Digital Commons Network^™

A Bibliometric Analysis Of Pat-Seig Evolution As An Alternative Energy Generation Method, Emanuel J. Nyirenda

Tanzania Journal of Engineering and Technology (TJET)

Pumps as Turbines (PATs) coupled with Self-Excited Induction Generators (SEIGs) as an alternative energy generation method have been the subject of significant research in recent years. This paper presents a bibliometric analysis of the evolution of PAT-SEIG technology as an alternative energy generation source. An analysis of a comprehensive dataset of peer-reviewed journal articles, conference proceedings, and patents related to PAT-SEIG systems, using advanced bibliometric techniques and PRISMA to identify key research themes, influential authors, the growth of the field and patterns of collaboration, and changes in research focus over time. Over a publication period of 32 years, a total …

Effects Of Technical Debt On Software Interoperability, Leonard Peter Binamungu

Tanzania Journal of Engineering and Technology (TJET)

Technical debt (TD) refers to sub-optimal development decisions that make the software costly to maintain and evolve. Examples of TD include structural complexity, violation of coding styles, and code complexity. Existing research has investigated the nature, causes and indicators of TD, as well as tools and strategies for managing TD. However, although TD could hinder the ability of a software system to be interoperable with others, existing literature has limited evidence on how TD affects systems interoperability. This limits the ability of software engineering teams to manage TD in ways that do not hinder systems interoperability. To fill this void, …

Towards A New Era Of Surgery Using Intelligent Robot, Ahmed Mahfouz, Hassan A. El Gamal, T. Awad, M.B. Badawi

Journal of Engineering Research

This research aims to overcome the difficulties of surgical tumor removal, especially in brain tumors that needs precision and time saving of the operations. The traditional surgical approach often is slow and targeting accurate manual cutting of the tumor, which is time-consuming and increase the risk to the patient. The error in cutting the deep layers of the tumor can occur, which increase the cost and dangerous for the patient.

To overcome these challenges, a proposed solution involves designing a robot that can quickly and accurately remove tumors by following their contours as it comes from the medical imaging data, …

A Survey On Food Ingredient Substitutions, Hyunwook Kim, Revathy Venkataramanan, Amit P. Sheth

Publications

Diet plays a crucial role in managing chronic conditions and overall well-being. As people become more selective about their food choices, finding recipes that meet dietary needs is important. Ingredient substitution is key to adapting recipes for dietary restrictions, allergies, and availability constraints. However, identifying suitable substitutions is challenging as it requires analyzing the flavor, functionality, and health suitability of ingredients. With the advancement of AI, researchers have explored computational approaches to address ingredient substitution. This survey paper provides a comprehensive overview of the research in this area, focusing on five key aspects: (i) datasets and data sources used to …

Maxwell's Second Equation: The Gauss's Law For Magnetostatic Fields, Ashanthi Maxworth Phd

EM Fields With Prof. Maxworth

Gauss's Law for magnetostatic fields says that the total magnetic flux through a closed surface is equal to zero. In otherwords, there are no magnetic monopoles. This law has been applied in multiple mathematical derivations. Watch the short video where Dr. Maxworth explains this law. In the worksheet you can observe the magnetic flux generated due to a current through a straight coaxial cable. Note that the magnetic flux always exisit as close loops making the total net flux through a closed surface zero and the direction of the magnetic field can be derived by the right hand rule, i.e …

Smart Homes, Grids, And Electric Vehicles Large-Scale Integration Studies Employing Machine Learning And Optimization Techniques, Rosemary E. Alden

Theses and Dissertations--Electrical and Computer Engineering

Residential digital twins are fundamental to the smart grid transition, and thus, must be both accurate and representative of existing homes and scalable for large distribution systems. Within this dissertation, new machine learning (ML) and physics-based methodologies are applied to the major individual residential loads, energy storage devices, and resources in the US to develop computationally efficient digital twins and new optimal control strategies for the virtual power plant (VPP) concept. Big data from experimental field demonstrations with dedicated metering, thousands of residential smart meter profiles, and large national human behavior surveys are employed to develop ultra-fast scalable residential load …

Guided-Mode Resonant Nanopatterns For Raman Generation And Photonic Devices, Renjie Chen

Electrical Engineering Dissertations - Archive

This dissertation explores advanced strategies for enhancing Raman amplification in silicon photonic devices, focusing on guided-mode resonance engineering and resonant mode manipulation. Silicon, despite its indirect bandgap, exhibits a strong Raman scattering coefficient, enabling it to function as a viable gain medium for integrated photonic systems. However, the realization of efficient, compact, and low-threshold silicon Raman amplifiers and lasers necessitates innovative design approaches that overcome inherent material and structural limitations.

