Answers are grounded in this paper and cite their sources.
Experimental study demonstrates enhanced knowledge integration and higher performance using a hierarchical optimization model, suggesting a scalable framework for complex engineering education.
Addressing the contradiction between heterogeneous student backgrounds and the industry demand for interdisciplinary talents, as well as fragmented knowledge modules in current curriculum reform, this paper constructs a hierarchical collaborative optimization model for landscape engineering curriculum oriented to complex-system competency cultivation. The model consists of four interconnected modules: knowledge analysis, collaborative optimization, front-end feedback, and backend optimization. The knowledge parsing module uses a knowledge-element semantic network and the Louvain algorithm to deconstruct the course into three logical levels: basic construction, system integration, and complex decision-making. The collaborative optimization module employs PageRank and Jaccard coefficients with dynamic weight allocation to generate a horizontal collaborative matrix and bind highly correlated knowledge elements. The front-end feedback module runs K-means clustering each teaching week, while the back-end feedback module runs a multi-constraint genetic algorithm after each course module. The experimental group achieves an average score of 88.58, and cross-knowledge collaborative calls increase by 174.8% compared with the control group. The model offers a transferable engineering-education optimization framework for complex-system courses, including electromagnetic and communication-engineering curricula.
No takes yet. Share an insight, caveat, or question.
Yang et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: