Résumé:
Antibiotic resistance is a growing global problem that occurs when bacteria evolve to resist the effects of antibiotics. This makes it more difficult to treat infections and illnesses caused by these resistant bacteria. This is a serious concern because it can result in longer hospital stays, higher healthcare costs, and increased mortality rates., making it crucial to identify and classify the efficiency of antibiotics. Weka; is a data mining tool, based on machine learning algorithms that are used to analyze the data and make predictions about the effectiveness of antibiotics. One of the most important aspects of this tool is the use of classification algorithms. These algorithms are designed to classify data into different categories based on specific characteristics.
In our study Antibiotic resistance datasets are classified by six classifier algorithms. these algorithms are Naïve Bayes, J48, SMO, Random forest, Random tree, and Rep tree. To evaluate the effectiveness of classification strategies for determining accuracy and predicting class labels, the algorithm is applied to the dataset using a combination of stratified 10-fold testing and a 66/33 data split. This approach allows for a thorough assessment of the classification algorithm's performance. The results show that the performance of the J48 technique is significantly superior to the other five techniques for the classification of antibiotics data
