检索结果-内蒙古大学图书馆

IEEE International Conference on Systems, Man and Cybernetics

作者： MingLe Zhou ChangLe Yi HongLin Wan Min Li Gang Li DeLong Han Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China College of Physics and Electronic Science Shandong Normal University Jinan China

The detection of defects in printed circuit boards requires high accuracy and realtime performance. Existing industrial detection models generally adopt a pure convolutional structure for ease of deployment. However, the detection accuracy of these models is often insufficient to meet the requirements of the scene. To improve the detection model accuracy and ease of deployment, this paper proposes a convolutional merging Transformer network(CMTRNet). The CMTR-Net model proposes a backbone network (CNN-Former) that uses convolutional modules to replace self-attention, combining the Transformer architecture with a convolutional structure. This approach not only avoids the drawback of self-attention high computation complexity that is detrimental to deployment but also improves the model detection accuracy. Based on CNN-Former, this paper also proposes a feature fusion module that can better fuse the features extracted by CNN-Former. Further-more, based on the CMTRNet model and the characteristics of circuit board defects, this paper proposes a loss function called Melt-IoU, which can make the initial training phase smoother and further improve detection accuracy. Experiments have shown that CMTRNet outperforms existing advanced models on both datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Scientific Workflow Engine Design and Implementation

A Scientific Workflow Engine Design and Implementation

引用

第四届公共管理与智能社会国际学术会议

作者： Zhichao Zhang Meng Guo Tingting Guo Key Laboratory of' Computing Power Network and Information Security of Ministry of Education Shandong Computer Science Center (National Supercomputing Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Inspur General Software Co.Ltd. Shandong Carbon Manager Group Co.Ltd.

This paper designs and implements a scientific workflow engine that follows the BPMN 2.0, enriching existing research on scientific workflow engine specification and theory. The engine is implemented using the Java language and adopts a layered architecture, including a process virtual machine, a BPMN model engine and a scientific workflow model engine from the bottom up, which has good scalability and is able to provide powerful support for the design and operation of scientific workflows so as to process scientific research data more efficiently.

关键词： Scientific workflow workflow workflow engine BPMN 2.0

来源：评论

学校读者我要写书评

暂无评论

Pulsar candidate recognition based on autoencoder and self-normalizing neural networks

Pulsar candidate recognition based on autoencoder and self-n...

引用

IEEE Joint International Information technology and Artificial Intelligence Conference (ITAIC)

作者： Zhihao Wang Peng Fu Meng Guo Key Laboratory of Computing Power Network and Information Security of Ministry of Education Shandong Computer Science Center (National Supercomputing Center in Jinan) (Shandong Academy of Sciences) Qilu University of Technology Jinan Shandong P. R. China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan Shandong P. R. China

The identification of pulsar candidates is a crucial step in radio astronomy research. With the continuous improvement of modern radio telescope equipment and the increasing scale of pulsar sky survey, a pulsar survey will produce a large number of pulsar candidates. Identifying pulse signals from a large number of pulsar candidates is a prerequisite for discovering new pulsar. In the face of massive pulsar candidate data, it is a huge workload to identify pulsar candidates manually only by experts in relevant fields. In order to improve the efficiency of identifying pulsar candidates, a stacked autoencoder and self-normalizing neural network based pulsar candidate recognition framework AESNN is proposed, which does not need to consider the imbalance of the number of positive and negative samples in the pulsar data set. The pulsar candidate contains many features, but not all of them are important. The stacked autoencoder is used to extract the feature representation of the data, perform unsupervised dimensionality reduction, and input these features into the self-normalizing neural network for training. AESNN introduces self-normalizing properties by introducing 'scaled exponential linear units', and experiments show that AESNN has a high F1 score, precision, and recall, and does not require the use of complex data augmentation methods, making it more advantageous compared to other algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Text Information Mining in Cyberspace: An Information Extraction Method Based on T5 and keyBERT

Text Information Mining in Cyberspace: An Information Extrac...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Kuan Liu Yumei Li Yuanhua Qi Ning Qi Mengran Zhai Information Research Institute of Shandong Academy of Sciences Qilu University of Technology (Shandong Academy of Sciences) Jinan China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Shandong Institute of Economy and Informatization Development Jinan China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China SHANDONG SCICOM Information and Economy Research Institute Co. Ltd Jinan China Shandong Institute of Economy and Informatization Development Jinan China

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

With the development of the digital economy and the advent of the big data era, the rapid growth of textual information in cyberspace has placed higher demands on information processing technology. This paper proposes an information extraction technique based on the Text-to-Text Transfer Transformer, known as T5, and keyBERT models, aiming to efficiently distill the key content from textual information in cyberspace. This method combines automatic summarization and keyword extraction to form information briefs. The experiments selected representative policy documents related to data elements as input data and employed information entropy and ROUGE scores as metrics to evaluate the automatic summarization model. The results were compared with the outputs of similar models. Experimental results indicate that the T5 model outperforms other models in terms of summarization effectiveness, and the proposed information extraction method shows significant advantages in readability and processing efficiency, demonstrating practical application value.

