检索结果-内蒙古大学图书馆

Graph Convolutional Network Combined with Semantic Feature Guidance for Deep Clustering

Tsinghua science and Technology 2022年第5期27卷 855-868页

作者： Junfen Chen Jie Han Xiangjie Meng Yan Li Haifeng Li Key Laboratory of Machine Learning and Computational Intelligence of Hebei Province the College of Mathematics and Information ScienceHebei UniversityBaoding 071002China School of Applied Mathematics Beijing Normal University ZhuhaiZhuhai 519087China Department of Computer Teaching Hebei UniversityBaoding 071002China

The performances of semisupervised clustering for unlabeled data are often superior to those of unsupervised learning,which indicates that semantic information attached to clusters can significantly improve feature representation *** a graph convolutional network(GCN),each node contains information about itself and its neighbors that is beneficial to common and unique features among *** these findings,we propose a deep clustering method based on GCN and semantic feature guidance(GFDC) in which a deep convolutional network is used as a feature generator,and a GCN with a softmax layer performs clustering ***,the diversity and amount of input information are enhanced to generate highly useful representations for downstream ***,the topological graph is constructed to express the spatial relationship of *** a pair of datasets,feature correspondence constraints are used to regularize clustering loss,and clustering outputs are iteratively *** external evaluation indicators,i.e.,clustering accuracy,normalized mutual information,and the adjusted Rand index,and an internal indicator,i.e., the Davidson-Bouldin index(DBI),are employed to evaluate clustering *** results on eight public datasets show that the GFDC algorithm is significantly better than the majority of competitive clustering methods,i.e.,its clustering accuracy is20% higher than the best clustering method on the United States Postal Service *** GFDC algorithm also has the highest accuracy on the smaller Amazon and Caltech ***,DBI indicates the dispersion of cluster distribution and compactness within the cluster.

关键词： self-supervised clustering graph convolutional network feature correspondence semantic feature guidance confusion matrix evaluation indicator

来源：评论

学校读者我要写书评

暂无评论

The Implementation of Artificial Intelligence Tools In Retail Sector Among Consumers - A New Evolution Traditional to Morden

The Implementation of Artificial Intelligence Tools In Retai...

引用

2024 IEEE International Conference on Electronic Systems and Intelligent Computing, ICESIC 2024

作者： Jenefa, Leena Ashok Kumar, S. Yiong, Bibiana Lim Chiu Jayakumar, M. Lenin Lokesh, B. Sakthivel, M. Hindustan Institute of Technology and Science School of Management Chennai India Swinburne University of Technology Sarawak Campus Learning and Teaching Unit Malaysia Vel Tech Rangarajan Dr.Sagunthala R and D Institute of Science and Technology Department of Management Studies Chennai India Vel Tech High Tech Dr. Rangarajan Dr.Sakunthala Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331522988

AI technologies may serve numerous functions in entire retail sector in value chain, and employ the employees for the job done by using to implement AI operations in the value chain. Because of the increasing degree of competition in the retail industry, merchants must now provide higher-quality services and prioritize their clients more than ever before. Retailers have increasingly adopted AI-based solutions to study new potential in the retail industry. The focus of the research is to know the people mind set to use the digital sectors. Performance expectation refers to consumers' belief that technology would improve productivity and effectiveness in reaching goals. The Indian retail sector has emerged as one of the most rapidly increasing industries. The findings show the influence are favorably connected to performance expectation, but not correlated with anthropomorphism. Retailers are always seeking to unleash the industry's true potential by using cutting-edge technologies such as artificial intelligence-based data analytics, CRM systems. © 2024 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Unlocking Maternal Outcome Prediction Potential: A Comprehensive Analysis of the ConvXGB Model Integrating XGBoost and Deep Learning

Research Square

引用

Research Square 2024年

作者： Nwokoro, Chukwudi Obinna Akinnuwesi, Boluwaji Ade Shastri, Sourabh Uzoka, Faith-Michael Inyang, Udoinyang G. Eyoh, Imo J. Duke, Onyeabochukwu Augustine Nwokoro, Kelechi Cynthia Joseph, Kingsley U. Department of Computer Science Faculty of Computing University of Uyo Nigeria Department of Computer Science Faculty of Science and Enginerring Univeristy of Eswatini Kwaluseni South Africa Department of Computer Science and IT University of Jammu Jammu and Kashmir Kathua184104 India Mathematics and Computing Department Mount Royal University Calgary Canada Department of Obstetrician and Gynaecologist University of Nigeria Teaching hospital Enugu state Nigeria Department of Paediatrics University of Port-Harcourt Teaching Hospital River State Nigeria

