arXiv subjects

Ilenia Tinnirello

Publications and source records attributed to Ilenia Tinnirello.

11 recordsLinked to original sources

arXiv2026

When the UE Turns Adversary: Real-Time Uplink Jamming from Within 5G Networks

This paper presents an investigation of a novel class of stealthy and selective reactive jamming attacks targeting the Physical Uplink Shared Channel (PUSCH) in 5G New Radio (NR) networks. We design and implement STORM-RJ (Stealthy Timing Obstruction and Radio Manipulation -- Reactive Jamming), a Software-Defined Radio (SDR)-based adversarial framework that enables highly precise, time-frequency aligned interference by dynamically adapting the bandwidth and center frequency of injected noise bursts in real time. STORM-RJ leverages decoded Downlink Control Information (DCI) to identify Uplink-Grants (UL-Grants) and synchronizes interference exactly with the resource blocks allocated to a target User Equipment (UE). We further characterize and mitigate the dominant latency sources -- both at the software processing and hardware Radio Frequency (RF) frontend levels -- to achieve a rapid jamming response upon grant detection. We conduct a comparative analysis of high-level versus low-level radio control strategies, demonstrating that only low-level tuning provides the microsecond-scale responsiveness necessary to meet 5G-NR timing constraints for effective reactive jamming. We analyze the practical feasibility of such selective jamming under realistic hardware and timing constraints, highlighting key trade-offs between SDR flexibility, processing latency, and synchronization accuracy. Finally, we discuss potential mitigation strategies, including Hybrid Automatic Repeat reQuest (HARQ) anomaly detection.

cs.NI↗

arXiv2025

RatioWaveNet: A Learnable RDWT Front-End for Robust and Interpretable EEG Motor-Imagery Classification

Brain-computer interfaces (BCIs) based on motor imagery (MI) translate covert movement intentions into actionable commands, yet reliable decoding from non-invasive EEG remains challenging due to nonstationarity, low SNR, and subject variability. We present RatioWaveNet, which augments a strong temporal CNN-Transformer backbone (TCFormer) with a trainable, Rationally-Dilated Wavelet Transform (RDWT) front end. The RDWT performs an undecimated, multi-resolution subband decomposition that preserves temporal length and shift-invariance, enhancing sensorimotor rhythms while mitigating jitter and mild artifacts; subbands are fused via lightweight grouped 1-D convolutions and passed to a multi-kernel CNN for local temporal-spatial feature extraction, a grouped-query attention encoder for long-range context, and a compact TCN head for causal temporal integration. Our goal is to test whether this principled wavelet front end improves robustness precisely where BCIs typically fail - on the hardest subjects - and whether such gains persist on average across seeds under both intra- and inter-subject protocols. On BCI-IV-2a and BCI-IV-2b, across five seeds, RatioWaveNet improves worst-subject accuracy over the Transformer backbone by +0.17 / +0.42 percentage points (Sub-Dependent / LOSO) on 2a and by +1.07 / +2.54 percentage points on 2b, with consistent average-case gains and modest computational overhead. These results indicate that a simple, trainable wavelet front end is an effective plug-in to strengthen Transformer-based BCIs, improving worst-case reliability without sacrificing efficiency.

cs.CV↗

arXiv2025

Investigating the Impact of Rational Dilated Wavelet Transform on Motor Imagery EEG Decoding with Deep Learning Models

The present study investigates the impact of the Rational Discrete Wavelet Transform (RDWT), used as a plug-in preprocessing step for motor imagery electroencephalographic (EEG) decoding prior to applying deep learning classifiers. A systematic paired evaluation (with/without RDWT) is conducted on four state-of-the-art deep learning architectures: EEGNet, ShallowConvNet, MBEEG\_SENet, and EEGTCNet. This evaluation was carried out across three benchmark datasets: High Gamma, BCI-IV-2a, and BCI-IV-2b. The performance of the RDWT is reported with subject-wise averages using accuracy and Cohen's kappa, complemented by subject-level analyses to identify when RDWT is beneficial. On BCI-IV-2a, RDWT yields clear average gains for EEGTCNet (+4.44 percentage points, pp; kappa +0.059) and MBEEG\_SENet (+2.23 pp; +0.030), with smaller improvements for EEGNet (+2.08 pp; +0.027) and ShallowConvNet (+0.58 pp; +0.008). On BCI-IV-2b, the enhancements observed are modest yet consistent for EEGNet (+0.21 pp; +0.044) and EEGTCNet (+0.28 pp; +0.077). On HGD, average effects are modest to positive, with the most significant gain observed for MBEEG\_SENet (+1.65 pp; +0.022), followed by EEGNet (+0.76 pp; +0.010) and EEGTCNet (+0.54 pp; +0.008). Inspection of the subject material reveals significant enhancements in challenging recordings (e.g., non-stationary sessions), indicating that RDWT can mitigate localized noise and enhance rhythm-specific information. In conclusion, RDWT is shown to be a low-overhead, architecture-aware preprocessing technique that can yield tangible gains in accuracy and agreement for deep model families and challenging subjects.

