Computer Science - Conference Items

Permanent URI for this collection

https://hdl.handle.net/10468/568

Browse

Recent Submissions

Now showing 1 - 5 of 354
  • Thumbnail Image
    Item
    Carbon stock estimation at scale from aerial and satellite imagery
    (Institute of Electrical and Electronics Engineers (IEEE), 2024) To, Alex; Pham, Hoang Quoc Viet; Nguyen, Quang H.; Davis, Joseph G.; O’Sullivan, Barry; Pan, Shan L.; Nguyen, Hoang D.; Science Foundation Ireland
    In the ongoing efforts to mitigate climate change effect, the capability to reliably estimate forest carbon stock on a global scale is vital to support sustainable development. This entails the investigation of tree coverage from diverse forest ecosystems worldwide, necessitating a substantial volume of high-resolution images. This paper integrates a variety of remote sensing data sources, from aerial to satellite imagery, for the training and development of our AI system. Given the heterogeneous nature of these data sources, we develop a standardization method to ensure consistent image size and resolution between source platforms. Our harmonized dataset includes 86,088 training images and 21,768 validation images, each with a high resolution of 1.194 m2 per pixel. We introduce a novel technique for tree semantic segmentation which offers a more effective alternative to traditional individual tree crown delineation for large-scale tree coverage estimation. To assess the adaptability of our AI models, we conducted experiments on a hand-annotated satellite image test set and achieved a High Vegetation IoU score of 45.73%. Building on these findings, we present an interactive web-based Geographic Information System for navigating high vegetation segmented satellite images and estimating carbon stock on a global scale.
  • Thumbnail Image
    Item
    Multimedia learning analytics feedback in simulation-based training: A brief review
    (Association for Computing Machinery (ACM), 2024) Le, Lai Hoang; Nguyen, Hoang D.; Crane, Martin; Mai, Tai Tan; Science Foundation Ireland; European Regional Development Fund
    Learning analytics has gained significant attention in recent years, particularly in the healthcare field. This area of research offers valuable insights to educators, students, and researchers to enhance the quality of education. One area of focus in learning analytics is how stakeholders provide feedback to each other during training in operating theatres. With the availability of diverse multimedia elements, such as text, images, and spoken language, as data, employing effective feedback methods can bring substantial benefits to teachers, students, and researchers. This study synthesizes various approaches that apply multimedia to provide feedback in teaching, comparing and exploring their potential application in simulation-based medical training. The feasibility of input data, the effectiveness of feedback on recipients, and the AI method of generating or synthesizing feedback using existing data efficiency are also discussed in line with ethical standards. Finally, a multimedia feedback framework is proposed, which utilizes diverse multimedia formats and can be effectively implemented in various realworld scenarios.
  • Thumbnail Image
    Item
    LLM-powered multimodal AI conversations for diabetes prevention
    (Association for Computing Machinery (ACM), 2024) Dao, Dung; Teo, Jun Yi Claire; Wang, Wenru; Nguyen, Hoang D.; Science Foundation Ireland; Ministry of Health -Singapore; European Regional Development Fund
    The global prevalence of diabetes remains high despite rising life expectancy with improved quality and access to healthcare services. The significant burden that diabetes imposes warrants efforts to improve existing interventions in diabetes care. Present research on diabetes management has shown that artificial intelligence (AI) and Large Language Models (LLM) play an important role in various aspects of the diabetes continuum but a distinct lack of studies in diabetes prevention is observed. Our research introduces a comprehensive digital solution, leveraging the capabilities of GPT- 3.5 models maintained by OpenAI, focused specifically on the active prevention of diabetes. The system encompasses a user-friendly interface accessible via mobile and web applications, an AI-powered chatbot for instant Q&A and advice, personalized reminder systems, a data analysis module for tailored guidance, resource aggregators for health-related information, and an emotional support module to ensure a holistic approach to prevention. Furthermore, our experiments involved testing the quality of responses generated by a fine-tuned GPT-3.5 model, utilizing the Assistants API or a retrieval-augmented generation (RAG) system powered by FAISS for enhanced context awareness and personalized advice. The testing focused on a structured dataset of questions and answers related to diabetes prevention, with results highlighting the superiority of the GPT-3.5 model combined with the Assistants API in providing relevant, detailed, and personalized responses, thus demonstrating its potential as an invaluable tool in the proactive prevention of diabetes.
  • Thumbnail Image
    Item
    Towards trustworthy AI systems: A human-AI interaction study
    (2024) Nguyen, Thuy-Trinh; Pan, Shan L.; Nguyen, Hoang D.
    The partnership between humans and artificial intelligence (AI) has transformed decisionmaking and brought significant improvements in various fields. However, the complex operations of AI remain a black box in many cases, causing a lack of transparency that affects human trust in AI systems, particularly in high-risk scenarios. To address this issue, multi-agent systems have been proposed, where humans and AI interact and collaborate to achieve a better outcome and trust level. This study investigates the dynamic human-AI interaction and how it affects trust. We proposed design guidelines for interactive, trustworthy AI systems and developed two prototype versions to facilitate fake profile screening on online social networks. The study reports a mean trust score of 3.84/5 between humans and AI, despite a significant difference in their decisions on 2,142 user profiles. The results offer comprehensive insights into information systems involving human-AI interactions and underscore the increasing necessity for trustworthy AI.
  • Thumbnail Image
    Item
    Autofusion: Fusing multi-modalities with interactions
    (Elsevier, 2024) Nguyen, Thuy-Trinh; Deligianni, Fani; Nguyen, Hoang D.; Science Foundation Ireland
    In the context of escalating data flows through diverse channels, multimodal machine learning holds the potential to simultaneously process varied data formats from multiple sources, offering robust solutions for uncertainty in various applications. The study highlights the often under-explored correlation information among data modalities and emphasizes the importance of disentangling enriched interactions for more informed decision-making. This paper navigates the burgeoning field of multimodal artificial intelligence (AI) by proposing Autofusion, a pioneering framework addressing representation learning and fusion challenges. Our proposed approach integrates autoencoder structures to address overfitting issues in unimodal machine learning, simultaneously tackling information balancing challenges. The framework’s application in Alzheimer’s disease detection, using DementiaBank’s Pitt corpus, demonstrates promising results, outperforming unimodal methods and showcasing a substantial advantage over traditional fusion techniques. This research significantly contributes by introducing Autofusion as a comprehensive multimodal machine learning solution, demonstrating its efficacy through DementiaBank’s Pitt corpus to detect Alzheimer’s disease, and shedding light on the influential role of cross-modality interaction for enhanced performance in complex applications.