Browse Items (16481 total)
Sort by:
-
Decoding sustainability: A machine learning-based analysis of socioeconomic drivers in global sustainable developmental goals progress
Sustainability, a concept that gained prominence with the Brundtland Report in 1987, is defined as a development approach that addresses present needs without jeopardizing the ability of future generations to meet theirs. Over the years, sustainability has evolved beyond its initial environmental focus, now encompassing economic, social, and political dimensionsmaking it an essential pillar of modern development initiatives. To drive global sustainable development forward, the United Nations adopted the 2030 Agenda, featuring 17 Sustainable Development Goals (SDGs). These goals aim to resolve some of the most pressing challenges faced by humanity, including poverty eradication, climate action, gender equality, and economic growth. The SDG Index, which evaluates a countrys progress toward these goals, helps measure and compare performance across nations. The Intersection of Socioeconomic Factors and SDG Progress is significant for the growth of a country. A countrys Gross Domestic Product (GDP) has often been seen as a key economic indicator, reflecting its ability to invest in sustainable initiatives. However, sustainability is not solely dependent on financial resourcessocial factors play a critical role. To assess the connection between well-being and sustainability, researchers often analyze the Happiness Index alongside SDG scores. Countries demonstrating both high happiness levels and strong sustainability scores provide valuable insights into the relationship between social welfare and global progress. Furthermore, machine learning (ML) techniques have emerged as powerful tools in sustainability research. By analyzing vast datasets, AI-driven approaches can predict trends, optimize resources, and enhance policy implementationaccelerating progress toward a sustainable future. The Evolving Landscape of Sustainability and Its Global Impact is realized using statistical and ML approaches in this study. Rethinking Strategies for a Sustainable Tomorrow is very important in 2025 as we are approaching 2030 very fast. Understanding the underlying factors influencing SDG scores allows nations to refine their approaches to sustainability. By tailoring action plans based on socioeconomic conditions, governments can improve their policies, ensuring both environmental stewardship and enhanced quality of life for their citizens. As global challenges evolve, interdisciplinary approachesspanning technology, economics, and social scienceswill continue to shape sustainability efforts, fostering a future where development aligns seamlessly with environmental and societal well-being. 2026 selection and editorial matter, Siddhartha Bhattacharyya, Jan Plato, Soumyadip Dhar, Naba Kumar Mondal, Ivan Zelinka, Jyoti Sekhar Banerjee and Abhijit Das; individual chapters, the contributors. -
Healthcare and wearables in smart cyber-physical systems
[No abstract available] -
Investigating system vulnerabilities in digital environments
[No abstract available] -
Smart grid and energy management in smart cyber-physical systems (SCPS)
[No abstract available] -
Exploring advancements in space object detection through computer vision
[No abstract available] -
Uses of Generative AI for SAP HANA Data Management
This chapter examines the transformative role of generative artificial intelligence (AI) in enterprise analytics, with emphasis on the Generative Pre-trained Transformer (GPT) family and related attention-based architectures. In contrast to conventional machine-learning pipelines whose performance is constrained by task-specific supervision and rigid feature engineering generative models exploit large-scale self-supervised pre-training, enabling emergent reasoning and effective transfer across heterogeneous downstream tasks. We demonstrate these advantages through a pragmatic integration of GPT-class large language models (LLMs) within an SAP HANA environment. By fine-tuning the LLM on domain-specific SQL corpora and curated schema metadata, the system learns to synthesise syntactically correct, execution-ready SQL statements that align with the underlying business logic. This design obviates costly data-centralisation efforts: users can pose natural-language questions and obtain HANA-compliant queries over distributed enterprise data without deep knowledge of relational algebra or SAP-specific functions. Moreover, explicit injection of domain ontologies during fine-tuning improves semantic grounding and materially increases query-generation accuracy. A sales-reporting case study substantiates these claims, showing that the approach streamlines complex analytic workflows, reduces time-to-insight, and enhances report reliability. Collectively, the findings position generative AI as a catalytic technology for modernising enterprise data management and accelerating data-driven innovation. 2026 Ram Kumar Chenthur Pandian, Shanmuga Raju Sekar, Subrata Chowdhury, Muhammad Rukunuddin Ghalib, and Kassian T.T. Amesho. -
Artificial Intelligence and Machine Learning in Detecting Autism: Transforming Diagnosis and Care
Autism Spectrum Disorder (ASD) is a condition that involves many aspects and falls into the category of neurodevelopmental disorders. This is shown by problems in socializing, talking and repetitive actions. Despite the fact that early intervention is beneficial such initiatives may be postponed due to the lengthy process of assessing the disease by qualified doctors. More people are interested in AI and ML technologies which may help detect ASD earlier and more accurately. The goal of this paper is to describe the machine learning techniques used to spot ASD in individuals of any age, using information from behaviour, genes and brain images. It applies supervised learning, unsupervised learning and deep learning, using Support Vector Machines, Random Forests and Convolutional Neural Networks to find autistic patterns in complex data. We also discuss the use of facial recognition, speech recognition, motion analysis and wearable devices in helping with early detection and creating personal intervention programs. At the same time, these technologies are concerned with data accuracy, biased algorithms, lack of openness and ethical and social issues such as data safety and consent. It explains the benefits and the issues that come with using AI and ML in healthcare to find cases of autism spectrum disorder (ASD). By working together, policymakers, researchers and clinicians can help these technologies advance the diagnosis and treatment of ASD which will improve the lives of those with ASD and their families. 2026 Ram Kumar Chenthur Pandian, Shanmuga Raju Sekar, Subrata Chowdhury, Muhammad Rukunuddin Ghalib, and Kassian T.T. Amesho. -
