检索结果-内蒙古大学图书馆

Pothole Detection: A Study of Ensemble Learning and Decision Framework

International Journal of Advanced Computer Science and Applications 2025年第4期16卷 67-79页

作者： Gorro, Ken D. Ranolo, Elmo B. Ilano, Anthony S. Balijon, Deofel P. Center for Cloud Computing Big Data and Artificial Intelligence Philippines College of Computing Artificial Intelligence and Sciences of Cebu Normal University Philippines

This study investigates the potential use of ensemble learning (YOLOv9 and Mask R-CNN) and Multi-Criteria Decision Making for pothole detection system. A series of experiments were conducted, including variations in confidence thresholds, IoU thresholds, dynamic weight configurations, camera angles and MCDM criteria, to assess their effects on detection performance. The YOLOv9 model achieved a mean Average Precision (mAP) of 0.908 at 0.5 IoU and an F1 score of 0.58 at a confidence threshold of 0.282, indicating a strong balance between precision and recall. However, adjusting IoU thresholds showed that lower thresholds improved recall but resulted in false positives, while higher thresholds improved precision but reduced recall. Dynamic weight configurations were explored, with balanced weights (wY = 0.5, wM = 0.5) yielding the best overall performance, while uneven weights allowed trade-offs between precision and recall based on specific application needs. The MCDM framework refined detection outputs by evaluating pothole features such as size, position, depth, and shape. The proposed algorithm has the potential to be widely used in practical applications. Overfitting is the main drawback of the proposed algorithm, but this is dependent on the use case where the pothole detection will be used. © (2025), (Science and Information Organization). All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Towards Robust Video Anomaly Detection in 6G Networks: A Scene-Adaptive Framework

引用

IEEE Network 2025年

作者： Zhang, Sijia Yu, Yong Tao, Xiaoling Wang, Lianhai Shaanxi Normal University School of Computer Science China Guilin University of Electronic Technology Guangxi Cooperative Innovation Center of Cloud Computing and Big Data China Qilu University of Technology Shandong Academy of Sciences Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing China

With the rapid advancement of 5th Generation (5G) networks, their low latency and high bandwidth facilitate the development of smart city systems. Among the smart city systems, anomaly detection in surveillance videos has been an essential part due to its importance to public safety and security. With the transition to 6G technology, the practical applications of video anomaly detection are expanding to encompass a variety of scenarios, such as sidewalks, shopping malls and campuses, which exhibit significant differences. However, most existing anomaly detection methods deployed in the cloud typically rely on the fixed datasets for training and apply the trained uniform model to the edge services across different scenarios. The distinct environmental conditions may lead to varying performance of a uniform anomaly detection model. To alleviate these issues, we propose a scene-adaptive video anomaly detection framework in 6G-based applications. The proposed framework leverages the advantages of 6G networks to facilitate localized processing and rapid adaptation to diverse environments. To enable the anomaly detection model to adapt more robustly to local environments, the proposed framework integrates a pre-trained model and simulates anomalies to train the anomaly detection model in a denoising manner. By integrating pre-trained teacher models with edge computing nodes, the proposed method facilitates accurate anomaly detection while maintaining robust performance across varying scenarios. The framework utilizes both original data and simulated anomalous data to fine-tune the edge model, ensuring it aligns with the unique characteristics of each environment. Experimental results demonstrate the effectiveness of the proposed method across different scenarios, enabling smarter and more responsive surveillance systems in the 6G era. © 2025 IEEE.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

Hyper-Parameter Optimization and Proxy Re-encryption for Federated Learning 6th

Hyper-Parameter Optimization and Proxy Re-encryption for F...

引用

6th International Conference on Blockchain and Trustworthy Systems, BlockSys 2024

作者： Du, Wanrong Wen, Bin Ma, Mengshuai Liu, Wenlong Wei, Xiaoxun Key Laboratory of Data Science and Smart Education Ministry of Education Hainan Normal University Haikou571158 China School of Information Science and Technology Hainan Normal University Haikou571158 China Cloud Computing and Big Data Research Center Hainan Normal University Haikou571158 China

ISBN: (纸本)9789819614103

Federated learning is a distributed machine learning paradigm that allows multiple participants to collaborate on training a shared model without revealing their own data. However, federated learning faces challenges such as data heterogeneity, communication overhead, security attacks, etc., which result in low efficiency of data training. To address these issues, this paper proposes a strategy to enhance the training efficiency of federated learning data through hyperparameter optimization and proxy re-encryption. A semi-supervised model of federated learning based on generative adversarial network is designed so that each participant can automatically adjust and optimize their own training parameters according to their own data distribution and environment in order to adapt to the data heterogeneity and dynamics of federated learning. Finally, experiments demonstrate that the proposed method can significantly improve the efficiency of data training and model performance compared with traditional federated learning methods across different datasets and scenarios. Experimental results show that the proposed strategy can achieve the same or even better accuracy than centralized machine learning while safeguarding data privacy and enabling ciphertext conversion. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Morphology and structural stability of Pt–Pd bimetallic nanoparticles

