检索结果-内蒙古大学图书馆

International Conference on P2P, Parallel, Grid, Cloud and Internet computing (3PGCIC)

作者： Martin Watmough Simon Polovina Babak Khazaeri Richard Hill Conceptual Structures Research Group Department of Computing Sheffield Hallam University UK Distributed and Intelligent Systems Research Group University of Derby UK

The aim of this paper is to identify the requirements on data that are necessary to support a collective intelligence solution for future supply chains. It is based on an evidential discussion of the information flows in future supply chains and the impact these will have on the life cycle, governance and ownership of data. Supply Chains are facing an increasing complex future if they are to provide the services required while operating in increasingly diverse landscapes and environments. Integration and coordination across the whole supply chain is requiring new approaches, systems and processes therefore data must be enhanced to support these new demands and provide the agility that organisations and consumers envisage. The content of data or data sets is discussed in the context of semantics and Service Orientated Architecture (SOA). A shift in the content of data to include behaviour and increased synchronisation across processes is developed as a possible solution for future supply chains. The evolution and importance of understanding is discussed and developed into a reliance on the integration of data and processes through change control and governance to achieve a collective intelligence across the supply chain.

关键词： Supply chains Semantics Process control Planning Synchronization Context

来源：评论

学校读者我要写书评

暂无评论

Rank-SIFT: Learning to rank repeatable local interest points

Rank-SIFT: Learning to rank repeatable local interest points

引用

作者： Li, Bing Xiao, Rong Li, Zhiwei Cai, Rui Lu, Bao-Liang Zhang, Lei Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai 200240 China Microsoft Research Asia Beijing 100190 China MOE Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Shanghai Jiao Tong University Shanghai 200240 China

ISBN: (纸本)9781457703942

Scale-invariant feature transform (SIFT) has been well studied in recent years. Most related research efforts focused on designing and learning effective descriptors to characterize a local interest point. However, how to identify stable local interest points is still a very challenging problem. In this paper, we propose a set of differential features, and based on them we adopt a data-driven approach to learn a ranking function to sort local interest points according to their stabilities across images containing the same visual objects. Compared with the handcrafted rule-based method used by the standard SIFT algorithm, our algorithm substantially improves the stability of detected local interest point on a very challenging benchmark dataset, in which images were generated under very different imaging conditions. Experimental results on the Oxford and PASCAL databases further demonstrate the superior performance of the proposed algorithm on both object image retrieval and category recognition. © 2011 IEEE.

关键词： Image retrieval

来源：评论

学校读者我要写书评

暂无评论

An Improved YOLOv5 Detection Algorithm with Pruning and OpenVINO Quantization

An Improved YOLOv5 Detection Algorithm with Pruning and Open...

引用

2023 China Automation Congress, CAC 2023

作者： Chen, Cheng Gan, Yahui Han, Zao Gao, Huan Li, Ang School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education NanJing China Nanjing YingQi Intelligent Technology Co. Ltd. Intel Joint Research Institute on Intelligent Edge Computing NanJing China

ISBN: (纸本)9798350303759

In order to address the problem of current object detection models being too large to be deployed on robot controllers, this paper proposes improvements to YOLOv5 for real-time detection. The YOLOv5s model is pruned at the Batch Normalization (BN) layer, and further optimized using the OpenVINO tool for quantization. The results demonstrate that our improvements effectively improve the model's inference speed while maintaining its accuracy. Compared to the original YOLOv5 model, the pruned model achieves the same accuracy without degradation, with a 36.6% reduction in parameter count and a 35% reduction in weight storage file size. Furthermore, after optimization with OpenVINO, the final model achieves a FPS of 56. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Rethinking Graph Masked Autoencoders through Alignment and Uniformity 38

Rethinking Graph Masked Autoencoders through Alignment and U...

引用

38th AAAI Conference on Artificial Intelligence, AAAI 2024

作者： Wang, Liang Tao, Xiang Liu, Qiang Wu, Shu Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China

