Rapid bacterial colony classification using deep learning

Abstract

Bacterial colonies infection is one of the causes of bloodstream disease, and it can be a fatality. Therefore, medical diagnoses require fast identification and classification of organisms. Artificial Intelligence with deep learning (DL) can now be developed as a rapid bacterial classification. The research aims to combine deep learning and support vector machines (SVM). The ResNet-101 model of the DL algorithm extracted the image’s features using transfer learning then classified by the SVM classifier. According to the experimental results, this model had 99.61% accuracy, 99.58% recall, 99.58% precision, and 99.97% specificity. The technique presented might enhance clinical decision-making.

Machine learning approaches in the diagnosis of infectious diseases: a review

“…Ensemble technique became state of art that produces better results than the existing models [48], [49]. Table 2 (see in Appendix) [23], [27], [32], [35]- [47], [50]- [61] summarizes reviewed articles on infectious disease diagnosis using various ML techniques. As ML techniques have shown their potential in medical systems, there is still sufficient potential to rise in various areas [14], [62].…”

“…𝑛, 𝑥𝑖𝑅𝑑, 𝑦𝑖  {−1, 1} be separated by a Hyperplane with margin ρ then distance from example xi to the separator is, 𝑟 = 𝑤 𝑇 𝑥 𝑖 + 𝑏 ‖𝑤‖ commonly used SVM algorithms are the support vector regression, least squares SVM, and successive projection algorithm-SVM [4]. SVMs are widely used in pattern recognition and classification and have been effectively used in various real-world problems [25]- [27].…”

“…However, the CNN model does not encode the object's position and orientation and needs a lot of training data to work efficiently. These networks can be trained to recognize visual patterns, including voice, handwriting, and image recognition [27], [35]- [40]. As a result, modern NNs are significantly more potent than their predecessors.…”

A computational intelligent analysis of autism spectrum disorder using machine learning techniques

“…In the future, it is suggested to use a large-size data set to compare our classification models. The CNN technique can interpret brain biomarkers in ASD patients using fMRI [26].…”

“…The class/ASD dataset [24], [25] has been employed, with subgroups based on age and verbal intelligence quotient (VIQ) used for analysis via the RF model. Although the obtained classification accuracy is relatively low, it can serve as a useful reference for clinical diagnosis and early detection of ASD [26]. Explored the classification of images using pre-trained CNN models, namely VGG16, VGG19, InceptionV3, and ResNet101 [27].…”