Engineering Commons^™

Distance Metric Learning Techniques For The Performance Improvement Of Ml-Knn And Ranking-Svm-Based Multi-Label Pattern Classification, Shajee Mohan B. S., Sneha S Mohan

ASEAN Journal on Science and Technology for Development

A multi-label pattern classification system tries to predict the set of class labels of a test example by learning from the training examples with the relevant label sets. Classification that involve datasets having multiple labels found immense of applications in pattern analysis tasks involving image, music and video. A test sample can be labeled to indicate different objects, people, music categories or concepts. Classification problems involving data having multiple labels, have to consider training dataset associated with variety of labels. Multi-label extensions of popular algorithms, kNN and Support Vector Machine (SVM) called Multi-label kNN (ML-kNN) and Ranking-SVM are commonly used …

Neuro-Symbolic Ai: A Future Of Tomorrow, Pankaj Chandre, Parikshit Mahalle, Gitanjali Shinde, Bhagyashree Shendkar, Shraddha Kashid

ASEAN Journal on Science and Technology for Development

Neuro-Symbolic AI: A Future of Tomorrow" explores the convergence of neural learning and symbolic reasoning to advance artificial intelligence (AI) systems. Symbolic reasoning makes use of knowledge representation techniques and rule-based systems, whereas neural learning analyzes data using deep learning models. AI becomes more adept at fusing data-driven insights with deductive reasoning when these methods are integrated using hybrid models and differentiable reasoning techniques. Applications show enhanced diagnostic precision and decision-making skills in a variety of industries, including robotics, healthcare, and finance. To promote responsible AI development, regulatory frameworks and ethical principles address issues like bias and transparency. Future paths …

The Influence Of The Digital Economy On The Ecological Environment And Its Sustainable Development, Xinpan Lyu, Jianhua Dai

ASEAN Journal on Science and Technology for Development

This study aims to examine the impact of the digital economy on ecological sustainability and its development in China from 2000 to 2022. The study focuses on the role of innovation in the digital sector, where the adoption of big data technologies is considered, with reference to sustainable development, from an environmental perspective. A dynamic threshold model and, in particular, the Iterated Generalized Least Squares (IGLS) technique is used to analyze the given data.The research reveals a significant link between adopting digital technologies and managing environmental sustainability efficiently. To investigate the interconnection between the digital economy and ecological goals, it …

Analysis Of The Sustainability Management Of Coral Reef Ecosystem In The Marine Protected Area Of Wediombo, Gunungkidul, Nabilah L. Rohmah, Rika Harini, Sudrajat Sudrajat

ASEAN Journal on Science and Technology for Development

The Wediombo Coastal Area is a Marine Protected Area (MPA) with highly potential in coral reef ecosystems. According to the Millennium Ecosystem Assessment (MEA), coral reefs play a vital role in supporting human life by providing provisioning, supporting, regulating, and cultural services. However, the utilization of this area as a tourist destination and suboptimal management practices have led to the degradation of its coral reef ecosystems. Efective management strategies for the sustainability of coral reefs can have positive impacts across ecological, economic, social, technological, and institutional dimensions. Therefore, this study aims to analyze the sustainability management of coral reef ecosystem …

Potential Of Green Synthesis Of Silver And Gold Nanoparticles For The Management Of Metabolic Associated Steatotic Liver Disease: A Mini Review, Atiqah Suhaili, Ya Chee Lim, Mei Ann Lim, Lee Hoon Lim, Mohammad Mansoob Khan, Monowarul Mobin Siddique

ASEAN Journal on Science and Technology for Development

Metabolic-associated steatotic liver disease is a metabolic disorder with limited pharmacological treatment options and only one approved medication to date. MASLD can be asymptomatic in its earlier stage and hence, prevention of this disease progression is the most effective approach. Recently, green-synthesized nanoparticles, particularly silver (AgNPs) and gold nanoparticles (AuNPs), have gained interest due to their eco-friendly production, biocompatibility, and bioactive properties. This review highlights the biosynthesis of AgNPs and AuNPs using medicinal plant extracts and their reported biological effects relevant to MASLD management including anti-hyperlipidemic, anti-diabetic, antioxidant and anti-inflammatory activities. While findings are promising, further mechanistic studies and preclinical …

