Frank Yong Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Frank Yong Li has a total of 92 co-authors. Here are the top co-authors by number of shared publications:
- Indika Anuradha Mendis Balapuwaduge
Department of Information and Communication Technology, University of Agder (UiA), Grimstad, Norway
8 shared publications - Vicent Pla
Universitat Politècnica de València Spain
7 shared publications Debasish Ghose
5 shared publications- Debasish Ghose
Kristiania University of Applied Sciences, Bergen, Norway
5 shared publications Lakshmikanth Guntupalli
4 shared publications- Marius Vochin
Department of Telecommunications, National University of Science and Technology POLITEHNICA, Bucharest, Romania
4 shared publications
Latest Publications
- 1 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 73 (12) , 14413-14429
Semi-Contention-Free Access in IoT NOMA Networks: A Reinforcement Learning Framework
- 1 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 73 (12) , 14413-14429
Semi-Contention-Free Access in IoT NOMA Networks: A Reinforcement Learning Framework
- Open Access
- 19 August 2025
- Published by Springer Nature in Telecommunication Systems
- Vol. 88 (3) , 1-19
Enabling machine learning-assisted resource monitoring for network slice creation and management in OSM: design, implementation, and validation
As a novel concept introduced in 5th generation (5G) mobile networks, network slicing allows configuring a shared physical infrastructure into multiple logical networks that are virtually isolated from each other. Through these logical networks, resource allocation for specific use cases is tailored, facilitating rapid and flexible development of new services and applications. To create and manage network slices, open source management and orchestration (OSM) has emerged as a powerful tool for software developers and network operators. Within the scope of automatic slice generation and management using OSM, however, whether and how machine learning can play a role remain as a hardly addressed research question. In this paper, we explore the feasibility of applying machine learning to OSM for the purpose of improving slice creation and management efficiency. To do so, we introduce an enhancement in the monitoring module of the OSM architecture. More specifically, a machine learning based alarm monitoring sub-module is developed, such that a new field value is automatically generated every time when an alarm is identified. In addition, we create a prediction model for resource utilization prediction so that the most suitable resources can be allocated when a slice is created. Furthermore, we have implemented our solution in a network slicing platform we developed based on OSM and performed proof-of-concept validation through two network slicing scenarios. Through simulation-based validation and testing, we reveal that the proposed method achieves reliable performance and demonstrate the effectiveness of our solution towards automation network slice creation and management in OSM.
- 19 August 2025
- Published by Springer Nature in Telecommunication Systems
- Vol. 88 (3) , 1-19
Open AccessEnabling machine learning-assisted resource monitoring for network slice creation and management in OSM: design, implementation, and validation
As a novel concept introduced in 5th generation (5G) mobile networks, network slicing allows configuring a shared physical infrastructure into multiple logical networks that are virtually isolated from each other. Through these logical networks, resource allocation for specific use cases is tailored, facilitating rapid and flexible development of new services and applications. To create and manage network slices, open source management and orchestration (OSM) has emerged as a powerful tool for software developers and network operators. Within the scope of automatic slice generation and management using OSM, however, whether and how machine learning can play a role remain as a hardly addressed research question. In this paper, we explore the feasibility of applying machine learning to OSM for the purpose of improving slice creation and management efficiency. To do so, we introduce an enhancement in the monitoring module of the OSM architecture. More specifically, a machine learning based alarm monitoring sub-module is developed, such that a new field value is automatically generated every time when an alarm is identified. In addition, we create a prediction model for resource utilization prediction so that the most suitable resources can be allocated when a slice is created. Furthermore, we have implemented our solution in a network slicing platform we developed based on OSM and performed proof-of-concept validation through two network slicing scenarios. Through simulation-based validation and testing, we reveal that the proposed method achieves reliable performance and demonstrate the effectiveness of our solution towards automation network slice creation and management in OSM.
- 14 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Networking Letters
- Vol. 7 (1) , 26-30
Decentralized Coded Caching With Distributed Storage Across Data and Parity Servers
Traditional single server based coded caching may face server saturation and service vulnerability problems. In this letter, we integrate decentralized coded caching with a multi-server architecture comprising both data and parity servers. For file distribution in this network, a method referred to as file stripping is adopted, and a novel file delivery scheme is proposed. Closed-form expressions for the total transmission rate achieved by this scheme are derived, considering all the operational servers along with the worst-case transmission rate amongst these servers. Additionally, a comparative analysis between the proposed scheme and the conventional decentralized coded caching scheme is presented. The simulation results demonstrate the viability of our proposed scheme.
