No description available.

This work focuses on a cognitive science inspired solution to an event detection problem in a video domain. The thesis raises the question whether video sequences that are taken in highway tunnels can be used to create meaningful data in terms of symbolic representation, and whether these symbolic representations can be used as sequences to be parsed by attribute grammars into abnormal and normal events. The main motivation of the research was to develop a novel algorithm that parses sequences of primitive events created by the image processing algorithms. The domain of the research is video detection and the special application purpose is for highway tunnels, which are critical places for abnormality detection. The method used is attribute grammars to parse the sequences. The symbolic sequences are created from a cascade of image processing algorithms such as / background subtracting, shadow reduction and object tracking. The system parses the sequences and creates alarms if a car stops, moves backwards, changes lanes, or if a person walks into the road or is in the vicinity when a car is moving along the road. These critical situations are detected using Earley&rsquo / s parser, and the system achieves real-time performance while processing the video input. This approach substantially lowers the number of false alarms created by the lower level image processing algorithms by preserving the number of detected events at a maximum. The system also achieves a high compression rate from primitive events while keeping the lost information at minimum. The output of the algorithm is measured against SVM and observed to be performing better in terms of detection and false alarm performance.

No description available.

Notre travail porte sur le développement d'algorithmes performants d'application de grammaires locales, en prenant comme référence ceux des logiciels libres existants: l'analyseur syntaxique descendant d'Unitex et l'analyseur syntaxique à la Earley d'Outilex. Les grammaires locales sont un formalisme de représentation de la syntaxe des langues naturelles basé sur les automates finis. Les grammaires locales sont un modèle de construction de descriptions précises et à grande échelle de la syntaxe des langues naturelles par le biais de l'observation systématique et l'accumulation méthodique de données. L'adéquation des grammaires locales pour cette tâche a été testée à l'occasion de nombreux travaux. À cause de la nature ambiguë des langues naturelles et des propriétés des grammaires locales, les algorithmes classiques d'analyse syntaxique tels que LR, CYK et Tomita ne peuvent pas être utilisés dans le contexte de ce travail. Les analyseurs descendant et Earley sont des alternatives possibles, cependant, ils ont des coûts asymptotiques exponentiels pour le cas des grammaires locales. Nous avons d'abord conçu un algorithme d'application de grammaires locales avec un coût polynomial dans le pire des cas. Ensuite, nous avons conçu des structures de données performantes pour la représentation d'ensembles d'éléments et de séquences. Elles ont permis d'améliorer la vitesse de notre algorithme dans le cas général. Nous avons mis en oeuvre notre algorithme et ceux des systèmes Unitex et Outilex avec les mêmes outils afin de les tester dans les mêmes conditions. En outre, nous avons mis en oeuvre différentes versions de chaque algorithme en utilisant nos structures de données et algorithmes pour la représentation d'ensembles et ceux fournis par la Standard Template Library (STL) de GNU. Nous avons comparé les performances des différents algorithmes et de leurs variantes dans le cadre d'un projet industriel proposé par l'entreprise Telefónica I+D: augmenter la capacité de compréhension d'un agent conversationnel qui fournit des services en ligne, voire l'envoi de SMS à des téléphones portables ainsi que des jeux et d'autres contenus numériques. Les conversations avec l'agent sont en espagnol et passent par Windows Live Messenger. En dépit du domaine limité et de la simplicité des grammaires appliquées, les temps d'exécution de notre algorithme, couplé avec nos structures de données et algorithmes pour la représentation d'ensembles, ont été plus courts. Grâce au coût asymptotique amélioré, on peut s'attendre à des temps d'exécution significativement inférieurs par rapport aux algorithmes utilisés dans les systèmes Unitex et Outilex, pour le cas des grammaires complexes et à large couverture.

This PhD thesis deals with the use of structural methods of objects identification for industrial robots operation. First, the present state of knowledge in the field is described, i.e. the whole process of objects recognition with the aid of common methods of the syntactic analysis. The main disadvantage of these methods is that is impossible to recognize objects whose digitalized image is corrupted in some ways (due to excessive noise or image disturbances), objects are therefore deformed. Further, other methods for the recognition of deformed objects are described. These methods use structural description of objects for object recognition, i.e. methods which determine the distance between attribute descriptions of images. The core part of this PhD thesis begins in Chapter 5, where deformation grammars, capable of description of all possible object deformations, are described. The only complication in the analysis is the ambiguity of the deformation grammar, which lowers the effectiveness of the analysis. Further, PhD thesis deals with the selection and modification of a proper parser, which is able to analyze a deformation grammar effectively. Three parsers are described: the modified Earley parser, the modified Tomita parser and the modified hybrid LRE(k) parser. As for the modified Earley’s parser, ways of its effective implementation are described. One of the necessary parts of the object recognition is providing the invariances, which this PhD thesis covers in detail, too. Finally, the results of described algorithms are mentioned (successfulness and speed of deformed objects recognition) and suggested testing environment and implemented algorithms are described. In conclusion, all determined possibilities of deformation grammars and their results are summarized.

<p>Synthesized speech may be used for nefarious purposes, such as fraud, spoofing, and misinformation campaigns. We present several speech forensics methods based on deep learning to protect against such attacks. First, we use a convolutional neural network (CNN) and transformers to detect synthesized speech. Then, we investigate closed set and open set speech synthesizer attribution. We use a transformer to attribute a speech signal to its source (i.e., to identify the speech synthesizer that created it). Additionally, we show that our approach separates different known and unknown speech synthesizers in its latent space, even though it has not seen any of the unknown speech synthesizers during training. Next, we explore machine learning for an objective in the aerospace domain.</p> <p><br></p> <p>Compared to conventional ballistic vehicles and cruise vehicles, hypersonic glide vehicles (HGVs) exhibit unprecedented abilities. They travel faster than Mach 5 and maneuver to evade defense systems and hinder prediction of their final destinations. We investigate machine learning for identifying different HGVs and a conic reentry vehicle (CRV) based on their aerodynamic state estimates. We also propose a HGV flight phase prediction method. Inspired by natural language processing (NLP), we model flight phases as “words” and HGV trajectories as “sentences.” Next, we learn a “grammar” from the HGV trajectories that describes their flight phase transition patterns. Given “words” from the initial part of a HGV trajectory and the “grammar”, we predict future “words” in the “sentence” (i.e., future HGV flight phases in the trajectory). We demonstrate that this approach successfully predicts future flight phases for HGV trajectories, especially in scenarios with limited training data. We also show that it can be used in a transfer learning scenario to predict flight phases of HGV trajectories that exhibit new maneuvers and behaviors never seen before during training.</p>