检索结果-内蒙古大学图书馆

International Conference on Neural Information Processing

作者： Geok See Ng Loo See Tan School of Computer Engineering Division of Software Systems Nanyang Technological University Singapore

ISBN: (纸本)9810475241

A type of network called the Contender Network (CN) was earlier proposed by Ng, Erdogan and Ng (1995). A classification algorithm is used to assign weighted vote in a monotonically decreasing function of the rank in CN. Modification to the CN classification algorithm known as the conscience algorithm is presented. However, a new problem is encountered when the conscience algorithm is used in CN. We name this problem as saturation problem (i.e. when saturation stage of the neural network is reached). This saturation problem is solved by introducing a count threshold. The threshold is decided rigorously through many experiments based on the criteria of the accuracy, error and confusion rates of the network performance. We present experiments that show that conscience algorithm introduced during training with appropriate count threshold can improve the network performance. Experimental results of this approach are presented and discussed through the application of the neural network in digit classification.

关键词： Intelligent networks Neural networks Voting Classification algorithms Equations computer networks software systems Learning systems

来源：评论

学校读者我要写书评

暂无评论

Adaptive Coordination with Graph Convolution Networks and Grey Wolf Optimization for Next-Gen 5G Network Slicing

Adaptive Coordination with Graph Convolution Networks and Gr...

引用

2024 International Conference on Fuzzy Theory and Its Applications, iFUZZY 2024

作者： Kowsalya, M. Ra, In-Ho Naveenraj, K.S. Thruvenkadam, S. Park, Seok-Woo School of Electrical Engineering Vellore Institute of Technology Vellore India School of Computer & Software Kunsan National University Gunsan Korea Republic of Jio Platform Limited Internet Protocol Division Mumbai India

ISBN: (纸本)9798350352788

The need for flexible and effective 5G communication networks has prompted studies into novel approaches for network slicing, a fundamental paradigm that permits network service personalization for a range of applications. In this research, we provide a unique technique that combines Graph Convolution Networks (GCN) and Grey Wolf Optimization (GWO) strategies to improve the adaptive configuration of 5G network slices. GCN, a software capable of recording detailed network interactions, and GWO, well-known for its metaheuristic optimization, combine to offer a strong foundation for tackling dynamic network slicing challenges. We optimize GWO settings via rigorous testing and demonstrate the effectiveness of the integrated strategy by achieving gains in important performance measures including latency, throughput, and resource use. The investigation not only advances the continuing development of 5G networks but also highlights how cutting-edge machine learning and optimization techniques can completely transform network slicing approaches. © 2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Optimizing Generative Adversarial Networks Models for Non-Pneumatic Tire Design: A Comparative Analysis and Evaluation 23

Optimizing Generative Adversarial Networks Models for Non-Pn...

引用

2023 Research in Adaptive and Convergent Systems, RACS 2023

作者： Seong, Ju-Yong Ji, Seung-Min Choi, Dong-Hyun Lee, Sungchul Division of Computer Science and Engineering Sunmoon University Chungcheongnam-do Asan-si Korea Republic of Department of Artificial Intelligence and Software Technology Sunmoon University Chungcheongnam-do Asan-si Korea Republic of

ISBN: (纸本)9798400702280

Pneumatic tires1 are used in a wide range of industries. However, they are difficult to design and rely on the knowledge of experienced designers. To aid in the design of pneumatic tires, this paper suggests the use of Generative Adversarial Networks (GAN) models. The 2000 created images for training were used after removing highly sim-ilar images using Mean Squared Error (MSE) and Structural Similarity Index (SSIM). To find the best model for generating patterns of regularly shaped non-pneumatic tires, GAN, Deep Convolu-tional Generative Adversarial Networks (DCGAN), StyleGANv2 ADA and ProjectedGAN were compared and analyzed. In the qualitative evaluation, the GAN, DCGAN, and StyleGAN v2-ADA models showed that the circle shape was distorted and did not maintain a consistent pattern, but ProjectedGAN showed that the circle remained consistent and the pattern was less distorted than the other GAN models. When evaluating quantitative metrics, ProjectedGAN performed best among several techniques that measure the difference be-tween the generated and actual image distributions. © 2023 ACM.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Constructing a non-linear model with neural networks for workload characterization

Constructing a non-linear model with neural networks for wor...

引用

IEEE International Symposium on Workload Characterization, IISWC-2006

作者： Yoo, Richard M. Lee, Han Chow, Kingsum Lee, Hsien-Hsin S. School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta GA 30332 United States Middleware Products Division Software and Solutions Group Intel Corp. Hillsboro OR 97123 United States

ISBN: (纸本)1424405084

Workload characterization involves the understanding of the relationship between workload configurations and performance characteristics. To better assess the complexity of workload behavior, a model based approach is needed. Nevertheless, several configuration parameters and performance characteristics exhibit non-linear relationships that prohibit the development of an accurate application behavior model. In this paper, we propose a non-linear model based on an artificial neural network to explore such complex relationship. We achieved high accuracy and good predictability between configurations and performance characteristics when applying such a model to a 3-tier setup with response time restrictions. As shown by our work, a nonlinear model and neural networks can increase the understandings of complex multi-tiered workloads, which further provide useful insights for performance engineers to tune their workloads for improving performance. ©2006 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Virtual device system for maximizing user experience on portable consumer electronic devices

Virtual device system for maximizing user experience on port...

