Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Antonio Nocera has a total of 49 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A dataset of Raman spectra with quantitative labels of mixtures of nitrate, nitrite and sulphate

    by Lorenzo Luciani, Antonio Nocera, Michela Raimondi, Agnese Sbrollini, Micaela Morettini, Rossana Galassi

  • Open Access

    When networks sense and decide: a preliminary investigation of the human and invisible ethical dimensions of ISAC in 6G

    by Maria Gardano, Antonio Nocera, Michela Raimondi, Ennio Gambi

    Integrated Sensing and Communication (ISAC) is expected to become a core capability of future 6G networks, enabling wireless infrastructures to sense physical environments and human presence through shared radio resources. While offering significant technological benefits, ISAC also raises ethical and societal concerns due to its invisible and pervasive sensing nature. This paper proposes a human-centric, questionnaire-based framework to assess the acceptability of ISAC functionalities and to operationalize ethical and societal perceptions into quantitative, design-oriented indicators. Two representative human-centric scenarios are investigated, namely domestic monitoring for Ambient Assisted Living and human motion monitoring for safety. The proposed framework directly quantifies selected 6G human-centric values, including trustworthiness and regulation, and identifies additional design requirements related to transparency, user control, and system understanding that significantly influence acceptability. The results show that ISAC acceptance is strongly context-dependent and driven more by governance, trust, and knowledge than by sensing capabilities alone. By translating user perceptions into actionable indicators and design requirements, this work provides a practical contribution toward ethical-by-design ISAC development, complementing traditional performance metrics and supporting the realization of transparent, trustworthy, and socially acceptable 6G networks.

  • Open Access

    Raman Peaks Feature-Based Machine Learning for Raman Spectroscopy Quantification of Inorganic Pollutants

    by Antonio Nocera, Michela Raimondi, Lorenzo Luciani, Laura Burattini, Laura Falaschetti, Rossana Galassi

    This study investigates how Raman peak features influence the accuracy of pollutant concentration quantification in Raman spectroscopy using feature-based machine learning. A Raman peak feature-based approach is applied to data acquired from laboratory Raman equipment for inorganic anion mixtures, with the objective of identifying processing strategies suitable for low-resolution Raman instruments. A dataset comprising nitrate, nitrite, and sulphate dissolved in water at varying concentrations was used to develop a pre-processing pipeline, train and validate models, and perform linear regression using peak- and area-based features extracted from analyte-specific spectral fingerprint regions. Signal downsampling was employed to simulate reduced spectral resolution and evaluate feature robustness under peak broadening conditions. Results indicate that peak-based regression is more sensitive to reduced peak resolution for nitrate and sulphate, whereas area-based regression produces more stable prediction errors across downsampling factors. Conversely, for nitrite, peak-based regression is less affected by downsampling, while area-based regression exhibits degraded performance. Area-based regression achieved mean absolute percentage errors below 7% and 16% for nitrate concentrations above 3833 mg/L and 1916 mg/L, respectively, and generally below 16% for sulphate concentrations above 1916 mg/L. For nitrite, peak-based regression yielded errors within 4%.

  • Open Access

    Seeing Without Being Seen: A Review of Ethical and Human-Centric ISAC in 6G

    by Maria Gardano, Antonio Nocera, Michela Raimondi, Ennio Gambi

    Integrated Sensing and Communication (ISAC), enabling communication infrastructure to simultaneously transmit data and sense the surrounding physical environment, is emerging as a cornerstone technology for sixth-generation (6G) mobile networks. While these capabilities unlock new applications in healthcare, safety, and ambient intelligence, they also introduce novel ethical and societal challenges related to privacy, transparency, user autonomy, and trust, which are values fundamental to the social acceptance of the technology. Firstly, an overview of academic, institutional, and industrial contributions on human-centric 6G is provided, with a focus on how ethical values are addressed in ISAC-related contexts. Secondly, this paper reviews the distinctive characteristics of ISAC through representative human-centric use cases involving non-interactive and often invisible sensing of people, highlighting the ethical and societal implications emerging from such scenarios. By analyzing current standardization efforts and the scientific literature, this paper identifies emerging trends in Key Values (KVs) relevant to ISAC, as well as open research gaps that must be addressed to support trustworthy and value-oriented ISAC design in future 6G networks.


