检索结果-内蒙古大学图书馆

LLM4CP:Adapting Large Language Models for Channel Prediction

Journal of Communications and Information networks 2024年第2期9卷 113-125页

作者： Boxun Liu Xuanyu Liu Shijian Gao Xiang Cheng Liuqing Yang State Key Laboratory of Advanced Optical Communication Systems and Networks School of ElectronicsPeking UniversityBeijing 100871China Internet of Things Thrust The Hong Kong University of Science and Technology(Guangzhou)Guangzhou 511400China Internet of Things Thrust and Intelligent Transportation Thrust The Hong Kong University of Science and Technology(Guangzhou)Guangzhou 511400China Department of Electronic and Computer Engineering and Department of Civil and Environmental Engineering The Hong Kong University of Science and TechnologyHong KongChina

Channel prediction is an effective approach for reducing the feedback or estimation overhead in massive multi-input multi-output (m-MIMO) systems. However, existing channel prediction methods lack precision due to model mismatch errors or network generalization issues. Large language models (LLMs) have demonstrated powerful modeling and generalization abilities, and have been successfully applied to cross-modal tasks, including the time series analysis. Leveraging the expressive power of LLMs, we propose a pre-trained LLM-empowered channel prediction(LLM4CP)method to predict the future downlink channel state information (CSI) sequence based on the historical uplink CSI sequence. We fine-tune the network while freezing most of the parameters of the pre-trained LLM for better cross-modality knowledge transfer. To bridge the gap between the channel data and the feature space of the LLM,preprocessor, embedding, and output modules are specifically tailored by taking into account unique channel characteristics. Simulations validate that the proposed method achieves state-of-the-art (SOTA) prediction performance on full-sample, few-shot, and generalization tests with low training and inference costs.

关键词： channel prediction massive multi-input multi-output(m-MIMO) large language models(LLMs) fine-tuning time-series

来源：评论

学校读者我要写书评

暂无评论

Distributed online bandit tracking for Nash equilibrium under partial-decision information setting

引用

science China(Technological sciences) 2023年第11期66卷 3129-3138页

作者： FENG ZhangCheng XU WenYing CAO JinDe YANG ShaoFu RUTKOWSKI Leszek Jiangsu Provincial Key Laboratory of Networked Collective Intelligence School of MathematicsSoutheast UniversityNanjing 211189China Frontiers Science Center for Mobile Information Communication and Security Nanjing 210096China School of Computer Science and Engineering Southeast UniversityNanjing 211189China The Systems Research Institute of the Polish Academy of Sciences Warsaw 01-447Poland AGH University of Science and Technology Krakow 30-059Poland

This paper is concerned with a Nash equilibrium(NE)tracking issue in online games with bandit feedback,where cost functions vary with time and agents only have access to the values of these functions at two points during each round.A partial-decision information setting is considered,in which agents have only access to the decisions of their *** primary objective of this paper is to develop a distributed online NE tracking algorithm that ensures sublinear growth of regret with respect to the total round T,under both the bandit feedback and partial-decision information *** utilizing a two-point estimator together with the leader-following consensus method,a new distributed online NE tracking algorithm is established with the estimated gradient and local estimated decisions based on the projection gradient-descent ***,sufficient conditions are derived to guarantee an improved upper bound of dynamic regret compared to existing bandit ***,a simulation example is presented to demonstrate the effectiveness of the proposed algorithm.

关键词： online game bandit feedback partial-decision two-point gradient estimator

来源：评论

学校读者我要写书评

暂无评论

A New Method of Image Restoration technology Based on WGAN

引用

computer Systems science & Engineering 2022年第5期41卷 689-698页

作者： Wei Fang Enming Gu Weinan Yi Weiqing Wang Victor S.Sheng School of Computer&Software Engineering Research Center of Digital ForensicsMininstry of EducationNanjing University of Information Science&TechnologyNanjing210044China Provincial Key Laboratory for Computer Information Processing Technology Soochow UniversitySuzhou215325China Texas Tech University USA

With the development of image restoration technology based on deep learning,more complex problems are being solved,especially in image semantic inpainting based on ***,image semantic inpainting techniques are becoming more ***,due to the limitations of memory,the instability of training,and the lack of sample diversity,the results of image restoration are still encountering difficult problems,such as repairing the content of glitches which cannot be well integrated with the original ***,we propose an image inpainting network based on Wasserstein generative adversarial network(WGAN)*** the corresponding technology having been adjusted and improved,we attempted to use the Adam algorithm to replace the traditional stochastic gradient descent,and another algorithm to optimize the training used in recent *** evaluated our algorithm on the ImageNet *** obtained high-quality restoration results,indicating that our algorithm improves the clarity and consistency of the image.

