RESUMO

The continuous improvement of the steelmaking process is a critical issue for steelmakers. In the production of Ca-treated Al-killed steel, the Ca and S contents are controlled for successful inclusion modification treatment. In this study, a machine learning technique was used to build a decision tree classifier and thus identify the process variables that most influence the desired Ca and S contents at the end of ladle furnace refining. The attribute of the root node of the decision tree was correlated with process variables via the Pearson formalism. Thus, the attribute of the root node corresponded to the sulfur distribution coefficient at the end of the refining process, and its value allowed for the discrimination of satisfactory heats from unsatisfactory heats. The variables with higher correlation with the sulfur distribution coefficient were the content of sulfur in both steel and slag at the end of the refining process, as well as the Si content at that stage of the process. As secondary variables, the Si content and the basicity of the slag at the end of the refining process were correlated with the S content in the steel and slag, respectively, at that stage. The analysis showed that the conditions of steel and slag at the beginning of the refining process and the efficient S removal during the refining process are crucial for reaching desired Ca and S contents.

RESUMO

Functional magnetic resonance imaging (fMRI) studies on migraine with aura are challenging due to the rarity of patients with triggered cases. This study optimized methodologies to explore differences in ictal and interictal spatiotemporal activation patterns based on visual stimuli using fMRI in two patients with unique aura triggers. Both patients underwent separate fMRI sessions during the ictal and interictal periods. The Gaussian Process Classifier (GPC) was used to differentiate these periods by employing a machine learning temporal embedding approach and spatiotemporal activation patterns based on visual stimuli. When restricted to visual and occipital regions, GPC had an improved performance, with accuracy rates for patients A and B of roughly 86-90% and 77-81%, respectively (p < 0.01). The algorithm effectively differentiated visual stimulation and rest periods and identified times when aura symptoms manifested, as evident from the varying predicted probabilities in the GPC models. These findings contribute to our understanding of the role of visual processing and brain activity patterns in migraine with aura and the significance of temporal embedding techniques in examining aura phenomena. This finding has implications for diagnostic tools and therapeutic techniques, especially for patients suffering from aura symptoms.

Assuntos

RESUMO

This paper proposes the transformation S→C→, where S is a digital gray-level image and C→ is a vector expressed through the textural space. The proposed transformation is denominated Vectorial Image Representation on the Texture Space (VIR-TS), given that the digital image S is represented by the textural vector C→. This vector C→ contains all of the local texture characteristics in the image of interest, and the texture unit T→ entertains a vectorial character, since it is defined through the resolution of a homogeneous equation system. For the application of this transformation, a new classifier for multiple classes is proposed in the texture space, where the vector C→ is employed as a characteristics vector. To verify its efficiency, it was experimentally deployed for the recognition of digital images of tree barks, obtaining an effective performance. In these experiments, the parametric value λ employed to solve the homogeneous equation system does not affect the results of the image classification. The VIR-TS transform possesses potential applications in specific tasks, such as locating missing persons, and the analysis and classification of diagnostic and medical images.

