Query：
学者姓名：刘漳辉
Refining：
Year
Type
Indexed by
Source
Complex
Co-
Language
Clean All
Abstract ：
对话状态追踪是对话系统的重要组成部分,旨在从用户与系统的对话中跟踪用户意图,其通常表示为槽位-槽值对序列.近年来,深度神经网络模型在对话状态追踪问题上取得了较大进展.然而,现有模型在槽位相关性建模方面还存在可拓展性差与易引入噪声等问题.针对上述问题,本文提出了一种知识增强与自注意力引导的图神经网络KESA-GNN(Knowledge-En-hanced &Self-Attention Guided Graph Neural Network).首先,KESA-GNN通过外部知识嵌入增强槽的语义表征提升多头自注意力机制对槽位间相关性的辨别能力.其次,为了精确建模槽位间的诸如共指、共现等相关性,提出了 一种自注意力引导的图神经网络建模槽位相关性.该网络采用多头注意力机制获得槽位间的注意力矩阵以及槽位表征,通过Max-N Relation算法获得注意力矩阵中强相关关系集,将稠密的注意力矩阵稀疏化,从而引导图神经网络中强相关槽位间的信息传播,降低无关槽位的噪声影响.最后,KESA-GNN采用门控融合机制过滤槽位多头注意力和图神经网络输出的槽位表征,从而获取更准确的槽位表征向量,进一步提升了 KESA-GNN的鲁棒性.在多域对话数据集上的实验结果表明,KESA-GNN模型的性能优于最新的基线模型.
Keyword ：
图神经网络 图神经网络 对话状态追踪 对话状态追踪 知识图谱 知识图谱 自注意力引导 自注意力引导 门控融合 门控融合
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 刘漳辉 , 林宇航 , 陈羽中 . 一种用于多域对话状态追踪的知识增强与自注意力引导的图神经网络 [J]. | 小型微型计算机系统 , 2024 , 45 (1) : 108-114 . |
| MLA | 刘漳辉 等. "一种用于多域对话状态追踪的知识增强与自注意力引导的图神经网络" . | 小型微型计算机系统 45 . 1 (2024) : 108-114 . |
| APA | 刘漳辉 , 林宇航 , 陈羽中 . 一种用于多域对话状态追踪的知识增强与自注意力引导的图神经网络 . | 小型微型计算机系统 , 2024 , 45 (1) , 108-114 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Digital microfluidic biochips (DMFBs) have a significant stride in the applications of medicine and the biochemistry in recent years. DMFBs based on micro -electrode -dot -array (MEDA) architecture, as the nextgeneration DMFBs, aim to overcome drawbacks of conventional DMFBs, such as droplet size restriction, low accuracy, and poor sensing ability. Since the potential market value of MEDA biochips is vast, it is of paramount importance to explore approaches to protect the intellectual property (IP) of MEDA biochips during the development process. In this paper, an IP authentication strategy based on the multi-PUF applied to MEDA biochips is presented, called bioMPUF, consisting of Delay PUF, Split PUF and Countermeasure. The bioMPUF strategy is designed to enhance the non -linearity between challenges and responses of PUFs, making the challenge-response pairs (CRPs) on the MEDA biochips are difficult to be anticipated, thus thwarting IP piracy attacks. Moreover, based on the easy degradation of MEDA biochip electrodes, a countermeasure is proposed to destroy the availability of piracy chips. Experimental results demonstrate the feasibility of the proposed bioMPUF strategy against the brute force attack and modeling attack.
Keyword ：
Hardware security Hardware security IP protection IP protection MEDA biochips MEDA biochips Modeling attack Modeling attack Multi-PUF Multi-PUF
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Dong, Chen , Guo, Xiaodong , Lian, Sihuang et al. Harnessing the advances of MEDA to optimize multi-PUF for enhancing IP security of biochips [J]. | JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES , 2024 , 36 (3) . |
| MLA | Dong, Chen et al. "Harnessing the advances of MEDA to optimize multi-PUF for enhancing IP security of biochips" . | JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES 36 . 3 (2024) . |
| APA | Dong, Chen , Guo, Xiaodong , Lian, Sihuang , Yao, Yinan , Chen, Zhenyi , Yang, Yang et al. Harnessing the advances of MEDA to optimize multi-PUF for enhancing IP security of biochips . | JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES , 2024 , 36 (3) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Community detection is widely used in network analysis, which seeks to divide network nodes into distinct communities based on the topology structure and attribute information of the network. Due to its interpretability, nonnegative matrix factorization becomes an essential method for community detection. However, it decomposes the adjacency matrix and attribute matrix separately, which do not tightly incorporate topology and attributes. And in the problem of division inconsistency based on topology and attributes caused by the mismatch between the topology similarity and attribute similarity of paired nodes, it ignores the difference in the matching degree of each attribute and each node. In this paper, we propose a nonnegative matrix factorization algorithm for community detection (MTACD) based on the matching degree between topology and attribute. First, we employ an attribute embedding mechanism to enhance the node-attribute relationship. Second, we design an attribute matching degree and a node topology-and-attribute matching degree in order to resolve the mismatch between topology and attribute similarity. Experiments on both real-world and synthetic networks demonstrate the effectiveness of our algorithm. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
Keyword ：
Matrix algebra Matrix algebra Matrix factorization Matrix factorization Population dynamics Population dynamics Topology Topology
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zeng, Ruolan , Liu, Zhanghui , Guo, Kun . Nonnegative Matrix Factorization Based on Topology-and-Attribute-Matching Degree for Community Detection [C] . 2024 : 137-151 . |
| MLA | Zeng, Ruolan et al. "Nonnegative Matrix Factorization Based on Topology-and-Attribute-Matching Degree for Community Detection" . (2024) : 137-151 . |
| APA | Zeng, Ruolan , Liu, Zhanghui , Guo, Kun . Nonnegative Matrix Factorization Based on Topology-and-Attribute-Matching Degree for Community Detection . (2024) : 137-151 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
方面级情感分析是情感分析的子任务，旨在判断评论目标的具体方面所对应的情感极性.近年来，深度神经网络模型在方面级情感分析问题上取得了较大进展.然而，现有的方面级情感分析模型仍存在方面信息丢失、没有充分利用句法依存关系等问题.本文提出了一种基于关系注意力机制的图卷积网络RAGCN(Relational Attention based Graph Convolutional Network).首先，RAGCN通过两个双向长短期记忆网络分别对句子和增强后的方面建模，以引导图卷积网络对向量表示进行更新.其次，为了区分上下文单词对给定方面情感的贡献，提出了一种关系注意力机制.该机制能充分利用评论节点间的边类型，结合双向长短期记忆网络的输出以捕获方面和上下文单词之间的关系.此外，为进一步提高模型的鲁棒性，RAGCN采用门控融合机制来过滤关系注意力层和图卷积网络层的输出，从而获取多更准确的句子表征向量.多个方面级情感分析数据集上的实验结果表明，RAGCN模型在准确度，Macro-F1方面均优于对比模型.
Keyword ：
关系注意力 关系注意力 图卷积网络 图卷积网络 方面级情感分析 方面级情感分析 门控融合机制 门控融合机制
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 刘漳辉 , 陈羽中 , 杨耀东 . 一种用于方面级情感分析的关系注意力图卷积网络 [J]. | 小型微型计算机系统 , 2023 , 44 (04) : 752-758 . |
| MLA | 刘漳辉 et al. "一种用于方面级情感分析的关系注意力图卷积网络" . | 小型微型计算机系统 44 . 04 (2023) : 752-758 . |
| APA | 刘漳辉 , 陈羽中 , 杨耀东 . 一种用于方面级情感分析的关系注意力图卷积网络 . | 小型微型计算机系统 , 2023 , 44 (04) , 752-758 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Marine litter can cause significant damage to marine biodiversity, threatening the marine food chain and spreading harmful substances, posing a significant impact on the ocean ecosystem. Autonomous Underwater Vehicles (AUVs) can automatically remove marine litter using sensors and trained models. this paper evaluates the YOLOv7 series of models that utilize deep learning to detect targets in a real underwater environment. In order to improve the performance of the model, we introduced two attention mechanisms, and the experimental results showed a 2.5% increase in Mean Average Precision(mAP) values. We used a large publicly available dataset of re-annotated open-water debris to train convolutional neural networks for target detection, and we evaluated the trained models on a subset of the dataset, to provide insights into the ability of deep learning to detect marine litter. In addition, to prevent attacks by malicious actors during AUVs cloud platform access, we introduced data encryption protection to ensure that the model's predicted results can be correctly received by AUVs. © 2023 ACM.
