Pakistan Journal of Scientific Research

Next-Gen Facial Recognition for Criminal Detection: Leveraging Advanced Machine Learning Techniques

2024-07-30T08:48:16+00:00

The process of identifying and spotting a criminal is slow and difficult creating a criminal detection framework that could help policemen to recognize the face of a criminal or a suspect is proposed. The framework is a client-server video-based face recognition surveillance in real-time. The framework applies face detection and tracking the video footage from the camera can be used to identify suspects, criminals, runaways, missing persons, etc. This project focuses on the development of the client side of the proposed framework, face detection, and tracking using Android mobile devices. For the face detection stage, we are using Python for artificial intelligence. The face-tracking stage is based on an intelligence algorithm. The proposed face detection. Thus proposed paper explains a way to help a criminal identification system using ML and deep neural networks.

INTER-PROCESS COMMUNICATION AMONGST MICROSERVICES

2024-06-04T10:06:25+00:00

The purpose of the study is to perform critical analysis on Inter-Process Communication (IPC) in the Microservice Architecture and to evaluate its impact on the basis of various non-business-related functionalities, such as effectiveness of performance, accessibility, adaptability, and complexity. There are various techniques for establishing IPC within Microservices, each with its own set of benefits and drawbacks. Throughout this research, IPC approaches are divided into two categories: synchronous and asynchronous. The Representational State Transfer Application Programming Interface (REST API) and google Remote Procedure Call (gRPC) are utilized in the synchronous kind, whereas Rabbit Message Queue (RabbitMQ) is utilized in the asynchronous type. A workload test was conducted across each model to get quantitative measurements on the Performance Efficiency and Accessibility of each technique, and a relatively similar functionality set was utilized to provide qualitative data on almost every other IPC method's adaptability and complexity. The research outcome shows if there is any standardized IPC solution that can be utilized in all scenarios.

UNVEILING THE PATHOPHYSIOLOGICAL LANDSCAPE OF COVID-19: INSIGHTS FOR NOVEL THERAPEUTIC STRATEGIES

2024-06-06T10:17:13+00:00

The ongoing COVID-19 epidemic has emphasised the critical need for a thorough understanding of the disease’s pathophysiology environment. This article explores the complex relationship between SARS-CoV-2, the virus responsible for COVID-19, and the human body, offering light on the underlying mechanisms that determine illness susceptibility, development, and severity. The genetic, immunological, and physiological aspects that contribute to the different clinical presentations of COVID-19 using a multidisciplinary approach have been discussed. This article aims to provide significant insights that pave the way for potential therapeutic options addressing the core pathophysiological processes by deciphering these complex pathways. As the global community attempts to combat the epi- demic, a fuller knowledge of COVID-19’s molecular complexities holds the prospect of new interventions that can effectively lessen its effects. In addition, a case study featuring Quantitative Poly- merase Chain Reaction (QPCR) amplification curves and Cycle Threshold (CT) values is shown to demonstrate the significance of making an accurate diagnosis. This diagnostic approach lets physicians to distinguish between positive and negative cases, assess viral load, and offer informed treatment recommendations. By combining QPCR results with clinical data, we can acquire a greater understanding of COVID-19’s progression and influence the development of novel therapy methods. This research aims to aid the global effort to eradicate COVID-19 by elucidating its pathophysiological intricacies and employing sophisticated diagnostic techniques such as (QPCR).

ITSM APPLICATIONS WITHIN SELECTED LOGISTICS AND TRANSPORT

2024-05-18T13:36:56+00:00

This article manages data ITSM, with its procedures well-defined by ITIL structure, which is the data of ITSM library collection. ITSM is a customer-first approach to providing IT services, focusing on delivering IT services to customers within the same business, rather than a static system. The consequences of research depend on the proposition of data ITSM model concentrated on the choose logistics and transport administration (tracking and tracing service). Article shows the foundation of the tracking and tracing service and its lifecycle (administration technique, administration configuration, administration change, administration activity and ceaseless help improvement). The article defines connections among capacities and procedures of the tracking and tracing support. The proposition of the model is predictable with standardized procedures. The accuracy of the model is checked by contrasting its consistency and standard ISO/IEC20000.

