检索结果-内蒙古大学图书馆

8th international conference on Advances in Artificial Intelligence, ICAAI 2024

作者： Nguyen, Thanh-Hai Kim, Kyoung-Sook Kim, Kwanghoon Pio Thai Nguyen Thai Nguyen Viet Nam Contents Convergence Software Research Institute Kyonggi University Gyeonggi Suwon Korea Republic of AI Computer Science and Engineering Kyonggi University Gyeonggi Suwon Korea Republic of

ISBN: (纸本)9798400718014

This paper proposes a deep learning model for predicting the next activities in a temporal sequence of activity-events associated with a single process instance. The proposed model is based on a mixture of experts (MoE) mechanism supported by the Switch-Transformer neural network architecture. The deep learning model is trained from scratch on process enactment event log histories. The ultimate goal is to predict the next activities, generate their probabilities of occurrence, and visualize all the predicted next activities in a graphical form of temporal order representing each running case of the corresponding process model. To assess the operational effectiveness of the proposed model, we successfully conducted performance evaluations through a series of experiments on synthetic and real-life process event log datasets, which have been typically and usefully applied in other approaches in previous research works. © 2024 Copyright held by the owner/author(s).

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Non-local Refinement of Directional Intra Predictor

Non-local Refinement of Directional Intra Predictor

引用

2025 international Workshop on advanced Imaging Technology, IWAIT 2025

作者： Jeong, Hyunki Kim, Yongseong Jeon, Byeungwoo Department of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of

ISBN: (数字)9781510688131

ISBN: (纸本)9781510688124

In ongoing exploration of video compression beyond VVC capability by JVET in ISO/IEC and ITU-T, intra prediction is being further investigated to utilize more spatial neighbors to predict a current block in many different ways such as directional prediction, non-directional prediction, and offline-trained matrix-based prediction, *** that the intra prediction under the directional intra mode relies only on the local information, in this paper, we propose a non-local refinement of the predictor generated by the directional intra *** this purpose, a block vector of a neighboring block designates a non-local neighboring area for subsequent refinement of the predictor and the refinement is performed on a row and column basis by using predefined *** experiment conducted under the all intra configuration using the first 65 frames of natural video sequences of ECM-11.0 shows 0.02% gain in Y channel, 0.04% and 0.09% loss in Cb and Cr channel. © 2024 SPIE.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

research on photovoltaic power tracking based on IGWO-INC algorithm 4

Research on photovoltaic power tracking based on IGWO-INC al...

引用

4th international conference on advanced Manufacturing Technology and Electronic information, AMTEI 2024

作者： Gao, Chuang Ma, Hongwei School of Business Shanghai Dianji University Shanghai201306 China

ISBN: (数字)9781510688247

ISBN: (纸本)9781510688230

The P-U characteristic curves of PV arrays under localized shading conditions may exhibit multiple peaks. Conventional approaches are prone to encountering the local maximum power point (LMPP) and face challenges in effectively balancing the trade-off between speed and precision inherent in maximum power point tracking (MPPT) techniques. A hybrid IGWO-INC algorithm is proposed in this paper, which combines the Improved Gray Wolf (IGWO) algorithm with the conductivity incremental method (INC) to effectively search for the vicinity of the maximum power point (MPP) through velocity and position updates, thereby achieving accurate tracking of local maximum power points. The final simulation results demonstrate that the IGWO-INC algorithm enhances tracking speed and accuracy, reduces power oscillations, and ensures normal operation. The validity of the algorithm has been verified. © 2025 SPIE.

关键词： Detection and tracking algorithms Photovoltaics Optical power tracking algorithms Solar cells Particle swarm optimization computer simulations Solar energy Mathematical optimization

来源：评论

学校读者我要写书评

暂无评论

research on improved dynamic window approach based on fuzzy logic for adaptive obstacle avoidance control in unmanned surface vehicles 5

Research on improved dynamic window approach based on fuzzy ...

引用

5th international conference on Signal Processing and computer science, SPCS 2024

作者： Zhao, Xinyuan Zhao, Qi Peng, Jing Shanghai Maritime University Merchant Marine College Shanghai201306 China

ISBN: (数字)9781510686731

ISBN: (纸本)9781510686724

An adaptive improved dynamic window approach based on fuzzy logic is proposed to address the challenges of avoiding dense obstacles and the poor applicability of the traditional dynamic window approach. First, a target point traction evaluation sub-function is added to the original evaluation function. Then, fuzzy logic is integrated into the improved dynamic window approach, allowing for real-time adjustment of the weight coefficients of various evaluation sub-functions based on environmental information. This enables local dynamic path planning for unmanned surface vehicles in various scenarios. Finally, the effectiveness of the algorithm is validated through simulation experiments. © 2025 SPIE.

