Engineering Commons^™

Gender Classification Through Postural Analysis: A Comparative Study Of 2d Images And 3d Reconstructions., Prathamesh Dixit

Master's Projects

In computer vision, gender classification has become a vital task having applications in human-computer interaction, healthcare, and surveillance. In this study, we look at a two-step approach based on human joint information for gender classification. In this research, we use convolutional neural networks (CNNs).

With Leeds Sports Pose (LSP) dataset, we use a C5 pre-trained model to map and extract joint information from 2D RGB images and after pre-processing and background removal, we use PiFUHD to transform these 2D images into 3D representations. Next, we train our models on RGB images and joint images for both 2D and 3D representations. …

Understanding Distracted Driving And Gaze Patterns In A Driving Simulator: Simple Vs. Complex Challenges, Rishi Prabhat Narayana Sannala

Master's Projects

Distracted driving has grown in criticality over the recent years, given the numerous distractions that drivers face today, and which have further been magnified by the proliferation of in-vehicle technologies and mobile devices. Such distractions can seriously compromise a driver's ability to be fully focused on the road and to carry out timely responses and informed decisions that are key in minimizing the risks of a crash and maximizing road safety. The general aim of the research is to observe how simple versus complex distractors affect driving performance and gaze patterns. The eyetracker used is the Tobii Pro Fusion, synchronized …

An Empirical Analysis Of Adversarial Attacks In Federated Learning, Rohit Mapakshi

Master's Projects

In this paper, we experimentally analyze the susceptibility of selected Federated Learning (FL) systems to the presence of adversarial clients. We find that temporal attacks significantly affect model performance in FL, especially when the adversaries are active throughout and during the ending rounds of the FL process. Machine Learning models like Multinominal Logistic Regression, Support Vector Classifier (SVC), Neural Network models like Multilayer Perceptron (MLP), Convolution Neural Network (CNN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM) and tree-based machine learning models like Random Forest and XGBoost were considered. These results highlight the effectiveness of temporal attacks and the need …

Comparitive Analysis Of Time Series Forecasting Using Frequency Informed Dense Neural Networks And Lstm, Avinash Mangalore Suresh

Master's Projects

Time series forecasting influences our lives on a daily basis, being a versatile tool in various application areas like environmental studies, finance, medicine and much more. While there are many established statistical and deep learning approaches to model time series data, each implementation comes with their own set of drawbacks or areas of improvements. Most of the existing deep learning architectures and research have focused on modeling time series data in the time-domain exclusively. However training deep learning models in the time-domain has some drawbacks, mainly due to the inherent temporal dependence of each time-step on the time-steps before it, …

Personalizing Image Generation From Prompts Using Generative Ai, Mit Ramesh Jain

Master's Projects

The rapid advancements in Generative AI, particularly Text-to-Image (T2I) models, have opened up new possibilities for personalized image generation. Finetuning large T2I models for specific downstream tasks is a key approach to achieving tailored outputs. In recent years, Parameter-Efficient Fine-Tuning (PEFT) techniques have gained significant attention as a cost-effective and efficient solution for fine-tuning large models. Initially developed for fine-tuning large language models (LLMs), PEFT techniques have been extensively studied and compared in the context of language tasks. However, regarding the T2I domain, there is a lack of similarly exhaustive and detailed literature on PEFT. This research project, in the …

Load Balancing For Cloud-Based Applications, Nitish Ranjan

Master's Projects

Effective load balancing is critical in ensuring optimal resource utilization, reducing latency, and improving the overall performance of distributed systems. This report commences with a comprehensive literature review on existing load-balancing algorithms, examining their methodologies, strengths, and limitations within various computing environments, including cloud computing, data centers, and network traffic management. Despite significant advancements in this field, the dynamic nature of distributed systems, coupled with the ever-increasing demand for efficient data processing, poses ongoing challenges. In response, this study proposes a novel load-balancing algorithm to address these contemporary challenges. The approach leverages dynamic and hybrid load balancing, distinguishing it from …

