This thesis presents a system to display Structural Health Monitoring (SHM) data interactively at multiple scales that range from milliseconds to years. Typically, visualizing large SHM datasets produce static plots that take significant time to render. Our system improves upon standard tools by providing an interactive interface and a speed-optimized binning algorithm. Using the interface, a user is able to view data collected from a bridge's sensors at multiple scales in a web browser. This allows a user to visually inspect the entire range of their data to see both short and long-term trends. To render the data, the system uses a binning algorithm to calculate a five-number summary of a range of data. Those bins are combined to generate increasingly high levels of bins, which are then rendered as a binned line chart. The chart is rendered using a standard web browser on both desktop and mobile devices.

Cette thèse étudie les approches de classification automatique basées sur les modèles de mélange gaussiens et les critères de choix de modèles pour la classification automatique de données discrétisées. Quatorze algorithmes binned-EM et quatorze algorithmes bin-EM-CEM sont développés pour quatorze modèles de mélange gaussiens parcimonieux. Ces nouveaux algorithmes combinent les avantages des données discrétisées en termes de réduction du temps d’exécution et les avantages des modèles de mélange gaussiens parcimonieux en termes de simplification de l'estimation des paramètres. Les complexités des algorithmes binned-EM et bin-EM-CEM sont calculées et comparées aux complexités des algorithmes EM et CEM respectivement. Afin de choisir le bon modèle qui s'adapte bien aux données et qui satisfait les exigences de précision en classification avec un temps de calcul raisonnable, les critères AIC, BIC, ICL, NEC et AWE sont étendus à la classification automatique de données discrétisées lorsque l'on utilise les algorithmes binned-EM et bin-EM-CEM proposés. Les avantages des différentes méthodes proposées sont illustrés par des études expérimentales. / This thesis studies the Gaussian mixture model-based clustering approaches and the criteria of model selection for binned data clustering. Fourteen binned-EM algorithms and fourteen bin-EM-CEM algorithms are developed for fourteen parsimonious Gaussian mixture models. These new algorithms combine the advantages in computation time reduction of binning data and the advantages in parameters estimation simplification of parsimonious Gaussian mixture models. The complexities of the binned-EM and the bin-EM-CEM algorithms are calculated and compared to the complexities of the EM and the CEM algorithms respectively. In order to select the right model which fits well the data and satisfies the clustering precision requirements with a reasonable computation time, AIC, BIC, ICL, NEC, and AWE criteria, are extended to binned data clustering when the proposed binned-EM and bin-EM-CEM algorithms are used. The advantages of the different proposed methods are illustrated through experimental studies.

Cette thèse s'inscrit dans le cadre de la classification automatique de données symboliques par des méthodes géométriques bio-inspirées, plus spécifiquement par les cartes auto-organisatrices. Nous mettons en place plusieurs algorithmes d'apprentissage des cartes auto-organisatrices pour classifier des données symboliques mixtes ainsi que des données de type intervalle et des données discrétisées. Plusieurs jeux de données symboliques simulées et réelles, dont deux construits dans le cadre de cette thèse, sont utilisés pour tester les méthodes proposées. En plus, nous proposons une carte auto-organisatrice pour les données discrétisées (binned data) dans le but d'accélérer l'apprentissage des cartes classiques et nous appliquons la méthode proposée à la segmentation d'images. / This thesis concerns the clustering of symbolic data with bio-inspired geometric methods, more specifically with Self-Organizing Maps. We set up several learning algorithms for the self-organizing maps in order to cluster mixed-feature symbolic data as well as interval-valued data and binned data. Several simulated and real symbolic data sets, including two sets built as part of this thesis, are used to test the proposed methods. In addition, we propose a self-organizing map for binned data in order to accelerate the learning of standard maps, and we use the proposed method for image segmentation.

As more devices with different service requirements become connected to networked systems, such as Internet of Things (IoT) devices, maintaining quality of service becomes increasingly difficult. Large data sets can be obtained ahead of time in networks to train prediction models offline, however, resulting in high computational costs. Online learning is an alternative approach where a smaller cache of fixed size is maintained for training using sample selection algorithms, allowing for lower computational costs and real-time model re-computation. This project has resulted in two newly designed sample selection algorithms, Binned Relevance and Redundancy Sample Selection (BRR-SS) and Autoregressive First, In First Out-buffer (AR-FIFO). The algorithms are evaluated on data traces retrieved from a Key Value store and a Video on Demand service. Prediction accuracy of the resulting model while using the sample selection algorithms and the time to process a received sample is evaluated and compared to the pre-existing Reservoir Sampling (RS) and Relevance and Redundancy Sample Selection (RR-SS) with and without model re-computation. The results show that, while RS maintains the lowest computational overhead, BRR-SS outperforms both RS and RR-SS in prediction accuracy on the investigated traces. AR-FIFO, with its low computational cost, outperforms offline learning for larger cache sizes on the Key Value data set but shows inconsistencies on the Video on Demand trace. Model re-computation results in reduced error rates and significantly lowered variance on the investigated data traces, where periodic model re-computation overall outperforms change detection in practicality, prediction accuracy, and computational overhead. / Allteftersom fler enheter med olika servicekrav ansluts till nätverkssystem, såsom Internet of Things (IoT) enheter, ökar svårigheten att erhålla nödvändig servicekvalitet. Nätverk kan ge upphov till stora datamängder för träning av prediktionsmodeller offline, dock till en hög beräkningskostnad. Ett alternativt tillvägagångssätt är onlineinlärning där en mindre cache av fast storlek upprätthålls för träning med hjälp av datapunkturvalsalgoritmer. Detta möjliggör lägre beräkningskostnader samt realtidsmodellomräkningar. Detta projekt har resulterat i två nydesignade datapunkturvalsalgoritmer, Binned Relevance and Redundancy Sample Selection (BRR-SS) och Autoregressive First In, First Out-buffer (AR-FIFO). Algoritmerna utvärderas på dataspår som hämtats från ett Key Value-lager och en Video on Demand-tjänst. Förutsägelseförmåga för den resulterande modellen när datapunkturvalsalgoritmerna används och tid för bearbetning av mottagen datapunkt utvärderas och jämförs med dem redan existerande Reservoir Sampling (RS) och Relevance and Redundancy Sample Selection (RR-SS), med och utan modellomräkning. RS resulterar i lägst beräkningskostnad medan BRR-SS överträffar både RS och RR-SS i förutsägelseförmåga på dem undersökta spåren. AR-FIFO, med sin låga beräkningskostnad, överträffar offlineinlärning för större cachestorlekar på Key Value-spåret, men visar inkonsekvent beteende på Video on Demand-spåret. Modellomräkning resulterar i mindre fel och avsevärt sänkt varians på dem undersökta spåren, där periodisk modellomräkning totalt sett överträffar förändringsdetektering i praktikalitet, förutsägelseförmåga och beräkningskostnad. / Kandidatexjobb i elektroteknik 2022, KTH, Stockholm