ENHANCED AND OPTIMIZED INDUSTRIAL PROCESSES MANAGEMENT USING MACHINE LEARNING (ML) AND BLOCKCHAIN

2024-05-18T13:25:40+00:00

The development of the fourth Industrial Revolution 4.0 and inventive smart manufacturing gave rise to a predictive maintenance system for monitoring or tracking industrial equipment. At present, Industry 5.0 has emerged, smudging a significant milestone. Smart factories are on the rise in business productivity, thereby showcasing the limitations of Industry 4.0. The latest industrial revolution is represented by Industry 5.0, amalgamating technologies such as IoT and artificial intelligence. It encompasses an extensive network of interconnected devices, that ensures prompt data transport, especially within a 5G-capable setting. However going forward, the protocols that are based on centralization and conventional access control techniques are unlikely to remain relevant. Hence, for device-to-device interaction and communication, a robust and efficient decentralized access control system is required. Privacy, confidence and reliability stand out as the most significant issues Privacy, security and reliability stand out as primary concerns in the context of industrial process management. The melding of Blockchain (BC), Industrial IOT, MQTT communications protocol, and ML techniques are emphasized in this research study. Through industrial machinery, real-time data from sensors measure characteristics like current, vibration and temperature. Machine learning(ML) models are utilized for examining this data in order to detect any abnormalities or deviations and failures forecast. With the help of the MQTT communication protocol the consistent interaction among the cloud server, gateway devices and sensors. The system underwent testing using an up-running machine data set, employing the ML model linear regression (LR) algorithms for the processing in the proposed framework and analysis of collected/gathered data to forecast machine failures and provide enhanced and secure maintenance level. This method minimizes costs and operational interruptions through optimized maintenance decisions and schedules, illustrating an Industry 5.0 approach for advanced and smart manufacturing.

A SURVEY ON USABILITY SATISFACTION OF SELECTED UNIVERSITY WEBSITES IN PAKISTAN

2024-05-23T06:38:30+00:00

Due to the rapid increase the use of educational websites, the need arises to evaluates these websites from usability point of view for the improvement purpose. This study evaluates some selected university websites in Pakistan from the usability perspectives. Questionnaire based evaluation method is used for the said purpose. Six different features “Navigation”, “Interface Design”, “Performance”, “Information”, “Ease of use” and “Organization” are mentioned in the Questionnaire. A survey is conducted among the students of selected universities of Pakistan. Most of the users are satisfied with the available features of the selected university websites. However, some users are not satisfied with some usability features of websites. Due to this information the study will help to improve the usability features of these websites

CORRELATION ANALYSIS OF THE GLOBAL ACTIVITY LIMITATION INDICATOR WITH DISABILITY MEASURES IN ADULTS UNDER 65 SUFFERING FROM SPINAL AND HEPATIC HEALTH ISSUES

2024-02-05T12:20:44+00:00

Computer image processing technology has become essential for analyzing 2D and 3D spinal images in medical imaging. Deep learning algorithms have played a vital role in improving the accuracy of diagnosing spinal illnesses. This transition has led to a significant increase in the use of deep neural networks for medical imaging and the development of three-dimensional human spine models. These advancements hold great potential for enhancing medical teaching. Correctly segmenting vertebrae remains challenging owing to their similar shapes and appearances. The research utilizes essential factors to evaluate the health of the spine and liver, using measures such as pain, range of motion, and levels of liver enzymes. Additionally, the Global Activity Limitation Indicator thoroughly assesses functional impairment. Datasets such as the LSUN Spinal Cord MRI Segmentation Dataset assist in gathering data, whereas disability measures use a quantitative methodology via the Inventory of Identification of Needs. The results add to a complete framework for comprehending the intricacies of spinal and hepatic health, focusing on providing customized services based on recognized requirements. This paves the way for improved medical diagnosis and patient treatment.

