Digital Commons Network^™

Retrieval-Augmented Generation For Survival Analysis In Cancers: Methods And Evaluation On The Surveillance, Epidemiology, And End Results Database, Jyothi Vaidyanathan

Master's Projects

Healthcare is one of the most important fields that benefits from advancements in Artificial Intelligence (AI). From classic models like linear regression to cuttingedge transformers, AI is applied across various healthcare subdomains, such as drug discovery, predictive analytics, and personalized medicine, to name a few. These techniques enable medical practitioners to make more informed decisions, significantly improving both the speed and accuracy of diagnoses and treatments. Machine learning has played a transformative role in oncology, especially in areas like early detection, diagnosis, treatment planning, and patient monitoring, by analyzing medical images, clinical information, genomic data, sensor information. Our research aims …

Human Vs. Llm: Interpreting Emotion From Neutral Faces In Contextually Charged Backgrounds, Sai Mounika Peteti

Master's Projects

In this study, we investigate the intersection of cultural context, visual perception, and implicit bias in interpreting neutral human expressions. Specifically, we explore how emotionally charged backgrounds can shape viewers interpretations of neutral facial expressions. Using an experimental setup, participants are shown neutral human portraits paired with varying background types ranging from emotionally neutral or pleasant to evocative scenes. Participants are tasked with selecting which background best matches the emotional state of the person depicted in the portraits. Eye-tracking data is collected to analyze visual attention patterns and cognitive processing. In parallel, we also evaluate how large language models (LLMs) …

Characterization Of Cancer Cell Migration Through Brain Vascular Endothelium Model, Malak Taysser Al-Noubani

2025 Fall Honors Capstones Projects - Archive

One of the hallmarks of cancer is increased vessel growth to feed the tumor’s rapid expansion. The newly formed blood vessels are immature and often leaky due to structural and functional abnormalities. This leads to ineffective anti-cancer drug delivery and provides tumor cells with additional opportunities to metastasize. We propose to develop an in vitro vascular endothelium model and introduce aggressive triple-negative breast cancer (TNBC) cells to mimic the tumor environment, utilizing a Transwell migration assay. The impact of TNBC cells on vessel permeability will be assessed by staining for tight junction proteins, and the migratory capabilities of TNBC cells …

Ai-Powered Image-Based Assessment Of Pressure Injuries Using You Only Look Once (Yolo) Version 8 Models, Mehedi Hasan Tusar, Fateme Fayyazbakhsh, Niloofar Zendehdel, Eduard Mochalin, Igor Melnychuk, Lisa Gould, Ming C. Leu

Mechanical and Aerospace Engineering Faculty Research & Creative Works

Objective: The primary objective of this study is to enhance the detection and staging of pressure injuries using machine learning capabilities for precise image analysis. This study explores the application of the You Only Look Once version 8 (YOLOv8) deep learning model for pressure injury staging. Approach: We prepared a high-quality, publicly available dataset to evaluate different variants of YOLOv8 (YOLOv8n, YOLOv8s, YOLOv8m, YOLOv8l, and YOLOv8x) and five optimizers (Adam, AdamW, NAdam, RAdam, and stochastic gradient descent) to determine the most effective configuration. We followed a simulation-based research approach, which is an extension of the Consolidated Standards of Reporting Trials …

C 3 An: Custom, Compact And Composite Ai Systems - A Neurosymbolic Approach: 4Th-Generation Evolution Of Intelligent Systems, Amit P. Sheth, Kaushik Roy, Revathy Venkataramanan, Venkatesan Nadimuthu

Publications

Artificial Intelligence (AI) systems continue to evolve rapidly. From the architecture perspective, it is evolving from large, monolithic models trained on massive internet data to complex, multi-component “compound” systems and “agentic” frameworks capable of semi-autonomous decision-making. These systems show immense promise yet face numerous challenges in reliability, consistency, transparency, and alignment with user goals. In this article, we propose Custom, Compact and Composite AI with Neurosymbolic (C3AN) approach, a framework that paves way to 4th-generation of AI that integrates data, knowledge, and human expertise to build robust, intelligent and trustworthy AI systems defined by 14 foundation elements.

