检索结果-内蒙古大学图书馆

Credit assignment for trained neural networks based on Koopman operator theory

Frontiers of computer science 2024年第1期18卷 251-253页

作者： Zhen LIANG Changyuan ZHAO Wanwei LIU Bai XUE Wenjing YANG Zhengbin PANG Institute for Quantum Information&State Key Laboratory of High Performance Computing National University of Defense TechnologyChangsha 410000China Institute of Software Chinese Academy of SciencesBeijing 100190China College of Computer Science and Technology National University of Defense TechnologyChangsha 410000China

1 Introduction Artificial neural networks(ANNs,also NNs)have recently emerged as leading candidate models for deep learning,popularly used in various areas[1–3].Behind the enormous success,ANNs are generally with complicated structures,there being an intricate data flow through multiple linear or nonlinear components between the input layer and the output ***,it is pressing to evaluate how much a specific component contributes to the final output,termed the Credit Assignment Problem(CAP)[4]in this paper.

关键词： layer assignment operator

来源：评论

学校读者我要写书评

暂无评论

Multi-Controller Architecture Design and Features in Software - Defined Networking (SDN) 6

Multi-Controller Architecture Design and Features in Softwar...

引用

6th International Conference on Mobile computing and Sustainable Informatics, ICMCSI 2025

作者： Prabhu, V. Balamurugan, P. Department of Computer Science and Engineering School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamilnadu Chengalpattu603 203 India Department of Networking and Communications School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamilnadu Chengalpattu603 203 India

ISBN: (纸本)9798331522667

Networking paradigm known as "Software-Defined Networking" (SDN) offers more flexibility with network management and is fast gaining popularity. Separating the control plane from the data plane is largely responsible for this success. In SDN-enabled networks, a centralized controller is used to translate high-level network application requirements into low-level directives that are issued to the forwarding devices. Such the controller requires limited ability to react to the request for flow processing generated by forwarding devices. Whenever an SDN-enabled network expands in terms of size or as a network traffic rises, flow processing demands can’t be able to fulfill by a single centralized controller. This causes a controller's performance to decline, which eventually results in a malfunctioning SDN-enabled network. Implementing a multi-controller architecture, in which a number of controllers cooperate to manage a sizable amount of network traffic and flow processing requirements, would be a successful strategy. The introduction of a multi-controller architecture and a consideration of the problems with its scalability, coherence as well as accessibility make up the core contribution of this study. Additionally, it identifies areas where study in this area could still be done. © 2025 IEEE.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Mobile robot path planning using deep deterministic policy gradient with differential gaming (DDPG-DG) exploration

引用

Cognitive Robotics 2024年第1期4卷 156-173页

作者： Deshpande, Shripad V. R, Harikrishnan Ibrahim, Babul Salam KSM Kader Ponnuru, Mahesh Datta Sai Pune412115 India Gulf University for Science & Technology Hawally Kuwait Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur603203 India

Mobile robot path planning involves decision-making in uncertain, dynamic conditions, where Reinforcement Learning (RL) algorithms excel in generating safe and optimal paths. The Deep Deterministic Policy Gradient (DDPG) is an RL technique focused on mobile robot navigation. RL algorithms must balance exploitation and exploration to enable effective learning. The balance between these actions directly impacts learning efficiency. This research proposes a method combining the DDPG strategy for exploitation with the Differential Gaming (DG) strategy for exploration. The DG algorithm ensures the mobile robot always reaches its target without collisions, thereby adding positive learning episodes to the memory buffer. An epsilon-greedy strategy determines whether to explore or exploit. When exploration is chosen, the DG algorithm is employed. The combination of DG strategy with DDPG facilitates faster learning by increasing the number of successful episodes and reducing the number of failure episodes in the experience buffer. The DDPG algorithm supports continuous state and action spaces, resulting in smoother, non-jerky movements and improved control over the turns when navigating obstacles. Reward shaping considers finer details, ensuring even small advantages in each iteration contribute to learning. Through diverse test scenarios, it is demonstrated that DG exploration, compared to random exploration, results in an average increase of 389% in successful target reaches and a 39% decrease in collisions. Additionally, DG exploration shows a 69% improvement in the number of episodes where convergence is achieved within a maximum of 2000 steps. © 2024 The Authors

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced Route Optimization: Incorporating Road Safety Factors for Optimal Path Selection 4

Enhanced Route Optimization: Incorporating Road Safety Facto...

