Abstract

Recent efforts to embed ethical reasoning into AI and machine learning systems have focused on training deep learning models to generate moral judgments in response to situational inputs. Parallel developments in the criminal justice system illustrate the application of such technologies, where risk assessment tools are employed to predict defendants’ risk scores. These scores are then used by legal institutions to make decisions related to parole, policing, and sentencing. Together, these approaches reflect a growing trend towards integrating AI into moral decision-making and as a potential replacement for human decision-making. In our work, we critically evaluate moral decision-making in AI systems through a philosophical lens, with particular emphasis on virtue ethics. First, we evaluate Delphi (Jiang et. al., 2021 [1]), which attempts to use the Rawlsian decision procedure as a bottom-up approach to capture abstract moral principles from crowdsourcing moral opinions across a diverse demographic. We critically evaluate this model on the basis of the effectiveness of (a) the current bottom-up approach of incorporating Rawlsian decision procedure, and (b) the proposed hybridization of the former with a top-down approach leading to reflective equilibrium. We argue against (a) on the grounds that the system fails to satisfy the criteria for being a competent moral judge as outlined by Rawls (Rawls, 1971 [2]); further, we argue against (b) on the grounds that reflective equilibrium requires phronesis or practical wisdom, which cannot be embedded into AI systems. We critically evaluate (b) in the light of Irikefe’s neo-Aristotelian, agentbased account of reflective equilibrium (Irikefe, 2019 [3]) to argue against the possibility of AI-ML systems to incorporate phronesis in order to attain reflective equilibrium. We then evaluate COMPAS, a risk assessment software that predicts the risk of recidivism of defendants based on responses to a questionnaire. We investigate COMPAS from a virtue ethics perspective by (1) discussing how punishment in the criminal justice system can be implemented as a practice, as defined within the framework of MacIntyre’s virtue ethics (MacIntyre, 2007 [4]) and (2) analyzing why such a practice cannot be implemented by tools like COMPAS.

Abstract

We present an efficient framework for identity-preserving face swapping into scenic portrait sketches. First, we analyze latent identity representations via a StyleGAN-based face cartoonization pipeline. Our analysis reveals domain-dependent shifts in StyleGAN’s identity encodings when mapping photos to sketches, underscoring the need for cross-domain consistency. Second, we introduce Portrait Sketching StyleGAN (PS-StyleGAN), a novel GAN architecture with attentive affine-transform blocks. These blocks learn to modulate a pretrained StyleGAN’s style codes by joint content-and-style attention, thereby learning style-specific identity transformations. PS-StyleGAN requires only a few photo-sketch pairs (and short training) to learn each style, making it broadly adaptable. Thus, PS-StyleGAN produces editable, expressive portrait sketches that faithfully preserve the input identity. Third, we extend diffusion-based generative modeling by adapting InstantID for sketch synthesis. Our diffusion module integrates strong semantic identity embeddings and landmark guidance (inspired by InstantID’s IdentityNet) to steer high-fidelity portrait generation. This yields personalized sketches with markedly improved identity fidelity while requiring only zero-shot (tuning-free) personalization. Finally, motivated by recent diffusion-based face-swapping advances, we build a real-time end-to-end pipeline. By encoding facial identity and pose as conditioning inputs and optimizing the diffusion process for speed, our system can seamlessly embed user faces into tourist-style sketches on the fly. Extensive evaluations on standard benchmarks confirm that our methods significantly enhance identity preservation and visual quality compared to prior approaches, advancing the state of the art in generative portrait stylization and face swapping.

