Spiking Neural Networks Diagnosis of ADHD subtypes through EEG Signals Evaluation.

Attention-deficit hyperactivity disorder (ADHD) affects at least 5% of the world population and can disturb normal development causing serious issues in adulthood. Therefore, it is important to develop tools to help detecting ADHD so that treatment can start as soon as possible. Plus, the differentiation of ADHD in its subtypes is important to define the recommended treatment. Here we present original research to investigate the hypothesis of using a Spiking Neural Networks (SNN) EEG signals classifier for automated diagnostic of ADHD subtypes. This research used data from 243 patients and healthy volunteers acquired as part of the Healthy Brain Network. These resting state EEG signals were collected from 5-minutes scan with a 128 channel 500 Hz system. For benchmarking, we present a comparison of the SNN performance with a support vector machine, a k-nearest neighborhood, a random forest algorithm and a multi-layer perceptron. We present experiments for both the diagnostics of ADHD and for detecting which ADHD subtype the patient has. SNN presented a 72.00% accuracy for detecting ADHD surpassing all the other techniques by 9.1 % and 68% in detecting if the subject is a member of the Combined ADHD, Inattentive ADHD or control groups (18% better than the second-best technique). Clinical Relevance - This work has shown a resource that can be useful allied to other tools to help diagnosing ADHD and its subtypes.

Actor-Critic Reinforcement Learning Based Algorithm for Contaminant Minimization in sEMG Movement Recognition.

This paper aims to present an approach based on Reinforcement Learning (RL) concept to detect contaminants' type and minimize their effect on surface electromyography signal (sEMG) based movement recognition. The referred method was applied in the pre-processing stage of a sEMG based motion classification system using the Ninapro database 2 artificially contaminated with electrocardiography (ECG) interference, motion artifact (MOA), powerline interference (PLI) and additive white Gaussian noise (WGN). Support Vector Machine was the method for movement classification. The results showed an improvement of 8.9%, 16.7%, 15.9%, 16.5%, and 11.9% in the movement recognition accuracy with the application of the pre-processing algorithm to restore, respectively, one, three, six, nine, and 12 contaminated channels.

Actor-Critic Reinforcement Learning Based Algorithm for Contaminant Type Identification in Surface Electromyography Data.

This paper aims to present an innovative approach based on Reinforcement Learning (RL) concept to detect contaminants' type and minimize their effect on surface electromyography signal (sEMG). An agent-environment model was created based on the following elements: environment (muscle electrical activity), state (set of six features extracted from the signal), actions (application of filters/procedures to reduce the impact of each interference), and agent (controller, which will identify the type of contamination and take the appropriate action). The learning was conducted with Actor-Critic method. An average accuracy of 92.96% was achieved in an off-line experiment when detecting four contaminant types (electrocardiography (ECG) interference, movement artifact, power line interference, and additive white Gaussian noise).

Genetic Algorithm Application to Feature Selection in sEMG Movement Recognition with Regularized Extreme Learning Machine.

This paper presents a genetic algorithm (GA) feature selection strategy for sEMG hand-arm movement prediction. The proposed approach evaluates the best feature set for each channel independently. Regularized Extreme Learning Machine was used for the classification stage. The proposed procedure was tested and analyzed applying Ninapro database 2, exercise B. Eleven time domain and two frequency domain metrics were considered in the feature population, totalizing 156 combined feature/channel. As compared to previous studies, our results are promising - 87.7% accuracy was achieved with an average of 43 combined feature/channel selection.

Recurrent Neural Network for Contaminant Type Detector in Surface Electromyography Signals.

A surface Electromyography (sEMG) contaminant type detector has been developed by using a Recurrent Neural Network (RNN) with Long Short-Term (LSMT) units in its hidden layer. This setup may reduce the contamination detection processing time since there is no need for feature extraction so that the classification occurs directly from the sEMG signal. The publicly available NINAPro (Non-Invasive Adaptive Prosthetics) database sEMG signals was used to train and test the network. Signals were contaminated with White Gaussian Noise, Movement Artifact, ECG and Power Line Interference. Two out of the 40 healthy subjects' data were considered to train the network and the other 38 to test it. Twelve models were trained under a -20dB contamination, one for each channel. ANOVA results showed that the training channel could affect the classification accuracy if SNR = -20dB and 0dB. An overall accuracy of 97.72% has been achieved by one of the models.