引用

4th International Conference on Power, Energy, Control and Transmission Systems, ICPECTS 2024

作者： Subash, R. Prathaban, Banu Priya Ganeshkumar, N. Gopinathan, S. Srm Institute of Science and Technology School of Computing Department of Computing Technologies Chennai India Srm Institute of Science and Technology School of Computing Department of Networking and Communications Chennai India Gitam School of Technology Gandhi Institute of Technology and Management Department of Computer Science and Engineering Karnataka Bengaluru562163 India Sri Sai Ram Institute of Technology Department of Artificial Intelligence and Data Science Chennai India

ISBN: (纸本)9798331508845

Efficient route optimization is a crucial concern in modern transportation systems, influencing travel time, resource consumption, and user satisfaction. By empowering users to select their priority parameters, such as safety or efficiency, this project enables travellers to make eco-conscious choices and select routes that minimize their environmental footprint. Real-time data integration ensures users can bypass traffic jams and accidents, reducing emissions and fuel consumption. Furthermore, the focus on safety factors helps prevent accidents, thereby fostering safer road environments. Existing systems often fall short, providing limited customization and overlooking safety and sustainability priorities. To bridge these gaps, this project introduces an advanced route planning system that empowers users to select their priority parameters, integrates real-time data for up-to- the-minute updates, and prioritizes road safety. It introduces a pioneering approach that enhances the Dijkstra Algorithm by integrating real-time accident rate and travel time data into the route optimization process. By considering these additional factors, the algorithm produces routes that not only minimize distance but also prioritize safety and time efficiency in dynamic real-world conditions. The algorithm's multi-factor optimization considers distance, accident rates, and travel times, enabling the creation of routes that balance these criteria and offer improved decision-making for users through a user- friendly interface. The algorithm's dynamic adaptability, multi- factor optimization, and practical implementation showcase its potential to revolutionize how routes are planned, leading to safer, faster, and more informed travel experiences. © 2024 IEEE.

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

A Random Fusion of Mix 3D and Polar Mix to Improve Semantic Segmentation Performance in 3D Lidar Point Cloud

引用

computer Modeling in Engineering & sciences 2024年第7期140卷 845-862页

作者： Bo Liu Li Feng Yufeng Chen School of Computer Science and Engineering Macao University of Science and TechnologyMacao999078China School of Computer Science and Artificial Intelligence Chaohu UniversityChaohu238000China Institute of Vehicle Information Control and Network Technology Hubei University of Automotive TechnologyShiyan442002China

This paper focuses on the effective utilization of data augmentation techniques for 3Dlidar point clouds to enhance the performance of neural network *** point clouds,which represent spatial information through a collection of 3D coordinates,have found wide-ranging *** augmentation has emerged as a potent solution to the challenges posed by limited labeled data and the need to enhance model generalization *** of the existing research is devoted to crafting novel data augmentation methods specifically for 3D lidar point ***,there has been a lack of focus on making the most of the numerous existing augmentation *** this deficiency,this research investigates the possibility of combining two fundamental data augmentation *** paper introduces PolarMix andMix3D,two commonly employed augmentation techniques,and presents a new approach,named *** of using a fixed or predetermined combination of augmentation methods,RandomFusion randomly chooses one method from a pool of options for each instance or *** innovative data augmentation technique randomly augments each point in the point cloud with either PolarMix or *** crux of this strategy is the random choice between PolarMix and Mix3Dfor the augmentation of each point within the point cloud data *** results of the experiments conducted validate the efficacy of the RandomFusion strategy in enhancing the performance of neural network models for 3D lidar point cloud semantic segmentation *** is achieved without compromising computational *** examining the potential of merging different augmentation techniques,the research contributes significantly to a more comprehensive understanding of how to utilize existing augmentation methods for 3D lidar point *** data augmentation technique offers a simple yet effective method to leverage the diversity of augmentation techniques and boost the ro

关键词： 3D lidar point cloud data augmentation RandomFusion semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

QAR Data Imputation Using Generative Adversarial Network with Self-Attention Mechanism

引用

Big Data Mining and Analytics 2024年第1期7卷 12-28页

作者： Jingqi Zhao Chuitian Rong Xin Dang Huabo Sun School of Computer Science and Technology Tiangong UniversityTianjin 300387China Institute of Aviation Safety China Academy of Civil Aviation Science and TechnologyBeijing 100028China