Custom emphasizes …

Investigation On The Tribological Properties Of Al2o3-Tic Substrates In Fixed Abrasive Lapping For Data Storage Application, Benjie Fernandez

Chulalongkorn University Theses and Dissertations (Chula ETD)

Alumina titanium-carbide (Al2O3-TiC) or simply AlTiC substrates were widely used in the magnetic recording industry for their superior mechanical and tribological properties. This study investigated the effect of AlTiC substrate properties in slider lapping tribology. Two types of AlTiC substrates, Type-A AlTiC and Type-B AlTiC equipped with an electro lapping guide (ELG), fully functional reader and writer devices were used in the study. Type-A AlTiC was found to have higher hardness and lower coefficient of friction resulting to lower lapping material removal rate and smoother surface finish. The difference in mechanical properties were attributed to the crystal structure and chemical …

Synthesis Of Fes2 And Fes2-Mns2 Composite Nanostructured Photocatalysts For Dye Degradation, Septian Budiman

Chulalongkorn University Theses and Dissertations (Chula ETD)

This research addresses the environmental challenge of synthetic dye pollution by developing and evaluating novel photocatalysts. Iron pyrite (FeS2), an abundant and low-cost semiconductor, is a promising candidate for photocatalysis, but its practical application is severely limited by its high instability and susceptibility to photocorrosion under light irradiation. To overcome this limitation, this study investigates the synthesis of bare FeS2 nanoparticles and their modification with MnS2. FeS2 nanoparticles were first synthesized via a hydrothermal method at 180°C, using FeSO4·7H2O and Na2S2O3·5H2O precursors. Subsequently, a FeS2-MnS2 material was synthesized using a facile reflux method, with optimal conditions identified as 3 hours …

Automated Infinite Combos Detection System For Collectible Card Game, Amornpong Trakarnkulphun

Chulalongkorn University Theses and Dissertations (Chula ETD)

In Collectible Card Games, resources management is one of the most effective strategy. However, there are some combinations of cards which produce unlimited resources called infinite combos. Too-cheap infinite combos that can be played early in the game break game environment, because the player who executes the combo immediately wins. To solve the problem, game designers usually restrict a part of the combos from being played. Due to the large number of cards in the card pool, it is difficult to search for these combos and solve this problem before a release date of a card set. This research aims …

Effect Of Solvent On Nonanoic And Azelaic Acids Yield Enhancement From Oxidative Cleavage Of Oleic Acid, Chakreeya Santhadklang

Chulalongkorn University Theses and Dissertations (Chula ETD)

This study investigates the effect of solvent choice on the oxidative cleavage of oleic acid using hydrogen peroxide (H2O2) as the oxidant, with a focus on improving the yields of nonanoic acid (NA) and azelaic acid (AA). Solvent selection was found to play a critical role due to polarity differences between the reactants and oxidants. tert-Butanol was unsuitable because of its low boiling point, leading to the evaluation of higher-boiling solvents including guaiacol, acetoin, ethyl lactate, and isobutyric acid. Guaiacol and acetoin exhibited undesirable chemical reactivity, while ethyl lactate resulted in low yields due to hydrogen bonding with intermediate species. …

Enhancing Performance Of Lstm For Water Level Forecasting In Lower Mekong River With Feature Selection Strategy, Chanreng Sey Nhim

Chulalongkorn University Theses and Dissertations (Chula ETD)

This study addresses key research gaps, including the lack of systematic feature selection, structured hyperparameter optimization, and comprehensive long-term and cross-location performance evaluation in the Lower Mekong River Basin to enhance the water level forecasting performance. The research has utilized a Vanilla Long Short-Term Memory (LSTM) network trained on 22 years of historical water level data from the Mekong River Commission (MRC) and 16 localization meteorological features from Open-Meteo. The methodology uses Grid Search optimization for hyperparameter tuning and employs the Spearman rank correlation coefficient as a filter feature selection technique to identify relevant input variables and minimize redundancy. Performance …

Experimental Investigation Of Surfactant Impact On Surfactant-Oil-Brine System For Surfactant Enhanced Oil Recovery, Chananpat Worpattanaluk

