RESUMO

Stroke is a neurological condition that usually results in the loss of voluntary control of body movements, making it difficult for individuals to perform activities of daily living (ADLs). Brain-computer interfaces (BCIs) integrated into robotic systems, such as motorized mini exercise bikes (MMEBs), have been demonstrated to be suitable for restoring gait-related functions. However, kinematic estimation of continuous motion in BCI systems based on electroencephalography (EEG) remains a challenge for the scientific community. This study proposes a comparative analysis to evaluate two artificial neural network (ANN)-based decoders to estimate three lower-limb kinematic parameters: x- and y-axis position of the ankle and knee joint angle during pedaling tasks. Long short-term memory (LSTM) was used as a recurrent neural network (RNN), which reached Pearson correlation coefficient (PCC) scores close to 0.58 by reconstructing kinematic parameters from the EEG features on the delta band using a time window of 250 ms. These estimates were evaluated through kinematic variance analysis, where our proposed algorithm showed promising results for identifying pedaling and rest periods, which could increase the usability of classification tasks. Additionally, negative linear correlations were found between pedaling speed and decoder performance, thereby indicating that kinematic parameters between slower speeds may be easier to estimate. The results allow concluding that the use of deep learning (DL)-based methods is feasible for the estimation of lower-limb kinematic parameters during pedaling tasks using EEG signals. This study opens new possibilities for implementing controllers most robust for MMEBs and BCIs based on continuous decoding, which may allow for maximizing the degrees of freedom and personalized rehabilitation.

RESUMO

This work addresses the challenge of classifying multiclass visual EEG signals into 40 classes for brain-computer interface applications using deep learning architectures. The visual multiclass classification approach offers BCI applications a significant advantage since it allows the supervision of more than one BCI interaction, considering that each class label supervises a BCI task. However, because of the nonlinearity and nonstationarity of EEG signals, using multiclass classification based on EEG features remains a significant challenge for BCI systems. In the present work, mutual information-based discriminant channel selection and minimum-norm estimate algorithms were implemented to select discriminant channels and enhance the EEG data. Hence, deep EEGNet and convolutional recurrent neural networks were separately implemented to classify the EEG data for image visualization into 40 labels. Using the k-fold cross-validation approach, average classification accuracies of 94.8% and 89.8% were obtained by implementing the aforementioned network architectures. The satisfactory results obtained with this method offer a new implementation opportunity for multitask embedded BCI applications utilizing a reduced number of both channels (<50%) and network parameters (<110 K).

Assuntos

RESUMO

Objective: The Visual Short-Term Memory Binding (VSTMB) Test is a useful tool in the assessment of Alzheimer's disease (AD). Research has suggested that short-term memory binding is insensitive to the sociocultural characteristics of the assessed individuals. Such earlier studies addressed this influence by considering years of education. The current study aims to determine the influence of sociocultural factors via a measure of Socioeconomic Status (SES) which provides a more holistic approach to these common confounders. Methods: A sample of 126 older adults, both with (n = 59) and without (n = 67) amnestic mild cognitive impairment (aMCI), underwent assessment using a neuropsychological protocol including VSTMB test. All participants were classified as either high SES or low SES, employing the Standard Demographic Classification from the European Society for Opinion and Marketing Research. Results: ANOVA/ANCOVA models confirmed that performance of healthy and aMCI participants on traditional neuropsychological tests were sensitive to SES whereas the VSTMB Test was not. The results add to the growing array of evidence suggesting that there are cognitive abilities which are unaffected by socioeconomic factors, regardless of clinical condition. Conclusions: The lack of sensitivity to sociocultural factors previously reported for the VSTMB test is accompanied by a lack of sensitivity to socioeconomic factors thus broadening the scope of this test to aid in the detection of dementia across populations with different backgrounds. Future studies should take these findings forward and explore the potential influences of AD biomarkers (A/T/N) on the association between cognitive functions and demographic variables.

