Teses / dissertações sobre o tema "Multisensor monitoring"

Monitoring stress in real-time, in a non-laboratory environment can be benecial in several applications. One of these, which have been the motivation for this thesis, is to to perform this measurement during Attention decit hyperactivity disorder (ADHD) diagnosis. Monitoring several physiological responses to internal or external stimuli in a single soft-real-time system is nota solution widely used in an application like this. The thesis starts by studying several stress related responses in detail. Sensors for all of the responses are not implemented nor is it possible toimplement in to the desired system. After the study is was decided to implement two measurement modules. The first a Photo-plethysmogrophy (PPG) measurement module to measure heart rate and also estimate breathing. This module is prepared for estimating arterial blood oxygen levels but the calculation or verification have not been done. The second is Skin Conductance (SC) measurement module and in to both ofthese add a temperature sensor to measure the temperature of the skin. Time constraints limit the SC module to only be presented in theory. The PPG module on the other hand have been realisedin a prototype. This prototype performs the measurement in transmissive mode on the left earlobe, which leaves the hands free and it does not affect the hearing on that ear. The prototype giveout acceptable signal quality when good contact with the measurement site is achieved. The signalinterpretation, such as performing the signal analysis to count the beats per minute, is outside thescope of this thesis and will therefore not be presented but the signals can be seen in figures.
Att mäta stress i realtid i verkliga situationer kan vara fördelaktigt för flera applikationer. Det som har legat som grund för denna uppsats är att kunna mäta stress under ADHD diagnostisering. Genom att kombinera de vanliga testerna med stressnivåer hos patienten hoppas man kunna utveckla nya metoder för diagnostisering. Att mäta fera parametrar samtidigt i realtid är inte något ofta utförs idag. För att komma igång har fera kroppsliga funktioner som påverkas på olika sätt av stress studerats. Alla dessa funktioner kan inte inkluderas i det system som önskas konstrueras antingen på grund av systemets karaktär eller på grund tidsbrist. Efter att undersökningen var klar beslutades det att konstruera två moduler. Den första använder en mätteknik som kallas PPG och används för att mäta hjärtfrekvens, även andningsfrekvensen estimeras och modulen är förberedd för att estimera blodsyre nivåa men signalbehandling och validering för detta är inte gjord. Den andra modulen mäter resistans i huden. I dessa moduler lades även till en temperatur sensor för att mäta hudtemperaturen. Tidsbrist har gjort att endast en av dem två modulerna kunnat realiserats. Den som realiserat är PPG modulen och modulen för hudresistans presenteras endast teoretiskt. PPG modulen genomför matningen med en transmissiv teknik på vänster öra och ger ut en acceptabel signal kvalité om sensorn får bra kontakt. Arbetet är avgränsat och inkluderar inte signalanalysen av signalen däremot visualiseras signalen i figurer.

Dans cette thèse, une approche combinant des données issues de capteurs hétérogènes pour la reconnaissance d'activités des personnes âgées à domicile est proposée. Cette approche consiste à combiner les données fournies par des capteurs vidéo avec des données fournies par des capteurs environnementaux pour suivre l'interaction des personnes avec l'environnement. La première contribution est un nouveau modèle de capteur capable de donner une représentation cohérente et efficace des informations fournies par différents types de capteurs physiques. Ce modèle inclue l'incertitude sur la mesure. La deuxième contribution est une approche, basée sur une fusion multicapteurs, pour la reconnaissance d'activités. Cette approche consiste à détecter la personne, suivre ses mouvements, reconnaître ses postures et ses activités d'intérêt, par une analyse multicapteurs et une reconnaissance d'activités humaines. Pour résoudre le problème de la présence de capteurs hétérogènes, nous avons choisi de réaliser la fusion à haut niveau (niveau événement) des différentes données issues des différents capteurs, en combinant les événements vidéo avec les événements environnementaux. La troisième contribution est l'extension d'un langage de description qui permet aux utilisateurs (ex. Le corps médical) de décrire les activités d'intérêt dans des modèles formels. Les résultats de cette approche sont montrés pour la reconnaissance des AVQ pour de vraies personnes âgées évoluant dans un appartement expérimental appelé GERHOME équipé de capteurs vidéo et de capteurs environnementaux. Les résultats obtenus de la reconnaissance des différentes AVQ sont encourageants
In this thesis, an approach combining heterogeneous sensor data for recognizing elderly activities at home is proposed. This approach consists in combining data provided by video cameras with data provided by environmental sensors to monitor the interaction of people with the environment. The first contribution is a new sensor model able to give a coherent and efficient representation of the information provided by various types of physical sensors. This sensor model includes an uncertainty in sensor measurement. The second contribution is a multisensor based activity recognition approach. This approach consists in detecting people, tracking people as they move, recognizing human postures and recognizing activities of interest based on multisensor analysis and human activity recognition. To address the problem of heterogeneous sensor system, we choose to perform fusion at the high-level (event level) by combining video events with environmental events. The third contribution is the extension of a description language which lets users (i. E. Medical staff) to describe the activities of interest into formal models. The results of this approach are shown for the recognition of ADLs of real elderly people evolving in an experimental apartment called Gerhome equipped with video sensors and environmental sensors. The obtained results of the recognition of the different ADLs are encouraging

Due to structural damages from earthquakes and strong winds, engineers and scientists have focused on performance based design methods and sensors directly measuring relative displacements. Among the monitoring methods being considered include those using Global Positioning System (GPS) technology. However, as the technical feasibility of using GPS for recording relative displacements has been (and is still being) proven, the challenge for users is to determine how to make use of the relative displacements being recorded. This thesis proposes a mathematical framework that supports the use of RTK-GPS and multisensor data for structural monitoring. Its main contributions are as follows: (a) Most of the emerging GPS-based structural monitoring systems consist of GPS receiver arrays (dozens or hundreds deployed on a structure), and the issue of integrity of the GPS data generated must be addressed for such systems. Based on this recognition, a methodology for integrity monitoring using a data redundancy approach has been proposed and tested for a multi-antenna measurement environment. The benefit of this approach is that it verifies the reliability of both the measuring instruments and the processed data contrary to the existing methods that only verifies the reliability of the processed data. (b) For real-time structural monitoring applications, high frequency data ought to be generated. A methodology that can extract, in real-time, deformation parameters from high frequency RTK measurements is proposed. The methodology is tested and shown to be effective for determining the amplitude and frequency of structural dynamics. Thus, it is suitable for the dynamic monitoring of towers, tall buildings and long span suspension bridges. (c) In the overall effort of deformation analysis, large quantities of observations are required, both of causative phenomena (e.g., wind velocity, temperature, pressure), and of response effects (e.g., accelerations, coordinate displacements, tilt, strain, etc.). One of the problems to be circumvented is that of dealing with excess data generated both due to process automation and the large number of instruments employed. This research proposes a methodology based on multivariate statistical process control whose benefit is that excess data generated on-line is reduced, while maintaining a timely response analysis of the GPS data (since they can give direct coordinate results). Based on the above contributions, a demonstrator software system was designed and implemented for the Windows operating system. Tests of the system with datasets from UNSW experiments, the Calgary Tower monitoring experiment in Canada, the Xiamen Bank Building monitoring experiment in China, and the Republic Plaza Building monitoring experiment in Singapore, have shown good results.