Keyword ：
Autonomous underwater vehicles Autonomous underwater vehicles Biodiversity Biodiversity Convolutional neural networks Convolutional neural networks Cryptography Cryptography Deep learning Deep learning Large datasets Large datasets Learning systems Learning systems
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wu, Qiaowen , Ke, Yaojie , Liu, Zhanghui et al. Marine litter detection based on YOLOv7 algorithm and data encryption protection [C] . 2023 : 82-87 . |
| MLA | Wu, Qiaowen et al. "Marine litter detection based on YOLOv7 algorithm and data encryption protection" . (2023) : 82-87 . |
| APA | Wu, Qiaowen , Ke, Yaojie , Liu, Zhanghui , Zhang, Yuanyuan , Wu, Qiyan . Marine litter detection based on YOLOv7 algorithm and data encryption protection . (2023) : 82-87 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Load prediction is an essential technique to improve edge system performance by proactively configuring and allocating system resources. Traditional load prediction methods obtain high prediction when handling loads exhibiting cyclical trend behavior, but they are unable to capturing highly-variable loads in edge computing environments. Existing studies fit prediction models via independent time series and output single-point real-value predictions. However, in practical edge scenarios, it is more valuable to obtain application value by utilizing the probability distribution of future loads rather than directly predicting specific values. To solve these problems, we propose an Edge Load Prediction method empowered by Deep Auto-regressive Recurrent networks (ELP-DAR). The ELP-DAR uses the time-series data of edge loads to train deep auto-regressive recurrent networks, which integrate Long Short-Term Memory (LSTM) into the S2S framework to calculate the parameters of the probability distribution at the next time-point. Therefore, the ELP-DAR can efficiently extract the essential representations of edge loads and learn their complex patterns, and the probability distribution for highly-variable edge loads can be accurately predicted. Extensive simulation experiments are conducted to validate the effectiveness of the proposed ELP-DAR method based on real-world edge load datasets. The results show that the ELP-DAR achieves higher prediction accuracy than other benchmark methods with different prediction lengths.
Keyword ：
deep auto-regression deep auto-regression Edge computing Edge computing load prediction load prediction probability distribution probability distribution recurrent neural networks recurrent neural networks
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Liu, Zhanghui , Chen, Lixian , Chen, Zheyi et al. Load Prediction in Edge Computing Using Deep Auto-Regressive Recurrent Networks [J]. | ICC 2023 - IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS , 2023 : 809-814 . |
| MLA | Liu, Zhanghui et al. "Load Prediction in Edge Computing Using Deep Auto-Regressive Recurrent Networks" . | ICC 2023 - IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (2023) : 809-814 . |
| APA | Liu, Zhanghui , Chen, Lixian , Chen, Zheyi , Huang, Yifan , Liang, Jie , Yu, Zhengxin et al. Load Prediction in Edge Computing Using Deep Auto-Regressive Recurrent Networks . | ICC 2023 - IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS , 2023 , 809-814 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Although image segmentation is widely applied in many fields owing to the assistance of better analysis and understanding of images, the models based on fully convolutional neural networks still engender the problems of resolution reconstruction and contextual information usage in semantic segmentation. Aiming at the problems, a semantic propagation and fore-background aware network for image semantic segmentation is proposed. A joint semantic propagation up-sampling module(JSPU) is proposed to obtain semantic weights by extracting the global and local semantic information from high-level features. Then the semantic information is propagated from high-level features to low-level features for alleviating the semantic gap between them. The resolution reconstruction is achieved through a hierarchical up-sampling structure. In addition, a pyramid fore-background aware module is proposed to extract foreground and background features of different scales through two parallel branches. Multi-scale fore-background aware features are captured by establishing the dependency relationships between the foreground and background features, thereby the contextual representation of foreground features is enhanced. Experiments on semantic segmentation benchmark datasets show that SPAFBA is superior in performance. © 2022, Science Press. All right reserved.
Keyword ：
Backpropagation Backpropagation Benchmarking Benchmarking Convolution Convolution Convolutional neural networks Convolutional neural networks Semantics Semantics Semantic Segmentation Semantic Segmentation Semantic Web Semantic Web Signal sampling Signal sampling
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Liu, Zhanghui , Zhan, Xiaolu , Chen, Yuzhong . Image Semantic Segmentation Network Based on Semantic Propagation and Fore-Background Aware [J]. | Pattern Recognition and Artificial Intelligence , 2022 , 35 (1) : 71-81 . |
| MLA | Liu, Zhanghui et al. "Image Semantic Segmentation Network Based on Semantic Propagation and Fore-Background Aware" . | Pattern Recognition and Artificial Intelligence 35 . 1 (2022) : 71-81 . |
| APA | Liu, Zhanghui , Zhan, Xiaolu , Chen, Yuzhong . Image Semantic Segmentation Network Based on Semantic Propagation and Fore-Background Aware . | Pattern Recognition and Artificial Intelligence , 2022 , 35 (1) , 71-81 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
虽然图像语义分割因其有助于更好地分析和理解图像而被广泛应用于多个领域,但是基于全卷积神经网络的模型在语义分割方面依然存在分辨率重构及如何利用上下文信息的问题.因此,文中提出基于语义传播与前/背景感知的图像语义分割网络.首先,提出联合语义传播上采样模块,提取高层特征的全局语义信息与局部语义信息,用于得到语义权重,将高层特征语义传播到低层特征,缩小两者之间的语义差距,再通过逐层上采样实现分辨率重构.此外,还提出金字塔前/背景感知模块,通过两个并行分支提取不同尺度前景特征与背景特征,建立前景与背景间的依赖关系,捕获多尺度的前/背景感知特征,增强前景特征的上下文表示.语义分割基准数据集上的实验表明,文...
