Abstract

In the era of digital intimacy, online dating applications like Bumble have significantly reshaped social interactions and romantic engagements, particularly in India. This thesis delves into the gender disparities manifested within these platforms, focusing on the algorithmic biases present in Bumble�s match recommendations. By examining how these algorithms might favour specific user demographics over others, this research addresses the broader implications of such biases on the visibility and representation of non-binary and marginalized genders. The thesis posits that while these platforms claim neutrality, their underlying algorithms often replicate societal biases, thereby influencing user experiences based on gender. This investigation is anchored in India�s rapidly evolving digital landscape, where traditional norms meet a burgeoning digital dating culture. Employing a mixed-methods approach, this study combines quantitative data analysis with qualitative interviews to offer a comprehensive view of how users perceive and experience gender biases. The quantitative analysis assesses the disparities in match recommendations. At the same time, qualitative insights are gathered from user narratives to explore the subjective impact of these algorithms on individual self-perception and interpersonal interactions. This methodological framework highlights the prevalence of algorithmic bias and enriches the understanding of its practical effects on users. The research findings indicate a significant difference in the algorithmic treatment of users based on gender, revealing a complex interplay of technology and social identity that often reinforces traditional gender roles and stereotypes. The conclusions drawn from this study underscore the urgent need for algorithmic transparency and the integration of ethical considerations in the design and deployment of dating applications. By documenting the nuanced ways in which gender disparities are embedded within digital platforms, this thesis contributes to the critical discourse on digital ethics and algorithmic fairness. The research advocates for more inclusive and equitable design practices that consider the diverse spectrum of gender identities, ultimately aiming to inform developers, policymakers, and the broader community about the challenges and opportunities for fostering inclusivity in digital spaces. The findings pave the way for future research into the inclusivity of digital platforms and serve as a call to action for adopting more responsible technology practices in online dating.

Abstract

The network of cameras around urban cities is increasing in a manner unmanageable by current infrastructure. Video feeds in these networks requires deploying extensive Computer Vision pipelines to generate useful insights. However, poorly designed architectures lead to overspending on the infrastructure by local authorities. This dissertation proposes a scalable distributed video analytics framework that can process thousands of video streams from sources such as CCTV cameras using semantic scene analysis. The main idea is to deploy deep learning pipelines on the fog nodes and generate semantic scene description records (SDRs) of video feeds from the associated CCTV cameras. These SDRs are transmitted to the cloud instead of video frames saving on network bandwidth. Using these SDRs stored on the cloud database, we can answer many complex queries and perform rich video analytics, within extremely low latencies. There is no need to scan and process the video streams again on a per query basis. The software architecture on the fog nodes allows for integrating new deep learning pipelines dynamically into the existing system, thereby supporting novel analytics and queries. We demonstrate the effectiveness of the system by proposing a novel distributed algorithm for real-time vehicle pursuit. The proposed algorithm involves asking multiple spatio-temporal queries in an adaptive fashion to reduce the query processing time and is robust to inaccuracies in the deployed deep learning pipelines and camera failures.

