A Swarm Intelligence Framework for Mobile Collaborative Learning.

Saved in:

Bibliographic Details
Title:	A Swarm Intelligence Framework for Mobile Collaborative Learning.
Authors:	Sun, Junju¹ sunjunju@xyvtc.edu.cn, Mei, Yan¹ meiyan@xyvtc.edu.cn
Source:	International Journal of Interactive Mobile Technologies. 2026, Vol. 20 Issue 12, p4-18. 15p.
Subjects:	Swarm intelligence, Mobile learning, Collaborative learning, Particle swarm optimization, Synchronization, Educational planning, Distributed computing
Abstract:	The digital transformation of education driven by mobile technologies urgently requires bridging the collaborative gap between classroom and extracurricular learning. Existing systems face critical challenges, including fragmented applications of swarm intelligence, insufficient depth of mobile interaction collaboration, and limited evaluation frameworks. To address these issues, this study proposes an integrated classroom-extracurricular digital learning ecosystem that combines swarm intelligence with mobile interaction collaboration mechanisms. The system adopts a three-tier cloud-edge-mobile distributed architecture and introduces four intelligent modules optimized for mobile scenarios: (1) a dynamic learner profiling module based on an improved particle swarm optimization (PSO) algorithm, (2) a cross-scenario learning path generation module driven by hybrid swarm intelligence, (3) a decentralized collaborative scheduling module supported by a lightweight distributed consensus algorithm, and (4) a collective knowledge evolution graph construction module driven by mobile data. Through multimodal mobile data collection and edge intelligence deployment, the system achieves low-latency, low-power, and precise collaborative learning. To evaluate system performance, a multidimensional assessment framework encompassing both mobile technology performance and learning collaboration effectiveness was designed. A controlled experiment involving 200 university students simulated real-world conditions, including network fluctuations and heterogeneous devices. The proposed system outperformed the control system in both technological performance and collaborative learning effectiveness: under normal network conditions, average response latency decreased by 41.8%, mobile energy consumption decreased by 31.2%, and task completion rate in low-bandwidth scenarios increased by 39.7%. In terms of learning collaboration, cross-scenario task completion improved by 32.7% and collaborative report scores increased by 17.5%. Limitations include adaptation to low-end devices, privacy protection, and insufficient validation in complex outdoor scenarios. This study provides both theoretical support and practical paradigms for the technological innovation and large-scale deployment of mobile learning ecosystems while expanding the application boundaries of swarm intelligence in resource-constrained mobile environments. [ABSTRACT FROM AUTHOR]
	Copyright of International Journal of Interactive Mobile Technologies is the property of International Journal of Interactive Mobile Technologies and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	The digital transformation of education driven by mobile technologies urgently requires bridging the collaborative gap between classroom and extracurricular learning. Existing systems face critical challenges, including fragmented applications of swarm intelligence, insufficient depth of mobile interaction collaboration, and limited evaluation frameworks. To address these issues, this study proposes an integrated classroom-extracurricular digital learning ecosystem that combines swarm intelligence with mobile interaction collaboration mechanisms. The system adopts a three-tier cloud-edge-mobile distributed architecture and introduces four intelligent modules optimized for mobile scenarios: (1) a dynamic learner profiling module based on an improved particle swarm optimization (PSO) algorithm, (2) a cross-scenario learning path generation module driven by hybrid swarm intelligence, (3) a decentralized collaborative scheduling module supported by a lightweight distributed consensus algorithm, and (4) a collective knowledge evolution graph construction module driven by mobile data. Through multimodal mobile data collection and edge intelligence deployment, the system achieves low-latency, low-power, and precise collaborative learning. To evaluate system performance, a multidimensional assessment framework encompassing both mobile technology performance and learning collaboration effectiveness was designed. A controlled experiment involving 200 university students simulated real-world conditions, including network fluctuations and heterogeneous devices. The proposed system outperformed the control system in both technological performance and collaborative learning effectiveness: under normal network conditions, average response latency decreased by 41.8%, mobile energy consumption decreased by 31.2%, and task completion rate in low-bandwidth scenarios increased by 39.7%. In terms of learning collaboration, cross-scenario task completion improved by 32.7% and collaborative report scores increased by 17.5%. Limitations include adaptation to low-end devices, privacy protection, and insufficient validation in complex outdoor scenarios. This study provides both theoretical support and practical paradigms for the technological innovation and large-scale deployment of mobile learning ecosystems while expanding the application boundaries of swarm intelligence in resource-constrained mobile environments. [ABSTRACT FROM AUTHOR]
ISSN:	18657923
DOI:	10.3991/ijim.v20i12.62260