ISBN: (纸本)1577358872

Self-supervised learning on graphs can be bifurcated into contrastive and generative methods. Contrastive methods, also known as graph contrastive learning (GCL), have dominated graph self-supervised learning in the past few years, but the recent advent of graph masked autoencoder (GraphMAE) rekindles the momentum behind generative methods. Despite the empirical success of GraphMAE, there is still a dearth of theoretical understanding regarding its efficacy. Moreover, while both generative and contrastive methods have been shown to be effective, their connections and differences have yet to be thoroughly investigated. Therefore, we theoretically build a bridge between GraphMAE and GCL, and prove that the node-level reconstruction objective in GraphMAE implicitly performs context-level GCL. Based on our theoretical analysis, we further identify the limitations of the GraphMAE from the perspectives of alignment and uniformity, which have been considered as two key properties of high-quality representations in GCL. We point out that GraphMAE's alignment performance is restricted by the masking strategy, and the uniformity is not strictly guaranteed. To remedy the aforementioned limitations, we propose an Alignment-Uniformity enhanced Graph Masked AutoEncoder, named AUG-MAE. Specifically, we propose an easy-to-hard adversarial masking strategy to provide hard-to-align samples, which improves the alignment performance. Meanwhile, we introduce an explicit uniformity regularizer to ensure the uniformity of the learned representations. Experimental results on benchmark datasets demonstrate the superiority of our model over existing state-of-the-art methods. The code is available at: https://***/AzureLeon1/AUGMAE. Copyright © 2024, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

An asynchronous neural network model for the shortest path problem

An asynchronous neural network model for the shortest path p...

引用

IEEE International Conference on Neural Networks, ICNN 1993

作者： Zhao, Songhe Dillon, T.S. Expert and Intelligent Systems Laboratory Applied Computing Research Institute Department of Computer Science and Computer Engineering La Trobe University BundooraVIC3083 Australia Northern Jiao-tong University Beijing China

ISBN: (纸本)0780309995

researchers have shown that the neural network models can be used to find solutions for many optimization problems. Most of these models are energy based models and there is no guarantee the network converges to a global optimal solution. In this paper, we propose a new neural shortest path network model which no special convergence procedure needs to be performed. The network can work in purely an asynchronous mode and guarantees to reach the global optimal solution. © 1993 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Divide and Repair: Using Options to Improve Performance of Imitation Learning Against Adversarial Demonstrations

arXiv

引用

arXiv 2023年

作者： Dasgupta, Prithviraj Distributed Intelligent Systems Section Information Technology Division Naval Research Laboratory WashingtonDC United States

We consider the problem of learning to perform a task from demonstrations given by teachers or experts, when some of the experts' demonstrations might be adversarial and demonstrate an incorrect way to perform the task. We propose a novel technique that can identify parts of demonstrated trajectories that have not been significantly modified by the adversary and utilize them for learning, using temporally extended policies or options. We first define a trajectory divergence measure based on the spatial and temporal features of demonstrated trajectories to detect and discard parts of the trajectories that have been significantly modified by an adversarial expert, and could degrade the learner's performance, if used for learning, We then use an options-based algorithm that partitions trajectories and learns only from the parts of trajectories that have been determined as admissible. We provide theoretical results of our technique to show that repairing partial trajectories improves the sample efficiency of the demonstrations without degrading the learner's performance. We then evaluate the proposed algorithm for learning to play an Atari-like computer-based game called LunarLander in the presence of different types and degrees of adversarial attacks of demonstrated trajectories. Our experimental results show that our technique can identify adversarially modified parts of the demonstrated trajectories and successfully prevent the learning performance from degrading due to adversarial demonstrations. © 2023, CC BY.

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

Performance Measurements in iVIC Virtual Machine Clones

Performance Measurements in iVIC Virtual Machine Clones

引用

International Conference on Advanced Information Networking and Applications Workshops (AINAW)

作者： James Hardy Lu Liu Nik Bessis Lei Cui Jianxin Li Distributed and Intelligent Systems Research Group School of Computing and Mathematics University of Derby Derby UK Advanced Computing Technology Institute Beihang University Beijing China

ISBN: (纸本)9781467308670

Virtualisation is a prevalent technology in current computing. Virtualisation can reduce hardware costs by server consolidation, implement "green computing" by reducing power consumption and is an underpinning process for cloud computing enabling the creation of a range of virtual networks and virtual supercomputers. This paper presents performance measurements for a cloning system known as iVIC developed in Beihang University, China. iVIC creates clusters of virtual computers that can communicate with each other through virtual switch mechanisms. The virtual switches can also allow communication between the clone environment and the physical world. The paper presents the results of impartial testing to identify the limiting factors for creating and starting numbers of clone machines, measure the power consumption of the physical system and the computational performance capability of the clones.

关键词： Cloning Random access memory Servers Virtual machining Documentation Testing Switches

来源：评论

学校读者我要写书评

暂无评论

Handling drifts and shifts in on-line data streams with evolving fuzzy systems

Handling drifts and shifts in on-line data streams with evol...