Quick Access Recorder(QAR),an important device for storing data from various flight parameters,contains a large amount of valuable data and comprehensively records the real state of the airline ***,the recorded data have certain missing values due to factors,such as weather and equipment *** missing values seriously affect the analysis of QAR data by aeronautical engineers,such as airline flight scenario reproduction and airline flight safety status ***,imputing missing values in the QAR data,which can further guarantee the flight safety of airlines,is *** data also have multivariate,multiprocess,and temporal ***,we innovatively propose the imputation models A-AEGAN("A"denotes attention mechanism,"AE"denotes autoencoder,and"GAN"denotes generative adversarial network)and SA-AEGAN("SA"denotes self-attentive mechanism)for missing values of QAR data,which can be effectively applied to QAR ***,we apply an innovative generative adversarial network to impute missing values from QAR *** improved gated recurrent unit is then introduced as the neural unit of GAN,which can successfully capture the temporal relationships in QAR *** addition,we modify the basic structure of GAN by using an autoencoder as the generator and a recurrent neural network as the *** missing values in the QAR data are imputed by using the adversarial relationship between generator and *** introduce an attention mechanism in the autoencoder to further improve the capability of the proposed model to capture the features of QAR *** mechanisms can maintain the correlation among QAR data and improve the capability of the model to impute missing ***,we improve the proposed model by integrating a self-attention mechanism to further capture the relationship between different parameters within the QAR *** results on real datasets demonstrate that the model can rea

关键词： multivariate time series data imputation self-attention Generative Adversarial Network(GAN)

来源：评论

学校读者我要写书评

暂无评论

Q-Learning-Assisted Meta-Heuristics for Scheduling Distributed Hybrid Flow Shop Problems

引用

computers, Materials & Continua 2024年第9期80卷 3573-3589页

作者： Qianyao Zhu Kaizhou Gao Wuze Huang Zhenfang Ma Adam Slowik Institute of Systems Engineering Macao University of Science and TechnologyMacao99078China Department of Electronics and Computer Science Koszalin University of TechnologyKoszalin75-453Poland

The flow shop scheduling problem is important for the manufacturing *** flow shop scheduling can bring great benefits to the ***,there are few types of research on Distributed Hybrid Flow Shop Problems(DHFSP)by learning assisted *** work addresses a DHFSP with minimizing the maximum completion time(Makespan).First,a mathematical model is developed for the concerned ***,four Q-learning-assisted meta-heuristics,e.g.,genetic algorithm(GA),artificial bee colony algorithm(ABC),particle swarm optimization(PSO),and differential evolution(DE),are *** to the nature of DHFSP,six local search operations are designed for finding high-quality solutions in local *** of randomselection,Q-learning assists meta-heuristics in choosing the appropriate local search operations during ***,based on 60 cases,comprehensive numerical experiments are conducted to assess the effectiveness of the proposed *** experimental results and discussions prove that using Q-learning to select appropriate local search operations is more effective than the random *** verify the competitiveness of the Q-learning assistedmeta-heuristics,they are compared with the improved iterated greedy algorithm(IIG),which is also for solving *** Friedman test is executed on the results by five *** is concluded that the performance of four Q-learning-assisted meta-heuristics are better than IIG,and the Q-learning-assisted PSO shows the best competitiveness.

关键词： Distributed scheduling hybrid flow shop meta-heuristics local search Q-learning

来源：评论

学校读者我要写书评

暂无评论

On the Security of Smart Home Systems:A Survey

引用

Journal of computer science & technology 2023年第2期38卷 228-247页

作者：袁斌万俊吴宇晗邹德清金海 School of Cyber Science and Engineering Huazhong University of Science and TechnologyWuhan 430074China Hubei Key Laboratory of Distributed System Security Huazhong University of Science and Technology Wuhan 430074China Hubei Engineering Research Center on Big Data Security Huazhong University of Science and Technology Wuhan 430074China National Engineering Research Center for Big Data Technology and System Huazhong University of Science and TechnologyWuhan 430074China Services Computing Technology and System Lab Huazhong University of Science and TechnologyWuhan 430074China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen 518057China School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430074China Cluster and Grid Computing Lab Huazhong University of Science and TechnologyWuhan 430074China

Among the plethora of IoT(Internet of Things)applications,the smart home is one of the ***,the rapid development of the smart home has also made smart home systems a target for ***,researchers have made many efforts to investigate and enhance the security of smart home *** a more secure smart home ecosystem,we present a detailed literature review on the security of smart home ***,we categorize smart home systems’security issues into the platform,device,and communication *** exploring the research and specific issues in each of these security areas,we summarize the root causes of the security flaws in today's smart home systems,which include the heterogeneity of internal components of the systems,vendors'customization,the lack of clear responsibility boundaries and the absence of standard security ***,to better understand the security of smart home systems and potentially provide better protection for smart home systems,we propose research directions,including automated vulnerability mining,vigorous security checking,and data-driven security analysis.