RESUMO

Different tests measure text comprehension, including the cloze gap-filling test, often used for language learning. Different studies hypothesized cognitive strategies in this type of test and their relationship with working memory and performance. However, no study investigated the cloze test, working memory, and possible cognitive strategies, while performing the test. Therefore, this study aimed to identify cognitive visual strategies in the cloze test by applying an unsupervised algorithm and to analyze the relationship between these strategies with working memory and performance in the cloze test. Our sample consisted of 51 university students, the largest sample in studies of cognitive strategies with cloze tests. Participants answered an 11-item cloze test in a computer with eye-tracking, a verbal working memory test, and a visuospatial working memory test. Our analysis of participants' scanpath identified two main strategies: one with fewer toggles between text and word bank and fewer fixations than the other one, indicating the existence of a global strategy. Furthermore, a model predicting the efficiency of participants in the cloze test found that item complexity, using a global strategy, and higher scores of working memory were the most significant predictors. These results confirm the hypothesis of a global strategy being related to successfully achieving higher-order reading processes.

Assuntos

RESUMO

India's commercial advancement and development depend heavily on agriculture. A common fruit grown in tropical settings is citrus. A professional judgment is required while analyzing an illness because different diseases have slight variati ons in their symptoms. In order to recognize and classify diseases in citrus fruits and leaves, a customized CNN - based approach that links CNN with LSTM was developed in this research. By using a CNN - based method, it is possible to automatically differenti ate from healthier fruits and leaves and those that have diseases such fruit blight, fruit greening, fruit scab, and melanoses. In terms of performance, the proposed approach achieves 96% accuracy, 98% sensitivity, 96% Recall, and an F1 - score of 92% for ci trus fruit and leave identification and classification and the proposed method was compared with KNN, SVM, and CNN and concluded that the proposed CNN - based model is more accurate and effective at identifying illnesses in citrus fruits and leaves.

El avance y desarrollo comercial de India dependen en gran medida de la agricultura. Un tipo de fruta comunmente cultivada en en tornos tropicales es el cítrico. Se requiere un juicio profesional al analizar una enfermedad porque diferentes enfermedades tienen ligeras variaciones en sus síntomas. Para reconocer y clasificar enfermedades en frutas y hojas de cítricos, se desarrolló e n esta investigación un enfoque personalizado basado en CNN que vincula CNN con LSTM. Al utilizar un método basado en CNN, es posible diferenciar automáticamente entre frutas y hojas más saludables y aquellas que tienen enfermedades como la plaga de frutas , el verdor de frutas, la sarna de frutas y las melanosis. En términos de desempeño, el enfoque propuesto alcanza una precisión del 96%, una sensibilidad del 98%, una recuperación del 96% y una puntuación F1 del 92% para la identificación y clasificación d e frutas y hojas de cítricos, y el método propuesto se comparó con KNN, SVM y CNN y se concluyó que el modelo basado en CNN propuesto es más preciso y efectivo para identificar enfermedades en frutas y hojas de cítricos.

Assuntos

RESUMO

Photovoltaic (PV) power prediction plays a critical role amid the accelerating adoption of renewable energy sources. This paper introduces a bidirectional long short-term memory (BiLSTM) deep learning (DL) model designed for forecasting photovoltaic power one hour ahead. The dataset under examination originates from a small PV installation located at the Polytechnic School of the University of Alcala. To improve the quality of historical data and optimize model performance, a robust data preprocessing algorithm is implemented. The BiLSTM model is synergistically combined with a Bayesian optimization algorithm (BOA) to fine-tune its primary hyperparameters, thereby enhancing its predictive efficacy. The performance of the proposed model is evaluated across diverse meteorological and seasonal conditions. In deterministic forecasting, the findings indicate its superiority over alternative models employed in this research domain, specifically a multilayer perceptron (MLP) neural network model and a random forest (RF) ensemble model. Compared with the MLP and RF reference models, the proposed model achieves reductions in the normalized mean absolute error (nMAE) of 75.03% and 77.01%, respectively, demonstrating its effectiveness in this type of prediction. Moreover, interval prediction utilizing the bootstrap resampling method is conducted, with the acquired prediction intervals carefully adjusted to meet the desired confidence levels, thereby enhancing the robustness and flexibility of the predictions.

RESUMO

ABSTRACT Purpose To address the need for a standardized assessment tool for assessing cognitive-communication abilities among Indian preschoolers, the current study aimed at describing a Delphi based development and validation process for developing one such tool. The objectives of the research were to conceptualize and construct the tool, validate its content, and assess its feasibility through pilot testing. Methods The study followed a Delphi approach to develop and validate the tool across four phases i.e. conceptualization; construction; content validation; and pilot testing. The first three phases were performed with a panel of six experts including speech-language pathologists and preschool teachers while the pilot testing was done with 20 typically developing preschoolers. A literature review was also conducted with the Delphi rounds to support the developmental process. Results The first two rounds of the Delphi aided in the construction of a culturally and linguistically suitable story-based cognitive-communication assessment tool with the memory (free recall, recognition, and literary recall) and executive function (reasoning, inhibition, and switching) related tasks relevant for preschoolers. The content validation of the tool was continued with the experts till the revisions were satisfactory and yielded an optimum Content Validity Index. The pilot test of the finalized version confirmed its feasibility and appropriateness to assess developmental changes in the cognitive-communication abilities of preschoolers. Conclusion The study describes the Delphi-based conceptualization, construction, content validation, and feasibility check of a tool to assess cognitive-communication skills in preschool children.

RESUMO

Melatonin is a hormone secreted by the pineal gland, it can be associated with circadian rhythms, aging and neuroprotection. Melatonin levels are decreased in sporadic Alzheimer's disease (sAD) patients, which suggests a relationship between the melatonergic system and sAD. Melatonin may reduce inflammation, oxidative stress, TAU protein hyperphosphorylation, and the formation of ß-amyloid (Aß) aggregates. Therefore, the objective of this work was to investigate the impact of treatment with 10 mg/kg of melatonin (i.p) in the animal model of sAD induced by the intracerebroventricular (ICV) infusion of 3 mg/kg of streptozotocin (STZ). ICV-STZ causes changes in the brain of rats similar to those found in patients with sAD. These changes include; progressive memory decline, the formation of neurofibrillary tangles, senile plaques, disturbances in glucose metabolism, insulin resistance and even reactive astrogliosis characterized by the upregulation of glucose levels and glial fibrillary acidic protein (GFAP). The results show that ICV-STZ caused short-term spatial memory impairment in rats after 30 days of STZ infusion without locomotor impairment which was evaluated on day 27 post-injury. Furthermore, we observed that a prolonged 30-day treatment with melatonin can improve the cognitive impairment of animals in the Y-maze test, but not in the object location test. Finally, we demonstrated that animals receiving ICV-STZ have high levels of Aß and GFAP in the hippocampus and that treatment with melatonin reduces Aß levels but does not reduce GFAP levels, concluding that melatonin may be useful to control the progression of amyloid pathology in the brain.

RESUMO

Insulators installed outdoors are vulnerable to the accumulation of contaminants on their surface, which raise their conductivity and increase leakage current until a flashover occurs. To improve the reliability of the electrical power system, it is possible to evaluate the development of the fault in relation to the increase in leakage current and thus predict whether a shutdown may occur. This paper proposes the use of empirical wavelet transform (EWT) to reduce the influence of non-representative variations and combines the attention mechanism with a long short-term memory (LSTM) recurrent network for prediction. The Optuna framework has been applied for hyperparameter optimization, resulting in a method called optimized EWT-Seq2Seq-LSTM with attention. The proposed model had a 10.17% lower mean square error (MSE) than the standard LSTM and a 5.36% lower MSE than the model without optimization, showing that the attention mechanism and hyperparameter optimization is a promising strategy.

