检索结果-内蒙古大学图书馆

An End-to-End Classification Network Model Based on Hybrid Supervision for Industrial Surface Defect Detection

International Journal of Pattern Recognition and Artificial Intelligence 2025年第5期39卷

作者： Qin, Runbing Chen, Ningjiang Gan, Shukun Guangxi University School of Computer Electronics and Information Nanning530004 China Education Department of Guangxi Zhuang Autonomous Region Key Laboratory of Parallel Distributed and Intelligent Computing Guangxi University Nanning530004 China Guangxi Intelligent Digital Services Research Center of Engineering Technology Nanning530004 China

Industrial part surface defect detection aims to precisely locate defects in images, which is crucial for quality control in manufacturing. The traditional method needs to be designed in advance, but it has shortcomings in terms of generalization ability. Deep neural network-based defect detection faces issues such as low resolution, data scarcity, labeling costs, and high computation. Therefore, an improved solution is necessary to enhance industrial product quality control efficiency and accuracy. A new method is proposed that utilizes end-to-end training of a two-stage neural network based on segmentation with an extended training process. The gradient flow from the classification to the segmentation network is adjusted to prevent unstable features from interfering with learning. To address the problem of image oversampling and undersampling during training, a frequency sampling scheme for negative samples is introduced. Additionally, positive pixels in the region-based segmentation mask are weighted using the distance transform algorithm so that regions with a high probability of defects can be detected without detailed annotation. Experiments are conducted across three distinct defect datasets by applying hybrid supervision encompassing diverse conditions. In the optimal case, the AP rate of the proposed model on the DAGM and KolektorSDD datasets reaches 100%, and the AP rate on the Severstal Steel dataset reaches 98.99%. The experiments’ results show that the detection accuracy has improved greatly, showing how well the proposed method works in the industry. © 2025 World Scientific Publishing Company.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

High performance multidimensional analysis of large datasets 1

High performance multidimensional analysis of large datasets

引用

1st ACM International Workshop on Data Warehousing and OLAP, DOLAP 1998

作者： Goil, Sanjay Choudhary, Alok Center for Parallel and Distributed Computing Department of Electrical and Computer Engineering Northwestern University Technological Institute 2145 Sheridan Road EvanstonIL60208 United States

ISBN: (纸本)1581131208

Summary information from data in large databases is used to answer queries in On-Line Analytical Processing (OLAP) systems and to build decision support systems over them. The Data Cube is used to calculate and store summary information on a variety of dimensions, which is computed only partially if the number of dimensions is large. Queries posed on such systems are quite complex and require different views of data. These may either be answered from a materialized cube in the data cube or calculated on the fly. Further, data mining for associations can be performed on the data cube. Analytical models need to capture the multi-dimensionality of the underlying data, a task for which multidimensional databases are well suited. Multidimensional databases store data in multidimensional structure on which analytical operations are performed. A challenge for these systems is how to handle large data sets in a large number of dimensions. This paper presents q parallel OLAP infrastructure for multidimensional databases integrated with association rule mining. Scheduling optimizations for parallel computation of complete data cubes are presented. We propose left and right schedules for partial data cubes for m-way mining of association rules. Our implementation on the IBM SP-2, a shared-nothing parallel machine, can handle large data sets and a large number of dimensions by using disk I/O in our algorithms. © ACM 1999.

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

Exploiting ownership sets in HPF 1

引用

13th International Workshop on Languages and Compilers for parallel computing, LCPC 2000

作者： Joisha, Pramod G. Banerjee, Prithviraj Center for Parallel and Distributed Computing Electrical and Computer Engineering Department Technological Institute Northwestern University 2145 Sheridan Road IL60208–3118 United States

ISBN: (数字)9783540455745

ISBN: (纸本)3540428623

Ownership sets are fundamental to the partitioning of program computations across processors by the owner-computes rule. These sets arise due to the mapping of data arrays onto processors. In this paper, a we focus on how ownership sets can be efficiently determined in the context of the HPF language, and show how the structure of these sets can be symbolically characterized in the presence of arbitrary data alignment and data distribution directives. Our starting point is a system of equalities and inequalities due to Ancourt et al. that captures the array mapping problem in HPF. We arrive at a refined system that enables us to efficiently solve for the ownership set using the Fourier-Motzkin Elimination technique, and which requires the course vector as the only auxiliary vector. We developb important and general properties pertaining to HPF alignments and distributions, and show how they can be used to eliminate redundant communication due to array replication. We also show how the generation of communication code can be avoided when pairs of array references are ultimately mapped onto the same processors. Experimental data demonstrating the improved code performance that the latter optimization enables is presented and discussed. © Springer-Verlag Berlin Heidelberg 2001.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Correctly detecting intrinsic type errors in typeless languages such as MATLAB

Correctly detecting intrinsic type errors in typeless langua...