Abstract

Smart Cities represent the nexus of innovation in urban planning, leveraging the Internet of Things (IoT) to foster enhanced urban living. However, the diversity of IoT devices and protocols often creates interoperability barriers. oneM2M, a global standard, addresses this challenge by providing a common service layer that enables seamless communication and data exchange between heterogeneous IoT devices along with features for device management, security, and semantic interoperability. Its resourcebased model and support for various communication protocols make it a key enabler for interoperable smart city solutions. This enables a wide range of intelligent smart city applications, including coordinated traffic management, intelligent energy grids, and responsive public services. This thesis zeroes in on the pivotal aspect of interoperability within Smart Cities, with a particular focus on oneM2M-based interoperability systems. Through a detailed exploration of oneM2M standards and their application in the Smart City context, this research underscores the importance of a unified, standards-based approach to IoT integration, highlighting the role of interoperability in unlocking the full potential of Smart City initiatives. In addressing the critical challenge of enhancing latency and performance in oneM2M-based systems within Smart City frameworks, this thesis recognizes the limitations of existing architectures, which often impede scalability and efficiency. A novel distributed, multi-layered data platform architecture for oneM2M based interoperability platforms is proposed, aiming to demonstrate significant improvements in latency and overall system performance while ensuring scalability across diverse and large-scale Smart City deployments. The research encompasses a comprehensive performance analysis of this architecture versus a centralized alternative within a real-world Smart City Living Lab deployment. Additionally, an exploratory analysis of open-source oneM2M-based interoperability systems (Mobius, OM2M, ACME) using this large-scale system offers insights into architectural choices and their suitability for smart city implementations. Another challenge that becomes fairly evident is the complexity that arises in the usage of the said interoperability solutions based on oneM2M. To increase the ease of use and of the oneM2M based solutions within the IoT ecosystems, this thesis presents the City IoT Operating Platform (ctOP). This platform, meticulously engineered as a lightweight oneM2M wrapper, is designed to enhance interoperability, streamline IoT device integration, and provide robust functionality such as user management and security within real-world smart city deployments. This contribution is pivotal for the IoT field, challenging the status quo of existing oneM2M system design paradigms and proposing a more adaptable, scalable, and user-friendly alternative. Through rigorous analysis, real-world deployment scenarios, and the development of the ctOP platform, this research contributes to both the academic discourse on Smart City development and provides actionable insights for practitioners and policymakers seeking to implement or refine IoT interoperability solutions in urban settings. The ultimate goal is to pave the way for more interconnected, sustainable, and resilient Smart Cities, where technology serves as a backbone for addressing complex urban challenges.

Abstract

Grover�s quantum search algorithm is one of the earliest discoveries in quantum computing. It is a fundamental algorithm that uses quantum superposition to provide a quadratic speedup for unstructured search tasks over the best possible classical method (linear search). However, this advantage is substantially affected due to the presence of quantum noise. Quantum noise arises due to the interaction between quantum systems and their environments. The resultant errors manifest between the execution of two quantum gates can be effectively modeled using quantum channels. In this study, we look at the effect of total partial depolarizing channel error, affecting the entire quantum register coherently with a certain probability. This modeling approach simulates continuous noise exposure in quantum computers and the stochastic nature of error introduction. In this scenario, implementing an error correction method is non-trivial and costly. Quantum theory allows for a scenario in which quantum channels, representing the flow of quantum information, are organized in a coherent superposition of alternative orders. This phenomenon, known as indefinite causal order, has sparked significant interest in recent years as researchers seek to understand its implications. A quantum switch is a device that operationalizes the concept of indefinite causal order. In a quantum switch, the advantages appear significantly due to the coherent superposition of alternative configurations of the quantum components, which are controlled by an additional control system. In this work, we propose a new approach to mitigate the impact of quantum noise on Grover�s search algorithm using quantum switches. For this, we assume the resultant noise at every iteration to be originating in discrete steps within the iteration such that it can be modeled as a composition of two depolarising channels. In particular, we propose two theoretical frameworks for incorporating these quantum switches in a noisy Grover�s algorithm and take the success probability of finding g, the desired element at any given iteration, as the sole quantifier of the switch�s action in diminishing the effect of noise in search space. In the first framework, we apply the superposition of channels� orders using a quantum switch and make a measurement followed by post-selection at every iteration or application of Grover operator G. In the second framework, we delay the measurement until the very end. In other words, if we want to look at the quantum switch�s action at the k th step, we already have k ? 1 th measurements followed by post-selections for the first framework. In contrast, we will only have a single measurement at the end of k th iteration in the second case. The measurements we make on the quantum switch intermittently between the iterations followed by post-selection destroy the quantum correlations between the target input system and the control qubit. Since these correlations are believed to capture the additional information in the combined system, the second framework is expected to retain more information than the first framework during the run of Grover�s Algorithm under the influence of noise. We observe in plots that the second framework gives a significant advantage in the success probability of Grover�s algorithm running on a search space of 24 elements or 4 qubits. Thus, we explore the quantum switch�s potential role as a tool for maintaining quantum computing�s promise against the challenges posed by quantum noise, marking a significant step forward in the field of quantum computing and information theory.