关键词： IoT(Internet of Things) smart home IoT security smart home security

来源：评论

学校读者我要写书评

暂无评论

Generative adversarial networks with stochastic gradient descent with momentum algorithm for video-based facial expression

引用

International Journal of Information technology (Singapore) 2024年第6期16卷 3703-3722页

作者： Cherian, Aswathy K. Vaidhehi, M. Arshey, M. Briskilal, J. Simpson, Serin V. Department of Computing Technologies SRM Institute of Science and Technology Kattankulathur Chennai India Department of AI & amp School of Computer Science & amp

Video data is an asset that may be used in various settings, such as a live broadcast on a personal blog or a security camera at a manufacturing facility. Both of these examples are examples of how video data can be used. It is becoming increasingly common practice across a wide range of applications to use a machine learning appliance as a tool for processing video. Recent years have seen significant advancements made in the field of machine learning in computer vision. These advancements have been achieved. The presentation of humans is approached or even surpassed in areas such as item identification, object categorization, and image segmentation. Despite this, challenging difficulties exist, such as identifying human emotions. This study aims to recognize human emotions by analyzing still images and motion pictures taken from motion pictures using numerous machine learning procedures. To accomplish this, neural networks constructed based on Generative Adversarial Networks (GAN) were used to classify each face picture obtained from a frame into one of the seven categories of facial emotions we chose. To communicate feelings, videos are mined for informative aspects such as audio, single, and multiple video frames. During this process stage, separate instances of the OpenSMILE and Inception-ResNet-v2 models extract feature vectors from the audio and frames. After that, numerous classification models are trained using stochastic gradient descent with the impetus approach (SGDMA). The findings from each of the pictures are compiled into a table, and from that, it is determined which facial expression was seen on-screen the most often throughout the film. The classification of audio feature vectors is accomplished with the application of GAN-SGDMA. The Inception-ResNet-v2 algorithm is utilized to recognize feelings conveyed by still photographs. The findings of several experiments suggest that the presented distributed model GAN-SGDMA could significantly boost the sp

关键词： Attention model Face recognition Generative Adversarial Networks (GAN) Stochastic gradient descent with momentum algorithm (SGDMA) Video surveillance

来源：评论

学校读者我要写书评

暂无评论

Depth Map Prediction of Occluded Objects Using Structure Tensor with Gain Regularization

引用

Intelligent Automation & Soft computing 2023年第7期37卷 1145-1161页

作者： H.Shalma P.Selvaraj Department of Computing Technologies Faculty of Engineering and TechnologySchool of ComputingSRM Institute of Science and TechnologyKattankulathurChennai603203Tamil NaduIndia

The creation of the 3D rendering model involves the prediction of an accurate depth map for the input images.A proposed approach of a modified semi-global block matching algorithm with variable window size and the gradient assessment of objects predicts the depth map.3D modeling and view synthesis algorithms could effectively handle the obtained disparity *** work uses the consistency check method to find an accurate depth map for identifying occluded *** prediction of the disparity map by semi-global block matching has used the benchmark dataset of Middlebury stereo for *** improved depth map quality within a reasonable process-ing time outperforms the other existing depth map prediction *** experimental results have shown that the proposed depth map predictioncould identify the inter-object boundaryeven with the presence ofocclusion with less detection error and *** observed that the Middlebury stereo dataset has very few images with occluded objects,which made the attainment of gain *** this gain,we have created our dataset with occlu-sion using the structured lighting *** proposed regularization term as an optimization process in the graph cut algorithm handles occlusion for different smoothing *** experimented results demonstrated that our dataset had outperformed the Tsukuba dataset regarding the percentage of occluded pixels.

关键词： Depth maps occlusion detection reconstruction refined disparity map

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：