检索结果-内蒙古大学图书馆

Flight Delay Prediction Based on Gradient Boosting Ensemble Techniques

学校读者我要写书评

暂无评论

Flight Delay Prediction Based on Gradient Boosting Ensemble ...

International Conference on Open Source Systems and Technologies (ICOSST)

作者： Rahemeen Khan Salas Akbar Tooba Ali Zahed Department of Software Engineering Bahria University Karachi Pakistan Department of Computer Science Bahria University Karachi Pakistan

ISBN: (纸本)9781665464789

In recent years, the volume of airline transportation has increased with the rapid development of aviation. With an increased demand for flights, aviation is confronted with the issue of flight delays, which becomes a series of issues that must be addressed efficiently. Correct flight delay prediction can improve airport operations efficiency and passenger travel comfort. The current study uses Gradient boosting ensemble models to build a machine learning flight delay prediction model. The Airline dataset was subjected to three different gradient boosting techniques: CatBoost, LightGBM, XGBoost, and Decision tree. to validate the performance and efficiency of the proposed method, a comparative analysis between the top performed Boosting techniques with other Ensemble Techniques is performed. CatBoost improves prediction accuracy while maintaining stability, according to the comparison results on the given dataset.

关键词： Atmospheric modeling Transportation Predictive models Boosting Airports Stability analysis Delays

Internet of Robotic Things: Current Technologies and applications

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Samara, Ghassan Hussein, Abla Matarneh, Israa Abdullah Alrefai, Mohammed Al-Safarini, Maram Y. Computer Science Department Zarqa University Zarqa Jordan Software Engineering Department Zarqa University Zarqa Jordan

The Internet of Robotic Things (IoRT) is a new domain that aims to link the IoT environment with robotic systems and technologies. IoRT connects robotic systems, connects them to the cloud, and transfers critical information as well as knowledge exchange to conduct complicated and intricate activities that a human cannot readily perform. The pertinent notion of IoRT has been discussed in this paper, along with the issues that this area faces on a daily basis. Furthermore, technological applications have been examined in order to provide a better understanding of IoRT and its current development phenomenon. The study describes three layers of IoRT infrastructure: network and control, physical, and service and application layer. In the next section, IoRT problems have been presented, with a focus on data processing and the security and safety of IoRT technological systems. In addition to discussing the difficulties, appropriate solutions have been offered and recommended. IoRT is regarded as an essential technology with the ability to bring about a plethora of benefits in smart society upon adoption, contributing to the generation and development of smart cities and industries in the near future. © 2022, CC BY.

关键词： Internet of things

Categorical Data Clustering via Value Order Estimated Distance Metric Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Yiqun Zhao, Mingjie Jia, Hong Lu, Yang Li, Mengke Cheung, Yiu-Ming School of Computer Science and Technology Guangdong University of Technology Guangzhou China College of Electronics and Information Engineering Shenzhen University Shenzhen China Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics Xiamen University China School of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Computer Science Hong Kong Baptist University Hong Kong

Categorical data composed of qualitative valued attributes are ubiquitous in machine learning tasks. Due to the lack of well-defined metric space, categorical data distributions are difficult to be intuitively understood. Clustering is a popular data analysis technique suitable for data distribution understanding. However, the success of clustering often relies on reasonable distance metrics, which happens to be what categorical data naturally lack. This paper therefore introduces a new finding that the order relation among attribute values is the decisive factor in clustering accuracy, and is also the key to understanding categorical data clusters, because the essence of clustering is to order the clusters in terms of their admission to samples. To obtain the orders, we propose a new learning paradigm that allows joint learning of clusters and the orders. It alternatively partitions the data into clusters based on the distance metric built upon the orders and estimates the most likely orders according to the clusters. The algorithm achieves superior clustering accuracy with a convergence guarantee, and the learned orders facilitate the understanding of the non-intuitive cluster distribution of categorical data. Extensive experiments with ablation studies, statistical evidence, and case studies have validated the new insight into the importance of value order and the method proposition. The source code is temporarily opened in https://***/r/OCL-demo. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

Navy STEM Challenges: Innovative Labs and Activities with SONAR

学校读者我要写书评

暂无评论

Navy STEM Challenges: Innovative Labs and Activities with SO...

