sEMG-Based Hand Posture Recognition Considering Electrode Shift, Feature Vectors, and Posture Groups

Surface electromyography (sEMG)-based gesture recognition systems provide the intuitive and accurate recognition of various gestures in human-computer interaction. In this study, an sEMG-based hand posture recognition algorithm was developed, considering three main problems: electrode shift, feature vectors, and posture groups. The sEMG signal was measured using an armband sensor with the electrode shift. An artificial neural network classifier was trained using 21 feature vectors for seven different posture groups. The inter-session and inter-feature Pearson correlation coefficients (PCCs) were calculated. The results indicate that the classification performance improved with the number of training sessions of the electrode shift. The number of sessions necessary for efficient training was four, and the feature vectors with a high inter-session PCC (r > 0.7) exhibited high classification accuracy. Similarities between postures in a posture group decreased the classification accuracy. Our results indicate that the classification accuracy could be improved with the addition of more electrode shift training sessions and that the PCC is useful for selecting the feature vector. Furthermore, hand posture selection was as important as feature vector selection. These findings will help in optimizing the sEMG-based pattern recognition algorithm more easily and quickly.

A Generic Deep Learning Based Cough Analysis System from Clinically Validated Samples for Point-of-Need Covid-19 Test and Severity Levels

We seek to evaluate the detection performance of a rapid primary screening tool of Covid-19 solely based on the cough sound from 8,380 clinically validated samples with laboratory molecular-test (2,339 Covid-19 positive and 6,041 Covid-19 negative). Samples were clinically labelled according to the results and severity based on quantitative RT-PCR (qRT-PCR) analysis, cycle threshold and lymphocytes count from the patients. Our proposed generic method is a algorithm based on Empirical Mode Decomposition (EMD) with subsequent classification based on a tensor of audio features and deep artificial neural network classifier with convolutional layers called DeepCough'. Two different versions of DeepCough based on the number of tensor dimensions, i.e. DeepCough2D and DeepCough3D, have been investigated. These methods have been deployed in a multi-platform proof-of-concept Web App CoughDetect to administer this test anonymously. Covid-19 recognition results rates achieved a promising AUC (Area Under Curve) of 98.800.83%, sensitivity of 96.431.85%, and specificity of 96.201.74%, and 81.08%5.05% AUC for the recognition of three severity levels. Our proposed web tool and underpinning algorithm for the robust, fast, point-of-need identification of Covid-19 facilitates the rapid detection of the infection. We believe that it has the potential to significantly hamper the Covid-19 pandemic across the world.

Quantifying Perceived Facial Asymmetry to Enhance Physician–Patient Communications

In cosmetic surgery, bridging the anticipation gap between the patients and the physicians can be challenging if there lacks objective and transparent information exchange during the decision-making and surgical process. Among all factors, facial symmetry is the most important for assessing facial attractiveness. The aim of this work is to promote communications between the two parties by providing a quadruple of quantitative measurements: overall asymmetry index (oAI), asymmetry vector, classification, and confidence vector, using an artificial neural network classifier to model people’s perception acquired from visual questionnaires concerning facial asymmetry. The questionnaire results exhibit a Cronbach’s Alpha value of 0.94 and categorize the respondents’ perception of each stimulus face into perceived normal (PN), perceived asymmetrically normal (PAN), and perceived abnormal (PA) categories. The trained classifier yields an overall root mean squared error < 0.01, and its result shows that the oAI is, in general, proportional to the degree of perceived asymmetry. However, there exist faces that are difficult to classify as either PN or PAN or either PAN or PA with competing confidence values. In such cases, oAI alone is not sufficient to articulate facial asymmetry. Assisting surgeon–patient conversations with the proposed asymmetry quadruple is advised to avoid or to mitigate potential medical disputes.

