Gulmina Malik

Ms. Gulmina Malik

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
20 June 2025 in AI
Verified
Journal Article
Open access
PDF file
Gulmina MalikGulmina Malik
Gulmina Malik
IDImran Chowdhury Dipto
Imran Chowdhury Dipto
Muhammad Umar MasoodMuhammad Umar Masood
Muhammad Umar Masood
MMMASHBOOB CHERUVAKKADU MOHAMED
MASHBOOB CHERUVAKKADU MOHAMED
SSStefano Straullu
Stefano Straullu
VCVittorio Curri
Vittorio Curri
We present a thorough machine-learning framework based on real-time state-of-polarization (SOP) monitoring for robust anomaly identification in optical fiber networks. We exploit SOP data under three different threat scenarios: (i) malicious or critical vibration events, (ii) overlapping mechanical disturbances, and (iii) malicious fiber tapping (eavesdropping). We used various supervised machine learning techniques like k-Nearest Neighbor (k-NN), random forest, extreme gradient boosting (XGBoost), and decision trees to classify different vibration events. We also assessed the framework’s resilience to background interference by superimposing sinusoidal noise at different frequencies and examining its effects on the polarization signatures. This analysis provides insight into how subsurface installations, subject to ambient vibrations, affect detection fidelity. This highlights the sensitivity to which external interference affects polarization fingerprints. Crucially, it demonstrates the system’s capacity to discern and alert on malicious vibration events even in the presence of environmental noise. However, we focus on the necessity of noise-mitigation techniques in real-world implementations while providing a potent, real-time mechanism for multi-threat recognition in the fiber networks.

1 November 2026 in IEEE Photonics Technology Letters
Verified
Journal Article
Closed access
AAAhtisham Ali
Ahtisham Ali
Muhammad Umar MasoodMuhammad Umar Masood
Muhammad Umar Masood
ARAndrea Rosso
Andrea Rosso
Gulmina MalikGulmina Malik
Gulmina Malik
MPMichela Pollone
Michela Pollone
VCVittorio Curri
Vittorio Curri
Disaggregation of the Radio Access Network (RAN) imposes stringent fronthaul latency and physical-layer performance requirements on supporting the optical transport infrastructure. This paper evaluates the feasibility of Access–DU–Access (A–DU–A) routes in a converged metro–access optical network, jointly considering Bit Error Rate (BER) and the fronthaul latency constraint of 250 μs, considering functional split 7.2 defined by 3GPP. Two deployment scenarios are examined: (i) DU/CU hosting at metropolitan Points of Presence (PoPs) and (ii) DU/CU hosting at external data centers (DCs). Using Cassini and Phoenix whiteboxes hosting pluggable DCO transceivers (TRxs), the analysis quantifies the impact of modulation format, BER thresholds, and end-to-end propagation latency on service feasibility. Results show that metro-based hosting supports 87.9% latency-compliant routes compared to 47.6% under data-center hosting, and that Cassini consistently provides higher BER feasibility across modulation formats. The findings demonstrate that physical-layer impairments and functional placement must be jointly optimized to support latency-constrained, virtualized RAN transport in converged metro–access networks.

1 January 2021
Verified
Conference Paper
Closed access
PDF file
Gulmina MalikGulmina Malik
Gulmina Malik
AAAkhlaque Ahmad
Akhlaque Ahmad
AAArsalan Ahmad
Arsalan Ahmad
We implement the co-existence of independent DBA algorithms, at OLT, sharing the PON upstream capacity. Results indicate that service performance, in terms of packet loss and delay, is affected by virtual operator's choice of DBA.

