Automated Swarm-Intelligence Approach for Auditable Disinfection in Smart IoT Environments

Abstract

Monitoring liquid disinfectants is essential in healthcare, food processing and water treatment, where it ensures effective pathogen elimination while maintaining compliance with safety regulations. However, classifying disinfectant-related gases and odours remains challenging because of the high dimensionality and correlated nature of gas-sensor data. Existing swarm-based feature-selection methods often suffer from limited exploration or premature convergence to local optima, particularly in such complex scenarios. At the same time, the growth of the Internet of Things (IoT) has created new opportunities to automate hygiene monitoring in pathogenic environments. To address these issues, this study proposes a binary hybrid of the grey wolf optimizer (GWO) and the genetic algorithm (GA), termed BGWOA, which selects the most informative subset of features from an array of MQ-series gas sensors while simultaneously minimizing the number of selected features. Although GWO converges rapidly, its restricted search behaviour can limit exploration and lead to premature convergence; the proposed hybrid therefore uses GWO to drive fast convergence in the early stages and GA-based mutation and selection to sustain population diversity and refine the global search in later stages. Because the precision of disinfectant identification is critical, the k-nearest neighbour (k NN) classifier is used as the wrapper fitness function to evaluate the candidate feature subsets generated by BGWOA and to identify optimal solutions. Five classical machine-learning classifiers (k NN, decision tree, Naïve Bayes, multilayer perceptron and support vector machine) are compared on a purpose-built disinfectant dataset, and the BGWOA-k NN framework consistently outperforms the individual classifiers and competing wrapper methods (GWO, PSO, BBA and GA). Across all five classifiers and five folds, BGWOA achieves a mean accuracy of 0.996 (with the BGWOA-k NN framework attaining an AUC and average precision of 1.00) against approximately 0.88 for the baselines. It is also the most efficient wrapper, requiring only 173.8 s versus 432.6 s for plain GWO. A nonparametric Friedman test confirms that these improvements are significant ($$, 4 degrees of freedom, p = 0.0159), with BGWO obtaining the best average rank (1.00) among the five algorithms. Beyond accuracy, the proposed system supports auditable disinfection by promoting the consistent and correct use of disinfectants by facility personnel, thereby reducing potential health risks.