A5055773757- Advanced MIMO Systems Optimization
- Cognitive Radio Networks and Spectrum Sensing
- Advanced Wireless Communication Technologies
- Indoor and Outdoor Localization Technologies
- Advanced Wireless Network Optimization
- Caching and Content Delivery
- Wireless Communication Networks Research
- Cooperative Communication and Network Coding
- Microgrid Control and Optimization
- Smart Grid Energy Management
- Advanced biosensing and bioanalysis techniques
- UAV Applications and Optimization
- Satellite Communication Systems
- Modular Robots and Swarm Intelligence
- Opportunistic and Delay-Tolerant Networks
- Soil Moisture and Remote Sensing
- Advanced SAR Imaging Techniques
- IoT and Edge/Fog Computing
- Computational and Text Analysis Methods
- Medical Image Segmentation Techniques
- DNA and Biological Computing
- Privacy-Preserving Technologies in Data
- Metallurgy and Material Forming
- Wireless Signal Modulation Classification
- Image and Video Quality Assessment
Technology Innovation Institute
2022-2024
Xi'an University of Technology
2024
Nanjing University of Science and Technology
2024
Beijing Jiaotong University
2023
Hebei University of Science and Technology
2023
Hunan Agricultural University
2021
Nokia (France)
2021
Huawei Technologies (China)
2019
University of York
2012-2016
Recently, along with the rapid development of mobile communication technology, edge computing theory and techniques have been attracting more attentions from global researchers engineers, which can significantly bridge capacity cloud requirement devices by network edges, thus accelerate content deliveries improve quality services. In order to bring intelligence systems, compared traditional optimization methodology, driven current deep learning techniques, we propose integrate Deep...
The evolution of generative artificial intelligence (GenAI) constitutes a turning point in reshaping the future technology different aspects. Wireless networks particular, with blooming self-evolving networks, represent rich field for exploiting GenAI and reaping several benefits that can fundamentally change way how wireless are designed operated nowadays. To be specific, large models envisioned to open up new era autonomous which multi-modal trained over various Telecom data, fine-tuned...
Rapidly deployable and reliable mission-critical communication networks are fundamental requirements to guarantee the successful operations of public safety officers during disaster recovery crisis management preparedness. The ABSOLUTE project focused on designing, prototyping, demonstrating a high-capacity IP mobile data network with low latency large coverage suitable for many forms multimedia delivery including scenarios. combines aerial, terrestrial, satellites providing robust...
The convergence of generative large language models (LLMs), edge networks, and multi-agent systems represents a groundbreaking synergy that holds immense promise for future wireless generations, harnessing the power collective intelligence paving way self-governed networks where intelligent decision-making happens right at edge. This article puts stepping-stone incorporating artificial (AI) in sets scene realizing on-device LLMs, LLMs are collaboratively planning solving tasks to achieve...
In this paper, we investigate the use of a transfer learning approach applied to topology management framework in 5G heterogeneous aerial-terrestrial broadband access network, reduce energy consumption and deployment cost, improve system capacity QoS. We implement cognitive engine
This paper addresses the issue of difficulty in obtaining inter-turn fault (ITF) samples electric motors, specifically permanent magnet-synchronous motors (PMSMs), where number ITF stator windings is severely lacking compared to healthy samples. To effectively identify these faults, an improved diagnosis method based on combination a cycle-generative adversarial network (GAN) and deep autoencoder (DAE) proposed. In this method, Cycle GAN used expand collection for PMSMs, while DAE enhances...
This paper presents the concept of Win-or-Learn-Fast (WoLF) variable learning rate for distributed Q-learning based dynamic spectrum management algorithms. It demonstrates importance choosing correctly by simulating a large scale stadium temporary event network. The results show that using WoLF provides significant improvement in quality service, terms probabilities file blocking and interruption, over typical values fixed rates. have also demonstrated it is possible to provide better more...
Abstract This paper introduces and studies a novel solution of transfer learning applied to spectrum management in cognitive radio networks order improve the Quality Service (QoS) convergence performance conventional full distributed learning. Cooperation has been investigated enhance as way reducing need for control information exchange between agents while providing same effective QoS that achieved fully coordinated network. A structured approach is taken learning, including source agent...
