Al-Kindi Center for Research and Development (KCRD) (E-Journals)
Not a member yet
6248 research outputs found
Sort by
Modeling PM2.5 Concentrations in the Export Processing Area of Dhaka Over a 12-Month Period Using Time Series
No full textAir pollution, particularly PM2.5, poses significant health risks, with Dhaka, Bangladesh, experiencing some of the highest concentrations of fine particulate matter. This study employs 11 time-series models to analyze PM2.5 concentrations in the export processing area of Dhaka. Using a recently published dataset from January 2019 to December 2023, the models were trained to forecast PM2.5 concentrations for a given day of each month over a 12-month period. The results indicated that the Holt-Winters model, followed by a Neural Network and SARIMA, achieved the best performance. An ensemble model incorporating these top three models was developed, demonstrating high forecasting accuracy compared to the other models. This study provides valuable insights for policymakers and businesses, offering an advanced framework for forecasting PM2.5 concentrations to address the ongoing air pollution issue in Dhaka
AI-Driven Next-Gen U.S. Retail: An Empirical Study on Optimizing Supply Chains by leveraging Artificial Intelligence, Business Intelligence, and Machine Learning.
No full textBusiness Intelligence (BI), Artificial Intelligence (AI), and Machine Learnings (ML) have been playing an important role for optimizing Supply Chain Management (SCM) in the U.S. retail industry. The integration of these innovative and cutting-edge technologies into SCM has transformed the efficiency, agility, and profitability of retail businesses across the nation. It’s important to know how these advanced technologies transformed the supply chain process for optimizing inventory level to avoid any bottleneck, overstocking or stockout situation. This research examines how the integration of these modern technologies transformed the supply chain process and enabled retailers in optimizing their supply chain management. In this research work, we have used extensive knowledgebase on Business Intelligence, Artificial Intelligence, Machine Learning, the U.S. retail industry, and the Supply Chain Management, and later we applied this knowledgebase in the U.S retail domain to see how retailers integrate these technologies into their supply chain management process. We also used secondary information available online from reliable sources to make it more realistic. The U.S retail sales revenue was reported at US$7.6 trillion in Y2024 with an expected growth of CAGR of 3.2% over the last five years (Y2019-Y2024). We see a steady growth in the retail sector after the COVID-19 pandemic. Therefore, there is a growing demand for integrating these technologies into the retailers’ SCM so that they can predict consumer demand more accurately and maximize their sales revenue. These technologies serve retailers with greater benefits like forecasting product demand, optimizing inventory level, data-driven decision making, cost reductions by avoiding overstocking, increasing efficiency etc. Though these modern technologies enable retailers with supply chain optimization, there are still some downsides, which include high initial payouts, data silos, resistance to adoption of new technology, consistent and quality dataflow, data integration from various sources etc.
AI-Driven Risk Assessment in National Security Projects: Investigating machine learning models to predict and mitigate risks in defense and critical infrastructure projects
No full textArtificial Intelligence (AI) is revolutionizing national security and risk assessment, providing enhanced predictive capabilities, automated threat detection, and strategic decision-making tools. This paper explores the integration of AI and machine learning (ML) in national defense strategies, cybersecurity frameworks, and critical infrastructure protection. AI-driven risk assessment models utilize big data analytics, deep learning, and predictive algorithms to proactively identify, classify, and mitigate security threats before they materialize. The study examines AI applications in cyber risk management, military defense systems, fraud prevention, and digital forensics, highlighting their effectiveness in safeguarding government agencies, financial institutions, and energy grids. Additionally, the paper discusses ethical considerations, algorithmic biases, and regulatory challenges associated with AI-driven risk assessment. The findings emphasize the increasing reliance on AI in cybersecurity and national security operations, demonstrating how AI-based risk assessment tools contribute to threat intelligence, operational resilience, and automated decision-making in critical security environments. The research concludes with future directions for AI adoption, emerging innovations, and policy recommendations to ensure ethical and effective deployment of AI in national security frameworks
Quantum Computing Systems with Qubit Technology: A Technical Overview
No full textThis article provides a comprehensive technical examination of quantum computing systems based on qubit technology, exploring their revolutionary potential to transform computational capabilities beyond classical limitations. Beginning with an analysis of the fundamental quantum mechanical principles—superposition, entanglement, and quantum interference—the article elucidates how these phenomena enable exponential computational advantages for specific problem domains. Various physical implementations of qubits are evaluated, including superconducting circuits, trapped ions, photonic systems, and theoretical topological approaches, with each platform presenting unique advantages and engineering challenges. It extends to practical applications across cryptography, optimization, and artificial intelligence, where quantum computing promises transformative capabilities. However, significant obstacles remain, including decoherence, high error rates, scalability limitations, and the ongoing development of practical quantum algorithms. Despite these challenges, the quantum computing landscape is evolving toward a hybrid paradigm where quantum and classical resources work in concert, with specialized quantum processors likely to deliver commercial value in specific domains before universal quantum computers become a reality
The Synergistic Integration of Artificial Intelligence and Cloud Orchestration in Process Automation
