Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 49.162
Filtrar
1.
Clin EEG Neurosci ; 53(1): 37-44, 2022 Jan.
Artigo em Inglês | MEDLINE | ID: mdl-34037471

RESUMO

The balanced processing of the internal mental world and the external world is a crucial aspect of everyday well-being. An extensive control of the internal emotional and cognitive world that often results in an internal expression of distress is a common feature of internalizing disorders. However, how depression affects the processing of the external world is still an open question. We, therefore, tested the processing of visual signals in major depressive disorder (MDD). To this end, we recorded the electroencephalogram of 38 MDD patients and 38 controls, while they performed a response-choice task with informative feedback and a passive viewing task. MDD patients differed significantly from controls in the early information processing of visual stimuli. The vertex positive potential (VPP) evoked by feedback in the response-choice task and pictures in the passive viewing task were smaller in MDD patients than in controls. This outcome suggests that depression might subtract attentional resources from external signal processing, with potential consequences in various cognitive domains.


Assuntos
Transtorno Depressivo Maior , Atenção , Eletroencefalografia , Emoções , Humanos , Processamento de Sinais Assistido por Computador
2.
Clin EEG Neurosci ; 53(1): 24-36, 2022 Jan.
Artigo em Inglês | MEDLINE | ID: mdl-34080925

RESUMO

Electroencephalogram (EEG)-based automated depression diagnosis systems have been suggested for early and accurate detection of mood disorders. EEG signals are highly irregular, nonlinear, and nonstationary in nature and are traditionally studied from a linear viewpoint by means of statistical and frequency features. Since, linear metrics present certain limitations and nonlinear methods have proven to be an efficient tool in understanding the complexities of the brain in the identification of underlying behavior of biological signals, such as electrocardiogram, EEG and magnetoencephalogram and thus, can be applied to all nonstationary signals. Various nonlinear algorithms can be used in the analysis of EEG signals. In this research paper, we aim to develop a novel methodology for EEG-based depression diagnosis utilizing 2 advanced computational techniques: frequency-domain extended multivariate autoregressive (eMVAR) and deep learning (DL). We proposed a hybrid method comprising a pretrained ResNet-50 and long-short term memory (LSTM) to capture depression-specific information and compared with a strong conventional machine learning (ML) framework having eMVAR connectivity features. The following 8 causality measures, which interpret the interaction mechanisms among spectrally decomposed oscillations, were used to extract features from multivariate EEG time series: directed coherence (DC), directed transfer function (DTF), partial DC (PDC), generalized PDC (gPDC), extended DC (eDC), delayed DC (dDC), extended PDC (ePDC), and delayed PDC (dPDC). The classification accuracies were 84% with DC, 85% with DTF, 95.3% with PDC, 95.1% with gPDC, 84.8% with eDC, 84.6% with dDC, 84.2% with ePDC, and 95.9% with dPDC for the eMVAR framework. Through a DL framework (ResNet-50 + LSTM), the classification accuracy was achieved as 90.22%. The results demonstrate that our DL methodology is a competitive alternative to the strong feature extraction-based ML methods in depression classification.


Assuntos
Aprendizado Profundo , Algoritmos , Encéfalo , Depressão/diagnóstico , Eletroencefalografia , Humanos , Processamento de Sinais Assistido por Computador
3.
Ultrasonics ; 118: 106580, 2022 Jan.
Artigo em Inglês | MEDLINE | ID: mdl-34555738

RESUMO

Recently, a method for estimating three-dimensional acoustic impedance profiles in cultured cells and human dermal organs was proposed by interpreting the reflected ultrasonic signal based on a 1-D transmission line model for acoustic impedance microscopy (AIM). However, AIM has a disadvantage that reflected signals from cells overlap with that from a reference substrate. Additionally, the amplitudes of the reflected signals from the specimens are significantly weaker than that from the substrate. In this paper, we proposed a new method for separation of those signals based on a concept of clutter filter, which had been developed for a color Doppler method in medical ultrasonic imaging. The proposed filter using singular value decomposition (SVD) could separate original signals into desired signals such as those from the substrate and cells. Additionally, an effect from a tilt of the substrate was investigated in this study. Separability of the proposed filter was evaluated by two investigations. First one was to evaluate the separability by estimating a correlation coefficient between the filtered signal and signal reflected from a position only with the substrate. Second one was to compare a slope of the substrate estimated from the original signal with that estimated from the filtered signals from the substrate. The experimental results showed that the proposed filter could separate signals from the substrate, and the compensation of the tilt of the substrate could improve the performance of the proposed filter.