RESUMO

Diabetic Macular Edema (DME) is the most common sight-threatening complication of type 2 diabetes. Optical Coherence Tomography (OCT) is the most useful imaging technique to diagnose, follow up, and evaluate treatments for DME. However, OCT exam and devices are expensive and unavailable in all clinics in low- and middle-income countries. Our primary goal was therefore to develop an alternative method to OCT for DME diagnosis by introducing spectral information derived from spontaneous electroretinogram (ERG) signals as a single input or combined with fundus that is much more widespread. Baseline ERGs were recorded in 233 patients and transformed into scalograms and spectrograms via Wavelet and Fourier transforms, respectively. Using transfer learning, distinct Convolutional Neural Networks (CNN) were trained as classifiers for DME using OCT, scalogram, spectrogram, and eye fundus images. Input data were randomly split into training and test sets with a proportion of 80 %-20 %, respectively. The top performers for each input type were selected, OpticNet-71 for OCT, DenseNet-201 for eye fundus, and non-evoked ERG-derived scalograms, to generate a combined model by assigning different weights for each of the selected models. Model validation was performed using a dataset alien to the training phase of the models. None of the models powered by mock ERG-derived input performed well. In contrast, hybrid models showed better results, in particular, the model powered by eye fundus combined with mock ERG-derived information with a 91 % AUC and 86 % F1-score, and the model powered by OCT and mock ERG-derived scalogram images with a 93 % AUC and 89 % F1-score. These data show that the spontaneous ERG-derived input adds predictive value to the fundus- and OCT-based models to diagnose DME, except for the sensitivity of the OCT model which remains the same. The inclusion of mock ERG signals, which have recently been shown to take only 5 min to record in daylight conditions, therefore represents a potential improvement over existing OCT-based models, as well as a reliable and cost-effective alternative when combined with the fundus, especially in underserved areas, to predict DME.

Assuntos

RESUMO

BACKGROUND: Autism Spectrum Disorder (ASD) diagnosis can be aided by approaches based on eye-tracking signals. Recently, the feasibility of building Visual Attention Models (VAMs) from features extracted from visual stimuli and their use for classifying cases and controls has been demonstrated using Neural Networks and Support Vector Machines. The present work has three aims: 1) to evaluate whether the trained classifier from the previous study was generalist enough to classify new samples with a new stimulus; 2) to replicate the previously approach to train a new classifier with a new dataset; 3) to evaluate the performance of classifiers obtained by a new classification algorithm (Random Forest) using the previous and the current datasets. METHODS: The previously approach was replicated with a new stimulus and new sample, 44 from the Typical Development group and 33 from the ASD group. After the replication, Random Forest classifier was tested to substitute Neural Networks algorithm. RESULTS: The test with the trained classifier reached an AUC of 0.56, suggesting that the trained classifier requires retraining of the VAMs when changing the stimulus. The replication results reached an AUC of 0.71, indicating the potential of generalization of the approach for aiding ASD diagnosis, as long as the stimulus is similar to the originally proposed. The results achieved with Random Forest were superior to those achieved with the original approach, with an average AUC of 0.95 for the previous dataset and 0.74 for the new dataset. CONCLUSION: In summary, the results of the replication experiment were satisfactory, which suggests the robustness of the approach and the VAM-based approaches feasibility to aid in ASD diagnosis. The proposed method change improved the classification performance. Some limitations are discussed and additional studies are encouraged to test other conditions and scenarios.

Assuntos

RESUMO

In industrial applications based on texture classification, efficient and fast classifiers are extremely useful for quality control of industrial processes. The classifier of texture images has to satisfy two requirements: It must be efficient and fast. In this work, a texture unit is coded in parallel, and using observation windows larger than 3×3, a new texture spectrum called Texture Spectrum based on the Parallel Encoded Texture Unit (TS_PETU) is proposed, calculated, and used as a characteristic vector in a multi-class classifier, and then two image databases are classified. The first database contains images from the company Interceramic®® and the images were acquired under controlled conditions, and the second database contains tree stems and the images were acquired in natural environments. Based on our experimental results, the TS_PETU satisfied both requirements (efficiency and speed), was developed for binary images, and had high efficiency, and its compute time could be reduced by applying parallel coding concepts. The classification efficiency increased by using larger observational windows, and this one was selected based on the window size. Since the TS_PETU had high efficiency for Interceramic®® tile classification, we consider that the proposed technique has significant industrial applications.

RESUMO

The current contribution aimed to evaluate the capacity of the naive Bayes classifier to predict the progression of dengue fever to severe infection in children based on a defined set of clinical conditions and laboratory parameters. This case-control study was conducted by reviewing patient files in two public hospitals in an endemic area in Mexico. All 99 qualifying files showed a confirmed diagnosis of dengue. The 32 cases consisted of patients who entered the intensive care unit, while the 67 control patients did not require intensive care. The naive Bayes classifier could identify factors predictive of severe dengue, evidenced by 78% sensitivity, 91% specificity, a positive predictive value of 8.7, a negative predictive value of 0.24, and a global yield of 0.69. The factors that exhibited the greatest predictive capacity in the model were seven clinical conditions (tachycardia, respiratory failure, cold hands and feet, capillary leak leading to the escape of blood plasma, dyspnea, and alterations in consciousness) and three laboratory parameters (hypoalbuminemia, hypoproteinemia, and leukocytosis). Thus, the present model showed a predictive and adaptive capacity in a small pediatric population. It also identified attributes (i.e., hypoalbuminemia and hypoproteinemia) that may strengthen the WHO criteria for predicting progression to severe dengue.

RESUMO

This paper presents the development of an instrumented exoskeleton with baropodometry, electromyography, and torque sensors. The six degrees of freedom (Dof) exoskeleton has a human intention detection system based on a classifier of electromyographic signals coming from four sensors placed in the muscles of the lower extremity together with baropodometric signals from four resistive load sensors placed at the front and rear parts of both feet. In addition, the exoskeleton is instrumented with four flexible actuators coupled with torque sensors. The main objective of the paper was the development of a lower limb therapy exoskeleton, articulated at hip and knees to allow the performance of three types of motion depending on the detected user's intention: sitting to standing, standing to sitting, and standing to walking. In addition, the paper presents the development of a dynamical model and the implementation of a feedback control in the exoskeleton.

Assuntos

RESUMO

The work carried out in this paper consists of the classification of the physiological signal generated by eye movement called Electrooculography (EOG). The human eye performs simultaneous movements, when focusing on an object, generating a potential change in origin between the retinal epithelium and the cornea and modeling the eyeball as a dipole with a positive and negative hemisphere. Supervised learning algorithms were implemented to classify five eye movements; left, right, down, up and blink. Wavelet Transform was used to obtain information in the frequency domain characterizing the EOG signal with a bandwidth of 0.5 to 50 Hz; training results were obtained with the implementation of K-Nearest Neighbor (KNN) 69.4%, a Support Vector Machine (SVM) of 76.9% and Decision Tree (DT) 60.5%, checking the accuracy through the Jaccard index and other metrics such as the confusion matrix and ROC (Receiver Operating Characteristic) curve. As a result, the best classifier for this application was the SVM with Jaccard Index.

Assuntos

RESUMO

Livestock is an important part of many countries gross domestic product, and sanitary control impacts herd management costs. To contribute to incorporating new technologies into this economic chain, this work presents a mobile application for decision assistance to treatment against parasitic infection by Haemonchus contortus in small ruminants. Based on the Android system, the proposed software is a semi-automated computer-aided procedure to assist Famacha© pre-trained farmers in applying anthelmintic treatment. It mimics the two-class decision procedure performed by the veterinarian with the help of the Famacha© card. The embedded cell phone camera was employed to acquire an image from the ocular conjunctival mucosa, classifying the animal as healthy or anemic. Two machine-learning strategies were assessed, resulting in an accuracy of 83 % for a neural network and 87 % for a support vector machine (SVM). The SVM classifier was embedded into the app and made available for evaluation. This work is particularly interesting to small property owners from regions with difficult access or restrictions on obtaining continuous post-training technical guidance to use the Famacha© method effectively.