Multimodal Techniques For Malware Classification, Jonathan Jiang

Master's Projects

The threat of malware has remained a serious concern for computer networks and systems, highlighting the need for accurate classification techniques. This research adopted the structured nature of PE files incorporated with a multi-modal machinelearning approach, to classify malware types. Features extracted from the PE headers were used to train an LSTM model. Features extracted from the PE sections were used to train a CNN model. Probabilities produced from these two models were then concatenated and fed into an SVM classifier. This multi-modal approach demonstrated high accuracy by experimenting with and verifying the approach on a large and labeled dataset. …

An Attributed And Diverse Encoder-Decoder Processing Technique For Anomaly Detection., Kenneth Antony John

Master's Projects

Attributed graphs are graphs that contain extra information about the attributes of nodes and edges. They can be used to model a plethora of real-world scenarios like social networks, bank transactions, and even academic citation data. Anomalies in such graphs can be irregularities or unusual patterns that are observed in the attributes or the structure of the graph. Anomaly detection in attributed networks is a crucial task, aiming to identify such anomalies. Existing methodologies use various deep learning techniques using graph neural networks, graph encoder-decoder architectures, and multi-layer perceptions. This study proposes a new approach to improve the existing methods …

Explainable Reinforcement Learning For Network Routing Optimization, Yu Xiu

Master's Projects

Software-defined Networking (SDN) provides a solution for configuring multiple network devices by offering a centralized controller architecture. Network routing is one of the most crucial problems in network configuration. In particular, the surging network traffic demands require efficient routing techniques to load balance communication links. In order to optimize the communication path’s utilization and reduce request blocking, this project utilizes Reinforcement Learning (RL) to decide the routes for given network requests. Furthermore, we adopt Explainable Reinforcement Learning (XRL) to explain the RL learning agent’s decision-making process to enhance the trustworthiness of our approach. In particular, we focus on Feature Importance …

Reinforcement Learning And Hidden Markov Models For Simulating And Analyzing Social Engineering Attacks., Bharkavi Sachithanandam

Master's Projects

The advent of the internet has revolutionized communication and connectivity on a global scale. Now every computer is connected to the internet. Although this technological advancement has made human life easier, this has also led to an increase in sophisticated methods of exploitation. Social Engineering is such a prominent threat to the human community. Social engineering attackers manipulate the victim into giving away sensitive details. Understanding the dynamics of social engineering is crucial for developing measures to help individuals and organizations avoid falling prey to these deceptive tactics. Hence it is essential to understand the attackers. Thus gaining insight into …

Optimizing Web Design Code Generation: A Comparative Study Of Finetuning, Pretrained Models, And Rag (Retrieval Augmented Generation), Srinivas Rao Chavan

Master's Projects

Website Creation is revolutionized by automated code generation, reducing the development effort, speeding the production process, and ensuring consistency in design. Automated web design code generation has emerged as a transformative tool bridging the gap between design and development. In this research, a website design tool is developed and used to create visual layouts, exporting them as JSON designs. These JSON outputs were then transformed into textual prompts, optimized using established HCI principles and UI/UX rules to ensure consistency, visual hierarchy, aesthetics and minimalistic design, accessibility, user-friendly navigation and flexibility. These generated prompts were fed into large language models for …

Predicting Quality Of Life In Driving Scene Using Image Recognition Techniques And User Group Information, Ployrada Suvarnakuta

Chulalongkorn University Theses and Dissertations (Chula ETD)

This study presents a machine learning approach for predicting perceived urban Quality of Life (QoL) by integrating visual features from street-level imagery with personal attributes, including demographic, socioeconomic, and travel behavior data. Using datasets from Bangkok and London, we trained supervised models—Support Vector Machines and Multilayer Perceptrons—under multiple input configurations to evaluate the contribution of each data type. Results show that combining visual and personal features improves prediction accuracy compared to using visual features alone. Statistical feature selection identified income, education, housing stability, and travel patterns as consistently important predictors, with some variation across urban contexts. These findings underscore the …

Using Ontological Methods To Compare Cybersecurity Maturity Model Certification 2.0 And Cobit 19, Aaron Marshall Ramey

CCAC Theses and Dissertations

Cybersecurity frameworks developed by a variety of organizations and implemented by a much larger collection of organizations differ in their focus and application. Whether designed by a private or government organization, the primary goal is to provide a framework to assess and reduce risk. The Department of Defense (DoD) has recently implemented the second version of the Cybersecurity Maturity Model Certification (CMMC 2.0). In some situations, compliance with CMMC 2.0 has already become mandatory for the Defense Industrial Base (DIB). Compliance will soon be required for all Large Businesses (LB) and Small Businesses (SB) within the DIB. While COBIT 19 …