Mapping Barriers to Net Zero in Quick Commerce A Fuzzy DEMATEL Approach
The fast-paced growth of q-commerce platforms has radically changed the shopping arena to deliver consumers unparalleled convenience. However, this speedy delivery poses significant challenges to achieving net-zero emissions, essentially due to inefficiencies in logistics and high energy usage. This research applies the Fuzzy DEMATEL approach to explain and analyze the barriers to sustainability in q-commerce by uncovering interconnections between factors. The findings showed that the primary logistical inefficiency is preceded by high energy usage and sustainable packaging as significant drivers. Other evaluated factors, though with lower scores, are regulatory challenges and consumer awareness. The mitigation of logistical inefficiencies can serve to greatly improve routing and resource management in such a way as to bring significant decreases in carbon footprint. Also, by augmenting consumer awareness for more sustainable practices, one creates an increasing demand for alternative choices, hence giving way to positive feedback that may help drive companies toward adopting even more sustainable approaches. From a policy perspective, the results indicate that regulatory frameworks should support investments in green infrastructure and technologies by engaging the different stakeholders, including businesses, consumers, and governmental entities, in a common strategy toward sustainability. While the present research supplies important insights into the challenges with which q-commerce is confronted while achieving net-zero emissions, it recognizes some constraints, such as potential biases due to expert judgments and the dynamic character of the business. The following studies would include more stakeholders and variables influencing sustainability and broaden the scope. Through addressing these barriers as a collective, the q-commerce industry can move toward achieving its net-zero dreams while advancing broader environmental goals for a greener world. 2026 selection and editorial matter, Siddhartha Roy, Soumya Sen, and Agostino Cortesi; individual chapters, the contributors. -
Data Analytics and Automation for a Broadband Franchise
Its challenging to envision a world without the internet. From acquiring knowledge to ordering food, our lives have become incredibly convenient thanks to it. As technology advances, internet access is becoming easier and more affordable, with India being renowned for having the lowest internet costs. Internet service providers (ISPs) aim to offer better speeds, fewer disruptions, and professional service. They charge fees for allowing customers to shop online, browse the web, stay connected with loved ones, and conduct business. Due to a lack of data comprehension, the company struggles to leverage reports in daily operations. Consequently, BSNL is finding it hard to outshine competitors and become profitable. Key highlights from the project include understanding customer mentality and addressing issues faced by franchise owners. This research aimed to enhance organizational operations by reducing manual interventions and automating customer communication. User sentiments toward the brand and its competitors were analyzed, and exploratory data analysis was conducted to assess the organizations position. Data visualization with Tableau and Python programming were utilized to derive insights from the data. 2025 selection and editorial matter, Shruti Sharma, Ashutosh Sharma, and Trinh Van Chien. -
Revolutionizing Healthcare: The Impact of Generative AI and Large Language Models
The chapter explores the transformative impact of generative AI and large language models (LLMs) in healthcare, emphasizing their potential to revolutionize patient care, clinical operations, and medical research. Generative AI, a subset of artificial intelligence, offers groundbreaking capabilities such as personalized medicine, virtual health assistants, and enhanced diagnostic accuracy. LLMs like Med-PaLM and BioBERT are fine-tuned to perform specific healthcare tasks, such as clinical note summarization and diagnostic support. These models also assist in drug discovery, clinical trials, and pandemic preparedness by analyzing complex medical data and predicting patient outcomes with high accuracy. The chapter also addresses the ethical and regulatory considerations associated with AI in healthcare, including data privacy, bias, and accountability. While the integration of AI technologies promises significant advancements, it also requires stringent regulatory oversight to ensure safety, efficacy, and fairness. The potential of generative AI to generate synthetic medical data offers a secure way to advance research without compromising patient privacy. Additionally, AI can optimize healthcare processes, enhance patient engagement, and accelerate medical research, contributing to a more efficient and personalized healthcare system. The chapter concludes by highlighting the need for continuous collaboration between AI developers, healthcare professionals, and regulators to maximize the benefits of these technologies while addressing the associated risks. 2025 selection and editorial matter, Sakshi Gupta, Umesh Gupta, Moolchand Sharma, Kamal Malik; individual chapters, the contributors. -
Synthesis and Future Directions on Circular Economy
Stakeholders participation is vital to the success of circular business models, and the investor is perceived as the principal stakeholder. So, it is essential to understand the factors shaping investment behavior in the circular economy. In this context, this study is an initial attempt to explore the factors playing a role in shaping investor behavior. The study explores the role of perception on sustainable investments, awareness of ESG practices, and environmental considerations in shaping investment behavior. The study finds that perception of sustainable investment and awareness of ESG practices have significant effects on sustainable investment behavior. It is seen that digital technologies, including financial technologies, have a huge role in bringing up circular economy efforts. In this context, by building fuzzy logic, artificial intelligence can be an effective tool in determining investor behavior in the hands of corporates. At the same time, from the investors side, building digital financial literacy is required to deal with sustainable investments by upholding independence in decision-making. 2026 selection and editorial matter, Biswadip Basu Mallik, Gunjan Mukherjee, Rahul Kar, and Youqing Fan; individual chapters, the contributors.