Implementing statistical learning methods through Bayesian networks (Part 2): bayesian evaluations for results of black toner analyses in forensic document examination

This paper presents and discusses the use of Bayesian procedures - introduced through the use of Bayesian networks in Part I of this series of papers - for 'learning' probabilities from data. The discussion will relate to a set of real data on characteristics of black toners commonly used in printing and copying devices. Particular attention is drawn to the incorporation of the proposed procedures as an integral part in probabilistic inference schemes (notably in the form of Bayesian networks) that are intended to address uncertainties related to particular propositions of interest (e.g., whether or not a sample originates from a particular source). The conceptual tenets of the proposed methodologies are presented along with aspects of their practical implementation using currently available Bayesian network software.

Error and attack tolerance of layered complex networks.

Many complex systems may be described by not one but a number of complex networks mapped on each other in a multi-layer structure. Because of the interactions and dependencies between these layers, the state of a single layer does not necessarily reflect well the state of the entire system. In this paper we study the robustness of five examples of two-layer complex systems: three real-life data sets in the fields of communication (the Internet), transportation (the European railway system), and biology (the human brain), and two models based on random graphs. In order to cover the whole range of features specific to these systems, we focus on two extreme policies of system's response to failures, no rerouting and full rerouting. Our main finding is that multi-layer systems are much more vulnerable to errors and intentional attacks than they appear from a single layer perspective.

Dyadic pulsations as a signature of sustainability in correspondence networks

In this paper, we introduce the concept of dyadic pulsations as a measure of sustainability in online discussion groups. Dyadic pulsations correspond to new communication exchanges occurring between two participants in a discussion group. A group that continuously integrates new participants in the on-going conversation is characterized by a steady dyadic pulsation rhythm. On the contrary, groups that either pursue close conversation or unilateral communication have no or very little dyadic pulsations. We show on two examples taken from Usenet discussion groups, that dyadic pulsations permit to anticipate future bursts in response delay time which are signs of group discussion collapses. We discuss ways of making this measure resilient to spam and other common algorithmic production that pollutes real discussions

Incremental neural networks for function approximation

A new strategy for incremental building of multilayer feedforward neural networks is proposed in the context of approximation of functions from R-p to R-q using noisy data. A stopping criterion based on the properties of the noise is also proposed. Experimental results for both artificial and real data are performed and two alternatives of the proposed construction strategy are compared.

An architecture for adaptive replication-based multimedia streaming in P2P networks

This PhD thesis addresses the issue of scalable media streaming in large-scale networking environments. Multimedia streaming is one of the largest sink of network resources and this trend is still growing as testified by the success of services like Skype, Netflix, Spotify and Popcorn Time (BitTorrent-based). In traditional client-server solutions, when the number of consumers increases, the server becomes the bottleneck. To overcome this problem, the Content-Delivery Network (CDN) model was invented. In CDN model, the server copies the media content to some CDN servers, which are located in different strategic locations on the network. However, they require heavy infrastructure investment around the world, which is too expensive. Peer-to-peer (P2P) solutions are another way to achieve the same result. These solutions are naturally scalable, since each peer can act as both a receiver and a forwarder. Most of the proposed streaming solutions in P2P networks focus on routing scenarios to achieve scalability. However, these solutions cannot work properly in video-on-demand (VoD) streaming, when resources of the media server are not sufficient. Replication is a solution that can be used in these situations. This thesis specifically provides a family of replication-based media streaming protocols, which are scalable, efficient and reliable in P2P networks. First, it provides SCALESTREAM, a replication-based streaming protocol that adaptively replicates media content in different peers to increase the number of consumers that can be served in parallel. The adaptiveness aspect of this solution relies on the fact that it takes into account different constraints like bandwidth capacity of peers to decide when to add or remove replicas. SCALESTREAM routes media blocks to consumers over a tree topology, assuming a reliable network composed of homogenous peers in terms of bandwidth. Second, this thesis proposes RESTREAM, an extended version of SCALESTREAM that addresses the issues raised by unreliable networks composed of heterogeneous peers. Third, this thesis proposes EAGLEMACAW, a multiple-tree replication streaming protocol in which two distinct trees, named EAGLETREE and MACAWTREE, are built in a decentralized manner on top of an underlying mesh network. These two trees collaborate to serve consumers in an efficient and reliable manner. The EAGLETREE is in charge of improving efficiency, while the MACAWTREE guarantees reliability. Finally, this thesis provides TURBOSTREAM, a hybrid replication-based streaming protocol in which a tree overlay is built on top of a mesh overlay network. Both these overlays cover all peers of the system and collaborate to improve efficiency and low-latency in streaming media to consumers. This protocol is implemented and tested in a real networking environment using PlanetLab Europe testbed composed of peers distributed in different places in Europe.

