Characterisation and Classification of Foodborne Bacteria Using Reflectance FTIR Microscopic Imaging

This work investigates the application of reflectance Fourier transform infrared (FTIR) microscopic imaging for rapid, and non-invasive detection and classification between Bacillus subtilis and Escherichia coli cell suspensions dried onto metallic substrates (stainless steel (STS) and aluminium (Al) slides) in the optical density (OD) concentration range of 0.001 to 10. Results showed that reflectance FTIR of samples with OD lower than 0.1 did not present an acceptable spectral signal to enable classification. Two modelling strategies were devised to evaluate model performance, transferability and consistency among concentration levels. Modelling strategy 1 involves training the model with half of the sample set, consisting of all concentrations, and applying it to the remaining half. Using this approach, for the STS substrate, the best model was achieved using support vector machine (SVM) classification, providing an accuracy of 96% and Matthews correlation coefficient (MCC) of 0.93 for the independent test set. For the Al substrate, the best SVM model produced an accuracy and MCC of 91% and 0.82, respectively. Furthermore, the aforementioned best model built from one substrate was transferred to predict the bacterial samples deposited on the other substrate. Results revealed an acceptable predictive ability when transferring the STS model to samples on Al (accuracy = 82%). However, the Al model could not be adapted to bacterial samples deposited on STS (accuracy = 57%). For modelling strategy 2, models were developed using one concentration level and tested on the other concentrations for each substrate. Results proved that models built from samples with moderate (1 OD) concentration can be adapted to other concentrations with good model generalization. Prediction maps revealed the heterogeneous distribution of biomolecules due to the coffee ring effect. This work demonstrated the feasibility of applying FTIR to characterise spectroscopic fingerprints of dry bacterial cells on substrates of relevance for food processing.

Download Full-text

UV ability to inactivate microorganisms combined with factors affecting radiation

Water Science & Technology ◽

10.2166/wst.1997.0718 ◽

1997 ◽

Vol 35 (11-12) ◽

pp. 107-112 ◽

Cited By ~ 7

Author(s):

A. M. Shaban ◽

G. E. El-Taweel ◽

G. H. Ali

Keyword(s):

Microbial Communities ◽

Uv Radiation ◽

Contact Time ◽

Tap Water ◽

Scenedesmus Obliquus ◽

Morphological Characters ◽

The Other ◽

Bacterial Cells ◽

Dark Repair ◽

Nile Water

In the present study, the effect of UV radiation on the inactivation of a range of microorganisms was studied. Each organism was seeded into sterile tap water and exposed to UV in batch experiments with changing turbidities. In addition, the effect of UV on microbial communities in river Nile water was examined. It was found that 1min contact time (0.5L/min flow rate) was effective against vegetative cells levels almost reaching zero (except with Staphylococcus aureus). On the other hand, spore-forming bacteria, Candida albicans and coliphage were more resistant to UV. This contact time caused coenobia cells in single form with Scenedesmus obliquus while for Microcystis aeruginosa colonies broke into smaller groups. Exposure of Nile water microbial communities to UV showed that yeasts and Aeromonas survived better than the other organisms while in the phytoplankton partial fragmentation occurred in some algal groups. The protective effect of turbidity differed between organisms, with increased contact time under conditions of stable turbidity having no effect on the organisms. At 20 NTU the UV radiation had no effect on the morphological characters of algal cells. In reactivation experiments, it is clear that photoreactivation, and not dark repair, takes place with bacterial cells. Only coliphage had no photoreactivation and dark repair responses although with coliphage and host, both reactivation processes worked well. Moreover, the irradiated algae regained their normal shape after 3 days in suitable media and enough light.

Download Full-text

Predicting Future Occurrence of Acute Hypotensive Episodes Using Noninvasive and Invasive Features

Military Medicine ◽

10.1093/milmed/usaa418 ◽

2021 ◽

Vol 186 (Supplement_1) ◽

pp. 445-451

Author(s):

Yifei Sun ◽

Navid Rashedi ◽

Vikrant Vaze ◽

Parikshit Shah ◽

Ryan Halter ◽

...