引用

Chinese Physics B 2015年第3期24卷 149-156页

作者：刘暾东郑骥文邵桂芳范天娥文玉华 Center for Cloud Computing and Big Data Department of AutomationXiamen University Institute of Theoretical Physics and Astrophysics Department of PhysicsXiamen University

The morphologies and structures of Pt–Pd bimetallic nanoparticles determine their chemical and physical ***, a fundamental understanding of their morphologies and structural stabilities is of crucial importance to their applications. In this article, we have performed Monte Carlo simulations to systematically explore the structural stability and structural features of Pt–Pd alloy nanoparticles. Different Pt/Pd ratios, and particle sizes and shapes were *** simulated results reveal that the truncated octahedron, which has the remarkably lowest energy among all the considered shapes, exhibits the best structural stability while the tetrahedron has the worst invariably. Furthermore, all the structures of Pt–Pd alloy nanoparticles present Pd-rich in the outmost layer but Pt-rich in the sub-outmost layer. Especially, atomic distribution and chemical short-range order parameter were applied to further characterize the structural features of Pt–Pd alloy nanoparticles. This study provides a significant insight not only into the structural stability of Pt–Pd alloy nanoparticles with different compositions, and particle sizes and shapes but also to the design of bimetallic nanoparticles.

关键词： nanoparticles structural stability Monte Carlo simulation

来源：评论

学校读者我要写书评

暂无评论

N-Body Simulation Inspired by Metaheuristics Optimization

引用

Computer Systems Science & Engineering 2022年第6期41卷 1143-1155页

作者： Muhammad Ali Ismail Maria Waqas Farah Sadiq National Center in Big Data and Cloud Computing Department of Computer and Info Systems EngineeringNED University of Engineering and TechnologyKarachiPakistan

The N-body problem in classical physics, is the calculation of force ofgravitational attraction of heavenly bodies towards each other. Solving this problem for many heavenly bodies has always posed a challenge to physicists andmathematicians. Large number of bodies, huge masses, long distances and exponentially increasing number of equations of motion of the bodies have been themajor hurdles in solving this problem for large and complex galaxies. Adventof high performance computational machines have mitigated the problem to muchextent, but still for large number of bodies it consumes huge amount of resourcesand days for computation. Conventional algorithms have been able to reduce thecomputational complexity from O n2 ð Þ to O nlogn ð Þ by splitting the space into atree or mesh network, researchers are still looking for improvements. In thisresearch work we propose a novel solution to N-body problem inspired by metaheuristics algorithms. The proposed algorithm is simulated for various time periods of selected heavenly bodies and analyzed for speed and accuracy. Theresults are compared with that of conventional algorithms. The outcomes showabout 50% time saving with almost no loss in accuracy. The proposed approachbeing a metaheuristics optimization technique, attempts to find optimal solution tothe problem, searching the entire space in a unique and efficient manner in a verylimited amount of time.

关键词： N-body problem metaheuristics optimization particle swarm optimization heavenly bodies

来源：评论

学校读者我要写书评

暂无评论

Workload Characterization and Green Scheduling on Heterogeneous Clusters 22

Workload Characterization and Green Scheduling on Heterogene...

引用

22nd International Conference on Advanced computing and Communication, ADCOM 2016

作者： Jivrajani, Aarti Raghu, Dhanya Apoorva, K.H. Phalachandra, H.L. Sitaram, Dinkar Center for Cloud Computing and Big Data PES University India

ISBN: (纸本)9781538623893

With the emergence of large, heterogeneous, shared computing clusters, their efficient use by mixed distributed workloads and tenants remains an important challenge. This paper focuses on scheduling of batches of similar jobs on the cluster of machines with similar characteristics to fully utilize the resources at the node and reduce the energy consumption of the datacenter. We use a novel algorithm to find the best fit machine in that cluster. We perform hierarchical clustering to identify common groups of jobs and common groups of machines, which is a more efficient way of clustering than the conventional k-means clustering. To estimate the energy saving, we analyze a recent Google release of scheduler request and utilization data across a large (12500+) general-purpose compute cluster over 29 days. We offer a statistical profile of the data, with several interesting discoveries regarding batching similar tasks in a heterogeneous dataset, CPU and memory consumptions, task durations, and others. © 2016 IEEE.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

