I2S Masters/ Doctoral Theses

This project presents Intellinotes, an AI-powered platform that transforms educational documents into multiple learning formats to address information-overload challenges in modern education. The system leverages large language models (GPT-4o-mini) to automatically generate four complementary outputs from a single document upload: educational summaries, conversational podcast scripts, hierarchical mind maps, and interactive flashcards.

The platform employs a three-tier architecture built with Next.js, FastAPI, and MongoDB, supporting multiple document formats (PDF, DOCX, PPTX, TXT, images) through a robust parsing pipeline. Comprehensive evaluation on 30 research documents demonstrates exceptional system reliability with a 100% feature success rate across 150 tests (5 features × 30 documents), and strong semantic understanding with a semantic similarity score of 0.72.

While ROUGE scores (ROUGE-1: 0.40, ROUGE-2: 0.09, ROUGE-L: 0.17) indicate moderate lexical overlap typical of abstractive summarization, the high semantic similarity demonstrates that the system effectively captures and conveys the conceptual meaning of source documents—an essential requirement for educational content. This validation of meaning preservation over word matching represents an important contribution to evaluating educational AI systems.

The system processes documents in approximately 65 seconds with perfect reliability, providing students with comprehensive multi-modal learning materials that cater to diverse learning styles. This work contributes to the growing field of AI-assisted education by demonstrating a practical application of large language models for automated educational content generation supported by validated quality metrics.

Designing a well-balanced exam requires instructors to review extensive course materials, determine key concepts, and design questions that reflect appropriate difficulty and cognitive depth. This project develops an AI-powered Question Paper Generator that automates much of this process while keeping instructors in full control. The system accepts PDFs, Word documents, PPT slides, and text files, extracts their content, and builds a FAISS-based retrieval index using sentence-transformer embeddings. A large language model then generates multiple question types—MCQs, short answers, and true/false—guided by user-selected difficulty levels and Bloom’s Taxonomy distributions to ensure meaningful coverage. Each question is evaluated with a grounding score that measures how closely it aligns with the source material, improving transparency and reducing hallucination. A React frontend enables instructors to monitor progress, review questions, toggle answers, and export to PDF or Word, while an ASP.NET Core backend manages processing and metrics. The system reduces exam preparation time and enhances consistency across assessments.

The rapid spread of misinformation across online platforms has made automated fake news detection essential. This project develops and compares machine learning (SVM, Decision Tree) and deep learning (LSTM) models to classify news headlines from the GossipCop and PolitiFact datasets as real or fake. After extensive preprocessing— including text cleaning, lemmatization, TF-IDF vectorization, and sequence tokenization—the models are trained and evaluated using standard performance metrics. Results show that SVM provides a strong baseline, but the LSTM model achieves higher accuracy and F1-scores by capturing deeper semantic and contextual patterns in the text. The study highlights the challenges of domain variation and subtle linguistic cues, while demonstrating that context-aware deep learning methods offer superior capability for automated fake content detection.

Emerging applications in next-generation wireless networks, such as augmented and virtual reality (AR/VR) and autonomous vehicles, demand significant computational and communication resources at the network edge. This PhD research focuses on developing joint communication–computation solutions while incorporating various network-, application-, and user-imposed constraints. In the first thrust, we examine the problem of energy-constrained computation offloading to edge servers in a multi-user, multi-channel wireless network. To develop a decentralized offloading policy for each user, we model the problem as a partially observable Markov decision process (POMDP). Leveraging bandit learning methods, we introduce a decentralized task offloading solution in which edge users offload their computation tasks to nearby edge servers over selected communication channels. 

The second thrust focuses on user-driven requirements for resource-intensive applications, specifically the Quality of Experience (QoE) in 2D and 3D video streaming. Given the unique characteristics of millimeter-wave (mmWave) networks, we develop a beam alignment and buffer-predictive multi-user scheduling algorithm for 2D video streaming applications. This algorithm balances the trade-off between beam alignment overhead and playback buffer levels for optimal resource allocation across multiple users. We then extend our investigation to develop a joint rate adaptation and computation distribution framework for 3D video streaming in mmWave-based VR systems. Numerical results using real-world mmWave traces and 3D video datasets demonstrate significant improvements in video quality, rebuffering time, and quality variations perceived by users.

