Embedded Machine Learning System for Muscle Patterns Detection in a Patient with Shoulder Disarticulation.

The integration of artificial intelligence (AI) models in the classification of electromyographic (EMG) signals represents a significant advancement in the design of control systems for prostheses. This study explores the development of a portable system that classifies the electrical activity of three shoulder muscles in real time for actuator control, marking a milestone in the autonomy of prosthetic devices. Utilizing low-power microcontrollers, the system ensures continuous EMG signal recording, enhancing user mobility. Focusing on a case study-a 42-year-old man with left shoulder disarticulation-EMG activity was recorded over two days using a specifically designed electronic board. Data processing was performed using the Edge Impulse platform, renowned for its effectiveness in implementing AI on edge devices. The first day was dedicated to a training session with 150 repetitions spread across 30 trials and three different movements. Based on these data, the second day tested the AI model's ability to classify EMG signals in new movement executions in real time. The results demonstrate the potential of portable AI-based systems for prosthetic control, offering accurate and swift EMG signal classification that enhances prosthetic user functionality and experience. This study not only underscores the feasibility of real-time EMG signal classification but also paves the way for future research on practical applications and improvements in the quality of life for prosthetic users.

Quantitative EEG analysis in typical absence seizures: unveiling spectral dynamics and entropy patterns.

A typical absence seizure is a generalized epileptic event characterized by a sudden, brief alteration of consciousness that serves as a hallmark for various generalized epilepsy syndromes. Distinguishing between similar interictal and ictal electroencephalographic (EEG) epileptiform patterns poses a challenge. However, quantitative EEG, particularly spectral analysis focused on EEG rhythms, shows potential for differentiation. This study was designed to investigate discernible differences in EEG spectral dynamics and entropy patterns during the pre-ictal and post-ictal periods compared to the interictal state. We analyzed 20 EEG ictal patterns from 11 patients with confirmed typical absence seizures, and assessed recordings made during the pre-ictal, post-ictal, and interictal intervals. Power spectral density (PSD) was used for the quantitative analysis that focused on the delta, theta, alpha, and beta bands. In addition, we measured EEG signal regularity using approximate (ApEn) and multi-scale sample entropy (MSE). Findings demonstrate a significant increase in delta and theta power in the pre-ictal and post-ictal intervals compared to the interictal interval, especially in the posterior brain region. We also observed a notable decrease in entropy in the pre-ictal and post-ictal intervals, with a more pronounced effect in anterior brain regions. These results provide valuable information that can potentially aid in differentiating epileptiform patterns in typical absence seizures. The implications of our findings are promising for precision medicine approaches to epilepsy diagnoses and patient management. In conclusion, our quantitative analysis of EEG data suggests that PSD and entropy measures hold promise as potential biomarkers for distinguishing ictal from interictal epileptiform patterns in patients with confirmed or suspected typical absence seizures.

Type 1 diabetes affects the brain functional connectivity underlying working memory processing.

Visuospatial working memory (VSWM) deficits have been demonstrated to occur during the development of type-1-diabetes (T1D). Despite confirming the early appearance of distinct task-related brain activation patterns in T1D patients compared to healthy controls, the effect of VSWM load on functional brain connectivity during task performance is still unknown. Using electroencephalographic methods, the present study evaluated this topic in clinically well-controlled T1D young patients and healthy individuals, while they performed a VSWM task with different memory load levels during two main VSWM processing phases: encoding and maintenance. The results showed a significantly lower number of correct responses and longer reaction times in T1D while performing the task. Besides, higher and progressively increasing functional connectivity indices were found for T1D patients in response to cumulative degrees of VSWM load, from the beginning of the VSWM encoding phase, without notably affecting the VSWM maintenance phase. In contrast, healthy controls managed to solve the task, showing lower functional brain connectivity during the initial VSWM processing steps with more gradual task-related adjustments. Present results suggest that T1D patients anticipate high VSWM load demands by early recruiting supplementary processing resources as the probable expression of a more inefficient, though paradoxically better adjusted to task demands cognitive strategy.

Multilayer Network Approach in EEG Motor Imagery with an Adaptive Threshold.

The brain has been understood as an interconnected neural network generally modeled as a graph to outline the functional topology and dynamics of brain processes. Classic graph modeling is based on single-layer models that constrain the traits conveyed to trace brain topologies. Multilayer modeling, in contrast, makes it possible to build whole-brain models by integrating features of various kinds. The aim of this work was to analyze EEG dynamics studies while gathering motor imagery data through single-layer and multilayer network modeling. The motor imagery database used consists of 18 EEG recordings of four motor imagery tasks: left hand, right hand, feet, and tongue. Brain connectivity was estimated by calculating the coherence adjacency matrices from each electrophysiological band (δ, θ, α and ß) from brain areas and then embedding them by considering each band as a single-layer graph and a layer of the multilayer brain models. Constructing a reliable multilayer network topology requires a threshold that distinguishes effective connections from spurious ones. For this reason, two thresholds were implemented, the classic fixed (average) one and Otsu's version. The latter is a new proposal for an adaptive threshold that offers reliable insight into brain topology and dynamics. Findings from the brain network models suggest that frontal and parietal brain regions are involved in motor imagery tasks.