Abstract

With Large Language Models (LLMs) and Language models in general becoming a more significant part of our daily content consumption, it is paramount to ensure that languages with fewer resources do not get excluded. As most language models are trained using online data, their performance is usually significantly worse for low-resource languages than languages such as English. This gap in performance leaves speakers of low-resource languages with a handicapped experience of consuming information and participating in online discourse. In recent years, methods have come up that seek to address this resource gap by generating large datasets to enable the training of models for low-resource languages across various tasks. One such task is fact-to-text generation, where cross-lingual generation has gained prominence due to its ability to leverage high-resource languages to augment generation for low-resource languages. However, these works rarely address the noisy nature of synthetically created datasets, which can cause models to hallucinate, reducing their usefulness for factually grounded tasks. This work investigates various methods and ideas that revolve around carefully using noisy datasets. Methods that account for the noisy nature of data can improve the quality of generation of texts without requiring significant modelling or architectural changes. We leverage techniques such as curriculum learning and, in the process, describe various metrics that can be used to quantify data quality. Our work focuses on cross-lingual fact-to-text generation, and thus, we extend our work to generating factually-grounded text. We begin our study by using the XAlign dataset. We investigate how curriculum learning can be used to improve the performance of models for the task mentioned above. We experiment with different curriculum schedules and data-ordering metrics using a sharded curriculum learning framework and delineate how different metrics perform under different schedules. We show that curriculum learning outperforms plain, non-curriculum learning-based training using commonly used metrics. We also introduce a novel metric for ordering data - coverage score, which captures the semantic alignment between the input text and reference text. We show that training with data ordered according to coverage score under a gradually refining schedule results in the best-performing model. Next, we apply these findings to a more challenging setting - long-text generation. To this end, we create a new synthetic dataset using the XAlign dataset and show that previous findings do not apply to this problem setting. We identify the cause of this discrepancy and show that more than a simple curriculum learning framework is needed here. We denoise the training set using different trusted data sources and show that ordering data based on this noise score and a probabilistic sampling-based curriculum improves performance. Finally, we conclude our studies by explicitly focusing on reducing hallucinations in long-text generation. We introduce a modular pipeline-based approach with multiple steps to mitigate hallucination during various stages of training. We show that this approach results in sizeable improvements compared to end-to-end training. We also introduce a new evaluation metric for evaluating texts with divergent references, where accounting for the source is also essential. In summary, this work covers various facets of learning with noisy data for the problem of cross-lingual fact-to-text generation. Synthetically created datasets can bridge the gap between languages, but training models using such datasets is challenging. Through extensive experimentation, we demonstrate several ways to tackle this problem.

Abstract

The rapid development of the Internet of Things (IoT) has led to a surge in the number of IoT devices within households, resulting in a significant strain on traditional household wiring and switch infrastructure. As the number of devices increases, existing wiring systems struggle to accommodate the growing demand, leading to energy conversion losses and inefficiencies. Furthermore, the fixed positioning of sockets and switches limits modularity and hampers the flexibility to redesign and adapt to the expanding needs of modern households. This thesis addresses these challenges by proposing innovative solutions to enhance the adaptability, efficiency, and modularity of household wiring and switch systems in the era of IoT proliferation. This thesis introduces an innovative approach to home automation by integrating smart ceiling tiles and energy-harvesting Bluetooth Low-Energy (BLE) switches for controlling household appliances. The system employs trilateration techniques to determine the precise location of switches based on signals received by the smart tiles installed in various rooms. Localisation accuracy was achieved across rooms by analysing received signal strength indicator (RSSI) values. The smart tiles are powered by DC power via support rails, significantly reducing the need for complex wiring. By using machine learning classification algorithms with RSSI values as features, the system accurately predicts switch locations with a high accuracy rate of 93% . The Smart tiles use Power Line communication (PLC) to communicate between the tiles using Carrier Sense and Multiple Access with Collision Detection(CSMA/CD). Integrating smart tiles into false ceilings, combined with energy-harvesting BLE switches and PLC, offers several benefits, including simplified wiring, enhanced user convenience, and improved aesthetic appeal. This thesis contributes to advancing the field of home automation by presenting a scalable and efficient infrastructure for smart home control systems.