Finally, we develop novel edge computing solutions for multi-layer immersive video processing systems. By exploring and exploiting the elastic nature of computation tasks in these systems, we propose a multi-agent reinforcement learning (MARL) framework that incorporates two learning-based methods: the centralized phasic policy gradient (CPPG) and the independent phasic policy gradient (IPPG). IPPG leverages shared information and model parameters to learn edge offloading policies; however, during execution, each user acts independently based only on its local state information. This decentralized execution reduces the communication and computation overhead of centralized decision-making and improves scalability. We leverage real-world 4G, 5G, and WiGig network traces, along with 3D video datasets, to investigate the performance trade-offs of CPPG and IPPG when applied to elastic task computing.

Customer churn is a critical challenge for subscription-based businesses, as it directly impacts revenue, profitability, and long-term customer loyalty. Because retaining existing customers is more cost-effective than acquiring new ones, accurate churn prediction is essential for sustainable growth. This work presents a machine learning based framework for predicting and analyzing customer churn, coupled with an interactive Streamlit web application that supports real time decision making. Using historical customer data that includes demographic attributes, usage behavior, transaction history, and engagement patterns, the system applies extensive data preprocessing and feature engineering to construct a modeling-ready dataset. Multiple models Logistic Regression, Random Forest, and XGBoost are trained and evaluated using the Scikit-Learn framework. Model performance is assessed with metrics such as accuracy, precision, recall, F1-score, and ROC-AUC to identify the most effective predictor of churn. The top performing models are serialized and deployed within a Streamlit interface that accepts individual customer inputs or batch data files to generate immediate churn predictions and summaries. Overall, this project demonstrates how machine learning can transform raw customer data into actionable business intelligence and provides a scalable approach to proactive customer retention management.

Latency–accuracy tradeoffs are fundamental in real-time applications of deep neural networks (DNNs) for cyber-physical systems. In autonomous driving, in particular, safety depends on both prediction quality and the end-to-end delay from sensing to actuation. We observe that (1) when latency is accounted for, the latency-optimal network configuration varies with scene context and compute availability; and (2) a single fixed-resolution model becomes suboptimal as conditions change.

We present a multi-resolution, end-to-end deep neural network for the CARLA urban driving challenge using monocular camera input. Our approach employs a convolutional neural network (CNN) that supports multiple input resolutions through per-resolution batch normalization, enabling runtime selection of an ideal input scale under a latency budget, as well as resolution retargeting, which allows multi-resolution training without access to the original training dataset.

We implement and evaluate our multi-resolution end-to-end CNN in CARLA to explore the latency–safety frontier. Results show consistent improvements in per-route safety metrics—lane invasions, red-light infractions, and collisions—relative to fixed-resolution baselines.

Reliable cellular connectivity is essential for modern services such as telehealth, precision agriculture, and remote education; yet, measuring network performance in rural areas presents significant challenges. Traditional drive testing cannot access large geographic areas between roads, while crowdsourced data provides insufficient spatial resolution in low-population regions. To address these limitations, we develop an open-source UAV-based measurement platform that integrates an onboard computation unit, commercial cellular modem, and automated flight control to systematically capture Radio Access Network (RAN) signals and end-to-end network performance metrics at different altitudes. Our platform collects synchronized measurements of signal strength (RSRP, RSSI), signal quality (RSRQ, SINR), latency, and bidirectional throughput, with each measurement tagged with GPS coordinates and altitude. Experimental results from a semi-rural deployment reveal a fundamental altitude-dependent trade-off: received signal power improves at higher altitudes due to enhanced line-of-sight conditions, while signal quality degrades from increased interference with neighboring cells. Our analysis indicates that most of the measurement area maintains acceptable signal quality, along with adequate throughput performance, for both uplink and downlink communications. We further demonstrate that strong radio signal metrics for individual cells do not necessarily translate to spatial coverage dominance such that the cell serving the majority of our test area exhibited only moderate performance, while cells with superior metrics contributed minimally to overall coverage. Next, we develop several machine learning (ML) models to improve the prediction accuracy of signal strength at unmeasured altitudes. Finally, we extend our measurement platform by integrating non-terrestrial network (NTN) user terminals with the UAV components to investigate the performance of Low-earth Orbit (LEO) satellite networks with UAV mobility. Our measurement results demonstrate that NTN offers a viable fallback option by achieving acceptable latency and throughput performance during flight operations. Overall, this work establishes a reproducible methodology for three-dimensional rural network characterization and provides practical insights for network operators, regulators, and researchers addressing connectivity challenges in underserved areas.