Inhibitory control under emotional contexts in women with borderline personality disorder: An electrophysiological study.

Borderline personality disorder (BPD) is characterized by emotional dysregulation and difficulties in cognitive control. Inhibitory control, meanwhile, is modulated by the presence of emotional stimuli. The objective of the present study was to examine the effects of implicit emotional contexts on response inhibition in BPD patients. Participants performed a response inhibition task (Go-NoGo) under 3 background context conditions: neutral, pleasant and unpleasant. Behavioral performance did not differed between groups. Significantly higher P3NoGo amplitudes, shorter N2 latencies and lower global connectivity were observed in the patients regardless of the emotional valence of the background images compared to controls. In addition, higher P3NoGo amplitudes were correlated with more pronounced psychopathological symptoms. Emotional contexts enhanced N2 amplitudes compared to neutral ones in both groups. Results indicate that BPD required greater neural effort to successfully perform the inhibitory task. Finally, BPD showed lower synchronization between cortical regions, which may indicate a disruption in the effective temporal coupling of distributed areas associated with emotional stimuli-processing during both response and response inhibition.

Frequency spectra characterization of noncoding human genomic sequences.

BACKGROUND: Noncoding sequences have been demonstrated to possess regulatory functions. Its classification is challenging because they do not show well-defined nucleotide patterns that can correlate with their biological functions. Genomic signal processing techniques like Fourier transform have been employed to characterize coding and noncoding sequences. This transformation in a systematic whole-genome noncoding library, such as the ENCODE database, can provide evidence of a periodic behaviour in the noncoding sequences that correlates with their regulatory functions. OBJECTIVE: The objective of this study was to classify different noncoding regulatory regions through their frequency spectra. METHODS: We computed machine learning algorithms to classify the noncoding regulatory sequences frequency spectra. RESULTS: The sequences from different regulatory regions, cell lines, and chromosomes possessed distinct frequency spectra, and that machine learning classifiers (such as those of the support vector machine type) could successfully discriminate among regulatory regions, thus correlating the frequency spectra with their biological functions CONCLUSION: Our work supports the idea that there are patterns in the noncoding sequences of the genome.

Whole-Genome k-mer Topic Modeling AssociatesBacterial Families.

Alignment-free k-mer-based algorithms in whole genome sequence comparisons remainan ongoing challenge. Here, we explore the possibility to use Topic Modeling for organismwhole-genome comparisons. We analyzed 30 complete genomes from three bacterial families bytopic modeling. For this, each genome was considered as a document and 13-mer nucleotiderepresentations as words. Latent Dirichlet allocation was used as the probabilistic modeling of thecorpus. We where able to identify the topic distribution among analyzed genomes, which is highlyconsistent with traditional hierarchical classification. It is possible that topic modeling may be appliedto establish relationships between genome's composition and biological phenomena.

Type-1 diabetes shapes working memory processing strategies.

BACKGROUND: Type 1 diabetes (T1D) is a metabolic disorder characterized by recurrent hypo- and hyperglycemic episodes, whose clinical development has been associated with cognitive and working memory (WM) deficits. OBJECTIVE: To contrast quantitative electroencephalography (qEEG) measures between young patients with T1D and healthy controls while performing a visuospatial WM task with two memory load levels and facial emotional stimuli. METHODS: Four or five neutral or happy faces were sequentially and pseudo-randomly presented in different spatial locations, followed by subsequent sequences displaying the reversed spatial order or any other. Participants were instructed to discriminate between these two alternatives during EEG recording. RESULTS: A significant increase in the absolute power of the delta and theta bands, distributed mainly over the frontal region was found during task execution, with a slight decrease of alpha band power in both groups but mainly in control individuals. However, these changes were more pronounced in the T1D patients, and reached their maximum level during the WM encoding phase, even on trials with the lower memory load. In contrast, changes seemed to occur more gradually in controls and results differed significantly only on the trials with the higher WM load. CONCLUSIONS: These results reflect adaptive WM-processing mechanisms in which cognitive strategies have evolved in T1D patients in order to meet task demands.

A step forward in the quest for a mobile EEG-designed epoch for psychophysiological studies.

