Percentage Of Correct Classification Research Articles

Predicting the development of vulvar lichen sclerosus

Relevance. The issue of timely diagnosis and treatment of vulvar lichen sclerosus has become especially acute in recent years due to the “rejuvenation” of the disease and the risk of its malignancy. In this regard, it is urgent to search for effective methods for predicting and early detection of the disease. The aim of the study - to develop amodel for predicting vulvar lichen sclerosus based on established clinical and anamnestic risk factors. Materials and Methods. The prospective case-control study included 404 women aged 20 to 70 years, of which 344 were patients with vulvar lichen sclerosus and 60 were women without vulvar diseases. At the first stage, acomparative statistical correlation analysis of the clinical and anamnestic data of the subjects was carried out using the Spearman correlation coefficient (R0.15), Chi-square tests, Phi and Cramer statistics, the Mann-­Whitney U test and the Student t test (p 0.05). The data obtained were used to develop aneural network model for predicting vulvar lichen sclerosus in the second stage of the study. Results and Discussion. Based on established reliably significant (p0.05) obstetric-­gynecological, somatic, infectious, hygienic and household factors influencing the risk of developing vulvar lichen sclerosus (Rindicator - from 0.16 to 0.38 confirms the statistical significance of correlations), aneural network model for predicting vulvar lichen sclerosus was developed (the percentage of correct classification on the test sample is the maximum possible value - 100%) and acomputer program was written that automates the procedure for predicting the disease. Conclusion. The neural network model for predicting the disease, developed on the basis of reliably (p0.05) significant risk factors for vulvar lichen sclerosus, has high prognostic properties, and acomputer program written on its basis allows the doctor in amatter of minutes to identify the patient at risk for the development of vulvar lichen sclerosus and give she needs preventive recommendations aimed at preventing or early detection of the disease.

Geometry of posterior larval spiracles to identify medically and forensically important calliphorids in Thailand

Fly identification is the primary step of analysis in forensic entomology. Although morphology and molecular techniques are considered satisfactory methods, some constraints may arise from a financial or even human point of view. Over the past decade, the geometric morphometric approach has been increasingly advocated for the classification and identification of arthropods. This study explored the method for species identification of 800 third-instar larvae of eight blow fly species of medical and forensic importance: Chrysomya chani Kurahashi, Chrysomya megacephala (Fabricius), Chrysomya (Ceylonomyia) nigripes Aubertin, Chrysomya pinguis (Walker), Chrysomya (Achoetandrus) rufifacies (Macquart), Hemipyrellia ligurriens (Wiedemann), Lucilia cuprina (Wiedemann), and Lucilia porphyrina (Walker). Based on the posterior spiracles geometry, the cross-validation revealed a relatively high percentage of correct classification in most species, ranking from 86% to 100%. The results of this study confirmed that the geometric morphometric (GM) analysis of posterior spiracles might be utilized as a larva identification tool. Therefore, this GM method represents one way of overcoming difficulties with the identification of blow fly larvae and can support further studies of these flies.

Optimisation of an Industrial Optical Sorter of Legumes for Gluten-Free Production Using Hyperspectral Imaging Techniques

The market demand for gluten-free food is increasing due to the growing gluten sensitivity and coeliac disease (CD) in the population. The market requires grass-free cereals to produce gluten-free food. This requires sorting methods that guarantee the perfect separation of gluten contaminants from the legumes. The objective of the research was the development of an optical sorting system based on hyperspectral image processing, capable of identifying the spectral characteristics of the products under investigation to obtain a statistical classifier capable of enabling the total elimination of contaminants. The construction of the statistical classifier yielded excellent results, with a 100% correct classification rate of the contaminants. Tests conducted subsequently on an industrial optical sorter validated the result of the preliminary tests. In fact, the application of the developed classifier was able to correctly select the contaminants from the mass of legumes with a correct classification percentage of 100%. A small proportion of legumes was misclassified as contaminants, but this did not affect the scope of the work. Further studies will aim to reduce even this small share of waste with investigations into optimising the seed transport systems of the optical sorter.

Neck circumference as an additional predictor of cardiovascular disease mortality: A multi-center prospective population-based study in northeastern China

Background and aimsThis study aimed to assess the potential of neck circumference (NC) and neck-to-height ratio (NHR) as predictors of future cardiovascular disease (CVD) mortality in a general population from Northeastern China. MethodsA multi-center prospective study was conducted in Northeastern China, involving 18, 796 participants. The associations between NC or NHR and the incidence of overall CVD mortality, stroke mortality, and coronary heart disease (CHD) mortality were examined using multivariate Cox regression models. Hazard ratios (HRs) and the corresponding 95% confidence intervals (CIs) were calculated. Reclassification analyses were conducted to determine the incremental predictive value of NC or NHR. ResultsNC was significantly associated with the risk of CVD mortality, independent of other anthropometric measurements for obesity. Individuals in the highest quartile of NC had a 1.83-fold (95% CI 1.29 to 2.61) and a 2.40-fold (95% CI 1.45 to 4.00) higher risk of overall CVD mortality and CHD mortality, respectively. Larger NC was significantly related to a heightened risk of ischemic stroke mortality, although no such association was observed with hemorrhagic stroke mortality. Furthermore, the risk of overall CVD mortality, stroke mortality, and CHD mortality increased by approximately 1.21 to 1.25 times per 1-SD change in NC. Similar findings were observed for NHR. The percentages of correct classification of overall CVD mortality improved by 12.1% and 16.3% after the addition of NC or NHR into established models, respectively. ConclusionsNC and NHR might be promising predictors of CVD mortality, with higher values indicating greater risk.

Eucalyptus Species Discrimination Using Hyperspectral Sensor Data and Machine Learning

The identification of tree species is very useful for the management and monitoring of forest resources. When paired with machine learning (ML) algorithms, species identification based on spectral bands from a hyperspectral sensor can contribute to developing technologies that enable accurate forest inventories to be completed efficiently, reducing labor and time. This is the first study to evaluate the effectiveness of classification of five eucalyptus species (E. camaldulensis, Corymbia citriodora, E. saligna, E. grandis, and E. urophyla) using hyperspectral images and machine learning. Spectral readings were taken from 200 leaves of each species and divided into three dataset sizes: one set containing 50 samples per species, a second with 100 samples per species, and a third set with 200 samples per species. The ML algorithms tested were multilayer perceptron artificial neural network (ANN), decision trees (J48 and REPTree algorithms), and random forest (RF). As a control, a conventional approach by logistic regression (LR) was used. Eucalyptus species were classified by ML algorithms using a randomized stratified cross-validation with 10 folds. After obtaining the percentage of correct classification (CC) and F-measure accuracy metrics, the means were grouped by the Scott–Knott test at 5% probability. Our findings revealed the existence of distinct spectral curves between the species, with the differences being more marked from the 700 nm range onwards. The most accurate ML algorithm for identifying eucalyptus species was ANN. There was no statistical difference for CC between the three dataset sizes. Therefore, it was determined that 50 leaves would be sufficient to accurately differentiate the eucalyptus species evaluated. Our study represents an important scientific advance for forest inventories and breeding programs with applications in both forest plantations and native forest areas as it proposes a fast, accurate, and large-scale species-level classification approach.

Early detection of bacterial wilt in bananas caused by Ralstonia solanacearum using reflectance spectroscopy

Bacterial wilt is one of the most important vascular diseases that generate high worldwide losses. The main strategy to control it involves early detection of infected plants that mitigate its spread in the field. This research characterized the spectral response of healthy plants, infected with Ralstonia solanacearum E.F. Smith race 2 and subjected to water stress, in two banana cultivars by spectroscopy reflectance. The spectral data were used to detect vascular wilt during the incubation period of the disease in Gros Michel and Cavendish banana cultivars. The reflectance data were collected from the leaves using a portable spectrometer. Both varieties of healthy plants showed a typical low reflectance in the visible range, with a peak of green of around 12% in Williams and 5% in Gros Michel. In the measured infrared range, the two varieties presented values between 60 and 70% in the latest days post-infection measurements, decreasing to ~ 50% after 12 dpi. The results obtained indicate that plants infected with R. solanacearum have no initial increase in reflectance in the visible (Vis) range, whereas decrease rapidly after 6 dpi in the 700–1000 nm range. This methodology identifies three wavelengths (710, 770, and 965 nm) that allow differentiation between ill and healthy plants after 6 days post-inoculation, with a percentage of correct classification that ranges from 96 to 100%. The spectral response characterization in healthy plants and those subjected to various types of stress is a fundamental input for the development of early disease detection systems based on spectroscopy techniques.

Machine Learning in the Hyperspectral Classification of Glycaspis brimblecombei (Hemiptera Psyllidae) Attack Severity in Eucalyptus

Assessing different levels of red gum lerp psyllid (Glycaspis brimblecombei) can influence the hyperspectral reflectance of leaves in different ways due to changes in chlorophyll. In order to classify these levels, the use of machine learning (ML) algorithms can help process the data faster and more accurately. The objectives were: (I) to evaluate the spectral behavior of the G. brimblecombei attack levels; (II) find the most accurate ML algorithm for classifying pest attack levels; (III) find the input configuration that improves performance of the algorithms. Data were collected from a clonal eucalyptus plantation (clone AEC 0144—Eucalyptus urophilla) aged 10.3 months old. Eighty sample evaluations were carried out considering the following severity levels: control (no shells), low infestation (N1), intermediate infestation (N2), and high infestation (N3), for which leaf spectral reflectances were obtained using a spectroradiometer. The spectral range acquired by the equipment was 350 to 2500 nm. After obtaining the wavelengths, they were grouped into representative interval means in 28 bands. Data were submitted to the following ML algorithms: artificial neural networks (ANN), REPTree (DT) and J48 decision trees, random forest (RF), support vector machine (SVM), and conventional logistic regression (LR) analysis. Two input configurations were tested: using only the wavelengths (ALL) and using the spectral bands (SB) to classify the attack levels. The output variable was the severity of G. brimblecombei attack. There were differences in the hyperspectral behavior of the leaves for the different attack levels. The highest attack level shows the greatest distinction and the highest reflectance values. LR and SVM show better accuracy in classifying the severity levels of G. brimblecombei attack. For the correct classification percentage, the RL and SVM algorithms performed better, both with accuracy above 90%. Both algorithms achieved F-score values close to 0.90 and above 0.8 for Kappa. The entire spectral range guaranteed the best accuracy for both algorithms.

Abstract 15667: The Transvalvular Pressure Gradient to Valve Area Ratio: A Novel, Simple Doppler Echocardiographic Parameter to Adjudicate Low-Gradient Aortic Stenosis Severity

Background: In patients with low-gradient (LG) aortic stenosis (AS), dobutamine stress echocardiography (DSE) or aortic valve calcium scoring (AVCS) by computed tomography is required to confirm AS severity and the indication for intervention. Hypothesis: We hypothesized that the mean transvalvular gradient to effective orifice area ratio (MG/EOA, in mmHg/cm 2 ) measured during rest echocardiography predicts true-severe AS (TSAS) and clinical outcomes in LG-AS patients. The present study aimed to assess the diagnostic accuracy and prognostic value of the MG/EOA ratio in LG-AS patients. Methods: The diagnostic accuracy of the MG/EOA ratio to predict TSAS was assessed in: i) an in vitro dataset obtained in a circulatory model, and ii) an in vivo dataset collected in 198 patients recruited in the prospective observational cohort TOPAS study (NCT01835028), using receiver operating characteristic (ROC) curve analysis. The prognostic value of this parameter was assessed using spline curve analysis and multivariate Cox regression, using a composite of aortic valve replacement or all-cause mortality at 2-years as clinical endpoint. Results: The MG/EOA ratio at rest predicted TSAS with an area under the ROC curve of 0.99 [0.98-1.00] in the in vitro dataset and 0.92 [0.87-0.95] in the in vivo dataset of LG-AS patients. In the in vivo dataset predominantly composed of patients with a low flow state, the optimal cut-off of MG/EOA ratio was 29 mmHg/cm 2 with a normal flow state (percentage of correct classification: 95%) and 25 mmHg/cm 2 with a low flow state (85%). In LG-AS patients, a MG/EOA ratio ≥ 23 mmHg/cm 2 was associated with increased risk of the composite endpoint (unadjusted HR=2.16 [1.58-3.06], p<0.001; adjusted HR=2.80 [1.94-4.03], p<0.001). The net reclassification index (NRI) of the resting parameter MG/EOA was 0.57 (p<0.001), which was similar to projected EOA (NRI=0.61, p<0.001) measured by DSE. Conclusion: We propose a new, easily obtainable parameter from standard echocardiography that outperforms other rest echocardiographic parameters and is non-inferior to DSE with respect to diagnostic accuracy and prognostic value. The MG/EOA ratio can be useful in LG-AS to confirm AS severity and may thus avoid the use of additional tests such as DSE or AVCS.

Detecting Faking on Self-Report Measures Using the Balanced Inventory of Desirable Responding

We compared three methods for scoring the Balanced Inventory of Desirable Responding (BIDR) to detect faked responses on self-report measures: (1) polytomous, (2) dichotomous emphasizing exaggerating endorsement of socially desirable behaviors, and (3) dichotomous emphasizing exaggerating denial of such behaviors. The results revealed that respondents on average were able to fake good or fake bad and that faking markedly affected score distributions, subscale score intercorrelations, and overall model fits. When using the Impression Management scale, polytomous and dichotomous exaggerated endorsement scoring were best for detecting faking good, whereas polytomous and dichotomous exaggerated denial scoring were best for detecting faking bad. When using the Self-Deceptive Enhancement scale, polytomous and dichotomous exaggerated endorsement scoring again were best for detecting faking good, but dichotomous exaggerated denial scoring was best for detecting faking bad. Percentages of correct classification of honest and faked responses for the most effective methods for any given scale ranged from 85% to 93%, with accuracy on average in detecting faking bad greater than in detecting faking good and greater when using the Impression Management than using the Self-Deceptive Enhancement scale for both types of faking. Overall, these results best support polytomous scoring of the BIDR Impression Management scale as the single most practical and efficient means to detect faking. Cut scores that maximized classification accuracy for all scales and scoring methods are provided for future use in screening for possible faking within situations in which relevant local data are unavailable.

Exploring the efficacy of artificial neural networks in predicting lung cancer recurrence: a retrospective study based on patient records.

Lung cancer remains a significant public health concern, accounting for a considerable number of cancer-related deaths worldwide. Neural networks have emerged as a promising tool that can aid in the diagnosis and treatment of various cancers. Consequently, there has been a growing interest in exploring the potential of artificial intelligence (AI) methods in medicine. The present study aimed to evaluate the effectiveness of a neural network in predicting lung cancer recurrence. The study employed retrospective data from 2,296 medical records of patients diagnosed with lung cancer and admitted to the Warmińsko-Mazurskie Center for Lung Diseases in Olsztyn, Poland. The statistical software STATISTICA 7.1, equipped with the Neural Networks module (StatSoft Inc., Tulsa, USA), was utilized to analyze the data. The neural network model was trained using patient information regarding gender, treatment, smoking status, family history, and symptoms of cancer. The study employed a multilayer perceptron neural network with a two-phase learning process. The network demonstrated high predictive ability, as indicated by the percentage of correct classifications, which amounted to 87.5%, 89.1%, and 89.9% for the training, validation, and test sets, respectively. The findings of this study support the potential usefulness of a neural network-based predictive model in assessing the risk of lung cancer recurrence. Further research is warranted to validate these findings and to explore AI's broader implications in cancer diagnosis and treatment.

Wing morphometrics of biting midges (Diptera: Culicoides) of veterinary importance in Madagascar.

Biting midges are vectors of arboviruses such as bluetongue virus, bovine ephemeral fever virus, Akabane virus, African horse sickness virus, epizootic haemorrhagic disease virus and Schmallenberg virus. Fast and accurate identification of biting midges is crucial in the study of Culicoides-borne diseases. Morphological identification of biting midges has revealed the presence of cryptic species. A total of 20 species are reported in Madagascar. In this study, we assessed wing morphometric analysis for identification of seven species namely C. dubitatus Kremer, Rebholtz-Hirtzel and Delécolle, C. enderleini Cornet and Brunhes, C. kibatiensis Goetghebuer, C. miombo Meiswinkel, C. moreli Clastrier, C. nevilli Cornet and Brunhes, and C. zuluensis de Meillon. Culicoides enderleini, C. miombo, C. moreli, C. nevilli and C. zuluensis are vectors diseases. A molecular approach, based on the cytochrome oxidase I gene (Cox1), was used for species delimitation. The molecular analysis presented seven different clades grouped two-by-two according to morphological characters. A total of 179 wing images were digitised. We found morphometric variation among seven species based on 11 landmarks and two outlines. Wing shape variation plots showed that species overlapped with species belonging to the same group. The cross-validation revealed a relatively high percentage of correct classification in most species, ranging from 91.3% to 100% for landmarks; 60% to 82.6% for outlines-1 and 77.1% to 91.3% for outlines-2. Our study suggests that wing geometric morphometric analysis is a robust tool for reliable "Moka Fohy" identification in Madagascar. This inexpensive and simple method is a precise supplement to morphological identification, with reaches the accuracy of Cox1 barcoding.

Machine learning for high-resolution landslide susceptibility mapping: case study in Inje County, South Korea

Landslides are a major natural hazard that can significantly damage infrastructure and cause loss of life. In South Korea, the current landslide susceptibility mapping (LSM) approach is mainly based on statistical techniques (logistic regression (LR) analysis). According to previous studies, this method has achieved an accuracy of approximately 75.2%. In this paper, we expand upon this traditional approach by comparing the performance of six machine learning (ML) algorithms for LSM in Inje County, South Korea. The study employed a combination of geographical data gathered from 2005 to 2019 to train and evaluate six algorithms, including LR, Gaussian Naive Bayes (GNB), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Random Forest (RF), and Extreme Gradient Boosting (XGB). The effectiveness of these models was measured by various criteria, such as the percentage of correct classification (PCC) score, F1 score, and Kappa score. The results demonstrated that the PCC and F1 scores of the six models fell between [0.869–0.941] and [0.857–0.940], respectively. RF and XGB had the highest PCC and F1 scores of 0.939 and 0.941, respectively. This study indicates that ML can be a valuable technique for high-resolution LSM in South Korea instead of the current approach.

Detection of Mycobacterium tuberculosis complex field infections in cattle using fecal volatile organic compound analysis through gas chromatography-ion mobility spectrometry combined with chemometrics.

Bovine tuberculosis is considered a re-emerging disease caused by different species from the Mycobacterium tuberculosis complex (MTC), important not only for the livestock sector but also for public health due to its zoonotic character. Despite the numerous efforts that have been carried out to improve the performance of the current antemortem diagnostic procedures, nowadays, they still pose several drawbacks, such as moderate to low sensitivity, highlighting the necessity to develop alternative and innovative tools to complement control and surveillance frameworks. Volatilome analysis is considered an innovative approach which has been widely employed in animal science, including animal health field and diagnosis, due to the useful and interesting information provided by volatile metabolites. Therefore, this study assesses the potential of gas chromatography coupled to ion mobility spectrometry (GC-IMS) to discriminate cattle naturally infected (field infections) by MTC from non-infected animals. Volatile organic compounds (VOCs) produced from feces were analyzed, employing the subsequent information through chemometrics. After the evaluation of variable importance for the projection of compounds, the final discriminant models achieved a robust performance in cross-validation, as well as high percentages of correct classification (>90%) and optimal data of sensitivity (91.66%) and specificity (99.99%) in external validation. The tentative identification of some VOCs revealed some coincidences with previous studies, although potential new compounds associated with the discrimination of infected and non-infected subjects were also addressed. These results provide strong evidence that a volatilome analysis of feces through GC-IMS coupled to chemometrics could become a valuable methodology to discriminate the infection by MTC in cattle. IMPORTANCE Bovine tuberculosis is endemic in many countries worldwide and poses important concerns for public health because of their zoonotic condition. However, current diagnostic techniques present several hurdles, such as low sensitivity and complexity, among others. In this regard, the development of new approaches to improve the diagnosis and control of this disease is considered crucial. Volatile organic compounds are small molecular mass metabolites which compose volatilome, whose analysis has been widely employed with success in different areas of animal science including animal health. The present study seeks to evaluate the combination of fecal volatilome analysis with chemometrics to detect field infections by bovine tuberculosis (Mycobacterium tuberculosis complex) in cattle. The good robust performance of discriminant models as well as the optimal data of sensitivity and specificity achieved highlight volatilome analysis as an innovative approach with huge potential.

Dietary adaptations and tooth morphology in squirrels: Insights from extant and extinct species

An important part of the ecological evolution of many lineages consists of adaptations to new diets as climate and available resources changed. In this study, we inferred when squirrels adapted morphologically to new diets by analyzing data from both extant and extinct species. We relied on the relationship between tooth morphology in extant squirrels and their dietary preferences to infer the diets of extinct species. To achieve this, we employed two approaches, namely geometric morphometrics and Elliptic Fourier analyses, to measure the outline of the fourth lower premolar (p4) in occlusal view. We then used both datasets to infer the diets of extinct species. Additionally, we used phylogenetic comparative methods on extant data to explore the evolution of diet and tooth size, identifying potential drivers of squirrel morphological evolution in the context of past climatic changes. Our findings indicate that the morphology of squirrel teeth has been maintained through the evolutionary history of most lineages, but that it also has changed in some lineages as a result of adaptations to particularly demanding diets, sometimes mediated by climatic factors, which have played a crucial role in shaping tooth morphology. Furthermore, we demonstrated that both geometric morphometrics and Elliptic Fourier analyses can yield a similar percentage of correct classifications and congruent dietary inferences. This study provides valuable insights into the macroevolutionary changes in squirrels and provides further evidence of the usefulness of tooth morphology for inferring the diets of extinct mammalian species.

Intravenous ketamine for benzodiazepine deprescription and withdrawal management in treatment-resistant depression: a preliminary report

We present the first evidence that sub-anesthetic ketamine infusions for treatment resistant depression (TRD) may facilitate deprescription of long-term benzodiazepine/z-drugs (BZDRs). Long-term BZDR prescriptions are potentially harmful yet common, partly because of challenging withdrawal symptoms. Few pharmacological interventions have evidence for facilitating BZDR discontinuation, and none in patients actively suffering from TRD. In this ambi-directional cohort study, discontinuation of long-term (>6 month) BZDRs was attempted in 22 patients with severe unipolar or bipolar TRD receiving a course of six subanesthetic ketamine infusions over four weeks. We investigated the rates of successful BZDRs deprescription, trajectories of acute psychological withdrawal symptoms, and subsequent BZDRs abstinence during a mean follow-up of 1 year (primary outcome). Clinically significant deteriorations in depression, anxiety, sleep, and/or suicidality during the acute BZDR discontinuation phase were measured by repeated standardized scales and analyzed by latent growth curve models and percent correct classification analysis. Of the 22 eligible patients, all enrolled in this study and 91% (20/22) successfully discontinued all BZDRs by the end of the 4-week intervention, confirmed by urinary analyses. Less than 25% of discontinuers experienced any significant worsening of anxiety, depression, sleep difficulties, or suicidality during treatment. During follow-up (mean [range] duration, 12 [3–24] months), 64% (14/22) of patients remained abstinent from any BZDRs. These preliminary results suggest that ketamine infusions for TRD may facilitate the deprescription of BZDRs, even in patients with active depressive symptoms and significant comorbidity. Further investigation is warranted into this potential novel application of ketamine.

Electronic periodontal tool integration to enrich clinical diagnosis.

The objective of this study was to evaluate the effectiveness of an Electronic-Periodontal-Diagnosis-Tool (EPDT) to facilitate the formulation of a correct periodontal diagnosis and analyze students' perceptions of the use of the EPDT. Fifty Year-3 students who recently started their clinical training, were randomly assigned to two groups. Two clinical scenarios involving challenging periodontal diagnoses, each one with unique components, variables, and categories were distributed with specific instructions. The cases were analyzed to determine the correct periodontal diagnosis-half without the use of the EPDT and half with the use of the EPDT. A post-exercise discussion conducted by the faculty explained the answer rationales. The students completed an anonymous/voluntary survey to evaluate their perceptions. Statistical analysis using likelihood ratio chi-square tests and a generalized linear model evaluated whether the use of the EPDT resulted in higher percentages of correct diagnoses. EPDT use resulted in a three times higher percentage of correct classifications than no tool use (48% versus 16%), which the investigators considered an important effect of the EPDT. The generalized-linear-model assessment confirmed that EPDT resulted in better classifications (p<0.0001). The feedback about the perceptions of the EPDT was favorable. Students using the EPDT resulted in higher percentages of correct diagnoses. The EPDT provided students with a useful framework to determine the correct periodontal diagnoses, which is essential in providing appropriate treatments.

Classification of Lubricating Oil Types Using Mid-Infrared Spectroscopy Combined with Linear Discriminant Analysis–Support Vector Machine Algorithm

To realize the classification of lubricating oil types using mid-infrared (MIR) spectroscopy, linear discriminant analysis (LDA) was used for the dimensionality reduction of spectrum data, and the classification model was established based on the support vector machine (SVM). The spectra of the samples were pre-processed by interval selection, Savitzky–Golay smoothing, multiple scattering correction, and normalization. The Kennard–Stone algorithm (K/S) was used to construct the calibration and validation sets. The percentage of correct classification (%CC) was used to evaluate the model. This study compared the results obtained with several chemometric methods: PLS-DA, LDA, principal component analysis (PCA)-SVM, and LDA-SVM in MIR spectroscopy applications. In both calibration and verification sets, the LDA-SVM model achieved 100% favorable results. The PLS-DA analysis performed poorly. The cyclic resistance ratio (CRR) of the calibration set was classified via the LDA and PCA-SVM analysis as 100%, but the CRR of the verification set was not as good. The LDA-SVM model was superior to the other three models; it exhibited good robustness and strong generalization ability, providing a new method for the classification of lubricating oil types by MIR spectroscopy.

Exploring the potential of a machine learning-based methodology for fault classification in inverter-based resource interconnection lines

Considering the increasing penetration of Inverter-Based Resources (IBRs) in electrical power systems, and the observed impacts on protection and fault diagnosis functions due to their atypical operational characteristics, this paper proposes a fault classification methodology that presents high efficiency for IBR interconnection lines. The fault classification methodology, which combines Discrete Wavelet Transform (DWT) with Machine Learning (ML) tree or rule-based methods, is presented and evaluated. The generalization ability of this methodology as well as the influence of the number and representativeness of training instances on the percentage of correct fault classifications are scrutinized. The proposed methodology was also evaluated for systems with different voltage levels, noisy signals, and considering variations in fault types, locations, inception angles, and resistances, in addition to different grid short circuit levels and IBR controls. Finally, comparisons are made with state-of-the-art fault classification methods to prove the impact of IBRs on these methods and to highlight the superiority of the proposed methodology. For the case studies, two systems with different voltage levels and typical connection topologies of IBRs to the grid are modeled in the PSCAD software, and several contingency scenarios are simulated.

Rapid discrimination of the identity of infant formula by triple-channel models

Infant formula is related to children's life and health. However, the existing identification methods for infant formula are time-consuming, costly and prone to environmental pollution. Therefore, a simple, efficient and less polluting identification method for infant formula is urgently needed. The aim of this study was to distinguish between goat and cow infant formula using HS-SPME-GC–MS and E-nose combined with triple-channel models. The results indicated that the main difference of them attributed to thirteen volatile compounds and three sensor variables. Based on this, the linear discriminant and partial least squares discriminant analyses were conducted, and a multilayer perceptron neural network model was constructed to identify the commercial samples. There was a high percentage of correct classifications (>90%) in samples. Together, our work demonstrated that the volatile compounds of infant formula combined with chemometric analysis were effective and rapid for detecting two infant formulas.

ВЫБОР МЕТОДОВ СТАТИСТИЧЕСКОЙ ОБРАБОТКИ РЕЗУЛЬТАТОВ РАДИОМИЧЕСКОГО АНАЛИЗА КТ-ИЗОБРАЖЕНИЙ ОПУХОЛЕЙ ГОЛОВЫ И ШЕИ

Purpose: Selection of the optimal method for statistical processing of the results of texture analysis of conventional CT images in patients with head and neck tumors. Material and methods: A total of 118 patients aged from 4 to 80 years with a verified diagnosis of 37 benign and 81 malignant head and neck tumors were studied. Texture analysis was performed using LIFEx program, version 7.10, with statistical processing using SPSS, MedCalc, XLSTAT, R. Results: The 39 texture indicators extracted from CT images were subjected to statistical processing by different methods, including Mann-Whitney U test, correlation matrix, factor analysis, LASSO-regression, ending with the development of a logistic classification model. Of the multiple processing methods, LASSO-regression followed by logistic model was optimal; according to its results, the percentage of correct classification of benign and malignant patient groups was – 81.3 %, area under the ROC curve was 0.902±0.029 (p&lt;0.0001), sensitivity – 82.7 %, specificity – 87.5 %. Conclusion: Texture analysis of medical images allows non-invasive prediction of benign or malignant nature of the imaged head and neck mass. The choice of the correct method for statistical processing of texture analysis results is critical to assess and classify patients according to the nature of the tumor.