4 June 2026 in Journal of Optical Communications and Networking
Verified
Journal Article
Closed access
EVEmanuele Virgillito
Emanuele Virgillito
FNFederico Notarstefano
Federico Notarstefano
RARenato Ambrosone
Renato Ambrosone
Gulmina MalikGulmina Malik
Gulmina Malik
SSStefano Straullu
Stefano Straullu
VCVittorio Curri
Vittorio Curri
Transforming optical transport networks into a distributed sensing grid is a promising pathway to enhance infrastructure resilience and environmental awareness. To achieve widespread scalability without disrupting data traffic, operators can exploit the synergy between different sensing techniques naturally coexisting on the same infrastructure. In this paper, we present an in-field demonstration of a multi-technique sensing framework operating on live terrestrial optical networks, combining interferometric phase sensing and state of polarization (SOP) monitoring. We first propose and validate an unsupervised anomaly detection pipeline based on autoencoders, applied to a 38 km regional link connecting Ascoli Piceno and Teramo (Italy), and show some examples of detected events. This framework proves capable of automatically identifying signal anomalies across different physical observables without relying on manual labeling. Subsequently, we move to a metropolitan urban scenario in the city of Turin and assess a multi-tech sensing analysis using coherent transceivers and state-of-polarization metrics obtained from polarimeters and a cost-effective polarization beam splitter-based device. We highlight the correlation between specific sensing metrics and standard network telemetry data, such as the bit error rate (BER) and temperature, and validate the system’s capability to detect mechanical perturbations originating from human activity along the cable or from controlled experiments using a robotic arm. These results confirm the feasibility of aggregating heterogeneous data sources into a unified sensing plane to enable pervasive infrastructure supervision.

26 March 2026 in IEEE Photonics Technology Letters
Verified
Journal Article
Closed access
Gulmina MalikGulmina Malik
Gulmina Malik
Muhammad Umar MasoodMuhammad Umar Masood
Muhammad Umar Masood
AAAhtisham Ali
Ahtisham Ali
MMMASHBOOB CHERUVAKKADU MOHAMED
MASHBOOB CHERUVAKKADU MOHAMED
SSStefano Straullu
Stefano Straullu
VCVittorio Curri
Vittorio Curri
This work presents a machine-learning framework for detecting and classifying independent and overlapping anomaly signatures in optical fiber infrastructure using state-of-polarization (SOP) dynamics. The framework exploits temporal variations of the Stokes parameters to characterize bending, tapping, shaking, and their simultaneous combinations. An experimentally collected dataset is used to evaluate multiple machine-learning models under realistic noise conditions representative of practical fiber monitoring environments. The results demonstrate that SOP-based features enable accurate identification of complex fiber disturbances, strengthening physical-layer monitoring and supporting the secure and reliable operation of next-generation optical networks.

27 May 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
Gulmina MalikGulmina Malik
Gulmina Malik
IDImran Chowdhury Dipto
Imran Chowdhury Dipto
MMMuhammad Umar Masood
Muhammad Umar Masood
MMMASHBOOB CHERUVAKKADU MOHAMED
MASHBOOB CHERUVAKKADU MOHAMED
SSStefano Straullu
Stefano Straullu
VCVittorio Curri
Vittorio Curri
We present a thorough machine-learning framework based on real-time state of polarization (SOP) monitoring for robust anomaly identification in optical fiber networks. We exploit SOP data under three different threat scenarios: (i) malicious or critical vibration events, (ii) overlapping mechanical disturbances, and (iii) malicious fiber tapping (eavesdropping). We have used various supervised machine learning techniques like k-Nearest Neighbor (kNN), random forest, extreme gradient boosting (XGBoost) and decision trees to classify different vibration events. We also assessed the framework’s resilience to background interference by superimposing sinusoidal noise at different frequencies and examining its effects on the polarization signatures. This analysis provides insight into how subsurface installations, subject to ambient vibrations, affect detection fidelity. This highlights the sensitivity to which external interference affects polarization fingerprints. Crucially, it demonstrates the system’s capacity to discern and alert on malicious vibration events even in the presence of environmental noise. However, we focus on the necessity of noise-mitigation techniques in real-world implementations while providing a potent, real-time mechanism for multi-threat recognition in the fiber networks.