检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Computational Electromagnetics, ICCEM 2024

作者： Dai, Jinpeng Xie, Guoda Hou, Guilin Zhang, Liyuan Huang, Zhixiang Anhui University The Key Laboratory of Intelligent Computing and Signal Processing Hefei China Education of Anhui Province Anhui Province Key Laboratory of Target Recognition and Feature Extraction Anhui Luan237000 China Ministry of Education The Key Laboratory of Intelligent Computing and Signal Processing Hefei China Institute of Energy Hefei Comprehensive National Science Center Hefei230031 China Institute of Plasma Physics Hefei Institutes of Physical Science Chinese Academy of Sciences Hefei230031 China Anhui Province Anhui University Key Laboratory of Electromagnetic Environmental Sensing Hefei230601 China Anhui University Hefei China

ISBN: (纸本)9798350383317

This article introduces an innovative and efficient deep learning-assisted Finite-Difference Time-Domain (DL-FDTD) method in the field of computational electromagnetics. This method ingeniously integrates the Gated Recurrent Unit (GRU) network and Particle Swarm Optimization (PSO) algorithm into the traditional FDTD framework, termed as the PSO-GRU-FDTD model. A key innovation of this model is the application of the particle swarm algorithm, which significantly simplifies the parameter tuning process, thereby accelerating model development. This advancement represents a notable breakthrough from the complex parameter adjustment process typical in traditional neural network models. Moreover, compared to the traditional Long Short-Term Memory (LSTM) networks, the GRU network excels in simplicity, convenience, and efficiency, while also ensuring accuracy. Ultimately, this method is applied to three-dimensional electromagnetic simulation and emulation. Numerical results demonstrate that this approach exhibits outstanding performance in both simulation accuracy and efficiency. © 2024 IEEE.

关键词： Electromagnetic simulation

来源：评论

学校读者我要写书评

暂无评论

DOA Estimation for RIS Assisted Multi-User Wireless Communication System with Squared-Sine Error Criterion and Lawson Norm Constraint 6

DOA Estimation for RIS Assisted Multi-User Wireless Communic...

引用

6th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2023

作者： Yu, Canping Li, Li Li, Yingsong Sun, Dazhi Li, Liping Huang, Zhixiang Loh, Tian Hong Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China Beijing101399 China National Physical Laboratory Electromagnetic and Eletrochemical Technologies Department Middlesex Teddington United Kingdom

ISBN: (纸本)9798350399059

Reconfigurable intelligent surface (RIS) can control the phase of reflected signals, and has become a hotspot in the field of wireless communication. In this paper, we propose a direction-of-arrival (DOA) estimation algorithm for RIS assisted multi-user wireless communication systems with squared-sine error criterion and Lawson norm constraint. This algorithm utilizes the sparsity of the signal and can achieve fast and accurate DOA estimation under the interference of impulsive noises. To suppress the line-of-sight (LOS) interference and thus to maximize the received signal-to-interference-plus-noise ratio (SINR), we also propose a random optimal phase selection (ROPS) technique to design the control matrix of RIS elements. The simulation results show that the proposed algorithm performs better than the existing methods. © 2023 IEEE.

关键词： Impulse noise

来源：评论

学校读者我要写书评

暂无评论

DragEntity:Trajectory Guided Video Generation using Entity and Positional Relationships 24

DragEntity:Trajectory Guided Video Generation using Entity a...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Wan, Zhang Tang, Sheng Wei, Jiawei Zhang, Ruize Cao, Juan Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Zhengzhou University Zhengzhou China Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China

ISBN: (纸本)9798400706868

In recent years, diffusion models have achieved tremendous success in the field of video generation, with controllable video generation receiving significant attention. However, existing control methods still face two limitations: Firstly, control conditions (such as depth maps, 3D Mesh) are difficult for ordinary users to obtain directly. Secondly, it's challenging to drive multiple objects through complex motions with multiple trajectories simultaneously. In this paper, we introduce DragEntity, a video generation model that utilizes entity representation for controlling the motion of multiple objects. Compared to previous methods, DragEntity offers two main advantages: 1) Our method is more user-friendly for interaction because it allows users to drag entities within the image rather than individual pixels. 2) We use entity representation to represent any object in the image, and multiple objects can maintain relative spatial relationships. Therefore, we allow multiple trajectories to control multiple objects in the image with different levels of complexity simultaneously. Our experiments validate the effectiveness of DragEntity, demonstrating its excellent performance in fine-grained control in video generation. © 2024 ACM.

关键词： controllable video generation

来源：评论

学校读者我要写书评

暂无评论

A Relay Buffer Prediction Method Based on LSTM in Terminal Cooperative Communication 23

A Relay Buffer Prediction Method Based on LSTM in Terminal C...

