A quantum Jensen-Shannon graph kernel using the continuous-time quantum walk

In this paper, we use the quantum Jensen-Shannon divergence as a means to establish the similarity between a pair of graphs and to develop a novel graph kernel. In quantum theory, the quantum Jensen-Shannon divergence is defined as a distance measure between quantum states. In order to compute the quantum Jensen-Shannon divergence between a pair of graphs, we first need to associate a density operator with each of them. Hence, we decide to simulate the evolution of a continuous-time quantum walk on each graph and we propose a way to associate a suitable quantum state with it. With the density operator of this quantum state to hand, the graph kernel is defined as a function of the quantum Jensen-Shannon divergence between the graph density operators. We evaluate the performance of our kernel on several standard graph datasets from bioinformatics. We use the Principle Component Analysis (PCA) on the kernel matrix to embed the graphs into a feature space for classification. The experimental results demonstrate the effectiveness of the proposed approach. © 2013 Springer-Verlag.

Attributed graph similarity from the quantum Jensen-Shannon divergence

One of the most fundamental problem that we face in the graph domain is that of establishing the similarity, or alternatively the distance, between graphs. In this paper, we address the problem of measuring the similarity between attributed graphs. In particular, we propose a novel way to measure the similarity through the evolution of a continuous-time quantum walk. Given a pair of graphs, we create a derived structure whose degree of symmetry is maximum when the original graphs are isomorphic, and where a subset of the edges is labeled with the similarity between the respective nodes. With this compositional structure to hand, we compute the density operators of the quantum systems representing the evolution of two suitably defined quantum walks. We define the similarity between the two original graphs as the quantum Jensen-Shannon divergence between these two density operators, and then we show how to build a novel kernel on attributed graphs based on the proposed similarity measure. We perform an extensive experimental evaluation both on synthetic and real-world data, which shows the effectiveness the proposed approach. © 2013 Springer-Verlag.

A new unsupervised convolutional neural network model for Chinese scene text detection

As one of the most popular deep learning models, convolution neural network (CNN) has achieved huge success in image information extraction. Traditionally CNN is trained by supervised learning method with labeled data and used as a classifier by adding a classification layer in the end. Its capability of extracting image features is largely limited due to the difficulty of setting up a large training dataset. In this paper, we propose a new unsupervised learning CNN model, which uses a so-called convolutional sparse auto-encoder (CSAE) algorithm pre-Train the CNN. Instead of using labeled natural images for CNN training, the CSAE algorithm can be used to train the CNN with unlabeled artificial images, which enables easy expansion of training data and unsupervised learning. The CSAE algorithm is especially designed for extracting complex features from specific objects such as Chinese characters. After the features of articficial images are extracted by the CSAE algorithm, the learned parameters are used to initialize the first CNN convolutional layer, and then the CNN model is fine-Trained by scene image patches with a linear classifier. The new CNN model is applied to Chinese scene text detection and is evaluated with a multilingual image dataset, which labels Chinese, English and numerals texts separately. More than 10% detection precision gain is observed over two CNN models.

Biologically inspired features for scene classification in video surveillance

Inspired by human visual cognition mechanism, this paper first presents a scene classification method based on an improved standard model feature. Compared with state-of-the-art efforts in scene classification, the newly proposed method is more robust, more selective, and of lower complexity. These advantages are demonstrated by two sets of experiments on both our own database and standard public ones. Furthermore, occlusion and disorder problems in scene classification in video surveillance are also first studied in this paper. © 2010 IEEE.

Color-based surface reflectance separation for scene illumination estimation and rendering

