Dissertations / Theses on the topic 'Heart rate detection'
To see the other types of publications on this topic, follow the link: Heart rate detection.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Heart rate detection.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Magnusson, Karolina. "Mechanical heart rate detection using cardiogenic impedance - a morphology approach." Thesis, Linköpings universitet, Institutionen för medicinsk teknik, 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-119381.
Full textAbstract:
The objective of this thesis is to examine the possibility to determine the mechanical heart rate using intracardiac impedance in the time domain. Deducing the mechanical heartrate from the impedance could help improve the performance of implanted devices that today depend on the measurement of the heart’s electrical activity. Cardiogenic – also known as intracardiac – impedance is based on the difference in conductivity between heart muscle tissue and blood, making the impedance vary as the heart is filled and emptied. The data used in this thesis was acquired from three previous studies performed by St Jude Medical, two clinical and one preclinical. Two impedance measurement configurations were chosen from these studies, one bipolar and one quadropolar. To deduce the heart rate from the intracardiac impedance six algorithms were evaluated. Three using continuous peak detection and three evaluating small frames of the impedance signal.The peak detection algorithms were peak detection on the impedance signal itself, on its derivative and on its integral. The three others were an Auto Correlation Function (ACF), an Average Magnutide Difference Function (AMDF) and an Average Wave Comparison Function (AWCF). In order to assess the heart rates deduced from the intracardiac impedance by the algorithms, these rates were compared to both the IEGM or the ECG (depending on which study was at hand) and the blood pressure. Several issues affected the performance of the algorithms. Impedance morphology can vary between patients. Some display so called “double peaks”, making it hard to decide whether a patient has for example a pulse of 80 bpm or of 160 bpm. The impedance morphology was also affected by amplitude modulation with the respiration frequency which in some patients cause difficulties to analyze the impedance signal. The results show that the two impedance measurement configurations perform equally well and that the ACF method was the overall best performing algorithm. They also show that individual patient impedance morphology has a large influence on the results and for future studies it should therefore be interesting to calibrate the algorithms for each patient, as this should improve performance.
2
Danielsson, Fanny. "NON-CONTACT BASED PERSON’S SLEEPINESS DETECTION USING HEART RATE VARIABILITY." Thesis, Mälardalens högskola, Akademin för innovation, design och teknik, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-44620.
Full textAbstract:
Today many strategies of monitoring health status and well-being are done through measurementmethods that are connected to the body, e.g. sensors or electrodes. These are often complicatedand requires personal assistance in order to use, because of advanced hardware and attachmentissues. This paper proposes a new method of making it possible for a user to self-monitoring theirwell-being and health status over time by using a non-contact camera system. The camera systemextracts physiological parameters (e.g. Heart Rate (HR), Respiration Rate (RR), Inter-bit-Interval(IBI)) based on facial color variations, due to blood circulation in facial skin. By examining anindividual’s physiological parameters, one can extract measurements that can be used in order tomonitor their well-being. The measurements used in this paper is features of heart rate variability(HRV) that are calculated from the physiological parameter IBI. The HRV features included andtested in this paper is SDNN, RMSSD, NN50 and pNN50 from Time Domain and VLF, LF andLF/HF from Frequency Domain. Machine Learning classification is done in order to classifyan individual’s sleepiness from the given features. The Machine Learning classification modelwhich gave the best results, in forms of accuracy, were Support Vector Machines (SVM). The bestmean accuracy achieved was 84,16% for the training set and 81,67% for the test set for sleepinessdetection with SVM. This paper has great potential for personal health care monitoring and can befurther extended to detect other factors that could help a user to monitor their well-being, such asmeasuring stress level
3
Aguilar, Pelaez Eduardo. "Real-time algorithms for acoustic heart rate detection and respiratory rate extraction for use in miniature wearable breathing and heart monitor." Thesis, Imperial College London, 2010. http://hdl.handle.net/10044/1/39384.
Full textAbstract:
This thesis presents novel research for real time heart sound detection, heart rate extraction and acoustic respiratory rate extraction algorithms. This was done based on signals obtained with a novel in-house developed wireless acoustic breathing and heart rate monitor. The core aim of this work is to enable additional features with respect to which physiological parameters can be measured by acoustic means with the above- mentioned sensor in the hospital bed environment. The performance evaluation was done with data collected from clinical trials carried out at Queens Square hospital - UCL Institute of Neurology - in London, UK. The respiratory rate extraction algorithm presented achieved a value difference bias of 0.07 and standard deviation of 1.55 breaths per minute with respect to the counted respiratory oscillations on the polysomnography device signals of the flow sensor as well as the abdominal and thoracic band evaluated on more than 21 hours of data from 13 different subjects during sleep. Similarly the novel heart rate extraction algorithm for processing the acoustic signals achieves a performance of 90.20% and 90.26% agreement with respect to heart rate value provided by the Konica-Minolta and SomnoMedics devices respec- tively evaluated on more than 57 hours of data acquired from 13 different subjects during sleep in the clinical trials. This is the largest dataset for acoustic heart sound classification and heart rate extraction in the literature to date. Overall, these results represent: a clear proof of concept for heart rate monitoring with the in-house developed wireless acoustic monitoring system; the addition of two very important monitoring capabilities to the wireless acoustic monitoring system; as well as significant contributions to the field of signal processing for both acoustic respiratory rate and heart rate monitoring.
4
Uggla, Lingvall Kristoffer. "Remote heart rate estimation by evaluating measurements from multiple signals." Thesis, KTH, Skolan för datavetenskap och kommunikation (CSC), 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-210303.
Full textAbstract:
Heart rate can say a lot about a person's health. While most conventional methods for heart rate measurement require contact with the subject, these are not always applicable. In this thesis, a non-invasive method for pulse detection is implemented and analyzed. Different signals from the color of the forehead—including the green channel, the hue channel and different ICA and PCA components—are inspected, and their resulted heart rates are weighted together according to the significance of their FFT peaks. The system is tested on videos with different difficulties regarding the amount of movement and setting of the scene. The results show that the approach of weighting measurements from different signals together has great potential. The system in this thesis, however, does not perform very well on videos with a lot of movement because of motion noise. Though, with better, less noisy signals, good results can be expected.En människas puls säger en hel del om dennes hälsa. För att mäta pulsenanvänds vanligtvis metoder som vidrör människan, vilket iblandär en nackdel. I det här examensarbetet tas en metod för pulsmätningpå avstånd fram, som endast använder klipp från en vanlig videokamera. Färgen i pannan mäts och utifrån den genereras flera signalersom analyseras, vilket resulterar i olika mätvärden för pulsen. Genomatt värdera dessa mätvärden med avseende på hur tydliga signalernaär, beräknas ett viktat medelvärde som ett slutgiltigt estimat på medelpulsen. Metoden testas på videoklipp med varierande svårighetsgrad,beroende på hur mycket rörelser som förekommer och på vilketavstånd från kameran försökspersonen står. Resultaten visar att metodenhar mycket god potential och att man kan man förvänta sig finaresultat med bättre, mindre brusiga signaler.
5
Häggmark, Sören. "Detection of myocardial ischemia : clinical and experimental studies with focus on vectorcardiography, heart rate and perioperative conditions /." Umeå : Kirurgisk och perioperativ vetenskap, 2005. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-598.
Full text
6
Häggmark, Sören. "Detection of myocardial ischemia : clinical and experimental studies with focus on vectorcardiography, heart rate and perioperative conditions." Doctoral thesis, Umeå universitet, Anestesiologi och intensivvård, 2005. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-598.
Full textAbstract:
Introduction. Multiple clinical methods for detecting myocardial ischemia are utilised in the hospital setting each day, but there is uncertainty about their diagnostic accuracy. In the operating room, multiple methods may be employed, while in the CCU advanced electrophysiological (ECG) techniques for myocardial ischemia detection, and in particular, ST segment analysis, are common. Vectorcardiography (VCG) is one form of ECG. Several conditions other than ischemia may cause marked ST changes, which can impair the process of diagnosis of clinical ischemia. Elevated HR is one of these factors, which is studied here. The hypotheses were about concordance of different methods to detect ischemia, and relation of ECG ST levels to HR with and without myocardial ischemia. Methods. Study I. Anesthetised vascular surgical patients with coronary artery disease were studied during the start of anesthesia and surgery: ECG, hemodynamic, mechanical, and metabolic parameters were measured and categorised as positive or negative with reference to a specific definition of myocardial ischemia. Study II. Awake patients with no ischemic heart disease were paced in graded steps, and VCG ST analyses were performed. Study III. Anesthetised pigs were studied for local metabolic and VCG ST changes related to controlled HR levels and transient coronary occlusion. Study IV. Thirty five anesthetised coronary artery disease (CAD) patients and ten non-CAD patients were paced at controlled levels, and great coronary artery vein (GCV) lactate measurement was used to determine presence or absence of myocardial ischemia. The CAD patients were paced up to HR levels where myocardial ischemia could be confirmed. The relation of HR-related VCG ST levels to presence or absence of ischemia was analysed. In Studies II,, III, and IV the ST vector magnitude (ST-VM), the change from baseline in ST-VM (STC-VM), and the vector angle change from baseline (STC-VA) were analysed for each step. Results. Study I. Poor concordance was demonstrated for positive events (presumed myocardial ischemia) between the hemodynamic, ECG, mechanical, and metabolic detection methods. Study II. STC-VM but not ST-VM levels demonstrated HR-related increases in the presumed absence of myocardial ischemia in 18 awake subjects. J point time to ST measurement did not affect the response of VCG ST to HR. Study III. STC-VM levels showed HR-related increases in the absence of ischemia (tested by local metabolic observations). VCG ST parameters responded positively to transient regional ischemia. Study IV. CAD patients, which demonstrated a clear pattern of onset and progress of ischemia during pacing, were further analysed for the relation of VCG ST level to ischemia. Sensitivity and specificity of STC-VM levels were described by ROC analysis for a range of STC-VM levels. Conclusions. Concordance of different measures for detection of onset of myocardial ischemia is difficult to assess in the absence of a very reliable reference method. The contribution of HR and ischemia to VCG ST levels were estimated in study subjects. HR-related increases in STC-VM occur in the absence of ischemia. HR levels need to be considered when interpreting STC-VM as a diagnostic test for ischemia. Further study is needed to establish criteria that take into account multiple clinical factors in order to improve the predictive value of our tests for myocardial ischemia.