- 14 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Networking Letters
- Vol. 7 (1) , 26-30
Decentralized Coded Caching With Distributed Storage Across Data and Parity Servers
Traditional single server based coded caching may face server saturation and service vulnerability problems. In this letter, we integrate decentralized coded caching with a multi-server architecture comprising both data and parity servers. For file distribution in this network, a method referred to as file stripping is adopted, and a novel file delivery scheme is proposed. Closed-form expressions for the total transmission rate achieved by this scheme are derived, considering all the operational servers along with the worst-case transmission rate amongst these servers. Additionally, a comparative analysis between the proposed scheme and the conventional decentralized coded caching scheme is presented. The simulation results demonstrate the viability of our proposed scheme.
- 25 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 28 (6) , 1437-1441
Optimal M-Level Two-Sided ASK for Noncoherent SIMO Wireless Systems in a Rician Fading Environment
This letter presents a noncoherent single input multiple output wireless communication system, in which the transmitter utilizes a multi-level two-sided amplitude shift keying (ASK) modulation scheme to transmit data symbols over statistically independent Rician fading channels. The receiver applies a maximum likelihood detector to decode the received data. For the performance assessment of such a system, a series-form expression for the union bound on symbol error probability (SEP) is derived and a closed-form expression for the SEP is obtained by applying the central limit theorem when the number of receive antennas is sufficiently large. Moreover, an optimization framework is introduced to obtain optimal ASK constellation, minimizing the SEP under an average transmit energy constraint. The superior performance of the system in comparison with the traditional two-sided ASK constellation is corroborated via numerical results under various parameter configurations.
- 25 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 28 (6) , 1437-1441
Optimal M-Level Two-Sided ASK for Noncoherent SIMO Wireless Systems in a Rician Fading Environment
This letter presents a noncoherent single input multiple output wireless communication system, in which the transmitter utilizes a multi-level two-sided amplitude shift keying (ASK) modulation scheme to transmit data symbols over statistically independent Rician fading channels. The receiver applies a maximum likelihood detector to decode the received data. For the performance assessment of such a system, a series-form expression for the union bound on symbol error probability (SEP) is derived and a closed-form expression for the SEP is obtained by applying the central limit theorem when the number of receive antennas is sufficiently large. Moreover, an optimization framework is introduced to obtain optimal ASK constellation, minimizing the SEP under an average transmit energy constraint. The superior performance of the system in comparison with the traditional two-sided ASK constellation is corroborated via numerical results under various parameter configurations.
- Open Access
- 29 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 32801-32818
Optimization Schedule Schemes for Charging Electric Vehicles: Overview, Challenges, and Solutions
Electric vehicles represent a global endeavor towards environmentally friendly transportation, and such a green transition is promoted worldwide, being deployed in many regions nowadays. As the number of electric vehicles has been increasing rapidly for more than a decade, how to meet the need for charging their batteries appears as an important research topic, having received remarkable attention in both industry and research community. Uncoordinated charging of many electric vehicles may lead to congestion at charging stations and unbalanced load of the power supply grid. To address this problem, optimized charging schemes which consider available energy resources and user requirements are required. This paper offers an overview of state-of-the-art charging solutions covering two main categories of approaches, namely, centralized and decentralized charging. In addition to addressing the potential challenges that arise in charging schedule optimization, we cover various optimization techniques that have been proposed for optimizing charging schedules. Furthermore, this paper analyzes the current solutions and identifies their limitations and gaps. Open research issues are identified and several potential research topics are suggested.
- 29 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 32801-32818
Open AccessOptimization Schedule Schemes for Charging Electric Vehicles: Overview, Challenges, and Solutions
Electric vehicles represent a global endeavor towards environmentally friendly transportation, and such a green transition is promoted worldwide, being deployed in many regions nowadays. As the number of electric vehicles has been increasing rapidly for more than a decade, how to meet the need for charging their batteries appears as an important research topic, having received remarkable attention in both industry and research community. Uncoordinated charging of many electric vehicles may lead to congestion at charging stations and unbalanced load of the power supply grid. To address this problem, optimized charging schemes which consider available energy resources and user requirements are required. This paper offers an overview of state-of-the-art charging solutions covering two main categories of approaches, namely, centralized and decentralized charging. In addition to addressing the potential challenges that arise in charging schedule optimization, we cover various optimization techniques that have been proposed for optimizing charging schedules. Furthermore, this paper analyzes the current solutions and identifies their limitations and gaps. Open research issues are identified and several potential research topics are suggested.
