STATISTICS, COMPUTING AND INTERDISCIPLINARY RESEARCH

The Advantages of Using Artificial Intelligence in Urban Planning – A Review of Literature

Muhammad Mashhood — 2023-10-20

Urban planning plays a crucial role in shaping communities for the future, analyzing their strengths and weaknesses, and proposing improvement solutions.
This systematic literature review process used in this study ensured the inclusion of a wide range of sources, providing a comprehensive overview of the advantages of using artificial intelligence in urban planning. After a careful review of the literature, it is found that artificial intelligence is primarily used to enhance efficiency in urban planning processes, contributing to sustainability. The potential for future challenges has accelerated the adoption of artificial intelligence in urban planning by emphasizing the need for resilient, technology-driven cities. It supports more efficient urban design by automating tasks through generative design software, which subdivides plots and applies housing solutions. Artificial intelligence's role expands to multiple areas within the urban planning obligations of a city, including transportation, environment, waste management, education, healthcare, agriculture, risk management, and security. It guides urban planners by improving analytical models for understanding future physical and social community conditions. Artificial intelligence empowers planners to explore new data collection and analysis methods for predicting urban behavior, saving time and resources. It addresses climate change challenges by supporting transportation, waste management, and water use applications. Artificial intelligence technologies continue to advance, urban planning stands to benefit from increased efficiency, data-driven decision-making, and the creation of more sustainable, resilient cities. Urban planners must adapt themselves by acquiring the necessary skills to ensure successful city planning for the future. Overall, Artificial intelligence is contributing heavily to achieving sustainability by integrating past practices, trends, and new AI-based models.

Thermal Performance of Autocatalytic Chemical Reaction for Hybrid Nanomaterial Fluid Flow

Tahir Mahmood — 2023-10-20

The mass and heat transfer in hybrid magnetohydrodynamic (MHD) nanofluids is controlled by an autocatalytic chemical mechanism, which is the subject of the current study's thorough analysis. The focus of the work is on the nanolayers at interfaces, which link nanoparticles with the supporting fluids and enable coupled mass and heat transfer phenomena.To further investigate its effects, a uniform transverse magnetic field is added to the study.By using similarity methods, the governing nonlinear coupled partial differential equation that describes this sophisticated system is converted into a collection of ordinary differential equations (ODEs). Two numerical approaches( Bvp4c) and the Shooting method, are used to solve the ODEs in order to get precise answers and do a comparison study. One interesting finding about the improvement of thermal performance is that a rise in nanolayer thickness (between 1 and 4) considerably adds to the enhancement. Additionally, it is discovered that improvements in the chemical reaction parameter, which ranges from 0.15 to 0.27, cause the Sherwood number to rise.It is noteworthy that the results of this study add to a better understanding of the complex interactions between magnetohydrodynamics, chemical processes, and nanofluid dynamics. The numerical techniques used highlight the significance of accurate mathematical modeling in illuminating the complexity of such systems. In addition to strengthening the theoretical foundation, this study offers useful information that could have an impact on heat transfer and nanofluid technology applications.

Analyzing the Impact of Subsectors and Population Growth on Agricultural Sector in Pakistan

Muhammad Islam — 2023-11-13

The agriculture sector in Pakistan plays its vital role for providing food security and economic stability. Pakistan's agriculture sector comprises various subsectors i.e. crops, livestock, fisheries, and forestry. Agriculture growth is threatened by the growth of these subsectors and the impact of population growth on it. No significant research has been conducted in Pakistan to study the statistical significance of these subsectors and their relationship with population growth. This study analyzes data from 2005 to 2023. Regression analysis is used to identify and to compare the statistical significance of all sub sectors of agriculture growth with population growth rate. Average growth rates found positive for agriculture, major crops, livestock, fisheries, and population, while negative for forestry. Model found good fit with R2 0.936. Major crops, livestock, and fisheries have positive and statistically significant impacts on Pakistan's agricultural growth, with coefficients of 0.316, 0.426, and 0.015, while forestry and population reported negative and statistically insignificant results with coefficients of -0.019 and -0.273. This research laid out good policy decisions aimed at boosting agricultural growth in Pakistan.

