检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2023年第3期4卷 464-472页

作者： Zhao, Shuai Liang, Zhuoqian Wen, Jinming Chen, Jie College of Information Science and Technology Jinan University Guangzhou511400 China Pazhou Lab Guangzhou510330 China Shanghai Key Laboratory of Trustworthy Computing School of Software Engineering East China Normal University Shanghai200062 China

Current neural language models are trained to minimize cross-entropy and use softmax to compute the locally normalized probabilities over the target. While this setup provides solid results in several natural language processing (NLP) tasks, one unsatisfying aspect is its dense output. This density is wasteful, making models hard to interpret and assigning probability mass to many implausible outputs. To overcome this problem, we propose T-softmax, a simple but effective method to draw considerably sparse probability out of neural language models than softmax. Our method avoids dense output by truncating the unreliable tail of the probability distribution to improve the model's performance. In addition, we generalize logits with temperature, a critical regularization technique, from the softmax to T-softmax. To show our approach as a drop-in replacement for softmax, we evaluate them on three NLP tasks: summary generation, question answer, and math word problem. Experimental results show that our proposed model significantly improves performance without sacrificing speed;notably, in all experiments, our method outperforms the softmax. © 2020 IEEE.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

A Performance Evaluation of the Clustering-based Labelling Scheme

A Performance Evaluation of the Clustering-based Labelling S...

引用

2022 International Conference on engineering and MIS, ICEMIS 2022

作者： Klaib, Alhadi A. Venters, Colin C. Elmergib University Department of Software Engineering Khoms Libya Huddersfield University School of Computing and Engineering Huddersfield United Kingdom

ISBN: (数字)9781665454360

ISBN: (纸本)9781665454360

XML is a common technique for formatting and exchanging data across the Internet world. Updating and retrieving XML data is an active research area. In addition, indexing XML data is a significant task to improve the efficiency of XML queries. Labelling nodes is the used technique for indexing XML data efficiently. The Clustering-based Labelling Scheme (CLS) was proposed to address some limitations and challenges of indexing XML data. This paper aims to evaluate the performance of the clustering-based labelling scheme. Thus, a set of experiments were identified and designed for the evaluation purpose. Moreover, an appropriate dataset for testing the CLS scheme was identified. Subsequently, the experiments were carried out, and then the results were analysed and assessed to gain the findings of the experiments. Consequently, the results of these experiments suggest that the CLS achieved the target results with few expectations. Therefore, this evaluation showed an improvement in the performance and oefficiency of labelling XML documents. © 2022 IEEE.

关键词： XML

来源：评论

学校读者我要写书评

暂无评论

Offloading approach for mobile edge computing based on chaotic quantum particle swarm optimization strategy

引用

Journal of Ambient Intelligence and Humanized computing 2023年第10期14卷 14333-14347页

作者： Zhang, DeGan Sun, GuiXiang Zhang, Jie Zhang, Ting Yang, Peng Tianjin Key Lab of Intelligent Computing and Novel Software Technology Tianjin University of Technology Tianjin300384 China School of Sports Economics and Management Tianjin University of Sport Tianjin301617 China School of Electronics and Information Engineering Beijing Jiaotong University Beijing100093 China

With the development of 5 g, computing-intensive and complex applications in smart-city is growing rapidly. Due to the limited resources of mobile terminal devices in smart-city, new applications have higher requirements for delay, bandwidth, security, and energy consumption. Computation offloading in mobile edge computing (MEC) is effective to reduce delay and energy consumption of Real-time video analysis. An improved chaos quantum-behaved particle swarm optimization (ICQPSO) algorithm is proposed for multi-user and multi-MEC edge Computation offloading scenarios. Compared with other heuristic algorithms, the improved chaos quantum-behaved particle swarm optimization algorithm can effectively reduce the delay and energy consumption of edge computing offloading. Experimental results show that the improved chaotic quantum-behaved particle swarm optimization (ICQPSO) can effectively avoid premature convergence, has stronger global searchability, and can solve multi-dimensional complex NP-hard problems more efficiently. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

A Novel Contrastive Clustering Algorithm Based on K-means 4

A Novel Contrastive Clustering Algorithm Based on K-means

引用

4th IEEE International Conference on Pattern Recognition and Machine Learning, PRML 2023

作者： Yun, Yu Yang, Geng Li, Qin You, Jane Shenzhen Institute of Information Technology School of Software Engineering Shenzhen China Xidian University School of Telecommunications Engineering Xi'an China The Hong Kong Polytechnic University Department of Computing Hong Kong Hong Kong

ISBN: (纸本)9798350324303

Benefitting from the simplicity and ease of implementation, K-means algorithm and its variants have been extensively studied and applied. However, the similarity measure manner limits the performance of previous K-means methods. Specifically, existing methods only take the similarity between the data point and itself cluster centroid into account while failing to consider the relationship with other centroids. In this study, we propose a method called Contrastive K-means (CKm). For training, to learn satisfactory cluster centroids of input data points for clustering, CKm simultaneously considers the similarity/dissimilarity between positive/negative pairs when optimizing the cluster centroids of data. Experimental results on seven prevalent datasets substantiate that CKm surpasses other K-means and variants in performance. © 2023 IEEE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Image super‐resolution via dynamic network