Communication in networks with hierarchical branching

We present a simple model of communication in networks with hierarchical branching. We analyze the behavior of the model from the viewpoint of critical systems under different situations. For certain values of the parameters, a continuous phase transition between a sparse and a congested regime is observed and accurately described by an order parameter and the power spectra. At the critical point the behavior of the model is totally independent of the number of hierarchical levels. Also scaling properties are observed when the size of the system varies. The presence of noise in the communication is shown to break the transition. The analytical results are a useful guide to forecasting the main features of real networks.

Self-similarity of complex networks and hidden metric spaces

We demonstrate that the self-similarity of some scale-free networks with respect to a simple degree-thresholding renormalization scheme finds a natural interpretation in the assumption that network nodes exist in hidden metric spaces. Clustering, i.e., cycles of length three, plays a crucial role in this framework as a topological reflection of the triangle inequality in the hidden geometry. We prove that a class of hidden variable models with underlying metric spaces are able to accurately reproduce the self-similarity properties that we measured in the real networks. Our findings indicate that hidden geometries underlying these real networks are a plausible explanation for their observed topologies and, in particular, for their self-similarity with respect to the degree-based renormalization.

Percolation and epidemic thresholds in clustered networks

We develop a theoretical approach to percolation in random clustered networks. We find that, although clustering in scale-free networks can strongly affect some percolation properties, such as the size and the resilience of the giant connected component, it cannot restore a finite percolation threshold. In turn, this implies the absence of an epidemic threshold in this class of networks, thus extending this result to a wide variety of real scale-free networks which shows a high level of transitivity. Our findings are in good agreement with numerical simulations.

Clustering in complex networks. I. General formalism

We develop a full theoretical approach to clustering in complex networks. A key concept is introduced, the edge multiplicity, that measures the number of triangles passing through an edge. This quantity extends the clustering coefficient in that it involves the properties of two¿and not just one¿vertices. The formalism is completed with the definition of a three-vertex correlation function, which is the fundamental quantity describing the properties of clustered networks. The formalism suggests different metrics that are able to thoroughly characterize transitive relations. A rigorous analysis of several real networks, which makes use of this formalism and the metrics, is also provided. It is also found that clustered networks can be classified into two main groups: the weak and the strong transitivity classes. In the first class, edge multiplicity is small, with triangles being disjoint. In the second class, edge multiplicity is high and so triangles share many edges. As we shall see in the following paper, the class a network belongs to has strong implications in its percolation properties.

Clustering in complex networks. II. Percolation properties

The percolation properties of clustered networks are analyzed in detail. In the case of weak clustering, we present an analytical approach that allows us to find the critical threshold and the size of the giant component. Numerical simulations confirm the accuracy of our results. In more general terms, we show that weak clustering hinders the onset of the giant component whereas strong clustering favors its appearance. This is a direct consequence of the differences in the k-core structure of the networks, which are found to be totally different depending on the level of clustering. An empirical analysis of a real social network confirms our predictions.

Tuning clustering in random networks with arbitrary degree distributions

We present a generator of random networks where both the degree-dependent clustering coefficient and the degree distribution are tunable. Following the same philosophy as in the configuration model, the degree distribution and the clustering coefficient for each class of nodes of degree k are fixed ad hoc and a priori. The algorithm generates corresponding topologies by applying first a closure of triangles and second the classical closure of remaining free stubs. The procedure unveils an universal relation among clustering and degree-degree correlations for all networks, where the level of assortativity establishes an upper limit to the level of clustering. Maximum assortativity ensures no restriction on the decay of the clustering coefficient whereas disassortativity sets a stronger constraint on its behavior. Correlation measures in real networks are seen to observe this structural bound.