The significance of maternal health cannot be overemphasized, and the ability to predict maternal outcomes accurately is critical to ensuring the well-being of both mothers and infants. This study presents ConvXGB, a novel predictive model that utilizes a combination of XGBoost, a potent gradient boosting algorithm, and deep learning to extract intricate features. The objective is to enhance precision and robustness of maternal outcome predictions. The study sourced diverse maternal health data from the southern region of Nigeria and implemented Synthetic Minority Oversampling Technique (SMOTE) to address any dataset imbalances. Results obtain demonstrate a significant improvement in model performance, with an accuracy rate of 97.96% across various maternal outcome classes. The recommendations from this study highlight the potential of ConvXGB in advancing maternal health predictive analytics, supporting informed clinical decision-making, and improving resource allocation. Further studies are warranted to explore the broader applicability of ConvXGB in different healthcare domains through outcome analyses and methodological advancements. © 2024, CC BY.

关键词： Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

A System for Network Asset Discovery and Localization Using Edge Computing Drones

A System for Network Asset Discovery and Localization Using ...

引用

World Congress on Computing and Communication Technologies (WCCCT)

作者： Zhe Zhang Yingjie Wang Guoliang Hu Hongjie Fan Songtao Ye School of Computer Science Xiangtan University Xiangtan China Hunan Branch of National Computer Network Emergency Response Technical Team/Coordination Center of China Changsha China The Department of Science and Technology Teaching China University of Political Science and Law Beijing China

ISBN: (数字)9798331512620

ISBN: (纸本)9798331512637

As network technologies rapidly advance, complexity in network asset management have become increasingly evident. Traditional methods protect network assets by segregating external and internal networks. However, this approach increases management complexity and brings potential security risks. Additionally, existing network mapping tools often lack the ability to accurately locate network assets. This limitation prevents administrators from easily identifying the geographic location of network assets. As a result, effective network asset management is hindered. To address these challenges, this study introduces an automated network mapping solution. The solution combines drone with edge computing devices. Drones with edge computing devices use active routers as access points for nighttime mapping. This approach overcomes the limitations of traditional methods and provides a novel idea for managing network assets.

关键词： Location awareness Protocols Smart cities Network topology Threat assessment Real-time systems Asset management Complexity theory Drones Edge computing

来源：评论

学校读者我要写书评

暂无评论

Learning double balancing representation for heterogeneous dose–response curve estimation

引用

Neural Networks 2025年 189卷 107600页

作者： Zhu, Minqin Wu, Anpeng Li, Haoxuan Xiong, Ruoxuan Li, Bo Wu, Fei Kuang, Kun College of Computer Science and Technology Zhejiang University China Center for Data Science Peking University China Department of Quantitative Theory and Methods Emory University United States School of Economics and Management Tsinghua University China

Estimating the individuals’ potential response to varying treatment doses is crucial for decision-making in areas such as precision medicine and management science. Most recent studies predict counterfactual outcomes by learning a covariate representation that is independent of the treatment variable. However, such independence constraints neglect much of the covariate information that is useful for counterfactual prediction, especially when the treatment variables are continuous. To tackle the above issue, in this paper, we first theoretically demonstrate the importance of the balancing and prognostic representations for unbiased estimation of the heterogeneous dose–response curves, that is, the learned representations are constrained to satisfy the conditional independence between the covariates and both of the treatment variables and the potential responses. Based on this, we propose an end-to-end Contrastive balancing Representation learning Network (CRNet) and a three-stage Weighted Double Balancing Network (WDBN) using a partial distance measure, for estimating the heterogeneous dose–response curves without losing the continuity of treatments. Extensive experiments are conducted on synthetic and real-world datasets demonstrating that our proposal significantly outperforms previous methods. Code is available at: https://***/euzmin/Contrastive-Balancing-Representation-Network-CRNet. © 2025 Elsevier Ltd