Optimal Solution for Segmentation of Malignant Melanoma Dermoscopic Images

Tahir Abbas — 2023-11-13

Melanoma Malignant (MM) is the most common and dangerous form of skin cancer, which is analyzed by using Dermoscopic images in computer sciences. Segmentation technique is used to separate lesion part from healthy part in Dermoscopic images. In this research, comparison of different most popular segmented Dermoscopic image technique like Type-2 Fuzzy, Hybrid Threshold, Wavelet, Gradient Vector Flow (GVF), and Watershed etc. is approached and then better segmentation technique is proposed. In these segmentation techniques different issues like problem of hair, different color lesion, specular reflection and smoothing transaction between lesion and skin were not taken under consideration. Our methodology involves three levels of hierarchy. In the preprocessing step, it deals with problem of hair, bubble noise, smoothing and reflection noise in Dermoscopic images. These noise removals are achieved by using different filters like “Derivative of Gaussian filter and Bootomhat filter”. After region of interest is extracted then combination of threshold, image enhancement and morphological filter are used to produce the efficient algorithm for segmentation. At the end step, segmented crop image is compared with dice coefficient and experimental results of gross error rate are evaluated. For this purpose, PH² Dataset is used that contains 200 Dermoscopic images with the lesion images. The lesion images are extracted by the expert dermatologists.

Modeling the Prevalence of Anemia among the Children in Pakistan: Classical and Bayesian Estimation Approach

Tahira Bano Qasim — 2023-12-31

Anemia remains a major public health concern in all nations, particularly affecting children worldwide. This disorder, which is defined as low hemoglobin or red blood cells in the blood, has multiple causes, the most common one being iron deficiency. The prevalence of anemia among children in Pakistan have been modeled by conducting a thorough statistical analysis emphasizing on inferential statistics and estimation techniques. The study explores the classical and non-classical essential categories of estimating methodologies. The work specifically looks into Bayesian estimation methods under squared error loss function (SELF) and weighted square error loss function (WSELF) for a new generalization of the Exponential Distribution introduced by Nadarajah Haghighi(2017) named as Nadarajah Haghighi Distribution (NHD). The Bayesian estimation of the parameters of NH distribution is run under uniform prior (Non-Informative) and exponential prior (Informative prior). The Lindley approximation method is utilized in this study to solve Bayesian integral. This methodology's practical application focuses on determining Pakistan's under-five-year-old population's anemia prevalence. Both maximum likelihood and Bayesian estimators by means of Monte Carlo simulations and practical application are used to thoroughly compared. Notably, it is empirically reveal that Bayesian estimation technique performs better than the classical estimation technique both in case of simulation and in modeling the prevalence of anemia among Pakistani children.

Detection and Classification of Lung Nodule in CT Scan Images Using CNN

Azhar Hussain — 2023-12-31

The Identification of lung malignant cells at premature stage remain as remarkable research area for researchers. Lung nodules are account as a normal reason for death in people all over the world. Identification of lung nodules at the initial stage can build the pace of endurance of patients. In this article computed tomography (CT) scan images as input to classify lung malignant cells of non-small cell lung cancer and categories according to subtypes of cancer by using the image processing technique with a convolutional neural network (CNN). The segmentation of the CT scan is performed to simplify the representation for meaningful and easier analysis. The feature extraction technique is used which is independent from the size and rotation of the image. These extracted features will use as an input to convolutional neural network (CNN), it pass through different layer of neural network at the end output layer classifies the affected and non-affected areas of the lung nodule with respect to subtypes (adenocarcinoma, squamous cell carcinoma, and large cell carcinoma). The deep learning algorithms VGG 16 show accuracy 85.01% while another deep learning algorithms VGG 19 show best accuracy 98.74% to correctly classify the nodules and subtypes.

Sentiment Analysis of Consumer Reviews: Unveiling Perspectives and Building a Machine Learning Model for Product Evaluation

Hassan Latif — 2023-12-31

The goal of this paper is to classify the unusual and dreadful critiques of the clients over one-of-a-kind products and put up a control analysis version to polarize big amounts of analysis. Our dataset comprises consumer reviews and ratings, which are information we have obtained through user evaluations of Amazon goods. We took the skills from our dataset and developed a large supervised version entirely based on them. These modes not great consist of conventional algorithms mutually with naive bays, linear helping vector machines, and k-nearest fellow resident, but also deep studying metrics which encompass frequent Neural Networks and complication neural networks. We evaluated the correctness of those fashions and got a higher know-how of the inverse attitude earlier to the produce. The initial objective is to describe the situation from the client's perspective and assess the intensity of the emotion. The goal of the second assignment is to build and train a machine learning system that can be used to divide customer evaluations into two categories: excellent and terrible. Regardless of the information that Amazon does now not have an API like Twitter to download evaluation with, it does have links for every assessment on every item for consumption, to theoretically traverse the web page through product IDs. We used Perl script written by way of Andrea Eula to get hold of the evaluation for the stimulation and some poles apart products. The most important script downloads the entire HTML page for the product, and the second searches the record for data about the appraisal, such as the product ID, rating, assessment date, and estimate passage. This study shows that the model had a classification accuracy of 78% and a precision similar to the sympathy and genuine score, but the Kappa do curve was rather low. In the future, more work can be done by improving the key parameters.