引用

8th International Conference on Information Science and Digital Content Technology, ICIDT 2012

作者： Kim, Do-Hyung Lee, Jae-Ho Ryu, Cheol Yoon, Seok-Jin Lee, Cheol-Hoon Embedded SW Research Division Electronics and Telecommunications Research Institute Daejeon Korea Republic of Dept. of Computer Engineering System Software Lab. Chungnam National University Daejeon Korea Republic of

ISBN: (纸本)9788988678695

We proposed a virtual device system to maximize user experience without real portable consumer electronic device before purchasing the product. The virtual device system can execute the entire software stack which is exactly same one to be used for the real products. The virtual device system enables the user to learn quickly how to operate the product by providing a mechanism which executes automatically the major features of portable consumer electronic devices without user interaction. Finally, we verified the functionality of the proposed virtual device system with Linux-powered mobile device. © 2012 AICIT.

关键词： Thermoelectric equipment

来源：评论

学校读者我要写书评

暂无评论

Hierarchical means: Single number benchmarking with workload cluster analysis

Hierarchical means: Single number benchmarking with workload...

引用

2007 IEEE International Symposium on Workload Characterization, IISWC

作者： Yoo, Richard M. Lee, Hsien-Hsin S. Lee, Han Chow, Kingsum School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta GA 30332 United States Managed Runtime Division Software and Solutions Group Intel Corp. Hillsboro OR 97123 United States

ISBN: (纸本)1424415616

Benchmark suite scores are typically calculated by averaging the performance of each individual workload. The scores are inherently affected by the distribution of workloads. Given the applications of a benchmark suite are typically contributed by many consortium members, workload redundancy becomes inevitable. Especially, the merger of the benchmarks can significantly increase artificial redundancy. Redundancy in the workloads of a benchmark suite renders the benchmark scores biased, making the score of a suite susceptible to malicious tweaks. The current standard workaround method to alleviating the redundancy issue is to weigh each individual workload during the final score calculation. Unfortunately, such a weight-based score adjustment can significantly undermine the credibility of the objectiveness of benchmark scores. In this paper, we propose a set of benchmark suite score calculation methods called the hierarchical means that incorporate cluster analysis to amortize the negative effect of workload redundancy. These methods not only improve the accuracy and robustness of the score, but also improve the objectiveness over the weight-based approach. In addition, they can also be used to analyze the inherent redundancy and cluster characteristics in a quantitative manner for evaluating a new benchmark suite. In our case study, the hierarchical geometric mean was applied to a hypothetical Java benchmark suite, which attempts to model the upcoming release of the new SPECjvm benchmark suite. In addition, we also show that benchmark suite clustering heavily depends on how the workloads are characterized. ©2007 IEEE.

关键词： Redundancy

来源：评论

学校读者我要写书评

暂无评论

Preventing packet dropping and message tampering attacks on AODV-based Mobile Ad Hoc Networks

Preventing packet dropping and message tampering attacks on ...

引用

2012 International Conference on computer, Information and Telecommunication Systems, CITS 2012

作者： Obaidat, Mohammad S. Woungang, Isaac Dhurandher, Sanjay Kumar Koo, Vincent Department of Computer Science and Software Engineering Monmouth University West Long Branch NJ 07764 United States Department of Computer Science Ryerson University Toronto ON Canada Division of Information Technology Netaji Subhas Institute of Technology University of Delhi India

ISBN: (纸本)9781467315500

Due to recent advances in mobile wireless communication and computing technologies, Mobile Ad hoc Networks (MANETs) have become the network of choice for use in various applications. But this advantage comes with serious security concerns, in particular from a wireless transmission medium perspective where such networks may be subject to data tampering and dropping attacks. This paper enhances a recently proposed AODV-based protocol named Highly Secured Approach against Attacks on MANETs (HSAM) that deals with this issue in at least two ways: (a) by performing for the first time a simulation study of the HSAM protocol;(b) by introducing a more efficient approach to securing the routes in the route selection phase of the HSAM scheme. Simulation results are provided, showing that the proposed enhanced HSAM scheme (so-called E-HSAM) outperforms HSAM in terms of packet delivery ratio, throughput rate, and number of broken links;chosen as performance metrics, when malicious nodes are present in the network. © 2012 IEEE.