Machine condition monitoring is an increasingly important area of research and plays an integral role in the economic competitiveness in many industries. Machine breakdown can lead to many adverse effects including increased operation and maintenance costs, reduced production output, decreased product quality and even human injury or death in the event of a catastrophic failure. As a way to overcome these problems, an automated machine diagnostics scheme may be implemented, which will continuously monitor machine health for the purpose of prediction, detection, and diagnosis of faults and malfunctions. In this work, a signal-based condition monitoring scheme is developed and tested on an industrial fish processing machine. A variety of faults are investigated including catastrophic on-off type failures, partial faults in gearbox components and sensor failures. The development of the condition monitoring scheme is divided into three distinct subtasks: signal acquisition and representation, feature reduction, and classifier design. For signal acquisition, the machine is instrumented with multiple sensors to accommodate sensor failure and increase the reliability of diagnosis. Vibration and sound signals are continuously acquired from four accelerometers and four microphones placed at strategic locations on the machine. The signals are efficiently represented using the wavelet packet transform and node energies are used to generate a feature vector. A measure for feature discriminant ability is chosen and the effect of choosing different analyzing wavelets is investigated. Since the dimensionality of the feature vector can become very large in multisensor applications, various means of feature reduction are investigated to reduce the computational cost and improve the classification accuracy. Local Discriminant Bases, a popular and complementary approach to wavelet-based feature selection is introduced and the drawbacks in the context of multisensor applications are highlighted. To address these issues, a genetic algorithm is proposed for feature selection in robust condition monitoring applications. The fitness function of the genetic algorithm consists of three criteria that are considered to be important in fault classification: feature set size, discriminant ability, and sensor diversity. A procedure to adjust the weights is presented. The feature selection scheme is validated using a data set consisting of one healthy machine condition and five faulty conditions. For classifier design, the theoretical foundations of two popular non-linear classifiers are presented. The performance of Support Vector Machines (SVM) and Radial Basis Function (RBF) networks are compared using features obtained from a filter selection scheme and a wrapper selection scheme. The classifier accuracy is determined under conditions of complete sensor data and corrupted sensor data. Different kernel functions are applied in the SVM to determine the effect of kernel variability on the classifier performance. Finally, key areas of improvement in instrumentation, signal processing, feature selection, and classifier design are highlighted and suggestions are made for future research directions.

In a fully automated manufacturing environment, instant detection of condition state of the cutting tool is essential to the improvement of productivity and cost effectiveness. In this paper, a tool condition monitoring system (TCM) via machine learning (ML) and machine ensemble (ME) approach was developed to investigate the effectiveness of multisensor fusion when machining 4340 steel with multi-layer coated and multi-flute carbide end mill cutter. Feature- and decision-level information fusion models utilizing assorted combinations of sensors were studied against selected ML algorithms and their majority vote ensemble to classify gradual and transient tool abnormalities. The criterion for selecting the best model does not only depend on classification accuracy but also on the simplicity of the implemented system where the number of features and sensors is kept to a minimum to enhance the efficiency of the online acquisition system. In this study, 135 different features were extracted from sensory signals of force, vibration, acoustic emission and spindle power in the time and frequency domain by using data acquisition and signal processing modules. Then, these features along with machining parameters were evaluated for significance by using different feature reduction techniques. Specifically, two feature extraction methods were investigated: independent component analysis (ICA), and principal component analysis (PCA) and two feature selection methods were studied, chi square and correlation-based feature selection (CFS). For various multi-sensor fusion models, an optimal feature subset is computed. Finally, ML algorithms using support vector machine (SVM), multilayer perceptron neural networks (MLP), radial basis function neural network (RBF) and their majority voting ensemble were studied for selected features to classify not only flank wear but also breakage and chipping. In this research, it has been found that utilizing the multisensor feature fusion technique under majority vote ensemble gives the highest classification performance. In addition, SVM outperformed other ML algorithms while CFS feature selection method surpassed other reduction techniques in improving classification performance and producing optimal feature sets for different models.

Diabetes is a disease that undermines the normal regulation of glucose levels in the blood. In people with diabetes, the body does not secrete insulin (Type 1 diabetes) or derangements occur in both insulin secretion and action (Type 2 diabetes). In spite of the therapy, which is mainly based on controlled regimens of insulin and drug administration, diet, and physical exercise, tuned according to self-monitoring of blood glucose (SMBG) levels 3-4 times a day, blood glucose concentration often exceeds the normal range thresholds of 70-180 mg/dL. While hyperglycaemia mostly affects long-term complications (such as neuropathy, retinopathy, cardiovascular, and heart diseases), hypoglycaemia can be very dangerous in the short-term and, in the worst-case scenario, may bring the patient into hypoglycaemic coma. New scenarios in diabetes treatment have been opened in the last 15 years, when continuous glucose monitoring (CGM) sensors, able to monitor glucose concentration continuously (i.e. with a reading every 1 to 5 min) over several days, entered clinical research. CGM sensors can be used both retrospectively, e.g., to optimize the metabolic control, and in real-time applications, e.g., in the "smart" CGM sensors, able to generate alerts when glucose concentrations are predicted to exceed the normal range thresholds or in the so-called "artificial pancreas". Most CGM sensors exploit needles and are thus invasive, although minimally. In order to improve patients comfort, Non-Invasive Continuous Glucose Monitoring (NI-CGM) technologies have been widely investigated in the last years and their ability to monitor glucose changes in the human body has been demonstrated under highly controlled (e.g. in-clinic) conditions. As soon as these conditions become less favourable (e.g. in daily-life use) several problems have been experienced that can be associated with physiological and environmental perturbations. To tackle this issue, the multisensor concept received greater attention in the last few years. A multisensor consists in the embedding of sensors of different nature within the same device, allowing the measurement of endogenous (glucose, skin perfusion, sweating, movement, etc.) as well as exogenous (temperature, humidity, etc.) factors. The main glucose related signals and those measuring specific detrimental processes have to be combined through a suitable mathematical model with the final goal of estimating glucose non-invasively. White-box models, where differential equations are used to describe the internal behavior of the system, can be rarely considered to combine multisensor measurements because a physical/mechanistic model linking multisensor data to glucose is not easily available. A more viable approach considers black-box models, which do not describe the internal mechanisms of the system under study, but rather depict how the inputs (channels from the non-invasive device) determine the output (estimated glucose values) through a transfer function (which we restrict to the class of multivariate linear models). Unfortunately, numerical problems usually arise in the identication of model parameters, since the multisensor channels are highly correlated (especially for spectroscopy based devices) and for the potentially high dimension of the measurement space. The aim of the thesis is to investigate and evaluate different techniques usable for the identication of the multivariate linear regression models parameters linking multisensor data and glucose. In particular, the following methods are considered: Ordinary Least Squares (OLS); Partial Least Squares (PLS); the Least Absolute Shrinkage and Selection Operator (LASSO) based on l1 norm regularization; Ridge regression based on l2 norm regularization; Elastic Net (EN), based on the combination of the two previous norms. As a case study, we consider data from the Multisensor device mainly based on dielectric and optical sensors developed by Solianis Monitoring AG (Zurich, Switzerland) which partially sponsored the PhD scholarship. Solianis Monitoring AG IP portfolio is now held by Biovotion AG (Zurich, Switzerland). Forty-five recording sessions provided by Solianis Monitoring AG and collected in 6 diabetic human beings undertaken hypo and hyperglycaemic protocols performed at the University Hospital Zurich are considered. The models identified with the aforementioned techniques using a data subset are then assessed against an independent test data subset. Results show that methods controlling complexity outperform OLS during model test. In general, regularization techniques outperform PLS, especially those embedding the l1 norm (LASSO end EN), because they set many channel weights to zero thus resulting more robust to occasional spikes occurring in the Multisensor channels. In particular, the EN model results the best one, sharing both the properties of sparseness and the grouping effect induced by the l1 and l2 norms respectively. In general, results indicate that, although the performance, in terms of overall accuracy, is not yet comparable with that of SMBG enzyme-based needle sensors, the Multisensor platform combined with the Elastic-Net (EN) models is a valid tool for the real-time monitoring of glycaemic trends. An effective application concerns the complement of sparse SMBG measures with glucose trend information within the recently developed concept of dynamic risk for the correct judgment of dangerous events such as hypoglycaemia. The body of the thesis is organized into three main parts: Part I (including Chapters 1 to 4), first gives an introduction of the diabetes disease and of the current technologies for NI-CGM (including the Multisensor device by Solianis) and then states the aims of the thesis; Part II (which includes Chapters 5 to 9), first describes some of the issues to be faced in high dimensional regression problems, and then presents OLS, PLS, LASSO, Ridge and EN using a tutorial example to highlight their advantages and drawbacks; Finally, Part III (including Chapters 10-12), presents the case study with the data set and results. Some concluding remarks and possible future developments end the thesis. In particular, a Monte Carlo procedure to evaluate robustness of the calibration procedure for the Solianis Multisensor device is proposed, together with a new cost function to be used for identifying models.