Assuntos
Astrócitos/ultraestrutura , Células Cultivadas/ultraestrutura , Microscopia Acústica/instrumentação , Animais , Desenho de Equipamento , Ratos , Processamento de Sinais Assistido por Computador
4.
Sensors (Basel) ; 21(21)2021 Oct 21.
Artigo em Inglês | MEDLINE | ID: mdl-34770303

RESUMO

Inertial sensors are widely used in the field of human activity recognition (HAR), since this source of information is the most informative time series among non-visual datasets. HAR researchers are actively exploring other approaches and different sources of signals to improve the performance of HAR systems. In this study, we investigate the impact of combining bio-signals with a dataset acquired from inertial sensors on recognizing human daily activities. To achieve this aim, we used the PPG-DaLiA dataset consisting of 3D-accelerometer (3D-ACC), electrocardiogram (ECG), photoplethysmogram (PPG) signals acquired from 15 individuals while performing daily activities. We extracted hand-crafted time and frequency domain features, then, we applied a correlation-based feature selection approach to reduce the feature-set dimensionality. After introducing early fusion scenarios, we trained and tested random forest models with subject-dependent and subject-independent setups. Our results indicate that combining features extracted from the 3D-ACC signal with the ECG signal improves the classifier's performance F1-scores by 2.72% and 3.00% (from 94.07% to 96.80%, and 83.16% to 86.17%) for subject-dependent and subject-independent approaches, respectively.


Assuntos
Fotopletismografia , Processamento de Sinais Assistido por Computador , Acelerometria , Eletrocardiografia , Atividades Humanas , Humanos
5.
Sensors (Basel) ; 21(21)2021 Oct 22.
Artigo em Inglês | MEDLINE | ID: mdl-34770309

RESUMO

Surface electromyography (sEMG) is a kind of biological signal that records muscle activity noninvasively, which is of great significance in advanced human-computer interaction, prosthetic control, clinical therapy, and biomechanics. However, the number of hand gestures that can be recognized is limited and the recognition accuracy needs to be further improved. These factors lead to the fact that sEMG products are not widely used in practice. The main contributions of this paper are as follows. Firstly, considering the increasing number of gestures to be recognized and the complexity of gestures, an extensible two-stage machine learning lightweight framework was innovatively proposed for multi-gesture task recognition. Secondly, the multivariate variational mode decomposition (MVMD) is applied to extract the spatial-temporal features from the multiple channels to the EMG signals, and the separable convolutional neural network is used for modelling. In this work, the experimental results for 52 hand gestures recognition task show that the average accuracy on each stage is about 90%. The potential movement information is mainly contained in the low-frequency oscillator of the sEMG signal, and the model performs better with the low-frequency oscillation from the MVMD algorithm on the second stage classification than that of other decomposition methods.


Assuntos
Gestos , Processamento de Sinais Assistido por Computador , Algoritmos , Eletromiografia , Mãos , Humanos , Redes Neurais de Computação
6.
Sensors (Basel) ; 21(21)2021 Oct 22.
Artigo em Inglês | MEDLINE | ID: mdl-34770310

RESUMO

This paper presents an innovative method for multiple lead electrocardiogram (ECG) monitoring based on Compressed Sensing (CS). The proposed method extends to multiple leads signals, a dynamic Compressed Sensing method, that were previously developed on a single lead. The dynamic sensing method makes use of a sensing matrix in which its elements are dynamically obtained from the signal to be compressed. In this method, for the application to multiple leads, it is proposed to use a single sensing matrix for which its elements are obtained from a combination of multiple leads. The proposed method is evaluated on a wide set of signals and acquired on healthy subjects and on subjects affected by different pathologies, such as myocardial infarction, cardiomyopathy, and bundle branch block. The experimental results demonstrated that the proposed method can be adopted for a Compression Ratio (CR) up to 10, without compromising signal quality. In particular, for CR= 10, it exhibits a percentage of root-mean-squared difference average among a wide set of ECG signals lower than 3%.


