Generate Classification Models Research Articles

MALDI-TOF as a powerful tool for identifying and differentiating closely related microorganisms: the strange case of three reference strains of Paenibacillus polymyxa

Accurate identification and typing of microbes are crucial steps in gaining an awareness of the biological heterogeneity and reliability of microbial material within any proprietary or public collection. Paenibacillus polymyxa is a bacterial species of great agricultural and industrial importance due to its plant growth-promoting activities and production of several relevant secondary metabolites. In recent years, matrix-assisted laser desorption ionisation time-of-flight mass spectrometry (MALDI-TOF MS) has been widely used as an alternative rapid tool for identifying, typing, and differentiating closely related strains. In this study, we investigated the diversity of three P. polymyxa strains. The mass spectra of ATCC 842T, DSM 292, and DSM 365 were obtained, analysed, and compared to select discriminant peaks using ClinProTools software and generate classification models. MALDI-TOF MS analysis showed inconsistent results in identifying DSM 292 and DSM 365 as belonging to P. polimixa species, and comparative analysis of mass spectra revealed the presence of highly discriminatory biomarkers among the three strains. 16S rRNA sequencing and Average Nucleotide Identity (ANI) confirmed the discrepancies found in the proteomic analysis. The case study presented here suggests the enormous potential of the proteomic-based approach, combined with statistical tools, to predict and explore differences between closely related strains in large microbial datasets.

Methodological proposal to identify the nationality of Twitter users through random-forests.

We disclose a methodology to determine the participants in discussions and their contributions in social networks with a local relationship (e.g., nationality), providing certain levels of trust and efficiency in the process. The dynamic is a challenge that has demanded studies and some approximations to recent solutions. The study addressed the problem of identifying the nationality of users in the Twitter social network before an opinion request (of a political nature and social participation). The employed methodology classifies, via machine learning, the Twitter users' nationality to carry out opinion studies in three Central American countries. The Random Forests algorithm is used to generate classification models with small training samples, using exclusively numerical characteristics based on the number of times that different interactions among users occur. When averaging the proportions achieved by inferences of the ratio of nationals of each country, in the initial data, an average of 77.40% was calculated, compared to 91.60% averaged after applying the automatic classification model, an average increase of 14.20%. In conclusion, it can be seen that the suggested set of method provides a reasonable approach and efficiency in the face of opinion problems.

Real and Altered Fingerprint Classification Based on Various Features and燙lassifiers

Biometric recognition refers to the identification of individuals through their unique behavioral features (e.g., fingerprint, face, and iris). We need distinguishing characteristics to identify people, such as fingerprints, which are world-renowned as the most reliable method to identify people. The recognition of fingerprints has become a standard procedure in forensics, and different techniques are available for this purpose. Most current techniques lack interest in image enhancement and rely on high-dimensional features to generate classification models. Therefore, we proposed an effective fingerprint classification method for classifying the fingerprint image as authentic or altered since criminals and hackers routinely change their fingerprints to generate fake ones. In order to improve fingerprint classification accuracy, our proposed method used the most effective texture features and classifiers. Discriminant Analysis (DCA) and Gaussian Discriminant Analysis (GDA) are employed as classifiers, along with Histogram of Oriented Gradient (HOG) and Segmentation-based Feature Texture Analysis (SFTA) feature vectors as inputs. The performance of the classifiers is determined by assessing a range of feature sets, and the most accurate results are obtained. The proposed method is tested using a Sokoto Coventry Fingerprint Dataset (SOCOFing). The SOCOFing project includes 6,000 fingerprint images collected from 600 African people whose fingerprints were taken ten times. Three distinct degrees of obliteration, central rotation, and z-cut have been performed to obtain synthetically altered replicas of the genuine fingerprints. The proposal achieved massive success with a classification accuracy reaching 99%. The experimental results indicate that the proposed method for fingerprint classification is feasible and effective. The experiments also showed that the proposed SFTA-based GDA method outperformed state-of-art approaches in feature dimension and classification accuracy.