引用

CAAI Transactions on Intelligence Technology 2024年第4期9卷 837-849页

作者： Chunwei Tian Xuanyu Zhang Qi Zhang Mingming Yang Zhaojie Ju School of Software Northwestern Polytechnical UniversityXi'anChina National Engineering Laboratory for Integrated Aero‐Space‐Ground‐Ocean Big Data Application Technology Xi'anChina Research&Development Institute Northwestern Polytechnical UniversityShenzhenChina School of Economics and Management Harbin Institute of Technology at WeihaiWeihaiChina Tencent AI Lab ShenzhenChina School of Computing University of PortsmouthPortsmouthUK

Convolutional neural networks depend on deep network architectures to extract accurate information for image super‐***,obtained information of these con-volutional neural networks cannot completely express predicted high‐quality images for complex scenes.A dynamic network for image super‐resolution(DSRNet)is presented,which contains a residual enhancement block,wide enhancement block,feature refine-ment block and construction *** residual enhancement block is composed of a residual enhanced architecture to facilitate hierarchical features for image super‐*** enhance robustness of obtained super‐resolution model for complex scenes,a wide enhancement block achieves a dynamic architecture to learn more robust information to enhance applicability of an obtained super‐resolution model for varying *** prevent interference of components in a wide enhancement block,a refine-ment block utilises a stacked architecture to accurately learn obtained ***,a residual learning operation is embedded in the refinement block to prevent long‐term dependency ***,a construction block is responsible for reconstructing high‐quality *** heterogeneous architecture can not only facilitate richer structural information,but also be lightweight,which is suitable for mobile digital *** results show that our method is more competitive in terms of performance,recovering time of image super‐resolution and *** code of DSRNet can be obtained at https://***/hellloxiaotian/DSRNet.

关键词： CNN dynamic network image super‐resolution lightweight network

来源：评论

学校读者我要写书评

暂无评论

A Graph Convolution Model for Intelligent Datum Features Selection 18

A Graph Convolution Model for Intelligent Datum Features Sel...

引用

18th CIRP Conference on Computer Aided Tolerancing, CAT 2024

作者： Lv, Wenbo Zhang, Chaolong Xu, Yuanping Kong, Chao Jin, Jin Li, Tukun Jiang, Xiangqian Tang, Dan Huang, Jian Zhang, Zongzheng School of Software Engineering Chengdu University of Information Technology Chengdu China School of Computing and Engineering University of Huddersfield HuddersfieldHD1 3DH United Kingdom Shandong Industrial Technology Research Institute of Zhejiang University Shandong China

The datum is a crucial component in tolerance specification, which is the foundation for the selections of geometric tolerances and tolerance principles. Currently, intelligent datum reasoning is largely based on logical rules that are mainly extracted from human experience, resulting in the high uncertainty and low efficiency. To tickle these issues, this study proposes a data selection model based on the GCN (Graph Convolutional Networks), In the devised model, the different geometric features of a workpiece are represented in a graph structure. The geometric, spatial, and assembly relationships, as well as positioning features are computed to obtain vectorized representations of the different geometric features, which serve as inputs to the constructed GCN model. Then, based on the GCN, a datum discriminant classifier has been developed on the training samples. To enhance the classifier accuracy, multiple GCN layers are employed for training, with the output of each GCN module added to a list. Ultimately, the outputs of all GCN modules are concatenated and subjected to classification prediction through fully connected layers. Datum specifications are established based on the classification of geometric features. The effectiveness and feasibility of this method are validated through case studies, e.g. rear floor crossbeams, with comparative results indicating a similarity rate of 85.19% with manually designed outcomes. © 2024 The Authors. Published by Elsevier B.V.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Knowledge-graph based Method for Datum Reference Frame Reasoning 18

A Knowledge-graph based Method for Datum Reference Frame Rea...

引用

18th CIRP Conference on Computer Aided Tolerancing, CAT 2024

作者： Fu, Hongsheng Kong, Chao Cao, Yanlong Xu, Yuanping Jin, Jin Li, Tukun Luo, Junding Zhang, Zongzheng School of Mechanical Engineering Zhejiang University Zhejiang China School of Computing and Engineering University of Huddersfield Queensgate Huddersfield United Kingdom School of Software Engineering Chengdu University of Information Technology Chengdu China CO. Ltd. China Shandong Industrial Technology Research Institute of Zhejiang University Shandong China

In mechanical engineering, the datum is essential in the tolerance specification, which impacts assembly and functional requirements. The standard mechanical parts, such as shaft and gear, already have a formalized datum reference frame (DRF) design process. However, non-standard parts still mainly rely on manual design. To this end, a knowledge-graph-based DRF reasoning method for non-standard parts is proposed. In this paper, an OWL 2-based knowledge model is constructed according to industrial practice. It combines empirical knowledge, knowledge graphs, and ontology reasoning methods to perform DRF generation automatically and precisely. The finite element method is introduced into this work to evaluate reasoned DRF. The effectiveness and feasibility of the method are demonstrated via a case study. © 2024 The Authors. Published by Elsevier B.V.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Empirical Insights into Product Security Challenges and Practices in software Development

Empirical Insights into Product Security Challenges and Prac...