The first chapter provides a fundamental overview of optics, including physical principles, spectral characteristics, guided-mode resonance, simulation methods, and nanopattern fabrication methods.

The second chapter delves into silicon-based Raman amplification …

Novel Electrophysiological Biomarkers In Pediatric Drug Resistant Epilepsy And Genetic Epilepsy Syndromes, Sakar Rijal

Bioengineering Dissertations - Archive

Pediatric epilepsies, particularly those that are drug-resistant or genetically driven, represent some of the most complex neurological disorders encountered in childhood. Central to their pathophysiology is a disruption in the delicate balance between cortical excitation and inhibition (E/I), often resulting from impaired GABAergic interneuron function. This imbalance manifests as aberrant network dynamics and altered neural oscillations, giving rise to seizures and long-term cognitive impairments. In this thesis, we developed a translational framework to identify electrophysiological biomarkers that (i) assess cortical E/I imbalance and (ii) map epileptogenic zones, with the aim of enhancing diagnosis, guiding surgical planning, and informing therapeutic monitoring …

Vision Of Nuclear Power Deployment In Latin America And The Caribbean: A Focus On Small Modular Reactors And The Regional Experience Of Central Argentina De Elementos Modulares, Alejandra Loreto Alfaro, Florencia Rentería, Camila Araujo

International Journal of Nuclear Security

Increasing the number of nuclear power reactors in the Latin American and Caribbean region presents technical, financial, regulatory, and environmental challenges. Focused on fostering economic stability, growth, and human capacity development, the deployment of small modular reactors (SMRs) emerges as a key aspect in the region’s energy landscape. The emergence of SMRs represents an opportunity for multidisciplinary cooperation among different sectors. To comprehensively address the challenges related to the protection of nuclear facilities in the region, the Tlatelolco Treaty and the Non-Proliferation Treaty should be strengthened as legally binding instruments to enforce the safety and safeguarding principles integral to the …

Autonomous Vehicle Platooning, Tony Abelson

McNair Summer Research Program

This research investigates the construction and performance optimization of two autonomous vehicles with using "Platooning," a strategy aimed at reducing fuel consumption and enhancing transportation efficiency. Platooning allows one vehicle to follow another closely, minimizing aerodynamic drag and improving fuel economy. This study addresses the growing need for sustainable transportation solutions in the context of increasing urbanization and environmental concerns, emphasizing the importance of efficient autonomous vehicle operation. The primary objectives of this research are to assemble autonomous vehicles from scratch and to optimize their performance in both individual and platoon operations. The methodology involves using Traxxas Slash chassis and …

Photonic Crystal Devices For Chip Scale Sensing Systems, Yudong Chen

Electrical Engineering Dissertations - Archive

This thesis investigates the design and integration of photonic crystal (PC) structures for compact, high-performance optical platforms, with a focus on applications in gas sensing, on-chip lasers, and flat optics. Chapter 1 introduces the fundamental principles of PC design and simulation, highlighting their potential to replace bulky components in micro-gas chromatography (µGC) systems through miniaturization and integration. Chapter 2 explores PC-based nanobeam lasers, including the Lambda-Scale Embedded Active-Region Photonic Crystal (LEAP) laser, which demonstrates strong optical confinement and energy-efficient operation, with energy consumption as low as 8 fJ/bit. These laser designs are evaluated for their suitability in low-power, high-speed on-chip …

Medical Ai: Solving Healthcare Challenges And Inspiring Ai Innovation, Xiaowei Yu

Computer Science and Engineering Dissertations - Archive

Artificial Intelligence (AI) is transforming healthcare by enabling large-scale analysis of medical data and integrating multimodal information for more comprehensive diagnostics. I present my work addressing fundamental and challenging problems in developing state-of-the-art AI models for medical data analysis, including multimodal brain data and other medical datasets. Additionally, I design brain-inspired AI models by integrating insights from organizational principles of brain networks. Specifically, my research tackles three critical aspects: (1) AI in Computational Neuroscience, where I design deep learning models for brain network analysis to uncover the organizational principles of brain networks; (2) Brain-Inspired AI, where I integrate superior brain …

Voltage And Var Control And Real-Time Digital Simulator-Based Protection System Testing For Power Distribution Systems, Gaurav Yadav