Stock Volatility Prediction Using Machine Learning during Covid-19

Saba Zahid — 2023-12-31

Predicting the stock prices’ movement has been considered a tedious task due to the stock market's volatile behavior. This study is an attempt to predict stock prices based on 15 trading factors by applying deep learning algorithm support vector machine (SVM) on daily price data of three stocks of COVID-19, collected from secondary sources and processed through Python software. The finding of this study suggests that the linear kernel gives 53%, the polynomial kernel gives 46% and the radical basis function (RBF) kernel gives 62% validation accuracy, which shows the RBF kernel predictive ability is highest than others during high volatility. The current study contributes to the stock return literature-originated machine learning algorithms during the unprecedented market condition. The finding of this study is helpful for investors and traders who calculate stock return in their portfolio diversified decisions, regulators, and policymakers in the formulation of their regulations & implementation decisions while the market condition is unprecedented. Thus, the support vector machine (SVM) algorithm offers an accurate prediction of stock return to investors who invest during high volatility.

AWS Cloud Computing Solutions: Optimizing Implementation for Businesses

Iqra Naseer — 2023-12-31

This study delves into the optimization strategies of Amazon Web Services (AWS) cloud computing solutions tailored specifically for businesses. It provides an in-depth exploration of the transformative impact that cloud computing has had on modern business operations, emphasizing the pivotal role played by AWS in delivering scalable, flexible, and cost-effective resources. With projections indicating the global public cloud services market's growth to $332.3 billion in 2021, it becomes evident that cloud solutions are increasingly relied upon, with AWS commanding a significant 32% market share. This paper highlights the importance of optimizing AWS solutions, considering its extensive range of services designed to meet diverse business needs. However, transitioning to cloud environments brings challenges related to data security, compliance, integration, and migration complexities, as evidenced by pertinent studies and literature reviews. This research synthesizes insights gleaned from various studies, emphasizing the adaptability and cost-effectiveness of AWS while stressing the critical role of robust security measures in its implementation across industries and geographic regions. Understanding prevalent business requisites and challenges in cloud adoption, including scalability, cost efficiency, reliability, availability, and compliance, is essential for organizations seeking to harness cloud technology effectively. Furthermore, this paper provides an overview of AWS's services encompassing computing, storage, databases, machine learning, and AI, showcasing how these empower businesses to streamline operations, foster innovation, and scale dynamically. It elucidates successful instances where AWS was strategically implemented in Netflix, Airbnb, Jollibee Group, and Capital One, demonstrating its impact on scalability, innovation, and service enhancement. The paper outlines anticipated trends in AWS and cloud computing, focusing on user-friendly tools, advancements in machine learning, infrastructure improvements, increased automation, and deeper integration of AI and advanced analytics. Ultimately, this research emphasizes business's need to optimize AWS solutions, navigate complexities, foster innovation, and achieve operational excellence in an increasingly competitive market.

DDOS Threats and Preventive Measures in IOT-Based Devices

Gulfraz Naqvi — 2023-12-31

This study explores the ever-changing landscape of IoT security in depth, with a specific emphasis given to thwarting the growing menace of Distributed Denial of Service (DDoS hereafter) assaults. A thorough literature assessment explores the sizable adoption of IoT era and associated security challenges, especially when it comes to DDoS assaults and their variations. The paper highlights the human implications of DDoS assaults throughout application, network, and transport layers, emphasizing the want for modern security features. Various studies make contributions precious insights into securing IoT devices, the potential role of block chain technology, and prevention techniques for home environments. The paper proposes a multifaceted defense mechanism, akin to fortifications in a virtual town, leveraging advanced detection techniques and continuous monitoring to limit the impact of DDoS attacks. In end, it advocates for a proactive technique, suggesting future studies instructions together with fortifying utility layers, exploring cloud computing implementations, and enhancing user awareness to ensure the resilience of IoT networks inside the face of evolving cyber threats.

