0000000000272918
AUTHOR
Croce D.
An SVM Ensamble Approach to Detect Irony and Stereotype Spreaders on Twitter
The problem we address in this work is classifying whether a Twitter user has spread Irony and Stereotype or not. We used a text vectorization layer to generate Bag-Of-Words sequences. Then such sequences are passed to three different text classifiers (Decision Tree, Convolutional Neural Network, Naive Bayes). Our final classifier is an SVM. To test and validate our approach we used the dataset provided for the author profiling task organized by PAN@CLEF 2022. Our team (missino) submitted the predictions on the provided test set to participate at the shared task. Over several cross fold validation our approach was able to reach a maximum binary accuracy on the best validation split equal to…
Dynamic Adaptation of LoRaWan Traffic for Real-time Emergency Operations
Modern standards for IoT communications support fast deployment, large coverage in the order of kilometers, and physical layer adaptations to increase link robustness under time-varying propagation and interference conditions. A possible use of such IoT technologies is in case of emergency scenarios where first responders (FRs) arrive after a disastrous event. Indeed, an important challenge for emergency management is the need to (re)establish real-time communication capabilities and to offer integrated decision making facilities based on information gathered by FRs acting on the crisis site. In this paper, we present a system architecture based on LoRaWAN technology for connecting emergenc…
The Quest for available bandwidth measurement techniques for large-scale distributed systems
In recent years the research community has developed many techniques to estimate the end-to-end available bandwidth of an Internet path. This important metric can be potentially exploited to optimize the performance of several distributed systems and, even, to improve the effectiveness of the congestion control mechanism of TCP. Thus, it has been suggested that some existing estimation techniques could be used for this purpose. However, existing tools were not designed for large-scale deployments and were mostly validated in controlled settings, considering only one measurement running at a time. In this paper, we argue that current tools, while offering good estimates when used alone, migh…
Hybrid VLC/WiFi Architectures with Priority Feedback Channels
In this paper, we consider integrating Visible Light Communication (VLC) and WiFi technologies in an ultra-dense (massive) Internet of Things scenario, where WiFi links are used for complementing VLC links and vice-versa. Indeed, in case of mobility and/or bidirectional communications, limited coverage areas and self-generated interference can be an issue. We consider hybrid VLC/WiFi nodes where the VLC link is used for the majority of (data) traffic and the WiFi link is employed as a feedback channel (e.g. transmitting TCP ACKs). In presence of intense WiFi traffic, the WiFi network may be congested and thus, to fully exploit the VLC bandwidth, we discuss possible priority mechanisms to fu…