检索结果-内蒙古大学图书馆

WirelessLLM: Empowering Large Language Models Towards Wireless Intelligence

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Shao, Jiawei Tong, Jingwen Wu, Qiong Guo, Wei Li, Zijian Lin, Zehong Zhang, Jun The Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong

The rapid evolution of wireless technologies and the growing complexity of network infrastructures necessitate a paradigm shift in how communication networks are designed, configured, and managed. Recent advancements in Large Language Models (LLMs) have sparked interest in their potential to revolutionize wireless communication systems. However, existing studies on LLMs for wireless systems are limited to a direct application for telecom language understanding. To empower LLMs with knowledge and expertise in the wireless domain, this paper proposes WirelessLLM, a comprehensive framework for adapting and enhancing LLMs to address the unique challenges and requirements of wireless communication networks. We first identify three foundational principles that underpin WirelessLLM: knowledge alignment, knowledge fusion, and knowledge evolution. Then, we investigate the enabling technologies to build WirelessLLM, including prompt engineering, retrieval augmented generation, tool usage, multi-modal pre-training, and domain-specific fine-tuning. Moreover, we present three case studies to demonstrate the practical applicability and benefits of WirelessLLM for solving typical problems in wireless networks. Finally, we conclude this paper by highlighting key challenges and outlining potential avenues for future research. Copyright © 2024, The Authors. All rights reserved.

关键词： Wireless networks

Toward Real-Time Edge AI: Model-Agnostic Task-Oriented Communication with Visual Feature Alignment

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xie, Songjie He, Hengtao Song, Shenghui Zhang, Jun Letaief, Khaled B. Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong

Task-oriented communication presents a promising approach to improve the communication efficiency of edge inference systems by optimizing learning-based modules to extract and transmit relevant task information. However, real-time applications face practical challenges, such as incomplete coverage and potential malfunctions of edge servers. This situation necessitates cross-model communication between different inference systems, enabling edge devices from one service provider to collaborate effectively with edge servers from another. Independent optimization of diverse edge systems often leads to incoherent feature spaces, which hinders the cross-model inference for existing task-oriented communication. To facilitate and achieve effective cross-model task-oriented communication, this study introduces a novel framework that utilizes shared anchor data across diverse systems. This approach addresses the challenge of feature alignment in both server-based and on-device scenarios. In particular, by leveraging the linear invariance of visual features, we propose efficient server-based feature alignment techniques to estimate linear transformations using encoded anchor data features. For on-device alignment, we exploit the angle-preserving nature of visual features and propose to encode relative representations with anchor data to streamline cross-model communication without additional alignment procedures during the inference. The experimental results on computer vision benchmarks demonstrate the superior performance of the proposed feature alignment approaches in cross-model task-oriented communications. The runtime and computation overhead analysis further confirm the effectiveness of the proposed feature alignment approaches in real-time applications. Copyright © 2024, The Authors. All rights reserved.

关键词： Linear transformations

Brain-computer Interface System Based on Common Spatial Patterns for Inner Speech Recognition from Electroencephalography Signal by Using a Convolutional Neural Networks

学校读者我要写书评

暂无评论

Brain-Computer Interface System Based on Common Spatial Patt...

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Abdalla, Hussna Elnoor M. Al-Haddad, Syed Abdul Rahman Basri, Hamidon Bin Aris, Ishak Bin Yusofv, Abdul Hanif Khan Bin Neyaz, Hisham University Putra Malaysia Malaysia & Sudan International University Sudan University Putra Malaysia Department of Computer and Communication System Engineering Malaysia University Putra Malaysia Faculty of Medicine and Health Sciences Department of Medicine Malaysia University Putra Malaysia Department of Electrical and Electronic Engineering Malaysia University Putra Faculty of Medicine and Health Sciences Department of Medicine Malaysia

