检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Yang, Guang Zhou, Yanlin Chen, Xiang Yu, Chi School of Information Science and Technology Nantong University China Ministry of Industry and Information Technology China The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions Wuyi University China

Pseudo-code written by natural language is helpful for novice developers’ program comprehension. However, writing such pseudo-code is time-consuming and laborious. Motivated by the research advancements of sequence-to-sequence learning and code semantic learning, we propose a novel deep pseudo-code generation method DeepPseudo via code feature extraction and Transformer. In particular, DeepPseudo utilizes a Transformer encoder to perform encoding for source code and then use a code feature extractor to learn the knowledge of local features. Finally, it uses a pseudo-code generator to perform decoding, which can generate the corresponding pseudo-code. We choose two corpora (i.e., Django and SPoC) from real-world large-scale projects as our empirical subjects. We first compare DeepPseudo with seven state-of-the-art baselines from pseudo-code generation and neural machine translation domains in terms of four performance measures. Results show the competitiveness of DeepPseudo. Moreover, we also analyze the rationality of the component settings in DeepPseudo. Copyright © 2021, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

PROM: A persistent routing optimization method based on supervised learning

引用

Journal of network and Computer Applications 2025年

作者： Yingya Guo Zebo Huang Mingjie Ding Bin Lin Huan Luo College of Computer and Data Science Fuzhou University China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University China Engineering Research Center of Big Data Intelligence Ministry of Education China

Traditional Traffic Engineering (TE) typically improves network performance by formulating and solving routing optimization problems based on measured or predicted Traffic Matrices (TMs). However, since network traffic is dynamic, routing strategies optimized for the current measured TMs may not be suitable for future traffic patterns. To adapt to dynamic traffic, one possible solution is to perform more frequent routing updates, but this may lead to service disruptions. Another approach is the two-step method of prediction followed by optimization, which could lead to degraded performance of routing strategies due to inaccuracies in traffic prediction. Additionally, existing approaches focus solely on either distributed or centralized networks, lacking flexibility to adapt to different network architectures. To address these challenges, we propose PROM, a Machine Learning (ML)-based routing optimization model that directly predicts an effective routing strategy in an end-to-end manner based on historical traffic. This routing strategy is applicable across multiple future TMs, thereby reducing the need for frequent routing updates. Furthermore, PROM can be easily extended from a centralized implementation to a distributed one, adapting to different network architectures. To enhance model performance, we have also designed a custom loss function for routing optimization scenarios to avoid overfitting. Extensive simulation results demonstrate that PROM can predict high-quality routing strategies in future unknown traffic scenarios and is adaptable to both centralized and distributed network architectures.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DRLO: Optimizing edge server placement in dynamic MEC scenarios using deep reinforcement learning

引用

Computer networks 2025年 268卷

作者： Yingya Guo Cen Chen College of Computer and Data Science Fuzhou University PR China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University PR China Engineering Research Center of Big Data Intelligence Ministry of Education Fujian PR China

As an emerging computing paradigm, Mobile Edge computing (MEC) significantly enhances user experience and alleviates network congestion by strategically deploying edge servers in close proximity to mobile users. However, the effectiveness of MEC hinges on the precise placement of these edge servers, a critical factor in determining the Quality of Experience (QoE) for mobile users. While existing studies predominantly focus on optimizing edge server placement in static scenarios, they often fall short when faced with user mobility, resulting in a degradation of QoE. To address this challenge, we propose an adaptive edge server placement approach that leverages Deep Reinforcement Learning (DRL) to select the base stations for placing edge servers in a dynamic MEC environment. Our objective is to minimize access delay by optimizing edge server placement for adapting to dynamic environment. To tackle the vast action space associated with edge server placement, we introduce a novel activation function in the actor neural network for efficient exploration. Furthermore, to enhance the adaptability of the derived edge server placement strategy, we meticulously design a new reward function, which takes into account the minimization of total access delay within dynamic MEC scenarios. Finally, to validate the effectiveness of our proposed method, extensive experiments were conducted using the Shanghai Telecom dataset. The results demonstrate that our approach outperforms baseline methods in minimizing access delay for users in dynamic MEC scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mobile Crowd-Sensing System Based on Participant Selection 15th

Mobile Crowd-Sensing System Based on Participant Selection

引用

15th International Conference on Green, Pervasive, and Cloud computing, GPC 2020

作者： Tu, Chunyu Han, Lei Wang, Leye Yu, Zhiyong College of Mathematics and Computer Science Fuzhou University Fuzhou China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fuzhou China Key Lab of High Confidence Software Technologies Peking University Beijing China