Improving Ethanol Purity By Methanol Adsorption Using Mcm-41: A Study Of Kinetics And Thermodynamics For Industrial Applications, Ali A. Yahya, Nisreen S. Ali, Basma B. Hameed, Talib M. Albayati, Issam K. Salih, Riyadh S. Almukhtar, Narges Elmi Fard

ASEAN Journal on Science and Technology for Development

One of the by-products of the fermentation process that produces ethanol, which is mostly utilized in industry and food, is methanol. For methanol adsorption in batch operations, mixed amines modified (MCM-41) was utilized. A batch adsorption technique loaded with MCM-41 sorbent was used in the study to separate methanol from ethanol. This study used methanol at varying initial concentrations (40-80 mg/L). As a result, the effect of temperature, duration of adsorption, amount of adsorbent and initial concentration of pollutant in the field of ethanol alcohol purification using MCM-41 was investigated through the adsorption mechanism. In addition, first and pseudo-second order …

Kadysnet: A Novel Approach To Dyslexia Prediction In Children: Combining Handwritten Text Recognition With A Hybrid Cnn-Bilstm-Ctc Model And Personalized Learning Strategies, Shailesh Prabhakar Patil, Ravindra Sadashivrao Apare, Ravindra Honaji Borhade, Parikshit Narendra Mahalle

ASEAN Journal on Science and Technology for Development

This study introduces a novel approach for early dyslexia detection in children through automated handwriting analysis, integrating a hybrid CNN-BiLSTM-CTC architecture with personalized learning strategies. Our method combines a custom CNN-BiLSTM-CTC model with tailored educational interventions to support dyslexic learners. We analyzed children's handwritten text images in English, collected from specially designed tests involving word rewriting, sentence reconstruction, and paragraph composition, particularly challenging tasks for dyslexic individuals. Notably, our CNN-BiLSTM-CTC model achieved the best result with an accuracy of 97.67%, outperforming other architectures. Compared to pre-trained models like EfficientNetB7, DenseNet121, and MobileNetV2, our custom CNN-BiLSTM-CTC model demonstrated superior performance. Key …

Leveraging Strategic Information Systems For Competitive Advantage: A Case Study Of Veolia As A Multinational Enterprise, Sohail Nawaz Sabir

ASEAN Journal on Science and Technology for Development

Instead of examining several components that link planning and strategy implementation, researchers have focused on the alignment of IT and business, as well as the Strategic Information Systems Planning (SISP) process. The goal of this study is to examine several approaches that can close the gap between IT project planning and execution. Therefore, the primary objective of the proposed study is to examine SISP implementation strategies that can be theorized in the context of Veolia, a global multinational corporation (MNC). The primary aspects influencing the SISP for this study are the frequency of planning, the function of IT/business managers, assessment …

Numerical And Experimental Investigation Of Mechanical Performance, Interface Pressure Distribution, And Structural Safety Of Glass Fiber-Reinforced Below-Knee Prosthetic Sockets, Saif M. Abbas, Kadhim K. Resan, Mohammed Ali Abdulrehman, Ali M. Flayyih

ASEAN Journal on Science and Technology for Development

In this study, below-knee prosthetic sockets reinforced with glass-fiber composites were investigated experimentally and numerically. In compliance with the ASTM guidelines, two lay-up configurations were constructed and tested for tensile and fatigue strengths. During the gait trials, the F-socket system was used to measure the interface pressure distribution. Stress, deformation, and safety factor responses under physiological loading conditions were simulated using complementary finite element analysis (FEA). With the yield strength, ultimate tensile strength, and fatigue life significantly improved in the reinforced group, the results demonstrated that the 10-layer laminate displayed superior mechanical performance relative to the 8-layer laminate; however, this …

Editorial: A Decade Of Apasti – Advancing Regional Prosperity Through Science, Technology And Innovation, Basilios Tsikouras

ASEAN Journal on Science and Technology for Development

A decade after its establishment, APASTI has emerged as a key regional mechanism for promoting science, technology and innovation as drivers of sustainable development, resilience, and shared prosperity in Southeast Asia. This editorial highlights the contributions of APASTI to policy alignment, knowledge exchange, research visibility, and collaborative network-building across ASEAN, while also acknowledging ongoing constraints related to governance, capacity, funding disparities, and uneven regional integration. It introduces a special issue of 14 papers published in AJSTD that collectively evaluate the implementation and impact of APASTI across diverse sectors, including geohazards, energy, materials, health, infrastructure, transport, and information systems. By positioning …