7
Syed, Shah Nemath Farhan. "IMPLEMENTATION OF INTERACTIVE REMOTE PHYSIOLOGICAL MONITORING AND FEEDBACK TRAINING SYSTEM." University of Akron / OhioLINK, 2006. http://rave.ohiolink.edu/etdc/view?acc_num=akron1164666232.
Full text
8
Raymondi, Luis Guillermo Antezana, Fabricio Eduardo Aguirre Guzman, Jimmy Armas-Aguirre, and Paola Agonzalez. "Technological solution for the identification and reduction of stress level using wearables." IEEE Computer Society, 2020. http://hdl.handle.net/10757/656578.
Full textAbstract:
El texto completo de este trabajo no está disponible en el Repositorio Académico UPC por restricciones de la casa editorial donde ha sido publicado.In this article, a technological solution is proposed to identify and reduce the level of mental stress of a person through a wearable device. The proposal identifies a physiological variable: Heart rate, through the integration between a wearable and a mobile application through text recognition using the back camera of a smartphone. As part of the process, the technological solution shows a list of guidelines depending on the level of stress obtained in a given time. Once completed, it can be measured again in order to confirm the evolution of your stress level. This proposal allows the patient to keep his stress level under control in an effective and accessible way in real time. The proposal consists of four phases: 1. Collection of parameters through the wearable; 2. Data reception by the mobile application; 3. Data storage in a cloud environment and 4. Data collection and processing; this last phase is divided into 4 sub-phases: 4.1. Stress level analysis, 4.2. Recommendations to decrease the level obtained, 4.3. Comparison between measurements and 4.4. Measurement history per day. The proposal was validated in a workplace with people from 20 to 35 years old located in Lima, Peru. Preliminary results showed that 80% of patients managed to reduce their stress level with the proposed solution.
Revisión por pares
9
Vykoupil, Pavel. "Použití analýzy HRV pro automatickou detekci ischemie u izolovaného zvířecího srdce." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2014. http://www.nusl.cz/ntk/nusl-220564.
Full textAbstract:
This paper deals with HRV analysis, creating segments for this analysis, calculating HRV parameters and their classification for automatic detection of ischemia. First part of the work is dedicated to theoretical describtion of heart anatomy, ECG reading, its processing and methods of HRV analysis. Next part of this work outline the principle of creating segments used for calculation of HRV parameters. Last part of the work indtroduces classification of said parameters with the help of multilayered neural networks and finding their best possible setup based on least classification error and computing time achieved. Calculation of HRV parameters and classification was realized using software Matlab.
10
Doyen, Matthieu. "Méthodes probabilistes pour le monitoring cardio-respiratoire des nouveau-nés prématurés." Thesis, Rennes 1, 2018. http://www.theses.fr/2018REN1S049/document.
Full textAbstract:
La surveillance des nouveau-nés prématurés placés en unité de soins intensifs a conduit à la notion de monitoring et à l'acquisition de nombreux signaux physiologiques. Si ces informations sont bien utilisées pour le diagnostic et la prévention des situations d'urgence, force est de constater qu'à ce jour, elles le sont beaucoup moins dans un objectif prédictif. La difficulté d'extraction d'informations fiables en temps réel, sans aucun contrôle visuel, à partir de signaux non stationnaires, en est vraisemblablement la cause. Ce mémoire vise donc à proposer des méthodes robustes, adaptées au contexte des unités de soins intensifs néonatals et du temps réel. Pour cela, un ensemble de méthodes génériques appliquées à la variabilité cardiaque, mais capable d'être adaptées à d'autres constantes physiologiques telles que la respiration, ont été développées et testées en contexte clinique. Quatre grandes parties illustrent notre propos : - La proposition d'une méthode originale de détection temps réel probabiliste multicaractéristique permettant de répondre à une problématique d'extraction robuste d'événements d'intérêt à partir de signaux physiologiques bruités. Générique, cette solution est appliquée à la détection robuste du QRS d'un signal ECG. Elle est basée sur le calcul temps réel de plusieurs probabilités a posteriori, concernant les propriétés du signal, qui sont ensuite fusionnées au sein d'un nœud de décision reposant sur l'utilisation pondérée de la divergence de Kullback-Leibler. Comparée à deux méthodes classiques de la littérature sur deux bases de données bruitées, elle obtient un taux d'erreur de détection inférieur (20.91% vs 29.02% (ondelettes) et 33.08% (Pan-Tompkins) sur la base de test). - La proposition d'une méthode impliquant plusieurs modèles semi-markoviens cachés, visant la segmentation de périodes au sein desquelles le détecteur temps réel probabiliste multicaractéristique fournit les détections d'évènements les plus fiables. En comparaison à deux méthodes de la littérature, la solution proposée obtient de meilleures performances, le critère d‘erreur obtenu est significativement plus faible (entre -21.37% et -74.98% selon la base et l'approche évaluée). - La sélection d'un détecteur optimal pour le monitoring d'événements d'apnée-bradycardie, en termes de fiabilité et précocité, à partir de données ECG obtenues chez le nouveau-né. Les performances du détecteur retenu seront comparées aux alarmes générées par un dispositif industriel de suivi continu classiquement utilisé en service de néonatalogie (moniteur Philips IntelliVue). La méthode basée sur le changement abrupt de la moyenne des RR obtient les meilleurs résultats au regard du délai (3.99 s vs 11.53 s pour le moniteur IntelliVue) et de la fiabilité (critère d'erreur de 43.60% vs 80.40%). - La conception et le développement d'une plateforme logicielle SYNaPSE (SYstem for Noninvasive Physiological Signal Explorations) permettant l'acquisition de divers signaux physiologiques en très grande quantité, et de façon non invasive, au sein des unités de soins. La conception modulaire de cette plateforme, ainsi que ses propriétés temps réel, permettent l'intégration simple et rapide de méthodes de traitement du signal complexes. Son intérêt translationnel est montré dans le dépouillement d'une base de données cherchant à étudier l'impact de la bilirubine sur la variabilité cardiaqueThe surveillance of premature newborns placed in intensive care units led to the notion of monitoring and the acquisition of many physiological signals. While this information is well used for the diagnosis and prevention of emergency situations, it must be acknowledged that, to date, it is less the case for predictive purposes. This is mainly due to the difficulty of extracting reliable information in real time, without any visual control, from non-stationary signals. This thesis aims to propose robust methods, adapted to the context of neonatal intensive care units and real time. For this purpose, a set of generic methods applied to cardiac variability, but capable of being adapted to other physiological constants such as respiration, have been developed and tested in clinical context. Four main parts illustrate these points : - The proposal of an original multicharacteristic probabilistic real time detection method for robust detection of interest events of noisy physiological signals. Generic, this solution is applied to the robust QRS complex detection of the ECG signals. It is based on the real time calculation of several posterior probabilities of the signal properties before merging them into a decision node using the weighted Kullback-Leibler divergence. Compared to two classic methods from the literature on two noisy databases, it has a lower detection error rate (20.91% vs. 29.02% (wavelets) and 33.08% (Pan-Tompkins) on the test database). - The proposal of using hidden semi-markovian models for the segmentation of temporal periods with most reliable event detections. Compared to two methods from the literature, the proposed solution achieves better performance, the error criterion obtained is significantly lower (between -21.37% and -74.98% depending on the basis and approach evaluated). - The selection of an optimal detector for the monitoring of apnea-bradycardia events, in terms of reliability and precocity, based on ECG data obtained from newborns. The performance of the selected detector will be compared to the alarms generated by an industrial continuous monitoring device traditionally used in neonatology service (Philips IntelliVue monitor). The method based on the abrupt change of the RR average achieves the best results in terms of time (3.99 s vs. 11.53 s for the IntelliVue monitor) and reliability (error criterion of 43.60% vs. 80.40%). - The design and development of SYNaPSE (SYstem for Noninvasive Physiological Signal Explorations) software platform for the acquisition of various physiological signals in large quantities, and in a non-invasive way, within the care units. The modular design of this platform, as well as its real time properties, allows simple and fast integration of complex signal processing methods. Its translational interest is shown in the analysis of a database in order to study the impact of bilirubin on cardiac variability
11
Macková, Pavlína. "EKG biofeedback." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2012. http://www.nusl.cz/ntk/nusl-219742.
Full textAbstract:
The master’s thesis is focused on the possibilities of measuring heart rate of ECG signal and its use in therapeutic game of ECG biofeedback. This thesis describes the way of measuring ECG with acquisition unit Biopac and analyzes signal processing for measurement of heart rate – algorithms of QRS detection, HRV analysis. Realisation of therapeutic is designed for applications in Matlab.
12
Dizon, Lucas, and Martin Johansson. "Atrial Fibrillation Detection Algorithm Evaluation and Implementation in Java." Thesis, KTH, Skolan för teknik och hälsa (STH), 2014. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-158878.