Abstract

River water quality is fundamentally influenced by hydrological factors such as discharge and water temperature, both of which are increasingly affected by climate variability and human-induced pressures. These variables, when considered independently, can provide a limited view of water quality risks. However, compound events, where low discharge coincides with high water temperatures, can pose significant ecological threats, particularly to sensitive aquatic species and overall river health. Existing studies often rely on univariate or deterministic models, which fail to capture the joint behaviour of these interconnected variables. There is also a noticeable gap in translating advanced statistical models into practical tools for river water quality risk management, especially in computing compound event probabilities and supporting basin-specific decision-making. This study addresses these gaps by developing a copula-based joint modelling framework to quantify compound low-flow and high-temperature risks across six diverse Indian rivers: Yamuna, Bhadra, Kaveri, Mahi, Sabarmati, and Vardha. The study begins by fitting appropriate univariate probability distributions to river discharge and water temperatures using diagnostic tools such as skewness, kurtosis, Q-Q plots, and information criteria to ensure statistically sound marginal modelling. Dependence structures between the variables are assessed using rank correlation metrics to identify rivers where joint modelling is both appropriate and necessary. An extensive set of 18 copula families, including symmetric, asymmetric, and tail-dependent models, is evaluated to capture complex interdependencies across river basins. The selected copulas are then applied to estimate joint probabilities, conditional probabilities, and return periods of compound events of discharge and water temperatures of various river gauging stations of India. The findings reveal clear differences in compound event frequencies and intensities across the studied rivers, underscoring the need for localized and river-specific water quality management strategies. The key objectives of this study include identifying the best-fit univariate distributions, selecting the most appropriate copula families for joint modelling, and constructing a flexible, transferable statistical framework that can support future applications, including multivariable risk assessments, climate change impact studies, and adaptive water resource management. By addressing the underutilization of joint probabilistic frameworks for Indian river systems and demonstrating their practical application, this study contributes to a more holistic understanding of compound water quality risks and provides valuable guidance for sustainable river management and policy development

Abstract

Coal mining has long served as a cornerstone of India’s industrial growth, energy security, and regional employment, powering not only factories and cities but also shaping the economic aspirations of mineral-rich states. However, behind its promise of development lies a complex terrain of ecological disruptions, social displacements, and uneven gains—making it imperative to critically examine the long-term impacts of coal extraction on landscapes and communities. This thesis undertakes an interdisciplinary analysis of the spatial, environmental, and socio-economic transformations induced by coal mining over the past five decades in two of India’s most prominent coalfields: North Karanpura in Jharkhand and the Ib Valley in Odisha. Leveraging remote sensing data and GIS-based change detection methods, the study maps and quantifies Land Use and Land Cover (LULC) changes across five time points. The results reveals an enormous and consistent expansion of open-cast mining zones—North Karanpura grew from 6.6 km² in 1973 to 49.6 km² in 2023, and Ib Valley from 0.12 km² in 1976 to 49.49 km² in 2024, accompanied by corresponding losses in dense vegetation, agricultural lands, and wetland ecosystems. Simultaneously, settlements increased manifold, reflecting rapid industrialisation and demographic shifts driven by labour migration and urban sprawl led to environmental degradation, including air and water pollution, biodiversity loss, and the depletion of potable water sources. The thesis also explores the human dimensions of these transformations, drawing upon census data, land acquisition records, and socio-demographic indicators to assess patterns of displacement, changes in literacy and employment, and the growing rural-urban divide. It highlights how industrial expansion has often excluded local and indigenous communities from its benefits, raising questions about justice, equity, and governance in resource management. By integrating geospatial evidence with socioeconomic narratives, the study not only documents the material footprint of coal mining but also critiques the institutional and policy mechanisms that have enabled its unchecked growth. Ultimately, the research calls for a more sustainable, inclusive, and spatially aware approach to development in India’s coal-bearing regions.