ISBN: (纸本)9783030642426

Mobile Crowdsensing (MCS) is often accompanied by various adverse objectives when performing data collection, which makes it difficult to collect accurate data of the entire target area with low cost. Therefore, how to collect a small part of the data to accurately infer the other data of the entire target area is a crucial issue. People’s daily trajectories usually follow a certain pattern, for example, students go to school, company employees go to work. This pattern allows us to find participants who often pass through fixed areas within a certain time span, leading their collected partial data are near optimal for the entire data collection task. This paper models the problem and develops multiple methods to improve the participant selection and the data recovery. Particularly, we use a random method, reinforcement learning, and greedy algorithm to handle this problem and compare the differences among these methods by experiments. © 2020, Springer Nature Switzerland AG.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Abnormal network Traffic Detection based on Leaf Node Density Ratio 2019

Abnormal Network Traffic Detection based on Leaf Node Densit...

引用

Proceedings of the 2019 the 9th International Conference on Communication and network Security

作者： Huajun Liu Zhanghui Liu Yanhua Liu Xiaoling Gao College of Mathematics and Computer Science Fuzhou University Fuzhou Fujian China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou Fujian China College of Mathematics and Computer Science Fuzhou University Fuzhou Fujian China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou Fujian China

ISBN: (纸本)9781450376624

As the network evolves, cyber-attacks become more and more diverse. In the process of detecting network traffic, the most complicated but also the most important task is to find unknown abnormal network traffic data in time. In the existing abnormal network traffic detection method based on Extended Isolation Forest, there are limitations such as unbalanced detection accuracy and insufficient generalization ability. An improved abnormal network traffic detection method EIF-LNDR is proposed for the above problems. Based on the leaf node density ratio, the anomaly score of the instance can be calculated differently for each iTree. The experiments show that EIF-LNDR has significant improvement in precision, false negative rate, and detector efficiency compared with Extended Isolation Forest and LOF methods.

关键词： leaf node density ratio extended Isolation Forest network traffic data mining cyber attack Abnormal detection

来源：评论

学校读者我要写书评

暂无评论

Self-adaptive resource allocation for cloud-based software services based on progressive QoS prediction model

引用

Science China(information Sciences) 2019年第11期62卷 192-194页

作者： Xing CHEN Junxin LIN Yun MA Bing LIN Haijiang WANG Gang HUANG College of Mathematics and Computer Science Fuzhou University Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University School of Software Tsinghua University College of Physics and Energy Fujian Normal University Key Laboratory of High Confidence Software Technologies Ministry of Education

Dear editor,Self-adaptation is a promising approach to allocate resources for cloud-based software services [1, 2].Traditional self-adaptive resource-allocation methods are rule-driven, which leads to high administrat... 详细信息

关键词： service Self-adaptive resource allocation for cloud-based software services based on progressive QoS prediction model

来源：评论

学校读者我要写书评

暂无评论

Energy Consumption and Time Delay optimization of MEC Based on MultiDimensional Game 5

Energy Consumption and Time Delay optimization of MEC Based ...

引用

5th IEEE International Conference on Cloud computing and Big Data Analytics, ICCCBDA 2020

作者： Wang, Hui Wang, Yi Lu, Xingjun Hu, Yanjun Anhui University Key Laboratory of Intelligent Computing Signal Processing Ministry of Education Hefei230601 China Key Laboratory of Wireless Sensor Network & Communication Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Shanghai200050 China

ISBN: (纸本)9781728160245

Mobile edge computing (MEC) reduces latency and power consumption of mobile devices by deploying servers on the network edge. Due to the limited computing resources of the MEC server, excessive offloading of the users in local cells will bring unexpected queuing delay and high energy consumption. To deal with these problems, this paper proposes a Multi-user Queue Offloading multi-dimensional game algorithm (MQO). By the algorithm, users could choose the most suitable strategy, in which the strategy space is two-dimensional to satisfy different needs of different users to a certain extent, including the offload strategy and power control of users. Simulation results show that MQO can improve the performance of both overhead and offloading number with the increase of users. © 2020 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Cell-Free Massive MIMO-OFDM for High-Speed Train Communications

arXiv

引用

arXiv 2022年

作者： Zheng, Jiakang Zhang, Jiayi Björnson, Emil Li, Zhetao Ai, Bo The School of Electronic and Information Engineering Beijing Jiaotong University Beijing100044 China The Department of Computer Science KTH Royal Institute of Technology Kista Sweden The Hunan International Scientific and Technological Cooperation Base of Intelligent Network Key Laboratory of Intelligent Computing & Information Processing Ministry of Education Xiangtan University Hunan411105 China The State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing100044 China

