1,720,988 research outputs found
Machine Learning methods for Quality-of-Transmission estimation : Chapter Seven
No full textMachine Learning (ML) is becoming an integral part of Quality-of-Transmission (QoT) estimation frameworks in optical networks. Application of ML is motivated by the increase in design and management complexity deriving by the emergence of new technologies such as elastic optical networking and coherent transmission. This chapter provides an overview of the application of ML-based methods for QoT estimation in optical networks. We start by introducing classical estimation approaches based on classification and regression, then we cover more recent methodologies, such as active learning and transfer learning. Additionally, we provide a discussion on the integration of ML-based QoT estimation within optimization tools for resource allocation. Finally, illustrative numerical results on the application of ML for QoT estimation conclude the chapter
AN INNOVATIVE SYSTEM BASED ON BIOIMPEDANCE MEASUREMENTS TO DEFINE THE BLADDER VOLUME
No full textObjectives: Alteration of the bladder sense of fullness due to spinal cord injury or radical cystectomy leads to the inability to plan micturition timing. The development of a system for the fullness detection would be highly desirable and would enable autonomous and spontaneous management of micturition by the patient. Here the design of an innovative system of bladder volume monitoring based on bioimpedance measurements is presented.
Methods: Bioimpedance measurements are performed on ex-vivo bladder tissue using traditional ECG sensors. Two couples of electrodes in different arrangements were applied on the bladder walls to detect degree of filling by 50ml step, from 0ml to 300ml. The bioimpedance values are obtained for frequencies ranging from 1 kHz to 2 MHz. Moreover, different compositions of artificial urine were tested, by varying relevant ions concentration.
Results: The impedance variations were recorded around 20ohm in average from empty to full status. However, the impedance variation was dependent to ion concentration in urine.
Discussion: The experiment shows the feasibility of this approach and the need to find the sensors arrangement able to normalize measurements with respect to urine composition.
Conclusions: A novel system to detect the bladder filling based on bioimpedence measures is reported. This approach could be feasible both in presence of natural or artificial/reconstructed bladder. Future work will target accurate volume estimation independently on urine composition, as well as combination with other sensing strategies.
Acknowledgements: The authors acknowledge INAIL (Istituto Nazionale Assicurazioni Infortuni sul Lavoro) for providing their collaboration within the BioSUP project
DeepLS: Local Search for Network Optimization based on Lightweight Deep Reinforcement Learning
Full text linkDeep Reinforcement Learning (DRL) is being investigated as a competitive alternative to traditional techniques for solving network optimization problems. A promising research direction lies in enhancing traditional optimization algorithms by offloading low-level decisions to a DRL agent. In this study, we consider how to effectively employ DRL to improve the performance of Local Search algorithms, i.e., algorithms that, starting from a candidate solution, explore the solution space by iteratively applying local changes (i.e., moves), yielding the best solution found in the process. We propose a Local Search algorithm based on lightweight Deep Reinforcement Learning (DeepLS) that, given a neighborhood, queries a DRL agent for choosing a move, with the goal of achieving the best objective value in the long term. Our DRL agent, based on permutation-equivariant neural networks, is composed by less than a hundred parameters, requiring only up to ten minutes of training and can evaluate problem instances of arbitrary size, generalizing to networks and traffic distributions unseen during training. We evaluate DeepLS on two illustrative NP-Hard network routing problems, namely OSPF Weight Setting and Routing and Wavelength Assignment, training on a single small network only and evaluating on instances 2x-10x larger than training. Experimental results show that DeepLS outperforms existing DRL-based approaches from literature and attains competitive results with state-of-the-art metaheuristics, with computing times up to 8x smaller than the strongest algorithmic baselines
A Layer Jamming Actuator for Tunable Stiffness and Shape-Changing Devices
No full textChanging the shape and the stiffness of a device in a dynamic and controlled way enables important advancements in the field of robotics and wearable robotics. Variable stiffness materials and technologies can be used to address this challenge. In particular, layer jamming actuation is a very promising technology, featured by high efficiency and low cost. In this article, a stiffness- and shape-changing device based on a novel mechanism including a multiple-chamber structure is proposed. It allows to effectively modulate the shape and stiffness of a device, by activating two jamming chambers while pressurizing/depressurizing one or more interposed inflatable chambers. Prototypes with a size of 45 x 270 mm(2) and an average thickness ranging from 4.4 to 13 mm were developed and their ability to undergo a stiffness change over two orders of magnitude was demonstrated. The prototypes were also able to change their shape according to the position and inflation level of the interposed inflatable chambers, thus resulting in an overall deflection >10 mm. The possibility to wear the system as an orthotic brace was also demonstrated: this technology increased the patient comfort in static positions, yet keeping a supportive function when needed (e.g., in dynamic conditions). The device working principle highlighted in this article could also be exploited in other domains, for example, to build walking soft robots, prostheses, or grippers, as demonstrated through additional tests
Vertical Federated Learning for Failure Localization in Partially Disaggregated Optical Networks
Full text linkMachine Learning (ML) for failure management in optical networks has recently gained noteworthy attention. Even though real field-collected data is crucial for ML-based failure management, it is challenging to access data in emerging disaggregated optical networks, where multi-vendor equipment co-exist, and the end-to-end network management requires coordination between operators that manage different network segments. Due to data confidentiality issues, network operators tend not to share business-critical data, which sets a barrier to utilizing ML-based approaches. To overcome this issue, we propose a Vertical Federated Learning (VFL) approach based on Split-Neural-Network (SplitNN) for failure localization. We consider different deployment scenarios for ML-based solutions in a collaborative and privacy-preserving manner. Our experiments show that, depending on the VFL client and server model architectures, the proposed approaches provide very similar accuracy compared to a baseline scenario of a single operator managing the whole network (differences are mostly within 1 % of accuracy), while minimizing the exposure of risk-sensitive data
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
Dispelling the Myths Behind First-author Citation Counts
Full text linkWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
- …