Il diabete e una malattia che compromette la normale regolazione dei livelli di glucosio nel sangue. Nelle persone diabetiche, il corpo non secerne insulina (diabete di tipo 1) o si vericano delle alterazioni sia nella secrezione che nell'azione dell'insulina stessa (diabete di tipo 2). La terapia si basa principalmente su somministrazione di insulina e farmaci, dieta ed esercizio fisico, modulati in base alla misurazione dei livelli di glucosio nel sangue 3-4 volte al giorno attraverso metodi finger-prick. Nonostante ciò, la concentrazione di glucosio nel sangue supera spesso le soglie di normalita di 70-180 mg/dL. Mentre l'iperglicemia implica complicanze a lungo termine (come ad esempio neuropatia, retinopatia, malattie cardiovascolari e cardiache), l'ipoglicemia puo essere molto pericolosa nel breve termine e, nel peggiore dei casi, portare il paziente in coma ipoglicemico. Nuovi scenari nella cura del diabete si sono affacciati negli ultimi 10 anni, quando sensori per il monitoraggio continuo della glucemia sono entrati nella fase di sperimentazione clinica. Questi sensori sono in grado di monitorare le concentrazioni di glucosio nel sangue con una lettura ogni 1-5 minuti per diversi giorni, permettendo un analisi sia retrospettiva, ad esempio per ottimizzare il controllo metabolico, che in tempo reale, per generare avvisi quando viene predetta l'uscita dalla normale banda euglicemica, e nel cosiddetto "pancreas artificiale". La maggior parte di questi sensori per il monitoraggio continuo della glicemia sono minimatmente invasivi perche sfruttano un piccolo ago inserito sottocute. Gli ultimi anni hanno visto un crescente interesse verso tecnologie non invasive per il monitoraggio continuo della glicemia, con l'obiettivo di migliorare il comfort del paziente. La loro capacità di monitorare i cambiamenti di glucosio nel corpo umano e stata dimostrata in condizioni altamente controllate tipiche di un'infrastruttura clinica. Non appena queste condizioni diventano meno favorevoli (ad esempio durante un uso quotidiano di queste tecnologie), sorgono diversi problemi associati a perturbazioni fisiologiche ed ambientali. Per affrontare questo problema, negli ultimi anni il concetto di "multisensore" ha ottenuto un crescente interesse. Esso consiste nell'integrazione di sensori di diversa natura all'interno dello stesso dispositivo, permettendo la misurazione di fattori endogeni (glucosio, perfusione del sangue, sudorazione, movimento, ecc) ed esogeni (temperatura, umidita, ecc). I segnali maggiormente correlati con il glucosio e quelli legati agli altri processi sono combinati con un opportuno modello matematico con l'obiettivo finale di stimare la glicemia in modo non invasivo. Modelli di sistema (o a "scatola bianca"), nei quali equazioni differenziali descrivono il comportamento interno del sistema, possono essere considerati raramente. Infatti, un modello fisico/meccanicistico legante i dati misurati dal multisensore con il glucosio non e facilmente disponibile. Un differente approccio vede l'impiego di modelli di dati (o a "scatola nera") che descrivono il sistema in esame in termini di ingressi (canali misurati dal dispositivo non invasivo), uscita (valori stimati di glucosio) e funzione di trasferimento (che in questa tesi si limita alla classe dei modelli di regressione lineari multivariati). In fase di identificazione dei parametri del modello potrebbero insorgere problemi numerici legati alla collinearita tra sottoinsiemi dei canali misurati dal multisensore (in particolare per i dispositivi basati su spettroscopia) e per la dimensione potenzialmente elevata dello spazio delle misure. L'obiettivo della tesi di dottorato e di investigare e valutare diverse tecniche per l'identicazione del modello di regressione lineare multivariata con lo scopo di stimare i livelli di glicemia non invasivamente. In particolare, i seguenti metodi sono considerati: Ordinary Least Squares (OLS), Partial Least Squares (PLS), the Least Absolute Shrinkage and Selection Operator (LASSO) basato sulla regolarizzazione con norma l1; Ridge basato sulla regolarizzazione con norma l2; Elastic-Net (EN) basato sulla combinazione delle due norme precedenti. Come caso di studio per l'applicazione delle metodologie proposte, consideriamo i dati misurati dal dispositivo multisensore, principalmente basato su sensori dielettrici ed ottici, sviluppato dall'azienda Solianis Monitoring AG (Zurigo, Svizzera), che ha parzialmente sostenuto gli oneri finanziari legati al progetto di dottorato durante il quale questa tesi e stata sviluppata. La tecnologia del multisensore e la proprietà intellettuale di Solianis sono ora detenute da Biovotion AG (Zurigo, Svizzera). Solianis Monitoring AG ha fornito quarantacinque sessioni sperimentali collezionate da 6 pazienti soggetti a protocolli ipo ed iperglicemici presso l'University Hospital Zurich. I modelli identificati con le tecniche di cui sopra, sono testati con un insieme di dati diverso da quello utilizzato per l'identicazione dei modelli stessi. I risultati dimostrano chei metodi di controllo della complessita hanno accuratezza maggiore rispetto ad OLS. In generale, le tecniche basate su regolarizzazione sono migliori rispetto a PLS. In particolare, quelle che sfruttano la norma l1 (LASSO ed EN), pongono molti coefficienti del modello a zero rendendo i profili stimati di glucosio piu robusti a rumore occasionale che interessa alcuni canali del multi-sensore. In particolare, il modello EN risulta il migliore, condividendo sia le proprietà di sparsita e l'effetto raggruppamento indotte rispettivamente dalle norme l1 ed l2. In generale, i risultati indicano che, anche se le prestazioni, in termini di accuratezza dei profili di glucosio stimati, non sono ancora confrontabili con quelle dei sensori basati su aghi, la piattaforma multisensore combinata con il modello EN è un valido strumento per il monitoraggio in tempo reale dei trend glicemici. Una possibile applicazione si basa sull'utilizzo del'informazione dei trend glicemici per completare misure rade effettuate con metodi finger-prick. Sfruttando il concetto di rischio dinamico recentemente sviluppato, e' possibile dare una corretta valutazione di eventi potenzialmente pericolosi come l'ipoglicemia. La tesi si articola in tre parti principali: Parte I (che comprende i Capitoli 1-4), fornisce inizialmente un'introduzione sul diabete, una recensione delle attuali tecnologie per il monitoraggio non-invasivo della glicemia (incluso il dispositivo multisensore di Solianis) e gli obiettivi della tesi; Parte II (che comprende i Capitoli 5-9), presenta alcune delle difficoltà affrontate quando si lavora con problemi di regressione su dati di grandi dimensioni, per poi presentare OLS, PLS, LASSO, Ridge e EN sfruttando un esempio tutorial per evidenziarne vantaggi e svantaggi. Infine, Parte III, (Capitoli 10-12) presenta il set di dati del caso di studio ed i risultati. Alcune note conclusive e possibili sviluppi futuri terminano la tesi. In particolare, vengono brevemente illustrate una metodologia basata su simulazioni Monte Carlo per valutare la robustezza della calibrazione del modello e l'utilizzo di un nuova nuova funzione obiettivo per l'identicazione dei modelli.