Full textAbstract:
Atrial fibrillation is a common heart arrhythmia which is characterized by a missing or irregular contraction of the atria. The disease is a risk factor for other more serious diseases and the total medical costs in society are extensive. Therefore it would be beneficial to improve and optimize the prevention and detection of the disease. Pulse palpation and heart auscultation can facilitate the detection of atrial fibrillation clinically, but the diagnosis is generally confirmed by an ECG examination. Today there are several algorithms that detect atrial fibrillation by analysing an ECG. A common method is to study the heart rate variability (HRV) and by different types of statistical calculations find episodes of atrial fibrillation which deviates from normal sinus rhythm. Two algorithms for detection of atrial fibrillation have been evaluated in Matlab. One is based on the coefficient of variation and the other uses a logistic regression model. Training and testing of the algorithms were done with data from the Physionet MIT database. Several steps of signal processing were used to remove different types of noise and artefacts before the data could be used. When testing the algorithms, the CV algorithm performed with a sensitivity of 91,38%, a specificity of 93,93% and accuracy of 92,92%, and the results of the logistic regression algorithm was a sensitivity of 97,23%, specificity of 93,79% and accuracy of 95,39%. The logistic regression algorithm performed better and was chosen for implementation in Java, where it achieved a sensitivity of 97,31%, specificity of 93,47% and accuracy of 95,25%.Förmaksflimmer är en vanlig hjärtrytmrubbning som kännetecknas av en avsaknad eller oregelbunden kontraktion av förmaken. Sjukdomen är en riskfaktor för andra allvarligare sjukdomar och de totala kostnaderna för samhället är betydande. Det skulle därför vara fördelaktigt att effektivisera och förbättra prevention samt diagnostisering av förmaksflimmer. Kliniskt diagnostiseras förmaksflimmer med hjälp av till exempel pulspalpation och auskultation av hjärtat, men diagnosen brukar fastställas med en EKG-undersökning. Det finns idag flertalet algoritmer för att detektera arytmin genom att analysera ett EKG. En av de vanligaste metoderna är att undersöka variabiliteten av hjärtrytmen (HRV) och utföra olika sorters statistiska beräkningar som kan upptäcka episoder av förmaksflimmer som avviker från en normal sinusrytm. I detta projekt har två metoder för att detektera förmaksflimmer utvärderats i Matlab, en baseras på beräkningar av variationskoefficienten och den andra använder sig av logistisk regression. EKG som kommer från databasen Physionet MIT används för att träna och testa modeller av algoritmerna. Innan EKG-signalen kan användas måste den behandlas för att ta bort olika typer av brus och artefakter. Vid test av algoritmen med variationskoefficienten blev resultatet en sensitivitet på 91,38%, en specificitet på 93,93% och en noggrannhet på 92,92%. För logistisk regression blev sensitiviteten 97,23%, specificiteten 93,79% och noggrannheten 95,39%. Algoritmen med logistisk regression presterade bättre och valdes därför för att implementeras i Java, där uppnåddes en sensitivitet på 91,31%, en specificitet på 93,47% och en noggrannhet på 95,25%.
13
Sandri, Gustavo Luiz. "Automated non-contact heart rate measurement using conventional video cameras." reponame:Repositório Institucional da UnB, 2016. http://dx.doi.org/10.26512/2016.02.D.21118.
Full textAbstract:
Dissertação (mestrado)—Universidade de Brasília, Faculdade de Tecnologia, Departamento de Engenharia Elétrica, 2016.Conforme o sangue flui através do corpo de um indivíduo, ele muda a forma como a luz é irradiada pela pele, pois o sangue absorve luz de forma diferente dos outros tecidos. Essa sutil variação pode ser capturada por uma câmera e ser usada para monitorar a atividade cardíaca de uma pessoa. O sinal capturado pela câmera é uma onda que representa as variações de tonalidade da pele ao longo do tempo. A frequência dessa onda é a mesma frequência na qual o coração bate. Portanto, o sinal capturado pela câmera pode ser usado para estimar a taxa cardíaca de uma pessoa. Medir o pulso cardíaco remotamente traz mais conforto pois evita o uso de eletrodos. Também permite o monitoramento de uma pessoa de forma oculta para ser empregado em um detector de mentira, por exemplo. Neste trabalho nós propomos dois algoritmos para a estimação da taxa cardíaca sem contato usando câmeras convencionais sob iluminação não controlada. O primeiro algoritmo proposto é um método simples que emprega um detector de face que identifica a face da pessoa sendo monitorada e extrai o sinal gerado pelas mudanças no tom da pele devido ao fluxo sanguíneo. Este algoritmo emprega um filtro adaptativo para aumentar a energia do sinal de interesse em relação ao ruído. Nós mostramos que este algoritmo funciona muito bem para vídeos com pouco movimento. O segundo algoritmo que propomos é uma melhora do primeiro para torná-lo mais robusto a movimentos. Nós modificamos o método usado para definir a região de interesse. Neste algoritmo é utilizado um detector de pele para eliminar pixels do plano de fundo do vídeo, os frames dos vídeos são divididos em micro-regiões que são rastreados com um algoritmo de fluxo ótico para compensar os movimentos e um algoritmo de clusterização é aplicado para selecionar automaticamente as melhores micro-regiões para efetuar a estimação da taxa cardíaca. Propomos também um esquema de filtragem temporal e espacial para reduzir o ruído introduzido pelo algoritmo de fluxo ótico. Comparamos os resultados dos nossos algoritmos com um oxímetro de dedo comercial e mostramos que eles funcionam bem para situações desafiadoras.
As the blood flows through the body of an individual, it changes the way that light is irradiated by the skin, because blood absorbs light differently than the remaining tissues. This subtle variation can be captured by a camera and be used to monitor the heart activity of a person. The signal captured by the camera is a wave that represents the changes in skin tone along time. The frequency of this wave is the same as the frequency by which the heart beats. Therefore, the signal captured by the camera could be used to estimate a person’s heart rate. This remote measurement of cardiac pulse provides more comfort as it avoids the use of electrodes or others devices attached to the body. It also allows the monitoring of a person in a canceled way to be employed in lie detectors, for example. In this work we propose two algorithms for non-contact heart rate estimation using conventional cameras under uncontrolled illumination. The first proposed algorithm is a simple approach that uses a face detector to identify the face of the person being monitored and extract the signal generated by the changes in the skin tone due to the blood flow. This algorithm employs an adaptive filter to boost the energy of the interest signal against noise. We show that this algorithm works very well for videos with little movement. The second algorithm we propose is an improvement of the first one to make it more robust to movements. We modify the approach used to define the region of interest. In this algorithm we employ a skin detector to eliminate pixels from the background, divide the frames in microregions that are tracked using an optical flow algorithm to compensate for movements and we apply a clustering algorithm to automatically select the best micro-regions to use for heart rate estimation. We also propose a temporal and spatial filtering scheme to reduce noise introduced by the optical flow algorithm. We compared the results of our algorithms to an off-the-shelf fingertip pulse oximeter and showed that they can work well under challenging situations.
14
Gaszczyk, Dariusz. "Wearable Assistant For Monitoring Solitary People." Thesis, Blekinge Tekniska Högskola, Institutionen för tillämpad signalbehandling, 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-14592.
Full textAbstract:
Master Thesis presents the system consisting of software and components of Arduinoplatform along with modules compatible with it, intended for use indoor. The device fulfils thefollowing requirements which are: to ensure privacy preservation, low energy consumptionand the wireless nature. This thesis reports the development of a prototype that would ensure step detection,posture detection, indoor localization, tumble detection and heart rate detection using themicrocontroller, AltIMU-10 v4 module, heart rate monitor, WiFi module and battery. Veryimportant part of the thesis is algorithm, which uses comparison function. Thanks to thewireless nature of a prototype, the system collects data regardless of an environment and sendthem directly to every device supported by Microsoft Windows platform, Linux platform orOS X platform, which are monitored by the supervisor, who takes care of the solitary person. The main contributions of the prototype are: indoor localization, identification andclassification of occurring situations and monitoring vital signs of the solitary person. To ensure indoor localization the prototype must collect data from accelerometer. Ofcourse data from AltIMU-10 v4 module in basic form are useless for the supervisor, so thealgorithm, using by the prototype, is programmed to processing and filtering it. Algorithm is also used to identification and classification occurring situations. Datafrom accelerometer are processed by it and compared with the created pattern. Monitoring vital signs of the solitary person are more complicated function, because itrequires not only data from accelerometer, but also from heart rate monitor. This sensor isusing to the analyzing condition of the patient when dangerous situation occurs.
15
Chakraborty, Prithwi Raj. "Detecting viewer interest in video using facial and heart rate responses." Thesis, Queensland University of Technology, 2017. https://eprints.qut.edu.au/108023/1/Prithwi%20Raj_Chakraborty_Thesis.pdf.
Full textAbstract:
This project investigates different methodologies to understand and quantify interest and engagement evoked in viewers. Interest is difficult to measure due to its subtleness, dependence over personal preference and viewed content. This project uses machine intelligence to measure interest in response to sports and movie videos. The findings of this project can be applied and extended in several fields including but not limited to teaching and learning, multimedia, and human computer interaction.
16
Lasanen, K. (Kimmo). "Integrated analogue CMOS circuits and structures for heart rate detectors and other low-voltage, low-power applications." Doctoral thesis, Oulun yliopisto, 2011. http://urn.fi/urn:isbn:9789514294556.