Frontiers in Education (FIE) Conference

作者： Joni Corbin Joni M. Lakin Sathish Akula Cheryl Seals Edward W. Davis Department of Educational Studies The University of Alabama Tuscaloosa AL USA Department of Computer Science and Software Engineering Auburn University Auburn AL USA Department of Mechanical Engineering Auburn University Auburn AL USA

Increasingly, high school students express interest in careers that have purpose and “make a difference”. Furthermore, students from minority racial and linguistic backgrounds may be more interested in careers that offer meaning beyond income or job security. Given these diverse career values, STEM education activities that leverage the motivations and personal values of students to promote learning have the potential to significantly impact student interest and knowledge of engineering careers. To broaden participation in engineering, therefore, a collaborative team-comprised of engineering faculty, education faculty, and high school science teachers-developed a curriculum for formal and informal high school education that aligned with the diverse motivations and life goals of Generation Z students in our predominantly rural region.

关键词：

Multi-Camera Multi-Object Tracking on the Move via Single-Stage Global Association Approach

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Nguyen, Pha Quach, Kha Gia Duong, Chi Nhan Phung, Son Lam Le, Ngan Luu, Khoa Computer Science and Computer Engineering Department University of Arkansas Fayetteville United States Computer Science and Software Engineering Department Concordia University MontrealQC Canada Faculty of Engineering and Information Sciences University of Wollongong NSW Australia

The development of autonomous vehicles generates a tremendous demand for a low-cost solution with a complete set of camera sensors capturing the environment around the car. It is essential for object detection and tracking to address these new challenges in multi-camera settings. In order to address these challenges, this work introduces novel Single-Stage Global Association Tracking approaches to associate one or more detection from multi-cameras with tracked objects. These approaches aim to solve fragment-tracking issues caused by inconsistent 3D object detection. Moreover, our models also improve the detection accuracy of the standard vision-based 3D object detectors in the nuScenes detection challenge. The experimental results on the nuScenes dataset demonstrate the benefits of the proposed method by outperforming prior vision-based tracking methods in multi-camera settings. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

Modeling and Analysis for the Propagation of DDoS Attacks in Microgrid System

学校读者我要写书评

暂无评论

Modeling and Analysis for the Propagation of DDoS Attacks in...

IEEE International Symposium on Dependable, Autonomic and Secure Computing (DASC)

作者： Lei Xiong Qichao Xu Dongfeng Fang Hui Zeng School of Mechatronic Engineering and Automation Shanghai University Shanghai China Department of Computer Science and Software Engineering California Polytechnic State University San Luis Obispo CA USA

With the development and progress of electric power technology and information technology, microgrid has become an important and indispensable part of smart grid. The cyber-security of microgrids has a significant impact on the stability and security of smart grids. Distributed denial-of-service (DDoS) attack as one of the common types of cyberattacks in microgrids has formed a considerable threat to the network security of microgrids. In a DDoS event, attackers first use malware to infect few nodes in the microgrid and the infected nodes can generate large-scale malware propagation in the system. These infection lays the foundation for the flood attacks. Therefore, this paper establishes a model to analyse the DDoS attack propagation in microgrid. Firstly, this paper establishs a dynamic model based on the epidemiological theory to describe the propagation dynamics of DDoS attack in microgrid. Then we go on to compute the attack threshold $(R_{0})$ of the model and prove the stability of equilibrium point. Finally we carry out the experimental simulation based on the model, and the experimental results show that the proposed model can reflect the propagation of DDoS attack in microgrid effectively.

关键词：

Advancing Medical Innovation through Blockchain-Secured Federated Learning for Smart Health

学校读者我要写书评

暂无评论

IEEE Journal of Biomedical and Health Informatics 2025年 PP卷 PP页

作者： Khan, Salabat Khan, Mansoor Khan, Muhammad Asghar Wang, Lu Wu, Kaishun Qilu Institute of Technology School of Computer and Information Engineering Jinan China Qilu Institute of Technology School of Intelligent Manufacturing and Control Engineering Jinan China Prince Mohammad Bin Fahd University Department of Electrical Engineering P.O. Box 1664 Al-Khobar31952 Saudi Arabia Shenzhen University College of Computer Science and Software Engineering Shenzhen China Thrust Guangzhou China

