In the field of video surveillance, vast amounts of data are gathered each day. To be able to identify what occurred during a recorded session, a human annotator has to go through the footage and annotate the different events. This is a tedious and expensive process that takes up a large amount of time. With the rise of machine learning and in particular deep learning, the field of both image and video captioning has seen large improvements. Contrastive Language-Image Pretraining is capable of efficiently learning a multimodal space, thus able to merge the understanding of text and images. This enables visual features to be extracted and processed into text describing the visual content. This thesis presents a system for extracting and ranking important events from surveillance videos as well as a way of automatically generating a description of the event. By utilizing the pre-trained models X-CLIP and GPT-2 to extract visual information from the videos and process it into text, a video captioning model was created that requires very little training. Additionally, the ranking system was implemented to extract important parts in video, utilizing anomaly detection as well as polynomial regression. Captions were evaluated using the metrics BLEU, METEOR, ROUGE and CIDEr, and the model receives scores comparable to other video captioning models. Additionally, captions were evaluated by experts in the field of video surveillance, who rated them on accuracy, reaching up to 62.9%, and semantic quality, reaching 99.2%. Furthermore the ranking system was also evaluated by the experts, where they agree with the ranking system 78% of the time. / Inom videoövervakning samlas stora mängder data in varje dag. För att kunna identifiera vad som händer i en inspelad övervakningsvideo så måste en människa gå igenom och annotera de olika händelserna. Detta är en långsam och dyr process som tar upp mycket tid. Under de senaste åren har det setts en enorm ökning av användandet av olika maskininlärningsmodeller. Djupinlärningsmodeller har fått stor framgång när det kommer till att generera korrekt och trovärdig text. De har också använts för att generera beskrivningar för både bilder och video. Contrastive Language-Image Pre-training har gjort det möjligt att träna en multimodal rymd som kombinerar förståelsen av text och bild. Detta gör det möjligt att extrahera visuell information och skapa textbeskrivningar. Denna master uppsatts beskriver ett system som kan extrahera och ranka viktiga händelser i en övervakningsvideo samt ett automatiskt sätt att generera beskrivningar till dessa. Genom att använda de förtränade modellerna X-CLIP och GPT-2 för att extrahera visuell information och textgenerering, har en videobeskrivningsmodell skapats som endast behöver en liten mängd träning. Dessutom har ett rankingsystem implementerats för att extrahera de viktiga delarna i en video genom att använda anomalidetektion och polynomregression. Video beskrivningarna utvärderades med måtten BLEU, METOER, ROUGE och CIDEr, där modellerna får resultat i klass med andra videobeskrivningsmodeller. Fortsättningsvis utvärderades beskrivningarna också av experter inom videoövervakningsområdet där de fick besvara hur bra beskrivningarna var i måtten: beskrivningsprecision som uppnådde 62.9% och semantisk kvalité som uppnådde 99.2%. Ranknignssystemet utvärderades också av experterna. Deras åsikter överensstämde till 78% med rankningssystemet.

<p dir="ltr">Anomaly detection is an active research field that widely applies to commercial applications to detect unusual patterns or outliers. Time series anomaly detection provides valuable insights into mission and safety-critical applications using ever-growing temporal data, including continuous streaming time series data from the Internet of Things (IoT), sensor networks, healthcare, stock prices, computer metrics, and application monitoring. While Generative Adversarial Networks (GANs) demonstrate promising results in time series anomaly detection, the opaque nature of generative deep learning models lacks explainability and hinders broader adoption. Understanding the rationale behind model predictions and providing human-interpretable explanations are vital for increasing confidence and trust in machine learning (ML) frameworks such as GANs. This study conducted a structured and comprehensive assessment of post-hoc local explainability in GAN-based time series anomaly detection using SHapley Additive exPlanations (SHAP). Using publicly available benchmarking datasets approved by Purdue’s Institutional Review Board (IRB), this study evaluated state-of-the-art GAN frameworks identifying their advantages and limitations for time series anomaly detection. This study demonstrated a systematic approach in quantifying the extent of GAN-based time series anomaly explainability, providing insights for businesses when considering adopting generative deep learning models. The presented results show that GANs capture complex time series temporal distribution and are applicable for anomaly detection. The analysis from this study shows SHAP can identify the significance of contributing features within time series data and derive post-hoc explanations to quantify GAN-detected time series anomalies.</p>