关键词： Unmanned surface vehicles

来源：评论

学校读者我要写书评

暂无评论

A Review of Link Prediction on Heterogeneous Networks 8th

A Review of Link Prediction on Heterogeneous Networks

引用

8th international conference on Cognitive Computing, ICCC 2024, Held as Part of the Services conference Federation, SCF 2024

作者： Mi, Rui Wang, Changbo Zhang, Liang-Jie Wu, Yirui Chen, Junyang Wang, Huan College of Informatics Huazhong Agricultural University Wuhan China Center of Health Administration and Development Studies Hubei University of Medicine Shiyan China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Hohai University Nanjing China

ISBN: (纸本)9783031779534

Link prediction is a central downstream assignment in network analysis, which denotes an attempt to assess the probability of a connection between two nodes based on observed link and node properties, which can be utilized across diverse categories of graph system, including knowledge graphs, network traffic, social networks, biological networks, etc. Heterogeneous networks usually contain diverse nodes and a variety of edges’ type, which can preserve more information than homogeneous information networks. However, the majority of researches focus on graph representation analysis of homogeneous networks. Limited research has systematically reviewed advanced techniques for link prediction and applications on Heterogeneous information Networks (HIN). Building upon this, we propose a classification summary for link prediction methods in heterogeneous information graphs. We will introduce some classical methods and some newly proposed methods for link prediction on heterogeneous graphs. We provide general technical ideas behind each method in classes and analysis performance of models. We further discuss the applications of link prediction on complex heterogeneous graphs across various domains. Additionally, the research challenges are discussed, and several possible research avenues for link prediction on heterogeneous network are pointed out. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Architecting Resilience: Digital Innovations in Humanitarian Logistics for Disaster-Ready Networks 5th

Architecting Resilience: Digital Innovations in Humanitarian...

引用

5th 5th Olympus - international conference on Supply Chain

作者： Aretoulaki, Eleni Ponis, Stavros T. Plakas, George Tzanetou, Dimitra Kitsantas, Antonios Natl Tech Univ Athens Sch Mech Engn Heroon Polytech 9 Athens 15780 Greece

ISBN: (纸本)9783031693502;9783031693519

Modern logistics networks, even under normal operating conditions intrinsically face a multitude of issues, which become even more daunting in the event of disasters and emergencies, which either disrupt existing networks by exerting extra strain or necessitate the formation of ad-hoc humanitarian logistics networks for disaster management, to alleviate the impacted areas and deliver aid to the victims. Although it is not feasible to entirely avert all disasters, it is well recognized that utilizing advanced digital technologies, including drones, big data analytics, the Internet of Things, machine learning and more, can significantly revolutionize humanitarian logistics operations implemented prior to, amidst, and following a disaster's occurrence. This paper delves into the realms of user interface design within the humanitarian logistics domain, emphasizing the pivotal role of drone and other digital technologies in refining disaster response mechanisms. It introduces an innovative humanitarian logistics platform, advocating for a design philosophy that merges scalability and modularity with user-centric navigation for diverse disaster scenarios. Through a user interface journey that evolves from conceptual designs to user-validated interfaces, this study highlights the balance between technological infrastructure and user engagement. The contribution of this research lies in its holistic design approach, blending offering a new perspective on developing humanitarian logistics platforms that are technologically advanced and closely attuned to humanitarian goals.

关键词： humanitarian logistics drones unmanned aerial vehicles design science research user interface design

来源：评论

学校读者我要写书评

暂无评论

Framework for Cloud-Based Data Management in Autonomous Vehicles

Framework for Cloud-Based Data Management in Autonomous Vehi...

引用

2025 IEEE international Students' conference on Electrical, Electronics and computer science, SCEECS 2025

作者： Pallapothu, Harshith Gopi Krishna, G. Sunil, Digvijay Teja Yadav, S. Nagasundari, S. Pes University Dept. of Computer Science & Engineering Bengaluru India Research Center for Information Security Forensics and Cyber Resilience Pes University Dept. of Computer Science & Engineering Bengaluru India

ISBN: (纸本)9798331529833

The increasing adoption of autonomous vehicles has driven the need for robust data management solutions that support real-time operations and ensure vehicle safety and efficiency. This work introduces a cloud-based framework for management of sensor data from autonomous vehicles, focusing on optimizing payload transmission rates. The framework leverages AWS IoT Core and AWS IoT Analytics to ensure efficient data flow from vehicle sensors to cloud storage. This framework demonstrates its potential for scalable deployment in real-world autonomous vehicle networks, contributing to the evolution of connected vehicle technologies and intelligent transport systems. This framework ensures reliable data transmission up to 250 payloads per second, beyond which data loss occurs. © 2025 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

AI-driven intrusion prevention system: leveraging mathematical foundations for advanced threats detection