Keyword ：
上下文信息 上下文信息 全卷积神经网络 全卷积神经网络 分辨率重构 分辨率重构 语义分割 语义分割
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 刘漳辉 , 占小路 , 陈羽中 . 基于语义传播与前/背景感知的图像语义分割网络 [J]. | 模式识别与人工智能 , 2022 , 35 (01) : 71-81 . |
| MLA | 刘漳辉 et al. "基于语义传播与前/背景感知的图像语义分割网络" . | 模式识别与人工智能 35 . 01 (2022) : 71-81 . |
| APA | 刘漳辉 , 占小路 , 陈羽中 . 基于语义传播与前/背景感知的图像语义分割网络 . | 模式识别与人工智能 , 2022 , 35 (01) , 71-81 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
无人机与移动边缘计算技术的结合突破了传统地面通信的局限性。无人机所提供的有效视距信道可大大改善边缘服务器与移动设备之间的通信质量。为了进一步提升移动边缘计算系统的服务质量，设计了一种多无人机使能的移动边缘计算系统模型。在该系统中，无人机作为边缘服务器为移动设备提供计算服务，通过联合优化无人机部署与计算卸载策略实现平均任务响应时间的最小化。基于问题定义，提出了一种PSO-GA-G双层嵌套联合优化方法，该方法的外层采用了结合遗传算法算子的离散粒子群优化算法(Discrete Particle Swarm Optimization Algorithm Combined with Genetic Al...
Keyword ：
无人机部署 无人机部署 离散粒子群优化算法 离散粒子群优化算法 移动边缘计算 移动边缘计算 计算卸载 计算卸载 贪心算法 贪心算法
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 刘漳辉 , 郑鸿强 , 张建山 et al. 多无人机使能移动边缘计算系统中的计算卸载与部署优化 [J]. | 计算机科学 , 2022 , 49 (S1) : 619-627 . |
| MLA | 刘漳辉 et al. "多无人机使能移动边缘计算系统中的计算卸载与部署优化" . | 计算机科学 49 . S1 (2022) : 619-627 . |
| APA | 刘漳辉 , 郑鸿强 , 张建山 , 陈哲毅 . 多无人机使能移动边缘计算系统中的计算卸载与部署优化 . | 计算机科学 , 2022 , 49 (S1) , 619-627 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
随着大数据和人工智能的发展,多轮对话算法受到了越来越多的关注.多轮对话回答选择是多轮对话算法中的关键问题之一,其目标是选择与输入消息和对话内容最相关的回答作为应答.近年来,深度神经网络模型在多轮对话回答选择问题上取得了较大进展.然而,如何提取对话上下文和回答中的相关语义信息并从中提取丰富的多粒度语义匹配特征仍然是多轮对话回答选择问题面临的巨大挑战.针对上述问题,本文提出了一种结合词注意力机制的多粒度循环神经网络模型MRNA(MultiGranularity Recurrent Neural Netw ork w ith Word Attention).首先,M RNA使用双通道网络,融合字符级...
Keyword ：
回答选择 回答选择 多轮对话 多轮对话 层级粒度 层级粒度 词注意力机制 词注意力机制
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 谢琪 , 陈羽中 , 刘漳辉 . 一种基于多粒度循环神经网络与词注意力的多轮对话回答选择方法 [J]. | 小型微型计算机系统 , 2021 , 42 (12) : 2553-2560 . |
| MLA | 谢琪 et al. "一种基于多粒度循环神经网络与词注意力的多轮对话回答选择方法" . | 小型微型计算机系统 42 . 12 (2021) : 2553-2560 . |
| APA | 谢琪 , 陈羽中 , 刘漳辉 . 一种基于多粒度循环神经网络与词注意力的多轮对话回答选择方法 . | 小型微型计算机系统 , 2021 , 42 (12) , 2553-2560 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
