Hojjat Navidan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Hojjat Navidan has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Adnan Shahid
Department of Information Technology, IDLab, Ghent University - imec, Ghent, Belgium
4 shared publications - Ingrid Moerman
Ghent University–imec
3 shared publications Adnan Shahid
Department of Information Technology, IDLab, Ghent University -imec
2 shared publications- Eli De Poorter
Ghent University
2 shared publications Ingrid Moerman
Department of Information Technology, IDLab, Ghent University -imec
2 shared publications- Jaron Fontaine
Department of Information Technology, IDLab, Ghent University - imec, Ghent, Belgium
2 shared publications
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Network
- Vol. 40 (6) , 125-133
Toward Autonomous O-RAN: A Multi-Scale Agentic AI Framework for Real-Time Network Control and Management
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Network
- Vol. 40 (6) , 125-133
Toward Autonomous O-RAN: A Multi-Scale Agentic AI Framework for Real-Time Network Control and Management
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Communications Society
- Vol. 7, 13828-13847
FedCoBott: Communication-Efficient Personalized Federated Learning for UWB LoS/NLoS Classification
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Communications Society
- Vol. 7, 13828-13847
Open AccessFedCoBott: Communication-Efficient Personalized Federated Learning for UWB LoS/NLoS Classification
- Open Access
- 11 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
An End-to-End Digital Twin Framework for Dynamic Traffic Analytics in O-RAN
Dynamic traffic patterns and shifts in traffic distribution in Open Radio Access Networks (O-RAN) pose a significant challenge for real-time network optimization in 5G and beyond. Traditional traffic analytics methods struggle to remain accurate under such non-stationary conditions, where models trained on historical data quickly degrade as traffic evolves. This paper introduces AIDITA, an AI-driven Digital Twin for Traffic Analytics framework designed to solve this problem through autonomous model adaptation. AIDITA creates a digital replica of the live analytics models running in the RAN Intelligent Controller (RIC) and continuously updates them within the digital twin using incremental learning. These updates use real-time Key Performance Metrics (KPMs) from the live network, augmented with synthetic data from a Generative AI (GenAI) component to simulate diverse network scenarios. Combining GenAI-driven augmentation with incremental learning enablestraffic analytics models, such as prediction or anomaly detection, to adapt continuously without the need for full retraining, preserving accuracy and efficiency in dynamic environments. Implemented and validated on a real-world 5G testbed, our AIDITA framework demonstrates significant improvements in traffic prediction and anomaly detection use cases under distribution shifts, showcasing its practical effectiveness and adaptability for real-time network optimization in O-RAN deployments.
- 11 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Open AccessAn End-to-End Digital Twin Framework for Dynamic Traffic Analytics in O-RAN
Dynamic traffic patterns and shifts in traffic distribution in Open Radio Access Networks (O-RAN) pose a significant challenge for real-time network optimization in 5G and beyond. Traditional traffic analytics methods struggle to remain accurate under such non-stationary conditions, where models trained on historical data quickly degrade as traffic evolves. This paper introduces AIDITA, an AI-driven Digital Twin for Traffic Analytics framework designed to solve this problem through autonomous model adaptation. AIDITA creates a digital replica of the live analytics models running in the RAN Intelligent Controller (RIC) and continuously updates them within the digital twin using incremental learning. These updates use real-time Key Performance Metrics (KPMs) from the live network, augmented with synthetic data from a Generative AI (GenAI) component to simulate diverse network scenarios. Combining GenAI-driven augmentation with incremental learning enablestraffic analytics models, such as prediction or anomaly detection, to adapt continuously without the need for full retraining, preserving accuracy and efficiency in dynamic environments. Implemented and validated on a real-world 5G testbed, our AIDITA framework demonstrates significant improvements in traffic prediction and anomaly detection use cases under distribution shifts, showcasing its practical effectiveness and adaptability for real-time network optimization in O-RAN deployments.