Abstract

This thesis is driven by the imperative to enhance efficiency and precision in warehouse management systems. The first part introduces MVRackLay, an innovative solution employing multi-view analysis to accurately estimate complex layouts of racks and shelves in warehouses, offering a comprehensive 3D rendering of the scene from a single monocular camera. In the second part, Imagine2Servo revolutionizes visual servoing algorithms by generating intermediate goal images through diffusion-based editing techniques, enabling precise control in object-reaching tasks in warehouses and tasks like longrange navigation and manipulation. Through real-world validation, these innovations mark significant advancements in warehouse automation and robotic control systems, promising transformative impacts across various domains. In the first part of this thesis (chapter 3), we showcase MVRackLay, a monocular multi-view layout estimation for warehouse racks and shelves. Unlike typical layout estimation methods, MVRackLay estimates multi-layered layouts across multiple views, wherein each layer corresponds to the layout of a shelf within a rack. Given a sequence of images of a warehouse scene, our model outputs segmented racks and each shelf�s front and top view layout within a rack. Further, MVRackLay shows superior performance vis-a-vis its single view counterparts in layout accuracy, quantized in terms of the mean IoU and mAP metrics. We also showcase multi-view stitching of the 3D layouts, resulting in a representation of the warehouse scene concerning a global reference frame akin to a rendering of the scene from a SLAM pipeline. To the best of our knowledge, this is the first such work to portray a 3D rendering of a warehouse scene in terms of its semantic components - Racks, Shelves and Objects - all from a single monocular camera. In the second part of this thesis (chapter 4), we introduce Imagine2Servo, an innovative approach leveraging diffusion-based image editing techniques to enhance visual servoing algorithms by generating intermediate goal images. Visual servoing, the method of controlling robot motion through feedback from visual sensors, has seen significant advancements with the integration of optical flow-based methods. However, its application remains limited by inherent challenges, such as the necessity for a target image at test time, the requirement of substantial overlap between initial and target images, and the reliance on feedback from a single camera. Imagine2Servo allows for the extension of visual servoing applications beyond traditional constraints, enabling tasks like long-range navigation and manipulation without pre-defined goal images. We show its applicability in precisely performing different warehouse tasks, navigation tasks and manipulation tasks. We propose a pipeline that synthesizes subgoal images grounded in the task at hand, facilitating servoing in scenarios with minimal initial and target image overlap and integrating multi-camera feedback for comprehensive task execution. Our contributions demonstrate a novel application of image generation to robotic control, significantly broadening the capabilities of visual servoing systems. Real-world experiments validate the effectiveness and versatility of the Imagine2Servo framework in accomplishing a variety of tasks, marking a notable advancement in the field of visual servoing.

Abstract

This thesis addresses the challenge of real-time facial emotion recognition through the lens of Deep Convolutional Neural Networks (DCNNs). While DCNNs have proven to be state-ofthe-art for image classification, their efficacy is contingent upon abundant, accurately labeled data. Emotion recognition, a complex and subjective task, suffers from a scarcity of comprehensive datasets. Existing facial expression databases lack the depth required to train deep neural networks effectively, particularly those that have excelled in object recognition tasks. The limitations are further compounded by high inter-subject variations, including age, gender, ethnic backgrounds, and individual expressiveness levels. Facial images are also subject to occlusions, pose variations, and wearable accessories, intensifying the complexity of the emotion recognition problem. Consequently, the choice of a benchmark dataset plays a pivotal role in the development and evaluation of an effective model. In this research, we explore the nuances of real-time facial emotion recognition, delving into the challenges posed by limited and diverse datasets. Our approach involves a deep investigation into the intricacies of emotion representation in facial images, leveraging the power of DCNNs. By addressing the dataset limitations and exploring techniques to mitigate the impact of diverse personal attributes, we aim to contribute to the advancement of facial emotion recognition models. The ultimate goal is the development of a real-time facial emotion recognition web application, demonstrating the practical application of our findings in a user-friendly and accessible manner