Assuntos
Compressão de Dados , Infarto do Miocárdio , Algoritmos , Eletrocardiografia , Humanos , Processamento de Sinais Assistido por Computador
7.
Sensors (Basel) ; 21(21)2021 Oct 22.
Artigo em Inglês | MEDLINE | ID: mdl-34770320

RESUMO

Electroencephalography (EEG) and electromyography (EMG) are widespread and well-known quantitative techniques used for gathering biological signals at cortical and muscular levels, respectively. Indeed, they provide relevant insights for increasing knowledge in different domains, such as physical and cognitive, and research fields, including neuromotor rehabilitation. So far, EEG and EMG techniques have been independently exploited to guide or assess the outcome of the rehabilitation, preferring one technique over the other according to the aim of the investigation. More recently, the combination of EEG and EMG started to be considered as a potential breakthrough approach to improve rehabilitation effectiveness. However, since it is a relatively recent research field, we observed that no comprehensive reviews available nor standard procedures and setups for simultaneous acquisitions and processing have been identified. Consequently, this paper presents a systematic review of EEG and EMG applications specifically aimed at evaluating and assessing neuromotor performance, focusing on cortico-muscular interactions in the rehabilitation field. A total of 213 articles were identified from scientific databases, and, following rigorous scrutiny, 55 were analyzed in detail in this review. Most of the applications are focused on the study of stroke patients, and the rehabilitation target is usually on the upper or lower limbs. Regarding the methodological approaches used to acquire and process data, our results show that a simultaneous EEG and EMG acquisition is quite common in the field, but it is mostly performed with EMG as a support technique for more specific EEG approaches. Non-specific processing methods such as EEG-EMG coherence are used to provide combined EEG/EMG signal analysis, but rarely both signals are analyzed using state-of-the-art techniques that are gold-standard in each of the two domains. Future directions may be oriented toward multi-domain approaches able to exploit the full potential of combined EEG and EMG, for example targeting a wider range of pathologies and implementing more structured clinical trials to confirm the results of the current pilot studies.


Assuntos
Processamento de Sinais Assistido por Computador , Acidente Vascular Cerebral , Eletroencefalografia , Eletromiografia , Humanos
8.
Sensors (Basel) ; 21(21)2021 Oct 26.
Artigo em Inglês | MEDLINE | ID: mdl-34770408

RESUMO

This paper presents a minimum signal model via the AC small-signal model and the uncertainty principle, which reveals the minimum AC signal that can be amplified by a bipolar transistor. The Ebers-Moll model (EM3) can describe the small signal amplification process, but it is difficult to define the minimum amplifiable signal of the bipolar transistor. In this study, the correspondence relationship between the non-equilibrium carrier and the electric injection is proved, and the relationship between the life of the non-equilibrium carrier and the measurable signal is proposed by the uncertainty principle. Next, the limit of perceived minimum voltage is also derived in this paper. Then, combining with EM3 model, the minimum AC signal model of bipolar transistor is presented to calculate the minimum voltage signal of bipolar transistor that can be amplified. Finally, a number of the simulation and experiment results show that when the minimum signal in the model is used as input, the carrier concentration of the bipolar transistor does not change and the base electrode cannot perceive the signal, which verifies the validity of the minimum AC signal model.


Assuntos
Microeletrodos , Processamento de Sinais Assistido por Computador , Simulação por Computador , Eletricidade , Eletrodos , Humanos
9.
Sensors (Basel) ; 21(21)2021 Oct 26.
Artigo em Inglês | MEDLINE | ID: mdl-34770417

RESUMO

The Y Balance Test (YBT) is a dynamic balance assessment typically used in sports medicine. This work proposes a deep learning approach to automatically score this YBT by estimating the normalized reach distance (NRD) using a wearable sensor to register inertial signals during the movement. This paper evaluates several signal processing techniques to extract relevant information to feed the deep neural network. This evaluation was performed using a state-of-the-art human activity recognition system based on recurrent neural networks (RNNs). This deep neural network includes long short-term memory (LSTM) layers to learn features from time series by modeling temporal patterns and an additional fully connected layer to estimate the NRD (normalized by the leg length). All analyses were carried out using a dataset with YBT assessments from 407 subjects, including young and middle-aged volunteers and athletes from different sports. This dataset allowed developing a global and robust solution for scoring the YBT in a wide range of applications. The experimentation setup considered a 10-fold subject-wise cross-validation using training, validation, and testing subsets. The mean absolute percentage error (MAPE) obtained was 7.88 ± 0.20%. Moreover, this work proposes specific regression systems to estimate the NRD for each direction separately, obtaining an average MAPE of 7.33 ± 0.26%. This deep learning approach was compared to a previous work using dynamic time warping and k-NN algorithms, obtaining a relative MAPE reduction of 10%.