ANALYSIS OF CORDA IMPLEMENTATION IN TAXATION SYSTEM OF PAKISTAN: A PERMISSIONED BLOCKCHAIN FRAMEWORK

2024-02-06T17:47:16+00:00

Pakistan's taxation system encounters several significant challenges, including a low tax-to-GDP ratio, pervasive tax evasion and avoidance, inadequate tax administration and compliance, lack of transparency and accountability, inefficient data management and verification processes, as well as instances of corruption and fraud. These challenges have adverse effects on revenue collection, economic growth, public service delivery, and public trust in the government. Corda, a blockchain platform designed for DeFi, offers features such as privacy, scalability, and interoperability that can be leveraged to enhance transparency and efficiency in tax administration. Additionally, this peer-to-peer and permissioned DLT can provide a secure platform for the storage and transfer of tax-related information, reducing the risk of data breaches and fraud. This research explores the potential of Corda blockchain technology for streamlining the taxation system in Pakistan. The research suggests that Corda blockchain technology can play a vital role in enhancing transparency and efficiency in Pakistan's taxation system, which can ultimately lead to increased tax revenues and a stronger economy. This framework includes integrating tax-related data and processes onto the Corda DLT network, establishing smart contracts for tax transactions, and creating a transparent and auditable tax ecosystem using AMQP/1.0 over TLS. The research also discusses potential challenges and limitations associated with implementing Corda DLT in Pakistan's taxation system.

STUDY OF MORPHOMETRIC CHARACTERS AND FEEDING PREFERENCES, OF SINDH SPARROW (PASSER PYRRHONOTUS) CAPTURED FROM PUNJAB AREAS OF PAKISTAN

2024-05-23T06:29:09+00:00

The primary aim of this study was to assess the morphological characteristics and feeding preferences of the Sindh sparrow. A total of 20 Sindh sparrow samples were collected from the marshes of District Bahawalnagar, Punjab, Pakistan. Measurements including bodyweight, total length, tail length, wingspan, single wing length, primary wing length, tarsal, metatarsal, head size, bill length, and body circumference were recorded. Significant differences were found in morphometric characteristics between male and female sparrows. Specific morphometric measurements were taken for male sparrows, including body weight (6.11 ± 0.11g), body length (13.60 ± 0.60 cm), tail length (5.40 ± 0.40 cm), wingspan (20.0 ± 1.50 cm), single-wing length (8.50 ± 1.00 cm), primary wing (7.00 ± 1.00 cm), tarsal (1.90 ± 0.60 cm), metatarsal (1.30 ± 0.50 cm), head (1.60 ± 0.40 cm), bill (1.40 ± 0.50 cm), and circumference (7.75 ± 0.75 cm). These measurements were compared to the female sparrows' corresponding values: body weight (16.20 ± 0.12 g), body length (14.00 ± 0.50 cm), tail length (6.2 ± 0.30 cm), wingspan (20.75 ± 1.75 cm), single-wing length (9.4 ± 0.40 cm), primary wing length (7.35 ± 1.15 cm), tarsal (1.9 ± 0.60 cm), metatarsal (1.45 ± 0.35 cm), head (1.65 ± 0.45 cm), bill (1.4 ± 0.50 cm), and circumference (8.5 ± 1.00 cm). This study concludes that morphometric characteristics and feeding preferences are similar between both sexes of the Sindh sparrow. Their diet consists of herbal substances and various species from different families.

TOPIC MODELING FOR URDU ARTICLES USING UNSUPERVISED LEARNING APPROACHES

2024-07-04T17:37:16+00:00

Topic modeling is a commonly used text-mining tool for discovering hidden semantic structures within a text corpus. This paper introduces an unsupervised learning-based topic modeling approach for Urdu documents, a language with limited resources. By leveraging unsupervised learning techniques such as Latent Dirichlet Allocation (LDA) and Unsupervised Latent Semantic Indexing (ULSI), specific and accurate topics are extracted from Urdu texts. The experimental results illustrate the dominance of our recommended ULSI model and LDA model, achieving 99% and 98% accuracy, and 44% and 37% coherence values in LDA and ULSI, respectively. The experimental results demonstrate the superiority of the proposed ULSI and LDA models, which achieve high accuracy and coherence values.