ISBN: (纸本)9781665410205

Inner speech recognition is a modern advancement in Brain computer interfaces (BCI) that facilitates a communication between the computer and the brain in a direct way. It is particularly beneficial for individuals who face communication issues due to speech disability. In this research, an end-to-end brain-computer interface system was developed that uses Electroencephalography (EEG) signals to recognize inner speech straight from the brain. The study utilized an open-access dataset presented on four Spanish words from ten participants. The proposed system involved preprocessing to clean and enhance the signal. Common Spatial Pattern (CSP) was utilized to extract features to improve the discrimination between the selected four words. A Convolutional Neural Networks (CNNs) deep learning model was used to enhance the inner speech recognition performance from spatial features. The result shows that the model can decode the inner speech with an average accuracy of 81.40% for the un-seeing dataset and 89.80% for the entire dataset, indicating that the proposed method outperforms previous works that used the same dataset. © 2024 IEEE.

关键词： Convolutional neural networks

Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Xinran Liu, Zifan Chen, Shibo Zhang, Jun Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong

In multi-agent reinforcement learning (MARL), effective exploration is critical, especially in sparse reward environments. Although introducing global intrinsic rewards can foster exploration in such settings, it often complicates credit assignment among agents. To address this difficulty, we propose Individual Contributions as intrinsic Exploration Scaffolds (ICES), a novel approach to motivate exploration by assessing each agent’s contribution from a global view. In particular, ICES constructs exploration scaffolds with Bayesian surprise, leveraging global transition information during centralized training. These scaffolds, used only in training, help to guide individual agents towards actions that significantly impact the global latent state transitions. Additionally, ICES separates exploration policies from exploitation policies, enabling the former to utilize privileged global information during training. Extensive experiments on cooperative benchmark tasks with sparse rewards, including Google Research Football (GRF) and StarCraft Multi-agent Challenge (SMAC), demonstrate that ICES exhibits superior exploration capabilities compared with baselines. The code is publicly available at https://***/LXXXXR/ICES. Copyright © 2024, The Authors. All rights reserved.

关键词： Scaffolds

NuRF: Nudging the Particle Filter in Radiance Fields for Robot Visual Localization

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Meng, Wugang Wu, Tianfu Yin, Huan Zhang, Fumin The Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong

Can we localize a robot in radiance fields only using monocular vision? This study presents NuRF, a nudged particle filter framework for 6-DoF robot visual localization in radiance fields. NuRF sets anchors in SE(3) to leverage visual place recognition, which provides image comparisons to guide the sampling process. This guidance could improve the convergence and robustness of particle filters for robot localization. Additionally, an adaptive scheme is designed to enhance the performance of NuRF, thus enabling both global visual localization and local pose tracking. Real-world experiments are conducted with comprehensive tests to demonstrate the effectiveness of NuRF. The results showcase the advantages of NuRF in terms of accuracy and efficiency, including comparisons with alternative approaches. Furthermore, we report our findings for future studies and advancements in robot navigation in radiance fields. Copyright © 2024, The Authors. All rights reserved.

关键词： Monte Carlo methods

Evaluation of UE Registration Performance in Open-Source 5G Core Networks

学校读者我要写书评

暂无评论

Evaluation of UE Registration Performance in Open-Source 5G ...

IEEE VTS Asia Pacific Wireless Communications Symposium (APWCS)

作者： Peng-Yu Chen Chin-Ya Huang Department of Electronic and Computer Engineering National Taiwan University of Science and Technology Taipei Taiwan

ISBN: (数字)9798350361704

ISBN: (纸本)9798350361711

The rapid advancement of communication technologies has led to the emergence of the 5th Generation (5G) mobile networks. The 5G system architecture adopts software-defined networking and network function virtualization, enabling a flexible and scalable 5G Core Network (CN). However, with the increasing demand for connections, challenges arise in both scalability and efficiency. To study the relevant implementations, we conduct experiments about User Equipment (UE) registrations on 2 scenarios using 3 open-source 5G CNs, free5GC, Open5GS, and OpenAirInterface (OAI). The first scenario investigates the impact of UE registration with 3 scales on the 5G CN. The second focuses on the impact of many duplicate UE registration requests on the Access and Mobility Management Function (AMF). Our findings empower the enhancement of 5G CN implementations.

