344 research outputs found
Bondar Andriy Danylovych
No full textУ статті відображено життєвий і творчий шлях Андрія Даниловича Бондаря, вченого-дослідника, у полі зору якого були проблеми історії освіти та виховання, дидактики вищої школи. Представлено науковий доробок автора та його вклад у розбудову освіти в Україні за радянських часів.The article deals with the life and creative way of Andriy Danilovich Bondar, a researcher and scientist, who studied issues of the history of education, didactics of higher education. The scientific contributions of the author and his contribution to the development of education in Ukraine during the Soviet times are presented in article
PPG-based heart rate estimation using Wiener filter, phase vocoder and Viterbi decoding
No full textAccurate heart rate (HR) estimation from the photoplethysmographic (PPG) signal during intensive physical exercises is tackled in this paper. Wiener filters are designed to attenuate the influence of motion artifacts. The phase vocoder is used to improve the initial Discrete Fourier transform (DFT) based frequency estimation. Additionally, Viterbi decoding is used as a novel post-processing step to find the path through time-frequency state-space plane. The system performance is assessed on a publically available dataset of 23 PPG recordings. The resulting algorithm is designed for scenarios that do not require online HR monitoring (swimming, offline fitness statistics). The resultant system with an error rate of 1.31 beats per minute outperforms all other systems reported to-date in literature and in contrast to existing alternatives requires no parameter to tune at the post-processing stage and operates at a much lower computational cost. The Matlab implementation is provided online
Accurate wearable heart rate monitoring during physical exercises using PPG
No full textObjective: The challenging task of heart rate (HR) estimation from the photoplethysmographic (PPG) signal, during intensive physical exercises is tackled in this paper. Methods: The study presents a detailed analysis of a novel algorithm (WFPV) that exploits a Wiener filter to attenuate the motion artifacts, a phase vocoder to refine the HR estimate and user-adaptive postprocessing to track the subject physiology. Additionally, an offline version of the HR estimation algorithm that uses Viterbi decoding is designed for scenarios that do not require online HR monitoring (WFPV+VD). The performance of the HR estimation systems is rigorously compared with existing algorithms on the publically available database of 23 PPG recordings. Results: On the whole dataset of 23 PPG recordings, the algorithms result in average absolute errors of 1.97 and 1.37 BPM in the online and offline modes, respectively. On the test dataset of 10 PPG recordings which were most corrupted with motion artifacts, WFPV has an error of 2.95 BPM on its own and 2.32 BPM in an ensemble with 2 existing algorithms. Conclusion: The error rate is significantly reduced when compared with the state-of-the art PPG-based HR estimation methods. Significance: The proposed system is shown to be accurate in the presence of strong motion artifacts and in contrast to existing alternatives has very few free parameters to tune. The algorithm has a low computational cost and can be used for fitness tracking and health monitoring in wearable devices. The Matlab implementation of the algorithm is provided online
AI-assisted analysis of heart sounds and interpretation of acoustic representation of brainwaves in neonates
No full textNumerous reports from World Health Organisation (WHO) consistently list the diseases of the heart and the brain among the top three causes of death across the globe. In low and low-to-middle-income countries, the neonatal stage is the most dangerous of the whole life and is a time of particular concern for medical professionals and parents. Timely detection of abnormalities during the first days of life allows medical staff to make informed decisions which have life-saving consequences. For this, continuous monitoring is required and it has several challenges in a clinical setting. First, acquiring physiological data from neonates is not trivial, often involving time-consuming processes that require specialised training. Second, specific monitoring equipment is often expensive and not affordable in low-income communities. More importantly, the complexity of the data may be difficult to interpret even for trained professionals and the required expertise might not be available 24/7. Alternative methods and tools that are low cost and require minimum training while providing the accuracy level of a specialist medical professional are required. This work deals with the development of such methods for the analysis of neonatal heart and brain signals by means of artificial intelligence (AI) and AI-guided sonification.
Sound analysis can play an important role as a non-invasive, intuitive, and cost-effective tool to facilitate the interpretation of physiological signals. Heart auscultation is already part of the clinical examination routine. It uses a stethoscope, which is a low cost and reliable tool to screen for neonatal heart defects. However, heart sound interpretation is subjective, dependent on the assessor’s hearing acuity and the acquired level of expertise. Assistance from AI can provide an objective interpretation of heart sounds to complement the traditional auscultation method. A novel, accurate method for detecting congenital heart disease in phonocardiogram (PCG) signals using AI is presented.
