DIGITAL LIBRARY
DELAY TOLERANT NETWORK AND ARTIFICIAL INTELLIGENCE TECHNOLOGY ON RESILIENT LEARNING
1 ISPGAYA (PORTUGAL)
2 ISPGAYA; CEOS.PP (PORTUGAL)
About this paper:
Appears in: EDULEARN24 Proceedings
Publication year: 2024
Pages: 2746-2753
ISBN: 978-84-09-62938-1
ISSN: 2340-1117
doi: 10.21125/edulearn.2024.0747
Conference name: 16th International Conference on Education and New Learning Technologies
Dates: 1-3 July, 2024
Location: Palma, Spain
Abstract:
Learning environment approaches are becoming a common option for learning experiences. After the COVID19 pandemic the e-learning model has been experiencing sustained growth, delivering several advantages such as user convenience, reduced carbon footprint, and enabling access for geographically dispersed users, in particular in underdeveloped countries or in catastrophe scenarios. The blending of technologies such as AR (Augmented Reality), VR (Virtual Reality), IoT (Internet of Things) and AI (Artificial Intelligence) promote a richer and immersive experience for the lecturer and students. The work presented is a description about an innovative adoption of strategies such as DTN (Delay Tolerant Network) approach supported by ML (Machine Learning) tools to enable optimized resources delivery and operate with intermittent connectivity. The blend of DTN and AI is described as an innovative solution for bringing robustness and even added security on the delivery of rich learning content. An extensive literature review and a discussion about the topic of using DTN with smart routing applied to e-learning platforms is presented.

The results enable a model proposal - a combining function - on applying DTN on e-learning, composed of artificial intelligence model types such as Recurrent Neuronal Networks (RNMs) in order to handle sequential data like text, speech, or even financial data, or Kalman Filters (KF), that provide a statistically optimal solution for estimating the evolving state concerning the position or velocity of a moving node. The optimization on resources provided by an e-learning environment model comprehend the user daily routine and external influences, such as traffic and special events.

The combining function applied in the process will provide a more accurate prediction model, quickly developed to aid in the smart routing of DTN thus enabling a faster routing decision along with an increased reliability in the data delivery enabling an effective use of e-learning platforms in spite of poor connectivity scenarios.
Keywords:
Delay Tolerant Networks, Artificial Intelligence, e-learning, Reliability on data delivery, Immersive Learning Experience.