Evaluation of Helping Hand for Relief and Development’s Services for Rehabilitation of Children with Disabilities in Pakistan

Fatima Javed — 2023-12-31

The journey of children with disabilities is marked by obstacles, and they require our firm support and understanding to overcome these obstacles and thrive in a world that often fails to accommodate their needs. This study evaluates the impact of the rehabilitation services provided by Helping Hand for Relief and Development (HHRD) to children with disabilities in Pakistan. The objectives were to identify the range of support services provided by HHRD and to assess parental satisfaction with these services. Data was collected from parents of 145 children at HHRD-CWDP Center in Bahawalpur, Pakistan, using a questionnaire. The findings indicate that HHRD provides a comprehensive range of therapies and material aid to children with disabilities. Parents expressed high levels of satisfaction with the services, highlighting the positive impact of HHRD’s services on their children's well-being. However, there is a clear need for further enhancement of learning assistance services to ensure holistic support for these children. The study also emphasizes that it is crucial to prioritize vocational training and other essential services to empower children with disabilities and promote their inclusion in society

Competent subordinates and Managers’ perception: A Threat or an Asset - An Empirical Evidence from the Higher Education Sector of Pakistan

Sadia Arshad — 2023-12-31

Workforce, by becoming more acquainted and versed in recent times proposes a predicament for managers who have years of experience at their hand. Managers who had been part of an organization for handsome numbers of years, expect to have a steadfast position, but get insecure in presence of competent and proficient subordinates, hence the dilemma has its toll on both workforce and organization. The germination of hostile behavior in response to insecurity, considered as workplace ostracism is a contaminant for the physical and mental well-being of the victim and thus has adverse outcomes in the form of emotional exhaustion.

This paper aimed at studying the impact of managers’ feeling of insecurity on emotional exhaustion of employee, through mediating effect of managers’ perception of competent subordinates and subordinates’ feeling of ostracism. In fact an effort was made to examine the complexities of competent workforce behavior and response of managers towards their competent subordinates. In current experiential research, hypotheses were developed and a structured questionnaire, comprising part A (for HODs and Professors) & part B (for all other faculty members), was used to conduct research survey, adopting convenient sampling technique. A sample of 180 respondents was chosen for statistical analysis of the data. The data were treated using statistical tools including Cronbach’s Alpha, Chi square, Regression analysis, CFA and Process Hayes, with help of software SPSS version 23. Findings of the study support all hypotheses have been accepted and manager’s feeling of insecurity does translate into behavior that is conceived ostracism by the subordinate. Managers’ insecurity is also a potential cause for ostracism and emotional exhaustion. When managers are insecure, they perceive the competent subordinates as challengers, rather than colleagues. The study is considered quite useful for the management of higher education sector / public sector Universities. It is equally beneficial for the researchers and academicians and other public and private educational institutions.

Using Employing K-Means Clustering Algorithm for Sophisticated Visualization of a Bank's Credit Card Data Landscape

Zarsha Nazim — 2023-12-31

Due to the emergence of numerous entrepreneurs with startup ideas and competitors, the new businesses are in significant need of exploring tools and technologies to figure out new buyers and at the same time to keep the older ones as well. Customer segmentation using k mean clustering is an imperative technique to separate the customers into targets segments which can help the businesses to apply marketing strategies accordingly. This can also help in providing exceptional customer services. The research is based on analyzing the dataset of a bank to estimate the customer segmentation of a credit card by proposing a model to help company define its marketing strategies. K-mean algorithm has been used for dividing the group of customers in to segments in the form of clusters by determining the value of k through a silhouette technique. For better visualization Principal Component analysis has been used for dimensionality reduction and to achieve better results by implementing better visualization in Jupiter notebook.

The Effect of Entertainment, Interactivity and Authenticity on Ecommerce Live Streaming among Tourists Purchase Intentions with mediating Role of Social Presence

Moazzam — 2023-12-31

This study examines the multifaceted interaction of entertainment, interaction, and authenticity in the context of e-commerce live streaming among tourist's purchase intentions. It also analyzes the mediating role of social presence. The theoretical underpinnings are based on SOR theory with the intent to understand factors influencing tourists' purchase decisions. A self-administered survey methodology is used to collect data. A sample of 250 respondents was collected by using the nonprobability sampling method. Data is analyzed through SPSS-21. The results are mixed in nature as it is found that entertainment had a strong beneficial impact on social presence and purchase intentions, whereas, a lack of a direct relationship between Interactivity and Authenticity on Social Presence. These findings highlight the value of compelling content in raising users' sense of presence on live streaming platforms for tourism-related e-commerce and emphasize the compelling need for more of these dimensions to be worked out to appeal to tourists in the situation of e-commerce live streaming. These findings have multiple theoretical and managerial implications in e-commerce live streaming.