Assuntos
Aprendizado Profundo , Algoritmos , Humanos , Pessoa de Meia-Idade , Movimento , Redes Neurais de Computação , Processamento de Sinais Assistido por Computador
10.
Sensors (Basel) ; 21(21)2021 Oct 28.
Artigo em Inglês | MEDLINE | ID: mdl-34770469

RESUMO

Heart rate is one of the most important diagnostic bases for cardiovascular disease. This paper introduces a deep autoencoding strategy into feature extraction of electrocardiogram (ECG) signals, and proposes a beat-to-beat heart rate estimation method based on convolution autoencoding and Gaussian mixture clustering. The high-level heartbeat features were first extracted in an unsupervised manner by training the convolutional autoencoder network, and then the adaptive Gaussian mixture clustering was applied to detect the heartbeat locations from the extracted features, and calculated the beat-to-beat heart rate. Compared with the existing heartbeat classification/detection methods, the proposed unsupervised feature learning and heartbeat clustering method does not rely on accurate labeling of each heartbeat location, which could save a lot of time and effort in human annotations. Experimental results demonstrate that the proposed method maintains better accuracy and generalization ability compared with the existing ECG heart rate estimation methods and could be a robust long-time heart rate monitoring solution for wearable ECG devices.


Assuntos
Eletrocardiografia , Dispositivos Eletrônicos Vestíveis , Algoritmos , Análise por Conglomerados , Frequência Cardíaca , Humanos , Distribuição Normal , Processamento de Sinais Assistido por Computador
11.
Sensors (Basel) ; 21(21)2021 Oct 30.
Artigo em Inglês | MEDLINE | ID: mdl-34770552

RESUMO

The signal quality limits the applicability of phonocardiography at the patients' domicile. This work proposes the signal-to-noise ratio of the recorded signal as its main quality metrics. Moreover, we define the minimum acceptable values of the signal-to-noise ratio that warrantee an accuracy of the derived parameters acceptable in clinics. We considered 25 original heart sounds recordings, which we corrupted by adding noise to decrease their signal-to-noise ratio. We found that a signal-to-noise ratio equal to or higher than 14 dB warrants an uncertainty of the estimate of the valve closure latencies below 1 ms. This accuracy is higher than that required by most clinical applications. We validated the proposed method against a public database, obtaining results comparable to those obtained on our sample population. In conclusion, we defined (a) the signal-to-noise ratio of the phonocardiographic signal as the preferred metric to evaluate its quality and (b) the minimum values of the signal-to-noise ratio required to obtain an uncertainty of the latency of heart sound components compatible with clinical applications. We believe these results are crucial for the development of home monitoring systems aimed at preventing acute episodes of heart failure and that can be safely operated by naïve users.


Assuntos
Ruídos Cardíacos , Processamento de Sinais Assistido por Computador , Algoritmos , Humanos , Fonocardiografia , Razão Sinal-Ruído
12.
Sensors (Basel) ; 21(21)2021 Oct 31.
Artigo em Inglês | MEDLINE | ID: mdl-34770564