Abstract

Despite the success of the Standard Model (SM), the absence of new physics signals at the Large Hadron Collider (LHC) motivates the exploration of Beyond the SM (BSM) scenarios that deviate from minimal assumptions. Searches for TeV-scale Vectorlike Quarks (VLQs), a common feature in many BSM frameworks, are generally assumed to decay through SM bosons, leading to stringent, model-dependent mass limits. In this thesis, we discuss the phe- nomenology of next-to-minimal VLQ models where this assumption is relaxed, allowing for dominant decays into a new, SM-singlet scalar or pseudoscalar state (Φ). First, we present the theoretical motivations for such extensions, demonstrating their potential to address funda- mental issues like the strong CP problem and Higgs vacuum stability, and their natural emer- gence within frameworks such as Two-Higgs-Doublet and Composite Higgs models. Then, a bottom-up phenomenological framework for both singlet and doublet VLQs containing top and bottom partners is developed. By reinterpreting current experimental constraints from the LHC, we see that a vast, viable parameter space for these exotic decays remains open with- out requiring significant fine-tuning. Finally, to assess the discovery potential at future LHC runs, detailed collider analyses of VLQ pair-production are presented, leveraging a full LHC simulation chain. We use advanced machine learning techniques to distinguish signals from substantial SM backgrounds in several challenging final states. Specifically, this work eval- uates prospects for three signatures with different ML models: 1) monoleptonic final states from singlet 𝑇-quark pair-production using boosted decision trees; 2) monoleptonic signatures from singlet 𝐵-quark pair-production via mixed decays, analysed with a deep neural network model; and 3) fully hadronic final states from 𝐵-quark pair-production, where a novel graph neural network-based model is used to perform event-level classification. The results project a strong discovery potential for VLQs with masses extending well beyond current limits, pro- viding a concrete roadmap for future experimental searches at the High-Luminosity LHC. This thesis underscores the critical synergy between BSM phenomenology and sophisticated machine learning in uncovering new physics in complex collider environments.

Abstract

Graph neural networks (GNNs) have shown great performance in learning from structured data, but their use in real-world situations faces two main difficulties: privacy-preserving training and resilience against adversarial attacks. With this thesis, two different areas of research are brought together to create a general framework for safe and reliable graph learning: adversarial attacks on temporal graphs and federated learning for non-IID graph data. First, we address privacy concerns in GNN training by building a federated spectral graph transformer model coupled with neural ordinary differential equations (ODEs). Especially relevant to social networks, recommendation systems, and fraud detection—where data privacy is vital—our method allows collaborative learning while preserving the decentralisation of sensitive graph data. This strategy increases the value of federated learning in a larger spectrum of complicated network scenarios by optimising bandwidth and considering non-IID heterophilic graphs. Second, we explore Temporal Graph Neural Network (TGNN) adversarial weaknesses and propose Temporal Edge Rank Adversarial Attack (TERA). This approach selectively corrupts important edges using a novel Temporal PageRank-based significance metric, therefore significantly reducing model efficacy while maintaining stealth. Our results underline the imminent need for strong defence methods since they show the sensitivity of advanced TGNNs to well-crafted adversarial attacks. This thesis integrates adversarial robustness with privacy-preserving federated learning to build a framework for safe and dependable graph learning systems. We investigate feasible defences against adversarial attacks in federated graph environments and propose future directions to enhance security and privacy in GNN implementations. Our work promotes the general goal of developing strong machine learning models capable of operating in adversarial, real-world, privacy-sensitive environments.

Abstract

Psychological well-being is a complex construct that is influenced by an interplay of individual traits and external stressors and circumstances. People manage stressors on an everyday basis based on their traits and behaviours. However, significant disruptive events can significantly amplify psychological strain. The COVID-19 pandemic was one such unprecedented disruption. The pandemic’s challenges turned daily life upside-down, with imposed lockdowns, job disruptions, and rampant infection rates. For students in India, students were unexpectedly faced with sudden changes in academics, social isolation and uncertainty about exams and their futures. This thesis explored how individual differences in various psychological traits and coping mechanisms buffer or worsen the impact of the pandemic’s challenges on well-being. Understanding these influences would be crucial for developing targeted interventions like ACT and CBT to foster resilience in future crisis events. The first study collected data from 161 intermediate and college students in India during the second wave of the pandemic. We measured variables such as psychological flexibility, coping styles and our own COVID-19 impact index as predictors of mental and cognitive health outcomes, such as psychological distress, depression, student-related stress, and attention measures of Sustained Attention to Response and Stroop tasks. Regression analyses showed that these individual traits and coping styles significantly predicted mental health outcomes. Mediation analyses further showed that the impact of the pandemic’s challenges was buffered by psychological flexibility and exacerbated by avoidant style coping strategies. These findings stress the importance of interventions that promote psychological flexibility and reduce the reliance of maladaptive coping strategies. We built upon these findings in our second study, expanding the sample size to 254 while narrowing our scope to only college students in India. We incorporated trait anxiety as an additional individual trait for our predictors while expanding our list of pandemic variables to more comprehensively capture the specific environmental stressors of the pandemic with our Pandemic Life Impact Scale. Regression showed that the addition of trait anxiety boosted the prediction of mental health outcomes significantly.