- Open Access
- 11 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Closed-loop Intelligence Using Large Language Models in Wireless Networks
Large Language Models (LLMs) are emerging as a transformative tool for wireless network management, offering the ability to interpret natural language instructions, reason over diverse data types, and adapt rapidly through in-context learning. Their generalization capabilities make them promising candidates for acting as the intelligent core within the Open Radio Access Networks (O-RAN), enabling more robust and flexible control of network behavior. However, it remains unclear how to systematically integrate, evaluate, and compare different LLMs for specific tasks in live network deployments. We present Closed-loop Intelligence using LLMs (CLI-LLM), an open-source framework that transforms real-time network metrics and operator intents into automated network control actions. The goal of this demo is to showcase how different LLMs, whether commercial or open-source, can be integrated into the RAN Intelligent Controller (RIC) to handle tasks such as resource allocation, while also providing time-series analysis capabilities, including anomaly detection and trend prediction.
- 11 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Open AccessClosed-loop Intelligence Using Large Language Models in Wireless Networks
Large Language Models (LLMs) are emerging as a transformative tool for wireless network management, offering the ability to interpret natural language instructions, reason over diverse data types, and adapt rapidly through in-context learning. Their generalization capabilities make them promising candidates for acting as the intelligent core within the Open Radio Access Networks (O-RAN), enabling more robust and flexible control of network behavior. However, it remains unclear how to systematically integrate, evaluate, and compare different LLMs for specific tasks in live network deployments. We present Closed-loop Intelligence using LLMs (CLI-LLM), an open-source framework that transforms real-time network metrics and operator intents into automated network control actions. The goal of this demo is to showcase how different LLMs, whether commercial or open-source, can be integrated into the RAN Intelligent Controller (RIC) to handle tasks such as resource allocation, while also providing time-series analysis capabilities, including anomaly detection and trend prediction.
- 4 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network and Service Management
- Vol. 23, 76-92
An End-to-End Digital Twin Framework for Dynamic Traffic Analytics in O-RAN
Dynamic traffic patterns and shifts in traffic distribution in Open Radio Access Networks (O-RAN) pose a significant challenge for real-time network optimization in 5G and beyond. Traditional traffic analytics methods struggle to remain accurate under such non-stationary conditions, where models trained on historical data quickly degrade as traffic evolves. This paper introduces AIDITA, an AI-driven Digital Twin for Traffic Analytics framework designed to solve this problem through autonomous model adaptation. AIDITA creates a digital replica of the live analytics models running in the RAN Intelligent Controller (RIC) and continuously updates them within the digital twin using incremental learning. These updates use real-time Key Performance Metrics (KPMs) from the live network, augmented with synthetic data from a Generative AI (GenAI) component to simulate diverse network scenarios. Combining GenAI-driven augmentation with incremental learning enables traffic analytics models, such as prediction or anomaly detection, to adapt continuously without the need for full retraining, preserving accuracy and efficiency in dynamic environments. Implemented and validated on a real-world 5G testbed, our AIDITA framework demonstrates significant improvements in traffic prediction and anomaly detection use cases under distribution shifts, showcasing its practical effectiveness and adaptability for real-time network optimization in O-RAN deployments.
- 4 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network and Service Management
- Vol. 23, 76-92
An End-to-End Digital Twin Framework for Dynamic Traffic Analytics in O-RAN
Dynamic traffic patterns and shifts in traffic distribution in Open Radio Access Networks (O-RAN) pose a significant challenge for real-time network optimization in 5G and beyond. Traditional traffic analytics methods struggle to remain accurate under such non-stationary conditions, where models trained on historical data quickly degrade as traffic evolves. This paper introduces AIDITA, an AI-driven Digital Twin for Traffic Analytics framework designed to solve this problem through autonomous model adaptation. AIDITA creates a digital replica of the live analytics models running in the RAN Intelligent Controller (RIC) and continuously updates them within the digital twin using incremental learning. These updates use real-time Key Performance Metrics (KPMs) from the live network, augmented with synthetic data from a Generative AI (GenAI) component to simulate diverse network scenarios. Combining GenAI-driven augmentation with incremental learning enables traffic analytics models, such as prediction or anomaly detection, to adapt continuously without the need for full retraining, preserving accuracy and efficiency in dynamic environments. Implemented and validated on a real-world 5G testbed, our AIDITA framework demonstrates significant improvements in traffic prediction and anomaly detection use cases under distribution shifts, showcasing its practical effectiveness and adaptability for real-time network optimization in O-RAN deployments.