Keyword(s):

Machine Learning ◽

Support Vector Machine ◽

Real World ◽

Short Term Memory ◽

Model Performance ◽

Learning Technologies ◽

Machine Learning Algorithms ◽

Support Vector ◽

K Nearest Neighbor ◽

Continuous Map

ABSTRACT Introduction Early prediction of the acute hypotensive episode (AHE) in critically ill patients has the potential to improve outcomes. In this study, we apply different machine learning algorithms to the MIMIC III Physionet dataset, containing more than 60,000 real-world intensive care unit records, to test commonly used machine learning technologies and compare their performances. Materials and Methods Five classification methods including K-nearest neighbor, logistic regression, support vector machine, random forest, and a deep learning method called long short-term memory are applied to predict an AHE 30 minutes in advance. An analysis comparing model performance when including versus excluding invasive features was conducted. To further study the pattern of the underlying mean arterial pressure (MAP), we apply a regression method to predict the continuous MAP values using linear regression over the next 60 minutes. Results Support vector machine yields the best performance in terms of recall (84%). Including the invasive features in the classification improves the performance significantly with both recall and precision increasing by more than 20 percentage points. We were able to predict the MAP with a root mean square error (a frequently used measure of the differences between the predicted values and the observed values) of 10 mmHg 60 minutes in the future. After converting continuous MAP predictions into AHE binary predictions, we achieve a 91% recall and 68% precision. In addition to predicting AHE, the MAP predictions provide clinically useful information regarding the timing and severity of the AHE occurrence. Conclusion We were able to predict AHE with precision and recall above 80% 30 minutes in advance with the large real-world dataset. The prediction of regression model can provide a more fine-grained, interpretable signal to practitioners. Model performance is improved by the inclusion of invasive features in predicting AHE, when compared to predicting the AHE based on only the available, restricted set of noninvasive technologies. This demonstrates the importance of exploring more noninvasive technologies for AHE prediction.

Download Full-text

Repeatability, Completion Time, and Predictive Ability of Four Diabetes-Related Foot Ulcer Classification Systems

Journal of Diabetes Science and Technology ◽

10.1177/1932296820986548 ◽

2021 ◽

pp. 193229682098654

Author(s):

Chanika Alahakoon ◽

Malindu Fernando ◽

Charith Galappaththy ◽

Peter Lazzarini ◽

Joseph V. Moxon ◽

...

Keyword(s):

Foot Ulcer ◽

Predictive Ability ◽

Classification Systems ◽

The Other ◽

Observer Agreement ◽

Foot Ulcers ◽

Substantial Agreement ◽

University Of Texas ◽

Trained Observers ◽

Completion Times

Introduction: The inter and intra-observer reproducibility of measuring the Wound Ischemia foot Infection (WIfI) score is unknown. The aims of this study were to compare the reproducibility, completion times and ability to predict 30-day amputation of the WIfI, University of Texas Wound Classification System (UTWCS), Site, Ischemia, Neuropathy, Bacterial Infection and Depth (SINBAD) and Wagner classifications systems using photographs of diabetes-related foot ulcers. Methods: Three trained observers independently scored the diabetes-related foot ulcers of 45 participants on two separate occasions using photographs. The inter- and intra-observer reproducibility were calculated using Krippendorff’s α. The completion times were compared with Kruskal-Wallis and Dunn’s post-hoc tests. The ability of the scores to predict 30-day amputation rates were assessed using receiver operator characteristic curves and area under the curves. Results: There was excellent intra-observer agreement (α >0.900) and substantial agreement between observers (α=0.788) in WIfI scoring. There was moderate, substantial, or excellent agreement within the three observers (α>0.599 in all instances except one) and fair or moderate agreement between observers (α of UTWCS=0.306, α of SINBAD=0.516, α of Wagner=0.374) for the other three classification systems. The WIfI score took significantly longer ( P<.001) to complete compared to the other three scores (medians and inter quartile ranges of the WIfI, UTWCS, SINBAD, and Wagner being 1.00 [0.88-1.00], 0.75 [0.50-0.75], 0.50 [0.50-0.50], and 0.25 [0.25-0.50] minutes). None of the classifications were predictive of 30-day amputation ( P>.05 in all instances). Conclusion: The WIfI score can be completed with substantial agreement between trained observers but was not predictive of 30-day amputation.