引用

2024 International Conference on Frontiers of Information Technology, FIT 2024

作者： Rafi, Saima Akbar, Muhammad Azeem Khan, Arif Ali School of Computing Engineering & the Built Environment Edinburgh Napier University EH10 5DT United Kingdom Software Engineering Department Lappeenranta-Lahti University of Technology Lappeenranta15210 Finland M3S Empirical Software Engineering Research Unit University of Oulu Oulu90570 Finland

ISBN: (纸本)9798331510503

Ensuring product security in software development is crucial, encompassing hardware, firmware, and holistic protection measures. With rising cyber threats, organizations face challenges in safeguarding software products, often viewing security as a bottleneck. To address these issues, we conducted an empirical study with 22 practitioners across various industries, exploring challenges and practices in product security. Our findings highlight both the applicability of security practices and the new challenges in their implementation. This research contributes valuable insights, enabling organizations to proactively address security concerns and develop robust strategies for protecting their software products. © 2024 IEEE.

关键词： Challenges empirical study Practices Product security

来源：评论

学校读者我要写书评

暂无评论

Metamorphic Relation Patterns for Metamorphic Testing, Exploration and Robustness

Metamorphic Relation Patterns for Metamorphic Testing, Explo...

引用

作者： Ying, Zhihao Towey, Dave Bellotti, Anthony Chua, Caslon Quan Zhou, Zhi School of Computer Science University of Nottingham Ningbo China Zhejiang Ningbo China Department of Computer Science and Software Engineering Swinburne University of Technology HawthornVIC Australia School of Computing and Information Technology University of Wollongong WollongongNSW Australia

Metamorphic testing (MT) is an effective software quality assurance method;it uses metamorphic relations (MRs) to examine the inputs and outputs of multiple test cases. Metamorphic exploration (ME) and metamorphic robustness testing (MRT) are advanced additions to the MT literature: ME can enable better understanding, and thus testing, of systems;MRT can test software robustness without an oracle. Metamorphic relation patterns (MRPs) are abstractions or templates for multiple concrete MRs. The performance of MT/ME/MRT relies on the quality of MRs, but the identification of MRs is often a manual task requiring some knowledge of MRPs, creative thinking and a good understanding of the system. In other words, the effective identification of MRs remains a challenge and requires further study. In this paper, we propose formal definitions to describe the relationship between multiple MRPs in order to classify them. We also identify a series of new MRPs and propose a new MT framework that can guide the identification and application of MRPs. Based on our definitions, we present the notion of MRP family trees and further propose two trees by classifying previously published MRPs and our proposed MRPs, in order to make it easier for users to find their target MRPs for reuse, reference or inference. Finally, we report on case studies using the MRPs and our framework to guide the identification of MRs for MT/ME/MRT and successfully detect multiple violations. © 2025 John Wiley & Sons Ltd.

关键词： software testing

来源：评论

学校读者我要写书评

暂无评论

Optimization Study of BP Neural Network Based on Genetic Algorithm

Optimization Study of BP Neural Network Based on Genetic Alg...

引用

2023 IEEE International Conference on Electrical, Automation and Computer engineering, ICEACE 2023

作者： Cai, Yongheng Zhou, Zhuye Li, Zehui School of Computing Zhuhai College of Science and Technology Zhuhai China School of Data Sciences Zhejiang University of Finance & Economics Hangzhou China School of Automation and Software Engineering Shanxi University Taiyuan China

ISBN: (纸本)9798350309614

In today's era of big data, neural networks play a pivotal role in fields such as image recognition and natural language processing. However, traditional Backpropagation (BP) neural networks often encounter challenges when dealing with complex problems, including slow convergence and getting stuck in local optima. To address these issues, this study employs a genetic algorithm as an optimization technique to optimize the weights and thresholds of BP neural networks. Training is conducted on a set of highly nonlinear mapping datasets to obtain the optimal weight and threshold configurations for the GA-BP model. Experimental results demonstrate that compared to traditional BP neural networks, the GA-BP model exhibits a 19.8% improvement in prediction accuracy, an approximately 9.20% increase in the coefficient of determination (R2), a reduction of approximately 62.50% in mean squared error (MSE), and a decrease of about 38.76% in root mean squared error (RMSE). Furthermore, the GA-BP model displays significantly accelerated convergence. The contribution of this research lies in proposing an optimization method that combines genetic algorithms with BP neural networks. This model not only enhances prediction accuracy compared to the standalone BP neural network but also significantly strengthens its generalization capabilities. As a result, it demonstrates substantial practical application potential across diverse datasets and application scenarios. © 2023 IEEE.

关键词： BP neural network genetic algorithm optimization algorithm

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：