RESUMO

The use of models capable of forecasting the production of photovoltaic (PV) energy is essential to guarantee the best possible integration of this energy source into traditional distribution grids. Long Short-Term Memory networks (LSTMs) are commonly used for this purpose, but their use may not be the better option due to their great computational complexity and slower inference and training time. Thus, in this work, we seek to evaluate the use of neural networks MLPs (Multilayer Perceptron), Recurrent Neural Networks (RNNs), and LSTMs, for the forecast of 5 min of photovoltaic energy production. Each iteration of the predictions uses the last 120 min of data collected from the PV system (power, irradiation, and PV cell temperature), measured from 2019 to mid-2022 in Maceió (Brazil). In addition, Bayesian hyperparameters optimization was used to obtain the best of each model and compare them on an equal footing. Results showed that the MLP performs satisfactorily, requiring much less time to train and forecast, indicating that they can be a better option when dealing with a very short-term forecast in specific contexts, for example, in systems with little computational resources.

RESUMO

An electric power distribution utility is responsible for providing energy to consumers in a continuous and stable way. Failures in the electrical power system reduce the reliability indexes of the grid, directly harming its performance. For this reason, there is a need for failure prediction to reestablish power in the shortest possible time. Considering an evaluation of the number of failures over time, this paper proposes performing failure prediction during the first year of the pandemic in Brazil (2020) to verify the feasibility of using time series forecasting models for fault prediction. The long short-term memory (LSTM) model will be evaluated to obtain a forecast result that an electric power utility can use to organize maintenance teams. The wavelet transform has shown itself to be promising in improving the predictive ability of LSTM, making the wavelet LSTM model suitable for the study at hand. The assessments show that the proposed approach has better results regarding the error in prediction and has robustness when statistical analysis is performed.

Assuntos

RESUMO

The vertebrates' scaffold proteins of the Dlg-MAGUK family are involved in the recruitment, clustering, and anchoring of glutamate receptors to the postsynaptic density, particularly the NMDA subtype glutamate-receptors (NRs), necessary for long-term memory and LTP. In Drosophila, the only gene of the subfamily generates two main products, dlgA, broadly expressed, and dlgS97, restricted to the nervous system. In the Drosophila brain, NRs are expressed in the adult brain and are involved in memory, however, the role of Dlg in these processes and its relationship with NRs has been scarcely explored. Here, we show that the dlg mutants display defects in short-term memory in the olfactory associative-learning paradigm. These defects are dependent on the presence of DlgS97 in the Mushroom Body (MB) synapses. Moreover, Dlg is immunoprecipitated with NRs in the adult brain. Dlg is also expressed in the larval neuromuscular junction (NMJ) pre and post-synaptically and is important for development and synaptic function, however, NR is absent in this synapse. Despite that, we found changes in the short-term plasticity paradigms in dlg mutant larval NMJ. Together our results show that larval NMJ and the adult brain relies on Dlg for short-term memory/plasticity, but the mechanisms differ in the two types of synapses.

Assuntos

RESUMO

Epilepsy is the most common neurological condition worldwide and is largely associated with memory impairment, both in human as well as animal models. Furthermore, differences in seizure onset and severity have already been observed between the sexes. The induction of epilepsy through multiple systemic injections of pentylenetetrazole (PTZ), a protocol known as chemical kindling, is a well-established tool for studies regarding epileptogenesis, as well as the efficacy of antiseizure medication. The aim of this study was to compare possible sex-related differences in seizure severity, memory, neuronal damage as well as the effects of the estrous cycle on seizure severity. Male (n = 10) and Female (n = 11) animals received 30 mg/kg i.p. injections three days a week for 6 weeks and, after the last application, were tested for short and long-term memory. Control, Male (n = 8) and Female (n = 5) groups did not receive PTZ injections. Although PTZ did not promote important changes into the estrous cycle phases throughout the entire experiment, female animals presented lower seizure scores but had both short and long-term memory impairments associated with cell loss in the hippocampus and anterior cingulate area. Male rats presented higher seizure scores associated with pronounced cell loss, but only long-term memory deficits. Our results demonstrate that the PTZ kindling protocol results in higher seizure scores with increased vulnerability in male rats, but female rats displayed more intense memory deficits.

