Raazia Saher

Supply chain service levels are highly vulnerable to disruptions originating from both suppliers and customers, including rare events such as natural disasters and transportation delays. Estimating their impact is complex and requires a proactive approach; however, many firms remain reactive due to limited analytical tools. Simulation-based methods offer a powerful solution by enabling scenario testing, prediction, and system behavior analysis under uncertainty. When integrated with Big Data Analytics (BDA)—characterized by volume, velocity, and variety—these capabilities are enhanced through data-driven insights. This chapter critically reviews how Big Data Analytics (BDA) can support Sustainable Supply Chain Management (SSCM) across procurement, logistics, reverse logistics, and circular supply chains. It further examines BDA-enabled simulation for proactive disruption management and sustainability-oriented decision-making, highlighting key challenges, limitations, and future research directions.

This chapter examines how artificial intelligence (AI) might improve data centers' environmental sustainability, focusing on three areas: waste heat recovery, water use, and cooling efficiency. It begins by outlining the rapid growth of data centers and their escalating energy and water demands, followed by a comprehensive review of traditional and innovative cooling technologies. The chapter highlights how AI and machine learning methods, including neural networks, reinforcement learning, and predictive analytics, may revolutionize cooling operations and reduce water consumption. It also highlights the economic and environmental potential of AI-driven waste heat recovery solutions, such as intelligent distribution systems and adaptive thermal mapping. This chapter provides a roadmap for greener digital infrastructure by combining international standards, business pledges, and new developments. Policymakers, engineers, and academics can use the insights to help them leverage AI for data center operations that are both sustainable and energy efficient.

The global coffee industry faces numerous environmental conservation and sustainability challenges, such as land management, irrigation, deforestation, biodiversity preservation, and waste management. This chapter explores the role of AI in sustainable land, precision farming, smart irrigation systems, harvesting, and post-harvest processing of coffee beans. The ability of AI algorithms to process large amounts of textual and multimedia data to identify patterns can contribute to addressing the sustainability challenges in coffee farming. This chapter discusses the application of various AI algorithms and techniques—including computer vision, data analytics, supervised learning, artificial neural networks, and deep learning—in advancing sustainable coffee farming. The chapter also explores the role of AI in repurposing coffee waste into biofuels. By aligning with the global sustainable development goals, AI-driven coffee farming presents exciting opportunities for the environmentally responsible future of the coffee industry.

This chapter explores the global issue of food loss and waste, emphasizing its economic and environmental impacts and implications on Sustainable Development Goals, with a specific focus on the coffee industry as a major waste-generating sector. Building on the context, the chapter examines global coffee consumption and production trends, highlighting the substantial volume of spent coffee grounds (SCGs) wasted and their environmental burden. The discussion then introduces Artificial Intelligence (AI) and emerging tools for achieving sustainable waste management in this domain. The chapter investigates AI applications across the coffee value chain, from optimizing production and supply to enabling the recycling and valorization of byproducts. It highlights ongoing research and real-world implementations, concluding with a vision for a circular, sustainable future—emphasizing stakeholder collaboration, AI-driven solutions, and actionable policies and industry recommendations.

The analysis of stress in response to videos using electroencephalography (EEG) has emerged as a significant field of research. In this study, we propose a methodology for classifying stress responses to videos using the Database for Emotion Analysis using Physiological Signals (DEAP). EEG signals are preprocessed with resampling and a median filter. We extracted Power Spectral Density (PSD) features from the alpha, beta, delta, and theta bands of the preprocessed EEG. Instances were labeled based on the valence and arousal values provided in the DEAP dataset in response to the presented videos. Four machine learning algorithms, namely Naïve Bayes (NB), Multilayer Perceptron (MLP), Logistic Regression (LR), and Sequential Minimal Optimization (SMO) classifiers, were employed to differentiate between stressed and relaxed states using a 10-fold cross-validation technique. The SMO classifier achieved the highest accuracy of 95.65%. Additionally, statistically significant variations in the alpha band using t-tests suggest that the DEAP dataset video clips can effectively induce stress and relaxation conditions in participants.

Effective waste management is of paramount importance as it contributes significantly to environmental preservation, mitigates health hazards, and aids in the preservation of precious resources. Conversely, mishandling waste not only presents severe environmental risks but can also disrupt the balance of ecosystems and pose threats to biodiversity. The emission of carbon dioxide, methane, and greenhouse gases (GHGs) can constitute a significant factor in the progression of global warming and climate change, consequently giving rise to atmospheric pollution. This pollution, in turn, has the potential to exacerbate respiratory ailments, elevate the likelihood of cardiovascular disorders, and negatively impact overall public health. Hence, efficient management of trash is extremely crucial in any society. It requires integrating technology and innovative solutions, which can help eradicate this global issue. The internet of things (IoT) is a revolutionary communication paradigm with significant contributions to remote monitoring and control. IoT-based trash management aids remote garbage level monitoring but entails drawbacks like high installation and maintenance costs, increased electronic waste production (53 million metric tons in 2013), and substantial energy consumption for always-vigilant IoT devices. Our research endeavors to formulate a comprehensive model for an efficient and cost-effective waste collection system. It emphasizes the need for global commitment by policymakers, stakeholders, and civil society, working together to achieve a common goal. In order to mitigate the depletion of manpower, fuel resources, and time, our proposed method leverages quick response (QR) codes to enable the remote monitoring of waste bin capacity across diverse city locations. We propose to minimize the deployment of IoT devices, utilizing them only when absolutely necessary and thereby allocating their use exclusively to central garbage collection facilities. Our solution places the onus of monitoring garbage levels at the community level firmly on the shoulders of civilians, demonstrating that a critical aspect of any technology is its ability to interact and collaborate with humans. Within our framework, citizens will employ our proposed mobile application to scan QR codes affixed to waste bins, select the relevant garbage level, and transmit this data to the waste collection teams’ database. Subsequently, these teams will plan for optimized garbage collection procedures, considering parameters such as garbage volume and the most efficient collection routes aimed at minimizing both time and fuel consumption.