GSG. Silambarasan

G. Silambarasan

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


G. Silambarasan has a total of 8 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Digital Twins for Infrastructure Governance, Scenario Analysis, and Resilience Planning

    by Gautam Shivaraj, G. Silambarasan

    In an era of climate disruption and complex systemic risk, digital twins, the dynamic virtual replicas of public infrastructure systems, are quickly becoming a governance game-changer. The chapter explores the use and conceptualization of digital twin technologies for the governance of critical infrastructures such as energy grids, transport networks, water systems and built environments. It highlights three interconnected areas: Infrastructure governance, with digital twins offering evidence-based regulatory oversight and stakeholder coordination; Scenario analysis, with digital twins helping to simulate and stress-test policies for the future; and Resilience planning, with digital twins delivering real-time situational awareness and adaptive management. The chapter reflects on the conceptual foundations of systems theory, policy informatics and urban analytics to examine the key architectural elements of infrastructure digital twins, institutional considerations for their use, and the issues of data integration, interoperability and algorithmic accountability.

  • AI-Driven Research Data Management

    by G. Silambarasan, Gautam Shivaraj

    The rapid growth of scientific data from sensors, simulations, genomic research, high-performance computing, and collaborative research platforms has transformed the requirements of modern research data management (RDM). Traditional manual methods for organising, curating, and retrieving data are no longer sufficient to manage the scale and complexity of today's scientific ecosystems. This chapter explores how artificial intelligence technologies such as machine learning, deep learning, natural language processing, knowledge graphs, large language models, federated learning, and explainable AI are reshaping RDM into intelligent and adaptive infrastructures. It examines AI-enabled capabilities including automated data acquisition, semantic enrichment, predictive analytics, workflow automation, and responsible governance. The chapter also highlights applications across genomics, climate science, medicine, physics, social sciences, and materials science while discussing key technical, ethical, and organisational challenges.

  • Enabling Platforms and Trust Infrastructures

    by Gautam Shivaraj, G. Silambarasan

    The rapid convergence of digital, physical, and biological systems that characterizes Industry 4.0 has fundamentally altered the conditions under which human beings work, collaborate, and make decisions. At the heart of this transformation lies a question that is simultaneously technical and deeply human: on what basis can people reasonably trust the platforms and infrastructures that increasingly mediate their professional and personal lives? This chapter examines the architecture of enabling platforms and the trust infrastructures that must accompany them if Industry 4.0 technologies are to fulfill their transformative potential in human-centered ways. Drawing on socio-technical systems theory, platform economics, institutional design, and emerging scholarship on algorithmic governance, the chapter traces how trust is produced, maintained, and sometimes eroded within complex digital ecosystems. It argues that trust is not a byproduct of good engineering but a designed artifact requiring deliberate institutional, social, and technical effort.

  • Student Experiences and Engagement With Prompting

    by G. Silambarasan, Gautam Shivaraj

    The chapter Student Experiences and Engagement with Prompting explores the dynamic relationship between students and various forms of prompting techniques used in educational settings. It examines how prompts, ranging from teacher-directed cues to digital tools, influence student engagement, cognitive processes, and overall learning outcomes. Drawing on qualitative data from student surveys and interviews, the study highlights the diversity of student experiences across different learning environments, such as face-to-face classrooms and online platforms. It also investigates how different prompting strategies, including verbal cues, visual aids, and technological interventions, impact students' ability to retain information, demonstrate critical thinking, and engage with the content actively. The findings reveal that the effectiveness of prompting is highly contextual

  • Sustainable Development Goals (SDGs) and Coastal Areas

    by Gautam Shivaraj, G. Silambarasan

    Coastal areas are among the world's most productive and ecologically significant regions, supporting biodiversity, economic development, food security, tourism, fisheries, and the livelihoods of billions of people. However, these regions are increasingly threatened by climate change, sea-level rise, coastal erosion, marine pollution, habitat degradation, overexploitation of natural resources, and rapid urbanization. The United Nations Sustainable Development Goals (SDGs) provide a comprehensive framework for addressing these interconnected environmental, social, and economic challenges while promoting inclusive and resilient coastal development. This chapter examines the relationship between the SDGs and sustainable coastal management, with particular emphasis on goals related to climate action, life below water, clean water and sanitation, sustainable cities and communities, responsible consumption and production, and partnerships for sustainable development.