Assuntos

RESUMO

Growing evidence indicates that brain carbonic anhydrases (CAs) are key modulators in cognition, particularly in recognition and aversive memories. Here we described a role for these enzymes also in social recognition memory (SRM), defined as the ability to identify and recognize a conspecific, a process that is of paramount importance in gregarious species, such as rodents and humans. Male adult Wistar rats were submitted to a social discrimination task and, immediately after the sample phase, received bilateral infusions of vehicle, the CAs activator D-phenylalanine (D-Phen, 50 nmols/side), the CAs inhibitor acetazolamide (ACTZ; 10 nmols/side) or the combination of D-Phen and ACTZ directly in the CA1 region of the dorsal hippocampus or in the medial prefrontal cortex (mPFC). Animals were tested 30 min (short-term memory) or 24 h later (long-term memory). We found that inhibition of CAs with infusion of ACTZ either in the CA1 or in the mPFC impaired short-term SRM and that this effect was completely abolished by the combined infusion of D-Phen and ACTZ. We also found that activation of CAs with D-Phen facilitated the consolidation of long-term SRM in the mPFC but not in CA1. Finally, we show that activation of CAs in CA1 and in the mPFC enhances the persistence of SRM for up to 7 days. In both cases, the co-infusion of ACTZ fully prevented D-Phen-induced procognitive effects. These results suggest that CAs are key modulators of SRM and unveil a differential involvement of these enzymes in the mPFC and CA1 on memory consolidation.

Assuntos

RESUMO

Objective.To propose novel SSVEP classification methodologies using deep neural networks (DNNs) and improve performances in single-channel and user-independent brain-computer interfaces (BCIs) with small data lengths.Approach.We propose the utilization of filter banks (creating sub-band components of the EEG signal) in conjunction with DNNs. In this context, we created three different models: a recurrent neural network (FBRNN) analyzing the time domain, a 2D convolutional neural network (FBCNN-2D) processing complex spectrum features and a 3D convolutional neural network (FBCNN-3D) analyzing complex spectrograms, which we introduce in this study as possible input for SSVEP classification. We tested our neural networks on three open datasets and conceived them so as not to require calibration from the final user, simulating a user-independent BCI.Results.The DNNs with the filter banks surpassed the accuracy of similar networks without this preprocessing step by considerable margins, and they outperformed common SSVEP classification methods (SVM and FBCCA) by even higher margins.Conclusion and significance.Filter banks allow different types of deep neural networks to more efficiently analyze the harmonic components of SSVEP. Complex spectrograms carry more information than complex spectrum features and the magnitude spectrum, allowing the FBCNN-3D to surpass the other CNNs. The performances obtained in the challenging classification problems indicates a strong potential for the construction of portable, economical, fast and low-latency BCIs.

Assuntos

RESUMO

Self-regulation is a widely studied construct, generally assumed to be cognitively supported by executive functions (EFs). There is a lack of clarity and consensus over the roles of specific components of EFs in self-regulation. The current study examines the relations between performance on (a) a self-regulation task (Heads, Toes, Knees Shoulders Task) and (b) two EF tasks (Knox Cube and Beads Tasks) that measure different components of updating: working memory and short-term memory, respectively. We compared 107 8- to 13-year-old children (64 females) across demographically-diverse populations in four low and middle-income countries, including: Tanna, Vanuatu; Keningau, Malaysia; Saltpond, Ghana; and Natal, Brazil. The communities we studied vary in market integration/urbanicity as well as level of access, structure, and quality of schooling. We found that performance on the visuospatial working memory task (Knox Cube) and the visuospatial short-term memory task (Beads) are each independently associated with performance on the self-regulation task, even when controlling for schooling and location effects. These effects were robust across demographically-diverse populations of children in low-and middle-income countries. We conclude that this study found evidence supporting visuospatial working memory and visuospatial short-term memory as distinct cognitive processes which each support the development of self-regulation.