The aim of this study was to compare a reconfigurable mobile electroencephalography (EEG) system (M-EMOTIV) based on the Emotiv Epoc® (which has the ability to record up to 14 electrode sites in the 10/20 International System) and a commercial, clinical-grade EEG system (Neuronic MEDICID-05®), and then validate the rationale and accuracy of recordings obtained with the prototype proposed. In this approach, an Emotiv Epoc® was modified to enable it to record in the parieto-central area. All subjects (15 healthy individuals) performed a visual oddball task while connected to both devices to obtain electrophysiological data and behavioral responses for comparative analysis. A Pearson's correlation analysis revealed a good between-devices correlation with respect to electrophysiological measures. The present study not only corroborates previous reports on the ability of the Emotiv Epoc® to suitably record EEG data but presents an alternative device that allows the study of a wide range of psychophysiological experiments with simultaneous behavioral and mobile EEG recordings.

Dataset on the EEG time-frequency representation in children with different levels of mathematical achievement.

This article presents the data related to the research paper entitled "The analysis of EEG coherence reflects middle childhood differences in mathematical achievement" (González-Garrido et al., 2018). The dataset is derived from the electroencephalographic (EEG) records registered from a total of 60 8-9-years-old children with different math skill levels (High: HA, Average: AA, and Low Achievement: LA) while performing a symbolic magnitude comparison task. The average brain patterns are shown through Time-Frequency Representations (TFR) for each group, and also grand-mean amplitudes within specific EEG epochs in a 19-electrode array are provided. Making this information publicly available for further analyses could significantly contribute to a better understanding on how math achievement in children associates with cognitive processing strategies.

Is sex an influential factor in type-1 diabetes neurofunctional development? A preliminary study.

The aim of the study was to evaluate the neurofunctional effect of gender in Type-1 Diabetes Mellitus (T1DM) patients during a Visual Spatial Working Memory (VSWM) task. The study included 28 participants with ages ranging from 17-28 years. Fourteen well-controlled T1DM patients (7 female) and 14 controls matched by age, sex, and education level were scanned performing a block-design VSWM paradigm. Behavioral descriptive analyses and mean comparisons were done, and between-group and condition functional activation patterns were also compared. Whole-brain cumulative BOLD signal (CumBS), voxel-wise BOLD level frequency, Euclidean distance, and divergence indices were also calculated. There were no significant differences between or within-group sex differences for correct responses and reaction times. Functional activation analyses showed that females had activation in more brain regions, and with larger clusters of cortical activations than males. Furthermore, BOLD activation was higher in males. Despite the preliminary nature of the present study given the relatively small sample size, current results acknowledge for the first time that sex might contribute to differences in functional activation in T1DM patients. Findings suggest that sex differences should be considered when studying T1DM-disease development.

The analysis of EEG coherence reflects middle childhood differences in mathematical achievement.

Symbolic numerical magnitude processing is crucial to arithmetic development, and it is thought to be supported by the functional activation of several brain-interconnected structures. In this context, EEG beta oscillations have been recently associated with attention and working memory processing that underlie math achievement. Due to that EEG coherence represents a useful measure of brain functional connectivity, we aimed to contrast the EEG coherence in forty 8-to-9-year-old children with different math skill levels (High: HA, and Low achievement: LA) according to their arithmetic scores in the Fourth Edition of the Wide Range Achievement Test (WRAT-4) while performing a symbolic magnitude comparison task (i.e. determining which of two numbers is numerically larger). The analysis showed significantly greater coherence over the right hemisphere in the two groups, but with a distinctive connectivity pattern. Whereas functional connectivity in the HA group was predominant in parietal areas, especially involving beta frequencies, the LA group showed more extensive frontoparietal relationships, with higher participation of delta, theta and alpha band frequencies, along with a distinct time-frequency domain expression. The results seem to reflect that lower math achievements in children mainly associate with cognitive processing steps beyond stimulus encoding, along with the need of further attentional resources and cognitive control than their peers, suggesting a lower degree of numerical processing automation.

Genomic signal processing for DNA sequence clustering.

Genomic signal processing (GSP) methods which convert DNA data to numerical values have recently been proposed, which would offer the opportunity of employing existing digital signal processing methods for genomic data. One of the most used methods for exploring data is cluster analysis which refers to the unsupervised classification of patterns in data. In this paper, we propose a novel approach for performing cluster analysis of DNA sequences that is based on the use of GSP methods and the K-means algorithm. We also propose a visualization method that facilitates the easy inspection and analysis of the results and possible hidden behaviors. Our results support the feasibility of employing the proposed method to find and easily visualize interesting features of sets of DNA data.

Vibrotactile Discrimination Training Affects Brain Connectivity in Profoundly Deaf Individuals.