Dans ce mémoire, nous présentons une étude visant à améliorer les soins aux personnes âgées grâce à la mise en œuvre d'un système de vidéosurveillance intelligent avancé. Ce système est conçu pour exploiter la puissance des algorithmes d’apprentissage profond pour détecter les anomalies de mobilité, avec un accent particulier sur l’identification des quasi-chutes. L’importance d’identifier les quasi-chutes réside dans le fait que les personnes qui subissent de tels événements au cours de leurs activités quotidiennes courent un risque accru de subir des chutes à l’avenir pouvant mener à des blessures graves et une hospitalisation. L’une des principales réalisations de notre étude est le développement d’un auto-encodeur capable de détecter les anomalies de mobilité, en particulier les quasi-chutes, en identifiant des erreurs de reconstruction élevées sur cinq images consécutives. Pour extraire avec précision une structure squelettique de la personne, nous avons utilisé MoveNet et affiné ce modèle sur sept points clés. Par la suite, nous avons utilisé un ensemble complet de 20 caractéristiques, englobant les positions des articulations, les vitesses, les accélérations, les angles et les accélérations angulaires, pour entraîner l’auto-encodeur. Afin d'évaluer l'efficacité de notre modèle, nous avons effectué des tests rigoureux à l'aide de 100 vidéos d'activités quotidiennes simulées enregistrées dans un laboratoire d'appartement, la moitié des vidéos contenant des cas de quasi-chutes. Un autre ensemble de 50 vidéos a été utilisé pour l’entrainement. Les résultats de notre phase de test sont très prometteurs, car ils indiquent que notre modèle est capable de détecter efficacement les quasi-chutes avec une sensibilité, une spécificité et une précision impressionnantes de 90 %. Ces résultats soulignent le potentiel de notre modèle à améliorer considérablement les soins aux personnes âgées dans leur environnement de vie. / In this thesis, we present a comprehensive study aimed at enhancing elderly care through the implementation of an advanced intelligent video surveillance system. This system is designed to leverage the power of deep learning algorithms to detect mobility anomalies, with a specific focus on identifying near-falls. The significance of identifying near-falls lies in the fact that individuals who experience such events during their daily activities are at an increased risk of experiencing falls in the future that can lead to serious injury and hospitalization. A key achievement of our study is the successful development of an autoencoder capable of detecting mobility anomalies, particularly near-falls, by pinpointing high reconstruction errors across five consecutive frames. To precisely extract a person's skeletal structure, we utilized MoveNet and focused on seven key points. Subsequently, we employed a comprehensive set of 20 features, encompassing joint positions, velocities, accelerations, angles, and angular accelerations, to train the model. In order to assess the efficacy of our model, we conducted rigorous testing using 100 videos of simulated daily activities recorded in an apartment laboratory, with half of the videos containing instances of near-falls. Another set of 50 videos was used for training. The results from our testing phase are highly promising, as they indicate that our model is able to effectively detect near-falls with an impressive 90% sensitivity, specificity, and accuracy. These results underscore the potential of our model to significantly enhance elderly care within their living environments.