Assuntos

RESUMO

We present a genome polymorphisms/machine learning approach for severe COVID-19 prognosis. Ninety-six Brazilian severe COVID-19 patients and controls were genotyped for 296 innate immunity loci. Our model used a feature selection algorithm, namely recursive feature elimination coupled with a support vector machine, to find the optimal loci classification subset, followed by a support vector machine with the linear kernel (SVM-LK) to classify patients into the severe COVID-19 group. The best features that were selected by the SVM-RFE method included 12 SNPs in 12 genes: PD-L1, PD-L2, IL10RA, JAK2, STAT1, IFIT1, IFIH1, DC-SIGNR, IFNB1, IRAK4, IRF1, and IL10. During the COVID-19 prognosis step by SVM-LK, the metrics were: 85% accuracy, 80% sensitivity, and 90% specificity. In comparison, univariate analysis under the 12 selected SNPs showed some highlights for individual variant alleles that represented risk (PD-L1 and IFIT1) or protection (JAK2 and IFIH1). Variant genotypes carrying risk effects were represented by PD-L2 and IFIT1 genes. The proposed complex classification method can be used to identify individuals who are at a high risk of developing severe COVID-19 outcomes even in uninfected conditions, which is a disruptive concept in COVID-19 prognosis. Our results suggest that the genetic context is an important factor in the development of severe COVID-19.

Assuntos

RESUMO

Feature selection is becoming a relevant problem within the field of machine learning. The feature selection problem focuses on the selection of the small, necessary, and sufficient subset of features that represent the general set of features, eliminating redundant and irrelevant information. Given the importance of the topic, in recent years there has been a boom in the study of the problem, generating a large number of related investigations. Given this, this work analyzes 161 articles published between 2019 and 2023 (20 April 2023), emphasizing the formulation of the problem and performance measures, and proposing classifications for the objective functions and evaluation metrics. Furthermore, an in-depth description and analysis of metaheuristics, benchmark datasets, and practical real-world applications are presented. Finally, in light of recent advances, this review paper provides future research opportunities.

RESUMO

BACKGROUND: The diagnosis of cancer in Bethesda III/IV thyroid nodules is challenging as fine-needle aspiration (FNA) has limitations, and these cases usually require diagnostic surgery. As approximately 77% of these nodules are not malignant, a diagnostic test accurately identifying benign thyroid nodules can reduce "potentially unnecessary" surgery rates. We have previously reported the development and validation of a microRNA-based thyroid classifier (mir-THYpe) with high sensitivity and specificity, which could be performed directly from FNA smear slides. We sought to evaluate the performance of this test in real-world clinical routine to support clinical decisions and to reduce surgery rates. METHODS: We designed a real-world, prospective, multicentre study. Molecular tests were performed with FNA samples prepared at 128 cytopathology laboratories. Patients were followed-up from March 2018 until surgery or until March 2020 (patients with no indication for surgery). The final diagnosis of thyroid tissue samples was retrieved from postsurgical anatomopathological reports. FINDINGS: A total of 435 patients (440 nodules) classified as Bethesda III/IV were followed-up. The rate of avoided surgeries was 52·5% for all surgeries and 74·6% for "potentially unnecessary" surgeries. The test achieved 89·3% sensitivity, 81·65% specificity, 66·2% positive predictive value, and 95% negative predictive value. The test supported 92·3% of clinical decisions. INTERPRETATION: The reported data demonstrate that the use of the microRNA-based classifier in the real-world can reduce the rate of thyroid surgeries with robust performance and support clinical decision-making. FUNDING: The São Paulo Research-Foundation (FAPESP) and Onkos.

Assuntos

RESUMO

Pulmonary tuberculosis (TB) is one of the top 10 causes of death worldwide caused by an infection. TB is curable with an adequate diagnosis, normally performed through bacilloscopies. Automate TB diagnosis implies bacilli detection and counting usually based on smear images processing and artificial intelligence. Works reported in the literature usually consider images with similar coloring characteristics, which are difficult to obtain due to the Ziehl - Neelsen staining method variations (excess or deficiency of coloration), provoking errors in the bacilli segmentation. This paper presents an image preprocessing technique, based on simple, fast and well-known processing techniques, to improve and standardize the contrast in the Acid-Fast Bacilli (AFB) images used to diagnose TB; these techniques are used previously to the segmentation stage to obtain accurate results. The results are validated with and without the preprocessing stage by the Jaccard index, pixel detection accuracy and UAC obtained in an Artificial Neural Network (ANN) and a Bayesian classifier with Gaussian mixture model (GMM). Obtained results indicate that the proposed approach can be applied to automate the Tuberculosis diagnostic.