Chulalongkorn University Theses and Dissertations (Chula ETD)

Enhanced Oil Recovery (EOR) is a vital technique for improving hydrocarbon extraction efficiency from mature or low-production reservoirs. Among various EOR methods, chemical flooding, particularly surfactant-based EOR, has gained attention due to its ability to reduce interfacial tension (IFT), to alter rock wettability, and to mobilize trapped oil. However, the performance of surfactant systems is highly sensitive to reservoir salinity, temperature, and rock-fluid interactions, leading to surfactant precipitation, adsorption losses, and interfacial tension reduction. Therefore, understanding the effects of salinity, surfactant concentration, and the role of scale inhibitors on the physicochemical stability of surfactant-oil-brine systems is essential for designing robust …

Efficient Photocatalytic Hydrogen Evolution Via Novel Syntheses Of Srtio₃/G-C₃N₄ Heterojunction Photocatalysts, Chiramet Thatsanakunlaphan

Chulalongkorn University Theses and Dissertations (Chula ETD)

Strontium titanate/graphitic carbon nitride (SrTiO3/g-C3N4) heterojunctions are widely used as photocatalysts. However, traditional multistep synthesis methods for these photocatalysts often involve complexity, long processing times, and high energy consumption. To address these issues, a systematic comparison of various simplified synthesis approaches was conducted, emphasizing the influence of synthesis parameters on the structural properties and hydrogen evolution performance. Six comparative studies were conducted to illustrate the roles of solvent choice, thermal post-treatment, and synthesis route. Results showed that ethylene glycol consistently produced more active photocatalysts than ethanol in both one-pot and two-step solvothermal methods. Non-calcined samples exhibited superior hydrogen evolution activity …

Quality Of Life Prediction For Driving Route Planning System Using Image Recognition And Deep Learning, Intouch Prakaisak

Chulalongkorn University Theses and Dissertations (Chula ETD)

Assessing travel-related Quality of Life (QoL) is a significant challenge due to its reliance on subjective human perception, which is difficult to measure. Traditional studies are often constrained by the limited scope of costly, manual data collection. The significant contribution of this research is the introduction of a new framework that can analyze tourist perception on a large and systematic scale. The novelty of this work lies in the utilization of Google Street View (GSV) as a large-scale visual data source, coupled with the use of a sequence-based model to analyze travel routes, which allows for the simulation of the …

Improving The Availability Of Aluminium Sheath Extrusion Machines In The Cable Industry, Jirathana Vasinyont

Chulalongkorn University Theses and Dissertations (Chula ETD)

Aluminium sheath extrusion machines (AL Seamless) play a critical role in the production of high-voltage cables, ensuring the integrity and quality of electrical transmission infrastructure. However, after commissioning such machines at PD Company was fraught with challenges, including frequent breakdowns, limited machine availability, and production inefficiencies. The underlying issues stemmed from inadequate standard operating procedures (SOPs), insufficient knowledge transfer during commissioning, and suboptimal maintenance practices. To address these challenges, this research applied structured methodologies, including Failure Mode and Effects Analysis (FMEA) to identify critical failure points and root causes, and Total Productive Maintenance (TPM) to improve operational reliability. Knowledge transfer …

Out-Of-Domain Tuberculosis Detection From Chest X-Ray Images Using Meta Learning With Soft Labels, Kanokphat Jinanarong

Chulalongkorn University Theses and Dissertations (Chula ETD)

Automated tuberculosis screening from chest x-ray images could greatly benefit regions with limited medical resources. However, currently available methods could not handle this problem well due to the difference in chest x-ray images in each region caused by the difference in machine and demographics, the possible noise in the available labels, and other reasons. We therefore propose a new machine learning algorithm that could detect tuberculosis with great accuracy on any other data sources by learning from completely different data sources. We used a model-agnostic meta-learning together with a soft label approach, utilizing the meta-gradient to dynamically adjust the soft …

A Study On The Impact Of Superconducting Fault Current Limiteron Arc Flash Hazard In An Industrial System, Kittipong Anantanasap