<p dir="ltr">Lessons learned in protecting desktop computers, servers, and cloud systems from cyberattacks have not translated to embedded systems easily. Yet, embedded systems impact our lives in many ways and are subject to similar risks. In particular, real-time embedded systems are computer systems controlling critical physical processes in industrial controllers, avionics, engine control systems, etc. Attacks have been reported on real-time embedded systems, some with devastating outcomes on the physical processes. Detecting intrusions in real-time is a prerequisite to an effective response to ensure resilience to damaging attacks. In anomaly detection methods, researchers typically model expected program behavior and detect deviations. This approach has the advantage of detecting zero-day attacks compared to signature-based intrusion detection methods; however, existing anomaly detection approaches suffer high false-positive rates and incur significant performance overhead caused by code instrumentation, making them impractical for hard real-time embedded systems, which must meet strict temporal constraints.</p><p dir="ltr">This thesis presents a hardware-assisted anomaly detection approach that uses an automaton to model valid control-flow transfers in hard real-time systems without code instrumentation. The approach relies on existing hardware mechanisms to capture and export runtime control-flow data for runtime verification without the need for code instrumentation, thereby preserving the temporal properties of the target program. We implement a prototype of the mechanism on the Xilinx Zynq Ultrascale+ platform and empirically demonstrate precise detection of control-flow hijacking attacks with negligible (0.18%) performance overhead without false alarms using a real-time variant of the well-known RIPE benchmark we developed for this work. We further empirically demonstrate via schedulability analysis that protecting a real-time program with the proposed anomaly detection mechanism preserves the program’s temporal constraints.</p>

This thesis presents a body of work on the theme of millimetre-wave FMCW radar, for the purposes of security screening and remote sensing. First, the development of an optimised software radar signal processor will be outlined. Through use of threading and GPU acceleration, high data processing rates were achieved using standard PC hardware. The flexibility of this approach, compared to specialised hardware (e.g. DSP, FPGA etc…), allowed the processor to be rapidly adapted and has produced a significant performance increase in a number of advanced real-time radar systems. An efficient tracker was developed and was successfully deployed in live trials for the purpose of real-time wave detection in an autonomous boat control system. Automated radar operation and remote data telemetry functions were implemented in a terrain mapping radar to allow continuous monitoring of the Soufrière Hills volcano on the Caribbean island of Montserrat. This work concluded with the installation of the system 3 km from the volcano. Hardware modifications were made to enable coherent measurement in a number of existing radar systems, allowing phase sensitive measurements, including range-Doppler, to be performed. Sensitivity to displacements of less than 200 nm was demonstrated, which is limited by the phase noise of the system. Efficient compensation techniques are presented which correct for quadrature mixer imbalance, FMCW chirp non-linearity, and scanner drive distortions. In collaboration with the Home Office, two radar systems were evaluated for the stand-off detection of concealed objects. Automatic detection capability, based on polarimetric signatures, was developed using data gathered under controlled conditions. Algorithm performance was assessed through blind testing across a statistically significant number of subjects. A detailed analysis is presented, which evaluates the effect of clothing and object type on detection efficiency.

Recommendation systems are information filtering systems that help users effectively and efficiently explore large amount of information and identify items of interest. Accurate predictions of users' interests improve user satisfaction and are beneficial to business or service providers. Researchers have been making tremendous efforts to improve the accuracy of recommendations. Emerging trends of technologies and application scenarios, however, lead to challenges other than accuracy for recommendation systems. Three new challenges include: (1) opinion spam results in untrustworthy content and makes recommendations deceptive; (2) users prefer diversified content; (3) in some applications user behavior data may not be available to infer users' preference. This thesis tackles the above challenges. We identify features of untrustworthy commercial campaigns on a question and answer website, and adopt machine learning-based techniques to implement an adaptive detection system which automatically detects commercial campaigns. We incorporate diversity requirements into a classic theoretical model and develop efficient algorithms with performance guarantees. We propose a novel and robust approach to infer user preference profile from recommendations using copula models. The proposed approach can offer in-depth business intelligence for physical stores that depend on Wi-Fi hotspots for mobile advertisement. / Graduate / 0984 / cchenv@uvic.ca