RESUMO

BACKGROUND: Electroencephalography (EEG)-derived event-related potentials (ERPs) provide information about a variety of brain functions, but often suffer from low inherent signal-to-noise ratio (SNR). To overcome the low SNR, techniques that pool data from multiple sensors have been applied. However, such pooling implicitly assumes that the SNR among sensors is equal, which is not necessarily valid. This study presents a novel approach for signal pooling that accounts for differential SNR among sensors. METHODS: The new technique involves pooling together signals from multiple EEG channels weighted by their respective SNRs relative to the overall SNR of all channels. We compared ERP responses derived using this new technique with those derived using both individual channels as well as traditional averaged-based channel pooling. The outcomes were evaluated in both simulated data and real data from healthy adult volunteers (n = 37). Responses corresponding to a range of ERP components indexing auditory sensation (N100), attention (P300) and language processing (N400) were evaluated. RESULTS: Simulation results demonstrate that, compared to traditional pooling technique, the new SNR-weighted channel pooling technique improved ERP response effect size in cases of unequal noise among channels (p's < 0.001). Similarly, results from real-world experimental data showed that the new technique resulted in significantly greater ERP effect sizes compared to either traditional pooling or individual channel approach for all three ERP components (p's < 0.001). Furthermore, the new channel pooling approach also resulted in larger ERP signal amplitudes as well as greater differences among experimental conditions (p's < 0.001). CONCLUSION: These results suggest that the new technique improves the capture of ERP responses relative to traditional techniques. As such, SNR-weighted channel pooling can further enable widespread applications of ERP techniques, especially those that require rapid assessments in noisy out-of-laboratory environments.


Assuntos
Eletroencefalografia , Potenciais Evocados , Adulto , Atenção , Feminino , Humanos , Idioma , Masculino , Processamento de Sinais Assistido por Computador , Razão Sinal-Ruído
13.
Sensors (Basel) ; 21(21)2021 Nov 04.
Artigo em Inglês | MEDLINE | ID: mdl-34770644

RESUMO

Smart manufacturing employs embedded systems such as CNC machine tools, programable logic controllers, automated guided vehicles, robots, digital measuring instruments, cyber-physical systems, and digital twins. These systems collectively perform high-level cognitive tasks (monitoring, understanding, deciding, and adapting) by making sense of sensor signals. When sensor signals are exchanged through the abovementioned embedded systems, a phenomenon called time latency or delay occurs. As a result, the signal at its origin (e.g., machine tools) and signal received at the receiver end (e.g., digital twin) differ. The time and frequency domain-based conventional signal processing cannot adequately address the delay-centric issues. Instead, these issues can be addressed by the delay domain, as suggested in the literature. Based on this consideration, this study first processes arbitrary signals in time, frequency, and delay domains and elucidates the significance of delay domain over time and frequency domains. Afterward, real-life signals collected while machining different materials are analyzed using frequency and delay domains to reconfirm its (the delay domain's) significance in real-life settings. In both cases, it is found that the delay domain is more informative and reliable than the time and frequency domains when the delay is unavoidable. Moreover, the delay domain can act as a signature of a machining situation, distinguishing it (the situation) from others. Therefore, computational arrangements enabling delay domain-based signal processing must be enacted to effectively functionalize the smart manufacturing-centric embedded systems.


Assuntos
Processamento de Sinais Assistido por Computador
14.
Sensors (Basel) ; 21(21)2021 Nov 07.
Artigo em Inglês | MEDLINE | ID: mdl-34770703

RESUMO

Vital signal detection using multiple radars is proposed to reduce the signal degradation from a subject's body movement. The phase variation in the transceiving signals of continuous-wave radar due to respiration and heartbeat is generated by the body surface movement of the organs monitored in the line-of-sight (LOS) of the radar. The body movement signals obtained by two adjacent radars can be assumed to be the same over a certain distance. However, the vital signals are different in each radar, and each radar has a different LOS because of the asymmetric movement of lungs and heart. The proposed method uses two adjacent radars with different LOS to obtain correlated signals that reinforce the difference in the asymmetrical movement of the organs. The correlated signals can improve the signal-to-noise ratio in vital signal detection because of a reduction in the body movement effect. Two radars at different frequencies in the 5.8 GHz band are implemented to reduce direct signal coupling. Measurement results using the radars arranged at angles of 30°, 45°, and 60° showed that the proposed method can detect the vital signals with a mean accuracy of 97.8% for the subject moving at a maximum velocity of 53.4 mm/s.