Theses and Dissertations--Electrical and Computer Engineering

Rising power demand calls for electric distribution systems to manage peak load. One option is reducing feeder voltage, which lowers voltage-dependent load demand and may also reduce energy usage. The technique, known as Conservation Voltage Reduction (CVR), may operate independently or within a volt/var control system. This dissertation examines CVR factor calculation using measurements collected at the substation, and proposes a curve-fitting and artificial neural network method to estimate active power losses using input active power, reactive power, and substation voltage. As utilities integrate more inverter-based resources (IBRs) to support increasing demand, rapid voltage fluctuations arise due to the intermittent …

Characterization And Profile Considerations Of Nickel-Zinc Energy Storage Under High-Power And Pulsed Loads, Benjamin P. Schmitz

Electrical Engineering Theses - Archive

There are many types of energy storage devices that are available for driving high-power electrical loads. Choosing the right chemistry is difficult and factors such as energy density, power density, safety, cycle life, and recharge rate are among the many that must be considered. Lithium-ion batteries (LIB) possess the highest combined power and energy density, making them an attractive option for many applications. Previous studies at the Pulsed Power and Energy Lab (PPEL) characterized lithium-iron-phosphate (LFP) and lithium-titanate-oxide (LTO) battery chemistries. LFP’s and LTO’s have modest power density, modest energy density and modest cycle life. However, there is still potential …

Evaluation Of Electric Vehicle Batteries For Enabling High Power Loads, Maxton K. Manker

Electrical Engineering Theses - Archive

The growing demand for high-power energy storage systems in applications such as artificial intelligence (AI) data centers, industrial backup systems, and grid-level stabilization efforts presents new challenges in technology selection. These loads have a uniquely high continuous or transient power demand that can impact the stability of the electric grid. To mitigate these challenges, energy storage in the form of batteries or supercapacitors has been proposed either as stand-alone or as intelligently controlled grid buffering sources. These same types of energy storage are commonly found in electric vehicles (EV) where they must respond to abrupt throttle and braking behavior, similar …

Smart Irrigation System Using Iot And Lstm For Optimal Water Management, Farley Y. Ruiz

Electrical Engineering Theses - Archive

This thesis presents the design and implementation of a smart irrigation system that combines Internet of Things hardware with a Long Short-Term Memory (LSTM) neural network for predictive soil moisture management. The goal is an affordable and reliable solution that uses real-time sensor data and environmental data to schedule irrigation before the substrate moisture drops below its target range. The system integrates soil moisture, temperature, humidity, and sensors on an Arduino Nano that communicates wirelessly with a Raspberry Pi. The Raspberry Pi runs a Python/Flask backend that collects and processes data, executes the LSTM model, and serves a secure web …

Auto-Tuning And Applications Of Transient Voltage Suppressor Models In Full-Wave Simulations, Daniel Peter Szanto

Masters Theses

System efficient electrostatic design (SEED) combines full-wave geometry information with SPICE models of non-linear protection devices, typically transient voltage suppression (TVS) diodes, to allow optimization and validation of electrostatic design (ESD) protection early in the design process. TVS models have previously been developed which may be used in SPICE simulation tools like Keysight ADS, but these models could not be used directly in full-wave simulation tools like CST Studio. A process was developed for converting existing ADS models of TVS devices to a form that can be used within a CST full wave/SPICE hybrid simulation. Three TVS models were converted …

Enhancing Irs Localization Via Ml-Driven Aoa And Distance Estimation, Nikhila Kotlapara Surendran

Theses and Dissertations

Intelligent Reflecting Surfaces (IRSs) are transforming next-generation wireless networks by enabling dynamic control of the propagation environment for improved localization and security. This thesis advances Angle-of-Arrival (AoA) and distance estimation in IRS-assisted systems using a hybrid architecture with active sensing and passive reflecting elements. A modified MUSIC algorithm, optimized for near-field localization, decouples 2‑D AoA and 1‑D range estimation using a grid-and-peak pseudo-spectrum scan, achieving sub-degree AoA (0.003 rad) and sub-meter range (0.05 m) accuracy with over 100× lower complexity than classical 3D MUSIC.