Assuntos

RESUMO

Astrocytes release gliotransmitters via connexin 43 (Cx43) hemichannels into neighboring synapses, which can modulate synaptic activity and are necessary for fear memory consolidation. However, the gliotransmitters released, and their mechanisms of action remain elusive. Here, we report that fear conditioning training elevated Cx43 hemichannel activity in astrocytes from the basolateral amygdala (BLA). The selective blockade of Cx43 hemichannels by microinfusion of TAT-Cx43L2 peptide into the BLA induced memory deficits 1 and 24 h after training, without affecting learning. The memory impairments were prevented by the co-injection of glutamate and D-serine, but not by the injection of either alone, suggesting a role for NMDA receptors (NMDAR). The incubation with TAT-Cx43L2 decreased NMDAR-mediated currents in BLA slices, effect that was also prevented by the addition of glutamate and D-serine. NMDARs in primary neuronal cultures were unaffected by TAT-Cx43L2, ruling out direct effects of the peptide on NMDARs. Finally, we show that D-serine permeates through purified Cx43 hemichannels reconstituted in liposomes. We propose that the release of glutamate and D-serine from astrocytes through Cx43 hemichannels is necessary for the activation of post-synaptic NMDARs during training, to allow for the formation of short-term and subsequent long-term memory, but not for learning per se.

Assuntos

RESUMO

Electroencephalography (EEG) is a technique that can be used in non-invasive brain-machine interface (BMI) systems to register brain electrical activity. The EEG signals are non-linear and non-stationary, making the decoding procedure a complex task. Deep learning techniques have been successfully applied in several research fields, often improving the results compared with traditional approaches. Therefore, it is believed that these techniques can also improve the process of decoding brain signals in BMI systems. In this work, we present the implementation of two deep learning-based decoders and we compared the results with other state of art deep learning methods. The first decoder uses long short-term memory (LSTM) recurrent neural network and the second, entitled EEGNet-LSTM, combines a well-known neural decoder based on convolutional neural networks, called EEGNet, with some LSTM layers. The decoders have been tested using data set 2a from BCI Competition IV, and the results showed that the EEGNet-LSTM decoder has been approximately 23% better than the competition-winning decoder. A Wilcoxon t-test showed a significant difference between the two decoders (Z = 2.524, p = 0.012). The LSTM-based decoder has been approximately 9% higher than the best decoder from the same competition. However, there was no significant difference (Z = 1.540, p = 0.123). In order to verify the replication of the EEGNet-LSTM decoder on another data, we performed a test with PhysioNet's Physiobank EEG Motor Movement/Imagery dataset. The EEGNet-LSTM presented a higher performance (0.85 accuracy) than the EEGNet (0.82 accuracy). The results of this work can be important for the development of new research, as well as EEG-based BMI systems, which can benefit from the high precision of neural decoders.

RESUMO

Serial dependence is the effect in which the immediately preceding trial influences participants' responses to the current stimulus. But for how long does this bias last in the absence of interference from other stimuli? Here, we had 20 healthy young adult participants (12 women) perform a coincident timing task using different inter-trial intervals to characterize the serial dependence effect as the time between trials increases. Our results show that serial dependence abruptly decreases from 0.1 s to 1 s inter-trial interval, but it remains pronounced after that for up to 8 s. In addition, participants' response variability slightly decreases over longer intervals. We discuss these results in light of recent models suggesting that serial dependence might rely on a short-term memory trace kept through changes in synaptic weights, which might explain its long duration and apparent stability over time.

Assuntos

RESUMO

In this paper, Transfer Learning is used in LSTM networks to forecast new COVID cases and deaths. Models trained in data from early COVID infected countries like Italy and the United States are used to forecast the spread in other countries. Single and multistep forecasting is performed from these models. The results from these models are tested with data from Germany, France, Brazil, India, and Nepal to check the validity of the method. The obtained forecasts are promising and can be helpful for policymakers coping with the threats of COVID-19.

Assuntos