Assuntos
Radar , Processamento de Sinais Assistido por Computador , Frequência Cardíaca , Monitorização Fisiológica , Respiração
15.
Artif Intell Med ; 121: 102179, 2021 11.
Artigo em Inglês | MEDLINE | ID: mdl-34763801

RESUMO

This study proposes a novel real-time frequency-independent myocardial infarction detector for Lead II electrocardiograms. The underlying Deep-LSTM network is trained using the PTB-XL database, the largest to date publicly available electrocardiography dataset, and is tested over the same and the older PTB database. By testing the model over distinct datasets, collected under different conditions and from different patients, a more realistic measure of the performance can be gauged from the deployed system. The detector is trained over 3589 myocardial infarction (MI) patients and 7115 healthy controls (HC) while it is evaluated on 1076 MIs and 1840 HCs. The proposed algorithm, achieved an accuracy of 77.12%, recall/sensitivity of 75.85%, and a specificity of 83.02% over the entire PTB database; 85.07%, 81.54%, 87.31% over the PTB-XL validation set (fold 9), and 84.17%, 78.37%, 87.55% over the PTB-XL test set (fold 10). The model also achieves stable performance metrics over the frequency range of 202 Hz to 2.8 kHz. The processing time is dependent on the sampling frequency, ranging from 130 ms at 202 Hz to 1.8 s at 2.8 kHz. Such outcome is within the time required for real-time processing (less than 300 ms for fast heartbeats), between 202 Hz and 500 Hz making the algorithm practically real-time. Therefore, the proposed MI detector could be readily deployed onto existing wearable and/or portable devices and test instruments; potentially having significant societal and clinical impact in the lives of patients at risk for myocardial infarction.


Assuntos
Infarto do Miocárdio , Redes Neurais de Computação , Algoritmos , Bases de Dados Factuais , Eletrocardiografia , Humanos , Infarto do Miocárdio/diagnóstico , Infarto do Miocárdio/epidemiologia , Processamento de Sinais Assistido por Computador
16.
J Neural Eng ; 18(5)2021 11 02.
Artigo em Inglês | MEDLINE | ID: mdl-34725311

RESUMO

A brain-computer interface (BCI) aims to derive commands from the user's brain activity in order to relay them to an external device. To do so, it can either detect a spontaneous change in the mental state, in the so-called 'active' BCIs, or a transient or sustained change in the brain response to an external stimulation, in 'reactive' BCIs. In the latter, external stimuli are perceived by the user through a sensory channel, usually sight or hearing. When the stimulation is sustained and periodical, the brain response reaches an oscillatory steady-state that can be detected rather easily. We focus our attention on electroencephalography-based BCIs (EEG-based BCI) in which a periodical signal, either mechanical or electrical, stimulates the user skin. This type of stimulus elicits a steady-state response of the somatosensory system that can be detected in the recorded EEG. The oscillatory and phase-locked voltage component characterising this response is called a steady-state somatosensory-evoked potential (SSSEP). It has been shown that the amplitude of the SSSEP is modulated by specific mental tasks, for instance when the user focuses their attention or not to the somatosensory stimulation, allowing the translation of this variation into a command. Actually, SSSEP-based BCIs may benefit from straightforward analysis techniques of EEG signals, like reactive BCIs, while allowing self-paced interaction, like active BCIs. In this paper, we present a survey of scientific literature related to EEG-based BCI exploiting SSSEP. Firstly, we endeavour to describe the main characteristics of SSSEPs and the calibration techniques that allow the tuning of stimulation in order to maximise their amplitude. Secondly, we present the signal processing and data classification algorithms implemented by authors in order to elaborate commands in their SSSEP-based BCIs, as well as the classification performance that they evaluated on user experiments.


Assuntos
Interfaces Cérebro-Computador , Encéfalo , Eletroencefalografia , Potenciais Somatossensoriais Evocados , Processamento de Sinais Assistido por Computador
17.
Sensors (Basel) ; 21(22)2021 Nov 10.
Artigo em Inglês | MEDLINE | ID: mdl-34833550

RESUMO

With the development of signal processing technology and the use of new radar systems, signal aliasing and electronic interference have occurred in space. The electromagnetic signals have become extremely complicated in their current applications in space, causing difficult problems in terms of accurately identifying radar-modulated signals in low signal-to-noise ratio (SNR) environments. To address this problem, in this paper, we propose an intelligent recognition method that combines time-frequency (T-F) analysis and a deep neural network to identify radar modulation signals. The T-F analysis of the complex Morlet wavelet transform (CMWT) method is used to extract the characteristics of signals and obtain the T-F images. Adaptive filtering and morphological processing are used in T-F image enhancement to reduce the interference of noise on signal characteristics. A deep neural network with the channel-separable ResNet (Sep-ResNet) is used to classify enhanced T-F images. The proposed method completes high-accuracy intelligent recognition of radar-modulated signals in a low-SNR environment. When the SNR is -10 dB, the probability of successful recognition (PSR) is 93.44%.


