In this dissertation, we study fractal sets and their properties, especially the open set condition, Hausdorff dimensions and Hausdorff measures for certain fractal constructions.

Machine learning algorithms have shown their abilities to tackle difficult recognition problems, but they are still rife with challenges. Among these challenges is how to deal with problems where new categories constantly occur, and the datasets can dynamically grow. Most contemporary learning algorithms developed to this point are governed by the assumptions that all testing data classes must be the same as training data classes, often with equal distribution. Under these assumptions, machine-learning algorithms can perform very well, using their ability to handle large feature spaces and classify outliers. The systems under these assumptions are called Closed Set Recognition systems (CSR). However, these assumptions cannot reflect practical applications in which out-of-set data may be encountered. This adversely affects the recognition prediction performances. When samples from a new class occur, they will be classified as one of the known classes. Even if this sample is far from any of the training samples, the algorithm may classify it with a high probability, that is, the algorithm will not only be wrong, but it may also be very confident in its results. A more practical problem is Open Set Recognition (OSR), where samples of classes not seen during training may show up at testing time. Inherently, there is a problem how the system can identify the novel sound classes and how the system can update its models with new classes. This thesis highlights the problems of multi-class recognition for OSR of sounds as well as incremental model adaptation and proposes solutions towards addressing these problems. The proposed solutions are validated through extensive experiments and are shown to provide improved performance over a wide range of openness values for sound classification scenarios.

This thesis describes research into the score-level fusion process in multimodal biometrics. The emphasis of the research is on the fusion of face and voice biometrics in the two recognition modes of verification and open-set identification. The growing interest in the use of multiple modalities in biometrics is due to its potential capabilities for eradicating certain important limitations of unimodal biometrics. One of the factors important to the accuracy of a multimodal biometric system is the choice of the technique deployed for data fusion. To address this issue, investigations are carried out into the relative performance of several statistical data fusion techniques for combining the score information in both unimodal and multimodal biometrics (i.e. speaker and/ or face verification). Another important issue associated with any multimodal technique is that of variations in the biometric data. Such variations are reflected in the corresponding biometric scores, and can thereby adversely influence the overall effectiveness of multimodal biometric recognition. To address this problem, different methods are proposed and investigated. The first approach is based on estimating the relative quality aspects of the test scores and then passing them on into the fusion process either as features or weights. The approach provides the possibility of tackling the data variations based on adjusting the weights for each of the modalities involved according to its relative quality. Another approach considered for tackling the effects of data variations is based on the use of score normalisation mechanisms. Whilst score normalisation has been widely used in voice biometrics, its effectiveness in other biometrics has not been previously investigated. This method is shown to considerably improve the accuracy of multimodal biometrics by appropriately correcting the scores from degraded modalities prior to the fusion process. The investigations in this work are also extended to the combination of score normalisation with relative quality estimation. The experimental results show that, such a combination is more effective than the use of only one of these techniques with the fusion process. The thesis presents a thorough description of the research undertaken, details the experimental results and provides a comprehensive analysis of them.

In traditional classification problems, all classes in the test set are assumed to also occur in the training set, also referred to as the closed-set assumption. However, in practice, new classes may occur in the test set, which reduces the performance of machine learning models trained under the closed-set assumption. Machine learning models should be able to accurately classify instances of classes known during training while concurrently recognizing instances of previously unseen classes (also called the open set assumption). This open set assumption is motivated by real world applications of classifiers wherein its improbable that sufficient data can be collected a priori on all possible classes to reliably train for them. For example, motivated by the DARPA WASH project at WPI, a disease classifier trained on data collected prior to the outbreak of COVID-19 might erroneously diagnose patients with the flu rather than the novel coronavirus. State-of-the-art open set methods based on the Extreme Value Theory (EVT) fail to adequately model class distributions with unequal variances. We propose the Variational Open-Set Recognition (VOSR) model that leverages all class-belongingness probabilities to reject unknown instances. To realize the VOSR model, we design a novel Multi-Modal Variational Autoencoder (MMVAE) that learns well-separated Gaussian Mixture distributions with equal variances in its latent representation. During training, VOSR maps instances of known classes to high-probability regions of class-specific components. By enforcing a large distance between these latent components during training, VOSR then assumes unknown data lies in the low-probability space between components and uses a multivariate form of Extreme Value Theory to reject unknown instances. Our VOSR framework outperforms state-of-the-art open set classification methods with a 15% F1 score increase on a variety of benchmark datasets.