- 9 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-14
Understanding LoRaWAN Transmissions in Harsh Environments: A Measurement-Based Campaign Through Unmanned Aerial/Surface Vehicles
Along with the ubiquity of various Internet of Things (IoT) applications, data collection in harsh environments with the help of unmanned aerial vehicles (UAVs) and unmanned surface vehicles (USVs) appears as a popular approach. However, from a networking and transmission perspective, how unmanned vehicles collaborate with each other and with end IoT devices as well as the propagation characteristics for such data transmissions are less exploited. In this article, we develop a long-range wide-area network (LoRaWAN)-based data collection framework which enables UAV and/or USV-assisted data acquisition in harsh environments. Within this framework, end devices are placed in hard-to-reach locations and data acquisition is performed in an on-demand manner by unmanned vehicles acting as a gateway or peer for end devices (EDs). The framework also includes a step-by-step procedure for data collection and analytics, from parameter configuration to model validation. To reveal the transmission characteristics, we identify three scenarios in a mountainous region in Romania and perform extensive real-life measurements for data collection. Based on the collected datasets, we develop four propagation models and demonstrate that our empirical models outperform the theoretical reference models. Based on the developed empirical models, the coverage of LoRaWAN for any spreading factor (SF) can be estimated with high precision.
- 9 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-14
Understanding LoRaWAN Transmissions in Harsh Environments: A Measurement-Based Campaign Through Unmanned Aerial/Surface Vehicles
Along with the ubiquity of various Internet of Things (IoT) applications, data collection in harsh environments with the help of unmanned aerial vehicles (UAVs) and unmanned surface vehicles (USVs) appears as a popular approach. However, from a networking and transmission perspective, how unmanned vehicles collaborate with each other and with end IoT devices as well as the propagation characteristics for such data transmissions are less exploited. In this article, we develop a long-range wide-area network (LoRaWAN)-based data collection framework which enables UAV and/or USV-assisted data acquisition in harsh environments. Within this framework, end devices are placed in hard-to-reach locations and data acquisition is performed in an on-demand manner by unmanned vehicles acting as a gateway or peer for end devices (EDs). The framework also includes a step-by-step procedure for data collection and analytics, from parameter configuration to model validation. To reveal the transmission characteristics, we identify three scenarios in a mountainous region in Romania and perform extensive real-life measurements for data collection. Based on the collected datasets, we develop four propagation models and demonstrate that our empirical models outperform the theoretical reference models. Based on the developed empirical models, the coverage of LoRaWAN for any spreading factor (SF) can be estimated with high precision.
- 13 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (8) , 14328-14343
Understanding Inter- and Intra-Cluster Concurrent Transmissions for IoT Uplink Traffic in MIMO-NOMA Networks: A DTMC Analysis
To enable concurrent transmissions for Internet of Things (IoT) traffic in multiantenna beyond fifth generation networks, nonorthogonal multiple access (NOMA) mechanisms appear as a promising approach. For NOMA-enabled transmissions, IoT devices are grouped into clusters in order to exploit the benefit of concurrent transmissions. However, how to facilitate transmissions from both intra- and intercluster is not an easy task and the performance of such concurrent transmissions is so far not well understood from a mathematical point of view, especially when error-prone channel conditions are considered. In this article, we propose two random access schemes which enable intra- and intercluster concurrent transmissions for uplink IoT traffic with and without access control. To assess the performance of such systems, we develop two analytical models based on discrete-time Markov chains (DTMCs) that mimic the behavior of such transmissions. Our models deal with cluster-level performance considering dynamic packet arrivals and the transmissions from devices belonging to the same or different clusters. Through extensive simulations, we validate the accuracy of the analytical models and evaluate the system- and cluster-level performance in terms of throughput and delay under various traffic load conditions and network configurations.