- Open Access
- 25 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Communications Society
- Vol. 5, 1975-1986
Radio Resource Management for Intelligent Neutral Host (INH) in Multi-Operator Environments
In the era of fifth-generation (5G) cellular networks and beyond, network sharing has emerged as a promising approach to address the escalating demand for spectrum and infrastructure resources. Intelligent Neutral Host (INH) is an advanced network-sharing method facilitated by Open Radio Access Network (O-RAN) capabilities. This paper addresses the challenge of Radio Resource Management (RRM) in a multi-operator, multi-slice scenario. We propose an algorithm based on Q-learning and deep Q-learning, particularly concerning different Physical Resource Block (PRB) types to cater to diverse operator requirements. Implemented as an xApp on the Colosseum platform, our algorithm introduces a dynamic resource allocation strategy that adheres to Service Level Agreement (SLA) constraints and optimizes real-time Key Performance metrics (KPMs), including throughput, buffer occupancy, and PRB utilization. We assess the performance and efficacy of our algorithm in a complex traffic scenario to demonstrate how it effectively allocates resources among operators’ slices to satisfy their respective SLA while ensuring optimal resource utilization. The experimental results show that our proposed algorithm can efficiently allocate resources to individual slices while satisfying the SLA. Compared to traditional algorithms, our approach significantly minimizes SLA violations, reducing them to 2.5% for enhanced Mobile Broadband (eMBB) slices and eliminating them entirely for Ultra-Reliable Low-Latency Communications (URLLC) slices.
- 25 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Communications Society
- Vol. 5, 1975-1986
Open AccessRadio Resource Management for Intelligent Neutral Host (INH) in Multi-Operator Environments
In the era of fifth-generation (5G) cellular networks and beyond, network sharing has emerged as a promising approach to address the escalating demand for spectrum and infrastructure resources. Intelligent Neutral Host (INH) is an advanced network-sharing method facilitated by Open Radio Access Network (O-RAN) capabilities. This paper addresses the challenge of Radio Resource Management (RRM) in a multi-operator, multi-slice scenario. We propose an algorithm based on Q-learning and deep Q-learning, particularly concerning different Physical Resource Block (PRB) types to cater to diverse operator requirements. Implemented as an xApp on the Colosseum platform, our algorithm introduces a dynamic resource allocation strategy that adheres to Service Level Agreement (SLA) constraints and optimizes real-time Key Performance metrics (KPMs), including throughput, buffer occupancy, and PRB utilization. We assess the performance and efficacy of our algorithm in a complex traffic scenario to demonstrate how it effectively allocates resources among operators’ slices to satisfy their respective SLA while ensuring optimal resource utilization. The experimental results show that our proposed algorithm can efficiently allocate resources to individual slices while satisfying the SLA. Compared to traditional algorithms, our approach significantly minimizes SLA violations, reducing them to 2.5% for enhanced Mobile Broadband (eMBB) slices and eliminating them entirely for Ultra-Reliable Low-Latency Communications (URLLC) slices.
- Open Access
- 28 September 2022
- Published by Elsevier in Computers & Security
- Vol. 123
Add noise to remove noise: Local differential privacy for feature selection
- 28 September 2022
- Published by Elsevier in Computers & Security
- Vol. 123
Open AccessAdd noise to remove noise: Local differential privacy for feature selection
- 1 July 2021
- Published by Elsevier in Computer Networks
- Vol. 194
Generative Adversarial Networks (GANs) in networking: A comprehensive survey & evaluation
- 1 July 2021
- Published by Elsevier in Computer Networks
- Vol. 194
Generative Adversarial Networks (GANs) in networking: A comprehensive survey & evaluation