GCN-Based Structure-Activity Relationship and DFT Studies of Staphylococcus aureus FabI Inhibitors

The enoyl-[acyl-carrier-protein] reductase (FabI) is an important enzyme in the fatty acid metabolism of Gram-positive bacteria, such as Staphylococcus aureus. FabI is also a potential target for the development of novel antibacterials. Several machine learning-driven studies were reported to develop FabI inhibitors, describing robust and predictive models. Herein, the authors applied the kGCN, a graph convolutional network framework, to generate classification models to select potential S. aureus FabI inhibitors. The most predictive model showed robustness for both active and inactive class prediction, according to statistical validation. Finally, the chemical interpretation of the model was consistent with prior experimental and theoretical works. The SAR analysis highlighted the importance of the occupation of hydrophobic pockets and polar interactions with Tyr-156 and NADPH cofactor present in the FabI catalytic site by potential inhibitors. A density functional theory study endorsed the SAR, where the electrostatic surfaces were consistent with the expected interactions with the pocket.

The Benefits of Automated Machine Learning in Hospitality: A Step-By-Step Guide and AutoML Tool

The manuscript presents a tool to estimate and predict data accuracy in hospitality by means of automated machine learning (AutoML). It uses a tree-based pipeline optimization tool (TPOT) as a methodological framework. The TPOT is an AutoML framework based on genetic programming, and it is particularly useful to generate classification models, for regression analysis, and to determine the most accurate algorithms and hyperparameters in hospitality. To demonstrate the presented tool’s real usefulness, we show that the TPOT findings provide further improvement, using a real-world dataset to convert key hospitality variables (customer satisfaction, loyalty) to revenue, with up to 93% prediction accuracy on unseen data. Doi: 10.28991ESJ-2022-06-06-02 Full Text: PDF

Evaluation of Accuracy Enhancement in European-Wide Crop Type Mapping by Combining Optical and Microwave Time Series

This investigation evaluates the potential of combining Copernicus Sentinel-1 (S1) and Sentinel-2 (S2) satellite data in producing a detailed Land Use and Land Cover (LULC) map with 19 crop type classes and 2 broader categories containing Woodland/Shrubland and Grassland over 28 Member States of Europe (EU-28). The Eurostat Land Use and Coverage Area Frame Survey (LUCAS) 2018 dataset is employed as ground truth for model training and validation. Monthly and yearly optical features from S2 spectral reflectance and spectral indices, alongside decadal (10-days) composites from an S1 microwave sensor, are extracted for the EU-28 territory for 2018 using Google Earth Engine (GEE). Five different feature sets using a mixture of indicators were created as input training data. A Random Forest (RF) machine learning algorithm was applied to classify these feature sets, and the generated classification models were compared using an identical validation dataset. Results show that S1 and S2 yearly features together are able to provide a full coverage map less dependent on cloud effects and having appropriate overall accuracy (OA). Based on this feature set, the 21 classes could be classified with an OA of 78.3% using the independent validation data set. The OA increases to 82.7% by grouping 21 classes into 8 broader categories. The comparison with similar studies using individual S1 and S2 data indicates that combining S1 and S2 time series can attain slightly better results while enhancing spatial coverage.

Applications of Machine Learning to Consequence Analysis of Hypothetical Accidents at Barakah Nuclear Power Plant Unit 1

The United Arab Emirates (UAE) built four nuclear power plants at the Barakah site to supply 25% of the region’s electricity. Among the Barakah Nuclear Power Plants, (BNPPs), their main objectives are to achieve the highest possible safety for the environment, operators, and community members; quality nuclear reactors and energy; and power production efficiency. To meet these objectives, decision-makers must access large amounts of data in the case of a nuclear accident to prevent the release of radioactive materials. Machine learning offers a feasible solution to propose early warnings and help contain accidents. Thus, our study aimed at developing and testing a machine learning model to classify nuclear accidents using the associated release of radioactive materials. We used Radiological Assessment System for Consequence Analysis (RASCAL) software to estimate the concentration of released radioactive materials in the four seasons of the year 2020. We applied these concentrations as predictors in a classification tree model to classify three types of severe accidents at Unit 1 of BNPPs each season. The average accuracy of the classification models in the four seasons was 97.3% for the training data and 96.5% for the test data, indicating a high efficacy. Thus, the generated classification models can distinguish between the three simulated accidents in any season.

Characterization of SARS-CoV-2 cases and COVID-19 deaths in the State of Baja California through five waves using machine learning

The Mexican State of Baja California, located in the north of Mexico, is a region of great importance due to its proximity to the United States, reason why it is of interest an analysis of the historical behavior of the pandemic caused by the SARS-CoV-2 virus in this region. Thus, based on the official data provided by the Mexican federal government during the years of the pandemic, particularly on Baja California, we undertook the task of preprocessing such data in order to generate classification models and identify rules of the behavior between virus infections and COVID-19 deaths. To carry out our study, as in previous works, we used the KDD methodology and specialized machine learning tools, beginning the study with the preprocessing of data and continuing with its exploitation for generating models with a high rate of correct classification, which were validated with the help of the cross-validation technique. In this way, the five waves that have occurred between March 2020 and October 2022 were characterized according to the relationships occurred between cases infected with the SARS-CoV-2 virus and COVID-19 deaths.