Full textAbstract:
Abstract This thesis describes the development of low-voltage, low-power circuit blocks and structures for portable, battery-operated applications such as heart rate detectors, pacemakers and hearing-aid devices. In this work, the definition for low supply voltage operation is a voltage equal to or less than the minimum supply voltage needed to operate an analogue switch, i.e. VDD(min) ≤ 2VT + Vov, which enables the use of a single cell battery whose polar voltage is 1 – 1.5 V. The targeted power consumption is in a range of microwatts. The design restrictions for analogue circuit design caused by the low supply voltage requirement of the latest and future CMOS process technologies were considered and a few circuit blocks, namely two operational amplifiers, a Gm–C filter and a bandgap voltage reference circuit, were first designed to investigate their feasibility for the above-mentioned low-voltage and low-power environment. Two operational amplifiers with the same target specifications were designed with two different types of input stages, i.e. a floating-gate and a bulk-driven input stage, in order to compare their properties. Based on the experiences collected from the designed circuit blocks, an analogue CMOS preprocessing stage for a heart rate detector and a self-calibrating RC oscillator for clock and resistive/capacitive sensor applications were designed, manufactured and tested. The analogue preprocessing stage for a heart rate detector includes a continuous-time offset-compensated preamplifier with a gain of 40 dB, an 8th-order switched-opamp switched-capacitor bandpass filter, a 32-kHz crystal oscillator and a bias circuit, and it achieves the required performance with a supply voltage range of 1.0 – 1.8 V and a current consumption of 3 μA. The self-calibrating RC oscillator operates with supply voltages of 1.2 – 3.0 V and achieves a tunable frequency range of 0.2 – 150 MHz with a total accuracy of ±1% within a supply voltage range of 1.2 – 1.5 V, a temperature range from -20 to 60 °C and a current consumption of less than 70 μA @ 5 MHz with external high precision resistor and capacitor. The measurement results prove that the developed low-voltage low-power analogue circuit structures can achieve the required performance and therefore be successfully implemented with modern CMOS process technologies with limited supply voltagesTiivistelmä Tämä väitöskirja käsittelee matalan käyttöjännitteen pienitehoisten piirirakenteiden kehittämistä kannettaviin, paristokäyttöisiin sovelluksiin kuten esimerkiksi sykemittareihin, sydämen tahdistimiin ja kuulolaitteisiin. Matalalla käyttöjännitteellä tarkoitetaan jännitettä, joka on pienempi tai yhtäsuuri kuin analogisen kytkimen tarvitsema pienin mahdollinen käyttöjännite, VDD(min) ≤ 2VT + Vov, joka mahdollistaa piirin toiminnan yhdellä paristolla, jonka napajännite on 1 – 1,5 V. Tavoiteltu tehonkulutus on mikrowattiluokkaa. Piirirakenteiden suunnittelussa otettiin huomioon viimeisimpien ja lähitulevaisuuden CMOS-valmistusteknologioiden aiheuttamat matalan käyttöjännitteen erityisvaatimukset ja niiden pohjalta kehitettiin aluksi kaksi erilaista operaatiovahvistinta, GmC-suodatin, ja bandgap-jännitereferenssi. Operaatiovahvistimet toteutettiin samoin tavoitevaatimuksin kahdella eri tekniikalla käyttäen toisen vahvistimen tuloasteessa ns. kelluvahilaisia tulotransistoreita ja toisen tuloasteessa ns. allasohjattuja tulotransistoreita. Kehitetyistä rakenteista saatujen kokemusten pohjalta suunniteltiin, valmistettiin ja testattiin kaksi erilaista CMOS-teknologialla toteutettua mikropiiriä, jotka olivat analoginen esikäsittelypiiri sydämen sykkeen mittaukseen ja itsekalibroiva RC-oskillaattori resistiivisiin/kapasitiivisiin sensorisovelluksiin. Sydämen sykkeen esikäsittelypiiri sisältää jatkuva-aikaisen, offset-kompensoidun esivahvistimen, jonka vahvistus on 40 dB, kytketyistä kapasitansseista ja kytketyistä operaatiovahvistimista koostuvan kahdeksannen asteen kaistanpäästösuodattimen, 32 kHz kideoskillaattorin ja bias-piirin. Esikäsittelypiiri saavuttaa vaadittavan suorituskyvyn 1,0 – 1,8 V käyttöjännitteellä ja 3 μA virrankulutuksella. Itsekalibroivan RC-oskillaattorin käyttöjännitealue puolestaan on 1,2 – 3,0 V ja käyttökelpoinen taajuusalue 0,2 – 150 MHz. Ulkoista tarkkuusvastusta ja kondensaattoria käytettäessä oskillaattori saavuttaa ±1 % tarkkuuden 1,2 – 1,5 V käyttöjännitteillä ja -20 – 60 °C lämpötila-alueella virrankulutuksen jäädessä alle 70 μA @ 5 MHz. Mittaustulokset osoittavat, että kehitetyt matalan käyttöjännitteen pienitehoiset analogiset rakenteet saavuttavat vaadittavan suorituskyvyn ja voidaan näin ollen menestyksekkäästi valmistaa moderneilla matalan käyttöjännitteen CMOS-teknologioilla
17
Fernandes, Patrícia Pinheiro Jervis. "Estudo do impacto do maneio na fertilidade de bovinos leiteiros da Irlanda." Master's thesis, Universidade Técnica de Lisboa. Faculdade de Medicina Veterinária, 2011. http://hdl.handle.net/10400.5/3578.
Full textAbstract:
Dissertação de Mestrado Integrado em Medicina VeterináriaO declínio da fertilidade que se tem sentido no sector leiteiro tem suscitado uma crescente preocupação e busca de soluções por parte dos produtores. Assim sendo, o papel do Médico Veterinário como conselheiro e fornecedor de respostas sobre performance reprodutiva tem aumentado consideravelmente. Neste trabalho foram estudadas 327 vacas de quatro explorações leiteiras do condado de Kildare, República da Irlanda, que praticavam sistemas de produção sazonais (Primavera) em regime semi-extensivo. Estes produtores solicitaram a ajuda dos Veterinários da UCD para melhorar a fertilidade dos seus efectivos. Através da análise de rigorosos registos produtivos e reprodutivos, foi possível constatar que os parâmetros que maior influência exerceram na taxa de gestação foram o valor genético – Economic Breeding Index (p < 0,01), a produção leiteira (p < 0,05) e a perda máxima de condição corporal após o parto (p < 0,05). Recorrendo a um modelo de regressão binomial com estas três variáveis foi possível calcular a probabilidade de um animal ficar gestante, para uma sensibilidade de 99 % e especificidade de 5,9 %. Dado que a fertilidade é uma parâmetro multifactorial, deveriam ter sido estudadas outras variáveis para completar este modelo. Foi também detectada uma grave falha da detecção de estro em três das quatro explorações. Nestas, os intervalos entre repetições de serviços foram anormais e muitos dos animais que os produtores referiam como em anestro estavam de facto a ciclar. Com este estudo conseguiu-se demonstrar aos produtores a importância do maneio na melhoria da fertilidade, através da compilação de relatórios com os resultados obtidos dos registos. Numa reunião com todos os produtores foram fornecidos conselhos e desencorajadas medidas menos correctas.
ABSTRACT - Study of the impact of management on Irish dairy cattle fertility - The trend towards infertility in the dairy industry has raised concerns and has made farmers actively search for solutions. Therefore, the Veterinary, as a counselor and source of answers about reproductive performance has become essential. The sample of this study consisted of 327 dairy cows from four Irish farms, co. Kildare, practicing seasonal calving in the Spring. All of them solicited the help of the UCD Veterinary team in order to improve their herd’s fertility. After analyzing meticulously the productive and reproductive records, it was clear that the factors which affected the pregnancy rate the most were the Economic Breeding Index (p < 0,01), the 305 days milk yeld (p < 0,05) and the maximum body condition score loss after calving (p < 0,05). Using a binomial regression model with these three variables, a formula to calculate the probability of a cow to become pregnant was created, with a sensibility of 99 % and specificity of 5,9%. Since fertility is a multifactorial parameter, other variables could have been included in the study in order to make it more accurate. A serious inaccuracy on heat detection was found on three of the four farms. These had abnormal interval service repeats and most of the animals tagged as anestrus were in fact cycling. With this study the impact of management on the improvement of fertility was evident to the farmers, as the final year reports were very clear about the results and outcomes. On a brief discussion, the veterinary team told the farmers which methods to use and which to abandon.
18
Olšanská, Eva. "Analýza arytmií v experimentálních záznamech EKG." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2016. http://www.nusl.cz/ntk/nusl-241093.
Full textAbstract:
This diploma thesis deals with analysis of electrograms recorded from isolated rat hearts. In theoretical part, basic principles of electrocardiography and differences between rat and human EG records are described. Types of arrhythmias and methods for classification and quantification of arrhythmias are also described. Examples of pathologies found during the manual classification and results of the analysis of the QTc interval duration are presented. An occurrence of premature beats is then compared between experimental groups. Finally, the method used for the automatic analysis of electrograms including the graphical user interface is described and the results of its evaluation using real data are presented
19
Máca, Kamil. "Kardiotachometr." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2010. http://www.nusl.cz/ntk/nusl-218654.
Full textAbstract:
This masters thesis describes possibilities of a heart rate measuring. Several methods of measuring will be discussed. The primary objective of this paper is to design battery powered cardiotachometr with a range of 30-240 beats/min and a low battery indication. Cardiotachometer uses the R waves detector to measure heart rate. This thesis is focused on creation of the block diagram, electrical circuit, printed circuit and calculation of electronic device used in cardiotachometers.
20
Lucena, Gonçalo Maria D'Aguiar de. "Tendências na evolução da fertilidade em explorações de bovinos leiteiros em Gloucestershire." Bachelor's thesis, Universidade Técnica de Lisboa. Faculdade de Medicina Veterinária, 2008. http://hdl.handle.net/10400.5/940.
Full textAbstract:
Dissertação de Mestrado Integrado em Medicina VeterináriaA fertilidade é um factor de extrema importância económica nas explorações de bovinos leiteiros. Nas últimas décadas tem-se observado, à escala mundial, uma diminuição da fertilidade aparentemente associada ao aumento da produção leiteira, e que ao ser contrariada, poderá contribuir para uma melhoria do desempenho económico das explorações. O intervalo entre partos ajustado é um índice que representa, de alguma forma, o impacto que essa diminuição da fertilidade tem na economia da exploração, mas outros índices, como as taxas de gestação e de detecção de estro tem que ser avaliadas para melhor compreensão dos problemas de fertilidade das explorações. Utilizando dados de campo, recolhido tanto pelos produtores como pelos veterinários do Wood Veterinary Group, avaliou-se o desempenho reprodutivo das explorações de bovinos leiteiros da região de Gloucestershire, no Reino Unido, utilizando uma variedade de índices. Observou-se que, entre 1984 e 2006, houve, em concordância com outros estudos, uma diminuição do desempenho reprodutivo, com base em quase todos os parâmetros estudados. Observou-se também que a taxa de detecção de cios diminuiu mais do que a taxa de gestação ao 1º serviço e a taxa de gestação global. Porém, a diminuição destas duas últimas pode estar relacionada com a diminuição da taxa de detecção de cios e que, por sua vez, contribui também para o alongamento do intervalo partoconcepção e do intervalo entre partos. É, portanto, importante desenvolver métodos mais eficientes e precisos de detecção de cio que ajudem a contrariar a tendência actual da fertilidade. Para isso, é também necessário utilizar estratégias nutricionais, hormonais e genéticas.