Wireless communications at high-frequency bands with large antenna arrays face challenges in beam management, which can potentially be improved by multimodality sensing information from cameras, LiDAR, radar, and GPS. In this paper, we present a multimodal transformer deep learning framework for sensing-assisted prediction. We employ convolutional neural network to extract the features sequence of images, point clouds, radar raw data sampled over time. At each layer, use encoders learn...
In this paper, we introduce a novel paradigm of transfer learning for spectrum and topology management in rapidly deployable opportunistic network the post disaster temporary event scenarios. The architecture is designed to be changing between different phases, highly flexible during period. Transfer developed learn dynamic radio environment from topologies. This also allows previously learnt information earlier phases deployment efficiently used influence process later deployment. A...
In this paper, we investigate the use of an integrated machine learning algorithm to jointly optimize spectrum allocation, load balancing and energy saving aspects in opportunistic mobile broadband network for temporary event disaster relief scenarios. A novel k-means has been developed dynamically partition users a cell into clusters, improve interference mitigation reuse. It is with Q resource allocation transfer selection. Topology management using BS placement sleep mode operation....
Extended Reality (XR) applications introduce challenging requirements for radio mobile systems in terms of capacity and latency. At the same time, XR devices needs to minimize power consumption extend battery lifetime limit dissipated heat. Addressing latency without excessively increasing user requires evolution 5G saving schemes. In this work, we propose an Adaptive DRX (ADRX) scheme design a control policy optimally adjust active duration cycle order satisfy energy consumption. To end,...
In this paper, machine learning solutions have been investigated to improve the decision of packet duplication in a multi-connectivity cellular network optimize satisfaction delay and reliability 5G. A multi-agent deep reinforcement scheme with sequential actor-critic model has developed from observations radio environment including channel state, interference load. multi-objective reward function minimize transmission delay, error rate maximize URLLC targets. System-level simulations...
Generative artificial intelligence (GenAI) and communication networks are expected to have groundbreaking synergies in 6G. Connecting GenAI agents over a wireless network can potentially unleash the power of collective pave way for general (AGI). However, current designed as "data pipe" not suited accommodate leverage GenAI. In this paper, we propose GenAINet framework which distributed communicate knowledge (high-level concepts or abstracts) accomplish arbitrary tasks. We first provide...
Industrial applications introduce new and complex requirements in terms of reliability latency for wireless communication systems. In particular, 3GPP has recently identified the need communications being ultra reliable as well robust against consecutive packet errors. These call approaches that span multiple layers to encompass latency-reliability trade-offs compared classical error correction schemes like (Hybrid) ARQ. For this purpose, techniques puncturing, power boosting, data...
This paper investigates a weighting factor based reinforcement learning scheme with physical information channel selection policy applied on multi-hop backhaul wireless network directional antennas, for high capacity density system, in order to enhance the spectrum efficiency and Quality of Service (QoS). The interference environment has been analyzed. A novel is designed obtained from sensing process, which incorporated into scheme. It demonstrated that can efficiently partition channels...
<p>The recent progress of artificial intelligence (AI) opens up new frontiers in the possibility automating many tasks involved Telecom networks design, implementation, and deployment. This has been further pushed forward with evolution generative (AI), including emergence large language models (LLMs), which is believed to be cornerstone toward realizing self-governed, interactive AI agents. Motivated by this, this paper, we aim adapt paradigm LLMs domain. In particular, fine-tune...
<p>The recent progress of artificial intelligence (AI) opens up new frontiers in the possibility automating many tasks involved Telecom networks design, implementation, and deployment. This has been further pushed forward with evolution generative (AI), including emergence large language models (LLMs), which is believed to be cornerstone toward realizing self-governed, interactive AI agents. Motivated by this, this paper, we aim adapt paradigm LLMs domain. In particular, fine-tune...
The evolution of generative artificial intelligence (GenAI) constitutes a turning point in reshaping the future technology different aspects. Wireless networks particular, with blooming self-evolving networks, represent rich field for exploiting GenAI and reaping several benefits that can fundamentally change way how wireless are designed operated nowadays. To be specific, large models envisioned to open up new era autonomous which multi-modal trained over various Telecom data, fine-tuned...