Classifying the Mexican epidemiological semaphore colour from the Covid-19 text Spanish news

This work aims to generate classification models that help determine the colour of an epidemiological semaphore (ES) by analysing online news and being better prepared for the different changes in the evolution of the pandemic. To accomplish this, we introduce Cov-NES-Mex corpus, a collection of 77,983 news (labelled with the Mexican ES system) related to Covid-19 for the 32 regions of Mexico. Also, we showed measures that describe the corpus as imbalanced and with a high vocabulary overlap between classes. In addition, evaluation measurements of the pandemic by region are proposed. Furthermore, a classification model, based on a transformer architecture specialised for the Spanish language, achieved up to 0.83 of F-measure. Thus, this work provides evidence that there is essential information in the news that can be used to determine the colour of the ES up to 4 weeks in advance. Finally, the presented results could be applied to other Spanish-speaking countries, which do not have an ES system, thus inferring and comparing their situation concerning the Mexican ES.

Automatic Cyberbullying Detection: a Mexican case in High School and Higher Education students

The social interaction among young students has been partially or totally transformed to mobile-based communication, specifically through the use of social networks. This new communication environment has allowed a more immediate, diverse and massive interaction, offering a faster and more effective situation when carrying out academic and recreational activities. However, this scenario has also promoted the phenomenon of social harassment known as bullying, exponentially increasing its scope and diversifying the types and forms of aggression. Machine learning and natural language processing techniques have been used to create models that detect bullying situations among students, using data corpus from mainly public social networks. However, generally, these data sources are not representative of the social networks commonly used by the students; generating classification models that do not consider the vocabulary used by this social group. This article describes the methodology used to create a representative data corpus of the interaction between Mexican high school and university students, and a comparative analysis on characteristics that influence the quality of the content of a corpus in this domain. In addition, the performance achieved by implementing various machine learning models to identify bullying situations is presented. The best result is reported for the Naive Bayesian classifier (F1-Score of 0.862), performing better than models based on deep learning such as Recurrent (F1-Score of 0.845) and Convolutional (F1-Score of 0.807) Neural Networks.

Information theory and machine learning based authentication of flaxseed oil using portable and handheld vibrational spectroscopy sensors

Flaxseed oil is one of the popular edible oils, and its adulteration has become a concern because of its high commodity value. Therefore, there is a need to detect adulterated flaxseeds with a rapid, non-invasive, and simple method to keep the quality of flaxseed oil. This study aimed to develop a machine learning algorithm and information theory to detect adulterated flaxseed oils by vibrational spectroscopy units combined with chemometrics. Oil spectra were collected with portable/handheld vibrational spectroscopic units and analyzed using conditional entropy, support vector machines (SVM), and soft independent modeling of class analogy (SIMCA) to generate classification models to identify the pureness of oils and partial least square regression (PLSR) to predict the adulterant levels and fatty acid distributions. Conditional entropy showed that two or three wavenumbers/shifts could discriminate the oils using machine learning algorithms with an accuracy of over 95%. SIMCA models determined the oils with an interclass distance (ICD) over 1.1. Specifically, the Fourier transform mid-infrared (FT-MIR) unit provided the best classification of the oils with ICD over 4.9. All instruments showed good performance in predicting fatty acids and adulteration levels with r val ≥0.89 and standard error prediction (SEP) ≤1.7%. Overall, these portable/handheld units showed great potential for rapid, simple, and non-invasive monitoring to identify adulterated flaxseed oils.

A system for real-time multivariate feature combination of endoscopic mitral valve simulator training data