Early auditory deprivation has serious neurodevelopmental and cognitive repercussions largely derived from impoverished and delayed language acquisition. These conditions may be associated with early changes in brain connectivity. Vibrotactile stimulation is a sensory substitution method that allows perception and discrimination of sound, and even speech. To clarify the efficacy of this approach, a vibrotactile oddball task with 700 and 900 Hz pure-tones as stimuli [counterbalanced as target (T: 20% of the total) and non-target (NT: 80%)] with simultaneous EEG recording was performed by 14 profoundly deaf and 14 normal-hearing (NH) subjects, before and after a short training period (five 1-h sessions; in 2.5-3 weeks). A small device worn on the right index finger delivered sound-wave stimuli. The training included discrimination of pure tone frequency and duration, and more complex natural sounds. A significant P300 amplitude increase and behavioral improvement was observed in both deaf and normal subjects, with no between group differences. However, a P3 with larger scalp distribution over parietal cortical areas and lateralized to the right was observed in the profoundly deaf. A graph theory analysis showed that brief training significantly increased fronto-central brain connectivity in deaf subjects, but not in NH subjects. Together, ERP tools and graph methods depicted the different functional brain dynamic in deaf and NH individuals, underlying the temporary engagement of the cognitive resources demanded by the task. Our findings showed that the index-fingertip somatosensory mechanoreceptors can discriminate sounds. Further studies are necessary to clarify brain connectivity dynamics associated with the performance of vibrotactile language-related discrimination tasks and the effect of lengthier training programs.

Electrophysiological dynamic brain connectivity during symbolic magnitude comparison in children with different mathematics achievement levels.

Children with mathematical difficulties usually have an impaired ability to process symbolic representations. Functional MRI methods have suggested that early frontoparietal connectivity can predict mathematic achievements; however, the study of brain connectivity during numerical processing remains unexplored. With the aim of evaluating this in children with different math proficiencies, we selected a sample of 40 children divided into two groups [high achievement (HA) and low achievement (LA)] according to their arithmetic scores in the Wide Range Achievement Test, 4th ed.. Participants performed a symbolic magnitude comparison task (i.e. determining which of two numbers is numerically larger), with simultaneous electrophysiological recording. Partial directed coherence and graph theory methods were used to estimate and depict frontoparietal connectivity in both groups. The behavioral measures showed that children with LA performed significantly slower and less accurately than their peers in the HA group. Significantly higher frontocentral connectivity was found in LA compared with HA; however, when the connectivity analysis was restricted to parietal locations, no relevant group differences were observed. These findings seem to support the notion that LA children require greater memory and attentional efforts to meet task demands, probably affecting early stages of symbolic comparison.

Epileptic brain reorganization dynamics on the basis of the probability of connections.

Ictal and interictal epileptiform discharges affect brain functional dynamics, but the issue of how they occur is still under debate. The present study evaluated the brain electrical activity that underlies epileptic seizures by focusing analysis on four electroencephalographic time stages around seizure onset. The dynamics of the functional organization of the brain regions at rest, and then immediately before, during, and after, epileptic seizures in a group of five patients diagnosed with intractable temporal epilepsy was examined. The analysis is based on the probability of connections between different brain regions as determined by partial directed coherence. A probability-based graph is constructed for each stage and then the dynamics of reorganization is described using invariant measures on the basis of the graphs obtained. The functional reorganization of brain connectivity is illustrated for each time period, reflecting their temporal variations. The graph method applied proved to be useful in depicting temporal variations in functional brain connectivity because of ictal disruptions in temporal epilepsy, thus providing the possibility of further evaluation of these changes in individual cases to support medical decisions.

Genomic signal processing methods for computation of alignment-free distances from DNA sequences.

Genomic signal processing (GSP) refers to the use of digital signal processing (DSP) tools for analyzing genomic data such as DNA sequences. A possible application of GSP that has not been fully explored is the computation of the distance between a pair of sequences. In this work we present GAFD, a novel GSP alignment-free distance computation method. We introduce a DNA sequence-to-signal mapping function based on the employment of doublet values, which increases the number of possible amplitude values for the generated signal. Additionally, we explore the use of three DSP distance metrics as descriptors for categorizing DNA signal fragments. Our results indicate the feasibility of employing GAFD for computing sequence distances and the use of descriptors for characterizing DNA fragments.

Connectivity estimation of three parametric methods on simulated electroencephalogram signals.

The global framework of this paper is the connectivity estimation in multichannel electroencephalogram (EEG) recordings, modeled as multidimensional autoregressive (AR) processes. The coherence, directed transfer function and partial directed coherence functions are evaluated on two simulated EEG signals for their later application on real EEG recordings. The results were evaluated computing the relative error and a second proposed performance criterion (eta) based on the entropy of the estimated connectivity matrix.