{"id":20492,"date":"2026-07-11T10:48:41","date_gmt":"2026-07-11T02:48:41","guid":{"rendered":"https:\/\/cde.nus.edu.sg\/edic\/?page_id=20492"},"modified":"2026-07-23T22:54:16","modified_gmt":"2026-07-23T14:54:16","slug":"urop-ay2026","status":"publish","type":"page","link":"https:\/\/cde.nus.edu.sg\/edic\/projects\/urop-ay2026\/","title":{"rendered":"UROP projects for AY2026\/2027"},"content":{"rendered":"\n<h2>\n\t\t\tUROP projects for AY2026\/2027\t<\/h2>\n\t<p>We welcome all students from the College of Design and Engineering to work on ad-hoc projects under <strong><a href=\"https:\/\/cde.nus.edu.sg\/undergraduate\/build-your-own-degree\/enhancement-courses\/undergraduate-research-opportunities-programme-eg2605-urop\/\">CDE2605 Undergraduate Research Opportunities Programme<\/a> (UROP)<\/strong>. We have a diverse range of projects that are offered by our faculty members and industry partners. They are grouped into a number of broad themes below.<\/p>\n<p>Students may work on these projects for one or two semesters either as individuals or with a team of other students. CDE2605 can be used to partially fulfil the compulsory internship requirement for students in Engineering majors.<\/p>\n<p>Find out more below about the projects that are offered for\u00a0<strong>Semester 1 AY2026\/2027<\/strong>\u00a0and\/or <strong>Semester 2 AY2026\/2027<\/strong>. Contact the projects supervisors and copy <a href=\"mailto:idp-query@nus.edu.sg\">idp-query@nus.edu.sg<\/a> if you are interested to sign up.<\/p>\n<h4>\n\t\t\tInnovating for Better Healthcare\t<\/h4>\n\t<p>Projects in this theme aim to design better solutions to meet healthcare needs in hospitals and the community. Students learn from and work closely with healthcare professionals and academic staff to conceptualise, design, test, and develop healthcare and medical technologies.<\/p>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-0\">AI-assisted medication code recognition for automated pharmacy dispensing<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-0\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-0\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisors: <strong>Dr Tang Kok Zuea<\/strong> (<a href=\"mailto:kz.tang@nus.edu.sg\">kz.tang@nus.edu.sg<\/a>), <strong>Mr Keith Tan<\/strong> (<a href=\"mailto:keithtcy@nus.edu.sg\">keithtcy@nus.edu.sg<\/a>)<\/p>\n<p>Industry partner\/collaborator: National University Hospital (NUH)<\/p>\n<p>NUH Pharmacy operates ROWA automated dispensing systems, which rely on accurate barcode or QR code scanning when medications are loaded for dispensing. In real-world settings, pharmaceutical packaging typically contains multiple codes on a single box, such as manufacturer identifiers, batch numbers, expiry dates, regulatory markings, and pharmacy-specific labels.<\/p>\n<p>A key challenge arises because the ROWA barcode scanning system is unable to reliably decipher and select the correct code when multiple codes are present on the same package. As a result, pharmacy staff must intervene manually to identify and scan the appropriate code required by ROWA. This manual intervention introduces significant workflow bottlenecks and diverts skilled pharmacy personnel away from higher-value clinical and operational activities. Given the volume and variety of medications processed daily, these inefficiencies have a substantial impact on overall pharmacy productivity and throughput.<\/p>\n<h4>Project aim<\/h4>\n<p>To develop an AI-assisted medication code recognition solution that enhances the ROWA medication loading process by accurately identifying and selecting the correct barcode or QR code from pharmaceutical packaging.<\/p>\n<h4>Possible project scope and learning opportunities<\/h4>\n<p>AI &amp; Computer Vision Exploration:<\/p>\n<ul>\n<li>Investigate suitable computer vision techniques for detecting codes on medication boxes<\/li>\n<li>Apply machine learning or deep learning models to classify different code types<\/li>\n<li>Evaluate accuracy, robustness, and usability in realistic pharmacy environments<\/li>\n<\/ul>\n<p>Professional &amp; Industry Skills:<\/p>\n<ul>\n<li>Working on a realistic operations challenge in healthcare setting<\/li>\n<li>Translating AI capabilities into practical, deployable solutions<\/li>\n<li>Communicate solutions clearly to both technical and non-technical stakeholders<\/li>\n<\/ul>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-1\">Development of an AI-powered system for senior wellbeing<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-1\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-1\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisors: <strong>A\/Prof Lim Li Hong Idris<\/strong> (<a href=\"mailto:lhi.lim@nus.edu.sg\">lhi.lim@nus.edu.sg<\/a>), <strong>Dr Kate Sangwon Lee<\/strong> (<a href=\"mailto:katelee@nus.edu.sg\">katelee@nus.edu.sg<\/a>)<\/p>\n<p>Industry partner\/collaborator: Imperial College London<\/p>\n<p>The rapid advancement of AI presents a transformative opportunity to address the growing wellbeing needs of senior citizens. This project proposes the development of an AI-powered system designed to support the wellbeing of older adults in both home and care settings. The system will leverage natural language processing and adaptive learning to provide personalised companionship, health monitoring reminders, cognitive engagement activities, and seamless communication with caregivers and family members. By centering the design process around the lived experiences of seniors, the project aims to produce an accessible, ethical, and empathetic AI solution that enhances quality of life, promotes independence, and reduces the burden on formal and informal care systems.<\/p>\n<p>Objectives:<\/p>\n<ul>\n<li>To design and develop an AI-powered system capable of engaging seniors in meaningful, natural dialogue that supports wellbeing and reduces feelings of loneliness and social isolation.<\/li>\n<li>To implement personalised health and wellness reminder functionality within the system, enabling timely prompts for medication, hydration, physical activity, and medical appointments.<\/li>\n<li>To integrate cognitive stimulation features &#8211; including memory exercises, trivia, and storytelling prompts &#8211; that support mental acuity and delay cognitive decline in older adults.<\/li>\n<li>To establish a secure caregiver and family communication interface that allows authorised users to monitor engagement patterns and receive alerts regarding changes in the senior&#8217;s routine or wellbeing.<\/li>\n<li>To evaluate the usability, accessibility, and acceptability of the AI-powered system through user testing with senior participants, ensuring the design meets the functional and emotional needs of the target population.<\/li>\n<li>To assess the ethical implications of deploying an AI-powered system in senior care, including considerations of privacy, data security, autonomy, and the appropriate boundaries of human-AI interaction.<\/li>\n<\/ul>\n<p><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/cde.nus.edu.sg\/edic\/wp-content\/uploads\/sites\/37\/2026\/04\/CDE4301-2026-AI-senior-wellbeing-1024x572.jpeg\" alt=\"\" width=\"1024\" height=\"572\" \/><\/p>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-2\">Fabric-based wearables for intelligent clinical applications using AI<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-2\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-2\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisor: <strong>Dr Tang Kok Zuea<\/strong> (<a href=\"mailto:kz.tang@nus.edu.sg\">kz.tang@nus.edu.sg<\/a>)<\/p>\n<p>Industry partner\/collaborator: Republic of Singapore Air Force (RSAF)<\/p>\n<p>Continuous monitoring of vital signs is essential for early detection of health deterioration, chronic disease management, and preventive care. Conventional wearable devices often rely on rigid electronics and discrete sensors, which may cause discomfort, limit wearability, and reduce long-term user compliance. This project aims to develop a fabric-based wearable system that can be integrated into garments to enable comfortable, unobtrusive, and continuous monitoring of vital physiological signals using AI.