Global Journal of Computer Science and Technology (GJCST)
Not a member yet
1830 research outputs found
Sort by
Emotion Detection in Arabic Text using Machine Learning Methods
Full text linkAbstract Emotions are essential to any or all languages and are notoriously challenging to grasp While numerous studies discussing the recognition of emotion in English Arabic emotion recognition research remains in its early stages The textual data with embedded emotions has increased considerably with the Internet and social networking platforms This study aims to tackle the challenging problem of emotion detection in Arabic text Recent studies found that dialect diversity and morpho- logical complexity in the Arabic language with the limited access of annotated training datasets for Arabic emotions pose the foremost significant challenges to Arabic emotion detection Social media is becoming a more popular kind of communication where users can share their thoughts and express emotions like joy sadness anger surprise hate fear so on some range of subjects in ways they d not typically neutralize person Social media also present different challenges which include spelling mistakes new slang and incorrect use of grammar The previous few years have seen a giant increase in interest in text emotion detectio
Digital Forensics: Techniques and Tools for Cybercrime Investigations
Full text linkDigital forensics is a crucial aspect of modern-day investigations particularly those involving cyber crimes With the increasing prevalence of digital devices the amount of electronic evidence available for investigation has also grown significantly Therefore it is essential to have the necessary techniques and tools to extract and analyse digital evidence accurately and efficiently This paper aims to provide an overview of digital forensics and highlight some of the most popular techniques and tools used in the fiel
Performance Study of Downlink Users in Non- Orthogonal Multiple Access (NOMA) for 5G Communications
Full text linkAn outline of NOMA principles is provided in this article Furthermore this page discusses cooperative NOMA and its variations explains power allocation in detail as a technique of resource allocation for NOMA and gives an overview of the research challenges related to NOMA We then use a two-case scenario to suggest a dynamic power allocation DPA plan for the downlink NOMA users albeit it can also be expanded to many use cases The DPA relies on channel state information CSI to guarantee the quality of service QOS for cell center customers user c The Outage probability OP as a critical performance criterion simulation data is also provided and they demonstrate a notable performance improvement when DPA is employed compared to fixed power allocatio
Journey of Artificial Intelligence Frontier: A Comprehensive Overview
Full text linkThe field of Artificial Intelligence AI is a transformational force with limitless promise in the age of fast technological growth This paper sets out on a thorough tour through the frontiers of AI providing a detailed understanding of its complex environment Starting with a historical context followed by the development of AI seeing its beginnings and growth On this journey fundamental ideas are explored looking at things like Machine Learning Neural Networks and Natural Language Processing Taking center stage are ethical issues and societal repercussions emphasising the significance of responsible AI application This voyage comes to a close by looking ahead to AI s potential for human-AI collaboration ground-breaking discoveries and the difficult obstacles that lie ahead This provides with a well-informed view on AI s past present and the unexplored regions it promises to explore by thoroughly navigating this terrai
Scalability and Performance of Microservices Architectures.
Full text linkAnnotation- The inevitability of continuous evolution and seamless integration of dynamic alterations remains a paramount consideration in the realm of software engineering This concern is particularly pronounced within the context of contemporary microservices architectures embedded in heterogeneous and decentralized systems composed of numerous interdependent components A pivotal focal point within such a software design paradigm is to sustain optimal performance quality by ensuring harmonious collaboration among autonomous facets within an intricate framework The challenge of microservices evolution has predominantly revolved around upholding the harmonization of diverse microservices versions during updates all while curbing the computational overhead associated with such validation This study leverages previous research outcomes and tackles the evolution predicament by introducing an innovative formal model coupled with a fresh exposition of microservices RESTful APIs The amalgamation of Formal Concept Analysis and the Liskov Substitution Principle plays a pivotal role in this proposed solution A series of compatibility constraints is delineated and subjected to validation through a controlled experiment employing a representative microservices syste
Research on Path of Blockchain Enabling Accounting Information System
Full text linkThis paper first describes the blockchain technology is the current national support for new technologies has an important position in the national development strategy then combined with the national accounting development plan it analyzes the opportunities and challenges faced by the accounting information system and the theoretical basis and advantages of the integration of blockchain technology and accounting information system Finally the path of blockchain enabling accounting information system is analyze
A Combination of Data Augmentation Techniques for Mango Leaf Diseases Classification
Full text linkMango is one of the most traded fruits in the world Therefore mango production suffers from several pests and diseases which reduce the production and quality of mangoes and their price in the local and international markets Several solutions for automatic diagnosis of these pests and diseases have been proposed by researchers in the last decade These solutions are based on Machine Learning ML and Deep Learning DL algorithms In recent years Convolutional Neural Networks CNNs have achieved impressive results in image classification and are considered as the leading methods for image classificatio
Optimal Control of Time-Delay Systems
No full textIt is shown how the time dealy of industrial processes can be handled in optimal control algorithms Comparision the classial and new modern algorithms is presente
Machine Learning Algorithm to Detect Impersonation in an Essay-Based E-Exam
Full text linkEssay-based E-exams require answers to be written out at some length in an E- learning platform The questions require a response with multiple paragraphs and should be logical and well-structured These type of examinations are increasingly becoming popular in academic institutions of higher learning based on the experience of COVID-19 pandemic Since the exam is mainly done virtually with reduced supervision the risk of impersonation and stolen content from other sources increases Due to this there is need to design cost effective and accurate techniques that are able to detect cheating in an essay based E- exa
The Poetry of Prompts: The Collaborative Role of Generative Artificial Intelligence in the Creation of Poetry and the Anxiety of Machine Influence
Full text link2022 has been heralded as the year of generative artificial intelligence AI Generative AI like ChatGPT and Stable Diffusion along with a host of others launched late in the year and immediately disrupted the status quo of the literary and artworlds leading to outcries to ban AI Art and spawning an entirely new market of NFTs Fears over the death of the artist and the death of college composition however are unfounded when considering the historical adoption of emerging technologies by creatives and the reconsideration of authorship that began with poststructuralism and the Foucauldian Death of the Author in 196