Omer Melih Gul

Dr. Omer Melih Gul

orcid

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
14 March 2023 in IEEE Access
Verified
Journal Article
Open access
OGOmer Melih Gul
Omer Melih Gul
MKMichel Kulhandjian
Michel Kulhandjian
Burak KantarciBurak Kantarci
Burak Kantarci
ATAzzedine Touazi
Azzedine Touazi
CECliff Ellement
Cliff Ellement
CDClaude D'Amours
Claude D'Amours
Industrial IoT-enabled critical infrastructures are susceptible to cyber attacks due to their mission-critical deployment. To ensure security by design, radio frequency (RF)-based security is considered an effective way for wirelessly monitored or actuated critical infrastructures. For this purpose, this paper presents a novel augmentation-driven deep learning approach to analyze unique transmitter fingerprints and determine the legitimacy of a user device or transmitter. An RF fingerprinting model is susceptible to various channel and environmental conditions that impact the learning performance of a machine/deep learning model. As data gathering cannot always be considered a feasible alternative, efficient solutions that can tackle the impact of varying propagation channels on learning performance are emergent. This work aims to shed light on the RF fingerprinting problem from a different angle when 4G, 5G, and WiFi data samples are collected from different transmitters by proposing a fine-grained augmentation approach to improve the learning performance of a deep learning model. This work also proposes an enhanced classifier structure following the fine-grained augmentation approach. Results of experiments, conducted on the POWDER dataset, demonstrate promising RF fingerprinting performance when training data are augmented in a waveform-specific fine-grained manner. Thus, the RF identification accuracy can be boosted to 97.84% on unseen RF data instances from our previously published work where we had achieved an accuracy of 87.94% using tapped delay line (TDL)/clustered delay line (CDL)-based augmentation approach. The paper also presents a sensitivity analysis of the fine-grained approach concerning different signal-to-noise-ratio (SNR), signal-to-interference-ratio (SIR) levels (20 dB and 30 dB), and signal-to-interference-plus-noise-ratio (SINR) levels (15 dB, 25 dB). The sensitivity analysis exhibits that it achieves 85.78% accuracy at 20 dB SIR on both Day 1 (train) and Day 2 (test) data. In addition, it achieves 92.37% accuracy even at 20 dB SNR on Day 2 data from POWDER dataset. Furthermore, it achieves 84.95% accuracy at 15 dB SINR on Day 2 data. Hence, these results exhibit the resiliency of the fine-grained augmentation approach against interference and noise.

13 December 2024 in Cluster Computing
Verified
Journal Article
Closed access
PDF file
ASAram Satouf
Aram Satouf
Ali HamidoğluAli Hamidoğlu
Ali Hamidoğlu
OGOmer Melih Gul
Omer Melih Gul
AKAlar Kuusik
Alar Kuusik
LALutfiye Durak Ata
Lutfiye Durak Ata
Seifedine KadrySeifedine Kadry
Seifedine Kadry


16 October 2020 in Sensors
Verified
Journal Article
Open access
PDF file
OGOmer Melih Gul
Omer Melih Gul
AEAydan Muserref Erkmen
Aydan Muserref Erkmen
In this work, our motivation focuses on an energy-efficient data collection problem by a mobile sink, an unmanned aerial vehicle (UAV) with limited battery capacity, in a robot network divided into several robot clusters. In each cluster, a cluster head (CH) robot allocates tasks to the remaining robots and collects data from them. Our contribution is to minimize the UAV total energy consumption coupled to minimum cost data collection from CH robots by visiting optimally a portion of the CH robots. The UAV decides the subset of CH robots to visit by considering not only the locations of all CH robots but also its battery capacity. If the UAV cannot visit all CH robots, then the CH robots not visited by the UAV transmit their data to another CH robot to forward it. The decision of transmission paths of transmitting robots is included in the cost optimization. Our contribution passes beyond the existing paradigms in the literature by considering the constant battery capacity for the UAV. We derive the optimal approach analytically for this problem. For various numbers of clusters, the performance of our strategy is compared with the approach in the close literature in terms of total energy consumed by CH robots, which affects network lifetime. Numerical results demonstrate that our strategy outperforms the approach in the close literature.

6 September 2024 in Sensors
Verified
Journal Article
Open access
PDF file
CECigdem Eris
Cigdem Eris
OGOmer Melih Gul
Omer Melih Gul
PBPinar Boluk
Pinar Boluk
Underwater acoustic sensor networks (UASNs) are fundamental assets to enable discovery and utilization of sub-sea environments and have attracted both academia and industry to execute long-term underwater missions. Given the heightened significance of battery dependency in underwater wireless sensor networks, our objective is to maximize the amount of harvested energy underwater by adopting the TDMA time slot scheduling approach to prolong the operational lifetime of the sensors. In this study, we considered the spatial uncertainty of underwater ambient resources to improve the utilization of available energy and examine a stochastic model for piezoelectric energy harvesting. Considering a realistic channel and environment condition, a novel multi-agent reinforcement learning algorithm is proposed. Nodes observe and learn from their choice of transmission slots based on the available energy in the underwater medium and autonomously adapt their communication slots to their energy harvesting conditions instead of relying on the cluster head. In the numerical results, we present the impact of piezoelectric energy harvesting and harvesting awareness on three lifetime metrics. We observe that energy harvesting contributes to 4% improvement in first node dead (FND), 14% improvement in half node dead (HND), and 22% improvement in last node dead (LND). Additionally, the harvesting-aware TDMA-RL method further increases HND by 17% and LND by 38%. Our results show that the proposed method improves in-cluster communication time interval utilization and outperforms traditional time slot allocation methods in terms of throughput and energy harvesting efficiency.

16 August 2018 in IEEE Access
Verified
Journal Article
Open access
OGOmer Melih Gul
Omer Melih Gul
MDMubeccel Demirekler
Mubeccel Demirekler
In this paper, we investigate a single-hop wireless sensor network in which a fusion center (FC) collects data packets from $M$ energy harvesting (EH) sensor nodes. Energy harvested by each node is stored without battery overflow and leakage at that node. The FC schedules $K$ nodes over its mutually orthogonal channels to receive data from them in each time slot. The FC knows neither the statistics of EH processes nor the battery states of nodes. The FC solely has information on consequences of previous transmission attempts. We aim for obtaining an efficient and simple policy achieving maximum throughput in this network. The nodes are data backlogged and the data transmission only depends on the harvested energy of the scheduled nodes. A node can transmit data whenever it is scheduled, provided that it has sufficient energy. We propose a simple policy, uniforming random ordered policy (UROP) , for the problem. We exhibit that the UROP is nearly throughput-optimal over finite time horizons for a broad class of EH processes. We also prove that for general EH processes, UROP achieves asymptotically optimal throughput over the infinite time horizon under infinite capacity battery assumption. Numerical results indicate that even with finite-capacity batteries, UROP achieves near-optimal throughput over finite time horizons. We believe that UROP is applicable to much wider area than EH wireless sensor networks.