No description available.

The aim of this study was to determine which land line telephone and/or mobile/cellular telephone will enable an individual with a cochlear implant to achieve the best speech discrimination scores. Objective measurements and the subjective experience of the individual were used. The literature review provided an overview on the telephone abilities of individuals fitted with cochlear implants. In this study three factors, the quality of the telephone, the speaker's voice and different speech-coding strategies, were discussed and examined, in order to explore and explain the technical difficulties commonly experienced by this population regarding the successful use of a telephone. Data regarding various telephones and the influence different voice-types has on the telecommunication abilities were obtained through the execution of the methodology. Telephone abilities on five different telephones were assessed. Ten participants, four females and six males, fitted with the ESPrit 22, ESPrit 24 and ESPrit 3G Nucleus cochlear implants were used. The Central Institute for the Deaf (CID) open-set sentences were used and data was statistically analysed using a split plot design. Significant differences between different types of telephones were found. The results also suggested that different voice types have an impact on these individual's ability to use a telephone independently. Possible reasons such as different coding strategies, technical interference and quality of voices were discussed. Recommendations for developing rehabilitation programs, to obtain successful telephone competence for these individuals, were made and discussed. The study aimed to empower technologists working in this field to actively take note of the need for development and continuous research regarding various telephones. These telephones should enable more individuals fitted with cochlear implants to receive the maximum speech discrimination with the minimum interference. The findings of this study should encourage future research regarding this topic. A more extensive range of telephones should be used and compared to the findings in this study. / Dissertation (M (Communication Pathology))--University of Pretoria, 2006. / Speech-Language Pathology and Audiology / Unrestricted

Crowds of people are gathering at multiple venues, such as concerts, political rallies, as well as in commercial malls, or just simply walking on the streets. More and more people are flocking to live in urban areas, thus generating a lot of scenarios of crowds. As a consequence, there is an increasing demand for automatic tools that can analyze and predict the behavior of crowds to ensure safety. Crowd motion analysis is a key feature in surveillance and monitoring applications, providing useful hints about potential threats to safety and security in urban and public spaces. It is well known that people gatherings are generally difficult to model, due to the diversity of the agents composing the crowd. Each individual is unique, being driven not only by the destination but also by personality traits and attitude. The domain of crowd analysis has been widely investigated in the literature. However, crowd gatherings have sometimes resulted in dangerous scenarios in recent years, such as stampedes or during dangerous situations. To take a step toward ensuring the safety of crowds, in this work we investigate two main research problems: we try to predict each person future position and we try to understand which are the key factors for simulating crowds. Predicting in advance how a mass of people will fare in a given space would help in ensuring the safety of public gatherings.

