Periodic Reporting for period 1 - i-MASTER (Integrating Adaptive Learning in Maritime Simulator-Based Education and Training with Intelligent Learning System)
Période du rapport: 2022-09-01 au 2023-08-31
The i-MASTER project aims to integrate emerging technologies into maritime education, enhancing nautical training effectiveness and operational safety through an Intelligent Learning System (ILS). This project addresses the pressing challenges highlighted by recent navigational incidents at sea and the integration of technological advancements in maritime education, aiming for transformative solutions. The project's structure comprises eight focused Work Packages (WPs):
WP 1 guides the project management, promoting collaborative decision-making and knowledge exchange among specialists.
WP 2 investigates intelligent learning methods and tools from other sectors for maritime simulator training applicability.
WP 3 develops simulations for remote and in-person training, maintaining exemplary standards and practices.
WP 4 constructs a learning analytics dashboard to track educational development and progress in maritime training.
WP 5 designs and prototypes the adaptive aspects of the ILS, improving remote simulations and AI-assisted training.
WP 6 integrates the ILS with ship simulation exercises and eye-tracking for immediate learner performance insights.
WP 7 conducts trials to evaluate the ILS's effectiveness.
WP 8 amplifies the project's influence, benefiting learners, educators and institutions, thereby serving the maritime sector and broader society.
WP 1 guides the project management, promoting collaborative decision-making and knowledge exchange among specialists.
WP 2 investigates intelligent learning methods and tools from other sectors for maritime simulator training applicability.
WP 3 develops simulations for remote and in-person training, maintaining exemplary standards and practices.
WP 4 constructs a learning analytics dashboard to track educational development and progress in maritime training.
WP 5 designs and prototypes the adaptive aspects of the ILS, improving remote simulations and AI-assisted training.
WP 6 integrates the ILS with ship simulation exercises and eye-tracking for immediate learner performance insights.
WP 7 conducts trials to evaluate the ILS's effectiveness.
WP 8 amplifies the project's influence, benefiting learners, educators and institutions, thereby serving the maritime sector and broader society.
The activities within each WP are detailed below:
WP1: Project management, communication, and coordination: This WP ensures effective management and communication among all consortium members. Project management planning tasks, development of gender equality plan, communication and coordination plan, research practice, quality assurance, risk management plan, and data management plan have all been completed.
WP2: Review of the state-of-the-art ILS technologies and KPI development, completed on 21st May 2023. This WP focused on comprehensive examination of the latest ILS technologies and potential application in MET. Several research tasks were completed in this WP, culminating in the publication of two research papers. This marked a milestone of specification of functional requirements and establishment of ILS technologies and KPIs.
WP3: WP3 has been instrumental in generating valuable research insights on maritime simulation scenario design, learning sources and performance standards for the established scenarios. Consolidated KPIs and performance metrics, which were essential for enhancing the learning analytics algorithm and the visualisation dashboard are generated. This advancement was a vital step in shaping the analytical capabilities of the ILS and contributed to the overall effectiveness of the training solution. All deliverables were submitted.
WP4: Using results from WP3, the task is to develop maritime learning analytics and develop a visualisation dashboard for simulations. A testing and evaluation of remote and on-site maritime simulations will be conducted followed by expert validation. Currently, D4.1 is under progress which will give an insight of algorithms for maritime learning analytics and visualization dashboard.
WP5: In WP5, adaptive learning function will be designed. A user interactive model will be generated based on the integration of expert, learner, and instruction model. Both qualitative and quantitative studies will be carried out to validate the developed models. ILS testable prototype(s) for nautical training will be developed from the results of previous tasks.
WP6: A prototype assessment of the maritime ILS will be carried out for remote simulation. ILS capabilities will be further extended to simulator outputs and eye tracking data to process real time data of users. Participating institutes will jointly conduct expert evaluation and validation regarding ILS systems.
WP7: Objective of WP7 is to deploy the developed learning analytics and ILS prototypes. The effectiveness and usability of prototype and its feasibility for expansion to larger maritime education and training industry will be evaluated.
WP8: This WP covers dissemination and communication of results. WP2 results were accepted for dissemination at three international outlets i.e. MIS4TEL, IEEM and AHFE conference. i-MASTER progress is made available to public through industrial events and meetings, project website, LinkedIn and other social media platforms.