The study further applies the algorithm to the DeepMIMO dataset (O1_28 scenario, 3.5 GHz) using …

Revealing Spatiotemporal Neural Activation Patterns In Electrocorticography Recordings Of Human Speech Production By Mutual Information, Julio Kovacs, Dean Krusienski, Minu Maninder, Willy Wriggers

Mechanical & Aerospace Engineering Faculty Publications

Background

Spatiotemporal mapping of neural activity during continuous speech production has been traditionally approached using correlation coefficient (CC) analysis between cortical signals and speech recordings. A prior study employed this approach using electrocorticography (ECoG) data from participants who underwent invasive intracranial monitoring for epilepsy. However, CC cannot detect nonlinear relationships and is dominated by the correspondence between periods of silence and of non-silence.

New Method

We introduce the mutual information (MI) measure, which can capture both linear and nonlinear dependencies. We validated CC and MI on the sub-second spatiotemporal brain activity recorded during continuous speech tasks. To refine the results, …

A Large Electroencephalogram Database Of Freewill Reaching And Grasping Tasks For Brain Machine Interfaces, Bhoj Raj Thapa, John Boggess, Jihye Bae

Electrical and Computer Engineering Faculty Publications

Brain machine interfaces (BMIs) offer great potential to improve the quality of life for individuals with neurological disorders or severe motor impairments. Among various neural recording modalities, electroencephalogram (EEG) is particularly favorable for BMIs due to its noninvasive nature, portability, and high temporal resolution. Existing EEG datasets for BMIs are often limited to experimental settings that fail to address subjects’ freewill in decision making. We present a large EEG dataset, containing a total of 6808 trials, recorded from 23 healthy young adults (eight females and 15 males with an age range from 18 to 24 years) while performing reaching and …

Speed Variation Based Power Regulation Concept For Dynamic Wireless Charging, Donovin D. Lewis, Sudarshan T. Harave, Omer Onar, Mostak Mohammad, Veda Prakash Galigekere, Gui-Jia Su, Dan Ionel

Electrical and Computer Engineering Graduate Research

On-road wireless charging of electric vehicles (EVs) in-motion could potentially reduce range anxiety or battery size with wide-spread deployment. The planning and implementation of such systems are greatly complicated due to their susceptibility to load variation inherent to traffic flow. This paper proposes a method for derisking the potential for traffic slowdowns by compensating for reduced vehicle speed and investigates how implementation may affect system performance. A load modeling case study is presented at 200kW for a mile of high-speed roadway employing speed-based power regulation with results indicating average power usage and maximum car hosting capability can be reduced by …

Multi-Objective Deep Reinforcement Learning For Dynamic Algorithm Selection In Open Ran, Saish Urumkar, Byrav Ramamurthy, Sachin Sharma

Conference papers

Open Radio Access Networks (Open RAN) provide flexible, modular multi-vendor interoperability. Growing mobile data demand requires balancing network performance with power efficiency. Mobile operators need intelligent resource management to achieve Key Performance Indicator (KPI) targets while maintaining operational efficiency. This paper proposes a solution using a multi-objective deep reinforcement learning (MODRL) model deployed on the Open RAN Intelligent Controller (RIC). Three customizable operator profiles (Power Saving, Balanced, and Performance) are used which define specific priority ratios between performance and power saving objectives.

To evaluate, individual algorithms (CPU scheduling and UE connection state switching) are implemented in Open RAN, achieving 5–20%CPU …

Pac-Oran: Power Saving Cpu Scheduling Approach For Scalable Mobile Ues In Open Ran, Saish Urumkar, Byrav Ramamurthy, Somayeh Mohammady, Sachin Sharma

Conference papers

Open RAN is a next-generation wireless network technology that promotes flexibility, cost efficiency, and interoperability through disaggregation and open interfaces. Energy efficiency remains a key challenge, especially in scalable deployments with many connected User Equipments (UEs), where dynamic power management at the gNodeB is critical. In this paper PAC-ORAN (Power-saving Adaptive CPU Scheduling for Open RAN) is proposed which is an advanced CPU scheduling algorithm evaluated with a large number of connected UEs to gNodeb. PAC-ORAN includes an advanced method using moving average adaptive threshold selection and dynamically adjusting CPU core states and frequency tuning based on real-time CPU metrics. …

Performance Evaluation Of Managed Switch Configurations For Secure And Efficient Plc-Based Industrial Automation Networks, Ahmed Salama

All Graduate Theses, Dissertations, and Other Capstone Projects

This thesis explores how managed switches can improve network performance and security in PLC-based industrial systems. Using simulations in GNS3 and Cisco Packet Tracer, and packet analysis via Wireshark, the study compares unmanaged and managed switch configurations. Redundancy protocols, particularly STP and RSTP, are evaluated under failure scenarios. Results show that RSTP offers faster recovery times, making it more suitable for time-sensitive environments. Additionally, managed switch features like VLANs, port security, and MAC filtering significantly reduce vulnerabilities and improve network segmentation. The findings highlight the importance of incorporating both cybersecurity and redundancy in industrial network design as systems move toward …