引用

2001 Conference on Array-Programming Languages: An Arrays Odyssey, APL 2001

作者： Joisha, Pramod G. Banerjee, Prithviraj Center For Parallel And Distributed Computing Electrical And Computer Engineering Department Technological Institute Northwestern University 2145 Sheridan Road IL60208-3118 United States

ISBN: (纸本)1581134193

Among the main impediments that languages such as MATLAB and APL present to a compiler is the lack of an explicit declaration for a variable's type, The determination of this important attribute could allow a compiler to generate more efficient code, and is a problem that has been extensively studied in the past. This paper revisits this problem but unlike prior efforts, the objective is a uniform approach to type estimation that also accommodates type incorrect programs in a way that facilitates stronger type error detection through the exact localization of the type error at run time. We also show how our methodology makes it possible to further reduce the run-time overhead due to type conformability checking. The techniques are clearly demonstrated by applying them to deduce the intrinsic types of program variables in the MATLAB language. © 2001 ACM.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

A Java graphical user interface for large-scale scientific computations in distributed systems 4

A Java graphical user interface for large-scale scientific c...

引用

4th International Conference/Exhibition on High Performance computing in the Asia-Pacific Region, HPC-Asia 2000

作者： Shen, X. Thiruvathukal, G. Liao, W. Choudhary, A. Singh, A. Center for Parallel and Distributed Computing Department of Electrical and Computer Engineering Northwestern University EvanstonIL60208 United States School of Computing Telecommunications and Information Sciences JHPC Laboratory DePaul University United States

ISBN: (纸本)0769505902

Large-scale scientific applications present great challenges to computational scientists in terms of obtaining high performance and in managing large datasets. These applications (most of which are simulations) may employ multiple techniques and resources in a heterogeneously distributed environment. Effective working in such an environment is crucial for modern large-scale simulations. In this paper, we present an integrated Java graphical user interface (IJ-GUI) that provides a control platform for managing complex programs and their large datasets easily. As far as performance is concerned, we present and evaluate our initial implementation of two optimization schemes: data replication and data prediction. Data replication can take advantage of 'temporal locality' by caching the remote datasets on local disks;data prediction, on the other hand, provides prefetch hints based on the datasets' past activities that are kept in databases. We first introduce the data contiguity concept in such an environment that guides data prediction. The relationship between the two approaches is discussed. © 2000 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

PDRL-CM: An efficient cooperative caching management method for vehicular networks based on deep reinforcement learning

引用

Ad Hoc Networks 2025年 176卷

作者： Pingjie Ou Ningjiang Chen Long Yang School of Computer and Electronic Information Guangxi University Nanning 530004 Guangxi China Key Laboratory of Parallel Distributed and Intelligent Computing Education Department of Guangxi Zhuang Autonomous Region Nanning 530004 Guangxi China The Guangxi Intelligent Digital Services Research Center of Engineering Technology Nanning 530004 Guangxi China

In vehicular networks, onboard devices face the challenge of limited storage, and computational resources constrain their processing and storage capabilities. This limitation is particularly significant for applications that require complex computations and real-time responses. Additionally, limited storage capacity reduces the range of cacheable data, which can impact the immediate availability of data and the continuity of services. Therefore, improving cache utilization and meeting vehicles’ real-time data demands pose significant challenges. Deep reinforcement learning can optimize the issues arising from agents’ continuously changing state and action spaces due to increasing request demands. However, training the network may encounter instability and convergence difficulties in dynamic and complex environments or situations with sparse rewards. In response to these issues, this paper proposes a Priority-based Deep Reinforcement Learning Collaborative Cache Management method (PDRL-CM). PDRL-CM first designs a lightweight cache admission strategy that leverages data’s inherent and combined attributes. It then makes cache admission decisions Using Monte Carlo sampling and a max-value search strategy combined with a feedforward neural network. Secondly, the method considers minimizing system latency and reducing vehicle energy consumption as joint optimization problems. An improved deep reinforcement learning algorithm solves this problem and makes cache-sharding decisions. A prioritized experience replay mechanism is incorporated to adjust the network prediction model quickly and accelerate the convergence process. Experimental results indicate that, compared to existing DRL-based caching methods, PDRL-CM offers faster data processing efficiency and higher cache hit rates under varying vehicle density, storage capacity, and content volume conditions.

关键词： Cache memory

来源：评论

学校读者我要写书评

暂无评论

Modeling of handoffs and performance analysis of wireless data networks

Modeling of handoffs and performance analysis of wireless da...