When dealing with the brain abnormalities in newborns, neonatal seizures are one of the most common neurological conditions, and they need to be treated as a medical emergency with prompt detection and intervention. Electroencephalography (EEG), the gold standard for monitoring electrical brain activity, is often difficult to interpret visually and requires a highly specialised medical professional. These professionals might not be readily available in low or medium-income settings, and even in high-income countries, they might be available only in tertiary care centres and not present 24/7. AI-driven sonification of EEG for detection of neonatal seizures, which is developed in this work, helps to improve the detection of these threatening seizure events by decreasing the level of expertise required from healthcare professionals while maintaining the same accuracy. It is shown that AI-assisted sonification can augment the medical professional to make decisions which are better than AI alone while improving the interpretability of the made decisions, which is a key requirement in the medical domain.
The proposed algorithms and methodologies are validated on numerous datasets. The developed prototypes are implemented using cloud and Internet of Things technologies. It is shown that these technologies allow for an affordable, real-time analysis of heart and brain physiological signals with minimum training
Portable acquisition and interpretation of EEG for neonatal healthcare applications
No full textNeonatal encephalopathy is a significant concern for both parents and medical staff. It results in the death or disability of over 2 million infants globally each year and accounts for 23% of all infant deaths. Early identification and treatment of brain injury is vital. Electroencephalography (EEG) is the gold standard for monitoring brain function. However, conventional EEG monitors are complex systems, which require specialised medical staff to configure and interpret the data. The equipment and expertise are limited to tertiary-care hospitals with neurology/neurophysiology facilities. Even in such hospitals, the process of diagnosing neonatal brain injuries suffers from long delays, making it difficult to intervene within the effective treatment window.
In this thesis, a portable EEG acquisition and interpretation system for clinical use in the neonatal population is investigated. The acquisition system includes the design of a low-power and wireless electronic circuit for the acquisition, processing, and transmission of EEG signals. Existing state-of-the-art devices are reviewed and analysed. A custom solution, which offers eight channels of low-noise EEG acquisition and integration with a low-power microcontroller unit for on-board data processing and machine learning inference, is proposed. Novel signal processing and machine learning algorithms to support EEG data interpretation are optimised for use in resource-constrained applications and platforms.
To date, minimal consideration is given to the regulatory and commercial requirements when developing medical devices in academia. This introduces a barrier to bringing academic innovation through to clinical adoption. A regulatory and commercial route-to-market is proposed herein for a cost-effective and time-efficient translation to clinical use
Implementation of an AI-assisted sonification algorithm on an edge device
No full textOxygen deprivation at birth leads to brain injury, which can have serious consequences. It is the dominant cause of seizures. Quickly and accurately detecting seizures is a challenging problem for neonates. A severe shortage of medical professionals with the necessary expertise for Electroencephalogram (EEG) analysis leads to significant delays in decision-making and hence treatment. These problems are made worse in disadvantaged communities. Artificial intelligence (AI) techniques have been proposed to automate the process and compensate for the lack of available expertise. However, these models are ’black boxes', and their lack of explainability dampens the wide adoption by medical professionals. AI-assisted sonification adds explainability to any such automated methodology, empowering medical professionals to make accurate decisions regardless of their level of expertise in EEG analysis. The feasibility of an implementation of an AI-assisted sonification algorithm on an edge device is presented and analyzed. A lightweight derived algorithm for resource-constrained implementation scenarios is also evaluated and presented, suggesting suitability for further ultra-low power, mobile and wearables implementations. Furthermore, a neural network is analysed for the potential of low-precision implementation, enabling inference on specialised hardware
Neonatal seizure detection: a deep learning approach
No full textThe detection of neonatal seizures is an important step in identifying neurological dysfunction in newborn infants. Research indicates that seizures in infants are underreported; specialist EEG monitoring equipment and neonatal neurophysiological expertise are required to reliably detect neonatal seizures due to the predominance of sub-clinical seizure events. Often, the required level of clinical expertise is not available around-the-clock in the NICU; medical experts have cited the need for decision support algorithms to assist staff during these times.
In this thesis novel automated neonatal seizure detection algorithms are proposed. Here deep learning end-to-end optimised algorithms, which detect seizures from raw multi-channel EEG, are presented. The deep learning approach differs from previous rule-based and machine learning systems, which rely on hand-engineered features. An appropriate input EEG representation is selected through empirical analysis; 2-dimensional time-frequency representations of EEG are compared to 1-dimensional temporal representations in a series of experiments. Deep learning algorithms prove capable of extracting discriminative intermediate hierarchical representations from raw EEG.