Cell-free (CF) massive multiple-input multiple-output (MIMO) systems show great potentials in low-mobility scenarios, due to cell boundary disappearance and strong macro diversity. However, the great Doppler frequency offset (DFO) leads to serious inter-carrier interference in orthogonal frequency division multiplexing (OFDM) technology, which makes it difficult to provide high-quality transmissions for both high-speed train (HST) operation control systems and passengers. In this paper, we focus on the performance of CF massive MIMO-OFDM systems with both fully centralized and local minimum mean square error (MMSE) combining in HST communications. Considering the local maximum ratio (MR) combining, the large-scale fading decoding (LSFD) cooperation and the practical effect of DFO on system performance, exact closed-form expressions for uplink spectral efficiency (SE) expressions are derived. We observe that cooperative MMSE combining achieves better SE performance than uncooperative MR combining. In addition, HST communications with small cell and cellular massive MIMO-OFDM systems are compared in terms of SE. Numerical results reveal that the CF massive MIMO-OFDM system achieves a larger and more uniform SE than the other systems. Finally, the train antenna centric (TA-centric) CF massive MIMO-OFDM system is designed for practical implementation in HST communications, and three power control schemes are adopted to optimize the propagation of TAs for reducing the impact of the DFO. Copyright © 2022, The Authors. All rights reserved.

关键词： MIMO systems

来源：评论

学校读者我要写书评

暂无评论

Research on Data Augmentation for Garbage Classification with Target Detection Algorithm

Research on Data Augmentation for Garbage Classification wit...

引用

International Applied Computational Electromagnetics Society Symposium (ACES)

作者： Jiansong Chen Shikai Zuo Yun Lin Kai Tang Jianhang Zou Naixing Feng Yijun Cai Smart Sensing Integrated Circuit Engineering Research Center of Universities in Fujian Province Xiamen University of Technology Xiamen China Xiamen Wish Information Technology Co. Ltd Xiamen China Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China

Garbage classification is an essential work in daily life. With the development of artificial intelligence (AI), we have begun to use object detection to achieve garbage classification. However, the stacking and occlusion of garbage often make the detection performance unsatisfactory. In this paper, YOLOv5 algorithm is used for garbage detection and classification. YOLOv5 has three detection heads, which can detect objects at multiple scales. At the same time, Mosaic and Coarse Dropout image augmentation techniques are used to process our private data set of garbage, which improves the diversity of images. In this way, the target classification accuracy of the detection model can reach 75.7%, which is significantly improved compared with 69.9% without data augmentation. This paper provides a new technical support for the scene classification of stacked garbage based on deep learning.

关键词： Training Deep learning Head Stacking Object detection Computational electromagnetics Data models

来源：评论

学校读者我要写书评

暂无评论

Fine-grained Pseudo-code Generation Method via Code Feature Extraction and Transformer

Fine-grained Pseudo-code Generation Method via Code Feature ...

引用

Asia-Pacific Conference on Software Engineering

作者： Guang Yang Yanlin Zhou Xiang Chen Chi Yu School of Information Science and Technology Nantong University China Key Laboratory of Safety-Critical Software Nanjing University of Aeronautics and Astronautics Ministry of Industry and Information Technology China The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions Wuyi University China

ISBN: (纸本)9781665437851

Pseudo-code written by natural language is helpful for novice developers' program comprehension. However, writing such pseudo-code is time-consuming and laborious. Motivated by the research advancements of sequence-to-sequence learning and code semantic learning, we propose a novel deep pseudo-code generation method DeepPseudo via code feature extraction and Transformer. In particular, DeepPseudo utilizes a Transformer encoder to perform encoding for source code and then use a code feature extractor to learn the knowledge of local features. Finally, it uses a pseudo-code generator to perform decoding, which can generate the corresponding pseudo-code. We choose two corpora (i.e., Django and SPoC) from real-world large-scale projects as our empirical subjects. We first compare DeepPseudo with seven state-of-the-art baselines from pseudo-code generation and neural machine translation domains in terms of four performance measures. Results show the competitiveness of DeepPseudo. Moreover, we also analyze the rationality of the component settings in DeepPseudo.

关键词： Codes Semantics Natural languages Writing Feature extraction Transformers Generators

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：