Given the importance of color processing in computer vision and computer graphics, estimating and rendering illumination spectral reflectance of image scenes is important to advance the capability of a large class of applications such as scene reconstruction, rendering, surface segmentation, object recognition, and reflectance estimation. Consequently, this dissertation proposes effective methods for reflection components separation and rendering in single scene images. Based on the dichromatic reflectance model, a novel decomposition technique, named the Mean-Shift Decomposition (MSD) method, is introduced to separate the specular from diffuse reflectance components. This technique provides a direct access to surface shape information through diffuse shading pixel isolation. More importantly, this process does not require any local color segmentation process, which differs from the traditional methods that operate by aggregating color information along each image plane. ^ Exploiting the merits of the MSD method, a scene illumination rendering technique is designed to estimate the relative contributing specular reflectance attributes of a scene image. The image feature subset targeted provides a direct access to the surface illumination information, while a newly introduced efficient rendering method reshapes the dynamic range distribution of the specular reflectance components over each image color channel. This image enhancement technique renders the scene illumination reflection effectively without altering the scene’s surface diffuse attributes contributing to realistic rendering effects. ^ As an ancillary contribution, an effective color constancy algorithm based on the dichromatic reflectance model was also developed. This algorithm selects image highlights in order to extract the prominent surface reflectance that reproduces the exact illumination chromaticity. This evaluation is presented using a novel voting scheme technique based on histogram analysis. ^ In each of the three main contributions, empirical evaluations were performed on synthetic and real-world image scenes taken from three different color image datasets. The experimental results show over 90% accuracy in illumination estimation contributing to near real world illumination rendering effects. ^

Notes on sufficient conditions for a graph to be Hamiltonian

The first part of this paper deals with an extension of Dirac's Theorem to directed graphs. It is related to a result often referred to as the Ghouila-Houri Theorem. Here we show that the requirement of being strongly connected in the hypothesis of the Ghouila-Houri Theorem is redundant. The Second part of the paper shows that a condition on the number of edges for a graph to be hamiltonian implies Ore's condition on the degrees of the vertices.

Network construction and graph theoretical analysis of functional language networks in pediatric epilepsy

This dissertation introduces a new approach for assessing the effects of pediatric epilepsy on the language connectome. Two novel data-driven network construction approaches are presented. These methods rely on connecting different brain regions using either extent or intensity of language related activations as identified by independent component analysis of fMRI data. An auditory description decision task (ADDT) paradigm was used to activate the language network for 29 patients and 30 controls recruited from three major pediatric hospitals. Empirical evaluations illustrated that pediatric epilepsy can cause, or is associated with, a network efficiency reduction. Patients showed a propensity to inefficiently employ the whole brain network to perform the ADDT language task; on the contrary, controls seemed to efficiently use smaller segregated network components to achieve the same task. To explain the causes of the decreased efficiency, graph theoretical analysis was carried out. The analysis revealed no substantial global network feature differences between the patient and control groups. It also showed that for both subject groups the language network exhibited small-world characteristics; however, the patient's extent of activation network showed a tendency towards more random networks. It was also shown that the intensity of activation network displayed ipsilateral hub reorganization on the local level. The left hemispheric hubs displayed greater centrality values for patients, whereas the right hemispheric hubs displayed greater centrality values for controls. This hub hemispheric disparity was not correlated with a right atypical language laterality found in six patients. Finally it was shown that a multi-level unsupervised clustering scheme based on self-organizing maps, a type of artificial neural network, and k-means was able to fairly and blindly separate the subjects into their respective patient or control groups. The clustering was initiated using the local nodal centrality measurements only. Compared to the extent of activation network, the intensity of activation network clustering demonstrated better precision. This outcome supports the assertion that the local centrality differences presented by the intensity of activation network can be associated with focal epilepsy.^

Intracranial Volume Estimation and Graph Theoretical Analysis of Brain Functional Connectivity Networks

Understanding pathways of neurological disorders requires extensive research on both functional and structural characteristics of the brain. This dissertation introduced two interrelated research endeavors, describing (1) a novel integrated approach for constructing functional connectivity networks (FCNs) of brain using non-invasive scalp EEG recordings; and (2) a decision aid for estimating intracranial volume (ICV). The approach in (1) was developed to study the alterations of networks in patients with pediatric epilepsy. Results demonstrated the existence of statistically significant (p