  • Open Access

    AI-assisted methodology for robust digital measurements by Raman spectroscopy: Quantification of inorganic pollutants in water

    by Antonio Nocera, Lorenzo Luciani, Gianluca Ciattaglia, Michela Raimondi, Laura Burattini, Susanna Spinsante, Ennio Gambi, Rossana Galassi


  • Development and Validation of a Frequency-Based Quality Index for Contactless Respiratory Volume Analysis

    by Antonio Nocera, Linda Senigagliesi, Gianluca Ciattaglia, Michela Raimondi, Ennio Gambi

    In contactless continuous monitoring of vital signs, assessing the quality of extracted signals is essential to increase the fidelity of the estimation. For this reason, a set of frequency-based quality indices is studied and analysed on a public dataset of torso displacements related to respiratory volume and recorded remotely under free breathing conditions. All the indices are based on the ratio between the power extracted in a frequency band associated with respiratory activity, against the complementary frequency band associated with noise. Parameters affecting the proposed indices, such as the number of harmonics and the frequency bandwidth around each harmonic, are evaluated to choose the most appropriate frequency band. Moreover, the indices are evaluated theoretically to understand in what range of noise they could properly work. Three experiments are performed: in the first one, white Gaussian noise is added to the considered signals to generate respiratory signals with a signal-to-noise ratio (SNR) ranging from -30 to 27 dB; in the second one, the temporal noise extracted from a depth camera at distances less than 4 meters from a wall is added to the considered signals to simulate a scenario closer to the real application. Mean absolute error (MAE) of less than 2 dB, root mean square error (RMSE) of less than 3 dB, and Pearson’s correlation between 0.97 to 0.99 in the defined range of applicability are the obtained results for the evaluated quality indices. In the third one, an experimental scenario with recordings from Intel RealSense D455 and Kinect V2, the proposed metrics demonstrated to discriminate adequately between lower and higher quality signals determined by subjects at increasing distances from the camera. The metrics showed to recognise the presence of occlusions and motion artefacts; a Respiration-to-Noise Ratio (RNR) with frequency interval of 0.4 Hz showed a great sensitivity to occlusions with a median worsening of the signal quality of 6 to 10 dB; on the other hand, an RNR with frequency interval of 0.05 Hz showed greater sensitivity to low-frequency body movements when comparing the breathing signals extracted from sitting against standing subjects.

  • mmTracking: A DL-Based mmWave RADAR Data Processing Algorithm for Indoor People Tracking

    by Michela Raimondi, Gianluca Ciattaglia, Antonio Nocera, Maria Gardano, Linda Senigagliesi, Susanna Spinsante, Ennio Gambi

    Locating and tracking targets in indoor environments is a challenging field of research. The complexity and variability of the environment limit the suitability of many technologies for this application. In this context, mmWave frequency modulated continuous wave (FMCW) radars can prove to be valuable sensors when combined with deep learning (DL) techniques, in order to extend performance in target locating and tracking. This article presents an original approach to locate and track moving targets in indoor environments, based on a YOLOv3 DL network that can be applied to radar data. To quantify the performance of the proposed method, here named mmTracking, tests were designed in accordance with the ISO/IEC 18305:2016 reference standard. The results show a mean error in localization of 0.39 m with a variance of 0.01 m2, and a root mean square error (RMSE) in the tracking of 0.40 m.


  • Sport DB 3.0: Use of Wearables for Cardiac Self-Monitoring During Sport

    by Agnese Sbrollini, Sofia Romagnoli, Antonio Nocera, Micaela Morettini, Ennio Gambi, Laura Burattini