- 13 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (8) , 14328-14343
Understanding Inter- and Intra-Cluster Concurrent Transmissions for IoT Uplink Traffic in MIMO-NOMA Networks: A DTMC Analysis
To enable concurrent transmissions for Internet of Things (IoT) traffic in multiantenna beyond fifth generation networks, nonorthogonal multiple access (NOMA) mechanisms appear as a promising approach. For NOMA-enabled transmissions, IoT devices are grouped into clusters in order to exploit the benefit of concurrent transmissions. However, how to facilitate transmissions from both intra- and intercluster is not an easy task and the performance of such concurrent transmissions is so far not well understood from a mathematical point of view, especially when error-prone channel conditions are considered. In this article, we propose two random access schemes which enable intra- and intercluster concurrent transmissions for uplink IoT traffic with and without access control. To assess the performance of such systems, we develop two analytical models based on discrete-time Markov chains (DTMCs) that mimic the behavior of such transmissions. Our models deal with cluster-level performance considering dynamic packet arrivals and the transmissions from devices belonging to the same or different clusters. Through extensive simulations, we validate the accuracy of the analytical models and evaluate the system- and cluster-level performance in terms of throughput and delay under various traffic load conditions and network configurations.
- Open Access
- 27 November 2023
- Published by Elsevier in Vehicular Communications
- Vol. 45
Network slice allocation for 5G V2X networks: A case study from framework to implementation and performance assessment
- 27 November 2023
- Published by Elsevier in Vehicular Communications
- Vol. 45
Open AccessNetwork slice allocation for 5G V2X networks: A case study from framework to implementation and performance assessment
- Open Access
- 8 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 57470-57480
Multi-Class Stress Detection Through Heart Rate Variability: A Deep Neural Network Based Study
Stress is a natural human reaction to demands or pressure, usually when perceived as harmful or/and toxic. When stress becomes constantly overwhelmed and prolonged, it increases the risk of mental health and physiological uneasiness. Furthermore, chronic stress raises the likelihood of mental health plagues such as anxiety, depression, and sleep disorder. Although measuring stress using physiological parameters such as heart rate variability (HRV) is a common approach, how to achieve ultra-high accuracy based on HRV measurements remains as a challenging task. HRV is not equivalent to heart rate. While heart rate is the average value of heartbeats per minute, HRV represents the variation of the time interval between successive heartbeats. The HRV measurements are related to the variance of RR intervals which stand for the time between successive R peaks. In this study, we investigate the role of HRV features as stress detection bio-markers and develop a machine learning-based model for multi-class stress detection. More specifically, a convolution neural network (CNN) based model is developed to detect multi-class stress, namely, no stress, interruption stress, and time pressure stress , based on both time- and frequency-domain features of HRV. Validated through a publicly available dataset, SWELL–KW, the achieved accuracy score of our model has reached 99.9% ( Precision=1, Recall=1, F1-score=1, and MCC=0.99 ), thus outperforming the existing methods in the literature. In addition, this study demonstrates the effectiveness of essential HRV features for stress detection using a feature extraction technique, i.e., analysis of variance.
- 8 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 57470-57480
Open AccessMulti-Class Stress Detection Through Heart Rate Variability: A Deep Neural Network Based Study
Stress is a natural human reaction to demands or pressure, usually when perceived as harmful or/and toxic. When stress becomes constantly overwhelmed and prolonged, it increases the risk of mental health and physiological uneasiness. Furthermore, chronic stress raises the likelihood of mental health plagues such as anxiety, depression, and sleep disorder. Although measuring stress using physiological parameters such as heart rate variability (HRV) is a common approach, how to achieve ultra-high accuracy based on HRV measurements remains as a challenging task. HRV is not equivalent to heart rate. While heart rate is the average value of heartbeats per minute, HRV represents the variation of the time interval between successive heartbeats. The HRV measurements are related to the variance of RR intervals which stand for the time between successive R peaks. In this study, we investigate the role of HRV features as stress detection bio-markers and develop a machine learning-based model for multi-class stress detection. More specifically, a convolution neural network (CNN) based model is developed to detect multi-class stress, namely, no stress, interruption stress, and time pressure stress , based on both time- and frequency-domain features of HRV. Validated through a publicly available dataset, SWELL–KW, the achieved accuracy score of our model has reached 99.9% ( Precision=1, Recall=1, F1-score=1, and MCC=0.99 ), thus outperforming the existing methods in the literature. In addition, this study demonstrates the effectiveness of essential HRV features for stress detection using a feature extraction technique, i.e., analysis of variance.