The objective of this research is to apply micromachined silicon-based resonant gravimetric sensors to the detection of gas-phase volatile organic compounds (VOCs). This is done in two primary tasks: 1) the optimization and application of silicon disk resonators to the detection of gas-phase VOCs, and 2) the development and application of a novel gravimetric-capacitive multisensor platform for the detection of gas-phase VOCs. In the rst task, the design and fabrication of a silicon-based disk resonator structure utilizing an in-plane resonance mode is undertaken. The resonance characteristics of the disk resonator are characterized and optimized. The optimized characteristics include the resonator Q-factor as a function of geometric parameters, and the dynamic displacement of the in-plane resonance mode. The Q-factors of the disk resonators range from 2600 to 4360 at atmosphere for disk silicon thicknesses from 7 µm to 18 µm, respectively. The resonance frequency of the in-plane resonance mode ranges from 260 kHz up to 750 kHz. The disk resonators are applied to the sensing of gas-phase VOCs using (poly)isobutylene as a sensitive layer. Limits of detection for benzene, toluene and m-xylene vapors of 5.3 ppm, 1.2 ppm, and 0.6 ppm are respectively obtained. Finally, models for the limits of detection and chemical sensitivity of the resonator structures are developed for the case of the polymer layers used. In the second task, a silicon-based resonator is combined with a capacitive structure to produce a multisensor structure for the sensing of gas-phase VOCs. Fabrication of the multisensor structure is undertaken, and the sensor is theoretically modeled. The baseline capacitance of the capacitor component of the multisensor is estimated to be 170 fF. Finally, initial VOC detection results for the capacitive aspect of the sensor are obtained.

Wetlands are essential for controlling the global climate, sustaining the global hydrological cycle, conserving ecological variety, and ensuring human wellbeing. As wetlands are one of the most endangered environments due to land conversion, infrastructure development, and overexploitation, they require constant monitoring. In Sweden, there are 68 sites recognized as wetlands with international importance. The inundated area and the connectivity of the wetlands are affected by climate change. For this reason, we need to better delineate water bodies in these valuable environments. Advances in remote sensing technologies helped us to improve the monitoring of wetlands; however, detecting the presence of water under vegetation is still a challenge for correctly delineating the water extent. To address this issue and better detect the presence of water below vegetation, we employ different polarization of SAR sentinel-1 data in combination with optical sentinel-2. After preprocessing the images, we use the K-means clustering algorithm provided in the cloud computing platform of Google Earth Engine, to detect the increased backscatter coming from flooded vegetation duo to the double-bounce of the radar signal. We also take advantage of the high-resolution national land cover of Sweden as an ancillary layer to extract only the relevant information in our study area. Finally, we compare our results with hydroclimatic and field data gathered from the study area. Our workflow improves water-extent delineation in Swedish wetlands by 20% on average by detecting hidden water below the vegetation, which is generally not recognized by optical methods. The proposed method can be extended to monitor and study wetlands’ water availability and changes, contributing to the increase of their resilience to anthropogenic pressures and climate change.

Peat moorlands represent a nationally significant carbon store. Wildfires in peat moorlands release CO2 into the atmosphere, reducing the carbon store and burn into the seed bank preventing vegetation recovery. Burned areas of bare peat remain, known as ‘burn scars’ which are eroded by freeze thaw and desiccation, then weathered by precipitation and wind to cause discolouration of the water supply. A technique for the systematic monitoring of peat moorland burn scars is essential for informing land management and moorland restoration. Satellite data enables peat moorland burn scars to be monitored at the landscape scale for operational services e.g. European Forest Fire Information System (EFFIS). However, in the UK cloud is highly problematic for optical satellites and thermal data provides only a short window of opportunity for active fire detection. This thesis provides a unique line of enquiry by exploring the potential of Synthetic Aperture Radar (SAR) intensity and Interferometric Synthetic Aperture Radar (InSAR) coherence for burn scar characterisation and persistence, using a multi-temporal and multi-sensor approach for degraded peat moorland. The Peak District National Park (PDNP) was selected because it is a marginal moorland environment, which experiences high rates of peat erosion and will experience more wildfires, based on future projections of increased temperature, due to global warming. Initial SAR intensity results for the Bleaklow 2003 burn scar showed a clear post-fire increase of 7 dB for burned peat bog when acquired under wet conditions. Post-fire, dry − wet InSAR pairs were characterised by vegetation removal caused by combustion within the burn scar area, whereas wet − wet InSAR pairs characterised the burn scar, but also degraded peat moorland caused by previous wildfires blurring the new burn scar perimeter. Intensity differed significantly with slope for the PDNP 2003 wildfires, reducing the effectiveness of the technique for characterising burn scars on slopes facing away from the sensor, although these wildfires showed no significant difference on coherence for the inland bare ground class. When using coherence as a burn scar discriminator, this research found that it is essential to acquire InSAR pairs immediately post-fire with B⊥ < 550 m. Using a combination of intensity and coherence data a multi-difference colour composite was produced and an ISODATA classification applied. Results were reclassified to produce a burned area map with an overall map accuracy of 94% and Kappa Coefficient of 0.69 covering the Bleaklow and Kinder 2003 burn scars. Burn scars < 6 km2 provided a persistently higher burned area intensity signal for up to six months after the wildfire but only 2 − 3 months for coherence. The smaller Edale burn scar (0.10 km2) was characterised by 2 − 3 dB greater intensity for the burned area over a year after the wildfire. The Edale 2008 case study showed that L-band PALSAR data is less sensitive to characterising peat moorland burn scars compared to C-band data. This study therefore strongly recommends C-band data for peat moorland burn scar characterisation and monitoring. Future research will explore the new C-band Sentinel-1 data which offers improved spatial resolution and repeat-pass time.