Assuntos
Radar , Processamento de Sinais Assistido por Computador , Redes Neurais de Computação , Razão Sinal-Ruído , Análise de Ondaletas
18.
Sensors (Basel) ; 21(22)2021 Nov 13.
Artigo em Inglês | MEDLINE | ID: mdl-34833619

RESUMO

Pedestrian trajectory prediction is one of the main concerns of computer vision problems in the automotive industry, especially in the field of advanced driver assistance systems. The ability to anticipate the next movements of pedestrians on the street is a key task in many areas, e.g., self-driving auto vehicles, mobile robots or advanced surveillance systems, and they still represent a technological challenge. The performance of state-of-the-art pedestrian trajectory prediction methods currently benefits from the advancements in sensors and associated signal processing technologies. The current paper reviews the most recent deep learning-based solutions for the problem of pedestrian trajectory prediction along with employed sensors and afferent processing methodologies, and it performs an overview of the available datasets, performance metrics used in the evaluation process, and practical applications. Finally, the current work exposes the research gaps from the literature and outlines potential new research directions.


Assuntos
Condução de Veículo , Aprendizado Profundo , Pedestres , Acidentes de Trânsito , Humanos , Processamento de Sinais Assistido por Computador , Tecnologia
19.
Sensors (Basel) ; 21(22)2021 Nov 14.
Artigo em Inglês | MEDLINE | ID: mdl-34833639

RESUMO

We investigated the effects of a quality screening method on unconstrained measured signals, including electrocardiogram (ECG), photoplethysmogram (PPG), and ballistocardiogram (BCG) signals, in our collective chair system for smart healthcare. Such an investigation is necessary because unattached or unbound sensors have weaker connections to body parts than do conventional methods. Using the biosignal chair, the physiological signals collected during sessions included a virtual driving task, a physically powered wheelchair drive, and three types of body motions. The signal quality index was defined by the similarity between the observed signals and noise-free signals from the perspective of the cross-correlations of coefficients with appropriate individual templates. The goal of the index was to qualify signals without a reference signal to assess the practical use of the chair in daily life. As expected, motion artifacts have adverse effects on the stability of physiological signals. However, we were able to observe a supplementary relationship between sensors depending on each movement trait. Except for extreme movements, the signal quality and estimated heart rate (HR) remained within the range of criteria usable for status monitoring. By investigating the signal reliability, we were able to confirm the suitability of using the unconstrained biosignal chair to collect real-life measurements to improve safety and healthcare.


Assuntos
Balistocardiografia , Processamento de Sinais Assistido por Computador , Atenção à Saúde , Eletrocardiografia , Reprodutibilidade dos Testes
20.
Sensors (Basel) ; 21(22)2021 Nov 18.
Artigo em Inglês | MEDLINE | ID: mdl-34833740

RESUMO

Sudden Cardiac Death (SCD) is an unexpected sudden death due to a loss of heart function and represents more than 50% of the deaths from cardiovascular diseases. Since cardiovascular problems change the features in the electrical signal of the heart, if significant changes are found with respect to a reference signal (healthy), then it is possible to indicate in advance a possible SCD occurrence. This work proposes SCD identification using Electrocardiogram (ECG) signals and a sparse representation technique. Moreover, the use of fixed feature ranking is avoided by considering a dictionary as a flexible set of features where each sparse representation could be seen as a dynamic feature extraction process. In this way, the involved features may differ within the dictionary's margin of similarity, which is better-suited to the large number of variations that an ECG signal contains. The experiments were carried out using the ECG signals from the MIT/BIH-SCDH and the MIT/BIH-NSR databases. The results show that it is possible to achieve a detection 30 min before the SCD event occurs, reaching an an accuracy of 95.3% under the common scheme, and 80.5% under the proposed multi-class scheme, thus being suitable for detecting a SCD episode in advance.


Assuntos
Eletrocardiografia , Processamento de Sinais Assistido por Computador , Bases de Dados Factuais , Morte Súbita Cardíaca , Coração , Humanos
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA
...