cs.HC↗

arXiv2025

An Energy-Autonomous and Battery-Free Resistive Sensor using a Time-Domain to Digital Conversion with Bluetooth Low Energy connectivity

This paper introduces an innovative Energy-Autonomous Wireless Sensing Node (EAWSN) that addresses power constraints by harnessing ambient light for energy. It combines this energy harvesting capability with the Time Domain to Digital Conversion (TDDC) technique for efficient and accurate measurements of resistive sensors. Bluetooth Low Energy (BLE) communication ensures data can be transmitted wirelessly to a base station, providing a promising solution for various applications, particularly in environments with limited access to wired power sources, enabling long-term, maintenance-free operation by eliminating batteries. Experimental results showed a linear relationship between the test resistance R_m and the measured number of clock pulses N_m within the sensor's operating range.

eess.SY↗

arXiv2025

The Text Classification Pipeline: Starting Shallow going Deeper

Text classification stands as a cornerstone within the realm of Natural Language Processing (NLP), particularly when viewed through computer science and engineering. The past decade has seen deep learning revolutionize text classification, propelling advancements in text retrieval, categorization, information extraction, and summarization. The scholarly literature includes datasets, models, and evaluation criteria, with English being the predominant language of focus, despite studies involving Arabic, Chinese, Hindi, and others. The efficacy of text classification models relies heavily on their ability to capture intricate textual relationships and non-linear correlations, necessitating a comprehensive examination of the entire text classification pipeline. In the NLP domain, a plethora of text representation techniques and model architectures have emerged, with Large Language Models (LLMs) and Generative Pre-trained Transformers (GPTs) at the forefront. These models are adept at transforming extensive textual data into meaningful vector representations encapsulating semantic information. The multidisciplinary nature of text classification, encompassing data mining, linguistics, and information retrieval, highlights the importance of collaborative research to advance the field. This work integrates traditional and contemporary text mining methodologies, fostering a holistic understanding of text classification.

cs.CL↗

arXiv2023

A CSI Dataset for Wireless Human Sensing on 80 MHz Wi-Fi Channels

In the last years, several machine learning-based techniques have been proposed to monitor human movements from Wi-Fi channel readings. However, the development of domain-adaptive algorithms that robustly work across different environments is still an open problem, whose solution requires large datasets characterized by strong domain diversity, in terms of environments, persons and Wi-Fi hardware. To date, the few public datasets available are mostly obsolete - as obtained via Wi-Fi devices operating on 20 or 40 MHz bands - and contain little or no domain diversity, thus dramatically limiting the advancements in the design of sensing algorithms. The present contribution aims to fill this gap by providing a dataset of IEEE 802.11ac channel measurements over an 80 MHz bandwidth channel featuring notable domain diversity, through measurement campaigns that involved thirteen subjects across different environments, days, and with different hardware. Novel experimental data is provided by blocking the direct path between the transmitter and the monitor, and collecting measurements in a semi-anechoic chamber (no multi-path fading). Overall, the dataset - available on IEEE DataPort [1] - contains more than thirteen hours of channel state information readings (23.6 GB), allowing researchers to test activity/identity recognition and people counting algorithms.

eess.SP↗

arXiv2022

SHARP: Environment and Person Independent Activity Recognition with Commodity IEEE 802.11 Access Points

