Omar Serghini

Mr. Omar Serghini

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 December 2023 in Future Internet
Verified
Journal Article
Open access
PDF file
OSOmar Serghini
Omar Serghini
HSHayat SEMLALI
Hayat SEMLALI
AMAsmaa Maali
Asmaa Maali
AGAbdelilah Ghammaz
Abdelilah Ghammaz
Salvatore SerranoSalvatore Serrano
Salvatore Serrano
Spectrum sensing is an essential function of cognitive radio technology that can enable the reuse of available radio resources by so-called secondary users without creating harmful interference with licensed users. The application of machine learning techniques to spectrum sensing has attracted considerable interest in the literature. In this contribution, we study cooperative spectrum sensing in a cognitive radio network where multiple secondary users cooperate to detect a primary user. We introduce multiple cooperative spectrum sensing schemes based on a deep neural network, which incorporate a one-dimensional convolutional neural network and a long short-term memory network. The primary objective of these schemes is to effectively learn the activity patterns of the primary user. The scenario of an imperfect transmission channel is considered for service messages to demonstrate the robustness of the proposed model. The performance of the proposed methods is evaluated with the receiver operating characteristic curve, the probability of detection for various SNR levels and the computational time. The simulation results confirm the effectiveness of the bidirectional long short-term memory-based method, surpassing the performance of the other proposed schemes and the current state-of-the-art methods in terms of detection probability, while ensuring a reasonable online detection time.

29 June 2024 in Electronics
Verified
Journal Article
Open access
PDF file
Salvatore SerranoSalvatore Serrano
Salvatore Serrano
LPL. Patané
L. Patané
OSOmar Serghini
Omar Serghini
Scarpa MarcoScarpa Marco
Scarpa Marco
Sleep disorders are steadily increasing in the population and can significantly affect daily life. Low-cost and noninvasive systems that can assist the diagnostic process will become increasingly widespread in the coming years. This work aims to investigate and compare the performance of machine learning-based classifiers for the identification of obstructive sleep apnea–hypopnea (OSAH) events, including apnea/non-apnea status classification, apnea–hypopnea index (AHI) prediction, and AHI severity classification. The dataset considered contains recordings from 192 patients. It is derived from a recently released dataset which contains, amongst others, audio signals recorded with an ambient microphone placed ∼1 m above the studied subjects and apnea/hypopnea accurate events annotations performed by specialized medical doctors. We employ mel spectrogram images extracted from the environmental audio signals as input of a machine-learning-based classifier for apnea/hypopnea events classification. The proposed approach involves a stacked model which utilizes a combination of a pretrained VGG-like audio classification (VGGish) network and a bidirectional long short-term memory (bi-LSTM) network. Performance analysis was conducted using a 5-fold cross-validation approach, leaving out patients used for training and validation of the models in the testing step. Comparative evaluations with recently presented methods from the literature demonstrate the advantages of the proposed approach. The proposed architecture can be considered a useful tool for supporting OSAHS diagnoses by means of low-cost devices such as smartphones.

14 October 2025 in Data
Verified
Journal Article
Open access
PDF file
Salvatore SerranoSalvatore Serrano
Salvatore Serrano
OSOmar Serghini
Omar Serghini
GEGiulia Esposito
Giulia Esposito
SCSilvia Carbone
Silvia Carbone
Carmela MentoCarmela Mento
Carmela Mento
Luigi AtzoriLuigi Atzori
Luigi Atzori
Speech emotion recognition (SER) has become increasingly important in areas such as healthcare, customer service, robotics, and human–computer interaction. The progress of this field depends not only on advances in algorithms but also on the databases that provide the training material for SER systems. These resources set the boundaries for how well models can generalize across speakers, contexts, and cultures. In this paper, we present a narrative review and comparative analysis of emotional speech corpora released up to mid-2025, bringing together both psychological and technical perspectives. Rather than following a systematic review protocol, our approach focuses on providing a critical synthesis of more than fifty corpora covering acted, elicited, and natural speech. We examine how these databases were collected, how emotions were annotated, their demographic diversity, and their ecological validity, while also acknowledging the limits of available documentation. Beyond description, we identify recurring strengths and weaknesses, highlight emerging gaps, and discuss recent usage patterns to offer researchers both a practical guide for dataset selection and a critical perspective on how corpus design continues to shape the development of robust and generalizable SER systems.

14 June 2023 in TechRxiv
Verified
Preprint
Open access
PDF file
OSOmar Serghini
Omar Serghini
HSHayat SEMLALI
Hayat SEMLALI
AGAbdelilah Ghammaz
Abdelilah Ghammaz
AMAsmaa Maali
Asmaa Maali
Salvatore SerranoSalvatore Serrano
Salvatore Serrano
Spectrum sensing is an essential function of cognitive radio technology that can enable the reuse of available radio resources by so-called secondary users without creating harmful interference with licensed users. The application of machine learning techniques to spectrum sensing has attracted consid?erable interest in the literature. In this contribution, we study cooperative spectrum sensing in a cognitive radio network where multiple secondary users cooperate to detect a primary user. We introduced multiple cooperative spectrum sensing schemes based on a tree deep neural network architecture, which incorporate a one-dimensional convolutional neural network and a long short-term memory network. The primary objective of these schemes is to effectively learn the activity pattern of the primary user. The scenario of an imperfect transmission channel is considered to demonstrate the robustness of the proposed model. The performance of the proposed methods are evaluated with the receiver operating characteristic curves, the probability of detection for various SNR levels and the computational time. The simulation results confirm the effectiveness of the bidirectional long short-term memory based method, surpassing the performance of the other proposed schemes and the current state of the art in terms of detection probability while ensuring a reasonable online detection time.

13 November 2026 in Big Data and Cognitive Computing
Verified
Journal Article
Open access
PDF file
OSOmar Serghini
Omar Serghini
Salvatore SerranoSalvatore Serrano
Salvatore Serrano
Scarpa MarcoScarpa Marco
Scarpa Marco
MLMirko Lucchese
Mirko Lucchese
Post-default debt collection requires agencies to allocate delinquent cases across collectors under eligibility and workload constraints, yet most predictive research concentrates on credit scoring rather than on the assignment decision itself. This paper develops a prediction-to-assignment framework using 1.28 million longitudinal assignment episodes from utilities portfolios managed by a large European credit management company. A model selected on development data scores the feasible alternative agents at each historical decision point, reconstructed under strict temporal ordering. The resulting probabilities are used to evaluate capacity-constrained assignment policies, and the predicted differences between agents are tested against observed outcomes. Under the model’s scores, a conservative policy that prohibits score-decreasing reassignments raises mean predicted recovery probability by 2.37 percentage points under historical workloads. An observational contrast calibration, however, indicates that outcomes reflect the predicted agent differences at about 40% of their strength (slope 0.41); after calibration, the conservative policy gain is 0.96 points (95% period-bootstrap interval 0.89–1.03), 0.60–1.32 across the slope’s confidence interval, and 0.53 when combining the natural-roster slope, daily batches, and unchanged assignments outside the candidate rules. Doubly robust estimates for simpler policies imply slopes of 0.28–0.42, and random feasible reassignment yields negligible gain. Model-guided agent–case matching therefore retains positive estimated value under operational constraints, but uncalibrated scores substantially overstate it.