Abstract

Air pollution is a growing concern in India, specifically in the National Capital Region (NCR) which is one of the world’s most polluted regions. Despite the recognized problem, there is a lack of research focusing on how people actually perceive air pollution, the specific actions they take to protect their well-being from its impact, and how effective these personal strategies really are. This thesis is designed to address these knowledge gaps by examining public awareness of air pollution in India and the effectiveness of solutions used to improve Indoor Air Quality (IAQ) and further explores how urban residents respond to degraded air quality through a combination of personal behaviours, technological interventions, and adaptive strategies such as change in window opening and closing behaviour in response to pollution, change in day-to-day lifestyle choices and willingness to invest in cleaner air. As part of the study, ethnographic interviews were conducted in person to gather detailed socioeconomic perspectives. A mixed-methods approach was employed, involving interviews from 101 households in Delhi and it’s neighbouring cities like Ghaziabad and Noida. Both Qualitative and Quantitative methods were used to corroborate the statistical findings with descriptive accounts. The findings reveal widespread awareness of the Air Quality Index (88% are aware), but limited understanding of PM2.5 and its health implications (only 33% know about it). Air purifiers emerged as a common IAQ intervention, yet 40% of non-owners cited doubts about effectiveness or believe that IAQ in their house is sufficiently good. Cost and habitual behaviour to air purifiers were additional primary barriers. Among purifier owners, 75% reported perceived benefits, but many saw these as temporary or insufficient given the scale of outdoor pollution. Furthermore aspects like frequency of purifier use and regular maintenance were assessed as they impact the efficacy of solution. Over 35% of surveyed households already own purifiers indicating revealed Willingness to pay (WTP), while an additional 23% showed interest if costs were subsidized or if they were offered a different plan scheme once given enough information about Indoor Air Quality. Estimated WTP for clean air interventions ranges from 10,000–15,000 INR per household annually, depending on income and awareness levels. Similarly when asked about trust in government mitigation programs to address air pollution people, more than 60% people revealed that they don’t trust government to address these issues but around 58% of people still want to contribute a monthly amount to government to improve public transportation and other programs that addresses vehicular pollution. The study also assesses how people respond to pollution, and thus tries to bridge the gap between occupant behaviour and optimal natural ventilation practice. The thesis proposes a pollution-aware natural ventilation (NV) strategy, guided by PM2.5 and PM10 thresholds. To evaluate its effectiveness and compare it with common practices, this strategy was modelled using EnergyPlus simulations. The simulation results indicate that aligning natural ventilation (NV) schedules with real-time pollution data can reduce energy consumption by up to 10.5%, compared to typical occupant behaviour during pollution episodes, while maintaining acceptable indoor air quality. This approach promotes energy-efficient and occupant-centric ventilation practices even in high-pollution environments while making sure that IAQ is not compromised. The thesis concludes with recommending a multi-pronged approach: integrating sensor-based NV systems into residential buildings, scaling public awareness campaigns focused on PM2.5 literacy and IAQ awareness, and designing incentive programs to expand access to IAQ technologies including better usage practices of Air Purifiers. By combining interview-based behavioral insights, simulationbased optimization, and economic insights, this research offers actionable pathways for managing and improving Indoor Air Quality in polluted urban regions of India.