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/cde.nus.edu.sg\/edic\/wp-content\/uploads\/sites\/37\/2026\/04\/CDE4301-2026-fabric-wearables.jpg\" alt=\"\" width=\"640\" height=\"640\" \/><\/p>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-3\">Improving unit dose medication repackaging through workflow design and assistive technologies<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-3\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-3\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisors: <strong>Dr Tang Kok Zuea<\/strong> (<a href=\"mailto:kz.tang@nus.edu.sg\">kz.tang@nus.edu.sg<\/a>), <strong>Mr Soh Eng Keng<\/strong> (<a href=\"mailto:ek.soh@nus.edu.sg\">ek.soh@nus.edu.sg<\/a>)<\/p>\n<p>Industry partner\/collaborator: National University Hospital (NUH)<\/p>\n<p>The National University Hospital (NUH) inpatient pharmacy operates a closed loop medication management system that supports medication safety and traceability through unit dose repackaging and barcode enabled administration. A key part of this system involves pharmacy technicians manually converting medications into unit doses by cutting blister strips, separating capsules, relabelling ampoules, and repackaging bulk medications from bottles or multi dose containers.<\/p>\n<p>These tasks require repetitive manual handling, precision, and adherence to strict hygiene and safety standards. The predominantly manual workflow constrains throughput, introduces variability in packaging quality, and places high physical and cognitive demands on staff. Rather than fully automating this process, there is an opportunity to redesign workflows and introduce specially designed devices or enabling technologies that enhance productivity, consistency, and ergonomics while preserving human oversight and control.<\/p>\n<h4>Project aim<\/h4>\n<p>To design and prototype workflow enhancements and productivity enabling devices or technologies that assist pharmacy technicians in safely and accurately converting pharmaceutical packaging into unit dose formats.<\/p>\n<h4>Possible project scope and learning opportunities<\/h4>\n<ul>\n<li>Understand pharmacy operations and workflow challenges<\/li>\n<li>Design of assistive devices and workflow improvements<\/li>\n<li>Apply engineering design and innovation methods to a real healthcare operations challenge<\/li>\n<li>Gain experience in human centred design within regulated and safety critical settings<\/li>\n<\/ul>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-4\">Intelligent linen inspection and workflow redesign for hospital operations<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-4\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-4\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisors: <strong>Dr Tang Kok Zuea<\/strong> (<a href=\"mailto:kz.tang@nus.edu.sg\">kz.tang@nus.edu.sg<\/a>), <strong>Mr Soh Eng Keng<\/strong> (<a href=\"mailto:ek.soh@nus.edu.sg\">ek.soh@nus.edu.sg<\/a>)<\/p>\n<p>Industry partner\/collaborator: National University Hospital (NUH)<\/p>\n<p>The NUH Group Hospitality (GH) manages hospital linen operations, including patient pyjamas and other textile items that must meet strict hygiene and quality standards. Currently, patient pyjamas undergo 100% manual inspection for defects such as stains, fabric tears or pinholes, discolouration, odour or moisture, and missing buttons, followed by folding and packaging.<\/p>\n<p>These inspection processes are highly labour intensive, time consuming, and dependent on individual judgement, resulting in inconsistent quality and extended turnaround times. With increasing patient volumes and healthcare expansion, manual inspection has become a key operational bottleneck. There is a growing need to explore technology enabled inspection and workflow improvements that can improve inspection accuracy, consistency, and throughput while supporting workforce sustainability and maintaining hygiene standards.<\/p>\n<h4>Project aim<\/h4>\n<p>This project aims to design and prototype a technology enabled linen inspection solution, together with a redesigned operational workflow, that enhances the efficiency and consistency of hospital linen quality checks.<\/p>\n<h4>Possible project scope and learning opportunities<\/h4>\n<ul>\n<li>Understand current operations and quality criteria<\/li>\n<li>Research and evaluate suitable inspection technologies<\/li>\n<li>Propose a system concept that integrates intelligent inspection into the linen processing line<\/li>\n<li>Redesign the workflow to reduce reliance on manual inspection and enable smooth hand off to folding and packing stages<\/li>\n<\/ul>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-5\">Intelligent surgical tools checking using robotics and AI<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-5\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-5\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisor: <strong>Dr Tang Kok Zuea<\/strong> (<a href=\"mailto:kz.tang@nus.edu.sg\">kz.tang@nus.edu.sg<\/a>)<\/p>\n<p>Industry partners\/collaborators: Synapxe, Woodlands Hospital<\/p>\n<p>In a typical hospital, the instrument processing department may handle up to 900 surgical trays per day, creating a high potential for human error in inventory and surgical set preparation. The high demand in volume, combined with the visual similarity between many surgical tools, makes manual verification error-prone. This leads to frequent cases of missing instruments and incomplete surgical sets in operating theatres, resulting in workflow disruption, surgical delays, and increased stress for staff. To address this issue, this project explores the development of an intelligent scanning system that uses robotics and AI to detect, verify, and evaluate surgical tools. The system is designed to compare each scanned tool against a reference set, automatically flagging missing or incorrect instruments before the tools are packed.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/cde.nus.edu.sg\/edic\/wp-content\/uploads\/sites\/37\/2026\/04\/CDE4301-2026-surgical-tools.jpg\" alt=\"\" width=\"640\" height=\"640\" \/><\/p>\n<h4>\n\t\t\tInnovating with Immersive Reality\t<\/h4>\n\t<p>Projects in this theme aim to develop novel applications of virtual reality and augmented reality to serve the unmet needs in industry verticals such as healthcare, education and entertainment.<\/p>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-0\">AI conversation coach for nursing communication training<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-0\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-0\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisor: <b>A\/Prof Khoo Eng Tat <\/b>(<a href=\"mailto:etkhoo@nus.edu.sg\">etkhoo@nus.edu.sg<\/a>)<\/p>\n<p>Industry partner\/collaborator: National University Hospital (NUH)<\/p>\n<p>Traditional communication training at NUH relies heavily on in person workshops and role play, which are resource intensive, limited in frequency, and inconsistent across learners. Nurses are facing increasingly complex patient and family interactions, requiring more scalable and repeatable practice opportunities to build confidence and competence. The purpose of this project is to transform nursing communication training through an AI powered platform that enables nurses to practice difficult conversations &#8211; such as breaking bad news, serious illness discussions, behavioural coaching, and emotional distress counselling &#8211; in a safe, structured, and repeatable digital environment.<\/p>\n<p>This project aims to provide an AI conversation coach that simulates realistic patient and family interactions.<\/p>\n<p>Students in this project may design and develop one or more of the following scopes:<\/p>\n<ul>\n<li>Utilise Gen-AI to create realistic virtual patient\/family members scenarios based on diverse demographic profiles, commonly encountered case scenarios for different clinical contexts.<\/li>\n<li>Implement LLM to enable natural language processing for realistic and contextually appropriate dialogue between nurses and virtual patients\/family members.<\/li>\n<li>Integrate VR technology to provide an immersive environment where nurses can engage in simulated patient consultations.<\/li>\n<li>User study and analytics\/assessment of nurses&#8217; learning.