Chulalongkorn University Theses and Dissertations (Chula ETD)

The increasing integration of distributed generation raises short-circuit current levels, which lead to concerns about equipment overheating, insulation deterioration, and system stability issues. The Resistive Superconducting Fault Current Limiter (R-SCFCL) offers an effective solution by dynamically increasing circuit impedance during faults without affecting normal operation. However, its integration may alter the fault-clearing time of the protection system, which is crucial for arc-flash safety. This study evaluates the impact of R-SCFCL integration on arc-flash hazards in an industrial power system, utilizing DIgSILENT PowerFactory and calculations based on IEEE 1584. Results indicate that while the R-SCFCL effectively reduces arcing current, the incident …

Vehicle Routing Problem With Time Constraint From Multiple Origins To Selective Destinations By Using Genetic Algorithm, Manocha Kruetet

Chulalongkorn University Theses and Dissertations (Chula ETD)

This thesis addresses the vehicle routing problem with time constraints from multiple origins to selective destinations by using a genetic algorithm for efficient path planning. The focus is on optimizing field collection and repossession activities in the financial industry to enhance operational efficiency and customer satisfaction. The proposed approach integrates two main components: a tailored genetic algorithm for multi-objective optimization and a graph neural network for precise travel time estimation. The genetic algorithm is designed to minimize total travel distance or travel time and balance the workload among field collectors, while the graph neural network provides travel time estimates to …

Development Of Defective Tiox And Hfo2-X For Efficient Visible-Light-Driven Photocatalytic Degradation Of Organic Pollutants, Mohammad Rahim Pour

Chulalongkorn University Theses and Dissertations (Chula ETD)

The development of efficient photocatalysts capable of operating under visible light is critical for addressing persistent organic contaminants in wastewater. In this thesis, two complementary strategies are presented that exploit defect engineering and heterojunction construction to enhance charge separation, light absorption, and pollutant degradation. In the first study, titanium oxide quantum dots with a high density of oxygen vacancies were dispersed onto H-Beta zeolite supports via a sono-deposition approach. The zeolite substrate not only enabled uniform distribution of sub-5 nm TiOx particles, but also promoted pre-accumulation of cationic dyes, which significantly improved their subsequent oxidation. Structural and spectroscopic analyses confirmed …

Feasibility Study Of Utilization Of Calcium-Based Material For Integrated Methane Dry Reforming And Co2 Absorption-Mineralization Processes, Nattanan Watcharasawat

Chulalongkorn University Theses and Dissertations (Chula ETD)

This thesis investigates an integrated absorption-mineralization and dry reforming of methane (IAM-DRM) loop. The aim is to demonstrate the feasibility of using CaCO3 derived from amine scrubbing both as a CO2 sink and as reactive support for in situ Ni activation during DRM, while simultaneously regenerating the MEA solvent and calcium material for repeated use. CO2 absorption of monoethanolamine (MEA) yield equilibrium loadings of 0.66 mol CO2 mol-1 MEA with regenerated MEA maintaining identical performance. Mineralization on CaCl2 and Ca(OH)2 produced different phases product. Temperature programmed DRM demonstrated that mineralized CaCO3 can activate Ni in situ and sustain CH4 conversion. …

Electrochemical Reduction And Regeneration Of Carbamate, Nattiya Jumpadib

Chulalongkorn University Theses and Dissertations (Chula ETD)

A reliable method for removing carbon dioxide (CO2) gas from industrial emissions involves CO2 absorption into monoethanolamine (MEA) solution to achieve carbon neutrality. However, the regeneration of MEA is costly and still requires heat to release the CO2 that was captured and other processes to manage the CO2 onwards. Our research demonstrates that integrating CO2 capture with electrochemical CO2 conversion reduces regeneration processes and converts CO2 into valuable products. The electrochemical reduction and regeneration of MEA-CO2 adduct (carbamate) were investigated simultaneously by using copper pulse-electrodeposited on copper foils as a cathode in a microchannel reactor. The gas products were analyzed …

Effect Of Catalyst Bed Configuration On Temperature Profile And Reactor Performance For Fischer-Tropsch Synthesis : A Computational Fluid Dynamics Simulation, Natthasit Khawyen