Despite the advancements in the development of autonomous vehicles (AVs), there are still numerous complex situations in which AVs may encounter challenges. In recent years, the concept of teleoperation, which entails establishing a connection between a remote operator and the AV, has garnered substantial attention from both AV companies and governmental bodies as a viable safety backup method. However, a research gap is apparent when it comes to the remote manipulation of AVs positioned at a considerable distance. This gap involves a) AV with a temporal delay through real-time direct control within the constraints of current wireless communication technology in an unpredictable road environment, and b) enhancing the AV's inherent detection capabilities to augment its autonomous control abilities, thereby reducing the operator's workload. To address this research gap, this dissertation introduces an innovative teleoperation system. Initially, we devise a control system utilizing the wave variable approach as a communication method to alleviate the impact of signal latency. And Radial Basis Function Networks (RBFN) are employed to effectively manage the uncertain nonlinear dynamics of the vehicle. Subsequently, a saliency-based object detection (OD) algorithm, named SalienDet, is proposed to identify objects not present in the training sample set. SalienDet incorporates saliency maps generated without prior information into the neural network, enhancing image features for unfamiliar objects. This augmentation significantly aids the OD algorithm in detecting previously unknown objects, thereby empowering the AV to possess an improved perception ability. This advancement is particularly valuable when the operator imparts driving advice to the AV instead of exercising direct control. In conclusion, this dissertation makes a noteworthy contribution to AV teleoperation by furnishing a comprehensive solution that spans various aspects of AV teleoperation. / Doctor of Philosophy / This dissertation revolves around the teleoperation of autonomous vehicles (AVs), with the objective of formulating a comprehensive teleoperation system that encompasses two critical aspects: direct control and indirect control. In the initial segment of the dissertation, we introduce a real-time teleoperation direct control system based on neural networks. This framework plays a pivotal role in assisting operators in navigating AVs efficiently, especially in the face of challenges such as communication delays and complex external environments. Following this, we present a novel saliency-based object detection (OD) algorithm. This algorithm empowers the AV to recognize potential objects beyond its prior knowledge, thereby enhancing its level of autonomous control, particularly when operators opt not to exercise direct control over the remote AV. Our research findings delve into the essential facets of AV teleoperation. The developed teleoperation system serves as a valuable reference for future researchers and engineers dedicated to advancing autonomous vehicle technology.

Orientadores: Anderson de Rezende Rocha, Ricardo da Silva Torres / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Computação / Made available in DSpace on 2018-08-25T19:52:29Z (GMT). No. of bitstreams: 1 MendesJunior_PedroRibeiro_M.pdf: 10648148 bytes, checksum: 314a33c9bb6fb8a188bfa762899107e8 (MD5) Previous issue date: 2014 / Resumo: Em reconhecimento de padrões, um cenário aberto é aquele em que não há amostras de treinamento para algumas classes que podem aparecer durante o teste. Normalmente, muitas aplicações são inerentemente de cenário aberto. Consequentemente, as soluções bem sucedidas da literatura para cenário fechado nem sempre são adequadas para problemas de reconhecimento na prática. Nesse trabalho, propomos um novo classificador multiclasse para cenário aberto, que estende o classificador Optimum-Path Forest (OPF). O OPF é um classificador de padrões baseado em grafos, simples, independente de parâmetros, multiclasse e desenvolvido para para problemas de cenário fechado. O método que propomos, o Open-Set OPF (OSOPF), incorpora a capacidade de reconhecer as amostras pertencentes às classes que são desconhecidas no tempo de treinamento, sendo adequado para reconhecimento em cenário aberto. Além disso, propomos novas medidas para avaliação de classificadores propostos para problemas em cenário aberto. Nos experimentos, consideramos seis grandes bases de dados com diferentes cenários de reconhecimento e demonstramos que o OSOPF proposto supera significativamente as abordagens existentes na literatura / Abstract: An open-set recognition scenario is the one in which there are no a priori training samples for some classes that might appear during testing. Usually, many applications are inherently open set. Consequently, the successful closed-set solutions in the literature are not always suitable for real-world recognition problems. Here, we propose a novel multiclass open-set classifier that extends upon the Optimum-Path Forest (OPF) classifier. OPF is a graph-based, simple, parameter independent, multiclass, and widely used classifier for closed-set problems. Our proposed Open-Set OPF (OSOPF) method incorporates the ability to recognize samples belonging to classes that are unknown at training time, being suitable for open-set recognition. In addition, we propose new evaluation measures for assessing the effectiveness performance of classifiers in open-set problems. In experiments, we consider six large datasets with different open-set recognition scenarios and demonstrate that the proposed OSOPF significantly outperforms its counterparts of the literature / Mestrado / Ciência da Computação / Mestre em Ciência da Computação

No description available.