Download Full-text

Grasp to See—Object Classification Using Flexion Glove with Support Vector Machine

Sensors ◽

10.3390/s21041461 ◽

2021 ◽

Vol 21 (4) ◽

pp. 1461

Author(s):

Shun-Hsin Yu ◽

Jen-Shuo Chang ◽

Chia-Hung Dylan Tsai

Keyword(s):

Support Vector Machine ◽

Daily Life ◽

Object Classification ◽

Target Object ◽

The Other ◽

Support Vector ◽

Wide Range ◽

Dark Space ◽

Flex Sensors ◽

Shape And Size

This paper proposes an object classification method using a flexion glove and machine learning. The classification is performed based on the information obtained from a single grasp on a target object. The flexion glove is developed with five flex sensors mounted on five finger sleeves, and is used for measuring the flexion of individual fingers while grasping an object. Flexion signals are divided into three phases, and they are the phases of picking, holding and releasing, respectively. Grasping features are extracted from the phase of holding for training the support vector machine. Two sets of objects are prepared for the classification test. One is printed-object set and the other is daily-life object set. The printed-object set is for investigating the patterns of grasping with specified shape and size, while the daily-life object set includes nine objects randomly chosen from daily life for demonstrating that the proposed method can be used to identify a wide range of objects. According to the results, the accuracy of the classifications are achieved 95.56% and 88.89% for the sets of printed objects and daily-life objects, respectively. A flexion glove which can perform object classification is successfully developed in this work and is aimed at potential grasp-to-see applications, such as visual impairment aid and recognition in dark space.

Download Full-text

A Novel Approach to Oil Layer Recognition Model Using Whale Optimization Algorithm and Semi-Supervised SVM

Symmetry ◽

10.3390/sym13050757 ◽

2021 ◽

Vol 13 (5) ◽

pp. 757

Author(s):

Yongke Pan ◽

Kewen Xia ◽

Li Wang ◽

Ziping He

Keyword(s):

Optimization Algorithm ◽

Oil And Gas ◽

The Other ◽

Whale Optimization Algorithm ◽

Classification Model ◽

Support Vector ◽

Recognition Model ◽

Novel Approach ◽

Whale Optimization ◽

Oil And Gas Reservoir

The dataset distribution of actual logging is asymmetric, as most logging data are unlabeled. With the traditional classification model, it is hard to predict the oil and gas reservoir accurately. Therefore, a novel approach to the oil layer recognition model using the improved whale swarm algorithm (WOA) and semi-supervised support vector machine (S3VM) is proposed in this paper. At first, in order to overcome the shortcomings of the Whale Optimization Algorithm applied in the parameter-optimization of the S3VM model, such as falling into a local optimization and low convergence precision, an improved WOA was proposed according to the adaptive cloud strategy and the catfish effect. Then, the improved WOA was used to optimize the kernel parameters of S3VM for oil layer recognition. In this paper, the improved WOA is used to test 15 benchmark functions of CEC2005 compared with five other algorithms. The IWOA–S3VM model is used to classify the five kinds of UCI datasets compared with the other two algorithms. Finally, the IWOA–S3VM model is used for oil layer recognition. The result shows that (1) the improved WOA has better convergence speed and optimization ability than the other five algorithms, and (2) the IWOA–S3VM model has better recognition precision when the dataset contains a labeled and unlabeled dataset in oil layer recognition.

Download Full-text

The Effect of Different Annealing Strategies on the Microstructure Development and Mechanical Response of Austempered Steels

Metals ◽

10.3390/met11071041 ◽

2021 ◽

Vol 11 (7) ◽

pp. 1041

Author(s):

Eliseo Hernandez-Duran ◽

Luca Corallo ◽

Tanya Ros-Yanez ◽

Felipe Castro-Cerda ◽

Roumen H. Petrov

Keyword(s):