Combating Disinformation On Social Media Networks With Media And Information Literacy Training For Social Media Network Users, Oscar Kwok Chao Ho

CCAC Theses and Dissertations

In the Internet age, social media networks (SMNs), such as Facebook (FB), Instagram (IG), and Twitter (TW), have gained popularity and become an essential part of human life. SMNs provide ease of connection to family, friends, and communities; however, they increase the chances social media network users (SMN users) will disclose private information (PI), causing critical harm to SMN users’ information privacy (IP). Furthermore, SMN users are exposed to significant amounts of disinformation, misinformation, or fake news, which they share without realizing the information is untrustworthy.

The goal of this developmental research was to investigate, examine, and understand the effects …

A Technique For Visualization Of Multivariate Categorical Data, Janice James

CCAC Theses and Dissertations

Multivariate Categorical Data (MCD) plays a significant role in many industries, and the ability to understand the data is critical for insight and decision making. Visualization is a key tool for understanding the data. This dissertation designed and implemented a novel technique for visualizing MCD called Pivoting Parallel Charts (PPC). The design of PPC was informed by studying several existing MCD visualization techniques.

PPC visualizes MCD as a sequence of parallel axes with affixed bar charts. A user-specified axis, called the pivot, acts as the crucial point of consideration for all data relationships. The bar charts are color-coded by the …

Algorithms For Coordinating Multiple Autonomous Vehicles Under Various Constraints With Emphasis On Workload Balancing, Abhishek Patil

Dissertations, Master's Theses and Master's Reports

This dissertation focuses on developing algorithms to solve the problem of coordinating multiple autonomous vehicles under various constraints, aiming to produce practical solutions for real-world applications. Built upon three journal publications addressing two coordination-related problems in different domains, this research document tackles the challenges of heterogeneity constraints and cable entanglement issues encountered by autonomous vehicle systems.

The first problem tackles task allocation and path planning for heterogeneous ground mobile vehicles operating in a 2D environment with asymmetric travel costs. By enhancing previous Primal-Dual approximation heuristic methods, novel techniques are introduced to manipulate dual variables and achieve balanced workload distribution, ultimately …

Specification And Implementation Of Arm Isa Using Adl, Jonathan A. Rabideau

Dissertations, Master's Theses and Master's Reports

In this project, we implement a specification of ARM ISA using the ADL system. Current progress includes 79% of planned instructions, 79% of which are complete for our purposes, and also includes components such as a proxy kernel and a temporary preprocessor. Simple programs compiled directly from gcc can already be properly assembled and simulated using the tools generated by ADL. Once the specification is complete, we can integrate it with other components for testing ideas and theories. This report covers our progress and future plans regarding this project, including some background material and problem solutions.

Enhancing Iot Security: Optimizing Anomaly Detection Through Machine Learning, Maria Balega, Waleed Farag, Xin-Wen Wu, Soundarararjan Ezekiel, Zaryn Good

Computer Science Articles

As the Internet of Things (IoT) continues to evolve, securing IoT networks and devices remains a continuing challenge. Anomaly detection is a crucial procedure in protecting the IoT. A promising way to perform anomaly detection in the IoT is through the use of machine learning (ML) algorithms. There is a lack of studies in the literature identifying optimal (with regard to both effectiveness and efficiency) anomaly detection models for the IoT. To fill the gap, this work thoroughly investigated the effectiveness and efficiency of IoT anomaly detection enabled by several representative machine learning models, namely Extreme Gradient Boosting (XGBoost), Support …

A Robust Form Understanding System Using Graph-Based Neural Network, Chavin Chuangchaichatchavarn

Chulalongkorn University Theses and Dissertations (Chula ETD)

In this work, we address the challenge of form understanding in real-world documents affected by OCR noise and layout uncertainty. We introduce TONDFU, a bilingual Thai and English dataset consisting of official documents such as vehicle registrations and utility bills, annotated for entity labelling and entity linking. We also introduce a noisy character feature extractor that captures lexical and spatial patterns to improve the model's robustness against noisy textual content. This feature is integrated with geometric, visual, and semantic features in the graph-based model. Experiments show that the noisy character feature outperforms the frequency histogram baseline, and with pretraining on …

Assessing Performance Optimization Strategies In Cloud-Native Environments Through Containerization And Orchestration Analysis, Daniel E. Ukene

College of Graduate Studies: Theses & Dissertations

This thesis comprises three distinct, yet interconnected studies addressing critical aspects of web infrastructure management. We begin by studying containerization via Docker and its impact on web server performance, focusing on Apache and Nginx hosted on virtualized environments. Through meticulous load testing and analysis, we provide insights into the comparative performance of these servers, adding users of this technology know which webservers to leverage when hosting their webservice along alongside the infrastructure to host it on. Next, we expand our focus to examine the performance of caching systems, namely Redis and Memcached, across traditional VMs and Docker containers. By comparing …

Improvements In Biomedical Image Analysis With Computational Intelligence And Data Fusion Techniques, Akanksha Maurya

Doctoral Dissertations

"An estimated 2 million new cases of basal cell carcinoma (BCC) are diagnosed each year in the United States, making it one of the most common skin cancers. Earlier detection of these cancers enables less invasive biopsies. Clinical detection consists of a preliminary visual observation of these skin lesions by an experienced dermatologist making it a specialized task highly dependent on their time, availability, and resources. Hence, there is a need for automating this process that can assist healthcare staff. In recent years, deep learning (DL) has been used extensively and successfully to diagnose different cancers in dermoscopic images. Telangiectasia …

Deep Learning Techniques For Image Segmentation In Dermoscopic Skin Cancer Images, Norsang Lama

Doctoral Dissertations

"Melanoma is recognized as the most lethal type of skin cancer, responsible for a significant proportion of skin cancer-related deaths. However, early detection of melanoma is essential for successful treatment outcomes. Computer-aided skin cancer diagnosis tools can save lives by enabling earlier detection of skin cancer. Image segmentation is a crucial step in computer-aided diagnosis as it allows the detection of critical features or regions in an image. Thus, an accurate image segmentation method is necessary to create a more precise computer-aided diagnostic tool for skin cancer diagnosis. This dissertation includes investigating and developing deep learning techniques to improve image …

Modeling And Control For Precision Robotic Machining, Patrick Bazzoli

Doctoral Dissertations

"Robots are used in a wide variety of manufacturing applications, but machining applications in which robots can excel are limited by their lower accuracy and stiffness relative to traditional CNC machines. This work is composed of two parts: one to evaluate a robot’s accuracy and one to compensate for the vibrations of the robot due to its lower stiffness.

In order to evaluate whether a robot has the necessary accuracy to perform a given machining task, Paper 1 discusses a novel Model Invalidation method. This methodology provides a statistical framework as well as a measurement strategy for determining if a …

Factors Affecting The Adoption Of Information Technology In Medium And Small Enterprises: A Case Study In Mekong Delta, Vietnam, Thy-Lieu Nguyen-Thi, Duy-Dong Le, Kieu-Chinh Nguyen-Ly, Trung-Tien Nguyen, Mohamed Saleem Haja Nazmudeen

ASEAN Journal on Science and Technology for Development

This research endeavors to discern the determinants influencing the adoption of information technology in the management practices of small and medium-sized enterprises (SMEs) situ-ated within the Mekong Delta region of Vietnam. Leveraging the Unified Theory of Ac-ceptance and Use of Technology (UTAUT), PLS-SEM, and ANN models, this study ranks the pivotal factors that impact the decision to integrate information technology into SME management. The identified factors, in order of significance, encompass (1) Support from State Agencies, (2) Managerial Qualifications, (3) Competitive Landscape, (4) Enterprise Scale, and (5) Employee Qualifications. The investigation encompasses 496 SMEs across the Mekong Delta and evaluates …

An Efficient And Trusted Deep Learning Framework For Real-Time Ppe Detection In Secure Iomt Environment, Anusha Verma

Browse all Theses and Dissertations

Occupationally-acquired infections impact thousands of healthcare workers (HCWs) in the U.S., with many cases preventable through proper use of personal protective equipment (PPE). This study seeks to develop a robust system to enhance PPE compliance and reduce infection risks among HCWs. The objectives of this thesis are twofold: (1) to create a hybrid machine learning model that combines object detection and keypoint detection to ensure correct donning and doffing of PPE, and (2) to design a real-time feedback system using LED indicators and a display interface to offer actionable guidance to HCWs during PPE usage. The goal is to optimize …

An Enhanced Real-Time Object Detection Of Helmets And License Plates Using A Lightweight Yolov8 Deep Learning Model, Mounika Thatikonda

Browse all Theses and Dissertations

Traffic surveillance and enforcement heavily depend on the real-time detection of helmets and license plates, particularly in high-density urban environments. This study presents a dynamic and optimized lightweight model, the proposed G-YOLOv8n, designed for resource constrained edge devices like the Raspberry Pi. By integrating the GhostNet module into the YOLOv8n architecture, this research achieves a nearly 50% reduction in model size and computational load, while maintaining comparable detection accuracy to the original YOLOv8n. These enhancements enable real-time processing capabilities crucial for traffic monitoring operations. The growing demand for real-time, low-power solutions in intelligent transportation systems necessitates lightweight, efficient detection models. …

Thai-English Supported Automatic Speech Recognition For Endoscopic Reporting, Arpanant Saeng-Xuto

Chulalongkorn University Theses and Dissertations (Chula ETD)

This thesis presents the automatic speech recognition (ASR) system for endoscopic reporting that supports Thai-English code-switching. During endoscopic procedures, gastroenterologists are required to use both hands to handle instruments, thereby complicating the real-time documentation of abnormal findings. While recent advances in speech recognition offer promising solutions, existing models face difficulties with Thai-English code-switching and tend to overfit when fine-tuned on limited datasets. To overcome these limitations, we propose an ASR model enhanced with the Mixture of Experts (MoE) technique to improve transcription accuracy. Furthermore, the Named Entity Recognition (NER) model extracts gastrointestinal (GI) terminology from the transcriptions and classifies its …

Enhancing Large Language Models For Thai Legal Chatbots, Supachoke Hanwiboonwat

Chulalongkorn University Theses and Dissertations (Chula ETD)

Currently, developing a Thai legal question-answering system for the general public is highly challenging due to the complex, difficult-to-understand language and the extensive content of legal codes. This research proposes a Thai legal question-answering system designed for the public, aiming to establish best practices for developing effective legal QA systems. To improve performance, we created our own Thai legal QA dataset and incorporated data from various sources. We conducted comparative experiments to identify the most suitable language model for Thai legal contexts, and fine-tuned the models with diverse datasets for enhanced capabilities in legal QA and legal examinations. Additionally, we …

End-To-End Development Of Mandible Reconstruction Using Machine Learning, Nattapon Kamboonsri

Chulalongkorn University Theses and Dissertations (Chula ETD)

Virtual surgical planning (VSP) is a critical step in mandible reconstruction surgery, which involves preoperative planning and implant design to restore mandibular defects. This study focuses on two essential components of VSP: (1) mandible segmentation, specifically the separation of healthy and defective regions, which currently relies on manual annotation, and (2) generation of the complete mandible, where traditional approaches such as mirroring the contralateral side often fail in scenarios involving midline-crossing defects. While recent automated methods have addressed mandible segmentation from CT scans, they typically focus only on binary segmentation and often utilize conventional UNet-based architectures that suffer from limited …

Automated Cecum Identification In Colonoscopy Using Deep Learning Approach, Kittipoom Sutthinuntakorn

Chulalongkorn University Theses and Dissertations (Chula ETD)

Colonoscopy is essential for the early detection and prevention of colorectal cancer. Identifying the cecum is a vital element of this process. However, most existing automated methods rely on still images or temporal cues alone, without incorporating camera motion awareness, and are rarely suitable for real-time use. In this paper, we present a real-time cecum detection method that integrates spatial features, temporal modeling, and camera motion cues. We deploy ConvNeXtV2 for spatial feature extraction, LTContext for temporal modeling, and Depth Anything in Robotic Endoscopic Surgery (DARES) to enhance understanding of endoscope positioning and camera motion. The dataset used in this …