关键词： Measurement Biological system modeling Cyberspace Text summarization Information processing Information retrieval Transformers Data models Data mining Information entropy

来源：评论

学校读者我要写书评

暂无评论

Dynamic hybrid precoding relying on twin-resolution phase shifters in millimeter-wave communication systems

arXiv

引用

arXiv 2020年

作者： Feng, Chenghao Shen, Wenqian Gao, Xinyu An, Jianping Hanzo, Lajos School of Information and Electronics Beijing Institute of Technology Beijing100081 China Shaanxi Key Laboratory of Information Communication Network and Security Xi’an University of Posts & Telecommunications Xi’anShaanxi710121 China Huawei Technologies Co. Ltd Beijing100085 China Department of Electronics and Computer Science University of Southampton SouthamptonSO17 1BJ United Kingdom

Hybrid analog/digital precoding in millimeter-wave (mmWave) multi-input multi-ouput (MIMO) systems is capable of achieving the near-optimal full-digital performance at reduced hardware cost and power consumption compared to its full-RF digital counterpart. However, having numerous phase shifters is still costly, especially when the phase shifters are of high resolution. In this paper, we propose a novel twin-resolution phase-shifter network for mmWave MIMO systems, which reduces the power consumption of an entirely high-resolution network, whilst mitigating the severe array gain reduction of an entirely low-resolution network. The connections between the twin phase shifters having different resolutions and the antennas are either fixed or dynamically configured. In the latter, we jointly design the phase-shifter network and the hybrid precoding matrix, where the phase of each entry in the analog precoding matrix can be dynamically designed according to the required resolution. This method is slightly modified for the fixed network’s hybrid precoding matrix. Furthermore, we extend the proposed method to multi-user MIMO systems and provide its performance analysis. Our simulation results show that the proposed dynamic hybrid precoding method strikes an attractive performance vs. power consumption trade-off. © 2020, CC-BY.

关键词： Phase shifters

来源：评论

学校读者我要写书评

暂无评论

Prompt-Based Few-Shot Text Classification with Virtual Class Representation

Prompt-Based Few-Shot Text Classification with Virtual Class...

引用

International Conference on Computer and Communications (ICCC)

作者： Zhengyu Ju Zhao Li Ye Li Shiwei Wu Canjun Wang Shandong Academy of Sciences Qilu University of Technology Jinan China Key Laboratory of Computing Power Network and Information Security Ministry of Education Jinan China Shandong Computer Science Center National Supercomputer Center in Jinan Jinan China Shandong Provincial Key Laboratory of Computer Networks Jinan China Shandong Fundamental Research Center for Computer Science Jinan China Evay Info Jinan China

Over the past few years, "Pre-training + Fine-tuning" has been highly successful in Natural Language Processing (NLP) tasks, but it has limitations in few-shot tasks and zero-shot tasks. Recently, "Prompt-based Tuning + Pretrained Language models (PLMs)" has achieved great success in few-shot stage and zero-shot stage, including few-shot text classification. Prompt-based tuning wraps suggestive characters and [MASK] tokens into a raw input sequence. Additionally, Prompt learning uses a verbalizer to map the semantic information of the [MASK] position to the final classification prediction. The verbalizer contains manual verbalizer and automatic verbalizer, etc. However, manual verbalizers are too dependent on human experience and external knowledge, while automatic verbalizers still face significant challenges. In this work, we introduce a novel approach for constructing a verbalizer termed as “virtual class representation”. This method entails assigning a fixed-length sequence of digits to represent each label in the dataset. We train a small-scale randomly initialized embedding mechanism to achieve preliminary semantic information for each class when virtual class representation is introduced into the embedding mechanism. The semantic information of each category is then further extracted by a convolution operation, and the final model regression value is obtained by calculating the similarity between the last hidden state of PLM and the semantic vector of the class. Our extensive experiments demonstrate the effectiveness of the proposed method on few-shot text classification tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Multi-Path Orchestration Method for Cloud-Edge Data Transmission Based on DRL

A Multi-Path Orchestration Method for Cloud-Edge Data Transm...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Zhihui Wang Xubing Dou Shuyun Li Huan Ma Xinchang Zhang Maoli Wang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Shandong Normal University Jinan China QuFu normal university Jining China

ISBN: (数字)9798331515966

ISBN: (纸本)9798331515973

In addressing the multi-path problem of cloud-edge data transmission, this paper introduces a multi-path orchestration method based on deep reinforcement learning (DRL) within the context of software-defined networks (SDN), termed Deep Q-Routing (DQR). This method establishes optimal data transmission paths between the cloud and multiple edges, based on available bandwidth and transmission delay, while avoiding path congestion to improve bandwidth utilization and reduce transmission delay. The optimal routing in SDN is defined through the design of state space sets, reward functions, and neural networks. Simulation experiments were conducted to evaluate the DQR method. Compared to existing routing methods, the proposed DQR method, which includes a reward function with weighted parameters, demonstrates superior overall network performance.

