0000000000080720
AUTHOR
Tinnirello I.
T100: A modern classic ensemble to profile irony and stereotype spreaders
In this work we propose a novel ensemble model based on deep learning and non-deep learning classifiers. The proposed model was developed by our team for participating at the Profiling Irony and Stereotype Spreaders (ISSs) task hosted at PAN@CLEF2022. Our ensemble (named T100), include a Logistic Regressor (LR) that classifies an author as ISS or not (nISS) considering the predictions provided by a first stage of classifiers. All these classifiers are able to reach state-of-the-art results on several text classification tasks. These classifiers (namely, the voters) are a Convolutional Neural Network (CNN), a Support Vector Machine (SVM), a Decision Tree (DT) and a Naive Bayes (NB) classifie…
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…
Using self-deferral to achieve fairness between Wi-Fi and NR-U in downlink and uplink scenarios
Wireless networks operating in unlicensed bands generally use one of two channel access paradigms: random access (e.g., Wi-Fi) or scheduled access (e.g., LTE License Assisted Access, LTE LAA and New Radio-Unlicensed, NR-U). The coexistence between these two paradigms is based on listen before talk (LBT), which was, however, designed for random access. Meanwhile, scheduled systems require that their transmissions start at the beginning of a slot boundary. Synchronizing this boundary to the end of LBT usually requires transmitting a reservation signal (RS) to block the channel. Since the RS is a waste of channel resources, we investigate an alternative self-deferral approach (gap-based access…
Amarelli's Industry 4.0 Transformation with IoT and Digital Advertisement: Optimizing Operations and Engaging Customers
This paper presents a vertical IoT solution for Amarelli, a licorice producing company, aiming to optimize their operations and enhance their customer engagement through the integration of IoT technology, Enterprice Resource Planning (EPR) system, e-commerce and social media advertising. The proposed solution includes several key components, such as IoT-enabled production monitoring, warehouse monitoring, RFID tracking, and real-time data analysis. The solution also integrates an ERP system, to provide business intelligence and e-commerce combination to enhance online presence and customer engagement through social media advertising. This vertical solution will enable Amarelli to improve ef…
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…