Parallel implementation of w-projection wide-field imaging

引用

Science Bulletin 2019年第9期64卷 586-594页

作者： Baoqiang Lao Tao An Ang Yu Wenhui Zhang Junyi Wang Quan Guo Shaoguang Guo Xiaocong Wu Shanghai Astronomical Observatory Key Laboratory of Radio AstronomyChinese Academy of Sciences Guangxi Cooperative Innovation Center of Cloud Computing and Big Data Guilin University of Electronic Technology Guangxi Colleges and Universities Key Laboratory of Cloud Computing and Complex Systems Guilin University of Electronic Technology

w-Projection is a wide-field imaging technique that is widely used in radio synthesis arrays. Processing the wide-field big data generated by the future Square Kilometre Array(SKA) will require significant updates to current methods to significantly reduce the time consumed on data processing. data loading and gridding are found to be two major time-consuming tasks in w-projection. In this paper, we investigate two parallel methods of accelerating w-projection processing on multiple nodes: the hybrid Message Passing Interface(MPI) and Open Multi-Processing(OpenMP) method based on multicore Central Processing Units(CPUs) and the hybrid MPI and Compute Unified Device Architecture(CUDA)method based on Graphics Processing Units(GPUs). Both methods are successfully employed and operated in various computational environments, confirming their robustness. The experimental results show that the total runtime of both MPI + OpenMP and MPI + CUDA methods is significantly shorter than that of single-thread processing. MPI + CUDA generally shows faster performance when running on multiple nodes than MPI + OpenMP, especially on large numbers of nodes. The single-precision GPU-based processing yields faster computation than the double-precision processing; while the single-and doubleprecision CPU-based processing shows consistent computational performance. The gridding time remarkably increases when the support size of the convolution kernel is larger than 8 and the image size is larger than 2,048 pixels. The present research offers useful guidance for developing SKA imaging pipelines.

关键词： Radio synthesis arrays Square kilometre array Wide field imaging Parallelization w-Projection

来源：评论

学校读者我要写书评

暂无评论

Cache Characterization of Workloads in a Microservice Environment 8

Cache Characterization of Workloads in a Microservice Enviro...

引用

8th IEEE International Conference on cloud computing in Emerging Markets, CCEM 2019

作者： Athlur, Sanjith Sondhi, Nishant Batra, Sachit Kalambur, Subramaniam Sitaram, DInkar Center for Cloud Computing and Big Data Department of Computer Science PES University Bengaluru India

ISBN: (纸本)9781728163345

The advent of Microservice based architecture has lead to the obsolescence of the tedious way of building and deploying applications in a monolithic way. The number of organizations taking advantage of cloud computation and microservice architecture is steadily increasing. From the cloud providers perspective, the purpose of cloud computation is to leverage economies of scale by co-locating several workloads dynamically on the same powerful many-core servers. In this paper, we attempt to characterize cache usage and its impact on performance when multiple workloads are collocated on multicore servers. © 2019 IEEE.

关键词： Obsolescence

来源：评论

学校读者我要写书评

暂无评论

Energy efficient data center management under availability constraints 9

Energy efficient data center management under availability c...

引用

9th Annual IEEE International Systems Conference, SysCon 2015

作者： Sitaram, Dinkar Phalachandra, H.L. Gautham, S. Swathi, H.V. Tp, Sagar Center for Cloud Computing and Big Data Dept. CSE PES University Bangalore India

ISBN: (纸本)9781479959273

Due to increasing power consumption and cost, data center energy conservation has become increasingly important. As a result, a number of algorithms for optimizing compute, storage, and networking have been devised. However, these algorithms focus on job distribution based upon optimizing energy efficiency, and do not take availability into consideration. For example, if there are 3 servers, allocating workloads based only upon energy efficiency may result in consolidation of the workload into only 1 server, resulting in a single point of failure. This paper outlines the importance of availability and designs a hill climbing algorithm to prevent failure zone failure and hence also reduce the energy consumption by the datacenter. © 2015 IEEE.

关键词： Availability

来源：评论

学校读者我要写书评

暂无评论

Energy efficient VM scheduling in Reservation supported cloud data centers under availability constraints

Energy efficient VM scheduling in Reservation supported Clou...

引用

2021 International Conference on Intelligent Technologies, CONIT 2021

作者： Charan, Bhavya Goutham, K S Mampilli, Ruben John Kempaiah, Bharani Ujjaini Phalachandra, H L PES University Center for Cloud Computing and Big Data Dept of Computer Science and Engineering Bangalore India

ISBN: (纸本)9781728185835

The exponential surge in digital usage is resulting in a significant need for computational resources. This has led to businesses migrating to the cloud for benefits like usage of resources as a service, scalability, etc. Infrastructures supporting these businesses will need to conserve energy in the context of the ever-increasing size of the data centers and provide a highly available environment with mechanisms for business continuity, disaster recovery, etc. These would need to be supported at minimal costs while meeting the expected performance along with conformance to the SLAs. This paper considers a cost-efficient resource reservation based environment and evolves an approach to perform energy-efficient VM scheduling with migrations, while factoring in the network Overheads, having Availability as a constraint, and orchestrating the devices in terms of Dynamic Voltage Frequency Scaling, for optimal energy usage. Two novel algorithms are proposed: the Power and Availability Aware Best Fit Decreasing (PAABFD) allocation policy and the Power Availability Network DVFS Aware (PANDA) migration policy, when combined achieving up to 82.35% improvement in data center energy while offering an availability of 99.999% when compared with other scheduling policies. © 2021 IEEE.

关键词： Scheduling

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：