引用

23rd IEEE International Conference on Communication Technology, ICCT 2023

作者： Fei, Jie Zhi, Hui Tie, Kui Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei China School of Electronic and Information Engineering Anhui University Hefei China CO. Ltd Bengbu China

ISBN: (纸本)9798350325959

In terminal cooperative communication, relay assisted communication with buffer has significant advantages in improving system throughput, signal-to-noise ratio, and reducing system outage probability. The existing relay methods with buffer are all fixed buffer method with a fixed size of the buffer and only considering relay wholehearted cooperation and forwarding, that is, all buffer of the relay assists communication. However, when the forwarding task is small and there is a large idle in forwarding buffer, the buffer area cannot be fully utilized. When the forwarding task is large and forwarding buffer is busy, packet loss may occur in the forwarding task. In order to improve the usage efficiency of relay buffer and reduce packet loss, this paper proposes a relay buffer prediction method based on the long short-term memory network to predict the amount of data that the relay needs to forward. According to the prediction, the size of the relay buffer is divided, so that the buffer can be dynamically adjusted on demand. Simulation results show that, compared with the fixed buffer method, the relay buffer prediction method has a better buffer usage efficiency and a lower packet loss rate. © 2023 IEEE.

关键词： Buffer Forecast LSTM Relay

来源：评论

学校读者我要写书评

暂无评论

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration 38

Speculative Decoding with CTC-based Draft Model for LLM Infe...

引用

38th Conference on Neural Information processing Systems, NeurIPS 2024

作者： Wen, Zhuofan Gui, Shangtong Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences China Key Laboratory of Al Safety Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China

Inference acceleration of large language models (LLMs) has been put forward in many application scenarios and speculative decoding has shown its advantage in addressing inference acceleration. Speculative decoding usually introduces a draft model to assist the base LLM where the draft model produces drafts and the base LLM verifies the draft for acceptance or rejection. In this framework, the final inference speed is decided by the decoding speed of the draft model and the acceptance rate of the draft provided by the draft model. Currently the widely used draft models usually generate draft tokens for the next several positions in a non-autoregressive way without considering the correlations between draft tokens. Therefore, it has a high decoding speed but an unsatisfactory acceptance rate. In this paper, we focus on how to improve the performance of the draft model and aim to accelerate inference via a high acceptance rate. To this end, we propose a CTC-based draft model which strengthens the correlations between draft tokens during the draft phase, thereby generating higher-quality draft candidate sequences. Experiment results show that compared to strong baselines, the proposed method can achieve a higher acceptance rate and hence a faster inference speed. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cross Deployment of Active and Passive Reconfigurable intelligent Surfaces (RISs) for Next-Generation Communications 5

Cross Deployment of Active and Passive Reconfigurable Intell...

引用

5th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2022

作者： Chen, Luqi Chung, Kwok L. Lai, Guoming Yao, Junhao Zou, Xiaopeng Cheng, Xin Zheng, Kangtai Li, Yingsong School of Computer Science and Engineering Huizhou University China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China

ISBN: (数字)9781665472111

ISBN: (纸本)9781665472111

In recent years, reconfigurable intelligent surface (RIS) technologies have been proposed due to its ability in shaping propagation environment for future 6G network development. Existing RIS technologies mainly include the active reconfigurable intelligent surface (ARIS) and the passive reconfigurable intelligent surface (PRIS). In this paper, according to the characteristics of RIS and demands of lower costs, we present a new strategy on the cross-deployment of ARIS and PRIS that meets the beneficial maximization in both capital cost and running cost. © 2022 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

A Distributed Proximal Consensus Algorithm for Energy Saving in Ethylene Production

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024年第3期35卷 3052-3061页

作者： Nie, Rong Du, Wenli Wang, Ting Li, Zhongmei He, Shuping East China Univ Sci & Technol Minist Educ Key Lab Smart Mfg Energy Chem Proc Shanghai 200237 Peoples R China Qingyuan Innovat Lab Quanzhou 362801 Peoples R China Anhui Univ Sch Elect Engn & Automat Minist Educ Key Lab Intelligent Comp & Signal Processing Hefei 230601 Peoples R China Chengdu Univ Sch Elect Informat & Elect Engn Chengdu 610106 Peoples R China

This article presents a distributed optimization framework in order to solve the plant-wide energy-saving problem of an ethylene plant. First, the ethylene production process is abstracted into a distributed network, and then, a new distributed consensus algorithm is proposed, which is called adaptive step-size-based distributed proximal consensus algorithm (ASS-DPCA). This algorithm can dynamically adjust the step size and automatically abandon the irrational evolutionary route while eliminating the dependence of optimization algorithms on model gradient information. Moreover, the designed algorithm is able to converge to an optimal solution for any convex cost functions and approach to a convex constraint set of agents over an undirected connected graph. Finally, the results of numerical simulation and industrial experiments show that the algorithm can reduce the total energy consumption of an ethylene plant with less computing time and assured consensus.