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Queue Modelling and Jitter Control in Mobile Ad Hoc Networks 1

Queue Modelling and Jitter Control in Mobile Ad Hoc Networks

引用

1st Zimbabwe Conference of Information and Communication Technologies, ZCICT 2022

作者： Nyambo, Benny M. Janssens, Gerrit K. Marufu, Hillary Munyaradzi, Michael Mapako, Bernard Dzinavatonga, Kaitano Zimbabwe Open University Faculty of Technology Harare Zimbabwe Hasselt University Department Quantitative Methods Diepenbeek Belgium University of Zimbabwe Computer Science Department Harare Zimbabwe Zimbabwe Open University Faculty of Science Harare Zimbabwe

ISBN: (纸本)9781665475761

Jitter in multimedia traffic is mainly introduced by variations in network characteristics. Ifjitter is so significant in the application that is receiving, this can result in a degraded performance in real-time multimedia communications applications. Jitter causes inaudible audio or unclear video which can be undesirable and uncomfortable to the user. Buffers are often employed to temporarily to store arriving packets before playing them at equal intervals to curb and minimize jitter. Jitter for voice packets should not exceed 20-50 milliseconds within a given stream. This paper proposes a method to reducejitter in intermediate nodes is proposed, such that when the packets arrive at the receiving end, there would be little or nojitter to process in the de-jitter buffer. We analyze M/G/1 nonpreemptive and pre-emptive resume priority queuing in the intermediate node and analyze how these models will affect delay and jitter. We found out that preemptive priority queuing performs better but almost the same to non-preemptive priority queuing. Both Priority based queues performed much better than the First in First out queue. © 2022 IEEE.

关键词： Jitter

来源：评论

学校读者我要写书评

暂无评论

Discrete Population Competition Model of Poisonous Weed Invasion and Spatial Distribution 3

Discrete Population Competition Model of Poisonous Weed Inva...

引用

3rd International Conference on Modeling, Simulation, Optimization and Algorithm, ICMSOA 2021

作者： Liu, Hua Li, Yexuan Wei, Yumei Ming, M.A. Ma, Gang School of Mathematics and Computer Science Northwest Minzu University GanSu LanZhou China Department of Experimental Teaching Northwest Minzu University GanSu LanZhou China

Poisonous weeds invade ecosystems and compete with edible forage grassland, changing the population spatial distribution. In this paper, a discrete population competition model for the interaction between poisonous weeds and edible forage grass is established, and a diffusion coefficient to describe the invasion and diffusion effect of poisonous weeds is introduced. By using cellular automata methods, the influence of invasive diffusion of poisonous weeds on the spatial distribution of poisonous weed and edible forage populations is simulated. These findings indicated that the invasion of poisonous weeds affected the ecological distribution of grassland, and that the spatial distribution of poisonous weeds also changed from initial uniform distribution to aggregated distribution. © Published under licence by IOP Publishing Ltd.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Efficient handling of ACL policy change in SDN using reactive and proactive flow rule installation ( vol 14 , 14976 , 2024 )

引用

SCIENTIFIC REPORTS 2024年第1期14卷 1-19页

作者： Hussain, Mudassar Amin, Rashid Gantassi, Rahma Alshehri, Asma Hassan Frnda, Jaroslav Raza, Syed Mohsan Department of Computer Science and Creative Technologies Global College of Engineering and Technology CPO Ruwi 112 P.O Box 2546 Muscat Sultanate of Oman Department of Computer Science and IT University of Chakwal Chakwal 48800 Pakistan Department of Computer Science University of Engineering and Technology Taxila 47050 Pakistan Department of Electrical Engineering Chonnam National University Gwangju 61186 South Korea Department of Computer Science College of Computer Engineering and Science Prince Sattam Bin Abdulaziz University Alkharj 16273 Saudi Arabia Department of Quantitative Methods and Economic Informatics Faculty of Operation and Economics of Transport and Communications University of Zilina 01026 Zilina Slovakia Department of Telecommunications Faculty of Electrical Engineering and Computer Science VSB Technical University of Ostrava 70800 Ostrava Czech Republic SAMOVAR Telecom SudParis Institut Polytechnique de Paris 91120 Paris France

Software-defined networking (SDN) is a pioneering network paradigm that strategically decouples the control plane from the data and management planes, thereby streamlining network administration. SDN's centralized network management makes configuring access control list (ACL) policies easier, which is important as these policies frequently change due to network application needs and topology modifications. Consequently, this action may trigger modifications at the SDN controller. In response, the controller performs computational tasks to generate updated flow rules in accordance with modified ACL policies and installs flow rules at the data plane. Existing research has investigated reactive flow rules installation that changes in ACL policies result in packet violations and network inefficiencies. Network management becomes difficult due to deleting inconsistent flow rules and computing new flow rules per modified ACL policies. The proposed solution efficiently handles ACL policy change phenomena by automatically detecting ACL policy change and accordingly detecting and deleting inconsistent flow rules along with the caching at the controller and adding new flow rules at the data plane. A comprehensive analysis of both proactive and reactive mechanisms in SDN is carried out to achieve this. To facilitate the evaluation of these mechanisms, the ACL policies are modeled using a 5-tuple structure comprising Source, Destination, Protocol, Ports, and Action. The resulting policies are then translated into a policy implementation file and transmitted to the controller. Subsequently, the controller utilizes the network topology and the ACL policies to calculate the necessary flow rules and caches these flow rules in hash table in addition to installing them at the switches. The proposed solution is simulated in Mininet Emulator using a set of ACL policies, hosts, and switches. The results are presented by varying the ACL policy at different time instances, inter-packet de

关键词： ACL policy change Management Proactive flow rule installation Reactive flow rule installation SDN Security

来源：评论

学校读者我要写书评

暂无评论

Large Language Models with Human-In-The-Loop Validation for Systematic Review Data Extraction

arXiv

引用

arXiv 2025年

作者： Schroeder, Noah L. Jaldi, Chris Davis Zhang, Shan Department of Computer & Information Science & Engineering University of Florida GainesvilleFL United States Department of Computer Science & Engineering Wright State University DaytonOH United States School of Teaching and Learning University of Florida GainesvilleFL United States

Systematic reviews are time-consuming endeavors. Historically speaking, knowledgeable humans have had to screen and extract data from studies before it can be analyzed. However, large language models (LLMs) hold promise to greatly accelerate this process. After a pilot study which showed great promise, we investigated the use of freely available LLMs for extracting data for systematic reviews. Using three different LLMs, we extracted 24 types of data, 9 explicitly stated variables and 15 derived categorical variables, from 112 studies that were included in a published scoping review. Overall we found that Gemini 1.5 Flash, Gemini 1.5 Pro, and Mistral Large 2 performed reasonably well, with 71.17%, 72.14%, and 62.43% of data extracted being consistent with human coding, respectively. While promising, these results highlight the dire need for a human-in-the-loop (HIL) process for AI-assisted data extraction. As a result, we present a free, open-source program we developed (AIDE) to facilitate user-friendly, HIL data extraction with LLMs. Copyright © 2025, The Authors. All rights reserved.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Population-Based Novelty Searches Can Converge 34th

Population-Based Novelty Searches Can Converge

引用

34th International Florida Artificial Intelligence Research Society Conference, FLAIRS-34 2021

作者： Wiegand, R. Paul Department of Computer Science & Quantitative Methods Winthrop University Rock HillSC United States

Novelty search is a powerful tool for finding sets of complex objects in complicated, open-ended spaces. Recent empirical analysis on a simplified version of novelty search makes it clear that novelty search happens at the level of the archive space, not the individual point space. The sparseness measure and archive update criterion create a process that is driven by a clear pair of objectives: spread out to cover the space, while trying to remain as efficiently packed as possible driving these simplified variants to converge to an ɛ-net in the sense defined by k Nearest Neighbor theory. Among the simplifications was omission of a population: the archive itself served as both the potential candidate set solution, as well as the source of parents in the evolutionary search, which has the potential to fundamentally hamstring the search. In this paper, we relax this crucial assumption, generalizing the previous simplified novelty search so that a traditional population and (µ, λ) dynamics are used to produce new search points, and the population and the archive are updated separately. We show empirically that it still possible to converge, and that it can be even more likely to do so. © 2020, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Nearest neighbor search

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：