1,721,261 research outputs found
Machine Learning for Failure Management in Optical Networks
No full textAfter an overview on main concepts of machine learning, we discuss use cases in optical networks failure management, such as failure detection, root-cause identification and localization. Recent research trends and challenges are also highlighted
Cross-Task and Cross-Lightpath Failure Detection and Localization in Optical Networks Using Transfer Learning
Full text linkPractical deployments of Machine-Learning(ML)-based solutions for failure management in optical networks often suffer from limited data availability, due to, especially, scarcity of labelled data describing different failure scenarios. Transfer Learning (TL) is regarded as a promising direction in cases of data scarcity, thanks to its ability to transfer knowledge from a Source Domain (SD) (e.g. SD could be a digital twin or a laboratory testbed) to a Target Domain (TD) (e.g., the infield network). In this paper, we focus on cross-lightpath and cross-task application of TL for failure localization and failure detection in optical networks. We found that, depending on the number of retrained parameters in the ML model, cross-lightpath TL for failure localization provides satisfactory accuracy (higher than 90%, in some cases) with limited amounts of TD data, and is also convenient in terms of TD retraining duration with respect to cases where TL is not used. Moreover, we found that cross-task failure detection/localization reaches up to 12% or 25% improvement in TD accuracy when considering failure localization and detection as TD task, respectively
Addressing data scarcity in ML-based failure-cause identification in optical networks through generative models
Full text linkWe consider the issue of data scarcity with class imbalance in failure-cause identification for optical fiber systems using Machine Learning (ML) techniques. We use an open dataset comprising of real Optical Time-Domain Reflectometer (OTDR) traces which have been gathered in an artificial setup spanning tens of kilometers, consistent with a long-haul network. Whilst ML methods have shown satisfactory results for automating the process of identifying failure causes in optical fiber networks, the solutions are generally strongly dependent on available labeled datasets, and require extensive data to train and validate any findings. However, in the case of failure management in optical networks, building a valuable dataset with sufficiently informative samples is in general a hard process, due to the fact that, by nature, failures occur infrequently. As such, data-labeling is time and resource intensive for domain experts. We therefore seek to mitigate these issues by exploring two generative models, namely, conditional Generative Adversarial Network (cGAN) and conditional Variational Autoencoder (cVAE), to balance the number of failures samples in a multiclass dataset. In order to balance the dataset with accurate synthetic data across the different failure causes, we adopt generative models that are conditioned on the failure classes, the SNR level of the trace and the maximum amplitude of the signal. These approaches are compared to Synthetic Minority Over-sampling TEchnique (SMOTE). We compare our approaches by training our datasets using an autoencoder classifier and testing them against three holdout datasets. Results show that, with the cGAN and cVAE, failure-cause identification can be improved by more than 5% in terms of global accuracy when compared to the imbalanced dataset, and in particular for scarcely-represented failure classes, our generative models provide an improvement in the f1 scores of over 50%
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Low-Margin Optical-Network Design with Multiple Physical-Layer Parameter Uncertainties
Full text linkAnalytical QoT models require safety margins to account for uncertain knowledge of input parameters. We propose and evaluate a design procedure that gradually decreases these margins in presence of multiple physical-layer uncertainties, by leveraging monitoring data to build a ML-based QoT regressor
Merging mixed reality and computational modeling for enhanced visualization of cardiac biomechanics
No full textMixed reality (MR) has the potential to complement numerical simulations for enhanced post-processing and integrate digital models into the daily clinical practice of healthcare professionals. In complex cardiac anatomies, the decision-making process for bioprosthesis implantation involves the challenging analysis of heart valve distribution, positioning, and sealing. This study proposes a framework to visualize computational modeling results in an immersive environment for comprehensive analysis of the geometric implications of implanted devices on human heart function. After computational analysis, the biomechanical behavior of the Living Heart Human Model (LHHM) was used to develop MR content for the immersive visualization of the heart kinematics and the electrical field. Additionally, MR content was developed to assess the spatial implications of left ventricular outflow tract (LVOT) obstruction as observed in transcatheter mitral valve replacement (TMVR). Findings demonstrated that augmented exploration of cardiac biomechanics can be used for a better understanding of the electrical field of the beating heart. In the case of TMVR simulation, MR-related analysis of LVOT obstruction can result in improved visualization and manipulation of 3D anatomies and assessment of device-induced anatomic constraints. We conclude that the synergy between in-silico modeling and MR can potentially enhance physicians' ability to visualize the implications of biomedical device implants in complex cardiac anatomies, benefiting both physicians and simulation experts
Machine-learning-assisted DDoS attack detection with P4 language
Full text linkWhile Software Defined Networking (SDN) provides well-known advantages in terms of network automation, flexibility and resources utilization, it has been observed that SDN controllers may represent critical points of failure for the entire network infrastructure, especially when they are targeted by malicious cyber attacks such as Distributed Denial of Service (DDoS). To address this issue, in this paper we exploit stateful data planes, as enabled by P4 programming language, where switches maintain persistent memory of handled packets to perform attack detection directly at the data plane, with only marginal involvement of the SDN controllers. As machine learning (ML) is recognized as primary anomaly detection methodology, we perform DDoS attack detection using a MLbased classification and compare different ML algorithms in terms of classification accuracy and train/test duration. Moreover, we combine ML and P4-enab1ed stateful data planes to design a real-time DDoS attack detection module, which we evaluate in terms of latency required for the detection. Three real-time scenarios are considered, where P4-enab1ed switches elaborate the received packets in different ways, namely, packet mirroring, header mirroring, and P4-metadata extraction. Numerical results show significant latency reduction when P4 is adopted
- …