ABSTRACT Fertility is an extremely important issue in dairy farming economics. Over the last decades a decline in fertility in dairy cattle, associated with increasing milk yields, has been reported. Reverting this trend would improve dairy farming economic performance. Adjusted calving interval is a good index for fertility assessment, but other parameters should be used to investigate fertility problems. Reproductive performance was assessed in dairy farms in Gloucestershire, United Kingdom, using field data collected by farmers and Wood Veterinary Group veterinarians. Likewise in other studies data, there was a decrease in reproductive performance between 1984 and 2006, in virtually all parameters studied. Heat detection decreased more than the pregnancy rate, and the decrease observed in the latter might be related to decreasing heat detection accuracy. Increases in calving-conception and calving intervals are also related to declining heat detection rates. It’s important to develop new heat detection methods to revert the actual trend in fertility. Nutritional, endocrine therapy and genetic approaches will also be helpful.
21
Wåhlin, Peter. "Enhanching the Human-Team Awareness of a Robot." Thesis, Mälardalens högskola, Akademin för innovation, design och teknik, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-16371.
Full textAbstract:
The use of autonomous robots in our society is increasing every day and a robot is no longer seen as a tool but as a team member. The robots are now working side by side with us and provide assistance during dangerous operations where humans otherwise are at risk. This development has in turn increased the need of robots with more human-awareness. Therefore, this master thesis aims at contributing to the enhancement of human-aware robotics. Specifically, we are investigating the possibilities of equipping autonomous robots with the capability of assessing and detecting activities in human teams. This capability could, for instance, be used in the robot's reasoning and planning components to create better plans that ultimately would result in improved human-robot teamwork performance. we propose to improve existing teamwork activity recognizers by adding intangible features, such as stress, motivation and focus, originating from human behavior models. Hidden markov models have earlier been proven very efficient for activity recognition and have therefore been utilized in this work as a method for classification of behaviors. In order for a robot to provide effective assistance to a human team it must not only consider spatio-temporal parameters for team members but also the psychological.To assess psychological parameters this master thesis suggests to use the body signals of team members. Body signals such as heart rate and skin conductance. Combined with the body signals we investigate the possibility of using System Dynamics models to interpret the current psychological states of the human team members, thus enhancing the human-awareness of a robot.Användningen av autonoma robotar i vårt samhälle ökar varje dag och en robot ses inte längre som ett verktyg utan som en gruppmedlem. Robotarna arbetar nu sida vid sida med oss och ger oss stöd under farliga arbeten där människor annars är utsatta för risker. Denna utveckling har i sin tur ökat behovet av robotar med mer människo-medvetenhet. Därför är målet med detta examensarbete att bidra till en stärkt människo-medvetenhet hos robotar. Specifikt undersöker vi möjligheterna att utrusta autonoma robotar med förmågan att bedöma och upptäcka olika beteenden hos mänskliga lag. Denna förmåga skulle till exempel kunna användas i robotens resonemang och planering för att ta beslut och i sin tur förbättra samarbetet mellan människa och robot. Vi föreslår att förbättra befintliga aktivitetsidentifierare genom att tillföra förmågan att tolka immateriella beteenden hos människan, såsom stress, motivation och fokus. Att kunna urskilja lagaktiviteter inom ett mänskligt lag är grundläggande för en robot som ska vara till stöd för laget. Dolda markovmodeller har tidigare visat sig vara mycket effektiva för just aktivitetsidentifiering och har därför använts i detta arbete. För att en robot ska kunna ha möjlighet att ge ett effektivt stöd till ett mänskligtlag måste den inte bara ta hänsyn till rumsliga parametrar hos lagmedlemmarna utan även de psykologiska. För att tyda psykologiska parametrar hos människor förespråkar denna masteravhandling utnyttjandet av mänskliga kroppssignaler. Signaler så som hjärtfrekvens och hudkonduktans. Kombinerat med kroppenssignalerar påvisar vi möjligheten att använda systemdynamiksmodeller för att tolka immateriella beteenden, vilket i sin tur kan stärka människo-medvetenheten hos en robot.
The thesis work was conducted in Stockholm, Kista at the department of Informatics and Aero System at Swedish Defence Research Agency.
22
Herrmann, Théodore. "Centrales de mesures numériques, longue durée, portables pour l'acquisition de signaux physiologiques." Saint-Etienne, 1988. http://www.theses.fr/1988STET4011.
Full textAbstract:
Le premier appareil est un ensemble de détection portable pour la médecine nucléaire. Il permet de compter des rayons gamma, sur deux voies suivant une période d'échantillonnage variable et durant plus de 24 heures. Le second appareil mesure 4 paramètres (fréquence cardiaque, activité, températures ambiante et cutanée) durant plus de 15 jours
23
Zaylaa, Amira. "Analyse et extraction de paramètres de complexité de signaux biomédicaux." Thesis, Tours, 2014. http://www.theses.fr/2014TOUR3315/document.
Full textAbstract:
L'analyse de séries temporelles biomédicales chaotiques tirées de systèmes dynamiques non-linéaires est toujours un challenge difficile à relever puisque dans certains cas bien spécifiques les techniques existantes basées sur les multi-fractales, les entropies et les graphes de récurrence échouent. Pour contourner les limitations des invariants précédents, de nouveaux descripteurs peuvent être proposés. Dans ce travail de recherche nos contributions ont porté à la fois sur l’amélioration d’indicateurs multifractaux (basés sur une fonction de structure) et entropiques (approchées) mais aussi sur des indicateurs de récurrences (non biaisés). Ces différents indicateurs ont été développés avec pour objectif majeur d’améliorer la discrimination entre des signaux de complexité différente ou d’améliorer la détection de transitions ou de changements de régime du système étudié. Ces changements agissant directement sur l’irrégularité du signal, des mouvements browniens fractionnaires et des signaux tirés du système du Lorenz ont été testés. Ces nouveaux descripteurs ont aussi été validés pour discriminer des fœtus en souffrance de fœtus sains durant le troisième trimestre de grossesse. Des mesures statistiques telles que l’erreur relative, l’écart type, la spécificité, la sensibilité ou la précision ont été utilisées pour évaluer les performances de la détection ou de la classification. Le fort potentiel de ces nouveaux invariants nous laisse penser qu’ils pourraient constituer une forte valeur ajoutée dans l’aide au diagnostic s’ils étaient implémentés dans des logiciels de post-traitement ou dans des dispositifs biomédicaux. Enfin, bien que ces différentes méthodes aient été validées exclusivement sur des signaux fœtaux, une future étude incluant des signaux tirés d’autres systèmes dynamiques nonlinéaires sera réalisée pour confirmer leurs bonnes performancesThe analysis of biomedical time series derived from nonlinear dynamic systems is challenging due to the chaotic nature of these time series. Only few classical parameters can be detected by clinicians to opt the state of patients and fetuses. Though there exist valuable complexity invariants such as multi-fractal parameters, entropies and recurrence plot, they were unsatisfactory in certain cases. To overcome this limitation, we propose in this dissertation new entropy invariants, we contributed to multi-fractal analysis and we developed signal-based (unbiased) recurrence plots based on the dynamic transitions of time series. Principally, we aim to improve the discrimination between healthy and distressed biomedical systems, particularly fetuses by processing the time series using our techniques. These techniques were either validated on Lorenz system, logistic maps or fractional Brownian motions modeling chaotic and random time series. Then the techniques were applied to real fetus heart rate signals recorded in the third trimester of pregnancy. Statistical measures comprising the relative errors, standard deviation, sensitivity, specificity, precision or accuracy were employed to evaluate the performance of detection. Elevated discernment outcomes were realized by the high-order entropy invariants. Multi-fractal analysis using a structure function enhances the detection of medical fetal states. Unbiased cross-determinism invariant amended the discrimination process. The significance of our techniques lies behind their post-processing codes which could build up cutting-edge portable machines offering advanced discrimination and detection of Intrauterine Growth Restriction prior to fetal death. This work was devoted to Fetal Heart Rates but time series generated by alternative nonlinear dynamic systems should be further considered
24
Wang, Xiaoyue 1978. "CMOS IC implementation of heart rate detection hardware." Thesis, 2006. http://hdl.handle.net/10125/20561.
Full text
25
Yamada, Shuhei. "Compact doppler radar system for heart rate detection." Thesis, 2007. http://hdl.handle.net/10125/20565.
Full text
26
Wang, Sheng-Wei, and 王聖維. "Application of Near Infrared Heart Rate Detection System." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/q8ps5a.
Full textAbstract:
碩士國立臺北科技大學
電子工程系研究所
104
In recent year, traditional contact instruments are the gold standrad techniques for measurement of the heart rate. But traditional contact measurement instruments can cause a lot of inconvenience. Current, Non-Contact Imaging Photoplethysmography (iPPG) have been proven to feasible measurement vital signs. Non-Contact measurments can provide a more comfortable physiological assessment ,and alos more suitable for long-term monitoring at home or hospital medical care. However now it susceptible to limit ambient light intensity. In this paper, we will use near-infrared (NIR) characteristics and image processing overcome this problem. With near-infrared spectrum as a dedicated light source to penetrate through the skin. Using Python5000 Gen3 image sensor camera, constitute of a non-invasive, non-contact measurement system. Further more system measure the distance to reach 1.2 meters away and reducing ambient lighting effects heart rate measurement. Image processing conversion in RAW data format, by using discrete wavelet transform (DWT) fast segmentation image in to different frequency bands. It is for Eulerian Magnification (EM) to process image for visualizing variation of the human pluse recorded by image sensor. After finite impulse filter (FIR), heart pulse is filtered waveform signal. This paper presents an approch to reduce the ambient light of non-contact Imaging Photoplethysmography heart rate measurement system. As a result of Bland Altman value analysis with traditional contact heart rate measurement the mean difference 1.1, and compare with the commercially high-end webcam raised the mean difference 2.8, which includes accurate measurements make it a relatively broad application.
27
Liu, Hsiang-Chi, and 劉湘琦. "Heart Rate Detection Based on Facial Feature Points Tracking." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/sqj8n7.