This dissertation investigates and introduces novel algorithms, theories, and supporting frameworks to significantly improve the growing problem of Internet security. A distributed firewall and active response architecture is introduced that enables any device within a cyber environment to participate in the active discovery and response of cyber attacks. A theory of semantic association systems is developed for the general problem of knowledge discovery in data. The theory of semantic association systems forms the basis of a novel semantic path merger packet classification algorithm. The theoretical aspects of the semantic path merger packet classification algorithm are investigated, and the algorithm's hardware-based implementation is evaluated along with comparative analysis versus content addressable memory. Experimental results show that the hardware implementation of the semantic path merger algorithm significantly outperforms content addressable memory in terms of energy consumption and operational timing.

Le thème principal de cette thèse est d’étudier la détection d’anomalies dans des flux de données de grande dimension avec une application spécifique au Health Monitoring des moteurs d’avion. Dans ce travail, on considère que le problème de la détection d’anomalies est un problème d’apprentissage non supervisée. Les données modernes, notamment celles issues de la surveillance des systèmes industriels sont souvent des flux d’observations de grande dimension, puisque plusieurs mesures sont prises à de hautes fréquences et à un horizon de temps qui peut être infini. De plus, les données peuvent contenir des anomalies (pannes) du système surveillé. La plupart des algorithmes existants ne peuvent pas traiter des données qui ont ces caractéristiques. Nous introduisons d’abord un algorithme de clustering probabiliste offline dans des sous-espaces pour des données de grande dimension qui repose sur l’algorithme d’espérance-maximisation (EM) et qui est, en plus, robuste aux anomalies grâce à la technique du trimming. Ensuite, nous nous intéressons à la question du clustering probabiliste online de flux de données de grande dimension en développant l’inférence online du modèle de mélange d’analyse en composantes principales probabiliste. Pour les deux méthodes proposées, nous montrons leur efficacité sur des données simulées et réelles, issues par exemple des moteurs d’avion. Enfin, nous développons une application intégrée pour le Health Monitoring des moteurs d’avion dans le but de détecter des anomalies de façon dynamique. Le système proposé introduit des techniques originales de détection et de visualisation d’anomalies reposant sur les cartes auto-organisatrices. Des résultats de détection sont présentés et la question de l’identification des anomalies est aussi discutée. / The subject of this Thesis is to study anomaly detection in high-dimensional data streams with a specific application to aircraft engine Health Monitoring. In this work, we consider the problem of anomaly detection as an unsupervised learning problem. Modern data, especially those is-sued from industrial systems, are often streams of high-dimensional data samples, since multiple measurements can be taken at a high frequency and at a possibly infinite time horizon. More-over, data can contain anomalies (malfunctions, failures) of the system being monitored. Most existing unsupervised learning methods cannot handle data which possess these features. We first introduce an offline subspace clustering algorithm for high-dimensional data based on the expectation-maximization (EM) algorithm, which is also robust to anomalies through the use of the trimming technique. We then address the problem of online clustering of high-dimensional data streams by developing an online inference algorithm for the popular mixture of probabilistic principal component analyzers (MPPCA) model. We show the efficiency of both methods on synthetic and real datasets, including aircraft engine data with anomalies. Finally, we develop a comprehensive application for the aircraft engine Health Monitoring domain, which aims at detecting anomalies in aircraft engine data in a dynamic manner and introduces novel anomaly detection visualization techniques based on Self-Organizing Maps. Detection results are presented and anomaly identification is also discussed.