Correlations in weighted networks

We develop a statistical theory to characterize correlations in weighted networks. We define the appropriate metrics quantifying correlations and show that strictly uncorrelated weighted networks do not exist due to the presence of structural constraints. We also introduce an algorithm for generating maximally random weighted networks with arbitrary P(k,s) to be used as null models. The application of our measures to real networks reveals the importance of weights in a correct understanding and modeling of these heterogeneous systems.

Statistical mechanics of multi-edge networks

Statistical properties of binary complex networks are well understood and recently many attempts have been made to extend this knowledge to weighted ones. There are, however, subtle yet important considerations to be made regarding the nature of the weights used in this generalization. Weights can be either continuous or discrete magnitudes, and in the latter case, they can additionally have undistinguishable or distinguishable nature. This fact has not been addressed in the literature insofar and has deep implications on the network statistics. In this work we face this problem introducing multiedge networks as graphs where multiple (distinguishable) connections between nodes are considered. We develop a statistical mechanics framework where it is possible to get information about the most relevant observables given a large spectrum of linear and nonlinear constraints including those depending both on the number of multiedges per link and their binary projection. The latter case is particularly interesting as we show that binary projections can be understood from multiedge processes. The implications of these results are important as many real-agent-based problems mapped onto graphs require this treatment for a proper characterization of their collective behavior.

Secure many-to-one communications in wireless sensor networks

Wireless Sensor Networks (WSN) are formed by nodes with limited computational and power resources. WSNs are finding an increasing number of applications, both civilian and military, most of which require security for the sensed data being collected by the base station from remote sensor nodes. In addition, when many sensor nodes transmit to the base station, the implosion problem arises. Providing security measures and implosion-resistance in a resource-limited environment is a real challenge. This article reviews the aggregation strategies proposed in the literature to handle the bandwidth and security problems related to many-to-one transmission in WSNs. Recent contributions to secure lossless many-to-one communication developed by the authors in the context of several Spanish-funded projects are surveyed. Ongoing work on the secure lossy many-to-one communication is also sketched.

Mobility Management in Packet Switched Mobile Networks

Nykyisin matkaviestinverkot ovat osa jokapäiväistä elämää. Merkittävimpiä eroja kiinteiden ja matkaviestinverkkojen välillä on käyttäjän liikkuvuus, joka voidaan määritellä mahdollisuudeksi soittaa ja vastaanottaa puheluita missä ja milloin tahansa. Työ selittää termin liikkuvuus ja määrittää ongelmat, jotka täytyy ratkaista liikkuvuuden aikaansaamiseksi sekä tavat, joilla nämä ongelmat on ratkaistu matkaviestinverkoissa. Työ luo yleiskatsauksen liikkuvuuden aikaansaamisessa käytettäviin menetelmiin, joita ovat haku, sijainnin päivitys, sijainnin seuranta ja kanavan vaihto. Työ keskittyy liikkuvuuteen kolmannen sukupolven matkaviestinverkkojen paketti-kytkentäisessä osassa, esimerkkinä liikkuvuuden hallinta UMTS:ssa (Universal Mobile Telecommunications System). Erot paketti- ja piirikytkentäisen osan välillä tuodaan esille ja selitetään. Jotta käyttäjät ja heidän päätteensä voisivat liikkua, tiedon täytyy kulkea verkon eri osien välillä. Merkinanto verkkoelementtien välillä ja liikkuvuuden mahdollistavien toimenpiteiden suoritus tehdään yhteyskäytännön avulla. Työ kuvaa yhteyskäytännöt, jotka ovat osallisena liikkuvuuden tarjontaan. Painopiste on GPRS:n liikkuvuuden-hallintayhteyskäytännössä, GMM:ssä. GMM protokollan prototyypin toteutus on esitetty työn käytännön osassa.