In this article we present SHARP, an original approach for obtaining human activity recognition (HAR) through the use of commercial IEEE 802.11 (Wi-Fi) devices. SHARP grants the possibility to discern the activities of different persons, across different time-spans and environments. To achieve this, we devise a new technique to clean and process the channel frequency response (CFR) phase of the Wi-Fi channel, obtaining an estimate of the Doppler shift at a radio monitor device. The Doppler shift reveals the presence of moving scatterers in the environment, while not being affected by (environment-specific) static objects. SHARP is trained on data collected as a person performs seven different activities in a single environment. It is then tested on different setups, to assess its performance as the person, the day and/or the environment change with respect to those considered at training time. In the worst-case scenario, it reaches an average accuracy higher than 95%, validating the effectiveness of the extracted Doppler information, used in conjunction with a learning algorithm based on a neural network, in recognizing human activities in a subject and environment independent way. The collected CFR dataset and the code are publicly available for replicability and benchmarking purposes.

eess.SP↗

arXiv2021

Downlink channel access performance of NR-U: Impact of numerology and mini-slots on coexistence with Wi-Fi in the 5 GHz band

Coexistence between cellular systems and Wi-Fi gained the attention of the research community when LTE License Assisted Access (LAA) entered the unlicensed band. The recent introduction of NR-U as part of 5G introduces new coexistence opportunities because it implements scalable numerology (flexible subcarrier spacing and OFDM symbol lengths), and non-slot based scheduling (mini-slots), which considerably impact channel access. This paper analyzes the impact of NR-U settings on its coexistence with Wi-Fi networks and compares it with LAA operation using simulations and experiments. First, we propose a downlink channel access simulation model, which addresses the problem of the dependency and non-uniformity of transmission attempts of different nodes, as a result of the synchronization mechanism introduced by NR-U. Second, we validate the accuracy of the proposed model using FPGA-based LAA, NR-U, and Wi-Fi prototypes with over-the-air transmissions. Additionally, we show that replacing LAA with NR-U would not only allow to overcome the problem of bandwidth wastage caused by reservation signals but also, in some cases, to preserve fairness in channel access for both scheduled and random-access systems. Finally, we conclude that fair coexistence of the aforementioned systems in unlicensed bands is not guaranteed in general, and novel mechanisms are necessary for improving the sharing of resources between scheduled and contention-based technologies.

cs.NI↗

arXiv2019

Capture Aware Sequential Waterfilling for LoraWAN Adaptive Data Rate

LoRaWAN (Long Range Wide Area Network) is emerging as an attractive network infrastructure for ultra low power Internet of Things devices. Even if the technology itself is quite mature and specified, the currently deployed wireless resource allocation strategies are still coarse and based on rough heuristics. This paper proposes an innovative "sequential waterfilling" strategy for assigning Spreading Factors (SF) to End-Devices (ED). Our design relies on three complementary approaches: i) equalize the Time-on-Air of the packets transmitted by the system's EDs in each spreading factor's group; ii) balance the spreading factors across multiple access gateways, and iii) keep into account the channel capture, which our experimental results show to be very substantial in LoRa. While retaining an extremely simple and scalable implementation, this strategy yields a significant improvement (up to 38%) in the network capacity over the legacy Adaptive Data Rate (ADR), and appears to be extremely robust to different operating/load conditions and network topology configurations.

cs.NI↗

arXiv2018

Impact of LTE's Periodic Interference on Heterogeneous Wi-Fi Transmissions

The problem of Wi-Fi and LTE coexistence has been significantly debated in the last years, with the emergence of LTE extensions enabling the utilization of unlicensed spectrum for carrier aggregation. Rather than focusing on the problem of resource sharing between the two technologies, in this paper, we study the effects of LTE's structured transmissions on the Wi-Fi random access protocol. We show how the scheduling of periodic LTE transmissions modifies the behavior of 802.11's distributed coordination function (DCF), leading to a degradation of Wi-Fi performance, both in terms of channel utilization efficiency and in terms of channel access fairness. We also discuss the applicability and limitations of a persistent DCF model in analyzing Wi-Fi performance under periodic LTE interference.

cs.NI↗

arXiv2013

ARIANNA: pAth Recognition for Indoor Assisted NavigatioN with Augmented perception

ARIANNA stands for pAth Recognition for Indoor Assisted Navigation with Augmented perception. It is a flexible and low cost navigation system for vi- sually impaired people. Arianna permits to navigate colored paths painted or sticked on the floor revealing their directions through vibrational feedback on commercial smartphones.

cs.CV↗