Opportunistic Contact Graph Routing

L'ambiente di questa tesi è quello del Delay and Disruption Tolerant Networks (DTN), un'architettura di rete di telecomunicazioni avente come obiettivo le comunicazioni tra nodi di reti dette “challenged”, le quali devono affrontare problemi come tempi di propagazione elevati, alto tasso di errore e periodi di perdita delle connessioni. Il Bunde layer, un nuovo livello inserito tra trasporto e applicazione nell’architettura ISO/OSI, ed il protocollo ad esso associato, il Bundle Protocol (BP), sono stati progettati per rendere possibili le comunicazioni in queste reti. A volte fra la ricezione e l’invio può trascorrere un lungo periodo di tempo, a causa della indisponibilità del collegamento successivo; in questo periodo il bundle resta memorizzato in un database locale. Esistono varie implementazioni dell'architettura DTN come DTN2, implementazione di riferimento, e ION (Interplanetary Overlay Network), sviluppata da NASA JPL, per utilizzo in applicazioni spaziali; in esse i contatti tra i nodi sono deterministici, a differenza delle reti terrestri nelle quali i contatti sono generalmente opportunistici (non noti a priori). Per questo motivo all’interno di ION è presente un algoritmo di routing, detto CGR (Contact Graph Routing), progettato per operare in ambienti con connettività deterministica. È in fase di ricerca un algoritmo che opera in ambienti non deterministici, OCGR (Opportunistic Contact Graph Routing), che estende CGR. L’obiettivo di questa tesi è quello di fornire una descrizione dettagliata del funzionamento di OCGR, partendo necessariamente da CGR sul quale è basato, eseguire dei test preliminari, richiesti da NASA JPL, ed analizzarne i risultati per verificare la possibilità di utilizzo e miglioramento dell’algoritmo. Sarà inoltre descritto l’ambiente DTN e i principali algoritmi di routing per ambienti opportunistici. Nella parte conclusiva sarà presentato il simulatore DTN “The ONE” e l’integrazione di CGR e OCGR al suo interno.

A survey of graph and subgraph isomorphism problems

Mémoire numérisé par la Direction des bibliothèques de l'Université de Montréal.

'Corkonian exceptionalism': identity, authenticity and the emotional politics of place in a small city's popular music scene

Drawing from ethnographic research on Cork city’s popular music scene, this article explores meanings of ‘authenticity’ as constructed through geographical, social and ideological referents. It unpacks local music producers’ position-takings within the local field of cultural production, and locates their narrative claims to authenticity with respect to the city’s strong sense of cultural identity. Their authenticating discourses are revealed as complex, often produced through building imagined communities of ‘us’ (in Cork) versus ‘them’ (in Dublin). The analysis indicates local actors’ deep sense of emotional attachment to place and to others within the music-making community, which impacts on their self-conception as creative labourers, sustains DIY, collaborative practices, and promotes a solidaristic ethos within the local music scene.

A survey of graph and subgraph isomorphism problems

Mémoire numérisé par la Direction des bibliothèques de l'Université de Montréal.

Image usefulness of compressed surveillance footage with different scene contents

The police use both subjective (i.e. police staff) and automated (e.g. face recognition systems) methods for the completion of visual tasks (e.g person identification). Image quality for police tasks has been defined as the image usefulness, or image suitability of the visual material to satisfy a visual task. It is not necessarily affected by any artefact that may affect the visual image quality (i.e. decrease fidelity), as long as these artefacts do not affect the relevant useful information for the task. The capture of useful information will be affected by the unconstrained conditions commonly encountered by CCTV systems such as variations in illumination and high compression levels. The main aim of this thesis is to investigate aspects of image quality and video compression that may affect the completion of police visual tasks/applications with respect to CCTV imagery. This is accomplished by investigating 3 specific police areas/tasks utilising: 1) the human visual system (HVS) for a face recognition task, 2) automated face recognition systems, and 3) automated human detection systems. These systems (HVS and automated) were assessed with defined scene content properties, and video compression, i.e. H.264/MPEG-4 AVC. The performance of imaging systems/processes (e.g. subjective investigations, performance of compression algorithms) are affected by scene content properties. No other investigation has been identified that takes into consideration scene content properties to the same extend. Results have shown that the HVS is more sensitive to compression effects in comparison to the automated systems. In automated face recognition systems, `mixed lightness' scenes were the most affected and `low lightness' scenes were the least affected by compression. In contrast the HVS for the face recognition task, `low lightness' scenes were the most affected and `medium lightness' scenes the least affected. For the automated human detection systems, `close distance' and `run approach' are some of the most commonly affected scenes. Findings have the potential to broaden the methods used for testing imaging systems for security applications.