Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal TechComp Innovations: Journal of Computer Science and Technology Global Science: Journal of Information Technology and Computer Science
Umna iftikhar
Iqra University
Automotive Engineering Computer Science & IT Decision Sciences, Operations Research & Management

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Blockchain-Enabled Multi-Agent Reinforcement Learning for Secure Decentralised Resource Allocation in 5G/6G Network Slicing Agustinus Suradi; Muhamad Aris Sunandar; Umna iftikhar
Global Science: Journal of Information Technology and Computer Science Vol. 1 No. 3 (2025): September: Global Science: Journal of Information Technology and Computer Scien
Publisher : International Forum of Researchers and Lecturers

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70062/globalscience.v1i3.174

Abstract

The integration of blockchain technology with Multi-Agent Reinforcement Learning (MARL) presents a promising solution for optimizing resource allocation and ensuring security in decentralized network environments, particularly in 5G and 6G network slicing. This research proposes a model that combines the security features of blockchain with the adaptive, decentralized decision-making capabilities of MARL. Blockchain ensures the integrity and transparency of resource allocation by providing a secure, tamper-proof ledger for transaction validation, while MARL allows agents to dynamically allocate resources based on real-time network conditions. The simulation results demonstrate significant improvements in resource allocation efficiency, fairness among users, and resilience to cyberattacks. By combining these two technologies, the proposed model overcomes many of the challenges posed by traditional centralized systems and offers an enhanced, secure, and fair solution for resource distribution in future mobile networks. However, scalability remains a challenge, especially in large-scale networks where transaction processing and consensus overhead can create bottlenecks. Additionally, training complexity in MARL models presents computational challenges, particularly in highly dynamic network environments. The model's performance trade-offs, including the balance between high security and system overhead, are also discussed. Future research should focus on optimizing blockchain consensus mechanisms to improve scalability and enhancing MARL model training techniques to reduce computational costs and improve real-time decision-making. This integration holds significant potential for revolutionizing resource allocation in 5G and 6G networks, enabling more efficient, secure, and fair management of network resources in the increasingly complex and decentralized digital ecosystem
Federated Intelligence Architectures for Secure, Data-Driven Innovation Across AI, IoT, and Cloud Ecosystems Ravi Kumar Saidala; Umna Iftikhar; Tofig Hasanov; Vüqar Ahmad Mammadli
TechComp Innovations: Journal of Computer Science and Technology Vol. 2 No. 2 (2025): TechComp Innovations: Journal of Computer Science and Technology
Publisher : Pusat Riset dan Inovasi Nasional Mabadi Iqtishad Al Islami

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70063/techcompinnovations.v2i2.124

Abstract

This study examines the emerging paradigm of federated intelligence architectures as a secure, privacy-preserving, and scalable foundation for data-driven innovation across AI, IoT, and cloud ecosystems. With billions of interconnected devices generating massive heterogeneous data, traditional centralized machine-learning models face critical limitations, including privacy risks, regulatory constraints, latency, and single points of failure. Through a qualitative content-analysis approach, this paper synthesizes contemporary research on federated learning, blockchain integration, zero-trust governance, and edge intelligence to formulate a comprehensive understanding of distributed AI infrastructures. The findings highlight that federated learning enables collaborative model training without exposing raw data, significantly enhancing privacy, security, and compliance. Moreover, combining blockchain with federated learning strengthens auditability, model integrity, and trust, while zero-trust principles provide continuous verification and adaptive security enforcement across devices. Edge-AI integration further reduces latency and bandwidth consumption, enabling real-time analytics in resource-constrained IoT environments. Collectively, these elements contribute to the formation of cognitive ecosystems capable of autonomous, interoperable, and context-aware operations. The study underscores the transformative potential of federated intelligence while identifying critical gaps that inform future research trajectories.
Machine Learning Approaches for Detecting Political Disinformation in Social Media Ecosystems Ahmad Nur Ihsan Purwanto; Nur Hazwani Dzulkefly; Umna Iftikhar
TechComp Innovations: Journal of Computer Science and Technology Vol. 3 No. 1 (2026): TechComp Innovations: Journal of Computer Science and Technology
Publisher : Pusat Riset dan Inovasi Nasional Mabadi Iqtishad Al Islami

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70063/techcompinnovations.v3i1.190

Abstract

Political disinformation has become one of the most critical challenges in contemporary digital democracies due to the rapid expansion of social media ecosystems. This study investigates the effectiveness of machine learning approaches in detecting political disinformation across online platforms such as Twitter, Facebook, and political discussion forums. Using a qualitative research design with a content analysis approach, the study examines linguistic manipulation, emotional narratives, sentiment polarity, and behavioral communication patterns embedded in misleading political content. The findings indicate that deep learning models, particularly Long Short-Term Memory (LSTM) architectures, demonstrate superior performance in identifying contextual and semantic inconsistencies compared to traditional machine learning algorithms. The study also reveals that algorithmic amplification, echo chambers, and coordinated bot activities significantly contribute to the rapid spread of political misinformation. Furthermore, the research highlights the importance of ethical artificial intelligence governance, transparency, and digital literacy in strengthening democratic resilience and protecting information integrity within digital communication environments
Co-Authors Agustinus Suradi Ahmad Nur Ihsan Purwanto Muhamad Aris Sunandar Nur Hazwani Dzulkefly Ravi Kumar Saidala Tofig Hasanov Vüqar Ahmad Mammadli