PurposeFor an in-depth analysis of the learning benefits that a stereoscopic view presents during endoscopic training, surgeons required a custom surgical evaluation system enabling simulator independent evaluation of endoscopic skills. Automated surgical skill assessment is in dire need since supervised training sessions and video analysis of recorded endoscope data are very time-consuming. This paper presents a first step towards a multimodal training evaluation system, which is not restricted to certain training setups and fixed evaluation metrics.MethodsWith our system we performed data fusion of motion and muscle-action measurements during multiple endoscopic exercises. The exercises were performed by medical experts with different surgical skill levels, using either two or three-dimensional endoscopic imaging. Based on the multi-modal measurements, training features were calculated and their significance assessed by distance and variance analysis. Finally, the features were used automatic classification of the used endoscope modes.ResultsDuring the study, 324 datasets from 12 participating volunteers were recorded, consisting of spatial information from the participants’ joint and right forearm electromyographic information. Feature significance analysis showed distinctive significance differences, with amplitude-related muscle information and velocity information from hand and wrist being among the most significant ones. The analyzed and generated classification models exceeded a correct prediction rate of used endoscope type accuracy rate of 90%.ConclusionThe results support the validity of our setup and feature calculation, while their analysis shows significant distinctions and can be used to identify the used endoscopic view mode, something not apparent when analyzing time tables of each exercise attempt. The presented work is therefore a first step toward future developments, with which multivariate feature vectors can be classified automatically in real-time to evaluate endoscopic training and track learning progress.

FINDIK YAĞININ FT-NIR, FT-MIR VE RAMAN SPEKTROMETRELERİ İLE BİRLİKTE ÇOK BİLEŞENLİ VERİ ANALİZLERİ KULLANILARAK DOĞRULANMASI

This research studied the authentication of hazelnut oil by portable FT-NIR, FT-MIR, and Raman spectrometers. Hazelnut oils were adulterated with vegetable oils at various concentrations (0-25%) (w/w). Collected spectra were analyzed using Principal Component Analysis (PCA) and Soft Independent Modelling of Class Analogy (SIMCA) to generate classification models to authenticate pure hazelnut oil and Partial Least Squares Regression (PLSR) to predict the fatty acids and adulterant levels. For confirmation, oil’s fatty acid profile was determined by gas chromatography. In all three instruments, SIMCA provided distinct clusters for pure and adulterated samples with interclass distance (ICD)3. All instruments showed excellent performance in predicting fatty acids and adulteration levels with rval>0.93 and standard error prediction (SEP)<1.75%. Specifically, the FT-MIR unit provided the best performances. Still, all the units can be used as an alternative to traditional methods. These units showed great potential for in-situ surveillance to detect hazelnut oil adulterations.

Adaptive online terrain classification method for mobile robot based on vibration signals

To improve the accuracy of terrain classification during mobile robot operation, an adaptive online terrain classification method based on vibration signals is proposed. First, the time domain and the combined features of the time, frequency, and time–frequency domains in the original vibration signal are extracted. These are adopted as the input of the random forest algorithm to generate classification models with different dimensions. Then, by judging the relationship between the current speed of the mobile robot and its critical speed, the classification model of different dimensions is adaptively selected for online classification. Offline and online experiments are conducted for four different terrains. The experimental results show that the proposed method can effectively avoid the self-vibration interference caused by an increase in the robot’s moving speed and achieve higher terrain classification accuracy.

Rapid diagnosis and tumor margin assessment during pancreatic cancer surgery with the MasSpec Pen technology

Significance Surgical removal of pancreatic cancer remains the only option for a cure. To verify the extent of tumor removal, surgeons rely on pathologic evaluation of frozen sections of surgical margins. However, this process can be challenging, time consuming, and subjective. Here, we used the MasSpec Pen to rapidly distinguish pancreatic cancer from healthy pancreatic and bile duct tissues by generating classification models based on the molecular signatures acquired from tissue. We evaluated this technology in an operating room during pancreatic surgeries and used these classification models to predict on data obtained in vivo and ex vivo with high performance. Our results suggest that the MasSpec Pen platform has the potential to improve and expedite margin evaluation during pancreatic cancer surgery.

Explainable Internet Traffic Classification

The problem analyzed in this paper deals with the classification of Internet traffic. During the last years, this problem has experienced a new hype, as classification of Internet traffic has become essential to perform advanced network management. As a result, many different methods based on classical Machine Learning and Deep Learning have been proposed. Despite the success achieved by these techniques, existing methods are lacking because they provide a classification output that does not help practitioners with any information regarding the criteria that have been taken to the given classification or what information in the input data makes them arrive at their decisions. To overcome these limitations, in this paper we focus on an “explainable” method for traffic classification able to provide the practitioners with information about the classification output. More specifically, our proposed solution is based on a multi-objective evolutionary fuzzy classifier (MOEFC), which offers a good trade-off between accuracy and explainability of the generated classification models. The experimental results, obtained over two well-known publicly available data sets, namely, UniBS and UPC, demonstrate the effectiveness of our method.