Resilient EMG Classification to Enable Reliable Upper-Limb Movement Intent Detection.

Reliable control of assistive devices using surface electromyography (sEMG) remains an unsolved task due to the signal's stochastic behavior that prevents robust pattern recognition for real-time control. Non-representative samples lead to inherent class overlaps that generate classification ripples for which the most common alternatives rely on post-processing and sample discard methods that insert additional delays and often do not offer substantial improvements. In this paper, a resilient classification pipeline based on Extreme Learning Machines (ELM) was used to classify 17 different upper-limb movements through sEMG signals from a total of 99 trials derived from three different databases. The method was compared to a baseline ELM and a sample discarding (DISC) method and proved to generate more stable and consistent classifications. The average accuracy boost of ≈ 10% in all databases lead to average weighted accuracy rates higher as 53,4% for amputees and 89,0% for non-amputee volunteers. The results match or outperform related works even without sample discards.

Open Database for Accurate Upper-Limb Intent Detection Using Electromyography and Reliable Extreme Learning Machines.

Surface Electromyography (sEMG) signal processing has a disruptive technology potential to enable a natural human interface with artificial limbs and assistive devices. However, this biosignal real-time control interface still presents several restrictions such as control limitations due to a lack of reliable signal prediction and standards for signal processing among research groups. Our paper aims to present and validate our sEMG database through the signal classification performed by the reliable forms of our Extreme Learning Machines (ELM) classifiers, used to maintain a more consistent signal classification. To perform the signal processing, we explore the use of a stochastic filter based on the Antonyan Vardan Transform (AVT) in combination with two variations of our Reliable classifiers (denoted R-ELM and R-Regularized ELM (RELM), respectively), to derive a reliability metric from the system, which autonomously selects the most reliable samples for the signal classification. To validate and compare our database and classifiers with related papers, we performed the classification of the whole of Databases 1, 2, and 6 (DB1, DB2, and DB6) of the NINAProdatabase. Our database presented consistent results, while the reliable forms of ELM classifiers matched or outperformed related papers, reaching average accuracies higher than 99 % for the IEEdatabase, while average accuracies of 75 . 1 % , 79 . 77 % , and 69 . 83 % were achieved for NINAPro DB1, DB2, and DB6, respectively.

Recurrent Neural Network as Estimator for a Virtual sEMG Channel.

This study aims at estimating a virtual surface Electromyography (sEMG) channel through a Recurrent Neural Network (RNN) by using Long Short-Term Memory (LSTM) nodes. The virtual channel is used to classify hand postures from the publicly NinaPro database with a multi-class, one-against-all Support Vector Machine (SVM) using the Root Mean Square RMS of the sEMG signal as feature. The classification of the signals through the virtual channel was compared with uncontaminated data and data contaminated with noise saturation. The hit rate from the clean data has averaged 73.96% ± 3.02%. The classification from the contaminated data of one of the channels has improved from 9.29% ± 4.42% to 66.48% ± 6.11% with the virtual channel.

Smoothed arg max Extreme Learning Machine: An Alternative to Avoid Classification Ripple in sEMG Signals.

Despite all the recent developments of using the surface electromyography (sEMG) as a control signal, reliable classifications still remain an arduous task due to overlapping classes and classification ripples. In this paper, we present a straightforward approach to avoid classification ripple based on smoothing the arg max value of an Extreme Learning Machine (ELM) classifier. We compare the baseline accuracy of the classifier with an arg max filtered by a traditional Exponential Smoothing Filter (ESF) and our adaptation of Antonyan Vardan Transform (AVT). The classifiers were evaluated using sEMG data acquired through 12 channels from four subjects performing 17 different movements of forearm and fingers with three repetitions each. In the best scenario, our methods reached results higher than 96% and 82% of overall and weighted accuracy, respectively. Those results match or outperform similar papers of the literature using a simpler model, which may help the application of the techniques on embedded platforms and make the practical use of such devices more feasible.

