@article{4645,
  author = {Yong Liu, Xiaojiao Shen},
  title = {Enhanced Algorithms of Teaching Resources for Chemistry Learning Using an Improved Genetic Algorithm},
  journal = {Journal of Information Technology Review},
  year = {2026},
  volume = {17},
  number = {1},
  doi = {https://doi.org/10.6025/jitr/2026/17/1/22-36},
  url = {https://www.dline.info/jitr/fulltext/v17n1/jitrv17n1_3.pdf},
  abstract = {This article presents an improved genetic algorithm (DGA) to optimize teaching resource allocation particularly
classroom assignments for chemistry courses. Traditional scheduling methods are often inefficient and
inflexible, particularly for lab based disciplines that require spatial continuity. The proposed DGA uses decimal
encoding (rather than binary) to reduce chromosome length and avoid the Hamming cliff problem,
thereby enhancing computational efficiency and accelerating convergence. The fitness function prioritizes
minimizing classroom changes between consecutive periods by evaluating teaching building, floor, and location
proximity. Genetic operators including elite retention, improved single point crossover, and mutation
are tailored to reinforce classroom continuity while maintaining population diversity. Comparative experiments
with a standard genetic algorithm (SGA) show that DGA achieves higher fitness values and faster
execution times. In real world testing with undergraduate chemistry classes, students in the DGA-optimized
group (Group A) outperformed the control group (Group B) in both average scores and performance consistency.
Statistical analysis, including t-tests and Cohen's d effect sizes, confirms the educational significance
of the improvements, especially in Chemistry (1), where a medium to large effect (d ~ 0.65) was observed.
The study concludes that the improved algorithm effectively enhances scheduling efficiency, instructional
continuity, and student learning outcomes, with potential for broader application across educational contexts.},
}