关键词： Cloud computing Scalability Neural networks Distributed databases Bandwidth Routing Deep reinforcement learning Delays Data communication Software defined networking

来源：评论

学校读者我要写书评

暂无评论

Demand Response Scheme: Achieving Sustainability in Distributed Data Processing

Demand Response Scheme: Achieving Sustainability in Distribu...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Xueying Zhai Yunfeng Peng Xiuping Guo Liang Zhang Wei Zhang School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China School of Economics and Management Beijing University of Posts and Telecommunications Beijing China Guizhou Key Laboratory of Electric Power Big Data Guizhou Institute of Technology Guizhou China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

The rapid development of Internet of Things (IoT) technology has driven the intelligent transformation of various industries, including manufacturing, agriculture, and healthcare, etc., significantly enhancing their management capabilities and decision-making efficiency. Data analysis is crucial, serving as both the core technology of this transformation and a major driving force for advancing industry intelligence. However, the increasing volume of data has led to high energy consumption during data analysis, posing significant challenges to environmental and economic sustainability. Integrating renewable energy sources (RESs) is an effective way to reduce greenhouse gas emissions due to their low-carbon and renewable nature. Additionally, the spatiotemporal variability and complementarity of RES generation and grid electricity prices provide favorable conditions for distributed data processing. Therefore, a two-stage demand response scheme is proposed to reduce carbon emissions and electricity costs by prioritizing data processing in data centers (DCs) where RES is abundant or electricity prices are low, based on RES generation and electricity price signals. Simulation results show that the proposed scheme reduces 36.37% carbon emissions and 20.49% electricity costs compared to the benchmark algorithm, indicating its potential for both environmental and economic optimization.

关键词： Renewable energy sources Energy consumption Costs Electricity Simulation Carbon dioxide Spatiotemporal phenomena Internet of Things Sustainable development Optimization

来源：评论

学校读者我要写书评

暂无评论

Research on liquid crystal display technology based on regional dynamic dimming algorithm

Research on liquid crystal display technology based on regio...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Zhitao Yu Peng Sun Mingle Zhou Qianlong Liu Shilong Zhao Hisense Video Technology Co. Ltd Qing Dao China Hisense Visual Technology Co. Ltd Qing Dao China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

In vehicle liquid crystal display (LCD) technology has attracted much attention for its wide range of applications in automotive infotainment systems. However, conventional LCD technologies have limitations in terms of energy consumption and display quality, especially in the context of the increasing demand for high contrast and low energy consumption. To address these challenges, this paper carries out a study of LCD technology based on an area dynamic dimming algorithm. The technology significantly improves the contrast ratio of LCDs and effectively reduces energy consumption by dividing the backlight module into multiple independently adjustable regions and dynamically adjusting the backlight brightness of each region according to the image content. The results show that the region dynamic dimming algorithm proposed in this paper can effectively adjust the brightness of the backlight according to the image content, achieving higher display contrast and lower energy consumption.

关键词： Energy consumption Heuristic algorithms Brightness Light emitting diodes Liquid crystal displays Robustness Entropy Energy efficiency Vehicle dynamics Optimization

来源：评论

学校读者我要写书评

暂无评论

FedLRDP: Federated Learning Framework with Local Random Differential Privacy

FedLRDP: Federated Learning Framework with Local Random Diff...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Runtian Zhou Anming Dong Jiguo Yu Qingyan Ding Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China School of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Big Data Institute Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Federated learning (FL) is a distributed machine learning framework enabling multiple clients to collaboratively train a shared ML model without sharing raw data. Despite its aim to safeguard data security and privacy, FL faces risks from advanced adversarial attacks like membership inference attack (MIA), potentially leaking sensitive information. To counter these threats, differential privacy (DP) methods add noise to shared model parameters. However, traditional DP methods struggle with balancing model accuracy, training efficiency, and privacy protection, often compromising one for the other. Additionally, uniform DP mechanisms may not cater to varying client privacy and performance needs. To tackle these challenges, we propose a federated learning framework based on localized random differential privacy (FedLRDP). This approach empowers each client to control noise levels based on their privacy requirements, enhancing model performance while preserving data privacy. We further optimize client-side loss functions to enhance model performance. Theoretical analysis establishes the convergence bounds for FedLRDP, demonstrating its superior convergence performance. Experimental results on MNIST reveal that FedLRDP improves model accuracy by 3.28% compared to traditional DP methods while mitigating MIA with a 72.48% lower attack success rate than FedAvg. Moreover, on EMNIST, FedLRDP boosts model accuracy by 7.31% compared to traditional DP methods, maintaining a 59.4% lower attack success rate than FedAvg. These findings underscore FedLRDP’s efficacy in meeting client privacy needs while enhancing model performance.

关键词： Training Differential privacy Privacy Accuracy Federated learning Noise Data models

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：