Strategies for optimising chemical instrumental analysis methods based on the ADDIE model

Abstract

In order to study the optimization strategy of chemical instrumentation analysis methods, it can make the chemical instrumentation analysis methods more optimized. This paper proposes an improved sparrow search algorithm MSSA based on the ADDIE model, and a decision tree analysis method under random forest is introduced to assist chemical instrumentation analysis. The optimal prediction value of the algorithm is judged analytically, and adaptive operations change the size of the neighbourhood space to obtain the optimal strategy of the algorithm by a merit-seeking mechanism. The decision tree and evaluation indicators are then constructed with the decision tree under a random forest algorithm, and the indicators are used to select the optimisation path. From the experiments, it can be seen that the improved sparrow search algorithm MSSA strategy based on the ADDIE model can improve the optimisation ability of the algorithm. Furthermore, the MSSA algorithm also shows excellent performance in the experiments and obtains the best coverage effect. The coverage rate of the optimised chemical instrumentation analysis method reached 94.55%, which was 9.87%, 4.15%, 6.68%, 3.22% and 7.28% higher than other types of algorithms, respectively. It illustrates that the improved MSSA algorithm under the ADDIE model can also obtain better optimisation capability for practical chemical instrumental analysis method optimisation problems. The evaluation index complements this under the decision tree, which shows that the model is more conducive to the analytical capability of chemical instruments. It also provides a direction for solving the problem of choosing the optimal analytical method in chemical instrumentation analysis.

Keywords

• addie model
• chemical instrumentation analysis methods
• mssa optimization algorithm
• random forest decision tree algorithm
• optimal prediction strategy
• 65d99