Assuntos

RESUMO

The classifier selection problem in Assistive Technology Adoption refers to selecting the classification algorithms that have the best performance in predicting the adoption of technology, and is often addressed through measuring different single performance indicators. Satisfactory classifier selection can help in reducing time and costs involved in the technology adoption process. As there are multiple criteria from different domains and several candidate classification algorithms, the classifier selection process is now a problem that can be addressed using Multiple-Criteria Decision-Making (MCDM) methods. This paper proposes a novel approach to address the classifier selection problem by integrating Intuitionistic Fuzzy Sets (IFS), Decision Making Trial and Evaluation Laboratory (DEMATEL), and the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS). The step-by-step procedure behind this application is as follows. First, IF-DEMATEL was used for estimating the criteria and sub-criteria weights considering uncertainty. This method was also employed to evaluate the interrelations among classifier selection criteria. Finally, a modified TOPSIS was applied to generate an overall suitability index per classifier so that the most effective ones can be selected. The proposed approach was validated using a real-world case study concerning the adoption of a mobile-based reminding solution by People with Dementia (PwD). The outputs allow public health managers to accurately identify whether PwD can adopt an assistive technology which results in (i) reduced cost overruns due to wrong classification, (ii) improved quality of life of adopters, and (iii) rapid deployment of intervention alternatives for non-adopters.

Assuntos

RESUMO

The purpose of this study is to analyze the contribution of the interactions between electrodes, measured either as correlation or as Jaccard distance, to the classification of two actions in a motor imagery paradigm, namely, left-hand movement and right-hand movement. The analysis is performed in two classifier models, namely, a static (linear discriminant analysis, LDA) model and a dynamic (hidden conditional random field, HCRF) model. The impact of using the sliding window technique (SWT) in the static and dynamic models is also analyzed. The study proved that their combination with temporal features provides significant information to improve the classification in a two-class motor imagery task for LDA (average accuracy: 0.7192 no additional features, 0.7617 by adding correlation, 0.7606 by adding Jaccard distance; p < 0.001) and HCRF (average accuracy: 0.7370 no additional features, 0.7764 by adding correlation, 0.7793 by adding Jaccard distance; p < 0.001). Also, we showed that adding interactions between electrodes improves significantly the performance of each classifier, regarding the nature of the interaction measure or the classifier itself.

RESUMO

Knowledge of animal behavior can be indicative of the well-being, health, productivity, and reproduction of animals. The use of accelerometers to classify and predict animal behavior can be a tool for continuous animal monitoring. Therefore, the aim of this study was to provide strategies for predicting more and less frequent beef cattle grazing behaviors. The behavior activities observed were grazing, ruminating, idle, water consumption frequency (WCF), feeding (supplementation) and walking. Three Machine Learning algorithms: Random Forest (RF), Support Vector Machine (SVM) and Naïve Bayes Classifier (NBC) and two resample methods: under and over-sampling, were tested. Overall accuracy was higher for RF models trained with the over-sampled dataset. The greatest sensitivity (0.808) for the less frequent behavior (WCF) was observed in the RF algorithm trained with the under-sampled data. The SVM models only performed efficiently when classifying the most frequent behavior (idle). The greatest predictor in the NBC algorithm was for ruminating behavior, with the over-sampled training dataset. The results showed that the behaviors of the studied animals were classified with high accuracy and specificity when the RF algorithm trained with the resampling methods was used. Resampling training datasets is a strategy to be considered, especially when less frequent behaviors are of interest.