The Effect Of Blanching And Steaming Pretreatment On The Quality Of Durian (Durio Zibenthinus Murr.) Seed Flour, Nabilah Daniel, Rosnah Shamsudin, Mohd Sabri Pak Dek, Jhauharotul Muchlisyiyah, Masmunira Rambli

ASEAN Journal on Science and Technology for Development

Durian (Durio zibethinus Murr.), the "King of Fruits," has seeds that offer nutritional benefits, including high fiber for gut health and high protein for muscle growth. However, natural browning enzymes can limit its use in baking. This study investigates the comparative effects of blanching and steaming durations (5, 10, 15, 20, and 25 minutes) on the color and techno-functional properties of durian seed flour (DSF), providing an optimization-based approach rarely reported for this material.. Durian seeds were sourced from various stalls in Malaysia, washed, soaked in 0.6% sodium metabisulfite, and then blanched or steamed for for varying durations as …

Seismic Vulnerability Assessment With Rapid Visual Screening Of Hospital Buildings In Maguindanao Province, Philippines, Ebrahim B. Kayog, Kristine S. Companion, Kenny B. Cantila, Elizabeth Edan M. Albiento

ASEAN Journal on Science and Technology for Development

Hospitals are expected to maintain operations during and after earthquakes, yet many facilities in the Philippines remain structurally and non-structurally vulnerable. This study evaluates the seismic vulnerability of selected public hospitals in Maguindanao Province, located near the Cotabato Trench and the Western Mindanao Fault, using the FEMA P-154 (3rd ed.) Rapid Visual Screening (RVS) Level-1 procedure. Four government hospitals, comprising 53 buildings constructed between 1980 and 2025, were assessed through a systematic visual inspection and review of available secondary records. Basic structural hazard scores were adjusted using FEMA score modifiers (performance modification factors) to compute Final Level-1 scores (Sₗ₁) and …

Assessing The Probable Sources Affecting The Water Quality Index Of The Panch Prayag Belt Of Uttarakhand, India, Debasis Sau, Indranil Mukherjee, Wasim Akram, Kakali Ghosh, Rimi Paul, Reshmi Paul, Athar Akram

ASEAN Journal on Science and Technology for Development

The Water Quality Index (WQI) is an essential metric for evaluating the usability of surface water resources, particularly in ecologically sensitive and high-demand areas like the Panch Prayag belt of Uttarakhand, India. This region, comprising five major pilgrimage towns—Devaprayag, Nandprayag, Vishnuprayag, Karnaprayag, and Rudraprayag—faces seasonal fluctuations in water quality due to both natural and anthropogenic pressures. In this study, water samples were collected from 2021 to 2023 across pre-monsoon, monsoon, and post-monsoon seasons, and the WQI was computed using the Canadian Water Quality Index (CWQI 1.0). Results revealed that WQI values ranged from 36 to 45 across locations and seasons, …

Influence Of Unmanned Aerial Vehicle (Uav) Payloads And Flight Speeds On Pesticide Droplet Deposition: Indoor Testing Rig Study, Siti Amni Ismail, Azmi Yahya, Ahmad Suhaizi Mat Su, Anas Mohd Mustafah, Norhayu Asib

ASEAN Journal on Science and Technology for Development

This study aims to determine droplet deposition resulting from dynamic change in payloads and flight speeds of Unmanned Aerial Vehicle (UAV) during operation. The study was conducted at Universiti Putra Malaysia, Serdang, Malaysia. The Advansia A1 hexacopter was first set to fly at combinations of 3 payloads (3.3, 6.6, and 9.9 kg) with 3 flight speeds (3, 5 and 7 m/s) to collect individual rotor RPM, which will later be used to set the rotors’ speed during indoor testing experiment. During the experiment, actual pesticide (Alosa EC) was used at 0.5% concentration in the spray deposition test. The droplet deposition …

Performance Evaluation And Economic Analysis Of Lithium Iron Phosphate (Lfp) And Nickel Manganese Cobalt (Nmc) Batteries In Electric Vehicles In Indonesia, Yasa Sanusi, Fatwa Tresna Radityan, Farrah Anis Fazliatul Adnan, Jong Soo Rhee, Dianta Ginting