Mechanical Properties ◽

Retained Austenite ◽

Mechanical Response ◽

Steel Grade ◽

The Other ◽

Microstructure Development ◽

Microstructural Refinement ◽

Heterogeneous Distribution ◽

Parent Austenite ◽

Conventional Annealing

This study focuses on the effect of non-conventional annealing strategies on the microstructure and related mechanical properties of austempered steels. Multistep thermo-cycling (TC) and ultrafast heating (UFH) annealing were carried out and compared with the outcome obtained from a conventionally annealed (CA) 0.3C-2Mn-1.5Si steel. After the annealing path, steel samples were fast cooled and isothermally treated at 400 °C employing the same parameters. It was found that TC and UFH strategies produce an equivalent level of microstructural refinement. Nevertheless, the obtained microstructure via TC has not led to an improvement in the mechanical properties in comparison with the CA steel. On the other hand, the steel grade produced via a combination of ultrafast heating annealing and austempering exhibits enhanced ductility without decreasing the strength level with respect to TC and CA, giving the best strength–ductility balance among the studied steels. The outstanding mechanical response exhibited by the UFH steel is related to the formation of heterogeneous distribution of ferrite, bainite and retained austenite in proportions 0.09–0.78–0.14. The microstructural formation after UFH is discussed in terms of chemical heterogeneities in the parent austenite.

Download Full-text

Analysis of the Nosema Cells Identification for Microscopic Images

Sensors ◽

10.3390/s21093068 ◽

2021 ◽

Vol 21 (9) ◽

pp. 3068

Author(s):

Soumaya Dghim ◽

Carlos M. Travieso-González ◽

Radim Burget

Keyword(s):

Neural Network ◽

Machine Learning ◽

Image Processing ◽

Deep Learning ◽

The Other ◽

Support Vector ◽

Learning Approaches ◽

Microscopic Images ◽

Trained Neural Network ◽

Nosema Disease

The use of image processing tools, machine learning, and deep learning approaches has become very useful and robust in recent years. This paper introduces the detection of the Nosema disease, which is considered to be one of the most economically significant diseases today. This work shows a solution for recognizing and identifying Nosema cells between the other existing objects in the microscopic image. Two main strategies are examined. The first strategy uses image processing tools to extract the most valuable information and features from the dataset of microscopic images. Then, machine learning methods are applied, such as a neural network (ANN) and support vector machine (SVM) for detecting and classifying the Nosema disease cells. The second strategy explores deep learning and transfers learning. Several approaches were examined, including a convolutional neural network (CNN) classifier and several methods of transfer learning (AlexNet, VGG-16 and VGG-19), which were fine-tuned and applied to the object sub-images in order to identify the Nosema images from the other object images. The best accuracy was reached by the VGG-16 pre-trained neural network with 96.25%.

Download Full-text

Forecasting the risk at infractions: an ensemble comparison of machine learning approach

Industrial Management & Data Systems ◽

10.1108/imds-10-2020-0603 ◽

2021 ◽

Vol ahead-of-print (ahead-of-print) ◽

Author(s):

Lei Li ◽

Desheng Wu

Keyword(s):

Machine Learning ◽

Prediction Models ◽

Short Term Memory ◽

Model Performance ◽

Large Data ◽

Support Vector ◽

Learning Approaches ◽

Content Type ◽

Day To Day Operations ◽

Prediction Approach

PurposeThe infraction of securities regulations (ISRs) of listed firms in their day-to-day operations and management has become one of common problems. This paper proposed several machine learning approaches to forecast the risk at infractions of listed corporates to solve financial problems that are not effective and precise in supervision.Design/methodology/approachThe overall proposed research framework designed for forecasting the infractions (ISRs) include data collection and cleaning, feature engineering, data split, prediction approach application and model performance evaluation. We select Logistic Regression, Naïve Bayes, Random Forest, Support Vector Machines, Artificial Neural Network and Long Short-Term Memory Networks (LSTMs) as ISRs prediction models.FindingsThe research results show that prediction performance of proposed models with the prior infractions provides a significant improvement of the ISRs than those without prior, especially for large sample set. The results also indicate when judging whether a company has infractions, we should pay attention to novel artificial intelligence methods, previous infractions of the company, and large data sets.Originality/valueThe findings could be utilized to address the problems of identifying listed corporates' ISRs at hand to a certain degree. Overall, results elucidate the value of the prior infraction of securities regulations (ISRs). This shows the importance of including more data sources when constructing distress models and not only focus on building increasingly more complex models on the same data. This is also beneficial to the regulatory authorities.

