Machine learning algorithms in microbial classification: a comparative analysis.

This research paper presents an overview of contemporary machine learning methodologies and their utilization in the domain of healthcare and the prevention of infectious diseases, specifically focusing on the classification and identification of bacterial species. As deep learning techniques have gained prominence in the healthcare sector, a diverse array of architectural models has emerged. Through a comprehensive review of pertinent literature, multiple studies employing machine learning algorithms in the context of microbial diagnosis and classification are examined. Each investigation entails a tabulated presentation of data, encompassing details about the training and validation datasets, specifications of the machine learning and deep learning techniques employed, as well as the evaluation metrics utilized to gauge algorithmic performance. Notably, Convolutional Neural Networks have been the predominant selection for image classification tasks by machine learning practitioners over the last decade. This preference stems from their ability to autonomously extract pertinent and distinguishing features with minimal human intervention. A range of CNN architectures have been developed and effectively applied in the realm of image classification. However, addressing the considerable data requirements of deep learning, recent advancements encompass the application of pre-trained models using transfer learning for the identification of microbial entities. This method involves repurposing the knowledge gleaned from solving alternate image classification challenges to accurately classify microbial images. Consequently, the necessity for extensive and varied training data is significantly mitigated. This study undertakes a comparative assessment of various popular pre-trained CNN architectures for the classification of bacteria. The dataset employed is composed of approximately 660 images, representing 33 bacterial species. To enhance dataset diversity, data augmentation is implemented, followed by evaluation on multiple models including AlexNet, VGGNet, Inception networks, Residual Networks, and Densely Connected Convolutional Networks. The results indicate that the DenseNet-121 architecture yields the optimal performance, achieving a peak accuracy of 99.08%, precision of 99.06%, recall of 99.00%, and an F1-score of 98.99%. By demonstrating the proficiency of the DenseNet-121 model on a comparatively modest dataset, this study underscores the viability of transfer learning in the healthcare sector for precise and efficient microbial identification. These findings contribute to the ongoing endeavors aimed at harnessing machine learning techniques to enhance healthcare methodologies and bolster infectious disease prevention practices.

Distributed Neurodynamics-Based Backstepping Optimal Control for Robust Constrained Consensus of Underactuated Underwater Vehicles Fleet.

Robust constrained formation tracking control of underactuated underwater vehicles (UUVs) fleet in 3-D space is a challenging but practical problem. To address this problem, this article develops a novel consensus-based optimal coordination protocol and a robust controller, which adopts a hierarchical architecture. On the top layer, the spherical coordinate transform is introduced to tackle the nonholonomic constraint, and then a distributed optimal motion coordination strategy is developed. As a result, the optimal formation tracking of UUVs fleet can be achieved, and the constraints are fulfilled. To realize the generated optimal commands better and, meanwhile, deal with the underactuation, at the lower-level control loop a neurodynamics-based robust backstepping controller is designed, and in particular, the issue of "explosion of terms" appearing in conventional backstepping-based controllers is avoided and control activities are improved. The stability of the overall UUVs formation system is established to ensure that all the states of the UUVs are uniformly ultimately bounded in the presence of unknown disturbances. Finally, extensive simulation comparisons are made to illustrate the superiority and effectiveness of the derived optimal formation tracking protocol.

Use of AI to assess COVID-19 variant impacts on hospitalization, ICU, and death.

The rapid spread of COVID-19 and its variants have devastated communities worldwide, and as the highly transmissible Omicron variant becomes the dominant strain of the virus in late 2021, the need to characterize and understand the difference between the new variant and its predecessors has been an increasing priority for public health authorities. Artificial Intelligence has played a significant role in the analysis of various facets of COVID-19 since the early stages of the pandemic. This study proposes the use of AI, specifically an XGBoost model, to quantify the impact of various medical risk factors (or "population features") on the possibility of a patient outcome resulting in hospitalization, ICU admission, or death. The results are compared between the Delta and Omicron COVID-19 variants. Results indicated that older age and an unvaccinated patient status most consistently correspond as the most significant population features contributing to all three scenarios (hospitalization, ICU, death). The top 15 features for each variant-outcome scenario were determined, which most frequently included diabetes, cardiovascular disease, chronic kidney disease, and complications of pneumonia as highly significant population features contributing to serious illness outcomes. The Delta/Hospitalization model returned the highest performance metric scores for the area under the receiver operating characteristic (AUROC), F1, and Recall, while Omicron/ICU and Omicron/Hospitalization had the highest accuracy and precision values, respectively. The recall was found to be above 0.60 in most cases (with only two exceptions), indicating that the total number of false positives was generally minimized (accounting for more of the people who would theoretically require medical care).