The rapid digitization of healthcare systems has led to a vast accumulation of electronic medical records (EMRs), offering an invaluable source of patient data that can significantly advance medical research and improve patient care. However, sharing EMRs for research purposes presents challenges, particularly concerning data privacy, security, and the limitations of traditional centralized data-sharing models. This paper introduces a novel approach that leverages blockchain technology to facilitate federated learning with EMRs, thereby addressing these challenges. Federated learning enables multiple institutions to collaboratively train a robust machine learning model without sharing raw data, preserving privacy and security. By integrating blockchain, this framework enhances data integrity, immutability, and trust, all in a decentralized environment. The blockchain serves as a transparent and secure ledger, recording model updates and aggregating them through a consensus-based mechanism. Smart contracts further enforce data usage policies, allowing only authorized access and maintaining control over data ownership and sharing. This approach empowers medical researchers and institutions to collaborate more effectively, accelerating the discovery of treatments, advancements in personalized medicine, and insights into rare diseases. It also enables patients to contribute to medical research while retaining control over their personal data, fostering a patient-centered approach to healthcare innovation. Experimental results confirm the efficacy and efficiency of this blockchain-enabled federated learning framework, highlighting its potential to transform medical research and adhere to stringent privacy and security standards. This study emphasizes the pivotal role of blockchain in enhancing big data analytics within healthcare, paving the way for improved collaboration, innovation, and patient outcomes. © 2025 IEEE.

关键词： Federated learning

Relationship between factors influencing the software development process and software defects

学校读者我要写书评

暂无评论

Relationship between factors influencing the software develo...

IEEE International Conference on Dependable Systems, Services and Technologies (DESSERT)

作者： Oleksandr Gordieiev Daria Gordieieva Austen Rainer Olga Pishchukhina Department of Software engineering Lutsk National Technical University Lutsk Ukraine School of Electronics Electrical Engineering and Computer Science Queen’s University Belfast Belfast United Kingdom Department of Computer Engineering and Cybersecurity Lutsk National Technical University Lutsk Ukraine

Poor software quality can lead to crashes, failures or downtime, the consequences of which may be lost profits, financial costs, leakage or loss of data, accidents, human casualties, material losses or environmental disasters. The total cost of poor software quality for IT companies in the USA is estimated at ${\$}$2.41 trillion per year and tends to increase. Among the identified costs, the cost of unsuccessful projects is estimated at ${\$}$260 billion, and the total cost of operational failures caused by poor quality software is estimated at ${\$}$1.81 trillion. Late finding and fixing of software defects directly affects the success of the project as a whole, since it significantly increases the cost and development time, and affects its quality. This paper discussed the relationship between factors affecting the software development process and various groups of defects. It has been found that the leading groups of defects affecting the software quality are the defects in software requirements and defects in the design of software interfaces for human-computer interaction with the total percentage of influence of 33.3%.

关键词：

Joint Admission Control and Resource Allocation of Virtual Network Embedding via Hierarchical Deep Reinforcement Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Tianfu Shen, Li Fan, Qilin Xu, Tong Liu, Tongliang Xiong, Hui Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science University of Science and Technology of China Hefei230027 China The School of Big Data and Software Engineering Chongqing University ChinaScience Chongqing401331 China JD Explore Academy The UBTECH Sydney Artificial Intelligence Centre The School of Information Technologies Faculty of Engineering and Information Technologies The University of Sydney DarlingtonNSW2008 Australia Thrust of Artificial Intelligence Nansha Guangdong Guangzhou511400 China The Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong

As an essential resource management problem in network virtualization, virtual network embedding (VNE) aims to allocate the finite resources of physical network to sequentially arriving virtual network requests (VNRs) with different resource demands. Since this is an NP-hard combinatorial optimization problem, many efforts have been made to provide viable solutions. However, most existing approaches have either ignored the admission control of VNRs, which has a potential impact on long-term performances, or not fully exploited the temporal and topological features of the physical network and VNRs. In this paper, we propose a deep Hierarchical Reinforcement Learning approach to learn a joint Admission Control and Resource Allocation policy for VNE, named HRL-ACRA. Specifically, the whole VNE process is decomposed into an upper-level policy for deciding whether to admit the arriving VNR or not and a lower-level policy for allocating resources of the physical network to meet the requirement of VNR through the HRL approach. Considering the proximal policy optimization as the basic training algorithm, we also adopt the average reward method to address the infinite horizon problem of the upper-level agent and design a customized multi-objective intrinsic reward to alleviate the sparse reward issue of the lower-level agent. Moreover, we develop a deep feature-aware graph neural network to capture the features of VNR and physical network and exploit a sequence-to-sequence model to generate embedding actions iteratively. Finally, extensive experiments are conducted in various settings, and show that HRL-ACRA outperforms state-of-the-art baselines in terms of both the acceptance ratio and long-term average revenue. Our code is available at https://***/GeminiLight/hrl-acra. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning