A5083997342- ECG Monitoring and Analysis
- Heart Rate Variability and Autonomic Control
- Phonocardiography and Auscultation Techniques
- Artificial Intelligence in Healthcare
- Non-Invasive Vital Sign Monitoring
- EEG and Brain-Computer Interfaces
- Machine Learning in Healthcare
- Advanced Control Systems Optimization
- Neural Networks and Applications
- Time Series Analysis and Forecasting
- Cardiovascular Function and Risk Factors
- Hemodynamic Monitoring and Therapy
- Fault Detection and Control Systems
- Cardiac electrophysiology and arrhythmias
- Music and Audio Processing
- Cardiac Imaging and Diagnostics
- Blind Source Separation Techniques
- Complex Systems and Time Series Analysis
- Control Systems and Identification
- Photovoltaic System Optimization Techniques
- Acute Myocardial Infarction Research
- Explainable Artificial Intelligence (XAI)
- Cardiovascular Syncope and Autonomic Disorders
- Blood Pressure and Hypertension Studies
- Anomaly Detection Techniques and Applications
University of Coimbra
2015-2024
Hospital de Santo António
2024
Hasselt University
2024
Hospitais da Universidade de Coimbra
2017-2023
Escola Superior de Tecnologia da Saúde de Coimbra
2023
Institute for Systems Engineering and Computers
1999-2019
Instituto de Telecomunicações
2017
Universidade Federal de Minas Gerais
2016
Philips (Netherlands)
2016
Centro Hospitalar do Baixo Vouga
2015
Aims Although recognized as an important feature of atherosclerotic coronary disease, little is known about the frequency and prognostic importance distal embolization during primary angioplasty for acute myocardial infarction.
Heart rate variability (HRV) represents one of the most promising markers autonomic nervous system (ANS) regulation. However, it requires acquisition ECG signal in order to reliably detect RR intervals, which is not always easily and comfortably available personal health applications. Additionally, due progress single spot optical sensors, photoplethysmography (PPG) an interesting alternative for heartbeat interval measurements, since a more convenient less intrusive measurement technique....
Atrial fibrillation (AF) is an arrhythmia that can lead to several patient risks. This kind of affects mostly elderly people, in particular those who suffer from heart failure (one the main causes hospitalization). Thus, detection AF becomes decisive prevention cardiac threats. In this paper algorithm for based on a novel architecture and feature extraction methods proposed. The aforementioned analysis three physiological characteristics AF: i) P wave absence ii) rate irregularity iii)...
Cardiovascular disease has a huge impact on health care services, originating unsustainable costs at clinical, social, and economic levels. In this context, patients' risk stratification tools are central to support clinical decisions contributing the implementation of effective preventive care. Although useful, these present some limitations, in particular, lack performance as well impossibility consider new factors potentially important prognosis severe cardiac events. Moreover, actual use...
Abstract Osteoporosis is a disease characterized by impairment of bone microarchitecture that causes high socioeconomic impacts in the world because fractures and hospitalizations. Although dual-energy X-ray absorptiometry (DXA) gold standard for diagnosing disease, access to DXA developing countries still limited due its cost, being present only specialized hospitals. In this paper, we analyze performance Osseus, low-cost portable device based on electromagnetic waves measures attenuation...
A new unsupervised and low complexity method for detection of S1 S2 components heart sound without the ECG reference is described The most reliable invariant feature applied in current state-of-the-art segmentation algorithms implicitly or explicitly S1-S2 interval regularity. However; this criterion inherently prone to noise influence does not appropriately tackle arrhythmic cases. solution based upon a high frequency marker; which extracted from using fast wavelet decomposition, proposed...
Monitoring of cardiovascular function on a beat-to-beat basis is fundamental for protecting patients in different settings including emergency medicine and interventional cardiology, but still faces technical challenges several limitations. In the present study, we propose new method extraction performance surrogates from analysis photoplethysmographic (PPG) signal alone.