An Automatic Cycling Performance Classifier System Based on the Crank Arm Force Measurement Data.

This paper describes the development of an automatic cycling performance measurement system with a Fuzzy Logic Controller (FLC), using Mamdani Inference method, to classify the performance of the cyclist. From data of the average power, its standard deviation and the effective force bilateral asymmetry index, a score that represents the cyclist performance is determined. Data are acquired using an experimental crank arm load cell force platform developed with built-in strain gages and conditioning circuit that measure the force that is applied to the bicycle pedal during cycling with a linearity error under 0.6%. A randomized block experiment design was performed with 15 cyclists of 29±5 years with a body mass of 73±9kg and a height of 1.78±0.07m. The average power reached by the subjects was 137.63±59.6W; the mean bilateral asymmetry index, considering all trials, was 67.01±6.23%. The volunteers cycling performance scores were then determined using the developed FLC; the mean score was 25.4% ± 16.9%. ANOVA showed that the subject causes significant variation on the performance score.

Using Antonyan Vardan Transform and Extreme Learning Machines for Accurate sEMG Signal Classification.

In this paper, we present an evaluation of an adaptation of the Antonyan Vardan Transform (AVT) used in combination with an Extreme Learning Machines (ELM) classifier to process surface electromyography (sEMG) data used to classify six finger movements and a rest state. A total of 12 assays formed by three repetitions performed by four volunteers is analyzed. Additionally, a sample-by-sample output label comparison was performed to make a more comprehensive analysis of the system which was tested on a PC and embedded on a Rasp.berry Pi platform. Compared to literature papers, our system was capable to match or outperform similar solutions even using a simpler model, reaching mean accuracy rates above 94.

Fault-Tolerant Sensor Detection of sEMG signals: Quality Analysis Using a Two-Class Support Vector Machine.

The capacity to identify the contamination in surface electromyography (sEMG) signals is necessary for applying the sEMG controlled prosthesis over time. In this paper, the method for the automatic identification of commonly occurring contaminant types in sEMG signals is evaluated. The presented approach uses two-class support vector machine (SVM) trained with clean sEMG and artificially contaminated sEMG. The contaminants considered include electrocardiogram interference, motion artefact, power line interference, amplifier saturation, and electrode displacement. The results demonstrated that the sEMG signal with the contaminants could readily be distinguished, even with increase channels degraded. The SFTD detection depends on the noise type, whether the amputee or non-amputee subjects and which channel is being analysed. This method presented a suitable solution for the detection of contaminants in the sEMG signal, being able to provide the acquired signal validation before the movement intended recognition to operate in an intelligent recognition with greater reliability.

Virtual Sensor of Surface Electromyography in a New Extensive Fault-Tolerant Classification System.

A few prosthetic control systems in the scientific literature obtain pattern recognition algorithms adapted to changes that occur in the myoelectric signal over time and, frequently, such systems are not natural and intuitive. These are some of the several challenges for myoelectric prostheses for everyday use. The concept of the virtual sensor, which has as its fundamental objective to estimate unavailable measures based on other available measures, is being used in other fields of research. The virtual sensor technique applied to surface electromyography can help to minimize these problems, typically related to the degradation of the myoelectric signal that usually leads to a decrease in the classification accuracy of the movements characterized by computational intelligent systems. This paper presents a virtual sensor in a new extensive fault-tolerant classification system to maintain the classification accuracy after the occurrence of the following contaminants: ECG interference, electrode displacement, movement artifacts, power line interference, and saturation. The Time-Varying Autoregressive Moving Average (TVARMA) and Time-Varying Kalman filter (TVK) models are compared to define the most robust model for the virtual sensor. Results of movement classification were presented comparing the usual classification techniques with the method of the degraded signal replacement and classifier retraining. The experimental results were evaluated for these five noise types in 16 surface electromyography (sEMG) channel degradation case studies. The proposed system without using classifier retraining techniques recovered of mean classification accuracy was of 4% to 38% for electrode displacement, movement artifacts, and saturation noise. The best mean classification considering all signal contaminants and channel combinations evaluated was the classification using the retraining method, replacing the degraded channel by the virtual sensor TVARMA model. This method recovered the classification accuracy after the degradations, reaching an average of 5.7% below the classification of the clean signal, that is the signal without the contaminants or the original signal. Moreover, the proposed intelligent technique minimizes the impact of the motion classification caused by signal contamination related to degrading events over time. There are improvements in the virtual sensor model and in the algorithm optimization that need further development to provide an increase the clinical application of myoelectric prostheses but already presents robust results to enable research with virtual sensors on biological signs with stochastic behavior.