Python's dynamic nature makes performance enhancement challenging. Recently, a JIT compiler using a novel copy-and-patch compilation approach was implemented in the reference Python implementation, CPython. Our goal in this work is to study and understand the performance properties of CPython's new JIT compiler. To facilitate this study, we compare the quality and performance of the code generated by this new JIT compiler with a more mature and traditional meta-tracing based JIT compiler implemented in PyPy (another Python implementation). Our thorough experimental evaluation reveals that, while it achieves the goal of fast compilation speed, CPython's JIT severely lags in code quality/performance compared with PyPy. While this observation is a known and intentional property of the copy-and-patch approach, it results in the new JIT compiler failing to elevate Python code performance beyond that achieved by the default interpreter, despite significant added code complexity. In this thesis, we report and explain our novel experiments, results, and observations.

Recent research in Electronic Health Records (EHRs) has enabled personalized and longitudinal modeling of patient trajectories for health outcome improvement. Despite this progress, existing methods often struggle to capture the dynamic, heterogeneous, and interdependent nature of medical data. Specifically, many representation methods learn a rich set of EHR features in an independent way but overlook the intricate relationships among them. Moreover, data scarcity and bias, such as the cold-start scenarios where patients only have a few visits or rare conditions, remain fundamental challenges in clinical decision support in real-life. To address these challenges, this dissertation aims to introduce an integrated machine learning framework for sophisticated, interpretable, and adaptive EHR representation modeling. Specifically, the dissertation comprises three thrusts:

1. A time-aware graph transformer model that dynamically constructs personalized temporal graph representations that capture patient trajectory over different visits.
2. A contrasted multi-Intent recommender system that can disentangle the multiple temporal patterns that coexist in a patient’s long medical history, while considering distinct health profiles.
3. A few-shot meta-learning framework that can address the patient cold-start issue through a self- and peer-adaptive model enhanced by uncertainty-based filtering.

Together, these contributions advance a data-efficient, generalizable, and interpretable foundation for large-scale clinical EHR mining toward truly personalized medical outcome prediction.

In the light of rapid advancement of global connectivity and the increasing reliance on multilingual communication, speech-based Machine Translation (MT) systems have emerged as essential technologies for facilitating seamless cross-lingual interaction. These systems enable individuals and organizations to overcome linguistic boundaries by automatically translating spoken language in real time. However, despite their growing ubiquity in various applications such as virtual assistants, international conferencing, and accessibility services, the security and robustness of speech-based MT systems remain underexplored. In particular, limited attention has been given to understanding their vulnerabilities under adversarial conditions, where malicious actors intentionally craft or manipulate speech inputs to mislead or degrade translation performance.

This thesis presents a comprehensive investigation into the security landscape of speech-based machine translation systems from an adversarial perspective. We systematically categorize and analyze potential attack vectors, evaluate their success rates across diverse system architectures and environmental settings, and explore the practical implications of such attacks. Furthermore, through a series of controlled experiments and human-subject evaluations, we demonstrate that adversarial manipulations can significantly distort translation outputs in realistic use cases, thereby posing tangible risks to communication reliability and user trust.

Our findings reveal critical weaknesses in current MT models and underscore the urgent need for developing more resilient defense strategies. We also discuss open research challenges and propose directions for building secure, trustworthy, and ethically responsible speech translation technologies. Ultimately, this work contributes to a deeper understanding of adversarial robustness in multimodal language systems and provides a foundation for advancing the security of next-generation machine translation frameworks.