引用

International Conference on parallel Processing Workshops, ICPPW 2001

作者： Zeng, Qing-An Agrawal, D.P. Center for Distributed and Mobile Computing Department of Electrical and Computer Engineering and Computer Science University of Cincinnati OH45221-0030 United States

ISBN: (纸本)0769512607

In this paper, we introduce a handoff scheme for data mobile cellular radio systems. A steady-stale traffic model is established and an analytical model of the system performance is presented. Average queue length and transmission delay are evaluated. Although mobile users holding channels move from one cell to another, there is almost no packet loss except for the negligibly small blocking probability because a channel request can be transferred from the queue of one base station to another. © 2001 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

A reliable active scanning scheme for the IEEE 802.11 MAC layer handoff

A reliable active scanning scheme for the IEEE 802.11 MAC la...

引用

2003 IEEE Radio and Wireless Conference, RAWCON 2003

作者： Li, Wei Zeng, Qing-An Agrawal, D.P. Center of Distributed and Mobile Computing Department of Electrical and Computer Engineering and Computer Science University of Cincinnati CincinnatiOH45221-0030 United States

ISBN: (纸本)0780378296

In the IEEE 802.11 wireless local area networks (WLANs) with fixed access points (APs), handoff occurs when a mobile station (MS) with a communication in progress changes its associated AP from one to another. It is important to minimize the handoff latency because the active communications of a MS are interrupted before the handoff completes. Such a design needs to take into consideration the high error rate of WLANs. The IEEE 802.11 medium access control (MAC) protocol recommends an active scanning mode for the handoff process. The probe delay of the active scanning may increase greatly if the probe request is lost. However, the successful transmission of the probe request is very unpredictable due to the high collision probability and the lack of any acknowledgement. In this paper, we propose a highly reliable active scanning scheme which can be implemented with the current IEEE 802.11 channel scanning procedure. It is indicated to efficiently increase the reliability of channel scanning, especially in a noisy environment, by performing the probe request loss detection and retransmission. Furthermore, the proposed scheme reduces the overall handoff latency by providing a higher priority for management frames over data frames. © 2003 IEEE.

关键词： Probes

来源：评论

学校读者我要写书评

暂无评论

Extended collective I/O for efficient retrieval of large objects

Extended collective I/O for efficient retrieval of large obj...

引用

International Conference on High Performance computing

作者： S. More A. Choudhary Center for Parallel and Distributed Computing Department of Electrical and Computer Engineering Northwestern University USA

Object-relational database management systems (OR-DBMS) extend the capabilities of the relational databases by allowing definition of new data types and methods to operate on these data types while retaining most of the relational model semantics. In this paper we examine issues related to parallel processing of queries in the object-relational model with respect to efficient storage and retrieval of large objects. We extend the concept of collective I/O and other related techniques such as request merging and data sieving in the database domain to achieve high performance in the retrieval of large objects. We deal with the I/O optimization problem in the query executor, access methods and the low level runtime system. We also propose a new technique called pooled striping for efficient storage of large objects on multiple disks. The results presented in this paper clearly show the effectiveness of the proposed I/O optimization techniques in handling large amounts of data in a parallel object-relational database system.

关键词： electrical capacitance tomography parallel processing Concurrent computing Relational databases Database systems Information retrieval Merging Ear Data handling distributed computing

来源：评论

学校读者我要写书评

暂无评论

Design issues for a high-performance distributed shared memory on symmetrical multiprocessor clusters

引用

Cluster computing 1999年第3期2卷 177-186页

作者： Roy, Sumit Chaudhary, Vipin Parallel and Distributed Computing Laboratory Department of Electrical and Computer Engineering Wayne State University Detroit USA

Clusters of Symmetrical Multiprocessors (SMPs) have recently become the norm for high-performance economical computing solutions. Multiple nodes in a cluster can be used for parallel programming using a message passing library. An alternate approach is to use a software distributed Shared Memory (DSM) to provide a view of shared memory to the application programmer. This paper describes Strings, a high performance distributed shared memory system designed for such SMP clusters. The distinguishing feature of this system is the use of a fully multi-threaded runtime system, using kernel level threads. Strings allows multiple application threads to be run on each node in a cluster. Since most modern UNIX systems can multiplex these threads on kernel level light weight processes, applications written using Strings can exploit multiple processors on a SMP machine. This paper describes some of the architectural details of the system and illustrates the performance improvements with benchmark programs from the SPLASH-2 suite, some computational kernels as well as a full fledged application. It is found that using multiple processes on SMP nodes provides good speedups only for a few of the programs. Multiple application threads can improve the performance in some cases, but other programs show a slowdown. If kernel threads are used additionally, the overall performance improves significantly in all programs tested. Other design decisions also have a beneficial impact, though to a lesser degree.

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：