The purpose of this research is to study the detection of temporal changes between two (or more) multimodal images satellites, i.e., between two different imaging modalities acquired by two heterogeneous sensors, giving for the same scene two images encoded differently and depending on the nature of the sensor used for each acquisition. The two (or multiple) multimodal satellite images are acquired and coregistered at two different dates, usually before and after an event. In this study, we propose new models belonging to different categories of multimodal change detection in remote sensing imagery. As a first contribution, we present a new constraint scenario expressed on every pair of pixels existing in the before and after image change. A second contribution of our work is to propose a spatio-temporal textural gradient operator expressed with complementary norms and also a new filtering strategy of the difference map resulting from this operator. Another contribution consists in constructing an observation field from a pair of pixels and to infer a solution maximum a posteriori sense. A fourth contribution is proposed which consists to build a common feature space for the two heterogeneous images. Our fifth contribution lies in the modeling of patterns of change by anomalies and on the analysis of reconstruction errors which we propose to learn a non-supervised model from a training base consisting only of patterns of no-change in order that the built model reconstruct the normal patterns (non-changes) with a small reconstruction error. In the sixth contribution, we propose a pairwise learning architecture based on a pseudosiamese CNN network that takes as input a pair of data instead of a single data and constitutes two partly uncoupled CNN parallel network streams (descriptors) followed by a decision network that includes fusion layers and a loss layer in the sense of the entropy criterion. The proposed models are enough flexible to be used effectively in the monomodal change detection case. / Cette recherche a pour objet l’étude de la détection de changements temporels entre deux (ou plusieurs) images satellitaires multimodales, i.e., avec deux modalités d’imagerie différentes acquises par deux capteurs hétérogènes donnant pour la même scène deux images encodées différemment suivant la nature du capteur utilisé pour chacune des prises de vues. Les deux (ou multiples) images satellitaires multimodales sont prises et co-enregistrées à deux dates différentes, avant et après un événement. Dans le cadre de cette étude, nous proposons des nouveaux modèles de détection de changement en imagerie satellitaire multimodale semi ou non supervisés. Comme première contribution, nous présentons un nouveau scénario de contraintes exprimé sur chaque paire de pixels existant dans l’image avant et après changement. Une deuxième contribution de notre travail consiste à proposer un opérateur de gradient textural spatio-temporel exprimé avec des normes complémentaires ainsi qu’une nouvelle stratégie de dé-bruitage de la carte de différence issue de cet opérateur. Une autre contribution consiste à construire un champ d’observation à partir d’une modélisation par paires de pixels et proposer une solution au sens du maximum a posteriori. Une quatrième contribution est proposée et consiste à construire un espace commun de caractéristiques pour les deux images hétérogènes. Notre cinquième contribution réside dans la modélisation des zones de changement comme étant des anomalies et sur l’analyse des erreurs de reconstruction dont nous proposons d’apprendre un modèle non-supervisé à partir d’une base d’apprentissage constituée seulement de zones de non-changement afin que le modèle reconstruit les motifs de non-changement avec une faible erreur. Dans la dernière contribution, nous proposons une architecture d’apprentissage par paires de pixels basée sur un réseau CNN pseudo-siamois qui prend en entrée une paire de données au lieu d’une seule donnée et est constituée de deux flux de réseau (descripteur) CNN parallèles et partiellement non-couplés suivis d’un réseau de décision qui comprend de couche de fusion et une couche de classification au sens du critère d’entropie. Les modèles proposés s’avèrent assez flexibles pour être utilisés efficacement dans le cas des données-images mono-modales.

<p> This thesis presents work and simulations containing the use of Artificial Intelligence for real-time perception and real-time anomaly detection using the computer and sensors onboard an Unmanned Aerial Vehicle. One goal of this research is to develop a highly accurate, high-performance computer vision system that can then be used as a framework for object detection, obstacle avoidance, motion estimation, 3D reconstruction, and vision-based GPS denied path planning. The method developed and presented in this paper integrates software and hardware techniques to reach optimal performance for real-time operations. </p> <p>This thesis also presents a solution to real-time anomaly detection using neural networks to further the safety and reliability of operations for the UAV. Real-time telemetry data from different sensors are used to predict failures before they occur. Both these systems together form the framework behind the Intelligent UAV platform, which can be rapidly adopted for different varieties of use cases because of its modular nature and on-board suite of sensors. </p>