Nanomaterial-Enabled Enhancements In Thylakoid-Based Biofuel Cells, Amit Sarode, Gymama Slaughter

Center for Bioelectronics Publications

Thylakoid-based photosynthetic biofuel cells (TBFCs) harness the inherent light-driven electron transfer pathways of photosynthesis to enable sustainable solar-to-electrical energy conversion. While TBFCs offer a unique route toward biohybrid energy systems, their practical deployment is hindered by sluggish electron transfer kinetics, unstable redox mediators, and inefficient interfacing between biological and electrode components. This review critically examines recent advances in TBFCs, with a focus on three key surface engineering strategies: (i) incorporation of nanostructured materials to enhance electrode conductivity and surface area; (ii) application of redox mediators to facilitate charge transfer between photosynthetic proteins and electrodes; and (iii) functional exploitation of individual …

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 …

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 …

Bismuth Surfactant-Mediated Epitaxy Of Gaas(Bi) On On-Axis Ge(100) Substrates, Valgeir Sigmarsson

Chulalongkorn University Theses and Dissertations (Chula ETD)

In this work, Bi-surfactant-mediated epitaxy is applied in GaAs(Bi) film deposition on nom- inally on-axis Ge(100) substrates to investigate its effect on mitigating the formation of anti-phase domains (APDs) inherent to the polar-on-non-polar GaAs/Ge(100) heterostructure. GaAs(Bi) layers were deposited by solid-source molecular beam epitaxy (MBE) with a V/III ratio of ~90 and stepwise variations in Bi flux between samples. The Bi-free GaAs sample exhibited an unstable RHEED pattern indicating ill-ordered growth mode, confirmed by AFM showing an amor- phous surface with an RMS value of ~20 nm. In contrast, Bi-assisted growth produced stable RHEED (1×3) surface reconstructions. AFM revealed single-crystal …

การพัฒนาเกมกระตุ้นการรู้คิดด้วยเทคโนโลยีเสมือนจริงสำหรับผู้สูงอายุที่มีภาวะการรู้คิดบกพร่องเล็กน้อย, ธนกร ตันมาลาภรณ์

Chulalongkorn University Theses and Dissertations (Chula ETD)

ภาวะการรู้คิดบกพร่องเล็กน้อยเป็นระยะเปลี่ยนผ่านระหว่างภาวะสมองปกติกับภาวะสมองเสื่อม โดยมีอาการที่เกี่ยวข้องกับความจำ ภาษา การรู้คิด และการตัดสินใจ แต่ยังไม่ส่งผลกระทบต่อการใช้ชีวิตประจำวัน งานวิจัยนี้จึงมุ่งเน้นการนำเสนอแนวคิดการออกแบบเพื่อพัฒนาเกมที่สามารถช่วยกระตุ้นการรู้คิดของคนที่มีภาวะการรู้คิดบกพร่องเล็กน้อย ซึ่งได้ประยุกต์ใช้เทคโนโลยีเสมือนจริงด้วยแว่น Meta Quest 2 ยูนิตีและเบลนเดอร์ถูกใช้ในการพัฒนาเกม เนื่องจากเป็นซอฟต์แวร์โอเพนซอร์สและไม่มีค่าใช้จ่าย เกมถูกออกแบบมาเน้นการกระตุ้นการรู้คิดผ่านการฝึกความจำและการรับรู้ตำแหน่ง โดยผู้เล่นจะต้องจดจำตำแหน่งและสีของเฟอร์นิเจอร์ภายในห้อง และมีการพัฒนาเกมในระบบผู้เล่นหลายคนสำหรับ 2 บทบาท คือ ผู้เคลื่อนย้าย และ ผู้ช่วย เพื่อส่งเสริมการสื่อสารและการทำงานร่วมกัน นอกจากนี้ ยังมีการพัฒนาเกมในรูปแบบเว็บไซต์ควบคู่กันไป เพื่อให้เป็นทางเลือกที่ผู้สูงอายุสามารถเข้าถึงง่าย โดยไม่จำเป็นต้องใช้อุปกรณ์วีอาร์เฉพาะทาง จากอาสาสมัครทั้งบนเวอร์ชันวีอาร์และเวอร์ชันเว็บไซต์ พบว่าเวอร์ชันวีอาร์ให้ความสมจริงและช่วยให้ผู้เข้าทดลองมีสมาธิกับงานด้านความจำและการรับรู้ตำแหน่งมากขึ้น ขณะที่เวอร์ชันเว็บไซต์เข้าถึงง่ายและใช้งานสะดวกสำหรับผู้สูงอายุ โดยรวมแล้วทั้งสองแพลตฟอร์มน่าจะกระตุ้นการรู้คิดได้และได้รับผลตอบรับที่ดีจากอาสาสมัคร