A deep learning algorithm for detecting seizures in term neonates is proposed. The designed algorithm utilises only convolutional layers to process multi-channel temporal EEG and is designed to exploit the large quantity of weakly labelled data available in the training stage. The effect of varying architectural parameters is thoroughly studied, and the designed architecture compares favourably in terms of performance, inference run time and number of parameters when compared with baseline systems. The developed system outperforms state-of-the-art machine learning algorithms when tested on a large database of continuous EEG recordings (duration 834h) and when further validated on a held-out publicly available dataset (duration 112h), achieving AUC results of 98.5% and 95.6% respectively.
The challenges associated with detecting seizures in term EEG are exacerbated in preterm EEG due to the large variations in EEG morphology depending on gestational age and the limited amount of annotated preterm EEG available. A deep learning algorithm development framework is proposed where classifiers are trained to detect seizures for specific gestational age ranges. The developed algorithms leverage the existence of robustly trained term EEG models through transfer learning and classifier ensembling; this results in accurate seizure detection despite the scarcity of labelled training data. This preterm seizure detection framework represents the first time an algorithm of this kind has been developed; it achieves an AUC of 95.4% on a held-out test dataset (duration 575h), and detects approximately 50% of all seizure events at a false detection rate of one false alarm every four hours.
In this work, algorithms are investigated through a series of visualisation techniques. This analysis gives an understanding of the EEG patterns which contribute to algorithm decisions and highlights the differences between term and preterm EEG. The developed algorithm framework is also utilised as part of a mobile brain monitoring device where the light-weight nature of the designed network and the simplicity of the inference computations are exploited through AI-on-the-edge decision support. The ability to decipher deep learning algorithms and to integrate algorithms into existing brain monitoring systems are necessary steps for the translation of the work in this thesis into clinical domain
Acoustic event detection and classification
No full textL'activitat humana que té lloc en sales de reunions o aules d'ensenyament es veu reflectida en una rica varietat d'events acústics, ja siguin produïts pel cos humà o per objectes que les persones manegen. Per això, la determinació de la identitat dels sons i de la seva posició temporal pot ajudar a detectar i a descriure l'activitat humana que té lloc en la sala. A més a més, la detecció de sons diferents de la veu pot ajudar a millorar la robustes de tecnologies de la parla com el reconeixement automàtica a condicions de treball adverses. L'objectiu d'aquesta tesi és la detecció i classificació automàtica d'events acústics. Es tracta de processar els senyals acústics recollits per micròfons distants en sales de reunions o aules per tal de convertir-los en descripcions simbòliques que es corresponguin amb la percepció que un oient tindria dels diversos events sonors continguts en els senyals i de les seves fonts. En primer lloc, s'encara la tasca de classificació automàtica d'events acústics amb classificadors de màquines de vectors suport (Support Vector Machines (SVM)), elecció motivada per l'escassetat de dades d'entrenament. Per al problema de reconeixement multiclasse es desenvolupa un esquema d'agrupament automàtic amb conjunt de característiques variable i basat en matrius de confusió. Realitzant proves amb la base de dades recollida, aquest classificador obté uns millors resultats que la tècnica basada en models de barreges de Gaussianes (Gaussian Mixture Models (GMM)), i aconsegueix una reducció relativa de l'error mitjà elevada en comparació amb el millor resultat obtingut amb l'esquema convencional basat en arbre binari. Continuant amb el problema de classificació, es comparen unes quantes maneres alternatives d'estendre els SVM al processament de seqüències, en un intent d'evitar l'inconvenient de treballar amb vectors de longitud fixa que presenten els SVM quan han de tractar dades d'àudio. En aquestes proves s'observa que els nuclis de deformació temporal dinàmica funcionen bé amb sons que presenten una estructura temporal. A més a més, s'usen conceptes i eines manllevats de la teoria de lògica difusa per investigar, d'una banda, la importància de cada una de les característiques i el grau d'interacció entre elles, i d'altra banda, tot cercant l'augment de la taxa de classificació, s'investiga la fusió de lessortides de diversos sistemes de classificació. Els sistemes de classificació d'events acústicsdesenvolupats s'han testejat també mitjançant la participació en unes quantes avaluacions d'àmbitinternacional, entre els anys 2004 i 2006. La segona principal contribució d'aquest treball de tesi consisteix en el desenvolupament de sistemes de detecció d'events acústics. El problema de la detecció és més complex, ja que inclou tant la classificació dels sons com la determinació dels intervals temporals on tenen lloc. Es desenvolupen dues versions del sistema i es proven amb els conjunts de dades de les dues campanyes d'avaluació internacional CLEAR que van tenir lloc els anys 2006 i 2007, fent-se servir dos tipus de bases de dades: dues bases d'events acústics aïllats, i una base d'enregistraments de seminaris interactius, les quals contenen un nombre relativament elevat d'ocurrències dels events acústics especificats. Els