Chulalongkorn University Theses and Dissertations (Chula ETD)

This research investigates the performance of the Fischer–Tropsch reaction in a fixed-bed reactor packed with spiral-structured catalysts using COMSOL Multiphysics to evaluate heat management, hot spot reduction, and the enhancement of high-value product selectivity. The study comprises two main scenarios. The first examines the effects of tube spacing and number of tubes in a multitube reactor arranged in a hexagonal pattern using a 20% Co/SiO₂ spiral-structured catalyst. In models R1–R4, which contain a fixed number of 10 tubes, tube spacing was found to have only a limited influence on temperature distribution; all models still exhibited a hot spot near the …

Performance Evaluation Of Strategic Bandwidth Block Assignment For Interference Reduction In High-Density 5g Nr Cell Environments, Pasapong Wongprasert

Chulalongkorn University Theses and Dissertations (Chula ETD)

Due to the increasing demand for mobile data, mobile network operators (MNOs) typically rely on cell densification to increase capacity. However, doing so also introduces more inter-cell interference (ICI), leading to lower spectral efficiency and making further capacity enhancements challenging. This thesis explores a bandwidth block assignment method for ICI mitigation. The core idea is to divide the bandwidth of an NR carrier into two partially overlapping bandwidth parts (BWPs) to reduce the impact of ICI. By allowing the two BWPs to share the same synchronization signal block (SSB), the same attach and handover configurations can be applied. A modified …

Tailoring The Intrinsic Properties Of Polypropylene/Polypropylene Carbonate Blends Using Epoxidized Natural Rubber As A Bio-Based Compatibilizer, Patsita Suphansomboon

Chulalongkorn University Theses and Dissertations (Chula ETD)

The goal of this study was to enhance the biocompatibility of polypropylene/polypropylene carbonate (PP/PP) polymer blends by varying amounts of epoxidized natural rubber (ENR). This study focuses on determining how ENR concentration affects the interface and final properties of the polymer blend. A comprehensive analysis of the physical, mechanical, thermal, chemical, and dynamic mechanical properties, as well as the rheological properties of the PP/PPC system, was conducted to assess structural changes and property evolution within the PP/PPC system. The experimental results revealed that ENR can interact with PPC, resulting in a reduced domain size and a more uniform distribution. This …

Behavior Of Reinforced Concrete Beams With Externally Anchored Rebars, Nyan Soe Lynn

Chulalongkorn University Theses and Dissertations (Chula ETD)

This study investigates a minimally invasive rehabilitation method for reinforced concrete (RC) beams using externally anchored reinforcement by means of epoxy. Two programs were conducted: flexural rehabilitation using externally anchored longitudinal bars, and shear rehabilitation using externally anchored U-shaped stirrups. Four beam specimens were tested under four-point bending for the flexural program, and four under three-point bending for the shear program. Test results from the flexural program showed large deformation due to plastic hinge formation. Due to their unbonded nature, the external rebars engaged later than the internal reinforcement and developed large deflection. Load-carrying capacity, however, was not increased since …

Evaluating Co2 Storage Criteria : Focusing On Thailand's Petroleum Basins For Carbon Storage, Paul Tivere Benjamin

Chulalongkorn University Theses and Dissertations (Chula ETD)

Anthropogenic carbon dioxide (CO2) emissions from large point sources remain central to Thailand’s climate challenge, and geological carbon capture and storage (CCS) is now included in national mitigation plans. However, Thailand still lacks a transparent way to compare candidate saline aquifers and petroleum basins in terms of storage performance, containment, and socio-economic conditions, while allowing for uneven data quality. This thesis develops a Thailand-specific, two-stage framework that combines threshold-based screening with a multi-criteria ranking framework based on the Analytic Hierarchy Process (AHP) and Data Confidence Scores (DCS). Twenty-one criteria in three groups (capacity and injectivity, containment, and socio-economic constraints) were …

Simulation On Hydrogen Production From Mae-Moh Lignite Coal Gasification, Pitatchai Arunwong