Download Full-text

Simulating the action of zeitgebers on a coupled two-oscillator model of the human circadian system

AJP Regulatory Integrative and Comparative Physiology ◽

10.1152/ajpregu.1984.247.3.r418 ◽

1984 ◽

Vol 247 (3) ◽

pp. R418-R426

Author(s):

P. H. Gander ◽

R. E. Kronauer ◽

C. A. Czeisler ◽

M. C. Moore-Ede

Keyword(s):

Core Temperature ◽

Activity Rhythm ◽

Human Subjects ◽

Model Performance ◽

The Other ◽

Oscillator Model ◽

Temporal Isolation ◽

The Core ◽

Temperature Rhythm ◽

Rest Activity

Our two-oscillator model was originally designed to describe the circadian rhythms of human subjects maintained in temporal isolation. The performance of this model in response to simulated environmental synchronizing cycles (zeitgebers) is examined here. Six distinct types of synchronization are demonstrated between the x oscillator (postulated to regulate the core temperature rhythm), the y oscillator (postulated to regulate the rest-activity rhythm), and z (the zeitgeber). Four types of synchronization are identifiable, if we consider only the periods of the three oscillators. Both x and y may be synchronized by z; either may synchronize with z while the other exhibits a different period; or x, y, and z may each show different periods. Two further classes of synchronization are discernible when phase criteria are taken into account. When either x or y is on the verge of desynchronizing from the other two oscillators, it undergoes periodic phase modulations while retaining the common overall period. The type of synchronization observed depends on the periods of x, y, and z and on the strength of the z drive. The effects of modifying each of these parameters have been systematically investigated by simulation, and model performance is summarized in terms of range of entrainment "maps." These constitute extensive sets of predictions about expected patterns of entrainment of the core temperature and rest-activity rhythms of human subjects exposed to various environmental zeitgebers. Experimental data are available against which model predictions can be tested.

Download Full-text

Cooperative Roles of Nitric Oxide-Metabolizing Enzymes To Counteract Nitrosative Stress in Enterohemorrhagic Escherichia coli

Infection and Immunity ◽

10.1128/iai.00334-19 ◽

2019 ◽

Vol 87 (9) ◽

Cited By ~ 1

Author(s):

Takeshi Shimizu ◽

Akio Matsumoto ◽

Masatoshi Noda

Keyword(s):

Nitric Oxide ◽

Escherichia Coli ◽

Stationary Phase ◽

Nitrosative Stress ◽

Enterohemorrhagic Escherichia Coli ◽

The Other ◽

Anaerobic Growth ◽

Bacterial Cells ◽

Metabolizing Enzymes ◽

Microaerobic Conditions

ABSTRACT Enterohemorrhagic Escherichia coli (EHEC) has at least three enzymes, NorV, Hmp, and Hcp, that act independently to lower the toxicity of nitric oxide (NO), a potent antimicrobial molecule. This study aimed to reveal the cooperative roles of these defensive enzymes in EHEC against nitrosative stress. Under anaerobic conditions, combined deletion of all three enzymes significantly increased the NO sensitivity of EHEC determined by the growth at late stationary phase; however, the expression of norV restored the NO resistance of EHEC. On the other hand, the growth of Δhmp mutant EHEC was inhibited after early stationary phase, indicating that NorV and Hmp play a cooperative role in anaerobic growth. Under microaerobic conditions, the growth of Δhmp mutant EHEC was inhibited by NO, indicating that Hmp is the enzyme that protects cells from NO stress under microaerobic conditions. When EHEC cells were exposed to a lower concentration of NO, the NO level in bacterial cells of Δhcp mutant EHEC was higher than those of the other EHEC mutants, suggesting that Hcp is effective at regulating NO levels only at a low concentration. These findings of a low level of NO in bacterial cells with hcp indicate that the NO consumption activity of Hcp was suppressed by Hmp at a low range of NO concentrations. Taken together, these results show that the cooperative effects of NO-metabolizing enzymes are regulated by the range of NO concentrations to which the EHEC cells are exposed.

Download Full-text