关键词： Image restoration WGAN DCGAN context semantic

来源：评论

学校读者我要写书评

暂无评论

Real-time Energy Dispatching Strategy for Microgrid Based on Improved SD3 Algorithm

Journal of Network Intelligence

引用

Journal of Network Intelligence 2023年第4期8卷 1338-1357页

作者： Hang, Tian-Xiao He, Wen-Wu Pei, Bo-Yu Lin, Mei-Li Li, Pei-Qiang School of Computer Science and Mathematics Fujian University of Technology Xuefu South Road Fujian Province Fuzhou City350118 China School of Computer Science and Mathematics Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Xuefu South Road Fujian Province Fuzhou City350118 China School of Electronic Electrical Engineering and Physics Fujian University of Technology Xuefu South Road Fujian Province Fuzhou City350118 China

Deep reinforcement learning algorithms has attracted attention in the field of energy management in recent years, which can effectively interact with the environment and learn relevant policies to achieve specific goals. To eliminate Q-value estimation bias, in this paper we propose a real-time energy dispatching strategy for microgrid based on SD3 algorithm, and introduce prioritized experience replay and Huber loss, to develop an improved algorithm, called SD3 with loss-adjusted prioritized experience replay (SD3-LAP). A grid-connected microgrid that includes photovoltaic system, wind turbine, micro-turbine, energy storage system and electrical load is built to simulate the environment and validate the proposed methods. The problem of real-time energy dispatching for microgrid is recast as a Markov Decision Process, which aims to minimize the operating costs under the condition that the constraints of power balance and the upper and lower limits of SOC of the energy storage system are satisfied. Experimental results show that compared with baseline models, the energy dispatching strategies provide by SD3 algorithm and SD3-LAP algorithm are more effective and robust, and the mechanism of LAP is a general purposed plug-in that can effectively improve the performance of related reinforcement learning algorithm. The daily average operating cost of SD3-LAP algorithm and SD3 algorithm are respectively 37.9% and 22.89% lower than TD3 algorithm, while the daily average operating cost of of TD3 algorithm is 21.9% lower than DQN. In addition, compared with the original algorithms, namely SD3, TD3 and DQN, the LAP mechanism reduces respectively the daily average operating cost by 19.5%, 11.7%, and 20.1%. © 2023, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Shortest Link Scheduling in Wireless networks with Oblivious Power Control

引用

China Communications 2021年第4期18卷 137-152页

作者： Chunmei Ma Jiguo Yu Baogui Huang Yu Meng School of Computer Science Qufu Normal UniversityRizhao 276826China School of Computer Science and Technology Qilu University of Technology(Shandong Academy of Sciences)Jinan 250353China Shandong Computer Science Center(National Supercomputer Center in Jinan) Jinan 250014China Shandong Provincial Key Laboratory of Computer Networks Jinan 250014China School of Computer Science&Technology Georgia State UniversityGA 30303USA

Link scheduling has always been a fundamental problem in wireless networks for its direct impacts on the performance of wireless networks such as throughput capacity,transmission delay,lifetime,*** work is mainly established under graphbased models,which are not only impractical but also incorrect due to the essentially fading characteristics of *** this paper,we study the shortest link scheduling problem under two more realistic models,namely the signal to interference plus noise ratio(SINR)model and the Rayleigh fading *** propose a centralized square-based scheduling algorithm(CSSA)with oblivious power control under the SINR model and prove its correctness under both the SINR model and the Rayleigh fading ***,we extend CSSA and propose a distributed square-based scheduling algorithm(DSSA).Note that DSSA adopts CSMA/CA so that a wireless node can compete for the wireless channel before starting its *** also show theoretical analysis and conduct extensive simulations to exhibit the correctness and efficiency of our algorithms.