Percepção da autoimagem corporal em dependentes de crack / Perception of body self-image in crackdependent people

Este estudo objetivou analisar a imagem corporal, a composição corporal e fatores associados em dependentes de crack internados. Trata-se de um estudo quantitativo com delineamento transversal composto por 100 sujeitos hospitalizados para desintoxicação. Para a coleta de dados foram utilizados como instrumentos: ficha de dados sociodemográficos; escala de Silhuetas e avaliação antropométrica. Observou- se Índice de Massa Corporal médio de 24,01 kg/m² (±3,65), distorção da imagem de -1,48 (±1,80), e insatisfação corporal de 2,13 (±2,85). A análise estatística mostrou diferença significativa entre a imagem da silhueta real e a imagem da silhueta atual dos sujeitos (χ2=153,25; p<0,001). Concluiu-se que existe diferença entre a imagem da silhueta que os indivíduos possuem de si mesmo, quando comparada com aquela que se equipara ao seu IMC, mais que isto ficou evidente a existência de insatisfação dos sujeitos quanto às suas silhuetas, assim como o desejo que seu tamanho corporal fosse aumentado.

Current qualitative study with transversal design analyzes body image, body composition and factors associated with 100 crackdependent people, hospitalized for de-intoxication. Data collection comprised: a card with social and demographic data; silhouette scales and anthropometric evaluation. Mean Body Mass Index was 24.01 kg/ m² (±3.65); image distortion -1.48 (±1.80) and body dissatisfaction 2.13 (±2.85). Statistical analysis revealed a significant difference between the image of true silhouette and the image of the subjects' current silhouette (χ2=153.25; p<0.001). Results show that differences exist between the silhouette image people have of themselves when compared to that equivalent to their BMI. The subjects were dissatisfied by their silhouette and desired that their body size would be increased.

sEMG feature selection and classification using SVM-RFE.

It is challenging to obtain good results for hand movements classification. Previous studies expended efforts on filters for sEMG data, feature extraction and classifier algorithms to achieve the best results. This paper proposes the insertion of a step in the classification process that selects which features to use in training aiming to increase accuracy and performance. Feature selection was previously used in other classification tasks but is new in wrist/fingers movements classification. Obtained results were positives as the performance gain is huge (39 to 53 features out of 144 are used for classification) and accuracy reach promising values (above 90% for some subjects).

Reever control: A biosignal controlled interface.

With the development of new technologies, new accessibility solutions have emerged to increase the inclusion of user with disabilities. This paper details the development of Reever Control, an interface based on inertial sensors and sEMG signal processing to control a cursor in a virtual environment. The metrics of time, number of false clicks and average absolute error were used to characterize the system and compare it with Camera Mouse, an image processing-based interface. The Reever Control showed improvements compared to uniaxial control, robustness to artifacts, support of right click and runtime compatible with Camera Mouse.

Using non-iterative methods and random weight networks to classify upper-limb movements through sEMG signals.

This paper presents the use of two non-iterative methods to perform the classification of 17 different upper-limb movements through sEMG signal processing. The two methods were compared with a SVM classifier using three different databases involving amputee subjects. The non-iterative methods presented equivalent or superior classification accuracy than SVM method. Thereafter a stage of PCA pre-processing method was used in order to promote a better class separation prior the non-iterative classifiers. The best accuracy result without PCA was achieved by the Regularized Extreme Learning Machines algorithm (88,4% for non-amputee subjects and 79,4% for the amputee). The PCA method used boosted the accuracy of the two non-iterative methods which the mean accuracy was 94% for the non-amputee subjects and 85% for the amputee subjects.

Psychiatric hospitalizations due to alcohol and drug consumption among young people in Ceará, Brazil

Introduction: This study aimed to analyze the evolution of psychiatric hospitalizations among children and adolescents due to psychoactive substance use in the public health system in the state of Ceará, Brazil. Hospitalizations between 2000 and 2015 were used as indicators. Methods: Ecological study using secondary data. Data analysis was performed with the software Stata 11.1® from StataCorp LLC (Texas/USA) using Poisson regression with robust variance and Spearman correlation. A 95% confidence interval was adopted and significance level was set at 5%. Results: The variables hospitalization rates and mean length of hospital stay did not vary significantly. There was no variation when data were stratified by sex. A negative correlation was found between hospitalization rates and mean length of hospital stay (P < 0.05) among girls, but not among boys or overall population. Conclusion: In Ceará, the creation of alternative mechanisms to hospital admission has not resulted in reduced hospitalization rates (AU)

Hospitalization due to drug use did not change after a decade of the Psychiatric Reform.

OBJECTIVE: To investigate whether the psychiatric hospitalization rates due to use of psychoactive substances and average time of hospitalization suffered any changes after the first decade of effective implementation of the psychiatric reform in Brazil. METHODS: This article examines the evolution of hospitalizations due to disorders arising from the use of alcohol or other substances in the state of Santa Catarina, Southern Brazil, from 2000 to 2012. This is an ecological, time-series study, which uses data from admissions obtained by the Informatics Service of the Brazilian Unified Health System. Hospitalization rates by 100,000 inhabitants and average time of occupancy of beds were estimated. Coefficients of variation of these rates were estimated by Poisson Regression. RESULTS: The total and male hospitalization rates did not vary (p = 0.056 and p = 0.244, respectively). We observed an increase of 3.0% for the female sex (p = 0.049). We did not observe any significant variation for occupancy time of beds. CONCLUSIONS: The deployment of services triggered by the Brazilian psychiatric reform was not accompanied by a reduction of hospitalization rates or mean occupancy time of hospitalized patients during this first decade of implementation of the reform.

Padrão de uso e possibilidade de cessação do consumo do crack: estudo transversal / Patterns of crack cocaine use and probability of cessation: a cross-sectional study

O objetivo desta pesquisa foi analisar a relação entre o padrão de consumo de crack nos últimos seis meses de uso ativo e a condição de abstinência ou não no momento das entrevistas. Trata-se de um estudo transversal com amostragem de conveniência, sendo que foram entrevistadas 495 pessoas entre os 14 e os 54 anos de idade. Foram estimadas razões de prevalência por Regressão de Poisson robusta para a condição abstinente por 12 semanas ou mais, segundo os padrões de consumo referidos, ajustando para sexo, idade, escolaridade, tempo desde o primeiro contato com a droga, uso de medicação e hospitalização em função do crack. Identificou-se associação entre o uso frequente e pesado e a cessação do consumo (RP 1,06 [IC95%: 1,01 - 1,12] p = 0,019). Esse achado amplia o leque de particularidades em relação ao crack e reforça os investimentos terapêuticos para todos os padrões de consumo.

This study aimed to analyze the relationship between the patterns of crack cocaine use among active users over the past six months and abstinence (or not) at the time of the interviews. A cross-sectional study was conducted in a convenience sample of 495 crack users aged 14 to 54 years. Prevalence ratios of the variable abstinent for at least 12 weeks were estimated using Poisson regression with robust variance according to the patterns of use, adjusting for sex, age, education, time since first contact trying crack cocaine, and treatments and hospitalization associated with crack use. There was an association between regular and heavy use and cessation of drug use (PR 1.06 [95% CI: 1.01 to 1.12] p = 0.019). This finding expands the range of particularities regarding the use of crack and reinforces the need for investments in crack cocaine addiction treatments for all use patterns.