RESUMO

Several supervised machine learning algorithms focused on binary classification for solving daily problems can be found in the literature. The straight-line segment classifier stands out for its low complexity and competitiveness, compared to well-knownconventional classifiers. This binary classifier is based on distances between points and two labeled sets of straight-line segments. Its training phase consists of finding the placement of labeled straight-line segment extremities (and consequently, their lengths) which gives the minimum mean square error. However, during the training phase, the straight-line segment lengths can grow significantly, giving a negative impact on the classification rate. Therefore, this paper proposes an approach for adjusting the placements of labeled straight-line segment extremities to build reliable classifiers in a constrained search space (tuned by a scale factor parameter) in order to restrict their lengths. Ten artificial and eight datasets from the UCI Machine Learning Repository were used to prove that our approach shows promising results, compared to other classifiers. We conclude that this classifier can be used in industry for decision-making problems, due to the straightforward interpretation and classification rates.

RESUMO

Amyotrophic Lateral Sclerosis (ALS) is one of the most aggressive neurodegenerative diseases and is now recognized as a multisystem network disorder with impaired connectivity. Further research for the understanding of the nature of its cognitive affections is necessary to monitor and detect the disease, so this work provides insight into the neural alterations occurring in ALS patients during a cognitive task (P300 oddball paradigm) by measuring connectivity and the power and latency of the frequency-specific EEG activity of 12 ALS patients and 16 healthy subjects recorded during the use of a P300-based BCI to command a robotic arm. For ALS patients, in comparison to Controls, the results (p < 0.05) were: an increment in latency of the peak ERP in the Delta range (OZ) and Alpha range (PO7), and a decreased power in the Beta band among most electrodes; connectivity alterations among all bands, especially in the Alpha band between PO7 and the channels above the motor cortex. The evolution observed over months of an advanced-state patient backs up these findings. These results were used to compute connectivity- and power-based features to discriminate between ALS and Control groups using Support Vector Machine (SVM). Cross-validation achieved a 100% in specificity and 75% in sensitivity, with an overall 89% success.

Assuntos

RESUMO

Introduction: Several methods offer free volumetry services for MR data that adequately quantify volume differences in the hippocampus and its subregions. These methods are frequently used to assist in clinical diagnosis of suspected hippocampal sclerosis in temporal lobe epilepsy. A strong association between severity of histopathological anomalies and hippocampal volumes was reported using MR volumetry with a higher diagnostic yield than visual examination alone. Interpretation of volumetry results is challenging due to inherent methodological differences and to the reported variability of hippocampal volume. Furthermore, normal morphometric differences are recognized in diverse populations that may need consideration. To address this concern, we highlighted procedural discrepancies including atlas definition and computation of total intracranial volume that may impact volumetry results. We aimed to quantify diagnostic performance and to propose reference values for hippocampal volume from two well-established techniques: FreeSurfer v.06 and volBrain-HIPS. Methods: Volumetry measures were calculated using clinical T1 MRI from a local population of 61 healthy controls and 57 epilepsy patients with confirmed unilateral hippocampal sclerosis. We further validated the results by a state-of-the-art machine learning classification algorithm (Random Forest) computing accuracy and feature relevance to distinguish between patients and controls. This validation process was performed using the FreeSurfer dataset alone, considering morphometric values not only from the hippocampus but also from additional non-hippocampal brain regions that could be potentially relevant for group classification. Mean reference values and 95% confidence intervals were calculated for left and right hippocampi along with hippocampal asymmetry degree to test diagnostic accuracy. Results: Both methods showed excellent classification performance (AUC:> 0.914) with noticeable differences in absolute (cm3) and normalized volumes. Hippocampal asymmetry was the most accurate discriminator from all estimates (AUC:1~0.97). Similar results were achieved in the validation test with an automatic classifier (AUC:>0.960), disclosing hippocampal structures as the most relevant features for group differentiation among other brain regions. Conclusion: We calculated reference volumetry values from two commonly used methods to accurately identify patients with temporal epilepsy and hippocampal sclerosis. Validation with an automatic classifier confirmed the principal role of the hippocampus and its subregions for diagnosis.