Spam Detection Based on Feature Evolution to Deal with Concept Drift

Electronic messages are still considered the most significant tools in business and personal applications due to their low cost and easy access. However, e-mails have become a major problem owing to the high amount of junk mail, named spam, which fill the e-mail boxes of users. Several approaches have been proposed to detect spam, such as filters implemented in e-mail servers and user-based spam message classification mechanisms. A major problem with these approaches is spam detection in the presence of concept drift, especially as a result of changes in features over time. To overcome this problem, this work proposes a new spam detection system based on analyzing the evolution of features. The proposed method is divided into three steps: 1) spam classification model training; 2) concept drift detection; and 3) knowledge transfer learning. The first step generates classification models, as commonly conducted in machine learning. The second step introduces a new strategy to avoid concept drift: SFS (Similarity-based Features Se- lection) that analyzes the evolution of the features taking into account similarity obtained between the feature vectors extracted from training data and test data. Finally, the third step focuses on the following questions: what, how, and when to transfer acquired knowledge? The proposed method is evaluated using two public datasets. The results of the experiments show that it is possible to infer a threshold to detect changes (drift) in order to ensure that the spam classification model is updated through knowledge transfer. Moreover, our anomaly detection system is able to perform spam classification and concept drift detection as two parallel and independent tasks.

Insights into intrauterine growth restriction based on maternal and umbilical cord blood metabolomics

Intrauterine growth restriction (IUGR) is a fetal adverse condition, ascribed by limited oxygen and nutrient supply from the mother to the fetus. Management of IUGR is an ongoing challenge because of its connection with increased fetal mortality, preterm delivery and postnatal pathologies. Untargeted nuclear magnetic resonance (1H NMR) metabolomics was applied in 84 umbilical cord blood and maternal blood samples obtained from 48 IUGR and 36 appropriate for gestational age (AGA) deliveries. Orthogonal projections to latent structures discriminant analysis (OPLS-DA) followed by pathway and enrichment analysis generated classification models and revealed significant metabolites that were associated with altered pathways. A clear association between maternal and cord blood altered metabolomic profile was evidenced in IUGR pregnancies. Increased levels of the amino acids alanine, leucine, valine, isoleucine and phenylalanine were prominent in IUGR pregnancies indicating a connection with impaired amino acid metabolism and transplacental flux. Tryptophan was individually connected with cord blood discrimination while 3-hydroxybutyrate assisted only maternal blood discrimination. Lower glycerol levels in IUGR samples ascribed to imbalance between gluconeogenesis and glycolysis pathways, suggesting poor glycolysis. The elevated levels of branched chain amino acids (leucine, isoleucine and valine) in intrauterine growth restricted pregnancies were linked with increased insulin resistance.

What university attributes predict for graduate employability?

Research universities play an important role in developing new technologies that can be the basis for economic development, improved quality of life, and reduced environmental impacts. In developing countries, there have been accelerated efforts to transform teaching-oriented higher education institutions into research-intensive universities that can contribute to social development through the generation of new knowledge. There have also been parallel efforts to use internationalization to enrich both education and research. However, the effect of such reforms on the employability of university graduates is unclear. In this work, the influence of different institution attributes on graduate employability is investigated using the hyperbox machine learning technique, which is capable of generating classification models in the form of if/then rules. The analysis focuses on Southeast Asian universities listed in the 2020 Quacquarelli Symonds Asian University Rankings and uses the normalized scores across the different ranking criteria. Five plausible rule-based classifiers are derived and validated. The results show notable association between research and internationalization metrics with employability.

RETRACTED ARTICLE: User preference perception and intelligent search engine recommendation based on network behavior tracking in hyper-connected smart cities

User preference perception and intelligent search engine recommendation based on network behavior tracking with the web communities is analyzed in this research. In order to quickly and accurately detect the abnormal behavior of network users, it is first necessary to train and learn network data collected from the network that reflects the behavior of network users, to obtain user behavior characteristics, and to generate classification models. To this end, the selective integration learning technology is introduced into the collaborative learning process, and a selective collaborative learning method is proposed to obtain the user behavior classification model, so as to improve the training and learning effect while also adapting to the non-equilibrium training sample data. First, the actual network traffic data are collected and pre-processed, including the statistics and measurement of the traffic data according to the detection characteristic indicators to construct the network user behavior data. Some network user behavior data are marked by software tools, manual analysis and other methods to obtain the training samples of partial marks. Besides this, the web communities as the experimental data set has been analyzed to construct the efficient model. The experiment results compared with the latest methods have proven the effectiveness.