Determination of spectral resolutions for multispectral detection of apple bruises using visible/near-infrared hyperspectral reflectance imaging.

This study demonstrates a method to select wavelength-specific spectral resolutions to optimize a line-scan hyperspectral imaging method for its intended use, which in this case was visible/near-infrared imaging-based multiple-waveband detection of apple bruises. Many earlier studies have explored important aspects of developing apple bruise detection systems, such as key wavelengths and image processing algorithms. Despite the endeavors of many, development of a real-time bruise detection system is not yet a simple task. To overcome these problems, this study investigated selection of optimal wavelength-specific spectral resolutions for detecting bruises on apples by using hyperspectral line-scan imaging with the Random Track function for non-contiguous partial readout, with two experimental parts. The first part identified key-wavelengths and the optimal number of key-wavelengths to use for detecting low-, medium-, and high-impact bruises on apples. These parameters were determined by principal component analysis (PCA) and sequential forward selection (SFS) with four classification methods. The second part determined the optimal spectral resolution for each of the key-wavelengths by selecting and evaluating 21 combinations of exposure time and key-wavelength bandwidths, and then selecting the best combination based on the bruise detection accuracies achieved by each classification method. Each of the four classification methods was found to have a different optimized resolution for high accuracy bruise detection, and the optimized resolutions also allowed for use of shorter exposure times. The results of this work can be used to help develop multispectral imaging systems that provide rapid, cost-effective post-harvest processing to identify bruised apples on commercial processing lines.

Corrigendum: Identification of Variable Importance for Predictions of Mortality From COVID-19 Using AI Models for Ontario, Canada.

[This corrects the article DOI: 10.3389/fpubh.2021.675766.].

Identification of Variable Importance for Predictions of Mortality From COVID-19 Using AI Models for Ontario, Canada.

The Severe Acute Respiratory Syndrome Coronavirus 2 pandemic has challenged medical systems to the brink of collapse around the globe. In this paper, logistic regression and three other artificial intelligence models (XGBoost, Artificial Neural Network and Random Forest) are described and used to predict mortality risk of individual patients. The database is based on census data for the designated area and co-morbidities obtained using data from the Ontario Health Data Platform. The dataset consisted of more than 280,000 COVID-19 cases in Ontario for a wide-range of age groups; 0-9, 10-19, 20-29, 30-39, 40-49, 50-59, 60-69, 70-79, 80-89, and 90+. Findings resulting from using logistic regression, XGBoost, Artificial Neural Network and Random Forest, all demonstrate excellent discrimination (area under the curve for all models exceeded 0.948 with the best performance being 0.956 for an XGBoost model). Based on SHapley Additive exPlanations values, the importance of 24 variables are identified, and the findings indicated the highest importance variables are, in order of importance, age, date of test, sex, and presence/absence of chronic dementia. The findings from this study allow the identification of out-patients who are likely to deteriorate into severe cases, allowing medical professionals to make decisions on timely treatments. Furthermore, the methodology and results may be extended to other public health regions.

Permutationally Invariant Deep Learning Approach to Molecular Fingerprinting with Application to Compound Mixtures.

Recent advancements in deep learning have led to widespread applications of its algorithms to synthetic planning and reaction predictions in the field of chemistry. One major area, known as supervised learning, is being explored for predicting certain properties such as reaction yields and types. Many chemical descriptors known as fingerprints are being explored as potential candidates for reaction properties prediction. However, there are few studies that describe the permutational invariance of chemical fingerprints, which are concatenated at some stage before being fed to deep learning architecture. In this work, we show that by utilizing permutational invariance, we consistently see improved results in terms of accuracy relative to previously published studies. Furthermore, we are able to accurately predict hydrogen peroxide loss with our own dataset, which consists of more than 20 ingredients in each chemical formulation.