    Sport is normally recommended for its beneficial effects on health. However, in case of underlying and unknown cardiovascular diseases, sport may also trigger acute cardiac events, possibly leading to sudden cardiac death. Consequently, having the possibility to assess the risk of cardiac complications while practicing sport is highly desirable. While training, athletes often wear cardiorespiratory sensors, typically for performance optimization. However, the same devices are also potentially useful to evaluate the athletes' health status and to assess their cardiac risk. Under this assumption, we present the UNIVPM Sport DB 3.0, a database of cardiorespiratory datasets acquired by wearable and portable devices while practicing sport, and show how two software applications, CaRiSMA and Sport?Sicuro!, can be used to process and visualize data and signals in order to assess athletes' cardiac risk, beside their exercise performance. The Chest straps BioHarness 3.0 by Zephyr and Frontier X2 by Forth Frontiers, the KardiaMobile and Kardia 6L by AliveCor, the Polar M400, and the heart-rate sensor H7 were used to acquire cardiorespiratory signals from 245 athletes while practicing 20 different sports. Acquisitions were performed following sport-specific protocols, typically including a pseudo-resting initial phase, an uncontrolled training session, and a recovery phase. Data analysis by CaRiSMA and Sport?Sicuro! highlighted that over 20% of athletes overcome maximal heart rate during training. Moreover, three athletes presented abnormalities or pathologies (short QTc interval, paroxysmal atrial fibrillation and supraventricular tachycardia). Thus, data collected in Sport DB 3.0 are useful to support research activity finalized to investigate sport-triggered cardiovascular complications.

  • Open Access

    Raman Spectroscopy for Nitrate Detection in Water: A Review of the Current State of Art

    by Lorenzo Luciani, Antonio Nocera, Michela Raimondi, Gianluca Ciattaglia, Susanna Spinsante, Ennio Gambi, Rossana Galassi

    The contamination of natural basins by agricultural or industrial activities, and the growing need for potable water due to climate changes accelerate the drive to find versatile, fast, practical, and easy-to-use methods for water analysis. A potentially versatile technique suitable for water analysis is Raman Spectroscopy (RS). Featured by good resolution but low sensitivity, RS detects molecular vibrational modes of an analyte in water. Nitrate is an indicator of chemical and/or biological pollution, it displays Raman active vibrational modes affected by the interaction with other systems in solution, allowing a wide range of applications. Concerning Nitrate analysis in water, a general introduction to the Raman effect and the basic instrumentation were herein discussed. RS is a potential solution to wastewater analysis. This review first reports the theoretical background of the technique and its basic working principles, then, the state-of-the-art scientific contributions related to Nitrate detection are investigated with a particular interest in the instrumental setup and the chemometric techniques employed to improve its sensitivity. In the studies hereby considered, instrumental setup (for example, laser frequency, laser power, acquisition times) and different technical solutions (for example, micro- versus macro-Raman instruments) to increase the technique’s sensitivity on Nitrate detection are described. Concisely, the use of deep-UV lasers, optically active Surface-Enhanced Raman Spectroscopy (SERS) or Fiber-Enhanced Raman spectroscopy (FERS) equipment, coupled with instrumental settings, i.e. acquisition time, variable temperature of acquisition, use of special sampling apparatus (cuvettes or immersion probes), or with ion exchange resins for analyte enrichment, have been reported. Remarkably, examples of large data correction of unwanted fluorescence by mathematical processing or chemical quenching were reported too, suggesting solutions for the Raman analysis of wastewaters. Finally, a short digression on Machine Learning (ML) applied to RS is proposed, showing the promising results reported in other fields. Data-driven methods could be a solution to improve the low sensitivity of the RS for Nitrate detection. Hence, an approach of ML methods for the typical RS spectra processing (spike removal, baseline correction, fluorescence curve elimination, instrumental noise correction) was hereby mentioned, suggesting an improvement in the detection capability of Nitrate ion in water.


  • Indoor Tracking for Motion-Robust Respiration Rate Extraction with FMCW Radar

    by Michela Raimondi, Antonio Nocera, Gianluca Ciattaglia, Linda Senigagliesi, Ennio Gambi

    Respiratory rate is a relevant parameter to be monitored to prevent adverse cardiopulmonary situations. Radar sensing represents a promising alternative to wearable sensors, since it gives the opportunity to remotely monitor a subject, while maintaining privacy and fairness. In this work, radar is used to enable a single sensor to track and extract the respiratory rate of a freely moving subject. To validate performance, the subject first walks in a straight line and then moves randomly within a room. As a reference, they are instructed to control their breathing pace using a metronome. A state of art deep learning algorithm, previously developed for person detection purposes and called mmDetect, is applied to localize and track the subject. The developed processing pipeline allows the extraction of the beat signal phase shift associated with chest displacement at each location, which is then used to reconstruct a phase signal linked to the respiratory phenomenon. A resulting measurement error of 1 breath per minute (BPM) is demonstrated.