การพัฒนาระบบช่วยประเมินการอ่านแจกลูกสะกดคำไทยเพื่ออ่านโดยการปรับปรุงเทคนิคการประมวลผลภาษาธรรมชาติ, ภูริณัฐ กระจ่างศรี

Chulalongkorn University Theses and Dissertations (Chula ETD)

การแจกลูกสะกดคำถือเป็นพื้นฐานสำคัญที่หลักสูตรการศึกษาขั้นพื้นฐานเริ่มจัดให้มีการเรียนการสอนและการประเมินตั้งแต่ชั้นประถมศึกษาปีที่ 1 แต่ด้วยอัตราส่วนอาจารย์และนักเรียนที่แตกต่างกันมากอาจส่งผลให้อาจารย์ไม่สามารถประเมินการอ่านออกเสียงแจกลูกสะกดคำของนักเรียนได้อย่างทั่วถึง งานวิทยานิพนธ์นี้จึงพัฒนาระบบช่วยประเมินการอ่านแจกลูกสะกดคำไทย ด้วยความซับซ้อนของอักขรวิธีภาษาไทย ซึ่งแตกต่างจากภาษาอังกฤษ ทำให้เกิดปัญหาในการแบ่งกลุ่มตัวอักษรเพื่อสร้างคำอ่านแจกลูกสะกดคำที่ถูกต้องและการถอดข้อความจากเสียงเพื่อประเมินความถูกต้อง งานวิทยานิพนธ์นี้ได้นำเสนอการปรับปรุงเทคนิคการประมวลผลภาษาธรรมชาติ โดยการพัฒนาขั้นตอนวิธีการแบ่งกลุ่มตัวอักษรในคำไทยแต่ละคำอย่างแม่นยำโดยการสร้างพจนานุกรมรูปสระ และใช้การคำนวณทางสถิติของระยะห่างเลเวนชเตย์นในการเลือกโครงสร้างพยางค์ที่เหมาะสมที่สุด หลังจากนั้นระบบได้นำ แบบจำลองภาษาขนาดใหญ่ มาใช้ในการถอดข้อความเสียงการอ่านของผู้เรียน และใช้ขั้นตอนวิธีเกสตัลท์ในการประเมินความถูกต้องของเสียงอ่านอย่างละเอียด พบว่าวิธีการแบ่งกลุ่มตัวอักษรที่เสนอมีความถูกต้องสูงถึง 100% ในชุดข้อมูลคำไทย 708 คำ จากบัญชีคำพื้นฐาน และระบบสามารถจำแนกเสียงอ่านที่ถูกต้องและไม่ถูกต้องได้อย่างมีประสิทธิภาพ โดยมีค่า ความแม่นยำ 89.17%, ความเที่ยง 94.02%, และความไว 89.67% อีกทั้งยังตรวจจับข้อผิดพลาดประเภทวรรณยุกต์และการอ่านเกิน/ไม่อ่านได้แม่นยำ ระบบที่พัฒนาขึ้นมีความได้เปรียบด้านความถูกต้อง ความสม่ำเสมอ และความรวดเร็วเมื่อเทียบกับการประเมินโดยมนุษย์ จึงสามารถช่วยลดภาระการประเมินและเพิ่มโอกาสให้นักเรียนได้รับการสนับสนุนการเรียนรู้การอ่านออกเสียง สำหรับในอนาคตควรมีการปรับปรุงแบบจำลองรู้จำเสียงพูดสำหรับภาษาไทยด้วยข้อมูลเสียงของเด็กประถม การขยายชุดคำทดสอบให้ครอบคลุมคำที่ซับซ้อนขึ้น การพัฒนาในรูปแบบแอปพลิเคชันบนอุปกรณ์พกพา และการประเมินผลในระดับพฤติกรรมการเรียนรู้ของผู้เรียนเพื่อยืนยันผลทางการศึกษา