sistemes desenvolupats, que consisteixen en l'ús de classificadors basats en SVM que operen dinsd'una finestra lliscant més un post-processament, van ser els únics presentats a les avaluacionsesmentades que no es basaven en models de Markov ocults (Hidden Markov Models) i cada un d'ellsva obtenir resultats competitius en la corresponent avaluació. La detecció d'activitat oral és un altre dels objectius d'aquest treball de tesi, pel fet de ser un cas particular de detecció d'events acústics especialment important. Es desenvolupa una tècnica de millora de l'entrenament dels SVM per fer front a la necessitat de reducció de l'enorme conjunt de dades existents. El sistema resultant, basat en SVM, és testejat amb uns quants conjunts de dades de l'avaluació NIST RT (Rich Transcription), on mostra puntuacions millors que les del sistema basat en GMM, malgrat que aquest darrer va quedar entre els primers en l'avaluació NIST RT de 2006.Per acabar, val la pena esmentar alguns resultats col·laterals d'aquest treball de tesi. Com que s'ha dut a terme en l'entorn del projecte europeu CHIL, l'autor ha estat responsable de l'organització de les avaluacions internacionals de classificació i detecció d'events acústics abans esmentades, liderant l'especificació de les classes d'events, les bases de dades, els protocols d'avaluació i, especialment, proposant i implementant les diverses mètriques utilitzades. A més a més, els sistemes de detecciós'han implementat en la sala intel·ligent de la UPC, on funcionen en temps real a efectes de test i demostració.The human activity that takes place in meeting-rooms or class-rooms is reflected in a rich variety of acoustic events, either produced by the human body or by objects handled by humans, so the determination of both the identity of sounds and their position in time may help to detect and describe that human activity.Additionally, detection of sounds other than speech may be useful to enhance the robustness of speech technologies like automatic speech recognition. Automatic detection and classification of acoustic events is the objective of this thesis work. It aims at processing the acoustic signals collected by distant microphones in meeting-room or classroom environments to convert them into symbolic descriptions corresponding to a listener's perception of the different sound events that are present in the signals and their sources. First of all, the task of acoustic event classification is faced using Support Vector Machine (SVM) classifiers, which are motivated by the scarcity of training data. A confusion-matrix-based variable-feature-set clustering scheme is developed for the multiclass recognition problem, and tested on the gathered database. With it, a higher classification rate than the GMM-based technique is obtained, arriving to a large relative average error reduction with respect to the best result from the conventional binary tree scheme. Moreover, several ways to extend SVMs to sequence processing are compared, in an attempt to avoid the drawback of SVMs when dealing with audio data, i.e. their restriction to work with fixed-length vectors, observing that the dynamic time warping kernels work well for sounds that show a temporal structure. Furthermore, concepts and tools from the fuzzy theory are used to investigate, first, the importance of and degree of interaction among features, and second, ways to fuse the outputs of several classification systems. The developed AEC systems are tested also by participating in several international evaluations from 2004 to 2006, and the resultsare reported. The second main contribution of this thesis work is the development of systems for detection of acoustic events. The detection problem is more complex since it includes both classification and determination of the time intervals where the sound takes place. Two system versions are developed and tested on the datasets of the two CLEAR international evaluation campaigns in 2006 and 2007. Two kinds of databases are used: two databases of isolated acoustic events, and a database of interactive seminars containing a significant number of acoustic events of interest. Our developed systems, which consist of SVM-based classification within a sliding window plus post-processing, were the only submissions not using HMMs, and each of them obtained competitive results in the corresponding evaluation. Speech activity detection was also pursued in this thesis since, in fact, it is a -especially important - particular case of acoustic event detection. An enhanced SVM training approach for the speech activity detection task is developed, mainly to cope with the problem of dataset reduction. The resulting SVM-based system is tested with several NIST Rich Transcription (RT) evaluation datasets, and it shows better scores than our GMM-based system, which ranked among the best systems in the RT06 evaluation. Finally, it is worth mentioning a few side outcomes from this thesis work. As it has been carried out in the framework of the CHIL EU project, the author has been responsible for the organization of the above mentioned international evaluations in acoustic event classification and detection, taking a leading role in the specification of acoustic event classes, databases, and evaluation protocols, and, especially, in the proposal and implementation of the various metrics that have been used. Moreover, the detection systems have been implemented in the UPC's smart-room and work in real time for purposes of testing and demonstration.DOCTORAT EN TEORIA DEL SENYAL I COMUNICACIONS (Pla 1998
Estimation of heart rate from photoplethysmography during physical exercise using Wiener filtering and the phase vocoder
No full text- …
