检索结果-内蒙古大学图书馆

Observation points classifier ensemble for high-dimensional imbalanced classification

CAAI Transactions on Intelligence Technology 2023年第2期8卷 500-517页

作者： Yulin He Xu Li Philippe Fournier‐Viger Joshua Zhexue Huang Mianjie Li Salman Salloum College of Computer Science&Software Engineering Shenzhen UniversityShenzhenChina Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ) Shenzhen UniversityShenzhenChina Faculty of Information Technology Macao University of Science and TechnologyMacaoChina School of Computing National University of SingaporeSingaporeSingapore

In this paper,an Observation Points Classifier Ensemble(OPCE)algorithm is proposed to deal with High-Dimensional Imbalanced Classification(HDIC)problems based on data processed using the Multi-Dimensional Scaling(MDS)feature extraction ***,dimensionality of the original imbalanced data is reduced using MDS so that distances between any two different samples are preserved as well as ***,a novel OPCE algorithm is applied to classify imbalanced samples by placing optimised observation points in a low-dimensional data ***,optimization of the observation point mappings is carried out to obtain a reliable assessment of the unknown *** experiments have been conducted to evaluate the feasibility,rationality,and effectiveness of the proposed OPCE algorithm using seven benchmark HDIC data *** results show that(1)the OPCE algorithm can be trained faster on low-dimensional imbalanced data than on high-dimensional data;(2)the OPCE algorithm can correctly identify samples as the number of optimised observation points is increased;and(3)statistical analysis reveals that OPCE yields better HDIC performances on the selected data sets in comparison with eight other HDIC *** demonstrates that OPCE is a viable algorithm to deal with HDIC problems.

关键词： classifier ensemble feature transformation high-dimensional data classification imbalanced learning observation point mechanism

来源：评论

学校读者我要写书评

暂无评论

Review of cervical cell segmentation

引用

Multimedia Tools and Applications 2024年 1-40页

作者： Huang, Qian Zhang, Wei Chen, Yulin Chen, Junzhou Yang, Zheng College of Computer Science and Software Engineering Hohai University Nanjing China Nanjing Huiying Electronic Technology Corporation Nanjing China

Cervical cell segmentation is a significant task in medical image analysis and can be used for screening various cervical diseases. In recent years, substantial progress has been made in cervical cell segmentation techniques, leading to notable improvements in the performance of cervical cancer auxiliary diagnostic systems. This review summarizes and analyzes the recent research on cervical cell segmentation. The main contents include an introduction to cervical cell segmentation datasets, commonly used evaluation metrics, and various segmentation methods. Currently, mainstream segmentation methods can be classified into two categories: traditional and deep learning-based. Building upon this foundation, we unfold according to the context of segmentation objectives, evaluating the performance of each method in achieving specific segmentation objectives and exploring the relationships among different methods. Through this review, other researchers can clearly understand the development of cervical cell segmentation technology and future trends, and explore new methods and technologies based on integrating and sorting out existing technologies, so as to help cervical cancer auxiliary diagnosis systems achieve more accurate cell image segmentation. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Falcon Optimization Algorithm-Based Energy Efficient Communication Protocol for Cluster-Based Vehicular Networks

引用

computers, Materials & Continua 2024年第3期78卷 4243-4262页

作者： Youseef Alotaibi B.Rajasekar R.Jayalakshmi Surendran Rajendran Department of Software Engineering College of ComputingUmm Al-Qura UniversityMakkah21955Saudi Arabia Department of Electronics and Communication Engineering Sathyabama Institute of Science and TechnologyChennai600119India Department of Computer Science and Engineering Panimalar Engineering CollegeChennai600123India Department of Computer Science and Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical ScienceChennai602105India

Rapid development in Information Technology(IT)has allowed several novel application regions like large outdoor vehicular networks for Vehicle-to-Vehicle(V2V)*** networks give a safe and more effective driving experience by presenting time-sensitive and location-aware *** communication occurs directly between V2V and Base Station(BS)units such as the Road Side Unit(RSU),named as a Vehicle to Infrastructure(V2I).However,the frequent topology alterations in VANETs generate several problems with data transmission as the vehicle velocity differs with ***,the scheme of an effectual routing protocol for reliable and stable communications is *** research demonstrates that clustering is an intelligent method for effectual routing in a mobile ***,this article presents a Falcon Optimization Algorithm-based Energy Efficient Communication Protocol for Cluster-based Routing(FOA-EECPCR)technique in *** FOA-EECPCR technique intends to group the vehicles and determine the shortest route in the *** accomplish this,the FOA-EECPCR technique initially clusters the vehicles using FOA with fitness functions comprising energy,distance,and trust *** the routing process,the Sparrow Search Algorithm(SSA)is derived with a fitness function that encompasses two variables,namely,energy and distance.A series of experiments have been conducted to exhibit the enhanced performance of the FOA-EECPCR *** experimental outcomes demonstrate the enhanced performance of the FOA-EECPCR approach over other current methods.

