Figure 10 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
The increase in life expectancy, according to the World Health Organization, is a fact, and with it rises the incidence of age-related neurodegenerative diseases. The most recurrent symptoms are those associated with tremors resulting from Parkinson’s disease (PD) or essential tremors (ETs). The main alternatives for the treatment of these patients...
Citations
... Uma alternativa adotada para mitigar os tremores nas mãos é a utilização de dispositivos eletrônicos que empregam algoritmos adaptativos. Esses dispositivos recebem um sinal de entrada e geram um sinal de saída que neutraliza os tremores, permitindo que o indivíduo realize suas atividades com maior eficácia e conforto [8][9][10]. ...
... O estudo de [13] descreveu um dispositivo não invasivo para redução de tremores em pacientes com Parkinson, utilizando sensor de movimento, microcontrolador com controle fuzzy PI e dois atuadores. Simulações com dados reais de pacientes indicaram que o dispositivo pode atenuar até 75% dos tremores no eixo Z e até 35% no eixo X. Por sua vez, o estudo realizado por [9] abordou o emprego de algoritmos adaptativos para controlar tremores nas mãos, empregando o Fx-LMS, Fx-NLMS e Fx-NLMS&LMS em simulações com sinais de tremores simulados no MATLAB, demonstrando a eficácia dos algoritmos. O Fx-NLMS&LMS se destacou por sua rápida convergência em tremores fisiológicos (cerca de 4000 amostras), enquanto o Fsinx-LMS foi mais eficaz em tremores patológicos. ...
... Nesta seção serão apresentadas as configurações utilizadas para realizar as simulações e validar o funcionamento de cada um dos algoritmos adaptativos abordados. Com base na pesquisa conduzida em [9], optou-se pela seleção dos algoritmos Fx-LMS, Fx-NLM e Fx-NLMS&LMS para simulação, uma vez que foi demonstrada a eficácia desses algoritmos adaptativos na atenuação dos tremores das mãos. No estudo mencionado, foram empregados sinais de tremores sintéticos gerados a partir de modelos matemáticos. ...
In this research, we provide a detailed analysis of five adaptivealgorithms to attenuate hand tremors during writing. The evaluatedalgorithms included Filtered Least Mean Squared (Fx-LMS),Filtered Normalized LMS (Fx-NLMS), Hybrid Fx-LMS&NLMS, RecursiveLeast Squares (RLS), and Kalman Filter. We have conductedsimulations to assess the performance of these algorithms usingthe NewHandPD dataset, which contains hand tremor signals from31 patients. Our results show that the mean squared error (MSE)values of -38 dB for Fx-LMS, -42 dB for Fx-NLMS, -44 dB for Fx-LMSand NLMS, -53 dB for RLS, and -50 dB for the Kalman Filter. RLShad the lowest MSE and superior adaptation. On the other hand,the Kalman Filter demonstrated faster convergence to the steadystate, which is six times faster than RLS.
... The mean square error (MSE) measures the average square difference between the actual and predicted values. A smaller MSE indicates a better fit of the model to the data [32]. On the provided results for both the training and testing data, it can be observed that the model for warm conditions achieves lower MSE values, indicating a better fit to the data in terms of this parameter. ...
... The mean square error (MSE) measures the average square difference bet actual and predicted values. A smaller MSE indicates a better fit of the model to [32]. On the provided results for both the training and testing data, it can be obse the model for warm conditions achieves lower MSE values, indicating a better data in terms of this parameter. ...
This paper presents the process of creating a model for electric vehicle (EV) energy consumption , enabling the rapid generation of results and the creation of energy maps. The most robust validation indicators were exhibited by an artificial intelligence method, specifically neural networks. Within this framework, two predictive models for EV energy consumption were developed for winter and summer conditions, based on actual driving cycles. These models hold particular significance for microscale road analyses. The resultant model, for test data in summer conditions, demonstrates validation indicators of an R 2 of 86% and an MSE of 1.4, while, for winter conditions, its values are 89% and 2.8, respectively, confirming its high precision. The paper also presents exemplary applications of the developed models, utilizing both real and simulated microscale data. The results obtained and the presented methodology can be especially advantageous for decision makers in the management of city roads and infrastructure planners, aiding both cognitive understanding and the better planning of charging infrastructure networks.
... The mean square error (MSE) measures the average square difference between actual and predicted values. A smaller MSE indicates a better fit of the model to the data [15]. On the provided results for both training and testing data, it can be observed that the model for warm conditions achieves lower MSE values, indicating a better fit to the data in terms of this parameter. ...
The paper outlines a methodology for developing a model to estimate energy consumption in electric vehicles (EVs). The most robust validation indicators were exhibited by an artificial in-telligence method, specifically neural networks. Within this framework, two predictive models for EV energy consumption were developed for winter and summer conditions, based on actual driving cycles. Such models hold particular significance for microscale road analyses. The resultant model for test data in summer conditions demonstrates validation indicators with an R2 of 86% and an MSE of 1.4, while for winter conditions, the values are 89% and 2.8, respectively, confirming its high precision. The paper also presents exemplary applications of the developed models, utilizing both real and simulated microscale data. The results obtained and the presented methodology can be especially advantageous for decision-makers in city road management and infrastructure planners, aiding both cognitive understanding and better planning of charging infrastructure networks.
Tremor is a prevalent neurological disorder that affects individuals of almost all ages and can significantly impede their quality of life and occupational functioning. Wearable medical devices for suppressing tremors, typically low-frequency vibrations ranging between 3 and 12 Hz, are gaining popularity since active vibration absorbers integrated into such devices have demonstrated immediate efficacy and noninvasive nature. However, there are challenges in miniaturizing active absorbers for wearable applications with traditional actuators. To address this problem, here we present a light wearable active finger tremor-suppressing orthosis (AFTO) that consists of a stacked polyvinyl chloride (PVC) gel actuator-based absorber, an inertial measurement unit (IMU), and a force sensor. The integrated sensors allow the device to detect tremors and trigger the absorber to suppress vibrations, regardless of whether the fingertip is vibrating in the air or applying tremor force while in contact with an object. A 3D-printed compliant Sarrus-mechanism exoskeleton was used to house the PVC gel stacked actuator, thus minimizing the linear actuator's swaying while maximizing the effective actuation area. This innovative wearable finger tremor absorption system has the potential for various applications in daily life and occupational contexts, such as stabilizing the finger during grasping, typing, operating surgical instruments, drawing, and other tasks.