Abstract

The thesis entitled �Design of Low-Power Electronic Circuits & Systems for Point of Care Healthcare Applications� focuses on the development of a cutting-edge point of care device tailored for deployment in remote and resource-constrained settings. The impetus for this project stems from the urgent need to extend quality healthcare services in areas where conventional, cumbersome, and expensive medical equipment is untenable. Engineered for efficiency and ease of use, the device is characterized by its low power consumption and portability, making it well-suited for environments with sparse access to electrical power and established medical facilities. The core technology utilizes Electrical Impedance Spectroscopy (EIS) integrated with vital signs monitoring to detect physiological changes indicative of health conditions that require immediate medical attention. This dual functionality not only enables the early detection of critical health issues but also promotes timely medical interventions, significantly enhancing patient outcomes. This research further encompasses the innovative design of an active high pass filter within the analog baseband chain of the device�s integrated circuit. These components are specifically tailored for use in Frequency Modulated Continuous Wave (FMCW) radar systems, which form part of the receiver design to accurately detect heart and respiratory rates. Comprehensive evaluation of the device throughout the research confirms its effectiveness in meeting the healthcare delivery needs of isolated regions. The findings highlight the transformative potential of such devices in improving healthcare accessibility and efficacy across underserved populations. This device emerges as a vital instrument in the global initiative to enhance healthcare delivery, demonstrating significant implications for the future of remote medical practices and technology-driven health interventions.

Abstract

The rapid advancements in natural language processing have primarily focused on high-resource languages, leaving low-resource languages, such as those in the Dravidian family, underrepresented in terms of research and resources. To bridge this gap and enable more effective processing of Dravidian languages, this thesis explores the utilization of context beyond the sentence level, delving into linguistic structures at the paragraph and document level, and leverages multilingual training. This is done particularly for the tasks of neural machine translation and multi-class sentence classification. CoPara, the first publicly available paragraph-level n-way aligned corpus for Dravidian languages (Kannada, Malayalam, Tamil, Telugu) and English, was created. This dataset fills a critical gap in multilingual resources for low-resource Dravidian languages and enables research on the impact of paragraph-level information on NMT tasks. The corpus contains aligned paragraphs across English and four Dravidian languages, providing a rich resource for studying cross-lingual phenomena and improving machine translation quality. To demonstrate the utility of CoPara, neural machine translation experiments were conducted by fine-tuning a pre-trained multilingual sequence-to-sequence model on the dataset. The results show significant improvements in translation quality for paragraphs across all language pairs over models trained using sentence-level data, highlighting the potential of leveraging paragraph-level information and multilingual training for enhancing machine translation systems in low-resource settings. An annotated dataset of SEBI legal case files, along with its Indic adaptation, was created. The dataset consists of sentences classified into legally applicable categories and is the first of its kind for Indian legal adjudication orders concerning insider trading. This dataset facilitated the development of a novel system for aspect-based semantic segmentation of legal case files, tailored to different stakeholders like investors, defense lawyers, and adjudicating officers. The system leverages document-level context to improve sentence classification performance, and multilingual training using the Indic adaptation further enhances the results. The results highlight the importance of incorporating context beyond the sentence level and leveraging multilingual training to advance Dravidian language processing. In summary, the thesis provides a comprehensive exploration of utilizing paragraph and document-level context for NMT and sentence classification tasks. The datasets and methodologies introduced pave the way for future research on long-text processing and context-aware NLP tasks in low-resource languages, with potential implications for other language families and domains.