Artificial Neural Network-based Model for Classification Multiple Bacteria Types

Abstract

Data classification plays a crucial role in machine learning, as it entails assigning predefined labels or categories to a dataset. One highly effective approach for data classification is the utilization of artificial neural networks (ANNs), which mimic the structure and functionality of the human brain. ANNs possess the ability to learn from data, recognize patterns, and accurately classify new datasets through training. ANNs can be optimized for successful data classification processes. Moreover, ANNs exhibit remarkable adaptability and information processing capabilities, similar to the biological nervous system of the human brain. This makes them well-suited for handling complex data and adjusting to new tasks in order to achieve desired results. Particularly in the field of biosciences, where data complexity and sensitivity are prevalent, ANNs are advantageous for classifying diverse data such as different types of bacteria and human-body diseases. This paper presents a proposed Artificial Neural Network (ANN) model for the classification of five different types of bacteria using real collected data. The performance of the proposed ANN model is compared against various Machine Learning approaches, including Support Vector Machine (SVM) and Random Forest (RF). The results obtained at the conclusion of this research exhibit great promise, surpassing the current state-of-the-art methods.