Full textAbstract:
碩士國立雲林科技大學
資訊工程系
106
According to the 2016 statistics of causes of death (Taiwan Ministry of Health and Welfare), cardiovascular diseases(CVD) is the second leading cause of death. With the aging of population and the declined in the average age of suffering cardiovascular diseases, the prevention of the CVD has received more and more attentions. In recent years, with the improvement of photographic equipment and computer’s computational efficiency, there are many non-contact heartbeat detection technologies based on image had been proposed. However, their performances are suffering from the influences under complex environment such as illumination changes, and non-frontal face. In order to provide people can examine the body information in normal time, and achieve the prevention and reduce the chance of CVD, this thesis proposed a non-contact heart rate detection method. A regression tree was applied to located facial feature points, and tracked its trajectory. Then, the FastICA was used to separate blind source. The most appropriate channel for frequency domain analysis, and calculate heart rate. Experimental results showed that the accuracy of the proposed method is about 97.2%.
28
Chen, Chien-Hao, and 陳建豪. "Real-Time Face Detection with Remote Heart Rate Measurement." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/dwdx34.
Full textAbstract:
碩士國立交通大學
電子研究所
107
Face is one of the most frequently appearing objects in realistic world. Many applications with great potentialities such as face ID are now becoming more popular topics. However, those applications based on face region still need to obtain the face position in the image or video first, making face detection become a common issue. With a fast and accurate face detection model, the limitation in some moreover applications will not be too much. Several studies have shown a good performance with deep learning models but the overall inference are not quite effective. In this thesis, we refer to MTCNN [1] as our basic face detection model. In order to gain more speedup, several methods such as model simplification, complicated equation approximation and weight quantization have been applied to the original MTCNN. Finally, to achieve real-time face detection with competitive energy-efficiency, our face detection model can be 106 times faster and model size 3.6 times smaller comparing to the original MTCNN running on Andes Technology RISC-V embedding system, and accuracy on FDDB [3] dataset can still reach 0.8259 at FPPI 0.01 which also outperforms the state of the art (0.8188), making our proposal very suitable for Intelligent IoT devices. Furthermore, based on MTCNN, a deeper application: remote heart rate measurement via camera facial video with this face detection system has also been proposed. Heart rate is an important indicator which can show the physiological state of a subject. However the traditional heart rate measurement method requires body contact, subject needs to hold the electrodes to obtain the ECG signal, making more limitations to some deeper applications. Hence, based on MTCNN and the remote heart rate extraction method from [2], we propose a more accurate heart rate measurement system from camera facial video. Also we have collected a dataset to test our system performance. Total heart rate error can be reduced to 5.73 bpm, which is also better than the original method (17.70 bpm) on our testing dataset.
29
Lin, You-Wei, and 林侑緯. "Development of an Android-Based Heart Rate Abnormality Detection System." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/7j27fv.
Full textAbstract:
碩士國立臺北科技大學
電機工程系研究所
101
Nowadays, a great number of people suffer from cardiovascular diseases due to busy work and big life pressures. Therefore, how to apply technology to help people monitor their health has received much attention in recent years. This study aims to develop a heart rate abnormality detection system by using Android-based mobile devices, which consists of ECG acquisition circuit, QRS complex detection, and heart rate abnormality detection algorithms. This system can not only help people monitor their health anytime and anywhere, but also detect their symptoms of heart rate abnormalities as early as possible, thus avoiding sudden death. The proposed system has been verified by employing the MIT-BIH database to detect 5 categories of arrhythmia, which are Premature Atrial Contraction Beat (PACB), Premature Ventricular Contraction Beat (PVCB), Fusion of Paced and Normal Beat (FB), Second-Degree Atrioventricular Block (2o A-V Block), and Ventricular Escape Beats (VB) and achieved a detection accuracy of 97 %, which demonstrates practical potential of the proposed system.
30
Chan, Ya-yen, and 詹亞燕. "A Study of Fatigue Detection Based on Heart Rate Variability." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/352hyx.
Full textAbstract:
碩士國立臺灣科技大學
電子工程系
102
Most people often appear fatigued and dulled response during the long time drive. If drivers do not stop and take a rest immediately, it would cause a serious accident. Therefore, this paper focuses on the correlation between fatigue and heart rate variability. We observe the physiological changes from general state to fatigue states.This paper extracts the heart rate variability signal by ECG signal. According international standards, we compute heart rate variability in time domain and frequency domain parameters. In the frequency domain, we convert the heart rate variability to frequency domain by FFT (Fast Fourier Transform) and draw PSD (Power Spectral Density) figure. We use time domain and frequency domain parameters to analyze the degree of fatigue.We found that in fatigued state, the heart rate, SDNN and RMSSD parameters are lower than normal state. And the frequency parameters, like LF, LF/HF Ratio are increasing and HF is decreasing in fatigued state.
31
Lin, Jhe-Yuan, and 林哲遠. "Heart Beat Rate Estimation through Non-contact Detection Measuring System." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/19540747456079957646.
Full textAbstract:
碩士淡江大學
電機工程學系碩士班
102
Clinical testing heart beat information is an important indicator of life parameters; the current mainstream approach is the use of contact detection technology. Non-contact detection refers to the use of external energy without contacting the human body to detect changes of the human body in the physiological environment. Physiological monitor instrument is generally connecting the human body by using wired sensor to measure human body’s physical parameters; it is uncomfortable for people to using this monitoring instrument for a long time. Non-contact detection devices are not suitable for use in general household or personal, because its price is too expensive and difficult to acquire. This study proposes a non-contact method based on video format to measure the heartbeat. It uses the information of the absorption amount of our face to various lights to predict the heartbeat; it is also through image processing and Independent Components Analysis (ICA) to find the hidden information in images and to integrate these information, and then through frequency domain transformation and heartbeat estimation procedure, to achieve a complete automatic non-contact measurement.
32
Tsai, Ching-Hung, and 蔡青宏. "Construction of Heart Rate Detection System and Sports Training Application." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/13540505893183158199.
Full textAbstract:
碩士國立體育大學
競技與教練科學研究所
102
To achieve the physiological response data immediately and accurately is what the scientists are searching for . Sports scientists always use multiple biomarkers from exercise-induced responses to understand the body situations. Heart rate monitors are valuable and the easiest biomarker on stress at physical activities. To date, most of heart rate monitoring systems focus on personal training. It was lack of team sport events on heart rate detection system. Therefore, we develop hardware and software devices in team application, showing people and individual physiological data by color and graphics, to rapidly acquire physiological data presented scientific and applied to practical training goals. Another function is that the software and exercise training program is based on personal ability. This model can improve the safety of sport and exercise monitoring its convenience.
33
Chen, Po-Yu, and 陳伯育. "A frequency to voltage converter for abnormal heart-rate detection." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/96509935653878259545.
Full textAbstract:
碩士國立雲林科技大學
電子與資訊工程研究所
100
Heart disease is in second place among the top 10 causes of mortality in Taiwan. To reduce Heart disease-related mortality rate, it is important to receive therapeutic assistance within the golden hour. This study designed a frequency to voltage convertor chip (FVC) that can change the output voltage signals of the convertor according to the characteristics of frequency alternation. When applied in heart-rate detection, the chip can deliver immediate warnings to users when heart-rate abnormality is detected. The chip can be applied in heart rate detection to check the rate of heartbeats, and the detecting results are demonstrated on four LEDs for users to know whether their heart rates are abnormal. The study applied TSMC 0.18UM CMOS 1P6M 1.8&3.3V process to complete chip design. In the initial circuit design, peripheral circuits were applied along with the frequency to voltage convertor chip for system testing. Then in the second circuit design, peripheral circuits were involved in the chip to complete a portable heart rate detecting and warning system.
34
Chia-YiChu and 朱家毅. "The study of the Heart rate Detection System with PVDF." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/y68hx7.
Full textAbstract:
碩士國立成功大學
電腦與通信工程研究所
105
SUMMARY In this paper, we use PVDF(Polyvinylidene fluoride) sensor to get heart sound. It’s different form ECG(Electrocardiography) and heart sound. It collect chest tremor by heart beat. This sensor can collect your breathing, too. The Development board we use is Arduino because it’s easy to coding and it has a lot of module to use. And then we use BLE module to send raw data to smart phone, including heart wave data, heart rate, user’s location, and user’s temperature. We made a wearable device and app for our system. The app will show the heart sound wave and user ID, location, temperature and heart rate. The raw data will be recorded for use algorithm to analysis wave on PC by MATLAB, and compare heart rate’s correct rate.
35
Zhou, Qin 1980. "Detection of heatbeats in wireless signal." Thesis, 2006. http://hdl.handle.net/10125/20563.
Full text
36
Prawiro, Eka Adi Prasetyo Joko, and 艾卡愛迪. "Heart Rate Detection Method for Low Power Exercise Intensity Monitoring Device." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/835286.
Full textAbstract:
碩士國立臺灣科技大學
電子工程系
102
Exercise is important for our health, however inappropriate exercise would harm or affect nothing to our body. Therefore, a wearable exercise intensity monitoring device is needed to assist user for managing their exercise intensity. One of many parameter index to indicate the exercise intensity is heart rate (HR). In this thesis, we proposed a high accuracy HR detection method and implemented it on a wearable and low power device for exercise intensity monitoring. The accuracy of HR detection method has been verified into two levels, peak detection and HR detection. Peak detection is used for examining the accuracy of proposed algorithm compared with our implemented Pan Tompkins algorithm. We use MIT BIH ST-Change Database and MATLAB to verify the accuracy of the algorithm. The accuracy of peak detection is 99.2%. For HR detection, we verified the accuracy into three conditions i.e. initial, resting, and dynamic condition. In initial condition, the results show that the algorithm can detect the HR accurately in normal ECG, inverted ECG, and flat waveform. For resting condition, we use a commercial ECG simulator as signal input and obtain 100% for the accuracy of HR detection. For dynamic condition, we use treadmill test with ten subjects (8 male, 2 female) that has been asked to walk with six different speeds ranging from 1.8 km/h to 6.3 km/h and to run with speed 7.2 km/h. The accuracy of HR detection is 99.7%.