  • The Impact of the Russian-Ukrainian War on Central Asia

    by Gautam Shivaraj, G. Silambarasan, Sanganagouda Shivanagi

    The full-scale Russian invasion of Ukraine, launched in February 2022, triggered a cascade of geopolitical, economic, and security consequences that reverberated well beyond the borders of the two belligerents. Central Asia — comprising Kazakhstan, Uzbekistan, Kyrgyzstan, Tajikistan, and Turkmenistan — found itself at a critical intersection of competing pressures, loyalties, and opportunities. This chapter provides a comprehensive analysis of how the war has reshaped the geopolitical landscape of Central Asia across five dimensions: diplomatic positioning, economic and trade impacts, energy and food security, the evolving roles of external powers (Russia, China, the West, and Turkey), and long-term structural shifts in the region's strategic orientation. Drawing on comparative data across the five republics

  • Digital Games, Child Identity, and Parenting in the Age of Online Gaming

    by Gautam Shivaraj, Silambarasan G.

    The rapid proliferation of online gaming environments has fundamentally reshaped the developmental landscape for children and adolescents in the twenty-first century. This chapter explores the multidimensional relationship between digital gaming and child identity formation, offering parents, caregivers, and educators a comprehensive, evidence-informed guide for navigating the complex terrain of online play. Drawing on developmental psychology, media studies, and digital culture research, the chapter examines how online games serve simultaneously as sites of identity experimentation, social learning, cognitive development, and potential psychological risk. Key themes include the construction of virtual identities and avatar-self relationships, the socialization dynamics of multiplayer environments, the formation of gaming-based peer cultures, the gendered and culturally situated nature of game participation, and the risks associated with excessive engagement, cyberbullying, and predatory behavior in online spaces.

  • Reinforcement Learning for Adaptive Cyber Attack and Defense Strategies

    by A. Shivaraj, Gautam Shivaraj, G. Silambarasan

    As the nature of cyber warfare evolves, traditional methods of defense and attack are increasingly being outpaced by sophisticated, adaptive threats. In this context, Reinforcement Learning (RL) presents a transformative solution by enabling autonomous systems to learn, adapt, and optimize their strategies over time. This chapter explores the application of RL to both cyber attack and cyber defense, focusing on how RL-driven agents can enhance the effectiveness, efficiency, and resilience of cybersecurity systems. By enabling continuous learning and real-time adaptation to new threats,RL agents can autonomously optimize defense strategies, and evolve offensive tactics. The chapter also examines key challenges in integrating RL into cyber warfare, such as computational complexity, adversarial vulnerabilities, and ethical concerns. Furthermore, the future of RL in cyber warfare is discussed, with a focus on scaling RL systems, improving security, the need for human oversight.

  • Understanding the Impact of Labor Market and Development on Employee Performance

    by Gautam Shivaraj, G. Silambarasan, M. Gurusamy

    Manpower development has become a strategic component in enhancing organizational performance and achieving long-term objectives. This paper explores how manpower development, through structured training programs, career planning, and skill acquisition, affects employee performance in modern organizations. By reviewing empirical studies and theoretical frameworks, the research identifies a strong correlation between investment in human capital and improvements in employee productivity, job satisfaction, and organizational loyalty. The paper also highlights challenges in manpower development such as resource limitations, ineffective training modules, and misaligned HR policies. Recommendations include the integration of continuous learning, employee involvement in development planning, and periodic performance assessments to maximize returns on human capital investment.

  • AI and Machine Learning Models for Predicting Driver Fatigue or Drowsiness From Vibration Patterns

    by Gautam Shivaraj, G. Silambarasan

    Driver fatigue and drowsiness represent a leading cause of road traffic accidents worldwide, accounting for a substantial fraction of fatal collisions each year. The early and reliable prediction of fatigue onset is consequently one of the most critical challenges confronting intelligent transportation research. This chapter investigates the role of artificial intelligence and machine learning in detecting driver fatigue through the analysis of vibration signals — encompassing seat, steering wheel, floor, and body-worn inertial sensor data. Beginning with the biomechanical underpinnings of how fatigue progressively alters a driver's postural stability and muscular coordination, the chapter proceeds to examine signal acquisition techniques, feature engineering approaches, and the spectrum of machine learning architectures currently deployed in this domain. Supervised methods such as support vector machines and random forests, ensemble strategies, deep learning architectures including convolutional and recurrent neural networks.