WP1: Project management, communication, and coordination: This WP ensures effective management and communication among all consortium members. Project management planning tasks, development of gender equality plan, communication and coordination plan, research practice, quality assurance, risk management plan, and data management plan have all been completed.
WP2: Review of the state-of-the-art ILS technologies and KPI development, completed on 21st May 2023. This WP focused on comprehensive examination of the latest ILS technologies and potential application in MET. Several research tasks were completed in this WP, culminating in the publication of two research papers. This marked a milestone of specification of functional requirements and establishment of ILS technologies and KPIs.
WP3: WP3 has been instrumental in generating valuable research insights on maritime simulation scenario design, learning sources and performance standards for the established scenarios. Consolidated KPIs and performance metrics, which were essential for enhancing the learning analytics algorithm and the visualisation dashboard are generated. This advancement was a vital step in shaping the analytical capabilities of the ILS and contributed to the overall effectiveness of the training solution. All deliverables were submitted.
WP4: Using results from WP3, the task is to develop maritime learning analytics and develop a visualisation dashboard for simulations. A testing and evaluation of remote and on-site maritime simulations will be conducted followed by expert validation. Currently, D4.1 is under progress which will give an insight of algorithms for maritime learning analytics and visualization dashboard.
WP5: In WP5, adaptive learning function will be designed. A user interactive model will be generated based on the integration of expert, learner, and instruction model. Both qualitative and quantitative studies will be carried out to validate the developed models. ILS testable prototype(s) for nautical training will be developed from the results of previous tasks.
WP6: A prototype assessment of the maritime ILS will be carried out for remote simulation. ILS capabilities will be further extended to simulator outputs and eye tracking data to process real time data of users. Participating institutes will jointly conduct expert evaluation and validation regarding ILS systems.
WP7: Objective of WP7 is to deploy the developed learning analytics and ILS prototypes. The effectiveness and usability of prototype and its feasibility for expansion to larger maritime education and training industry will be evaluated.
WP8: This WP covers dissemination and communication of results. WP2 results were accepted for dissemination at three international outlets i.e. MIS4TEL, IEEM and AHFE conference. i-MASTER progress is made available to public through industrial events and meetings, project website, LinkedIn and other social media platforms.
Our project, as of present, has pioneered advancements beyond the state-of-the-art in the field of maritime performance evaluation. The results can be distilled into two main areas: enhanced clarity of key KPIs and performance evaluation process. Current performance assessment practices have relied on subjective and often inconsistent criteria. The initial phase of the I-MASTER project has thoroughly analyzed, defined, and extended a set of KPIs that provide a clear, measurable, and standardized benchmark for assessing navigation proficiency. These KPIs cover a comprehensive range of navigation skills and abilities, allowing for a more nuanced and precise evaluation. The clarity and robustness of these indicators represent a useful and essential step towards objective and automated performance assessment.
The application of multimodal data mining to the field of maritime education and training presents a novel research direction. The results from WP2 highlighted that, despite the same training protocols, the maritime education institutions were shown to vary in their approaches and priorities of teaching and assessing students, leading to significant variations in the conditions of knowledge of graduates. The experiments conducted during the initial phase in WP3 leveraged different Machine Learning (ML) techniques on simulation data, yielding promising advancements in the field of maritime learning analytics and we were able to discern distinct learning patterns during training. The findings from Phase 1(WP2 and WP3) also offered critical insights into effective instructional strategies and delineated user needs for the development of a specific learning analytics dashboard.
The application of multimodal data mining to the field of maritime education and training presents a novel research direction. The results from WP2 highlighted that, despite the same training protocols, the maritime education institutions were shown to vary in their approaches and priorities of teaching and assessing students, leading to significant variations in the conditions of knowledge of graduates. The experiments conducted during the initial phase in WP3 leveraged different Machine Learning (ML) techniques on simulation data, yielding promising advancements in the field of maritime learning analytics and we were able to discern distinct learning patterns during training. The findings from Phase 1(WP2 and WP3) also offered critical insights into effective instructional strategies and delineated user needs for the development of a specific learning analytics dashboard.