37
LIN, YU-YAO, and 林育堯. "Heart-Rate Variability based Driver Fatigue Detection and Prediction System Design." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/khe99w.
Full textAbstract:
碩士國立中正大學
資訊工程研究所
105
Host existing driver fatigue detection systems are real-time; however, they do not allow drivers enough buffer time to park his/her vehicle after he is fatigued. As a result, the system is not able to ensure driving safety after the driver is fatigued, which is very dangerous. To solve this problem, this Thesis proposes a Driver Fatigue Monitoring System which can simultaneously detect and predict driver fatigue. In this Thesis, we use a back-propagation neural network (BPNN) model to perform real-time fatigue detection and prediction by analyzing a driver's heart rate variability. The prediction module predicts the driver's future fatigue situation by analyzing changes in the driver's past fatigue levels and sends an early warning so as to give the driver enough time to park safely. However, heart rate variability is susceptible to interferences or shocks and their occurrence frequency. In this Thesis, we propose a dynamic weight moving average method based on data quality, which can dynamically adjust the weight of each time slot on the moving average by analyzing the quality of the data to reduce the influence of the interference on the final analysis result and improve the accuracy of detection and prediction. Experiments show that the proposed system can effectively detect a driver's fatigue, with an accuracy rate of up to 96%. The proposed system can also effectively predict a driver's fatigue situation, by up to 15 to 17 minutes before being actually fatigued, and the accuracy is higher than 90%. The dynamic weight moving average method proposed in this Thesis is more accurate than the traditional moving average method, it improves 10% accurate in detection and prediction. This is also proved in the experiments.
38
Tsai, Ching-Wei, and 蔡慶偉. "Real-Time Heart Rate Variability Analysis and Physical Activity Detection System." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/23673175772746226773.
Full textAbstract:
碩士國立陽明大學
醫學工程研究所
95
The aim of this thesis is the improvement of ambulatory ECG. We combine the development of the hardware and firmware activity detection, HRV analyzing and myocardial ischemia detection. We hope this system can assist us to detect the heart diseases prognostic symptom. We developed a microcontroller-based system , included three parts: 1. Using accelerometer to identify the activity level and posture of the user. 2. Using low power a microcontroller, we developed a real-time activity-considering heart rate variability spectral analysis mechanism for ischemia heart disease detection. 3. For long-term measurement, the bio-information is stored in flash memory for long-term tracing or further research. This research demonstrated that the improved ambulatory ECG system is able to fulfill the real-time processing and long-term monitoring (more than 24 hours) requirements. Five healthy male subjects, mean age 24, were collected to analyze the relationships between posture and HRV using our system. As the posture is changing from one to another, LF and HF power is higher in lying than in sitting and dynamic activity. LF and HF power is higher in sitting than in dynamic activity in some subjects. The LF power to HF power ratio form dynamic activity, sitting to lying posture is decreasing. Seven cases selected form European ST-T database were analyzed to observe the relationship between myocardial ischemia and HRV.
39
Tzeng, De Jeng, and 曾德正. "An FPGA Sensor Platform for Heart Rate and Ventricular Premature Contraction Detection." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/47769116633319316409.
Full textAbstract:
碩士長庚大學
電機工程學研究所
97
This research implemented an System on chip (S.O.C) biomedical information platform base on Xilinx Field-Programmable Gate Array (FPGA).This platform has been use for an IP which detect whether Ventricular Premature Contraction (VPC) happened or not. Base on Power PC 405, this system include of ADC for data acquisitions, codec for AC97 signal source , CF (compact flash) card for data storage and General purpose I/O. After data acquisition, data could storage in CF card, transfer to PC or analyzed in some user defined algorithm IP. Power PC and bus operate on same rate 100 Mhz for power consideration. This system has great expandable space . Whether PLB or OPB, user can insert more user defined devices or algorithms for this platform if hardware resource allow. In software, Consider it used of scheduled lightly. This platform used stand alone OS. For analyzing feasibility of platform. We implemented a VPC detection IP. This IP is to combine Phase-Space[1] algorithm and Pan-Tompkins[2] algorithm to analysis data. Then analysis data’s characteristics to detect whether VPC or not.
40
Yi-ChingChen and 陳怡靜. "Development of an Asthma Detection Algorithm based on Heart Rate Variability Analysis." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/2658sk.
Full text
41
Kabir, Muammar Muhammad. "Detection of cardiorespiratory interaction for clinical research applications." Thesis, 2012. http://hdl.handle.net/2440/74220.
Full textAbstract:
Human physiological systems are a widely studied topic in the field of Biomedical Engineering. There is a particular interest in the study of human cardiovascular and respiratory systems since these two systems do not act independently; there exists a strong coupling between them. Experimental studies use the concept of synchronization to demonstrate the interaction between different physiological systems. Synchronization is the appearance of some relationship between two periodic oscillators in the form of locking of their phases or adjustment of rhythms. Cardiorespiratory coordination is an aspect of the interaction between heart and respiratory rhythm that has been reported not only at rest or during exercise, but also in subjects under the influence of anesthesia and drugs. Through the quantification of cardiorespiratory coordination we can achieve a better understanding of its physiological functioning. Some of the conventional signal-processing techniques such as power spectral density and cross-correlation analysis have shown linear dependencies between heart and respiratory rate. However, as these biological signals are inherently non-linear, nonstationary, and contain superimposed noise, the techniques mentioned above often prove to be inadequate for characterizing their complex dynamics. Therefore, to overcome these issues, it is required to develop a technique that is less sensitive to noise, robust and possibly provides additional information about the interaction between cardiac rhythms and respiration. This Thesis introduces a new and relatively simple approach for the quantification of cardiorespiratory interaction based on joint symbolic dynamics, which provides an easy interpretation of physiological data by a simplified description of the system’s dynamics. Furthermore, this Thesis investigates the association between cardiorespiratory coordination and some of the physiological mechanisms, and assesses cardiorespiratory coordination as a marker of cardiorespiratory system disturbances.Thesis (Ph.D.) -- University of Adelaide, School of Electrical and Electronic Engineering, 2012
42
Tee, Jarwin-Jim Ang, and 鄭嘉輝. "Time-Domain Heart Rate Variability Analysis as a Tool for Sleep Apnea Detection." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/04701869442905345489.
Full textAbstract:
碩士中原大學
生物醫學工程研究所
101
Obstructive Sleep Apnea (OSA) is a syndrome in which there is a repeated event of a partial or complete obstruction of the upper airway during sleep, resulting in intermittent hypoxia and transient repetitive arousals from sleep. The characteristic heart rate pattern, known as the cyclic variation of heart rate (CVHR), that is known to accompany OSA episodes had been demonstrated in earlier studies to be an effective tool in the detection of OSA due to the high correlation between the CVHR index (CVHR per hour) and the apnea-hypopnea index. Moreover, Time- domain HRV analysis has been proven as powerful tool in definitive diagnosis and classification of OSAS by using R-wave detection to extract and analyze the RR intervals of ECG readings. In this study, the So and Chan algorithm for QRS detection was implemented along with time-domain HRV analysis in order to develop a system capable of deriving the required HRV characteristics for reliable diagnosis from ECG signals. The system was tested by using ECG recordings from Physionet’s Apnea-ECG database and also from ECG recorded using through the system. The results of the diagnosis from the Physionet data were then compared to the minute by minute classifications found in the Physionet database in order to test the reliability of the algorithm. The findings in the tests conducted have shown high accuracy, as high as 84% for recordings with severe apneas, and high sensitivity and specificity, around 90% and around 80% respectively. Real ECG data that was recorded using the National Instruments USB DAQ-6008 data acquisition device gave us similarly good results as with the analysis of the Physionet database.
43
Po-ChengLiu and 劉博烝. "Development and Application of E-learning Attention and the Heart Rate Detection System." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/21459828980827663137.
Full textAbstract:
碩士國立成功大學
工程科學系專班
100
Attention is the important key to improve the effectiveness of learning, and can absorb knowledge in a shorter time. Moreover, concentration on learning is easier to grasp the essentials of learning, and promote the outcome of learning effectively. In conventional classroom, a teacher and students usually conduct a teaching activity through face-by-face method that handles the whole students’ learning behavior, especially, in the small classroom. With the advance of computer technology, using computers and networks for teaching activities have already become teaching tool in E-learning. Although the use of digital device can assist on presenting diverse teaching methods, students may not actively learn on the classroom in the lack of the care of the teacher. In addition, the students may lack for attention and are easy to neglect learning. Therefore, the diversification of teaching and learning environment is not necessarily significantly increase the effectiveness of learning. In order to understand the attention of students in learning to improve the effectiveness of personalized E-learning, the study designs a heart-rate capture system to analyze students’ attention. The system uses a operating devices with heart-rate detection to capture a student's heart-rate to understand the attention in the learning period. Then the system instantly sent the information of the heart-rate to the teacher. After understanding the learning from the students, the teacher can adjust the learning progress. In the meanwhile, the heart-rate information is also stored in the database for future analysis, and improves the quality of teaching.
44
Hsiao, Yi-Hsin, and 蕭奕昕. "Evaluation of Filter Implementation for Heart Rate Detection in Different Postures and Measured Positions." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/cxjac5.
Full textAbstract:
碩士國立臺北科技大學
電腦與通訊研究所
99
Heart rate signal is one of the reliable reference for human healthy, and this signal is also enough to prevent out of fatigue and excessive exercise. There are lots of researches have been extended from heart rate signal, such as within electrodes in clothes, combined athletic postures in experiments, and electrodes effect on heart rate detection. It means the heart rate analysis is valuable for human. Users can not measure heart rate signal by products in the markets because of the muscle noise from postures, electric interference and the volume of the products, they only works in static state. There is a researching flow chart presented in this paper. In the first step, we capture the heart rate signal, investigate the feature of filters, then decide the filters which fit for capturing heart rate signal in other postures. There are some discussions about the orders of filters and the bandwidth which fit for heart rate detection. Then we combined these filters with heart rate detected circuit, and analysis the noise and the bandwidth by different postures and measured positions. Avoid these muscle noise and interference, and improve the heart rate signal recognition. It shows the performance is related by filter orders after this researching flow, but on the other hand, area of the filter circuit should be considered. The heart rate signal is clearer than other positions on the chest, and the signal which from neck cannot be evaluated; it means the signal-noise-ratio is worse than other measured position. People can choose the suitable filter size and orders of filters for these postures and evaluate the effect on anti-noise between two measured electrodes. This paper provide the evaluation about heart rate detection which measured in different postures and positions, and provide the characteristics for portable device designed in the future.