关键词： Wireless communication 5G mobile communication Scalability Systems architecture computer crashes Communications technology Network function virtualization

FedAQ: Communication-Efficient Federated Edge Learning via Joint Uplink and Downlink Adaptive Quantization

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Qu, Linping Song, Shenghui Tsui, Chi-Ying The Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong

Federated learning (FL) is a powerful machine learning paradigm which leverages the data as well as the computational resources of clients, while protecting clients’ data privacy. However, the substantial model size and frequent aggregation between the server and clients result in significant communication overhead, making it challenging to deploy FL in resource-limited wireless networks. In this work, we aim to mitigate the communication overhead by using quantization. Previous research on quantization has primarily focused on the uplink communication, employing either fixed-bit quantization or adaptive quantization methods. In this work, we introduce a holistic approach by joint uplink and downlink adaptive quantization to reduce the communication overhead. In particular, we optimize the learning convergence by determining the optimal uplink and downlink quantization bit-length, with a communication energy constraint. Theoretical analysis shows that the optimal quantization levels depend on the range of model gradients or weights. Based on this insight, we propose a decreasing-trend quantization for the uplink and an increasing-trend quantization for the downlink, which aligns with the change of the model parameters during the training process. Experimental results show that, the proposed joint uplink and downlink adaptive quantization strategy can save up to 66.7% energy compared with the existing schemes. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

FPGA-based Acceleration of Neural Network for Image Classification using Vitis AI

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Zhengdong Hong, Frederick Ziyang Yue, C. Patrick Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong

In recent years, Convolutional Neural Networks (CNNs) have been widely adopted in computer vision. Complex CNN architecture running on CPU or GPU has either insufficient throughput or prohibitive power consumption. Hence, there is a need to have dedicated hardware to accelerate the computation workload to solve these limitations. In this paper, we accelerate a CNN for image classification with the CIFAR-10 dataset using Vitis-AI on Xilinx Zynq UltraScale+ MPSoC ZCU104 FPGA evaluation board. The work achieves 3.33-5.82x higher throughput and 3.39-6.30x higher energy efficiency than CPU and GPU baselines. It shows the potential to extract 2D features for downstream tasks, such as depth estimation and 3D reconstruction. © 2024, CC BY-NC-SA.

关键词： Convolutional neural networks

Integrating Multimodal Contrastive Learning and Cross-Modal Attention for Alzheimer's Disease Prediction in Brain Imaging Genetics

学校读者我要写书评

暂无评论

Integrating Multimodal Contrastive Learning and Cross-Modal ...

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Zhou, Rong Zhou, Houliang Shen, Li Chen, Brian Y. Zhang, Yu He, Lifang Lehigh University Department of Computer Science and Engineering BethlehemPA United States University of Pennsylvania Department of Biostatistics Epidemiology and Informatics PhiladelphiaPA United States Lehigh University Department of Bioengineering BethlehemPA United States

ISBN: (纸本)9798350337488

High annotation costs serve as a significant hurdle in deploying modern deep learning architectures for clinically relevant medical applications, especially when dealing with the inherent heterogeneity of multimodal data, proving the critical need for innovative algorithms that can effectively utilize unlabeled data. In this paper, we propose a model named MCLCA, which integrates multimodal contrastive learning and cross-modal attention to diagnose Alzheimer's Disease (AD) and identify biomarkers using both labeled and unlabeled multimodal brain imaging genetics data. Through multimodal contrastive learning, MCLCA can effectively learn representations even in the absence of sufficient labels. By utilizing cross-modal attention blocks, the model captures deep connections between different modalities, providing a more comprehensive view of diagnosis. Our proposed MCLCA model is evaluated using the ADNI database with three imaging modalities (VBM-MRI, FDG-PET, and AV45-PET) and genetic SNP data. The results demonstrate that MCLCA can identify important biomarkers with better prediction accuracy compared to the existing methods. The source code is available at https://***/MCLCA. © 2023 IEEE.

关键词： Alzheimer's disease Brain imaging genetics contrastive learning cross-modal attention