Abstract

Flexible pressure sensors based on conductive polymers and porous dielectric materials are gaining significant attention for applications in wearable devices, human-machine interaction, and soft robotics. In this work, we present the fabrication and characterization of flexible pressure sensors using polypyrrolecoated cotton textile (PCC) and bubble-induced PDMS foam. A highly compressible multilayer capacitive pressure sensor was developed using PDMS foam as the dielectric layer and PCC as the electrodes. The PDMS foam was prepared by mixing specific amounts of ethanol into PDMS, and the electrodes were attached using silicone adhesive. The fabricated sensor demonstrated low hysteresis, high repeatability, and good step response. Surface profiling and scanning electron microscopy were used to characterize the bubble structure. Applications such as mouse click detection and grasping objects with varying weights were demonstrated, highlighting the sensor’s versatility for free-form electronics. Additionally, an ultra-soft capacitive pressure sensor was developed using polyurethane foam with polypyrrole-coated surfaces as electrodes. Various concentrations of pyrrole and FeCl3 were used to optimize the sensor performance, achieving a high sensitivity of 1.01 kPa−1 at 25 kPa pressure. Finite element simulations were performed to study mechanical deformation and space charge variations under pressure. This sensor also offers customizable shapes and sizes for diverse applications. Further, a piezoresistive pressure sensor was fabricated using PCC synthesized via in-situ chemical oxidative polymerization. This sensor exhibited high sensitivity in the low-pressure range of 160 Pa to 16 kPa and a response time of 463 ms. It showed excellent repeatability over 1000 loading-unloading cycles, with a gauge factor of 0.32 for compressive strains up to 99.6%, enabled by the fibrous structure of cotton. Finally, a large-area flexible conductive cotton fabric (20 cm × 20 cm) was fabricated using in-situ polymerization of polypyrrole. The fabric maintained stable conductivity after multiple washing cycles, with resistance changes stabilizing after the fourth wash. This demonstrates its potential in interactive textiles and smart fabric application

Abstract

Over the past decade, football analytics has transformed how the game is played, understood, and managed, primarily in elite European contexts. Football analytics refers to the use of data-driven methods to evaluate tactics, player performance, recruitment, and decision-making across all levels of the sport. Yet little is known about how data practices take shape in low-resource environments, especially in the Global South. This thesis investigates the emergence of Indian football analytics as a decentralised, digitally scaffolded ecosystem, driven by informal learning, frugal innovation, and community-led mentorship. Drawing on digital ethnography, semi-structured interviews, and social media shadowing, this research traces how aspiring analysts build careers, collaborate, and gain legitimacy in the absence of formal training pathways. Participants describe a rich peer-to-peer learning culture enabled by opensource tools, public data, and social media platforms. Knowledge circulates through blogs, repositories, newsletters, and YouTube videos, creating a porous but potent apprenticeship network. The thesis identifies four key dynamics that shape this ecosystem: (1) informal learning and community mentorship as alternatives to institutional training, (2) institutional frictions that limit the uptake of data in football clubs, despite analyst expertise, (3) frugal innovation and grassroots tooling to bypass infrastructure gaps, and (4) social media as a hiring and visibility pipeline. Together, these themes reveal an ecosystem that enables participation while denying long-term stability, where analysts must continuously navigate precarious labour conditions, shifting legitimacy structures, and platform pressures. By centring the everyday practices and lived experiences of Indian football analysts, this study makes three core contributions. First, it offers an empirically grounded account of how decentralised analytics infrastructures operate in the Global South. Second, it highlights how frugality and informality can be generative forces in technological learning and labour. Third, it calls attention to the politics of visibility, credibility, and care in informal data ecosystems. This work contributes to ongoing conversations in HCI and ICTD around alternative infrastructures, peer learning, and the ethics of digital labour. It concludes by offering design-oriented suggestions to support more sustainable, equitable pathways for young data workers in sport.