La reconnaissance d'activités de vie quotidienne (AVQs) fait l'objet, depuis des années, de recherches pour proposer des solutions performantes. Elle s'appuie sur l'analyse spatio-temporelle de situations, de comportements, etc. dont les données d'entrée sont les informations fournies par des capteurs ambiants ou par des capteurs portés par la personne. Cette thèse se focalise sur l'instrumentation du lieu de vie par des capteurs ambiants et sur la détection d'un état d'isolement social chez les personnes âgées. Deux approches sont utilisées pour évaluer l'isolement social. La première se base sur des questionnaires. La deuxième approche s'appuie sur l'utilisation de technologies pour la récupération objective de données représentatives d'un état ou d'un comportement. En particulier, l'activité " se nourrir " est liée à une séquence d'actions telles que faire les courses, cuisiner, manger et faire la vaisselle. L'activité " se déplacer " est liée à la mobilité au sein du domicile et au fait de sortir du logement. La littérature montre que ces deux activités semblent pertinentes pour évaluer un risque potentiel d'isolement social chez les aînés. Les travaux de thèse portent sur quatre contributions principales : Un état bibliographique des recherches sur la détection des AVQs afin d'en identifier les apports et les limites et tracer des voies de recherches pertinentes. Des critères spécifiques ont été choisis pour inclure les articles dans lesquels des systèmes de détection d'activités sont présentés. Une démarche de conception système appliquée à la reconnaissance d'AVQs. Cette démarche s'intègre dans un processus d'Ingénierie Système. Elle décrit l'analyse des exigences, leur modélisation au travers de diagrammes SysML et la mise en place d'une architecture matérielle et logicielle basée sur un réseau IoT. L'analyse des AVQs, dans notre étude, utilise les données de détecteurs de mouvement et de capteurs de contacts. Un affichage sur une application web permet de visualiser les résultats obtenus à destination de l'aide-soignant ou de la famille. L'utilisation originale de quatre méthodes de classification des AVQs à savoir "préparer le repas", "prendre le repas", "faire la vaisselle", "dormir/se relaxer", "hygiène", "la personne à l'extérieur du logement", "un visiteur à l'intérieur de la maison" et "autres activités". Les trois premières méthodes utilisées sont K-means, le modèle de mélange gaussien et BIRCH auxquelles on applique une pondération aux données. Les activités liées au repas n'ont ainsi pas le même poids que le reste des données, ce qui a permis d'améliorer la détection des AVQs. Le quatrième algorithme est basé sur une méthode logique à la suite de la détermination d'une matrice de corrélation prenant en entrée l'ensemble des capteurs disponibles. En utilisant les données de la matrice de corrélation, l'algorithme personnalise la détection des activités liées au repas en différenciant une personne qui prépare seule son repas d'une personne qui bénéficie d'un service de portage de repas. Nous validons nos méthodes en se référant aux formulaires remplis par les participants au début et à la fin de l'expérimentation dans lesquels ils indiquent le déroulement de leur journée-type. Ces algorithmes ont été appliqués sur une base de données annotée ouverte pour confirmer la précision de nos approches. La proposition d'un score du niveau d'isolement social chez la personne suivie. Ce score est établi sur la base de l'identification des activités pour extraire les habitudes quotidiennes au travers d'indicateurs du comportement (Le temps passé à l'extérieur de la maison et à l'intérieur de la cuisine, etc.). Six aînées ont été suivies pendant plus de 3 mois. L'algorithme régression logistique a été utilisé pour l'extraction du niveau d'isolement social qui a été comparé à celui identifié grâce au questionnaire " Lubben Social Network Scale " rempli avec chaque participant au début et à la fin de l'étude
The recognition of daily life activities has been the subject of research for years to provide effective solutions. It is based on the spatio-temporal analysis of situations and behaviors whose input data is information provided by ambient sensors or by sensors worn by the person. This thesis focuses on the instrumentation of the living space by ambient sensors and on the detection of a state of social isolation in elderly people. Two approaches are used to assess social isolation. The first one is based on questionnaires. The second approach is based on the use of technologies for the objective acquisition of data representative of a state, behavior, etc. In particular, the activity "eating" is linked to a sequence of actions such as shopping, cooking, eating and washing dishes. The activity "moving" is linked to mobility within the home and leaving the home. The literature shows that these two activities seem to be relevant for assessing a potential risk of social isolation among older people. The thesis work focuses on four main contributions: A bibliographic review of ADLs detection research to identify its contributions and limitations, and to outline relevant research directions. Specific criteria were chosen to include articles presenting activity detection systems. A system design approach applied to the detection of ADLs. This approach is part of a system engineering process. It describes the analysis of requirements, their modeling through SysML diagrams and the implementation of a hardware and software architecture based on an IoT network. The analysis of ADLs, in our study, uses data from motion detectors and contact sensors. A display on a web application allows you to visualize the results obtained for the caregiver or the family. The original use of four methods to classify ADLs, namely "preparing the meal", "eating the meal", "washing the dishes", "sleeping/relaxing", "hygiene", "the person outside the home", "a visitor inside the home" and "other activities". The first three methods used are K-means, the Gaussian mixture model and BIRCH, which applies weights to the data. Meal-related activities therefore do not have the same weight as the rest of the data, which made it possible to improve the detection of ADLs. The fourth algorithm is based on a logical method following the determination of a correlation matrix using all the available sensors as input. Using the data from the correlation matrix, the algorithm personalizes the detection of meal-related activities by distinguishing a person preparing their meal from a person using a meal delivery service. We validate our methods by referring to the forms filled in by the participants at the beginning and end of the experiment, in which they describe the course of their typical day. These algorithms were applied to an open annotated database to confirm the accuracy of our approaches. The proposal of a score for the level of social isolation of the person being monitored. This score is based on the identification of activities to extract daily habits through behavioral indicators (time spent outside the house and in the kitchen, etc.). Six elderly people were followed for more than 3 months. The logistic regression algorithm was used to extract the level of social isolation, which was compared with the level of social isolation identified using the "Lubben Social Network Scale" questionnaire, which was completed by each participant at the beginning and end of the study