<\/li>\n<\/ul>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-1\">AI simulated patient for dentistry student communication training in VR<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-1\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-1\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisor: <b>A\/Prof Khoo Eng Tat <\/b>(<a href=\"mailto:etkhoo@nus.edu.sg\">etkhoo@nus.edu.sg<\/a>)<\/p>\n<p>Industry partner\/collaborator: NUS Faculty of Dentistry<\/p>\n<p>Effective communication is crucial in dentistry for patient care and treatment success. However, many dentistry students face challenges in developing communication skills due to limited opportunities for practice with real patients. To address this, we propose the development of an AI Simulated Patient system tailored for dentistry student communication training. This project integrates emerging technologies including generative AI (Gen-AI), Large Language Models (LLM), and Virtual Reality (VR) to create realistic simulated patient interactions.<\/p>\n<p>Students in this project may design and develop one or more of the following scopes:<\/p>\n<ul>\n<li>Utilise Gen-AI to create realistic virtual patient scenarios based on diverse demographic profiles, dental conditions, and communication challenges commonly encountered in clinical practice.<\/li>\n<li>Implement LLM to enable natural language processing for realistic and contextually appropriate dialogue between students and virtual patients.<\/li>\n<li>Integrate VR technology to provide an immersive environment where students can engage in simulated patient consultations.<\/li>\n<li>User study and analytics\/assessment of students&#8217; learning.<\/li>\n<\/ul>\n<p>The project will be supervised by Associate Professor Khoo Eng Tat and supported by the research fellow and engineers from the Immersive Reality Lab. It will be carried out in collaboration with Associate Professor Wong Mun Loke from the NUS Faculty of Dentistry. Example of immersive reality (VR\/MR) and generative AI (Gen-AI) student projects completed under Immersive Reality Lab can be found on the website <a href=\"https:\/\/cde.nus.edu.sg\/edic\/projects\/innovating-with-immersive-reality\/\">https:\/\/cde.nus.edu.sg\/edic\/projects\/innovating-with-immersive-reality\/<\/a>.<\/p>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-2\">HapticNet: learning-based haptic rendering models<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-2\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-2\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisor:\u00a0<b>Dr Cai Shaoyu<\/b>\u00a0(<a href=\"mailto:shaoyucai@nus.edu.sg\">shaoyucai@nus.edu.sg<\/a>)<\/p>\nThis project uses machine learning to map input signals (visual\/audio\/physics data) to optimal haptic outputs, replacing hand-designed mappings. The proposed method can support data-driven haptic synthesis, personalisation of haptic feedback<br \/>\nand generalisable across devices.\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-3\">HapticSkin+: super-resolution wearable tactile interfaces for continuous interaction<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-3\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-3\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisor:\u00a0<b>Dr Cai Shaoyu<\/b>\u00a0(<a href=\"mailto:shaoyucai@nus.edu.sg\">shaoyucai@nus.edu.sg<\/a>)<\/p>\n<p>Industry partner\/collaborator: National Heritage Board (NHB)<\/p>\n<p>Building on liquid-metal sensing, this project develops a thin, flexible wearable skin capable of decoding continuous touch position and force at high resolution. The system enables expressive interaction (e.g., drawing, pressure-based control) on deformable surfaces.<\/p>\n<p>The contribution mainly covers:<\/p>\n<ul>\n<li>Super-resolution tactile sensing on wearables<\/li>\n<li>Multi-dimensional interaction (x, y, force)<\/li>\n<li>Integration with XR and tangible interfaces<\/li>\n<\/ul>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-4\">From prompts to galleries: exhibition design with diffusion models and Gaussian Splatting<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-4\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-4\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisor: <b>A\/Prof Khoo Eng Tat <\/b>(<a href=\"mailto:etkhoo@nus.edu.sg\">etkhoo@nus.edu.sg<\/a>)<\/p>\n<p>Industry partner\/collaborator: National Heritage Board (NHB)<\/p>\n<p>This project investigates how generative AI and advanced rendering techniques can transform exhibition design workflows for gallery curators and designers, enabling rapid exploration and prototyping of immersive gallery spaces from simple multimodal prompts.<\/p>\n<p>Students will develop an AI-assisted exhibition design and visualisation solution that translates text and voice inputs into spatial layouts using diffusion models, with high-fidelity scene reconstruction and rendering enabled through Gaussian Splatting. The solution will allow gallery designer to generate, refine, and compare multiple exhibition configurations in real time, bridging conceptual design and spatial visualisation.<\/p>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-5\">Future frontiers: GenAI and immersive reality<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-5\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-5\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisor: <b>A\/Prof Khoo Eng Tat <\/b>(<a href=\"mailto:etkhoo@nus.edu.sg\">etkhoo@nus.edu.sg<\/a>)<\/p>\n<p>Industry partners\/collaborators: NUS Yong Loo Lin School of Medicine, SIA-NUS Digital Aviation Corp Laboratory<\/p>\n<p>This project is dedicated to pushing the boundaries of immersive technologies, generative AI, and large language models (LLMs). Students can explore how these technologies can be integrated to transform VR\/AR simulation systems used in sectors like medical education, aviation training, and elderly care. Students will investigate the current limitations of immersive systems, design novel solutions to enhance realism, interactivity, and usability, and pioneer new use cases. A key emphasis will be placed on user experience (UX) design, real-time AI-driven feedback, and human-AI interaction.<\/p>\n<p>Students joining this project will have the flexibility to either select from a curated list of project topics or propose their own ideas that align with the studio&#8217;s themes. Under the guidance of A\/Prof Khoo Eng Tat and the Immersive Reality Lab team, students will work closely with industry partners to develop real-world solutions that innovate beyond today&#8217;s capabilities.<\/p>\n<p>Proposed areas of exploration:<\/p>\n<ul>\n<li>VR\/AR applications for medical, nursing, and aviation training<\/li>\n<li>Simulating realistic AI-driven virtual characters using GenAI and LLMs<\/li>\n<li>Auto-feedback and skill assessment systems powered by GenAI in healthcare training<\/li>\n<li>Computer vision and machine learning for object detection, tracking, and 3D reconstruction<\/li>\n<li>Simulating and sensing emotions in virtual human interactions<\/li>\n<\/ul>\n<p>Problem statements (students may choose or propose their own):<\/p>\n<ul>\n<li>Virtual Paediatric (Infant) Patient Simulation &#8211; Create an immersive VR experience for training in pediatric emergencies, focusing on respiratory distress scenarios. (Collaboration with Centre for Healthcare Simulation)<\/li>\n<li>AI Social Companion Robot\/Pet for Elderly &#8211; Design a virtual or physical AI companion for emotional support and engagement of elderly individuals. (Collaboration with NUS Nursing)<\/li>\n<li>AI Co-Pilot in VR Simulator for Pilot Competency Training &#8211; Integrate an AI-driven virtual co-pilot to enhance decision-making and skill development in pilot training simulators. (Collaboration with Singapore Airlines-NUS Digital Aviation Corp Lab)<\/li>\n<li>Emerging Applications of GenAI and VR\/MR &#8211; Students propose a novel idea combining GenAI, VR, and MR technologies to solve a real-world challenge or create a new experience.<\/li>\n<\/ul>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-6\">Gen-AI and VR-based full-body dance sensing and choreography optimisation<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-6\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-6\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisor: <b>A\/Prof Khoo Eng Tat <\/b>(<a href=\"mailto:etkhoo@nus.edu.sg\">etkhoo@nus.edu.sg<\/a>)<\/p>\n<p>Industry partners\/collaborators: NUS Eusoff Hall, NUS Centre For the Arts<\/p>\n<p>Advancements in full-body motion sensing and generative AI are opening new frontiers in the art and science of dance. Traditional dance practice often relies on repetitive rehearsals and instructor feedback, but dancers face challenges in achieving precise technique refinement and exploring creative movement variations.