Genetic Algorithm for Feature Selection Applied to Financial Time Series Monotonicity Prediction: Experimental Cases in Cryptocurrencies and Brazilian Assets.

Since financial assets on stock exchanges were created, investors have sought to predict their future values. Currently, cryptocurrencies are also seen as assets. Machine learning is increasingly adopted to assist and automate investments. The main objective of this paper is to make daily predictions about the movement direction of financial time series through classification models, financial time series preprocessing methods, and feature selection with genetic algorithms. The target time series are Bitcoin, Ibovespa, and Vale. The methodology of this paper includes the following steps: collecting time series of financial assets; data preprocessing; feature selection with genetic algorithms; and the training and testing of machine learning models. The results were obtained by evaluating the models with the area under the ROC curve metric. For the best prediction models for Bitcoin, Ibovespa, and Vale, values of 0.61, 0.62, and 0.58 were obtained, respectively. In conclusion, the feature selection allowed the improvement of performance in most models, and the input series in the form of percentage variation obtained a good performance, although it was composed of fewer attributes in relation to the other sets tested.

MFCC Parameters of the Speech Signal: An Alternative to Formant-Based Instantaneous Vocal Tract Length Estimation.

On the one hand, the relationship between formant frequencies and vocal tract length (VTL) has been intensively studied over the years. On the other hand, the connection involving mel-frequency cepstral coefficients (MFCCs), which concisely codify the overall shape of a speaker's spectral envelope with just a few cepstral coefficients, and VTL has only been modestly analyzed, being worth of further investigation. Thus, based on different statistical models, this article explores the advantages and disadvantages of the latter approach, which is relatively novel, in contrast to the former which arises from more traditional studies. Additionally, VTL is assumed to be a static and inherent characteristic of speakers, that is, a single length parameter is frequently estimated per speaker. By contrast, in this paper we consider VTL estimation from a dynamic perspective using modern real-time Magnetic Resonance Imaging (rtMRI) to measure VTL in parallel with audio signals. To support the experiments, data obtained from USC-TIMIT magnetic resonance videos were used, allowing for the 2D real-time analysis of articulators in motion. As a result, we observed that the performance of MFCCs in case of speaker-dependent modeling is higher, however, in case of cross-speaker modeling, which uses different speakers' data for training and evaluating, its performance is not significantly different of that obtained with formants. In complement, we note that the estimation based on MFCCs is robust, with an acceptable computational time complexity, coherent with the traditional approach.

An Experimental Analysis on Multicepstral Projection Representation Strategies for Dysphonia Detection.

Biometrics-based authentication has become the most well-established form of user recognition in systems that demand a certain level of security. For example, the most commonplace social activities stand out, such as access to the work environment or to one's own bank account. Among all biometrics, voice receives special attention due to factors such as ease of collection, the low cost of reading devices, and the high quantity of literature and software packages available for use. However, these biometrics may have the ability to represent the individual impaired by the phenomenon known as dysphonia, which consists of a change in the sound signal due to some disease that acts on the vocal apparatus. As a consequence, for example, a user with the flu may not be properly authenticated by the recognition system. Therefore, it is important that automatic voice dysphonia detection techniques be developed. In this work, we propose a new framework based on the representation of the voice signal by the multiple projection of cepstral coefficients to promote the detection of dysphonic alterations in the voice through machine learning techniques. Most of the best-known cepstral coefficient extraction techniques in the literature are mapped and analyzed separately and together with measures related to the fundamental frequency of the voice signal, and its representation capacity is evaluated on three classifiers. Finally, the experiments on a subset of the Saarbruecken Voice Database prove the effectiveness of the proposed material in detecting the presence of dysphonia in the voice.

New artificial intelligence index based on Scheimpflug corneal tomography to distinguish subclinical keratoconus from healthy corneas.

PURPOSE: To assess the efficiency of an index derived from multiple logistic regression analysis (MLRA) to measure differences in corneal tomography findings between subclinical keratoconus (KC) in 1 eye, corneal ectasia, and healthy corneas. SETTING: 2 private Brazilian ophthalmological centers. DESIGN: Multicenter case-control study. METHODS: This study included 187 eyes with very asymmetric ectasia and with normal corneal topography and tomography (VAE-NTT) in the VAE-NTT group, 2296 eyes with healthy corneas in the control group (CG), and 410 eyes with ectasia in the ectasia group. An index, termed as Boosted Ectasia Susceptibility Tomography Index (BESTi), was derived using MLRA to identify a cutoff point to distinguish patients in the 3 groups. The groups were divided into 2 subgroups with an equal number of patients: validation set and external validation (EV) set. RESULTS: 2893 patients with 2893 eyes were included. BESTi had an area under the curve (AUC) of 0.91 with 86.02% sensitivity (Se) and 83.97% specificity (Sp) between CG and the VAE-NTT group in the EV set, which was significantly greater than those of the Belin-Ambrósio Deviation Index (BAD-D) (AUC: 0.81; Se: 66.67%; Sp: 82.67%; P < .0001) and Pentacam random forest index (PRFI) (AUC: 0.87; Se: 78.49%; Sp: 79.88%; P = .021). CONCLUSIONS: BESTi facilitated early detection of ectasia in subclinical KC and demonstrated higher Se and Sp than PRFI and BAD-D for detecting subclinical KC.