关键词： link scheduling SINR Rayleigh fading wireless networks wireless communications

来源：评论

学校读者我要写书评

暂无评论

A Symbolic Rule Integration Framework with Logic Transformer for Inductive Relation Prediction 24

A Symbolic Rule Integration Framework with Logic Transformer...

引用

33rd ACM Web Conference, WWW 2024

作者： Pan, Yudai Liu, Jun Zhao, Tianzhe Zhang, Lingling Lin, Yun Dong, Jin Song School of Computer Science and Technology Xi'an Jiaotong University Shaanxi Xi'an China National Engineering Lab for Big Data Analytics Xi'an Jiaotong University Shaanxi Xi'an China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Shaanxi Xi'an China Shanghai Jiao Tong University Shanghai China National University of Singapore Singapore Singapore

ISBN: (纸本)9798400701719

Relation prediction in knowledge graphs (KGs) aims at predicting missing relations in incomplete triples, whereas the dominant paradigm by KG embeddings has a limitation to predict the relation between unseen entities. This situation is called an inductive setting, which is more common in the real-world scenario. To handle this issue, implicit symbolic rules have shown great potential in capturing the inductive capability. However, it is still challenging to obtain precise representations of logic rules from KGs. The argument variability and predicate non-commutativity in symbolic rule integration make the modeling of component symbols difficult. To this end, we propose a novel inductive relation prediction model named SymRITa with a logic transformer integrating rules. SymRITa firstly extracts the subgraph, whose embeddings are captured by a graph network. Meanwhile, symbolic rule graphs in the subgraph can be generated. Then, the symbolic rules are modeled by a proposed logic transformer. Specifically, the input format based on the subgraph-based embeddings is to focus on the argument variability in symbolic rules. In addition, a conjunction attention mechanism in the logic transformer can resolve predicate non-commutativity in the symbolic rule integration process. Finally, the subgraph-based and symbol-based embeddings obtained from the previous steps are combined for the training regime, and prediction results as well as rules explaining the reasoning process are explicitly output. Extensive experiments on twelve inductive datasets show that SymRITa achieves outstanding effectiveness compared to state-of-the-art inductive baselines. Moreover, the logic rules with corresponding confidences provide an interpretable paradigm. © 2024 ACM.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Drug-Protein Interaction Prediction by Fusion of Attention and Graph Neural Network 42

Drug-Protein Interaction Prediction by Fusion of Attention a...

引用

42nd Chinese Control Conference, CCC 2023

作者： Chen, Tianrui Tuo, Shouheng Feng, Zengyu School of Computer Science and Technology Xi'An University of Posts and Telecommunications Shaanxi Xi'an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Shaanxi Xi'an710121 China Xi'An Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi'an710121 China

ISBN: (纸本)9789887581543

The identification of drug-protein interactions (DTIs) is a critical step in drug development and repositioning. However, detecting these interactions using scientific methods presents a formidable challenge. Existing models often struggle to extract relevant information from drug-protein sequences, and they fail to consider pre-existing interactions between pairs. Here, we introduce a deep learning model, DPAG, based on attention mechanisms and graph neural networks, which overcomes these limitations. DPAG leverages information from both the drug and protein sequences, as well as the association between drug-protein pairs, to predict DTIs. We conducted multiple experiments to evaluate the performance of the model in benchmark datasets, and the results showed that DPAG achieved excellent performance in terms of AUC, AUPR, precision, and recall. Our findings suggest that DPAG holds significant potential as a promising tool for predicting DTIs in drug development and repositioning. Code is available at https://***/veresse/DPAG. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Training Data Leakage via Imperceptible Backdoor Attack

Training Data Leakage via Imperceptible Backdoor Attack

引用

2023 IEEE Symposium Series on Computational Intelligence, SSCI 2023

作者： Yang, Xiangkai Luo, Wenjian Zhou, Qi Chen, Zhijian School of Computer Science and Technology Harbin Institute of Technology Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies Guangdong Shenzhen518055 China Peng Cheng Laboratory Guangdong Shenzhen518055 China