The presence of motion artifacts in photoplethysmographic (PPG) signals is one the major obstacles extraction reliable cardiovascular parameters continuous monitoring applications. In current paper we present an algorithm for artifact detection based on analysis variations time and period domain characteristics PPG signal. extracted features are ranked using a normalized mutual information feature selection best used support vector machine classification model to distinguish between clean...
There is a lack of multi-session P300 datasets for Brain-Computer Interfaces (BCI). Publicly available are usually limited by small number participants with few BCI sessions. In this sense, the large, comprehensive various individuals and multiple sessions has advances in development more effective data processing analysis methods systems. This particularly evident to explore feasibility deep learning that require large datasets. Here we present BCIAUT-P300 dataset, containing 15 autism...
Heart sound is a valuable biosignal for diagnosis of large set cardiac diseases. Ambient and physiological noise interference one the most usual highly probable incidents during heart acquisition. It tends to change morphological characteristics that may carry important information disease diagnosis. In this paper, we propose new method applicable in real time detect ambient internal body noises manifested The algorithm developed on basis periodic nature sounds physiologically inspired...
Searching for similarity between time series plays an important role when large amounts of information need to be clustered integrate intelligent supported personal health care diagnosis systems. The performance classification, clustering and disease prediction are influenced by the prior stage where is performed. Physiologic signals vary even within same patient, so analysis their possible variation without affecting future accuracy hereby addressed. Commonly employed methods measuring were...
This paper aims to assess the predictive value of physiological data daily collected in a telemonitoring study early detection heart failure (HF) decompensation events. The main hypothesis is that time series with similar progression (trends) may have prognostic future clinical states (decompensation or normal condition). strategy composed two steps: trend similarity analysis and procedure. scheme combines Haar wavelet decomposition, which signals are represented as linear combinations set...
In this work thirty features were tested in order to identify the best feature set for robust detection of wheezes. The include wheezes signature spectrogram space (WS-SS) and twenty-nine musical usually used context Music Information Retrieval. method proposed detect imposes a temporal Gaussian regularization reduction false positives based on (geodesic) morphological opening by reconstruction operator. Our dataset contains wheezes, crackles normal breath sounds. Four selection algorithms...
Heart sounds entail crucial heart function information. In conditions of abnormalities, such as valve dysfunctions and rapid blood flow, additional are heard in regular sounds, which can be employed pathology diagnosis. These or so-called murmurs, show different characteristics with respect to cardiovascular diseases, namely disorders. this paper, we present a method murmur classification composed by three basic steps: feature extraction, selection, using nonlinear classifier. A new set 17...
Abstract Electrocardiogram (ECG) recordings, lasting hours before epileptic seizures, have been studied in the search for evidence of existence a preictal interval that follows normal ECG trace and precedes seizure’s clinical manifestation. The has not yet clinically parametrized. Furthermore, duration this varies seizures both among patients from same patient. In study, we performed heart rate variability (HRV) analysis to investigate discriminative power features HRV identification...
Abstract Typical seizure prediction models aim at discriminating interictal brain activity from pre-seizure electrographic patterns. Given the lack of a preictal clinical definition, fixed interval is widely used to develop these models. Recent studies reporting selection among range intervals show inter- and intra-patient variability, possibly reflecting heterogeneity generation process. Obtaining accurate labels can be train supervised and, hence, avoid setting for all seizures within same...
This paper presents a new algorithm for segmentation and classification of S1 S2 heart sounds without ECG reference. The proposed approach is composed three main stages. In the first stage fundamental sound lobes are identified using fast wavelet transform Shannon energy. Next, these validated classified into classes based on Mel-frequency coefficients non-supervised neural network. Finally, regular cycles in post-processing by rhythm criterion. was tested samples collected from prosthetic...
Systolic time intervals (STI) have shown significant diagnostic and prognostic value to assess the global cardiac function. Their has been largely established in hospital settings. Currently, STI are considered a promising tool for long-term patient follow-up with chronic cardiovascular diseases. Several technologies exist that enable beat-by-beat assessment of personal health application scenarios. A comparative study is presented using echocardiographic gold standard synchronized impedance...