La rééducation fonctionnelle classique comprend des séances thérapeutiques, des exercices à domicile et des mouvements avec ou sans l'aide de thérapeutes. Cette approche classique souffre de nombreuses limitations, en raison de l’incapacité de l’expert à suivre les séances à domicile du patient et du manque de motivation du patient pour répéter les exercices sans retour. Les jeux sérieux ont été présentés comme une solution à ces problèmes. Premièrement, des exergames ont été développés à l’aide d’une méthodologie de codesign, où patients, experts et développeurs ont pris part aux procédures de conception. Le capteur Kinect a été utilisé pour capturer la cinématique en temps réel au cours de l’exercice. Ensuite, une fusion de données a été étudier entre le capteur Kinect et les unités de mesure inertielles, afin d’augmenter la précision de l’estimation de l’angle des articulations, à l’aide d’une approche système de systèmes. Le système a été évalué par des patients avec différentes pathologies au cours de multiples campagnes d'évaluation. Les résultats obtenus montrent que les jeux sérieux peuvent être une solution pour des pathologies spécifiques. En outre, les experts ont été convaincus de la pertinence clinique de ce dispositif et ont estimé que les données proposées étaient suffisantes pour évaluer la situation du patient. La mise en place de tels systèmes maximiserait l’efficacité du programme de réadaptation. D'autre part, ce système permettrait également de réduire les limitations actuellement présentes dans les programmes de rééducation classiques, permettant aux patients de visualiser leurs mouvements et aux experts de suivre l'exécution de l'exercice à domicile
Conventional musculoskeletal rehabilitation consists of therapeutic sessions, home exercise assignment, and movement execution with or without the assistance of therapists. This classical approach suffers from many limitations, due to the expert’s inability to follow the patient’s home sessions, and the patient’s lack of motivation to repeat the same exercises without feedback. Serious games have been presented as a possible solution for these problems. This thesis was carried out in the eBioMed experimental platform of the Université de technologie de Compiège, and in the framework of the Labex MS2T. The aim of this thesis is to develop a real-time, serious gaming system for home-based musculoskeletal rehabilitation. First, exergames were developed, using a codesign methodology, where the patients, experts and developers took part in the design and implementation procedures. The Kinect sensor was used to capture real-time kinematics during each exercise. Next, data fusion was implemented between the Kinect sensor and inertial measurement units, to increase the accuracy of joint angle estimation, using a system of systems approach. In addition, graphical user interfaces were developed, for experts and patients, to suit the needs of different end-users, based on the results of an end-user acceptability study. The system was evaluated by patients with different pathologies through multiple evaluation campaigns. Obtained results showed that serious games can be a good solution for specific types of pathologies. Moreover, experts were convinced of the clinical relevance of this device, and found that the estimated data was more than enough to assess the patient’s situation during their home-based exercise sessions. Finally, during these three years, we have set the base for a home-based rehabilitation system that can be deployed at home or in a clinical environment. The implementation of such systems would maximize the efficiency of rehabilitation program, while saving the patient’s and expert’s time and money. On the other hand, this system would also reduce the limitation that are currently present in classical rehabilitation programs, allowing the patients to visualize their movements, and the experts to follow the home exercise execution

Mestrado de dupla diplomação com a Université Libre de Tunis
Some microorganisms contribute beneficially in processing, safety and quality of certain food products. However, many microorganisms are involved in processes that cause undesirable effects on food, or on the health of consumers, leading to spoilage or to occurrence of foodborne diseases. For that, microbiological surveillance of food corresponds to an area of great interest to ensure the quality and the safety of food to prevent foodborne diseases. Indeed, for reasons related to sampling, methodology and distribution of the microorganisms in the matrix, microbiological analysis for itself does not guarantee the safety of a final product analyzed. For that, a possible promising alternative to the traditional diagnostic methods in the electronic sensors such as the E-tongues that has been used for different applications in food and pharmaceutical industries, they have been useful for the detection of bacterial contamination or diagnosis of infections. The aim of the present study was the detection and discrimination of microorganism that played an important role in food and environmental areas, namely E. coli, Enterococcus faecalis, Pseudomonas aeruginosa and S. aureus. In this context, electronic tongues (E-tongues) have been employed for the detection and screening of microorganisms. Thus; the use of a potentiometric E-tongue, comprising lipid polymeric sensor membranes, together with unsupervised and supervised chemometric tools (e.g., principal component analysis, PCA; linear discriminant analysis, LDA; and. multiple linear regression models, MLRM) was evaluated aiming to explore the advantages of these innovative (bio)sensing devices for microorganism’s recognition and discrimination, in aqueous solutions. Our results showed that the potentiometric signals profiles acquired by the 40 E-tongue sensors allowed a satisfactory unsupervised recognition of P. aeruginosa and E. faecalis, contrary to E. coli and S. aureus, showed a clear over-plotting. Still to further assess the E-tongue classification capability, a LDA was performed since it represents the most discriminant and non-redundant sensors selected by the SA algorithm. The supervised discriminant model allowed to classify 100% of the original grouped data. Overall, the unsupervised and supervised classification performances clearly showed the potential use of the E-tongue as an accurate and fast recognition device of the four microorganisms studied.