引用

作者： Lughofer, E. Angelov, P. Department of Knowledge-based Mathematical Systems Johannes Kepler University of Linz Altenbergerstrasse 69 A-4040 Linz Austria Intelligent Systems Research Laboratory School of Computing and Communications Lancaster University LA1 4WA United Kingdom

In this paper, we present new approaches to handling drift and shift in on-line data streams with the help of evolving fuzzy systems (EFS), which are characterized by the fact that their structure (rule base and parameters) is not fixed and not pre-determined, but is extracted from data streams on-line and in an incremental manner. When dealing with so-called drifts and s hifts in data streams, one needs to take into account (1) automatic detection of drifts and shifts and (2) automatic reaction to the drifts and shifts. This is important to avoid interruptions in the learning process and downtrends in predictive accuracy. To address the first problem, we propose an approach based on the concept fuzzy rule age. The second problem is addressed by including gradual forgetting of (1) antecedent parts and (2) consequent parameters. The latter can be achieved by including a forgetting factor in the recursive local learning process of the parameters, whose value is automatically extracted based on the intensity of the shift/drift. For addressing the former problem, we introduce two alternative methods: one is based on the evolving density-based clustering (eClustering) used to form the antecedents in the eTS approach;the other is based on the automatic adaptation of the learning rate of the evolving vector quantization (eVQ) method used to form the antecedent in the FLEXFIS approach. The paper concludes with an empirical evaluation of the impact of the proposed approaches in (on-line) real-world data sets in which drifts and shifts occur. © 2010 Elsevier B.V. All rights reserved.

关键词： Fuzzy inference

来源：评论

学校读者我要写书评

暂无评论

Production Line Energy Cost Optimization with Renewable Energy Resource Usage in a Flexible Job Shop Configuration

引用

IFAC-PapersOnLine 2023年第2期56卷 7972-7977页

作者： Bruno Mota Pedro Faria Carlos Ramos GECAD - Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development LASI - Intelligent Systems Associate Laboratory Polytechnic of Porto Porto 4249-015 Portugal

Ever-increasing electricity prices due to inflation has become one of the main problems for manufacturing industries to deal with, mainly in a competitive market. The usage of Renewable Energy Resources (RER)s can be a great way to mitigate the energy costs of the electricity market, by not only covering the energy consumption but also turning a profit with the surplus. This paper aims to address these issues by proposing an intelligent production line scheduling system, in a flexible job shop configuration, that focuses on reducing energy costs. It considers dynamic pricing, RERs usage and surplus selling, and complex constraints applied in the production plan. To achieve these results, a Genetic Algorithm (GA) is employed. A case study from the literature, that uses real production data, is presented which does not take into account energy selling. Results show that with the proposed GA energy costs can be further reduced by 24.6% when considering RERs surplus selling.

关键词： Energy cost optimization Evolutionary algorithm Job shop scheduling

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-based Energy-Aware Offloading in Edge-Cloud Vehicular Networks 18

Machine Learning-based Energy-Aware Offloading in Edge-Cloud...

引用

18th International Conference on Mobile systems and Pervasive computing, MobiSPC 2021, The 16th International Conference on Future Networks and Communications, FNC 2021 and the 11th International Conference on Sustainable Energy Information Technology, SEIT 2021

作者： Ismail, Leila Materwala, Huned Intelligent Distributed Computing and Systems Research Laboratory Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University Al Ain Abu Dhabi15551 United Arab Emirates National Water and Energy Center United Arab Emirates University Al Ain Abu Dhabi15551 United Arab Emirates

A vehicular network underpinned by the 3-tier vehicle-edge-cloud infrastructure enables an efficient and safer travel experience. The compute-intensive vehicular applications are often offloaded to the edge and/or cloud servers to enhance the applications' Quality of Services (QoS). The underlying edge-cloud servers consume a high among of energy. Consequently, it becomes crucial to optimizing energy consumption in the offloading process. Current energy-efficient offloading strategies in 2-tier vehicle-edge infrastructure, do not account for cloud computing energy consumption. In this paper, we address this void by proposing a machine learning-based energy-aware offloading algorithm, which optimizes the energy of the edge-cloud computing platform. The offloading strategy is enabled by the Support Vector Machine (SVM) regression model machine learning algorithm used for the edge-cloud power prediction. The experimental results show that the proposed algorithm is a promising approach in energy savings. © 2021 Elsevier B.V.. All rights reserved.

关键词： Energy efficiency

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：