ISBN: (纸本)9781665430654

Recently, deep neural networks (DNNs) have been widely used and proven successful in many real-world tasks. There are many third-party DNN services available for data holders who want to develop custom DNN applications for their data and tasks. To ensure data privacy, it is crucial to safeguard the data holder's training data. This paper explores a unique attack paradigm where a hostile third-party DNN model supplier subtly obtains training data from the data holder. Prior attacks which can steal training data typically use augmented datasets to memorize the information of the data that the attacker intends to steal. However, these attacks are easily identified since the augmented datasets are visually different from the original dataset and rendered ineffective. In this attack, we generate an augmented dataset by modifying a portion of the training data using the DNN-based image steganography technique. This approach creates an augmented dataset that is visually identical to the original training dataset, making it difficult for humans to detect. Through extensive experiments, we have successfully and quietly accessed the confidential training data of data holders. © 2023 IEEE.

关键词： backdoor attack data privacy Deep neural networks steganography

来源：评论

学校读者我要写书评

暂无评论

Discriminative latent semantics-preserving similarity embedding hashing for cross-modal retrieval

引用

Neural Computing and Applications 2024年第18期36卷 10655-10680页

作者： Chen, Yongfeng Tan, Junpeng Yang, Zhijing Cheng, Yongqiang Chen, Ruihan School of Information Engineering Guangdong University of Technology Guangdong Guangzhou510006 China School of Electronic and Information Engineering South China University of Technology Guangdong Guangzhou510641 China Guangdong Provincial Key Laboratory of Intellectual Property and Big Data Guangdong Guangzhou510665 China Department of Computer Science and Technology University of Hull HullHU6 7RX United Kingdom

Recently, there has been a significant increase in interest in cross-modal hashing technology. For hash code learning, most previous supervision methods use label information to create a similarity matrix in a straightforward manner. However, there are still the following challenges: (1) The asymmetric similarity matrix method only considers the similarity of labels, and the discriminant constraint in Hamming space is ignored;(2) there are optimization errors between the cross-modal semantic correlation of the Hamming space and the nonlinearity of the feature space;and (3) the cross-modal hash matrix is in a dynamic state during the optimization process, and the hash code is easily disturbed and there is bit uncertainty. To this end, we propose the Discriminative Latent Semantics-preserving Similarity Embedding Cross-modal Hashing (DLSSECH) method. Specifically, to reduce the quantization error, we introduce a non-asymmetric similarity decomposition based on orthogonal rotation bias. It can decompose the bitwise correlation of the learned hash code to capture more discriminative semantic information and compact hash code. In addition, to capture the cross-modal semantic correlation of nonlinear feature transformation and reduce quantization error, we propose the latent correlation error matrices based on orthogonal rotation decomposition. The model maintains the maximum difference in semantic dependencies between the projected data and its semantic representation. Finally, we use a sparse common hash matrix and non-asymmetric similarity decomposition factors to solve the uncertainty of the dynamic changes of the hash code. The effectiveness of DLSSECH has demonstrated through experiments on four cross-modal retrieval datasets, where it outperformed some state-of-the-art methods. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Millimeter-wave radar-based algorithm for multi-person identification 43

Millimeter-wave radar-based algorithm for multi-person ident...

引用

43rd Chinese Control Conference, CCC 2024

作者： Wei, Jingpeng Guo, Jian Chen, Ming Wang, Zheyu Sun, Suyun Nanjing University of Posts and Telecommunications School of Computer Science Nanjing210023 China Nanjing University of Posts and Telecommunications Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Nanjing210023 China

ISBN: (纸本)9789887581581

Millimeter-wave radar-based identification technology has received extensive academic attention due to its advantages of passivity and nonintrusiveness. However, current research mostly focuses on single-target vital signs identification. And research on multi-person target identification is very few. Moreover, existing algorithms are unable to accurately monitor and separate multiple human targets in a scene, resulting in a low accuracy. To address these problems, this paper proposes a multi-person identification algorithm based on vital signs. The algorithm combines the minimum variance beam forming technique, the cell average constant false alarm rate and the k-means clustering method to extract the single person vital sign signals from the multi-person target signals. Next, the algorithm designs a multiscale fusion network model to extract features from phase one-dimensional waveform signals and two-dimensional short-time Fourier transform spectrograms, and then integrates them. Finally, the purpose of identity recognition is achieved through classification. Simulation experiments show that the proposed algorithm effectively separate multi-person targets and achieve a higher recognition accuracy than that of traditional algorithms. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：