<\/p>\n<p>This project aims to create an innovative system that integrates VR-based immersive full-body tracking with Generative AI-driven choreography. The goal is to empower dancers to train anywhere, receive real-time, AI-guided feedback, and collaborate with AI to generate new, optimized choreography. By blending immersive reality and creative AI generation, the project envisions a future where human dancers and AI co-create, enhance technical mastery, and expand artistic boundaries.<\/p>\n<p>We will collaborate with student dance groups to collect real-world motion data and evaluate the system&#8217;s impact on choreography development and learning outcomes.<\/p>\n<p>Students participating in this project can choose to contribute to one or more areas, including:<\/p>\n<ul>\n<li>Full-Body Pose Estimation: Develop real-time motion tracking models using VR devices (e.g., VR controllers, body sensors) to accurately capture dance movements.<\/li>\n<li>Generative AI for Choreography: Apply GenAI techniques to create, modify, and optimize dance sequences based on sensed body motions, proposing novel movement patterns and variations.<\/li>\n<li>Immersive VR Environment Design: Build VR spaces where dancers can interact with AI-generated feedback, practice performances, and experiment with choreographic ideas.<\/li>\n<li>User Research and Evaluation: Design and conduct user studies to assess how AI-assisted choreography impacts movement quality, creativity, technical refinement, and the dancer&#8217;s learning experience.<\/li>\n<\/ul>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-7\">Generative AI human: emotion simulation and emotional sensing for intelligent agents<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-7\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-7\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisor: <b>A\/Prof Khoo Eng Tat <\/b>(<a href=\"mailto:etkhoo@nus.edu.sg\">etkhoo@nus.edu.sg<\/a>)<\/p>\n<p>Industry partners\/collaborators: NUS Yong Loo Lin School of Medicine, SIA-NUS Digital Aviation Corp Laboratory<\/p>\n<p>As human-AI interaction becomes more pervasive in industries such as healthcare, customer service, and aviation, the ability for AI agents to simulate and respond to human emotions will be critical for realism, effectiveness, and empathy. This project, Generative AI Human, explores the creation of AI-driven virtual agents capable of both simulating human-like emotional expressions (e.g., anger, frustration, compassion) and detecting the emotional states of users to adapt their responses accordingly.<\/p>\n<p>Students will work on two intertwined challenges:<\/p>\n<h4>Simulating emotions in AI agents<\/h4>\n<p>Develop intelligent agents that can generate nuanced emotional behaviours, such as anger or impatience, critical for realistic training scenarios (e.g., angry customer simulations for service training, distressed patient simulations for medical training). This includes voice tone modulation, facial expression animation, and contextual behaviour adaptation using generative AI and LLM-based techniques.<\/p>\n<h4>Emotional detection and feedback loop<\/h4>\n<p>Implement systems capable of detecting user emotions through computer vision (facial recognition), audio analysis (speech tone\/sentiment), or physiological data. These insights can be fed back into the agent&#8217;s behaviour to create a dynamic two-way emotional interaction.<\/p>\n<p>Students will have the opportunity to contribute to both technical development (e.g., building emotion models, integrating sensing technology) and user experience design (e.g., ensuring the interaction feels natural and realistic). Applications range from customer service training simulations to healthcare communication skills education.<\/p>\n<p>Possible areas of focus (students may specialize based on interest):<\/p>\n<ul>\n<li>Emotion simulation using LLMs and multimodal generative AI (text, voice, and facial synthesis)<\/li>\n<li>Computer vision and audio analysis for real-time emotion detection<\/li>\n<li>Real-time adaptation of agent behaviour based on detected emotional cues<\/li>\n<li>User studies to evaluate realism, effectiveness, and user experience of emotional agents<\/li>\n<li>Ethics and bias mitigation in emotional AI systems<\/li>\n<\/ul>\n<p>Potential use cases:<\/p>\n<ul>\n<li>Customer service training: Simulating angry or dissatisfied customers for roleplay-based training.<\/li>\n<li>Healthcare communication training: Simulating distressed patients or anxious family members for doctors and nurses.<\/li>\n<li>Aviation crew training: Simulating emotional passenger interactions for cabin crew practice.<\/li>\n<li>Elderly care support: Creating empathetic AI companions that detect loneliness or sadness.<\/li>\n<\/ul>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-8\">Reimagining heritage: immersive storytelling for cultural learning and user experience<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-8\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-8\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisor: <b>A\/Prof Khoo Eng Tat <\/b>(<a href=\"mailto:etkhoo@nus.edu.sg\">etkhoo@nus.edu.sg<\/a>)<\/p>\n<p>Industry partner\/collaborator: National Heritage Board (NHB)<\/p>\n<p>This project explores how immersive technologies can transform digital heritage education through interactive storytelling, spatial computing, and user-centred design. Students will begin by studying and critically analysing existing cultural heritage AR\/VR applications developed by the National Heritage Board, forming a foundation for proposing new research directions and experience designs.<\/p>\n<p>Participants will design and implement immersive applications using curated 3D and digital heritage collections, while documenting complete development pipelines including asset optimisation, content authoring, interaction design, and deployment.<\/p>\n<p>The project also involves conducting user studies to evaluate how immersive experiences influence cultural perception, learning outcomes, and overall experience quality compared to conventional media. Students will gain hands-on experience at the intersection of immersive reality, storytelling, and human-centred research.<\/p>\n<h4>\n\t\t\tInnovations in Intelligent Systems\t<\/h4>\n\t<p>Projects in this theme focus on the design of complex engineering systems and automation for various applications.<\/p>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-0\">Autonomous drone swarm for indoor search and rescue<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-0\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-0\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisor: <b>Dr Elliot Law <\/b>(<a href=\"mailto:elaw@nus.edu.sg\">elaw@nus.edu.sg<\/a>)<\/p>\n<p>Industry partner\/collaborator: Temasek Laboratories, NUS<\/p>\n<p>A swarm of drones is particularly useful for disaster response missions. In addition to being able to operate in hazardous environment, they can also search large areas more quickly and efficiently than a few human rescuers. The goal of this project is to develop and integrate the necessary algorithms to automate a swarm of drones to rapidly and effectively search and locate disaster scenario victims in indoor environment.<\/p>\n<p>The project team will have the chance to participate in the Singapore Amazing Flying Machine Competition (Category E event on Swarm) which will be held sometime in March 2027. Building on the work of previous teams, students in this project will explore state-of-the-art techniques in computer vision, machine learning, formation flying, and swarm robotics. Students will develop or improve algorithms to optimise the search strategy of the drones and enable them to adapt to the dynamic and unpredictable environment.<\/p>\n<p>The following areas of work will be covered in this project:<\/p>\n<ol>\n<li>Swarm control and command<\/li>\n<li>Search strategy<\/li>\n<li>Localisation<\/li>\n<li>Collision avoidance and object detection<\/li>\n<li>Simulation<\/li>\n<\/ol>\nAn example of the nature of work in this project is shown in this video:<br \/>\n<a href=\"https:\/\/www.youtube.com\/watch?v=0wEo22QqvGk\">https:\/\/www.youtube.com\/watch?v=0wEo22QqvGk<\/a>\n<p>Note: Students who are interested in this project should preferably have prior experience with ROS2 and\/or have read CDE2310.