No full textThe integration of artificial intelligence and cloud orchestration revolutionizes process automation by enabling adaptive, intelligent systems that surpass traditional rule-based methods. This convergence creates intelligent, adaptive systems capable of autonomous operation, continuous self-optimization, and complex decision-making across distributed environments. Machine learning algorithms, natural language processing, and computer vision technologies form the foundation of this evolution, allowing organizations to implement predictive maintenance, automated incident response, and dynamic resource allocation. The synergy between AI and cloud orchestration delivers substantial benefits across multiple sectors, including information technology operations, manufacturing, and customer service. Although technical integration, data quality, skills shortages, and governance pose challenges, structured methodologies combining technology deployment with change management effectively unlock the potential of AI-driven automation. Organizations embracing this paradigm shift achieve significant improvements in operational efficiency, resource utilization, service quality, and adaptability to changing business conditions
Financial Inclusion through Digital Payments: How Technology is Bridging the Gap
No full textFinancial inclusion remains a critical global challenge, with digital payment technologies emerging as transformative solutions for the unbanked population. This article examines how innovative digital payment systems—from mobile banking platforms and digital wallets to cryptocurrency applications—are revolutionizing access to financial services worldwide. Through analysis of successful implementations like India\u27s Unified Payments Interface and mobile banking systems in developing economies, the article explores the technological frameworks enabling these advancements. The article addresses persistent challenges, including infrastructure limitations, regulatory complexities, and digital literacy barriers, while proposing collaborative strategies between governments, financial institutions, and technology providers to develop sustainable and accessible financial ecosystems. By examining both the technical architecture and social impact of digital payment innovations, the article provides a comprehensive roadmap for leveraging technology to create more equitable financial systems that empower traditionally underserved communities
AI-Driven Incident Response for Digital Forensics and Incident Response: A Comprehensive Framework
No full textArtificial intelligence is revolutionizing Digital Forensics and Incident Response (DFIR) by transforming detection, investigation, and remediation capabilities across the security operations lifecycle. Integrating machine learning, behavioral analytics, and automated workflows has created unprecedented opportunities to address cyber threats\u27 growing volume and complexity while improving operational efficiency. Security teams facing an overwhelming deluge of alerts can now leverage AI to rapidly identify genuine threats, prioritize responses, and accelerate investigations. This comprehensive article explores the multifaceted applications of AI across the DFIR domain, from automated threat detection and alert triage to sophisticated forensic analysis and orchestrated response capabilities. The technical considerations for successful implementation include data pipeline development, algorithm selection, and integration with existing security infrastructure. Equally important are the safeguards and ethical considerations for responsible AI adoption, encompassing data integrity, model security, bias mitigation, and human oversight. A structured framework for AI-driven incident response is presented, highlighting the critical balance between automation and human expertise throughout the detection, investigation, remediation, and continuous improvement phases. As the cybersecurity landscape evolves, this transformative approach promises substantial improvements in security posture and operational efficiency when implemented with appropriate governance and technical rigor
Unified Smart Home Control: AI-Driven Hybrid Mobile Applications for Network and Entertainment Management
No full textThis article examines the development of a sophisticated hybrid mobile application that seamlessly integrates artificial intelligence, machine learning, and cross-platform development technologies to revolutionize home network management and entertainment control. The solution bridges the gap between WiFi performance analysis, network optimization, and smart entertainment systems through an innovative architecture leveraging Flutter, React Native, and Kotlin Multiplatform. By strategically incorporating native code for performance-critical operations while maintaining cross-platform compatibility, the application delivers a highly responsive and customizable user experience. The template-driven interface adapts to individual preferences while AI-powered analytics enhance network diagnostics and anticipate user needs. The system ensures consistent performance and synchronization across the user\u27s device ecosystem through edge computing and cloud integration, establishing a new paradigm for smart home management applications that combines technical sophistication with intuitive usability
Leveraging Generative AI for Data Engineering Workflows
No full textGenerative AI represents a powerful new layer of automation for data engineering. When leveraged responsibly, it can improve efficiency, reduce errors, and even enable non-experts to contribute to data workflows, all while allowing expert data engineers to tackle more ambitious challenges. We are witnessing the early stages of this transformation. By staying informed of the latest tools, adopting best practices for AI usage, and continuously refining the human-AI partnership, data engineering teams can ride this wave to build more intelligent, adaptive, and robust data pipelines than ever before. The future data platform may very well be a co-creation of human engineers and AI, each complementing the other’s strengths – and the organizations that embrace this symbiosis will be positioned at the forefront of the data-driven era
Data-Driven Marketing Reinvented: Leveraging AI for Smarter, Ethical, and Personalized Campaigns
No full textThe article explores the transformative impact of artificial intelligence on modern marketing practices, focusing on how AI-driven tools enable smarter, more ethical, and highly personalized campaigns. It examines how organizations leverage predictive analytics, autonomous campaign optimization, and sentiment analysis to enhance customer engagement while addressing privacy concerns through technologies like federated learning and differential privacy. The discussion spans the economic benefits of privacy-preserving AI, the importance of implementation maturity models, and the strategic integration of AI capabilities within enterprise management systems. Throughout, the article emphasizes how these innovations are reshaping traditional marketing strategies by enabling data-driven decision-making, improving operational efficiency, building consumer trust, and delivering measurable performance improvements across various marketing functions and industry sectors