ASEAN Journal on Science and Technology for Development

The transfer to electric vehicles (EVs) in more and more countries is a response to the increasing problems of climate change and air pollution. Electric cars solve this issue as they have zero emissions. EVs can significantly reduce carbon and air pollution, depending on the charging energy mix. In Indonesia, lithium ferro phosphate and nickel manganese cobalt are among the two most preferred types of batteries for EVs, and both have their advantages. This study evaluates the performance of these batteries in terms of power, range, charging speed, and thermal properties, using a range of battery capacities from 26.7 kWh …

Macro-Ergonomic And Organizational Behavior Mapping For Organic Waste Management Using Hofstede Culture In Semarang, Indonesia : Pca & Sem Analysis Using Smart Pls, Ratih Setyaningrum, Sahana Pramukti, Ravindran Balasubramani

ASEAN Journal on Science and Technology for Development

Waste management has a very close and complex relationship with community behavior and culture . This relationship is two-way: community culture influences how waste is managed, and conversely, waste management practices can shape or change culture. This study to assess the organizational behavior related to organic waste management. Employing a quantitative methodology, data were gathered using the Hofstede Values Survey Module 13 (VSM 13) - closed questionnaire, with 109 Semarang city Community participants responding via a Google Form. The collected data were analyzed utilizing Hofstede's prescribed formula. The next stage is PCA (Principal Component Analysis) and SEM (Structural Equation Modeling) …

Safety And Sustainability In The Domestic Ferry Sector : A Pci Framework For Esg-Aligned Maritime Governance, Mirza Zeeshan Baig

World Maritime University Ph.D. Dissertations

The domestic ferry sector is a significant component of maritime transportation. It strengthens social ties, supports economic growth and connects communities. Despites its importance, this industry faces ongoing challenges. These include fragmented governance, operational adequacies, safety risks and environmental concerns. The study deals with these issues by combining a systems-based approach with governance and change management theories. It examines the interplay between human, technical and organizational aspects. The study integrates the rule-based and rights-based maritime governance along with the Lewin’s three stage change management model (Unfreeze, Change, and Refreeze).

At the core of the study is the development of a …

Fault And Cyberattack Diagnosis And Handling Via Large Language Models And State Prediction For Manufacturing And Quantum Systems, Jihan Abou Halloun

Wayne State University Dissertations

In the digitalization era and Smart Manufacturing, companies are harnessing the power of artificial intelligence (AI) and machine learning (ML) across multiple sectors, including process engineering optimization, process control and fault detection, to enhance efficiency and engineering decision making. Although AI and ML are widely used in anomaly detection and handling, there are still areas where it has been less explored. One of the major areas where AI’s potential in manufacturing needs to be characterized is with respect to the applications of large language models (LLMs) in manufacturing troubleshooting for fault/attack handling. A second major area where the potential of …

Maritime Digitalization And Decarbonization: A Sustainable Future, World Maritime University, Korea Research Institute Of Ships And Ocean Engineering, Korea Maritime Institute

Books

The book with the title “Maritime Digitalization and Decarbonization: A Sustainable Future” is the second major outcome following the publication of the Proceedings of WMU Maritime Week (WMW) 2024.

The purpose of WMU Maritime Week 2024 (WMW) was to convene experts from diverse sectors to discuss contemporary maritime issues, generate practical and academic insights, and contribute to the advancement of the international maritime community. Following the success of WMW 2024, the aim is to deliver a top-notch annual conference in the maritime field, producing practical and academic outputs through in-depth discussions of critical contemporary issues in the maritime field. …

Estimating Pedestrian Crossing Times At Scramble Crossings Via Machine Learning And Agent-Based Modeling, Sho Takami

CURE Proceedings

Scramble crosswalks differ from conventional crosswalks in their ability for pedestrians to cross diagonally. This research compares the average crossing times and investigates the walking behaviors that pedestrians adopt to produce the speediest times in the two crosswalk configurations. Identification of the most efficient set of walking behaviors is done through an agent-based model, whereas producing polynomials relating crossing times to the most prominent walking behaviors is done through regression algorithms in machine learning. With the combination of these two approaches, it is revealed that pedestrians must adopt a relaxed walking style to make each crosswalk configuration efficient. Additionally, between …

Thermo-Rheological And Tribological Properties Of Low- And High-Oleic Vegetable Oils As Sustainable Bio-Based Lubricants, Abiodun Saka, Tobechukwu K. Abor, Anthony C. Okafor, Monday U. Okoronkwo