Residual Neural Network precisely quantifies dysarthria severity-level based on short-duration speech segments.

Recently, we have witnessed Deep Learning methodologies gaining significant attention for severity-based classification of dysarthric speech. Detecting dysarthria, quantifying its severity, are of paramount importance in various real-life applications, such as the assessment of patients' progression in treatments, which includes an adequate planning of their therapy and the improvement of speech-based interactive systems in order to handle pathologically-affected voices automatically. Notably, current speech-powered tools often deal with short-duration speech segments and, consequently, are less efficient in dealing with impaired speech, even by using Convolutional Neural Networks (CNNs). Thus, detecting dysarthria severity-level based on short speech segments might help in improving the performance and applicability of those systems. To achieve this goal, we propose a novel Residual Network (ResNet)-based technique which receives short-duration speech segments as input. Statistically meaningful objective analysis of our experiments, reported over standard Universal Access corpus, exhibits average values of 21.35% and 22.48% improvement, compared to the baseline CNN, in terms of classification accuracy and F1-score, respectively. For additional comparisons, tests with Gaussian Mixture Models and Light CNNs were also performed. Overall, the values of 98.90% and 98.00% for classification accuracy and F1-score, respectively, were obtained with the proposed ResNet approach, confirming its efficacy and reassuring its practical applicability.

Predictive Factors of Long-Term Stay in the ICU after Cardiac Surgery: Logistic CASUS Score, Serum Bilirubin Dosage and Extracorporeal Circulation Time.

OBJECTIVE: To test the capacity of the Logistic CASUS Score on the second postoperative day, the total serum bilirubin dosage on the second postoperative day and the extracorporeal circulation time, as possible predictive factors of long-term stay in Intensive Care Unit after cardiac surgery. METHODS: Eight-two patients submitted to cardiac surgery with extracorporeal circulation were selected. The Logistic CASUS Score on the second postoperative day was calculated and bilirubin dosage on the second postoperative day was measured. The extracorporeal circulation time was also registered. Patients were divided into two groups: Group A, those who were discharged up to the second day of postoperative care; Group B, those who were discharged after the second day of postoperative care. RESULTS: In this study, 40 cases were listed in Group A and 42 cases in Group B. The mean extracorporeal circulation time was 83.9±29.4 min in Group A and 95.8±29.31 min in Group B. Extracorporeal circulation time was not significant in this study (P=0.0735). The level of P significance of bilirubin dosage on the second postoperative day was 0.0003 and an area under the ROC curve of 0.708 with a cut-off point at 0.51 mg/dl was registered. The level of P significance of Logistic CASUS Score on the second postoperative day was 0.0001 and an area under the ROC curve of 0.723 with a cut-off point at 0.40% was registered. CONCLUSION: The Logistic CASUS Score on the second postoperative day has shown to be better than the bilirubin dosage on the second postoperative day as a predictive tool for calculating the length of stay in intensive care unit during the postoperative care period of patients. Notwithstanding, extracorporeal circulation time has failed to prove itself as an efficient tool to predict an extended length of stay in intensive care unit.

Predictive factors of long-term stay in the icu after cardiac surgery: logistic casus score, serum bilirubin dosage and extracorporeal circulation time

Abstract Objective: To test the capacity of the Logistic CASUS Score on the second postoperative day, the total serum bilirubin dosage on the second postoperative day and the extracorporeal circulation time, as possible predictive factors of long-term stay in Intensive Care Unit after cardiac surgery. Methods: Eight-two patients submitted to cardiac surgery with extracorporeal circulation were selected. The Logistic CASUS Score on the second postoperative day was calculated and bilirubin dosage on the second postoperative day was measured. The extracorporeal circulation time was also registered. Patients were divided into two groups: Group A, those who were discharged up to the second day of postoperative care; Group B, those who were discharged after the second day of postoperative care. Results: In this study, 40 cases were listed in Group A and 42 cases in Group B. The mean extracorporeal circulation time was 83.9±29.4 min in Group A and 95.8±29.31 min in Group B. Extracorporeal circulation time was not significant in this study (P=0.0735). The level of P significance of bilirubin dosage on the second postoperative day was 0.0003 and an area under the ROC curve of 0.708 with a cut-off point at 0.51 mg/dl was registered. The level of P significance of Logistic CASUS Score on the second postoperative day was 0.0001 and an area under the ROC curve of 0.723 with a cut-off point at 0.40% was registered. Conclusion: The Logistic CASUS Score on the second postoperative day has shown to be better than the bilirubin dosage on the second postoperative day as a predictive tool for calculating the length of stay in intensive care unit during the postoperative care period of patients. Notwithstanding, extracorporeal circulation time has failed to prove itself as an efficient tool to predict an extended length of stay in intensive care unit.

Wavelet time-frequency analysis and least squares support vector machines for the identification of voice disorders.

This work describes a novel algorithm to identify laryngeal pathologies, by the digital analysis of the voice. It is based on Daubechies' discrete wavelet transform (DWT-db), linear prediction coefficients (LPC), and least squares support vector machines (LS-SVM). Wavelets with different support-sizes and three LS-SVM kernels are compared. Particularly, the proposed approach, implemented with modest computer requirements, leads to an adequate larynx pathology classifier to identify nodules in vocal folds. It presents over 90% of classification accuracy and has a low order of computational complexity in relation to the speech signal's length.