Alguns microrganismos contribuem para a segurança e qualidade de certos produtos alimentares. No entanto, outros grupos de microrganismos causam efeitos indesejáveis nos alimentos provocando a sua deterioração ou inclusive dando origem a doenças de origem alimentar colocando em risco a saúde dos consumidores. Neste contexto, a vigilância microbiológica dos alimentos é uma área de grande relevância de forma a garantir a qualidade e a segurança dos alimentos. Contudo, as técnicas analíticas convencionais utilizadas na deteção de microrganismos em alimentos são caras e demoradas. Alternativamente, podem ser aplicadas outras técnicas, nomeadamente línguas eletrónicas (LE), para cumprir essa tarefa crítica. Com este estudo pretendeu-se estudar a capacidade de deteção e discriminação de microrganismos que desempenham um papel importante nas áreas alimentares e ambientais, nomeadamente Escherichia coli, Enterococcus faecalis, Pseudomonas aeruginosa e Staphylococcus aureus. Para tal, utilizou-se uma LE potenciométrica e o seu desempenho de deteção foi avaliado recorrendo a ferramentas quimiométricas não supervisionadas e supervisionadas (análise principal de componentes, ACP; análise discriminante linear ADL). Os resultados mostraram que os sinais potenciométricos adquiridos pelos sensores da LE permitem reconhecer satisfatoriamente e não supervisionado a P. aeruginosa e o E. faecalis, ao contrário da E. coli e S. aureus A capacidade de classificação da LE foi ainda avaliada pela ADL, com vista a identificar os sensores não redundantes e com maior potencial discriminante. O modelo discriminatório supervisionado permitiu classificar 100% dos dados originais. Globalmente, os desempenhos de classificação confirmaram a possível utilização da LE como um dispositivo de reconhecimento preciso e rápido dos quatro microrganismos estudados.

Advances in sensor technology and computer science in the last three decades have boosted the importance of system identification and vibration-based structural health monitoring (SHM) in civil infrastructure safety and integrity assessment. On the other hand, practical and financial issues in system instrumentation, maintenance, and operation have remained as fundamental problems obstructing the widespread use of SHM applications. For this reason, to reduce system costs and improve practicality as well as sustainability, researchers have been working on emerging methods such as wireless, distributed, mobile, remote, smart, multisensory, and heterogeneous sensing systems. Smartphones with built-in batteries, processor units, and a variety of sensors, have stood as a promising hardware and software environment that can be used as SHM components. Communication capabilities with the web, enable them to compose a smart and participatory sensor network of outnumbered individuals. Besides, crowdsourcing power offered by citizens, sets a decentralized and self-governing SHM framework which can even be pertained by very limited equipment and labor resources. Yet, citizen engagement in an SHM framework brings numerous challenges as well as opportunities. In a citizen-induced SHM scenario, the system administrators have limited or no control over the sensor instrumentation and the operation schedule, and the acquired data is subjected change depending on the measurement conditions. The citizen-induced errors can stem from spatial, temporal, and directional uncertainties since the sensor configuration relies on smartphone users’ decisions and actions. Moreover, the sensor-structure coupling may be unavailable where the smartphone is carried by the user, and as a consequence, the vibration features measured by smartphones can be modified due to the human biomechanical system. In addition, in contrast with the conventional high fidelity sensors, smartphone sensors are of limited quality and are subjected to high noise levels. This dissertation utilizes multisensory smartphone features to solve citizen-induced uncertainties and develops a smartphone-based SHM methodology which enables a cyber-physical system through mobile crowdsourcing. Using smartphone computational and communicational power, combined with a variety of embedded sensors such as accelerometer, gyroscope, magnetometer and camera, spatiotemporal and biomechanical citizen-induced uncertainties can be eliminated from the crowdsourced smartphone data, and eventually, structural vibrations collected from numerous buildings and bridges can be collected on a single cloud server. Therefore, unlike the conventional platforms designed and implemented for a particular structure, citizen-engaged and smartphone-based SHM can serve as intelligent, scalable, fully autonomous, cost-free, and durable cyber-physical systems drastically changing the forthcoming trends in civil infrastructure monitoring. In this dissertation, iOS is used as the application development platform to produce a smartphone-based SHM prototype, namely Citizen Sensors for SHM. In addition, a web-based software is developed and cloud services are implemented to connect individual smartphones to an administrator base and automate data submission and processing procedure accordingly. Finally, solutions to citizen-induced problems are provided through numerous laboratory and field test applications to prove the feasibility of smartphone-based SHM with real life examples. Through collaborative use of the software, principles and methodologies presented in this dissertation, smartphones can be the core component of futuristic smart, resilient, and sustainable city and infrastructure systems. And this study lays down an innovative and integrated foundation empowering citizens to achieve these goals.