关键词： Production Optimization Energy consumption Consensus algorithm Upper bound Petrochemicals Linear programming Distributed optimization energy saving ethylene plant-wide optimization proximal consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

A dual-band antenna designed for 5G communication based on a self-decoupled antenna

A dual-band antenna designed for 5G communication based on a...

引用

2022 International Applied Computational Electromagnetics Society Symposium, ACES-China 2022

作者： Fang, Rongzhen Wu, Xianliang Chen, Zhipeng Dong, Mengying Hu, Yunfeng Li, Yuanyuan Anhui University Key Laboratory of Intelligent Computing and Signal Processing Hefei China Anhui University Department of Education of Anhui Province Hefei China

ISBN: (纸本)9781665452366

In this paper, a dual-band antenna for 5G communication based on an antenna design with self-decoupling properties is *** antenna is composed of a self-decoupled antenna unit vertically placed on an 30×80 mm2 ground plane and printed on 0.8 mm thick FR-4(ϵr = 4.4, tanδ = 0.02) substrate,and then added a pair of L-shaped coupling feeder structures on this *** shows that the antenna has two operating frequency bands of 3.3-4.2GHz and 4.8-5GHz, and has good transmission and isolation in the above two operating frequency ***,it also has the advantages of small size, self-decoupling,high isolation,simple structure and easy *** antenna can be used as 5G mobile phone communication antenna unit. © 2022 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

A Novel Construction of Two-Dimensional Z-Complementary Array Code Sets Based on Extended Boolean Functions

引用

IEEE Transactions on Vehicular Technology 2025年第5期74卷 7821-7834页

作者： Tian, Liying Song, Xiaoshi Li, Yubo Zhang, Haijun Northeastern University School of Computer Science and Engineering Shenyang110819 China Northeastern University Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Shenyang110189 China Yanshan University School of Information Science and Engineering Qinhuangdao066004 China Hebei Key Laboratory of Information Transmission and Signal Processing Qinhuangdao066004 China University of Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China

Two-dimensional (2-D) array sets with good 2-D correlation properties have received considerable attention in wireless communication systems. This paper focuses on 2-D Z-complementary array code sets (ZCACSs), which have ideal 2-D correlation properties within a rectangular zone around the origin. By developing a theory linking 2-D extended Boolean functions with 2-D arrays, we establish an efficient construction of 2-D ZCACSs. In contrast to previous work, the proposed construction is capable of producing 2-D ZCACSs with new flexible parameters. Constructions of three-dimensional (3-D) and higher-dimensional ZCACSs are further investigated. We remark that 2-D and higher-dimensional complete complementary codes (CCCs) can also be generated from the proposed constructions. © 1967-2012 IEEE.

关键词： Codes (symbols)

来源：评论

学校读者我要写书评

暂无评论

DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effective for LMMs 38

DeepStack: Deeply Stacking Visual Tokens is Surprisingly Sim...

引用

38th Conference on Neural Information processing Systems, NeurIPS 2024

作者： Meng, Lingchen Yang, Jianwei Tian, Rui Dai, Xiyang Wu, Zuxuan Gao, Jianfeng Jiang, Yu-Gang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China Microsoft Corporation United States

Most large multimodal models (LMMs) are implemented by feeding visual tokens as a sequence into the first layer of a large language model (LLM). The resulting architecture is simple but significantly increases computation and memory costs, as it has to handle a large number of additional tokens in its input layer. This paper presents a new architecture DeepStack for LMMs. Considering N layers in the language and vision transformer of LMMs, we stack the visual tokens into N groups and feed each group to its aligned transformer layer from bottom to top, as illustrated in Fig. 1. Surprisingly, this simple method greatly enhances the power of LMMs to model interactions among visual tokens across layers but with minimal additional cost. We apply DeepStack to both language and vision transformer in LMMs, and validate the effectiveness of DeepStack LMMs with extensive empirical results. Using the same context length, our DeepStack 7B and 13B parameters surpass their counterparts by 2.7 and 2.9 on average across 9 benchmarks, respectively. Using only one-fifth of the context length, DeepStack rivals closely to the counterparts that use the full context length. These gains are particularly pronounced on high-resolution tasks, e.g., 4.2, 11.0, and 4.0 improvements on TextVQA, DocVQA, and InfoVQA compared to LLaVA-1.5-7B, respectively. We further apply DeepStack to vision transformer layers, which brings us a similar amount of improvements, 3.8 on average compared with LLaVA-1.5-7B. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

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：