Mechanical and Aerospace Engineering Faculty Research & Creative Works

Vegetable oil-based lubricants have attracted increased research attention in recent decades as sustainable alternatives to conventional petroleum-based lubricants in metal machining. However, more studies are required to fully elucidate the thermo-rheological and tribological properties. This study presents an investigation of the thermo-rheological and tribological properties of different vegetable oils, including low- and high-oleic soybean oil, high-oleic sunflower, safflower, and canola oils. The lubricity, and evolution of viscosity and thermodynamic properties as a function of temperature were investigated to obtain important parameters including the viscosity index, flow behavior index, flow activation energy, specific heat capacity, thermal conductivity, coefficient of friction, contact …

Generative Ai (Gan & Vae) In Motion Sickness Research, Harigovind Harikumar, Tomojit Ghosh

Celebration of Undergraduate & Graduate Research, Scholarship, and Creative Activities Materials

No abstract provided.

A Systematic Study Of Freezing Behavior In Earthworms In Response To Auditory And Vibratory Stimuli, Navjot Singh, A. Burton, Dragana Ivkovich Claflin

Celebration of Undergraduate & Graduate Research, Scholarship, and Creative Activities Materials

While earthworms have largely been studied for their role in eliminating toxic metals from soil, less is known about their behavior overall. Previous work from our lab found that a predator-like auditory stimulus (grunting) reliably induced fear-related freezing behavior (Worthen et al., 2024). The present studies further explore earthworm behaviors in response to audio-vibratory stimuli. In Experiment 1, we manipulated amplitude levels and speaker location to examine the parameters needed to reliably induce a freezing fear response to the grunting sound. It was hypothesized that when the speaker was touching the apparatus and producing an added mechanical vibration, there would …

Synthesis Of Bio-Orthogonal Hydrogels For 3d Cell Culture Via Penicillamine Β-Thiolactone-Mediated Native Chemical Ligation, Kaelin E. Marshall, Matthew E. Currier, Nathan J. Oldenhuis

Honors Theses and Capstones

Many hydrogel systems designed to mimic the extracellular matrix (ECM) employ thiol-based chemistries with undesirable functional groups, including vinyl sulfones and methacrylates. In downstream applications, any unreacted functional groups are problematic and render hydrogels non-viable for human use. Here, we introduce modifications to the Native Chemical Ligation (NCL) mechanism, exploring the elimination of cytotoxic byproducts and increased reaction rate by using a β-thiolactone. The inclusion of the β-thiolactone results in retention of the thiol within the gel, as well as enhanced kinetics due to the thermodynamic favorability of the ring opening and amide formation. We achieved this by functionalizing 4-arm …

การศึกษาแบบแผนการเต้นของหัวใจระหว่างการวิ่ง โดยใช้การเรียนรู้ของเครื่องแบบไม่มีผู้สอนเพื่อการตรวจจับความผิดปกติ, ชวิน หังสสูต

Chulalongkorn University Theses and Dissertations (Chula ETD)