Detection of ADHD From EEG Signals Using Different Entropy Measures and ANN

Attention deficit hyperactivity disorder (ADHD) is a prevalent behavioral, cognitive, neurodevelopmental pediatric disorder. Clinical evaluations, symptom surveys, and neuropsychological assessments are some of the ADHD assessment methods, which are time-consuming processes and have a certain degree of uncertainty. This research investigates an efficient computer-aided technological solution for detecting ADHD from the acquired electroencephalography (EEG) signals based on different nonlinear entropy estimators and an artificial neural network classifier. Features extracted through fuzzy entropy, log energy entropy, permutation entropy, SURE entropy, and Shannon entropy are analyzed for effective discrimination of ADHD subjects from the control group. The experimented results confirm that the proposed techniques can effectively detect and classify ADHD subjects. The permutation entropy gives the highest classification accuracy of 99.82%, sensitivity of 98.21%, and specificity of 98.82%. Also, the potency of different entropy estimators derived from the t-test reflects that the Shannon entropy has a higher P-value (>.001); therefore, it has a limited scope than other entropy estimators for ADHD diagnosis. Furthermore, the considerable variance found from potential features obtained in the frontal polar (FP) and frontal (F) lobes using different entropy estimators under the eyes-closed condition shows that the signals received in these lobes will have more significance in distinguishing ADHD from normal subjects.

The implication of machine learning for financial solvency prediction: an empirical analysis on public listed companies of Bangladesh

PurposeFinancial health of a corporation is a great concern for every investor level and decision-makers. For many years, financial solvency prediction is a significant issue throughout academia, precisely in finance. This requirement leads this study to check whether machine learning can be implemented in financial solvency prediction.Design/methodology/approachThis study analyzed 244 Dhaka stock exchange public-listed companies over the 2015–2019 period, and two subsets of data are also developed as training and testing datasets. For machine learning model building, samples are classified as secure, healthy and insolvent by the Altman Z-score. R statistical software is used to make predictive models of five classifiers and all model performances are measured with different performance metrics such as logarithmic loss (logLoss), area under the curve (AUC), precision recall AUC (prAUC), accuracy, kappa, sensitivity and specificity.FindingsThis study found that the artificial neural network classifier has 88% accuracy and sensitivity rate; also, AUC for this model is 96%. However, the ensemble classifier outperforms all other models by considering logLoss and other metrics.Research limitations/implicationsThe major result of this study can be implicated to the financial institution for credit scoring, credit rating and loan classification, etc. And other companies can implement machine learning models to their enterprise resource planning software to trace their financial solvency.Practical implicationsFinally, a predictive application is developed through training a model with 1,200 observations and making it available for all rational and novice investors (Abdullah, 2020).Originality/valueThis study found that, with the best of author expertise, the author did not find any studies regarding machine learning research of financial solvency that examines a comparable number of a dataset, with all these models in Bangladesh.

Optimal Length of Heart Rate Variability Data and Forecasting Time for Ventricular Fibrillation Prediction Using Machine Learning

Ventricular fibrillation (VF) is a cardiovascular disease that is one of the major causes of mortality worldwide, according to the World Health Organization. Heart rate variability (HRV) is a biomarker that is used for detecting and predicting life-threatening arrhythmias. Predicting the occurrence of VF in advance is important for saving patients from sudden death. We extracted features from seven HRV data lengths to predict the onset of VF before nine different forecast times and observed the prediction accuracies. By using only five features, an artificial neural network classifier was trained and validated based on 10-fold cross-validation. Maximum prediction accuracies of 88.18% and 88.64% were observed at HRV data lengths of 10 and 20 s, respectively, at a forecast time of 0 s. The worst prediction accuracy was recorded at an HRV data length of 70 s and a forecast time of 80 s. Our results showed that features extracted from HRV signals near the VF onset could yield relatively high VF prediction accuracies.

Electroencephalogram Access for Emotion Recognition Based on a Deep Hybrid Network

In the human-computer interaction (HCI), electroencephalogram (EEG) access for automatic emotion recognition is an effective way for robot brains to perceive human behavior. In order to improve the accuracy of the emotion recognition, a method of EEG access for emotion recognition based on a deep hybrid network was proposed in this paper. Firstly, the collected EEG was decomposed into four frequency band signals, and the multiscale sample entropy (MSE) features of each frequency band were extracted. Secondly, the constructed 3D MSE feature matrices were fed into a deep hybrid network for autonomous learning. The deep hybrid network was composed of a continuous convolutional neural network (CNN) and hidden Markov models (HMMs). Lastly, HMMs trained with multiple observation sequences were used to replace the artificial neural network classifier in the CNN, and the emotion recognition task was completed by HMM classifiers. The proposed method was applied to the DEAP dataset for emotion recognition experiments, and the average accuracy could achieve 79.77% on arousal, 83.09% on valence, and 81.83% on dominance. Compared with the latest related methods, the accuracy was improved by 0.99% on valence and 14.58% on dominance, which verified the effectiveness of the proposed method.