Digital storytelling has been widely explored in mathematics education to situate abstract problems within meaningful narrative contexts. However, most existing systems present stories through static media such as text and images, offering limited opportunities for active engagement. In this paper, we present MathsTale, a storytelling web application we developed for teaching children abstract mathematical problems through interactive multimodal stories. The system adopts a multi-agent architecture and leverages generative artificial intelligence to produce narrative text, images, and executable code for interactive hands-on activities. To explore its potential, we conducted a preliminary user study involving children and teachers using semi-structured interviews. Findings suggest that interactive multimodal stories can enhance children’s understanding, enjoyment, and engagement in learning mathematical problems.

The present study aims to investigate the relationship between emotions experienced during learning and metacognition in typically developing (TD) children and those with autism spectrum disorder (ASD). This will assist us in using machine learning (ML) to develop a facial emotion recognition (FER) based intelligent tutor system (ITS) to support children’s metacognitive monitoring process in order to enhance their learning outcomes. In this paper, we first report the results of our preliminary research, which utilized an ML-based FER algorithm to detect four spontaneous epistemic emotions (i.e., neutral, confused, frustrated, and boredom) and six spontaneous basic emotions (i.e., anger, disgust, fear, happiness, sadness, and surprise). Subsequently, we adapted an application (‘BrainHood’) to create the ‘Meta-BrainHood’, that embedded our proposed ML-based FER algorithm to examine the relationship between facial emotion expressions and metacognitive monitoring performance in TD children and those with ASD. Finally, we outline the future steps in our research, which adopts the outcomes of the first two steps to construct an ITS to improve children’s metacognitive monitoring performance and learning outcomes.

In this extended abstract, we outline a PhD project which investigates the relationship between emotion and metacognition in children with Autism Spectrum Disorder (ASD) in order to design and develop an automatic Machine Learning based tool with real-time feedback to support metacognitive process of both Typically Developing (TD) children and children with ASD.

In this paper, we propose an OpenFlow enabled Internet infrastructure, using virtual path slicing in an end-to-end path, so that any user connected to an OpenFlow network is dynamically allocated a corresponding right of way. This approach allows an interference-free path, from other traffic, between any two endpoints, on multiple autonomous systems, for a given application flow (e.g., WebHD Video Streaming). Additionally, we propose and implement an end-to-end quality of service framework for the Future Internet and extend the virtual path slice engine to support future Internet technologies such as OpenFlow. The proposed framework is evaluated in distinct multiple autonomous scenarios for a city with a population of 1 million inhabitants, emulating xDSL (Digital Subscriber Line), LTE (Long-Term Evolution) and Fibre networking scenarios. The obtained results confirm the suitability of the proposed architecture between multiple autonomous systems, considering both data and control traffic scalability, as well as resilience and failure recovery. Furthermore, challenges and solutions for experimentation in a large-scale testbed are described.

Grid application performance is inherently dependent on the performance and reliability of the underlying network. In a production Grid infrastructure, network performance monitoring (NPM) information is required both for middleware resource-brokering decisions and operational monitoring. A variety of NPM frameworks are available which can provide such information. However, the diverse global nature of the EGEE (Enabling Grids for E-sciencE) fabric means it is impractical to mandate a single monitoring solution. In this paper we propose a broker-based federated architecture for integration of NPM information from a heterogeneous set of monitoring frameworks, which provides simplified access to the frameworks for clients. We also present an overview of the requirements for NPM gathered from EGEE middleware developers and operational monitoring users. Finally, we describe our pilot implementation which has proven the validity of the architecture and demonstrated the first integrated access to backbone and end-to-end data gathered using different monitoring frameworks.

Production Grid infrastructure requires end-to- end guarantees on the Quality of Service from the underlying networks. In this paper, we present use cases for advance network resource reservation and then describe a multi-layered architecture that can support them. The architecture presents a single bandwidth broker, called BAR, which sits at the Grid layer. BAR not only provides a single point of access to Grid applications to reserve guaranteed end-to-end bandwidth, but also presents its interface in application terms (instead of networking terms). We expose two guaranteed bandwidth services: the Guaranteed Delivery File Transfer and Virtual Leased Line services. Integrated with the GEANT2 bandwidth on demand infrastructure, our bandwidth broker deals with multiple network domains, further insulating the applications from network concerns. We also define additional components required for an end-to-end reservation as well as the interfaces between the components. Our deployed prototype demonstrated the world's first software-based, inter-domain bandwidth reservations based on Premium IP.