检索结果-内蒙古大学图书馆

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

Whole-proteome based phylogenetic tree construction with inter-amino-acid distances and the conditional geometric distribution profiles

引用

Molecular phylogenetics and evolution 2015年 89卷 37-45页

作者： Xian-Hua Xie Zu-Guo Yu Guo-Sheng Han Wei-Feng Yang Vo Anh Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Hunan 411105 PR China School of Mathematics and Computer Science Gannan Normal University Jiangxi 341000 PR China. Electronic address: xxianhua@***. School of Mathematical Sciences Queensland University of Technology GPO Box 2434 Brisbane QLD 4001 Australia. Electronic address: yuzuguo@***. Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Hunan 411105 PR China. Electronic address: korea10282003@***. Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Hunan 411105 PR China. Electronic address: yangweifeng09@***. School of Mathematical Sciences Queensland University of Technology GPO Box 2434 Brisbane QLD 4001 Australia. Electronic address: v.anh@qut.edu.au.

There has been a growing interest in alignment-free methods for whole genome comparison and phylogenomic studies. In this study, we propose an alignment-free method for phylogenetic tree construction using whole-proteome sequences. Based on the inter-amino-acid distances, we first convert the whole-proteome sequences into inter-amino-acid distance vectors, which are called observed inter-amino-acid distance profiles. Then, we propose to use conditional geometric distribution profiles (the distributions of sequences where the amino acids are placed randomly and independently) as the reference distribution profiles. Last the relative deviation between the observed and reference distribution profiles is used to define a simple metric that reflects the phylogenetic relationships between whole-proteome sequences of different organisms. We name our method inter-amino-acid distances and conditional geometric distribution profiles (IAGDP). We evaluate our method on two data sets: the benchmark dataset including 29 genomes used in previous published papers, and another one including 67 mammal genomes. Our results demonstrate that the new method is useful and efficient.

关键词： Alignment-free whole-proteome comparison Conditional geometric distribution profile Inter-amino-acid distances Phylogenetic tree

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

PCB Defect Detection Model with Convolutional Modules Instead of Self-Attention Mechanism

PCB Defect Detection Model with Convolutional Modules Instea...

引用

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

CMC v2: Towards More Accurate COVID-19 Detection with Discriminative Video Priors

arXiv

引用

arXiv 2022年

作者： Hou, Junlin Xu, Jilan Zhang, Nan Wang, Yi Zhang, Yuejie Zhang, Xiaobo Feng, Rui School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University China Academy for Engineering and Technology Fudan University China Shanghai AI Laboratory China Children’s Hospital of Fudan University National Children’s Medical Center Shanghai China

This paper presents our solution for the 2nd COVID-19 Competition, occurring in the framework of the AIMIA Workshop at the European Conference on computer Vision (ECCV 2022). In our approach, we employ the winning solution last year which uses a strong 3D Contrastive Mixup Classification network (CMC v1) as the baseline method, composed of contrastive representation learning and mixup classification. In this paper, we propose CMC v2 by introducing natural video priors to COVID-19 diagnosis. Specifically, we adapt a pre-trained (on video dataset) video transformer backbone to COVID-19 detection. Moreover, advanced training strategies, including hybrid mixup and cutmix, slice-level augmentation, and small resolution training are also utilized to boost the robustness and the generalization ability of the model. Among 14 participating teams, CMC v2 ranked 1st in the 2nd COVID-19 Competition with an average Macro F1 Score of 89.11%. © 2022, CC BY.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

A more effective definition of evidential conflict combined with evidential distance

引用

Journal of information and Computational Science 2011年第9期8卷 1729-1734页

作者： Chen, Yuxin Wu, Jiyi Cong, Jian Jie, Wenjing Deng, Yong School of Electronics and Information Technology Shanghai Jiao Tong University Shanghai 20024 China Hangzhou Key Lab of E-Business and Information Security Hangzhou Normal University Hangzhou 310036 China College of Food Science and Technology Shanghai Ocean University 999 Hucheng Huan Road Shanghai 201306 China Key Subject Laboratory of National Defense for Radioactive Waste and Environment Security Southwest University of Science and Technology Mianyang 621010 China Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Xiangtan Hunan 411105 China College of Computer and Information Sciences Southwest University Chongqing 400715 China

Evidence theory is widely used in many application systems such as information fusion and decision making under uncertainty environment. However, the classical Dempster combination rule is not efficient to deal with highly conflicting evidences. One of the open issues is how to determine the conflict degree in conflict evidence management. In this paper, a new conflict coefficient is proposed to measure the conflict degree between bodies of evidence. It can overcome some drawbacks of the classical conflict coefficient. The numerical example shows the efficiency of our proposed method. Copyright © 2011 Binary information Press.

关键词： information fusion

来源：评论

学校读者我要写书评

暂无评论

Feature Aggregation Network for Memory-Based Industrial Anomaly Detection

Feature Aggregation Network for Memory-Based Industrial Anom...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Min Li Delong Han Rui Shao Jinghui He Faculty of Data Science City University of Macau China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Shandong Computer Science Center (National Supercomputer Center in Jinan) 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) 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 the process of large-scale industrial production, complex defects of different shapes and sizes can occur in industrial products and their components, and these defects seriously affect the performance of industrial products and their components, and being able to quickly and accurately identify defective industrial products and their components is an important task. Memory-based methods are usually used for anomaly detection, and these methods often rely on pre-trained models for feature extraction, but have high requirements on feature quality. In addition, patch-based methods mainly focus on local differences in feature embedding when detecting anomalies without explicitly exploiting broader contextual information, thus greatly affecting the robustness and accuracy of anomaly detection. Aiming at the above problems and requirements, this paper proposes a Feature Aggregation Network for Memory-Based Industrial Anomaly Detection (FANet), which is based on the pre-extraction of anomalous features, attentional attention to key features, information aggregation of multi-level and multi-scale features, and the FANet provides advanced performance in industrial image anomaly detection and localisation by pre-extraction of anomalous features, attentional attention to key features, information aggregation of multi-layered and multi-scale features, and introduction of environmental information in the anomaly score computation to perform industrial anomaly detection tasks, and using core set subsampling to reduce storage requirements. On the MVTec AD, FANet has an image-level AUROC score of 99.1% and a pixel-level AUROC score of 98.2%. Similarly high detection results were achieved on the ViSA dataset, further demonstrating the robustness of FANet.

关键词： Training Runtime Shape Memory management Training data Production Feature extraction Robustness Anomaly detection Testing

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

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

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：