关键词： Mobile ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Next-Generation Human Activity Recognition Using Locality Constrained Linear Coding Combined With Machine Learning (NG-HAR-LCML)

引用

Healthcare Technology Letters 2025年第1期12卷

作者： Shabbir, Maryam Ahmad, Fahad Alanazi, Saad Awadh Khan, Muhammad Hassan Li, Jianqiang Mahmood, Tariq Naseem, Shahid Anwar, Muhammad Department of Computer Sciences Bahria University Punjab Lahore Pakistan Department of Computer Science Faculty of Computing & Information Technology University of the Punjab Lahore Pakistan School of Computing Faculty of Technology University of Portsmouth Portsmouth United Kingdom University of Portsmouth Portsmouth United Kingdom Department of Computer Science College of Computer and Information Sciences Jouf University Aljouf Sakaka Saudi Arabia The School of Software Engineering Beijing University of Technology Beijing China Lab CCIS Prince Sultan University Riyadh Saudi Arabia Department of Information Sciences University of Education Vehari Pakistan Faculty of Information Sciences Division Science &Technology University of Education Lahore Pakistan

Accurate Human Activity Recognition (HAR) is a critical challenge with wide-ranging applications in healthcare, assistive technologies, and human-computer interaction. Traditional feature extraction methods often struggle to capture the complex spatial and temporal dynamics of human movements, leading to suboptimal classification performance. To address this limitation, this study introduces a novel encoding approach using Locality-Constrained Linear Coding (LLC) to enhance the discriminative power of hand-crafted features extracted from low-cost wearable sensors—an accelerometer and a gyroscope. The proposed LLC-based encoding scheme enables robust feature representation, improving the accuracy of HAR models. The encoded features are classified using a diverse set of Machine Learning (ML) and Deep Learning (DL) algorithms, including Support Vector Machine (SVM), Logistic Regression (LR), Naive Bayes (NB), K-Nearest Neighbours (KNN), AdaBoost, Gradient Boosting Machine (GBM), and Deep Belief Network (DBN). Extensive quantitative evaluations demonstrate that LLC significantly outperforms conventional feature encoding techniques, leading to improved classification accuracy. Among the tested models, DBN achieves a state-of-the-art accuracy of 99%, highlighting its superiority for HAR tasks. The contributions of this research are threefold: (1) it establishes the necessity of an advanced encoding scheme (LLC) for feature enhancement in HAR, (2) it provides a rigorous comparative analysis of multiple ML and DL classifiers, and (3) it introduces a scalable and cost-effective HAR framework suitable for real-world applications. Performance is comprehensively assessed using robust evaluation metrics such as Area Under the Curve (AUC), Classification Accuracy (CA), F1 Score, Precision, Recall, and Matthews Correlation Coefficient (MCC). The findings of this study offer new insights into feature encoding for HAR, setting a foundation for future advancements in sensor-based act

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Feedback iterative learning control for time-delay systems based on 2D analysis approach

引用

控制理论与应用（英文版） 2010年第4期8卷 457-463页

作者： Deyuan MENG Yingmin JIA Junping DU Shiying YUAN The Seventh Research Division Beihang University Beijing 100191 China Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia School of Computer Science and Technology Beijing University of Posts and Telecommunications Beijing 100876 China School of Electrical Engineering and Automation Henan Polytechnic University Jiaozuo Henan 454000 China

This paper deals with the iterative learning control （ILC） design for multiple-input multiple-output （MIMO）,time-delay systems （TDS）.Two feedback ILC schemes are considered using the so-called two-dimensional （2D） analysis *** shows that continuous-discrete 2D Roesser systems can be developed to describe the entire learning dynamics of both ILC schemes,based on which necessary and sufficient conditions for their stability can be provided.A numerical example is included to validate the theoretical analysis.

关键词： Iterative learning control Time-delay systems 2D analysis approach

来源：评论

学校读者我要写书评

暂无评论

Network layer based secure routing protocol for wireless ad hoc sensor networks in urban environments

Network layer based secure routing protocol for wireless ad ...

引用

作者： Dhurandher, Sanjay K. Obaidat, Mohammad S. Gupta, Deepank Gupta, Nidhi Asthana, Anupriya Division of Information Technology Netaji Subhas Institute of Technology University of Delhi New Delhi India Department of Computer Science and Software Engineering Monmouth University NJ United States

ISBN: (纸本)9789898425249

Security is essential in wireless sensor networks as they are being used in urban environments, life saving disaster management and rescue operations. Any serious attack at the routing layer can cause serious damages. Although a lot of security measures have been proposed for application and transport layer, we have found that there is not enough research geared towards securing the network at the routing layer. In this paper, we propose a novel solution for securing against external as well as internal attacks. The protocol maintains a working network by using redundant multiple paths despite attacks at one route. It also identifies and removes the malicious nodes from the system. Since the system is totally distributed and does not require a central server as required in some of the other protocols, there is no single point of failure. We also keep in mind the limited computing resources and network bandwidth of the wireless sensor nodes. Finally the paper quantifies the protocol's effectiveness against some of the existing secure routing protocols namely QDV and SNEP using simulation studies.

关键词： Routing protocols

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：