Chulalongkorn University Theses and Dissertations (Chula ETD)

Hydrogen energy has attracted significant attention due to its cleanliness, efficiency, and sustainability. Gasification is considered one of the most promising thermochemical routes to convert coal into high-quality syngas, which can subsequently be utilized for hydrogen production. Mae-Moh lignite, a low-rank coal with low carbon content and high moisture and volatile matter, is selected as the feedstock for this study. This research aims to develop a comprehensive simulation model of a hydrogen production process, integrating gasification, water-gas shift (WGS), acid gas removal, and hydrogen purification using the software simulator. The model predicts hydrogen product gas composition from Mae-Moh lignite under …

A Novel Hydrothermal Synthesis Process Of Mil-53(Al) Using Bamboo Biochar As A Sustainable Precursor For Co₂ Adsorption, Pisit Phayutcharoenkun

Chulalongkorn University Theses and Dissertations (Chula ETD)

Among the numerous MOFs members, MIL-53 (Al) framework is one of the most interesting structures due to the breathing effect and has been widely investigated for hydrogen storage and water treatment. It is built up by the interconnection of infinite trans chains of corner-sharing AlO4(OH)2 octahedral by 1,4-benzenedicarboxylate ligands. MIL-53 crystallizes in a “wine rack” structure (Pnma, a = 17.129(2) Å, b = 6.628(1) Å, c = 12.182(1) Å, α = β = γ = 90°) with large internal pores held open by excess solvent and unreacted ligand in the as-synthesized state. Another challenge is the synthesis process and raw …

Suppressing Bromine Volatilization In Anthraquinone–Bromine Flow Batteries Using A Low-Cost Quaternary-Ammonium Complexing Agent, Prapassorn Areebumrungsuk

Chulalongkorn University Theses and Dissertations (Chula ETD)

The deployment of anthraquinone-bromine redox flow batteries (AQBFBs) is hindered by the volatilization and corrosiveness of bromine (Br2), which elevates safety risks, causes active species loss, and reduces Coulombic Efficiency (CE). This study investigates the use of the low-cost additive 3-chloro-2-hydroxypropyltrimethylammonium chloride (CHA) as a bromine-complexing agent to mitigate these issues. The CHA additive utilizes a quaternary ammonium group to electrostatically associate with bromine and polybromide species, forming stable CHA-Brn complexes. Simultaneously, its hydroxyl functionality enhances solubility in the aqueous electrolyte, which promoted the self-recovery of this oil phase to the aqueous phase and, in turn, suppresses bromine vapor pressure …

Properties Modification Of High-Density Polyethylene Blending With Polypropylene Carbonate-Grafted-Stearic Acid, Suphiriya Khongphom

Chulalongkorn University Theses and Dissertations (Chula ETD)

The purpose of this study is to improve the mechanical properties of high-density polyethylene (HDPE) by incorporating it with polypropylene carbonate-grafted-stearic acid (PPC-g-ST). PPC was modified with stearic acid to enhance interfacial adhesion and compatibility between HDPE and PPC. The blends were prepared using an internal mixer at 160°C with a rotation speed of 60 rpm for 8 minutes. PPC-g-ST was added to PPC at 3, 5, 7, and 10 wt% contents. FTIR confirmed the formation of ester linkages between the carboxylic groups of stearic acid (ST) and the hydroxyl groups of PPC through the appearance of characteristic absorption bands. …

Development Of Microfluidic Device To Monitor The Contamination In Drinking Water Using Impedance Spectroscopy, Pornpipat Oupchan

Chulalongkorn University Theses and Dissertations (Chula ETD)

Microplastic contamination is a growing concern, as microplastics have been found in brain tissue and can enter the body through consumption. The objective of this research is to develop a microfluidic device to monitor microplastic particles by using electrical impedance spectroscopy principles. The device operates based on a flow-through principle. The configuration of electrode consists of copper-based cylindrical electrode with diameter of 300 micrometer and a center-to-center spacing of 2000 micrometer. The electrodes are designed to be replaceable. The microchannel has a rectangular cross-section with a width of 2000 micrometer and a height of 1000 micrometer. The microfluidic device was …