45
Wang, Yu-Wen, and 王郁文. "Algorithm Design for the Detection of Human Heart Rate on a Doppler Radar System." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/10336061388987653815.
Full textAbstract:
碩士國立中山大學
機械與機電工程學系研究所
104
Due to the fact that people pay more attention on health nowadays, and the society of Taiwan gradually towards to an aging one, the cost of health care are increasing year by year. Under the circumstances, the low cost, suitable for long-time monitoring purpose, such as non-contact vital signs monitoring technologies, are urgently demanded. In order to detect human’s vital signs in non-contact way, this thesis adopts a Doppler radar system as the detection tool coupled with several signal processing approaches to estimate the heart rate of human. Four core methods are seleted to capture the periodic frequency of human heart motion, including Discrete fourier transform (DFT) method, Phase energy method, Velocity strength method, and Cyclic spectrum method. According to the performance comparison in both effectiveness and efficiency, we find that the Cyclic spectrum-based method perform the best. Therefore, we select Cyclic spectrum method as the main method, together with additional pre-processing and post-filtering steps, to propose a human’s heart rate detection algorithm, which can accurately determine if a human’s heart motion exist or not. This study further develops a MATLAB GUI interface, and designs some scenario experiments to verify the reliability of our algorithm. For the performance evaluation，the GUI can output the accuracies and matching rates of the detection results once the groundtruth and reference information are available. Through the experiments conducted on real data collected by the Doppler radar, it can be proved that the proposed algorithm can reliably detect human’s heart rate when he or she stays in a stationary condition.
46
Chen, Kuan-Yi, and 陳冠伊. "A Premature Ventricular Contraction (PVC) Detection Scheme Based on Heart Rate Variability (HRV) Statistics." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/54808895333661762857.
Full textAbstract:
碩士國立中正大學
通訊工程研究所
100
With the rapid development of science and technology, people get more pressure from their daily lives. An important sign of being unhealthy is having heart arrhythmia. Diagnosis for the arrhythmia is important technique to saving people's life. In particular, people's heart beats are affected by autonomic nervous system and physiological hormone. The Heart Rate Variability (HRV) is used to measure the changes of the heart beat rates, and we can study the strength of autonomic nervous system by analyzing it. The database of arrhythmia used in this thesis is from MIT-BIH. We also applied the Cubic Spline interpolation to derive the HRV parameters. The Statistical Product and Service Solutions (SPSS) is used to analyze the relation between parameters of HRV and a typical arrhythmia called Premature Ventricular Contraction (PVC). Results showed that the very low frequency power (VLFP), low frequency power(LFP), high frequency power(HFP) in HRV can be used to determine the PVC arrhythmia.
47
Choi, Jongyoon. "Minimally-invasive Wearable Sensors and Data Processing Methods for Mental Stress Detection." Thesis, 2011. http://hdl.handle.net/1969.1/ETD-TAMU-2011-12-10674.
Full textAbstract:
Chronic stress is endemic to modern society. If we could monitor our mental state, we may be able to develop insights about how we respond to stress. However, it is unfeasible to continuously annotate stress levels all the time. In the studies conducted for this dissertation, a minimally-invasive wearable sensor platform and physiological data processing methods were developed to analyze a number of physiological correlates of mental stress.
We present a minimally obtrusive wearable sensor system that incorporates embedded and wireless communication technologies. The system is designed such that it provides a balance between data collection and user comfort. The system records the following stress related physiological and contextual variables: heart rate variability (HRV), respiratory activity, electrodermal activity (EDA), electromyography (EMG), body acceleration, and geographical location.
We assume that if the respiratory influences on HRV can be removed, the residual HRV will be more salient to stress in comparison with raw HRV. We develop three signal processing methods to separate HRV into a respiration influenced and residual HRV. The first method consists of estimating respiration-induced portion of HRV using a linear system identification method (autoregressive moving average model with exogenous inputs). The second method consists of decomposing HRV into respiration-induced principal dynamic mode and residual using nonlinear dynamics decomposition method (principal dynamic mode analysis). The third method consists of splitting HRV into respiration-induced power spectrum and residual in frequency domain using spectral weighting method. These methods were validated on a binary discrimination problem of two psychophysiological conditions: mental stress and relaxation. The linear system identification method, nonlinear dynamics decomposition method, and spectral weighting method classified stress and relaxation conditions at 85.2 %, 89.2 %, and 81.5 % respectively. When tonic and phasic EDA features were combined with the linear system identification method, the nonlinear dynamics decomposition method, and the spectral weighting method, the average classification rates were increased to 90.4 %, 93.2 %, and 88.1 % respectively.
To evaluate the developed wearable sensors and signal processing methods on multiple subjects, we performed case studies. In the first study, we performed experiments in a laboratory setting. We used the wearable sensors and signal processing methods to discriminate between stress and relaxation conditions. We achieved 81 % average classification rate in the first case study. In the second study, we performed experiments to detect stress in ambulatory settings. We collected data from the subjects who wore the sensors during regular daily activities. Relaxation and stress conditions were allocated during daily activities. We achieved a 72 % average classification rate in ambulatory settings.
Together, the results show achievements in recognizing stress from wearable sensors in constrained and ambulatory conditions. The best results for stress detection were achieved by removing respiratory influence from HRV and combining features from EDA.
48
Yang, Shin-Fong, and 楊昕峰. "A New Heart Rate Detection Method from PPG Signal of Wearable Device Using Adaptive Filter." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/97653906433632225045.
Full textAbstract:
碩士國立中興大學
資訊科學與工程學系
105
Physical exercise plays a vital role in people’s life and has a great relationship with the growth of muscle and bones in the Adolescence. If we can develop good exercise habits during teenage years, it’s positive effect for both physical and mental. So we developed vital signal device to monitor health, helping the growth of teenager. In this work, we consider the convenience and comfort for the subject, using Heart rate monitoring from wrist-type photoplethysmographic(PPG). Wirelessing to the computer and measure young children photoplethysmographic(PPG) signals in the movement statement. We also used the Short Time Fourier Transform (STFT) and time domain methods to calculate heart rate. Previous methods for detection in high-noise situations can’t be effectively detection heart rate. In this paper, we propose a robust algorithm to detect the PPG peak under big motion artifact conditions. In the proposed algorithm, an adaptive threshold can cutoff the noise, an find peak method and the best peak method can make sure true peaks and eliminates fake peaks and error peaks from the adaptive filter PPG signal The result show that accuracy of calculation heart rate is higher than others. We use sensitivity, Positive predictivity, Failed detection rate to evaluate methods, also in a state of motion and comparison of multi data.
49
Hsieh, Cheng-Han, and 謝政翰. "An Electrocardiogram Signal Monitoring System with Heart Rate Detection and Energy Harvesting for Vehicle Driver." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/u6v4wj.
Full textAbstract:
博士國立中正大學
電機工程研究所
103
An Electrocardiogram (ECG) signal monitoring system with heart rate detection and energy harvesting based on smart phone for vehicle driver is proposed. There are four parts in this proposed system. The first part includes the proposed high resolution and low power analog front-end chip to implement the bio-signal sensing circuits (BSC). In the second part, a digital signal processor (DSP) with high recognition rate QRS detection algorithm has been proposed. The third part is the power management with energy harvesting from smart phone. It provides the stable supply voltage to BSC and the power conversion efficiency (PCE) of the proposed rectifier is more than 85%. The last part realizes a data record and heart rate variability (HRV) analysis interface based on Android. The BSC sensing the bio-signal of vehicle driver from conductive fabric on steering wheel. The resolution of BSC is higher than 10 bits. The output signal of BSC can be processed by a wavelet-based QRS detection algorithm and count the R-R interval value. The algorithm which is verified with data from MIT/BIH Arrhythmia Database achieves a sensitivity of 99.68% and a positive predictability of 99.64%. Most of chips are fabricated in TSMC 0.18 μm standard CMOS process.
50
Luo, Hua-I., and 羅華義. "Embedded System Implementation of Drowsiness Detection Based on Frequency Domain Analysis of Heart Rate Variability." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/05871963676824444835.
Full textAbstract:
碩士國立中興大學
電機工程學系所
100
Vehicle penetration rate rapidly increases in the word. In recent years, car accidents caused by fatigued driving and drowsy driving are raised. Driving is spiritually exhausted types of work. There are several symptom of tired drowsy driving such as awkward movements, blurred vision, trance, unresponsive…etc.. While drowsy driving happens, it accompanies with short duration sleep and losing control of driving. Drowsy driving is usually happening during high-speed driving. If the driver doesn’t take a rest or keeps spirits up, drowsy driving might cause serious traffic accidents. Generally, measuring the frequency of nod or close of eyes are the methods to judge the drowsiness state. However, the measuring information can only be gotten during drowsy condition. Hence, it is hard to measure drowsy information and to warn drowsy driver earlier. The thesis will use frequency domain analysis of heart rate variability (HRV) to detect if drowsiness state happens. This way is different than detect by external feature. It can early and exactly detect whether short duration sleep happens. It is a profitable way to prevent traffic accidents. The thesis proposes a drowsiness detection system, which is implemented by Cheetah development kit (CDK) and uses graphical user interface (GUI) in PC. It can immediately display electrocardiography (ECG) waveform and power spectral density (PSD) analysis of heart rate variability. The system based on embedded system and hardware system added HW-SW Bridge that integrates easily for all system to promote system on chip (SOC) implementation in the future.