การศึกษานี้มีวัตถุประสงค์เพื่อวิเคราะห์รูปแบบการเต้นของหัวใจระหว่างการวิ่ง โดยใช้เทคนิคการตรวจจับความผิดปกติแบบไม่มีผู้สอน (Unsupervised Anomaly Detection - UAD) เพื่อการตรวจจับความผิดปกติ ปัญหาหลักในงานวิจัยนี้คือข้อจำกัดทางจริยธรรมในการรวบรวมข้อมูลภาวะวิกฤตเพื่อใช้สอนแบบจำลอง และความแปรปรวนของข้อมูลสรีรวิทยาที่สูงมากระหว่างบุคคลเพื่อแก้ไขปัญหานี้ งานวิจัยนี้ได้พัฒนาระบบเว็บแอปพลิเคชันสำหรับการรวบรวมและกำกับข้อมูล โดยผู้เชี่ยวชาญ และได้สร้างชุดข้อมูลอ้างอิงจากกลุ่มตัวอย่างนักวิ่ง 5 ท่าน จากนั้น ได้ดำเนินการศึกษาเชิงเปรียบเทียบแบบจำลอง UAD จำนวน 7 แบบจำลอง โดยใช้กลยุทธ์การเรียนรู้แบบจำเพาะบุคคล ภายใต้เงื่อนไข การกำหนดค่าไฮเปอร์พารามิเตอร์แบบคงที่ เพื่อจำลองสถานการณ์การใช้งานจริงแบบเริ่มต้น โดยปราศจากการปรับแต่งค่าล่วงหน้า และประเมินผลด้วยค่า F0.5-Score เพื่อเน้นความแม่นยำและลดการแจ้งเตือนที่ผิดพลาดผลการทดลองพบว่า เมื่อไม่มีการปรับจูนพารามิเตอร์ ประสิทธิภาพโดยรวมของทุกแบบจำลองลดลงอย่างมีนัยสำคัญ ซึ่งสะท้อนถึงความท้าทายในการสร้างแบบจำลองสากล อย่างไรก็ตาม แบบจำลอง Matrix Profile (MP) ในกลุ่มคลาสสิก พิสูจน์ให้เห็นถึงความทนทานสูงที่สุด โดยมีประสิทธิภาพเฉลี่ยสูงสุด (F0.5-Score 2.71%) และสามารถตรวจจับความผิดปกติได้ดีในรายบุคคล ในขณะที่แบบจำลองพื้นฐานล้มเหลวโดยสิ้นเชิง (0.00%) สำหรับกลุ่มการเรียนรู้เชิงลึก (USAD, LSTM-AE) พบว่ามีข้อจำกัดในการใช้งานแบบเริ่มต้น (Cold-start) โดยไม่สามารถตรวจจับความผิดปกติได้แม้จะมีปริมาณข้อมูลมาก หากปราศจากการปรับแต่งค่าพารามิเตอร์ ผลลัพธ์นี้ยืนยันว่าระบบเฝ้าระวังสุขภาพในอนาคตจำเป็นต้องมีกลไกการเรียนรู้แบบปรับตัว ร่วมด้วยเพื่อให้สามารถนำไปใช้งานจริงได้อย่างมีประสิทธิภาพ

การคาดการณ์ค่าดัชนีความแตกต่างของพืชและความชื้น โดยใช้เทคนิคการเรียนรู้ของเครื่องอย่างชาญฉลาด เพื่อการติดตามด้านการเกษตรและสิ่งแวดล้อม, ณุทยา เข็มเจริญ

Chulalongkorn University Theses and Dissertations (Chula ETD)

ปัจจุบัน ภัยแล้งและการเปลี่ยนแปลงสภาพภูมิอากาศส่งผลกระทบต่อผลผลิตทางการเกษตร โดยเฉพาะพืชเศรษฐกิจของไทยอย่างทุเรียน ซึ่งต้องอาศัยการติดตามสุขภาพพืชและการจัดการน้ำอย่างใกล้ชิด ข้อมูลจากภาพถ่ายดาวเทียม ดัชนีความแตกต่างของพืชและความชื้น จึงเป็นเครื่องมือสำคัญในการวิเคราะห์สภาพพื้นที่เพาะปลูก โครงงานนี้พัฒนาแบบจำลองการเรียนรู้ของเครื่องเพื่อพยากรณ์ทั้งสองดัชนีรายสัปดาห์ โดยใช้การเฉลี่ยและเติมค่าข้อมูลที่ขาดหายด้วยการถดถอยเชิงเส้น ก่อนนำไปฝึกแบบจำลองผสมระหว่างโครงข่ายคอนโวลูชัน และหน่วยความจำระยะสั้นแบบยาว ระบบถูกออกแบบให้ทำงานอัตโนมัติภายใต้แนวคิดการปฏิบัติการด้านการเรียนรู้ของเครื่อง แสดงผลผ่านเว็บแอปพลิเคชัน ติดตั้งและทดสอบบนเครื่องเซิร์ฟเวอร์

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 …

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 …

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 …

Endoplanar: Deformable Planar-Based Gaussian Splatting For Surgical Scene Reconstruction, Thatphum Paonim

Chulalongkorn University Theses and Dissertations (Chula ETD)

Precise modeling of deformable anatomical structures from stereoscopic endoscopic footage plays a critical role in advancing surgical guidance and robotic automation within image-assisted medical procedures. Recent advances in Gaussian splatting have demonstrated real-time visualization capabilities with notable quality on endoscopic data; however, traditional 3D Gaussian representations introduce volumetric artifacts that compromise geometric fidelity and depth accuracy. We address these challenges through EndoPlanar, a deformable planar Gaussian framework that projects volumetric primitives onto planar surfaces. This planar formulation facilitates bias-free depth calculation and normal vector derivation—capabilities that remain elusive with standard ellipsoidal representations. We further incorporate a regularization mechanism to ensure …