal and unsteady drainage is considered. Geometry of the tank is in cylindrical and at the bottom a pipe for flow of the fluid is attached. Sub class of viscoelatic non-newtonian fluid is considered. It is planed to obtain the series solution of the model with Adomian Decompositon in the light of no slip conditon. It is also decided to compare the velocity profile of adomain decompositon with the perturbation method for this fluid. On the basis of the results and comparison efficiency of both methods will be disscussed
Improved Class of Regression Type Mean Estimators in Simple Random Sampling Using Concomitant Variable: An Application in T-20 International Cricket
Get PDFIn sample surveys, the information on supplementary variables is usually used to improve the efficiency of the estimators. The ratio, product, and regression estimators are examples. This study proposes new regression estimators for population mean estimation under simple random sampling using the data of Twenty20 (T-20) International Cricket. The estimators are proposed with the help of non-conventional location parameters of concomitant variable which includes Tri-Mean, Mid-Range, and coefficient of quartile deviation. The bias and mean squared error (MSE) of new estimators have been theoretically derived up to the first-order approximation. The theoretical findings were then compared with the existing estimators numerically through simulation study and real-life data. The numerical results reveal that the suggested estimators are more efficient than the estimators in the literature in all conditions
Parallel Numerical Solution of 2D Electrostatics Poisson Equation on Different Mesh Partitioning Schemes
Get PDFThe ideas of parallelism for the large scale problems or problems with dense meshes have gained much attention in last few decades. The key goal of applying the parallelization is to reduce the computational time. In this paper; the 2D finite difference mesh partitioning schemes and their effect on performance of parallel numerical solution is evaluated. The main objective was to investigate the mesh partitioning schemes for less computational time and high speedup. For testing and implementation purpose a 2D electrostatics Poisson’s equation with Dirichlet and Neumann boundary conditions applied on a 2D cross section of Electrohydrodynamic (EHD) planar ion-drag micropump is used to simulate the electric potential and electric field on a parallel system. The performance of the 7 different mesh partitioning schemes (PS) in terms of computational time, speedup, efficiency and communication cost was evaluated. It was revealed that among the seven different partitioning schemes the PS-3 (two-way or tile partitioning) is found the best scheme for the parallel numerical simulation of the problem. Moreover, the parallel algorithm remains more efficient on to workers while for P>8 the efficiency of the algorithm may drop because of the high communication time
Binary Opposition as an Element of Structural Semiotics for Expression of Spiritual Unity in Selected Kafis’s of Khwaja Ghulam Farid
Get PDFThis research aims to address the dialectic of binary opposition that is to be found in Khwaja Ghulam Farid\u27s poetry which is primarily concerned with unity and union with God. He advocates for the reunion of humanity, the universe, and God. This reintegration will be evaluated not only as a theological postulate but also in its broader metaphysical context. This call for unity arises on both an epistemic and an ontological level. His metaphysic is at odds with the epistemic division of the world into the “The Known – The Known”. Knowing, to him, is the process by which the knower becomes the known. In its ontological dimension, it calls for the unity of being, a doctrine held dear by Sufi saints and mystics worldwide. Consequently, the linchpin of this study is the examination of the use of semiotic binary opposition by Khwaja Ghulam Farid in order to depict the dialectic of the Oneness of the Supreme Being in his Kafis. The theoretical framework is derived from Structural Semantics: An Attempt at a Method (1966) by A. J. Greimas. The deviant collocations of metaphor and imagery used by the poet receive the closest scrutiny because they are the embodiment of the paradox that Khwaja Ghulam Farid depicts as lying at the heart of the binary opposition of the “The Known – The Known” enigma