引用

international Journal of information Technology (Singapore) 2025年 1-6页

作者： Vashistha, Avneesh Alghamdi, Tami Abdulrahman Almalki, Sultan Ahmed Ead, Waleed M. Kaur, Gaganpreet Department of Computer Science and Engineering SRM Institute of Science and Technology Delhi-NCR Campus Modinagar Ghaziabad India Computer Science Department Faculty of Computing and Information Al-Baha University Al-Baha Saudi Arabia Computer Department Applied College Najran University Najran Saudi Arabia Faculty of Computing and Information Al-Baha University Al-Baha Saudi Arabia Faculty of Computers and Artificial Intelligence Beni-Suef University Beni-Suef Egypt Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India

The given paper introduces a multi-staged AI-driven intrusion prevention system (IPS) that utilizes mathematical foundations like statistical analysis, probabilistic models, and optimization techniques to design strategic algorithms that recognize patterns as well as detect anomalies & potential attack vectors, which usually get missed out on by traditional security tools. The study focuses on the hybrid behavior that combines supervised and reinforcement learning (RL) methods to provide useful analysis of network traffic, which improves early detection of threats, whether they are known or unknown. This research demonstrates how the proposed AI-driven model can achieve a substantial decrease in the rate of false positives and improve threat detection accuracy. Thus, the given framework acts as a proactive component against today’s evolving cybersecurity threats and hence allows the creation of an efficient and responsive enterprise security framework. © Bharati Vidyapeeth's Institute of computer Applications and Management 2025.

关键词： Feedback loop Intrusion prevention Network traffic Reinforcement learning Threat detection

来源：评论

学校读者我要写书评

暂无评论

Document Storage and Retrieval with Efficient Clustering Using the Vector Space Model

Document Storage and Retrieval with Efficient Clustering Usi...

引用

2025 IEEE international Students' conference on Electrical, Electronics and computer science, SCEECS 2025

作者： Manoorkar, Jyoti Rawool, Siddhi Shinde, Shruti Shaikh, Nazaat Thaliya, Devansh I2IT Pune Department of Information Technology Pune India

ISBN: (纸本)9798331529833

The exponential growth of unstructured digital data transcends traditional document-retrieval systems wherein advanced strategies are built that will help realize improved efficiency and scalability. Here is a retrieval system that combines clustering techniques with the Vector Space Model and cosine similarity. The work retrieved in this study integrates k-means and hierarchical clustering, thus reducing search space, allowing enhanced retrieval speed and scalability. The clustering-augmented VSM has better recall and F1-scores especially for semantically complex queries compared to the BM25 model. The use of LSM trees improves indexing and can be used to manage high-dimensional data efficiently. Empirical tests confirm the effectiveness of the system, making it ideal for healthcare, finance, and legal research, where real-time and precise data retrieval is important. © 2025 IEEE.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

"Bibliometric Analysis of Possibilities, Legal and Technical Prerequisites for Establishing and Operating an international Freight-Logistic Hub" 5th

"Bibliometric Analysis of Possibilities, Legal and Technical...

引用

5th 5th Olympus - international conference on Supply Chain

作者： Sofia, Mavridou Aristotelis, Mavidis Dimitrios, Folinas Int Hellen Univ Panagioti Kanelopoulou 2 Katerini 60100 Greece

ISBN: (纸本)9783031693502;9783031693519

This study presents a comprehensive bibliometric analysis exploring the multifaceted aspects of establishing and operating an international freight logistics hub. Our research methodology encompasses four core components: network analysis, co-occurrence analysis, thematic mapping, and conceptual structure examination. This paper presents a comprehensive bibliometric analysis to explore the possibilities, legal, and technical prerequisites for establishing and operating an international Freight-Logistic Hub. Drawing on data from 2003 to 2023, the study analyses 241 documents from various sources, indicating a substantial and growing body of research in this field. The findings highlight a robust annual growth rate of 13.46% in scholarly output, significant international collaboration (21.16% of documents) and a diverse authorship base of 646 contributors. Key methodologies employed include network analysis, thematic mapping, co-occurrence analysis, and conceptual structure mapping using the Biblioshiny tool. The network analysis reveals influential authors and research clusters essential for policy engagement and strategic collaborations. Thematic mapping identifies crucial areas such as "containers," "port terminals," and "railroad yards and terminals" as Motor Themes, indicating their centrality and extensive research in hub operations. Co-occurrence analysis underscores the importance of supportive legal frameworks and technological advancements. At the same time, conceptual structure mapping highlights the role of specific technical aspects and geographical considerations in logistic hub operations. Our findings elucidate the critical legal and technical prerequisites for establishing a thriving hub and potential challenges and opportunities. The study provides valuable insights for policymakers and practitioners, emphasising the need to foster advanced technologies, comprehensive legal regulations, and international collaborations to enhance the efficiency and e

关键词： international Freight Logistics Bibliometric Analysis Legal and Technical Prerequisites Network Analysis Thematic Mapping

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：