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/cde.nus.edu.sg\/edic\/wp-content\/uploads\/sites\/37\/2024\/03\/EG4301-SAFMC.png\" alt=\"\" width=\"745\" height=\"647\" \/><\/p>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-1\">Autonomous library shelving robot<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-1\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-1\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisors: <b>Dr Elliot Law <\/b>(<a href=\"mailto:elaw@nus.edu.sg\">elaw@nus.edu.sg<\/a>), <strong>Mr Nicholas Chew<\/strong> (<a href=\"mailto:nickchew@nus.edu.sg\">nickchew@nus.edu.sg<\/a>)<\/p>\n<p>Industry partner\/collaborator: NUS Libraries<\/p>\n<p><em><strong>Can a robot read a call number, navigate a library, and put a book exactly where it belongs?<\/strong><\/em><\/p>\n<p>This project challenges you to adapt an existing robotic platform &#8211; a robotic arm mounted on an autonomous mobile robot (AMR) &#8211; into a system that solves a real problem faced by libraries everywhere: the time-consuming, error-prone task of reshelving books. Starting from this platform, you&#8217;ll develop the perception, reasoning, and control systems needed to identify a book&#8217;s call number using computer vision, determine where that book belongs on the shelves, navigate there, and physically place the book in its correct position.<\/p>\n<h4>What you&#8217;ll be building<\/h4>\n<p>This is a full-stack robotics challenge that spans perception, reasoning, mobility, and manipulation:<\/p>\n<ul>\n<li>Computer vision and optical character recognistino (OCR): Train and deploy a system that can reliably detect and read call number labels on book spines, even with varied fonts, lighting conditions, angles, and worn or partially obscured labels.<\/li>\n<li>Spatial reasoning: Develop the logic that maps a call number to a physical shelf location, accounting for classification schemes (e.g. Dewey Decimal) and the ordering conventions libraries actually use.<\/li>\n<li>Autonomous navigation: Adapt the AMR platform&#8217;s navigation stack to move safely and efficiently through library aisles, avoiding obstacles, people, and furniture while planning efficient routes to target shelves.<\/li>\n<li>Robotic manipulation: Configure and program the existing robotic arm to grasp books of different sizes and weights, and place them at the correct location on a shelf.<\/li>\n<li>Systems integration: Bring perception, navigation, and manipulation together into one coordinated pipeline that runs reliably from &#8220;here&#8217;s a book&#8221; to &#8220;book is shelved,&#8221; built on top of the platform&#8217;s existing hardware and control interfaces.<\/li>\n<\/ul>\n<h4>Why work on this project<\/h4>\n<p>This project sits at the intersection of computer vision, robotics, and practical engineering. You&#8217;ll be solving a problem where perception errors, navigation errors, and grasping errors all have to be handled together in the real world. Because you&#8217;re building on an existing arm-and-AMR platform, you can spend less time on low-level hardware setup and more time tackling the interesting open problems: robust call-number recognition, reliable shelf-mapping logic, and smooth coordination between navigation and manipulation.<\/p>\n<p>It&#8217;s an excellent opportunity to get hands-on experience with real robotic hardware, work through open-ended problems with no single &#8220;correct&#8221; solution, and build something with genuine real-world utility that could eventually be piloted in an actual library.<\/p>\n<p>Whether your interest lies in machine learning, control systems, or robotics software architecture, there&#8217;s a meaningful piece of this problem for you to own &#8211; and plenty of room to bring your own ideas to how the system should work.<\/p>\n<figure id=\"attachment_20564\" aria-describedby=\"caption-attachment-20564\" style=\"width: 1024px\" class=\"wp-caption alignnone\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/cde.nus.edu.sg\/edic\/wp-content\/uploads\/sites\/37\/2026\/07\/DSC01136-1024x719.png\" alt=\"\" width=\"1024\" height=\"719\" \/><figcaption id=\"caption-attachment-20564\" class=\"wp-caption-text\">Photo of robotic arm on AMR system that will be adapted for this project<\/figcaption><\/figure>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-2\">BoxBunny: intelligent boxing robot<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-2\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-2\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisors: <b>Mr Graham Zhu<\/b> (<a href=\"mailto:graham.zhu@nus.edu.sg\">graham.zhu@nus.edu.sg<\/a>), <strong>Mr Royston Shieh<\/strong> (<a href=\"mailto:shiehtw@nus.edu.sg\">shiehtw@nus.edu.sg<\/a>)<\/p>\n<p>Float like a butterfly, sting like a bee \ud83e\udd4a<\/p>\n<p>Meet BoxBunny &#8211; an intelligent boxing robot designed to make high-quality boxing training accessible, interactive, and fun. Imagine training with a smart sparring partner that adapts to your skill level, tracks your progress, and helps you improve step by step &#8211; just like a real coach.<\/p>\n<p>Over the past 2 years, BoxBunny has evolved through multiple iterations, and we&#8217;re now taking it to the next level-towards a professional, real-world product. This is your chance to be part of that journey.<\/p>\n<p>By joining this project, you won&#8217;t just build a robot &#8211; you&#8217;ll gain hands-on experience across multiple cutting-edge domains, including:<\/p>\n<ul>\n<li>Mechanical design &amp; prototyping<\/li>\n<li>Mechatronics and robotics<\/li>\n<li>Software &amp; firmware development<\/li>\n<li>Computer vision and AI<\/li>\n<li>UI\/UX design<\/li>\n<li>Product development &amp; entrepreneurship<\/li>\n<\/ul>\n<p>If you enjoy building, experimenting, and pushing ideas into reality, this project will challenge you, grow your skills, and let you work on something truly exciting and impactful.<\/p>\n<p>Step into the ring with BoxBunny &#8211; and help shape the future of smart training. \ud83d\ude80<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/cde.nus.edu.sg\/edic\/wp-content\/uploads\/sites\/37\/2026\/03\/IS-431-BoxBunny-1024x576.png\" alt=\"\" width=\"1024\" height=\"576\" \/><\/p>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-3\">Smart interface for lifts and autonomous mobile robots<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-3\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-3\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisor: <strong>Dr Tang Kok Zuea<\/strong> (<a href=\"mailto:kz.tang@nus.edu.sg\">kz.tang@nus.edu.sg<\/a>)<\/p>\n<p>Industry partner\/collaborator: KK Women&#8217;s and Children&#8217;s Hospital (KKH)<\/p>\n<p>This project aims to design a smart robotic panel is to be developed to be retrofitted on all lift panels that can communicate with human users and autonomous mobile robots.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/cde.nus.edu.sg\/edic\/wp-content\/uploads\/sites\/37\/2026\/04\/CDE4301-2026-lift-robot.jpg\" alt=\"\" width=\"640\" height=\"640\" \/><\/p>\n<h4>\n\t\t\tInnovations in Smart Solutions\t<\/h4>\n\t<p>Projects in this theme focus on designing smart devices and services to enhance everyday life, work, and play.<\/p>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-0\">AI-enabled sustainability data automation solution for global hospitality operations<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-0\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-0\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisors: <strong>Mr Royston Shieh<\/strong> (<a href=\"mailto:shiehtw@nus.edu.sg\">shiehtw@nus.edu.sg<\/a>), <strong>Mr Keith Tan<\/strong> (<a href=\"mailto:keithtcy@nus.edu.sg\">keithtcy@nus.edu.sg<\/a>)<\/p>\n<p>Industry partner\/collaborator: CapitaLand Ascott Trust<\/p>\n<p>Global hospitality operators depend on accurate, timely, and verifiable sustainability data from a large number of properties worldwide. These data underpin ESG reporting, corporate disclosures, and strategic sustainability decision-making. However, sustainability data collection today faces several challenges:<\/p>\n<ul>\n<li>The process is highly manual and time-consuming<\/li>\n<li>Data submissions are often incomplete, inconsistent, or late<\/li>\n<li>Regional differences introduce language barriers, varied local capabilities, and uneven understanding of sustainability requirements<\/li>\n<\/ul>\n<p>While digital tools such as online forms, dashboards, and basic automation are already in use, sustainability teams at headquarters still spend significant effort on data chasing, validation, and reconciliation, limiting their capacity to focus on analysis and impact.<\/p>\n<p>This capstone project invites students to design and prototype an AI-enabled toolkit or system that helps our industry partner to automate the extraction, validation, and transformation of sustainability data from known or input data sources. The system should intelligently map data into standardised formats suitable for dashboards, analytics, and sustainability reports, improving efficiency, accuracy, and scalability across global operations.<\/p>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-1\">Automated detection and mapping of underground power cables in Singapore&#8217;s urban road corridors<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-1\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-1\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisor: <b>Dr Elliot Law\u00a0<\/b>(<a href=\"mailto:elaw@nus.edu.sg\">elaw@nus.edu.sg<\/a>)<\/p>\n<p>Industry partner\/collaborator: HSC Pipeline Engineering Pte Ltd<\/p>\n<p>Singapore&#8217;s underground utility network is among the densest in the world. Before any excavation or road-opening works can commence, contractors are legally required under the Street Works Act and the Urban Redevelopment Authority Infrastructure Planning Authority Group (URA IPAG)\u00a0guidelines to identify and map all underground utilities within the works boundary. For power cables specifically, this detection is performed using handheld electromagnetic locators (EML) &#8211; instruments that sense the 50Hz magnetic field passively emitted by live buried cables.<\/p>\n<p>In current practice, a trained operator sweeps the EML instrument across the road surface and listens for a peak in the audible signal, then manually marks the cable position with spray paint. This process is inherently operator-dependent: detection quality varies with the skill and experience of the individual, and no data is recorded beyond a spray-paint mark on the road. If a cable is missed, there is no record of the survey coverage to indicate whether the area was scanned at all. Cable strikes during excavation &#8211; where construction equipment damages an undetected or incorrectly marked buried power cable &#8211; carry severe safety consequences including electrocution, supply disruption, and financial penalties. Despite advances in geophysical survey instrumentation globally, no continuous, data-logging, multi-sensor solution exists for this specific detection problem in Singapore&#8217;s urban road environment.<\/p>\n<p>The core challenge is that current instruments were designed to help an operator find a single cable at a point in time. They process the signal internally, apply automatic gain control, and output a locate point &#8211; not raw field data. As a result, the spatial magnetic field profile across the road cross-section is never captured, surveys cannot be audited or reproduced, and detection quality cannot be objectively measured.<\/p>\n<p>This project explores whether a cart-based multi-sensor system capable of continuously measuring and logging the passive electromagnetic field across a road cross-section could provide a more systematic, auditable, and data-rich approach to underground power cable detection. Students are expected to investigate the physical principles governing the magnetic field emitted by buried live cables, design and prototype a sensor array capable of capturing this field with spatial resolution, and develop a signal processing approach that can identify cable positions from the logged data. The system should be testable in real road environments in Singapore, where HSC Pipeline Engineering Pte Ltd will provide access to field sites and ground-truth validation data from open-trench excavations.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/cde.nus.edu.sg\/edic\/wp-content\/uploads\/sites\/37\/2026\/05\/CDE4301-2026-underground-cables.png\" alt=\"\" width=\"956\" height=\"537\" \/><\/p>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-2\">Bubble free filling<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-2\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-2\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisor:\u00a0<strong>Mr Royston Shieh<\/strong>\u00a0(<a href=\"mailto:shiehtw@nus.edu.sg\">shiehtw@nus.edu.sg<\/a>)<\/p>\n<p>Complex machines such as those used in lithography perform within very specific controlled conditions. Turbulent flow in cooling channels can result in performance degradation and disrupt the nanometer accuracy required in the industry. One of such contributing factors is the presence of bubbles in the cooling circuit. During the maintenance of such complex machines, the coolant must be drained and refilled in the shortest time possible to optimize the uptime of the machines.<\/p>\n<p>The goal of this project is to introduce technical problem-solving skill by thinking beyond the object boundaries like a system engineer. In this holistic approach, the students will explore the basics of fluid dynamics followed by developing a process and design solution which will most effectively fill a cooling circuit with a standard detachable flange. The team shall develop a filling process, and make design improvements from the standard flange with given boundary conditions. The goal is to prevent and remove any trapped bubbles in the circuit. They are to build a simple test set-up with a monitoring system capable of identifying air bubbles, and validate their solution (filling process) and flange designs using the test set up.<\/p>\n<p>Project scope:<\/p>\n<ul>\n<li>Explore the basics of fluid dynamics and their impact in cooling systems.<\/li>\n<li>Explore a variety of solutions and narrow down the options with help from design of experiment.<\/li>\n<li>Develop a process which minimizes bubbles creation during a filling process.<\/li>\n<li>Generate an FMEA for flange designs and test set up.<\/li>\n<li>Improve the design of a given standard flange to minimize\/prevent trapping air bubbles.<\/li>\n<li>Build a simple test set-up capable of measuring bubbles and maybe vibrations.<\/li>\n<li>Test and validate their solution using the set-up to achieve a bubble free circuit within the shortest fill time.<\/li>\n<\/ul>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-3\">Creating iconic audio experiences: indoor high precision localisation<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-3\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-3\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisors: <b>Dr Yen Shih Cheng <\/b>(<a href=\"mailto:shihcheng@nus.edu.sg\">shihcheng@nus.edu.sg<\/a>), <strong>Mr Graham Zhu<\/strong> (<a href=\"mailto:graham.zhu@nus.edu.sg\">graham.zhu@nus.edu.sg<\/a>)<\/p>\n<p>Industry partner\/collaborator: Bang &amp; Olufsen<\/p>\n<p>With the advent of computational audio, smart speakers now have the ability to use advanced algorithms and audio processing techniques to place sounds in different parts of a room, creating immersive audio landscapes. In addition, by using precise positioning technologies like Ultra-Wideband (UWB) or millimeter wave (mmWave) to localise the listener, these immersive experiences can potentially be automated and even follow a listener as they move around a room.<\/p>\n<p>In this project (working with our industry partner Bang &amp; Olufsen (<a href=\"https:\/\/www.bang-olufsen.com\/en\/sg\">https:\/\/www.bang-olufsen.com\/en\/sg<\/a>), we will explore how to get the best positional accuracy using estimates from multiple UWB devices or combining with mmWave devices.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/cde.nus.edu.sg\/edic\/wp-content\/uploads\/sites\/37\/2026\/04\/CDE4301-2026-iconic-audio-1024x535.png\" alt=\"\" width=\"1024\" height=\"535\" \/><\/p>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-4\">Educational technology: automated assessment creation tool<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-4\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-4\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisor: <strong>A\/Prof<\/strong><b> Mark De Lessio <\/b>(<a href=\"mailto:mdeles@nus.edu.sg\">mdeles@nus.edu.sg<\/a>)<\/p>\n<p>This project is based in the concept of how to fairly assess student comprehension based on the content delivery of the learning environment. The premise is the development of a device\/app that can be used to record\/scan delivered content and then automatically create assessments to measure the understanding of the content that has been delivered. There are a number of options to possibly achieve this through variations of AI ranging from doing key word assessment on the digitized content and then automatically determine the best assessment questions selected from a pool of pre-determined questions to actually developing the ability to automate the creation of relevant assessment material\/questions based on the digitized content that has been captured. A significant goal is to ensure that the assessment is most closely based on the content that has actually been delivered.<\/p>\n<p>Part of the goal of this project is to determine what AI technology is currently available to achieve the basic objective of the project and when technology may become available to continuously improve on it considering that the ultimate goal is to minimize human input as much as possible (i.e. manually creating question pools as opposed to having questions automatically created by the application).<\/p>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-5\">LifeQuest: game-based platforms for life skills development in AWWA schools<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-5\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-5\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisors: <strong>A\/Prof Lim Li Hong Idris<\/strong> (<a href=\"mailto:lhi.lim@nus.edu.sg\">lhi.lim@nus.edu.sg<\/a>), <b>Dr Kate Sangwon Lee\u00a0<\/b>(<a href=\"mailto:katelee@nus.edu.sg\">katelee@nus.edu.sg<\/a>)<\/p>\n<p>Industry partner\/collaborator: Asian Women&#8217;s Welfare Association in Singapore (AWWA)<\/p>\n<p>AWWA&#8217;s special education schools provide students with autism, aged 7 to 18, with nurturing and holistic educational experiences that build their independence and maximise their potential in tandem with their capabilities and aspirations. Children diagnosed with Autism Spectrum Disorder (ASD) often encounter significant challenges in developing the life skills necessary for independent living. Yet these competencies are critical for their long-term independence and quality of life.<\/p>\n<p>Despite growing awareness of autism in Singapore and globally, there remains a shortage of accessible, scalable, and engaging tools to support life skills training for children with ASD. Key challenges include:<\/p>\n<ul>\n<li>Inconsistent training environments: Real-world environments such as MRT stations are unpredictable and can overwhelm children who depend on routine and structure.<\/li>\n<li>Lack of technology-driven solutions: While educational games exist, few are designed specifically for autistic children with a focus on real-world daily activities.<\/li>\n<\/ul>\n<p>This project aims to design and develop a platform that is engaging, structured, repeatable, and accessible &#8211; one that mirrors real-life scenarios in a safe environment that children can navigate at their own pace.<\/p>\n<p>The scope of the project includes the following:<\/p>\n<ul>\n<li>Study the needs of students with autism and select appropriate engagement tools.<\/li>\n<li>Design and develop a platform that simulates real-world daily life scenarios, with an initial focus on navigating the MRT system.<\/li>\n<li>Apply evidence-based principles of autism-friendly design, including predictable interactions, visual cues, low sensory overload, and positive reinforcement mechanics.<\/li>\n<li>Create a platform that is intuitive and usable by autistic children aged 9 to 16 without requiring constant adult supervision.<\/li>\n<li>Provide caregivers and therapists with a dashboard to monitor skill acquisition over time.<\/li>\n<li>Evaluate the user experience, stability and repeatability.<\/li>\n<\/ul>\n<p><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/cde.nus.edu.sg\/edic\/wp-content\/uploads\/sites\/37\/2026\/04\/CDE4301-2026-LifeQuest.jpeg\" alt=\"\" width=\"756\" height=\"567\" \/><\/p>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-6\">Machine learning-based flow regime classifier for horizontal gas-liquid pipe flow<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-6\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-6\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisors:\u00a0<strong>Mr Royston Shieh<\/strong>\u00a0(<a href=\"mailto:shiehtw@nus.edu.sg\">shiehtw@nus.edu.sg<\/a>),\u00a0<strong>A\/Prof Loh Wai Lam<\/strong>\u00a0(<a href=\"mailto:mpelohwl@nus.edu.sg\">mpelohwl@nus.edu.sg<\/a>)<\/p>\n<p>Predicting when flow in a horizontal pipeline transitions from stable stratified flow to potentially damaging slug flow is a critical design challenge in the oil and gas industry. Classical models such as Taitel-Dukler (1976) are widely used but were derived under simplifying assumptions that reduce accuracy at elevated operating pressures. There is a practical need for a fast, data-driven prediction tool that can generalize across a wide range of operating conditions and pipe geometries without requiring expensive experiments or simulations for every new case.<\/p>\n<p>This project challenges the student to design, train, and validate a machine learning classification tool that predicts the stratified-to-slug flow transition boundary in horizontal gas-liquid pipe flow. The student will first conduct a structured literature review of flow regime transition physics and existing prediction methods, then compile a labelled training dataset from published experimental flow maps using dimensionless input features, liquid and gas Reynolds numbers, liquid Froude number, E\u00f6tv\u00f6s number, and dimensionless operating pressure.<\/p>\n<p>A baseline classifier (random forest or support vector machine) will be designed and tested in Semester 1, followed by refinement using a neural network architecture and systematic evaluation against held-out data and classical model predictions in Semester 2. The final deliverable is a validated, documented prediction tool with quantified accuracy and clearly identified operating limits.<\/p>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-7\">Proving the payback: data driven validation of energy saving technologies<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-7\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-7\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisor:\u00a0<strong>Mr Royston Shieh<\/strong>\u00a0(<a href=\"mailto:shiehtw@nus.edu.sg\">shiehtw@nus.edu.sg<\/a>)<\/p>\n<p>Industry partner\/collaborator: CapitaLand Ascott Trust<\/p>\n<p>At the corporate headquarters (HQ) level, teams regularly collaborate with technology vendors to pilot new energy saving solutions and equipment across properties. These pilots are intended to validate whether the technologies perform as claimed and whether the resulting energy savings justify broader roll out across the portfolio.<\/p>\n<p>However, reliably quantifying energy savings during pilot periods remains a major challenge. Energy consumption is influenced by fluctuating factors such as weather conditions and occupancy levels, and many properties lack comprehensive sensor infrastructure or historical baseline data for comparison. As a result, reported savings from vendors may not align clearly with observed changes in utility bills, making it difficult for HQ teams to make confident, evidence based scaling decisions. There is therefore a strong need for a practical, cost effective approach to energy savings quantification that works with limited data while remaining robust and transparent.