arXiv subjects

Edmundo de Souza e Silva

Publications and source records attributed to Edmundo de Souza e Silva.

9 recordsLinked to original sources

arXiv2024

Clustering Survival Data using a Mixture of Non-parametric Experts

Survival analysis aims to predict the timing of future events across various fields, from medical outcomes to customer churn. However, the integration of clustering into survival analysis, particularly for precision medicine, remains underexplored. This study introduces SurvMixClust, a novel algorithm for survival analysis that integrates clustering with survival function prediction within a unified framework. SurvMixClust learns latent representations for clustering while also predicting individual survival functions using a mixture of non-parametric experts. Our evaluations on five public datasets show that SurvMixClust creates balanced clusters with distinct survival curves, outperforms clustering baselines, and competes with non-clustering survival models in predictive accuracy, as measured by the time-dependent c-index and log-rank metrics.

cs.LG↗

arXiv2020

Network Anomaly Detection based on Tensor Decomposition

The problem of detecting anomalies in time series from network measurements has been widely studied and is a topic of fundamental importance. Many anomaly detection methods are based on packet inspection collected at the network core routers, with consequent disadvantages in terms of computational cost and privacy. We propose an alternative method in which packet header inspection is not needed. The method is based on the extraction of a normal subspace obtained by the tensor decomposition technique considering the correlation between different metrics. We propose a new approach for online tensor decomposition where changes in the normal subspace can be tracked efficiently. Another advantage of our proposal is the interpretability of the obtained models. The flexibility of the method is illustrated by applying it to two distinct examples, both using actual data collected on residential routers.

cs.NI↗

arXiv2019

On The Scalability of P2P Swarming Systems

One of the fundamental problems in the realm of peer-to-peer systems is that of determining their service capacities. In this paper, we focus on P2P scalability issues and propose models to compute the achievable throughput under distinct policies for selecting both peers and blocks. From these models, we obtain novel insights on the behavior of P2P swarming systems that motivate new mechanisms for publishers and peers to improve the overall performance. In particular, we obtain operational regions for swarm system. In addition, we show that system capacity significantly increases if publishers adopt the most deprived peer selection and peers reduce their service rates when they have all the file blocks but one.

cs.NI↗

arXiv2015

Flexible Content Placement in Cache Networks using Reinforced Counters

In this paper we study the problem of content placement in a cache network. We consider a network where routing of requests is based on random walks. Content placement is done using a novel mechanism referred to as reinforced counters. To each content we associate a counter, which is incremented every time the content is requested, and which is decremented at a fixed rate. We model and analyze this mechanism, tuning its parameters so as to achieve desired performance goals for a single cache or for a cache network. We also show that the optimal static content placement, without reinforced counters, is NP hard under different design goals.

cs.NI↗

arXiv2015

P-score: A Publication-based Metric for Academic Productivity

In this work we propose a metric to assess academic productivity based on publication outputs. We are interested in knowing how well a research group in an area of knowledge is doing relatively to a pre-selected set of reference groups, where each group is composed by academics or researchers. To assess academic productivity we propose a new metric, which we call P-score. Our metric P-score assigns weights to venues using only the publication patterns of selected reference groups. This implies that P-score does not depend on citation data and thus, that it is simpler to compute particularly in contexts in which citation data is not easily available. Also, preliminary experiments suggest that P-score preserves strong correlation with citation-based metrics.

cs.DL↗

arXiv2013

Enabling Information Centric Networks through Opportunistic Search, Routing and Caching

Content dissemination networks are pervasive in todays Internet. Examples of content dissemination networks include peer-to-peer networks (P2P), content distribution networks (CDN) and information centric networks (ICN). In this paper, we propose a new system design for information centric networks which leverages opportunistic searching, routing and caching. Our system design is based on an hierarchical tiered structure. Random walks are used to find content inside each tier, and gateways across tiers are used to direct requests towards servers placed in the top tier, which are accessed in case content replicas are not found in lower tiers. Then, we propose a model to analyze the system in consideration. The model yields metrics such as mean time to find a content and the load experienced by custodians as a function of the network topology. Using the model, we identify trade-offs between these two metrics, and numerically show how to find the optimal time to live of the random walks.

cs.NI↗

arXiv2013

R-Score: Reputation-based Scoring of Research Groups

To manage the problem of having a higher demand for resources than availability of funds, research funding agencies usually rank the major research groups in their area of knowledge. This ranking relies on a careful analysis of the research groups in terms of their size, number of PhDs graduated, research results and their impact, among other variables. While research results are not the only variable to consider, they are frequently given special attention because of the notoriety they confer to the researchers and the programs they are affiliated with. In here we introduce a new metric for quantifying publication output, called R-Score for reputation-based score, which can be used in support to the ranking of research groups or programs. The novelty is that the metric depends solely on the listings of the publications of the members of a group, with no dependency on citation counts. R-Score has some interesting properties: (a) it does not require access to the contents of published material, (b) it can be curated to produce highly accurate results, and (c) it can be naturally used to compare publication output of research groups (e.g., graduate programs) inside a same country, geographical area, or across the world. An experiment comparing the publication output of 25 CS graduate programs from Brazil suggests that R-Score can be quite useful for providing early insights into the publication patterns of the various research groups one wants to compare.

cs.DL↗

arXiv2012

Characterizing Continuous Time Random Walks on Time Varying Graphs

In this paper we study the behavior of a continuous time random walk (CTRW) on a stationary and ergodic time varying dynamic graph. We establish conditions under which the CTRW is a stationary and ergodic process. In general, the stationary distribution of the walker depends on the walker rate and is difficult to characterize. However, we characterize the stationary distribution in the following cases: i) the walker rate is significantly larger or smaller than the rate in which the graph changes (time-scale separation), ii) the walker rate is proportional to the degree of the node that it resides on (coupled dynamics), and iii) the degrees of node belonging to the same connected component are identical (structural constraints). We provide examples that illustrate our theoretical findings.

cs.SI↗

arXiv2011

Heterogeneous download times in a homogeneous BitTorrent swarm

Modeling and understanding BitTorrent (BT) dynamics is a recurrent research topic mainly due to its high complexity and tremendous practical efficiency. Over the years, different models have uncovered various phenomena exhibited by the system, many of which have direct impact on its performance. In this paper we identify and characterize a phenomenon that has not been previously observed: homogeneous peers (with respect to their upload capacities) experience heterogeneous download rates. The consequences of this phenomenon have direct impact on peer and system performance, such as high variability of download times, unfairness with respect to peer arrival order, bursty departures and content synchronization. Detailed packet-level simulations and prototype-based experiments on the Internet were performed to characterize this phenomenon. We also develop a mathematical model that accurately predicts the heterogeneous download rates of the homogeneous peers as a function of their content. Although this phenomenon is more prevalent in unpopular swarms (very few peers), these by far represent the most common type of swarm in BT.

cs.NI↗