<\/p>\n<p>This project aims to design and prototype a cost effective, data driven methodology or decision support tool that enables HQ teams to quantify and validate energy savings from technology pilots under real world operating conditions. The solution should achieve the following:<\/p>\n<ul>\n<li>Enable fair and repeatable comparison of energy performance across pilot and non pilot periods<\/li>\n<li>Account for variability in influencing factors (eg climate, occupancy, and usage) without excessive manual effort<\/li>\n<li>Reduce dependence on expensive sensing infrastructure by identifying suitable proxies and alternative data sources<\/li>\n<li>Reconcile differences between vendor claimed savings and actual utility bill outcomes to support confident scale up decisions<\/li>\n<\/ul>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-8\">Smart wearables: a new ubiquitous interface for daily life<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-8\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-8\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisor:\u00a0<b>Dr Cai Shaoyu<\/b>\u00a0(<a href=\"mailto:shaoyucai@nus.edu.sg\">shaoyucai@nus.edu.sg<\/a>)<\/p>\n<p>Smart wearables are transforming how we interact with the world, offering seamless and context-aware interfaces that integrate into everyday life. This project explores the design, development, and application of smart wearable technologies as ubiquitous interfaces that bridge physical and digital experiences. By embedding sensors, actuators, and communication modules into everyday accessories such as watches, glasses, clothing, or bands, these devices can perceive environmental cues, monitor user states, and deliver personalised feedback in real time. The project investigates key challenges in usability, comfort, data privacy, and multimodal interaction while prototyping wearable systems that enhance daily activities.<\/p>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-9\">Talent acquisition process improvement<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-9\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-9\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisor: <strong>A\/Prof<\/strong><b> Mark De Lessio <\/b>(<a href=\"mailto:mdeles@nus.edu.sg\">mdeles@nus.edu.sg<\/a>)<\/p>\n<p>In industry the terms recruitment and talent acquisition are often used interchangeably referring to the requirement of filling an immediate or expected responsibility gap in the organization&#8217;s current employee profile. However, many human resource experts would suggest that while the two are related they are quite separate entities. Puja Lawanji defines recruitment as the process of filling a vacancy as the need arises while differentiating talent acquisition as a broader hiring strategy (Lawanii 2019). In fact, this concept of &#8220;a broader hiring strategy&#8221; summarizes findings in existing literature which typically suggests that the talent acquisition process is represented by multiple stages beginning with a talent requirement realization and ending with on-boarding the hired candidate. However, these many representations are often flawed by missing stages, convolution between primary and sub-primary steps and skewed representation to a particular industry sector.<\/p>\n<p>One possible model suggests that the talent acquisition process includes the stages: Hiring Strategy, Value Requirements, Candidate Identification, Candidate Assessment, Candidate Selection, On Boarding and Retention and recognizes the subset of recruitment to include the stages of Value Requirements, Candidate Identification, Candidate Assessment and Candidate Selection. While there are many organizations that specialize in one aspect or another this overall process, very few consider it holistically. This project entails coming up with a product\/service that considers the entire talent acquisition process to ensure that organizations are consistently recruiting and retaining the best candidates. It may include the development of one or more related applications that work in unison and consider each stage of the overall process.<\/p>\n<h4>\n\t\t\tInnovations in Space Systems\t<\/h4>\n\t<p>Projects in this theme delve into solutions for the space industry and developing capabilities for future space missions.<\/p>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-0\">CanSat competition<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-0\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-0\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisors: <strong>Mr<\/strong><b> Eugene Ee <\/b>(<a href=\"mailto:wheee@nus.edu.sg\">wheee@nus.edu.sg<\/a>), <strong>Mr Soh Eng Keng<\/strong> (<a href=\"mailto:ek.soh@nus.edu.sg\">ek.soh@nus.edu.sg<\/a>), <strong>Dr Goh Shu Ting<\/strong> (<a href=\"mailto:elegst@nus.edu.sg\">elegst@nus.edu.sg<\/a>)<\/p>\n<p>This project aims to get students involved in the design, build, test and launch of a CanSat for the annual AAS CanSat Competition. We are looking for motivated final year project students across various engineering disciplines who are interested in taking part in this challenge for the 2027 competition season. In addition to the FYP deliverables, students will have to make quality submissions for the competition reviews eg. Preliminary Design Review (PDR), Critical Design Review (CDR), etc. in order to qualify for launch day held in the United States.<\/p>\n<p>In depth competition details can be found in this link: <a href=\"https:\/\/cansatcompetition.com\/\">https:\/\/cansatcompetition.com\/<\/a><\/p>\n<p>For more information about the project, please contact Mr Eugene Ee (Telegram dm: @wheee54).<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/cde.nus.edu.sg\/edic\/wp-content\/uploads\/sites\/37\/2024\/03\/CanSat-logo-300x300.png\" alt=\"\" width=\"300\" height=\"300\" \/><\/p>\n\t\t\t\t\t<a role=\"heading\" id=\"fl-accordion--label-1\">Galassia-5<\/a>\n\t\t\t\t\t\t\t\t\t\t\t<button type=\"button\" id=\"fl-accordion--icon-1\" aria-expanded=\"false\" aria-controls=\"fl-accordion--panel-1\"><i>Expand<\/i><\/button>\n\t\t\t\t\t<p>Project supervisors: <strong>Mr<\/strong><b> Eugene Ee <\/b>(<a href=\"mailto:wheee@nus.edu.sg\">wheee@nus.edu.sg<\/a>), <b>A\/Prof Chua Tai Wei <\/b>(<a href=\"mailto:taiwei@nus.edu.sg\">taiwei@nus.edu.sg<\/a>)<\/p>\n<p>This project aims to get students involved in the design and development of subsystems to be flown on our upcoming Galassia-5 undergraduate student built CubeSat mission. Projects can range from FPGA development, RF design and testing, PCB design, mechanical design, satellite integration and testing, etc. FYP students will be expected to work alongside the current student team towards key project milestones and deliverables set by the project grantor.<\/p>\n<p>For more information about the project, please contact Mr Eugene Ee (Telegram dm: @wheee54).<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/cde.nus.edu.sg\/edic\/wp-content\/uploads\/sites\/37\/2026\/04\/CDE4301-2026-Galassia-1024x731.png\" alt=\"\" width=\"1024\" height=\"731\" \/><\/p>\n\n","protected":false},"excerpt":{"rendered":"<p>UROP projects for AY2026\/2027 We welcome all students from the College of Design and Engineering to work on ad-hoc projects under CDE2605 Undergraduate Research Opportunities Programme (UROP). We have a diverse range of projects that are offered by our faculty members and industry partners. They are grouped into a number of broad themes below. Students [&hellip;]<\/p>\n","protected":false},"author":171,"featured_media":0,"parent":4674,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_acf_changed":false,"rs_blank_template":"","rs_page_bg_color":"","slide_template_v7":"","site-sidebar-layout":"default","site-content-layout":"default","ast-site-content-layout":"default","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"disabled","ast-breadcrumbs-content":"","ast-featured-img":"disabled","footer-sml-layout":"","ast-disable-related-posts":"","theme-transparent-header-meta":"default","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"set","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"footnotes":""},"class_list":["post-20492","page","type-page","status-publish","hentry"],"acf":[],"_links":{"self":[{"href":"https:\/\/cde.nus.edu.sg\/edic\/wp-json\/wp\/v2\/pages\/20492","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cde.nus.edu.sg\/edic\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/cde.nus.edu.sg\/edic\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/cde.nus.edu.sg\/edic\/wp-json\/wp\/v2\/users\/171"}],"replies":[{"embeddable":true,"href":"https:\/\/cde.nus.edu.sg\/edic\/wp-json\/wp\/v2\/comments?post=20492"}],"version-history":[{"count":4,"href":"https:\/\/cde.nus.edu.sg\/edic\/wp-json\/wp\/v2\/pages\/20492\/revisions"}],"predecessor-version":[{"id":20565,"href":"https:\/\/cde.nus.edu.sg\/edic\/wp-json\/wp\/v2\/pages\/20492\/revisions\/20565"}],"up":[{"embeddable":true,"href":"https:\/\/cde.nus.edu.sg\/edic\/wp-json\/wp\/v2\/pages\/4674"}],"wp:attachment":[{"href":"https:\/\/cde.nus.edu.sg\/edic\/wp-json\/wp\/v2\/media?parent=20492"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}