关键词： Vehicular networks communication protocol clustering falcon optimization algorithm routing

来源：评论

学校读者我要写书评

暂无评论

A Data-Driven Analysis of software Testing Automation Challenges Using Structural Equation Modeling (SEM) Approach

引用

IEEE Access 2025年 13卷 96159-96181页

作者： Abrar, Muhammad Faisal Faran Majeed, Muhammad Saqib, Muhammad Alferaidi, Ali Razauddin University of Hail College of Computer Science and Engineering Hail55476 Saudi Arabia Kohsar University at Murree Department of Computer Science Punjab Murree47150 Pakistan University of Engineering and Technology at Peshawar Department of Software Engineering Peshawar25000 Pakistan

The adoption of automation in software testing presents challenges that can hinder its effectiveness and scalability. This study systematically investigates these challenges using a multi-phase research approach. First, a Systematic Literature Review (SLR) was conducted to identify 14 Critical Challenges (CCs) in automation adoption. Second, a questionnaire survey of 50 industry experts validated these challenges and examined their interrelationships. Finally, Structural Equation Modeling (SEM) a mathematical and statistical approach was employed to analyze correlations and uncover structural dependencies among the challenges. The SEM analysis identified five latent variables: Human Resource Constraints (HRC), Technological & Process Challenges (TPC), Financial & Resource Constraints (FRC), Security & Reliability Issues (SRI), and Future Adaptability & Scalability (FAS) that significantly influence automation adoption. Hypothesis testing revealed that HRC (-0.32), TPC (-0.45), FRC (−0.41), and SRI (−0.38) negatively impact automation success, whereas FAS (+0.51) plays a pivotal role in enabling successful adoption. Model validation through Confirmatory Factor Analysis (CFA) and Exploratory Factor Analysis (EFA) confirmed strong construct reliability and fit indices (RMSEA = 0.043, CFI = 0.95, TLI = 0.92, SRMR = 0.037). The study highlights the need for workforce training, standardized automation processes, cost-effective solutions, and security enhancements. By providing an empirically validated framework, this research contributes to both academia and industry, guiding decision-makers in optimizing automation strategies and improving software testing efficiency. © 2013 IEEE.

关键词： software testing

来源：评论

学校读者我要写书评

暂无评论

SFTCS: Multiform Semantic Fusion Based on Transformer for Code Summarization 14

SFTCS: Multiform Semantic Fusion Based on Transformer for Co...

引用

14th International Conference on software Technology and engineering, ICSTE 2024

作者： Yang, Jun Ao, Longhao Qi, Rongzhi College of Computer Science and Software Engineering Hohai University Nanjing China

ISBN: (纸本)9798350378955

Automatic code summarization aims to create co-herent natural language descriptions for code snippets. Recent studies indicate that integrating additional code representation structures improve the quality of generated summaries beyond token sequence-based approaches. Current technical research mainly concentrates on the graph structure information of code snippets. However, using a graph method makes it challenging to extract meaningful semantic information from the code snippets. To address the issue, we investigate how to learn more about code semantics and information from the perspective of code text feature representation. Consequently, we propose a novel model named SFTCS. SFTCS employs a conjoint feature fusion strategy, focusing on two types of information in code snippets: code token sequence features and FGT features based on Abstract Syntax Trees (AST) sequence and graph sequence. An N-adjacency ma-trix based on AST features is constructed, and the corresponding feature for AST block are optimized through a graph-based structure. Subsequently, a FGC decoder processes the two types of features. With the aid of an attention mechanism for feature enhancement, the SFTCS model ultimately predicts the results concretely. Evaluations on two publicly available Java datasets validate the effectiveness of SFTCS, showing its superiority over six advanced code summarization models. Ablation studies further elucidate the contributions of each component within the SFTCS model. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Leanor: A Learning-Based Accelerator for Efficient Approximate Nearest Neighbor Search via Reduced Memory Access 24

Leanor: A Learning-Based Accelerator for Efficient Approxima...

引用

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Wang, Yi Liu, Huan Yuan, Jianan Chen, Jiaxian Wang, Tianyu Ma, Chenlin Mao, Rui College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (纸本)9798400706011

Approximate Nearest Neighbor Search (ANNS) is a classical problem in data science. ANNS is both computationally-intensive and memory-intensive. As a typical implementation of ANNS, Inverted File with Product Quantization (IVFPQ) has the properties of high precision and rapid processing. However, the traversal of non-nearest neighbor vectors in IVFPQ leads to redundant memory accesses. This significantly impacts retrieval efficiency. A promising approach involves the utilization of learned indexes, leveraging insights from data distribution to optimize search efficiency. Existing learned indexes are primarily customized for low-dimensional data. How to tackle ANNS in high-dimensional vectors is a challenging *** paper introduces Leanor, a learned-index-based accelerator for the filtering of non-nearest neighbor vectors within the IVFPQ framework. Leanor minimizes redundant memory access, thereby enhancing retrieval efficiency. Leanor incorporates a dimension reduction component, mapping vectors to one-dimensional keys and organizing them in a specific order. Subsequently, the learned index leverages this ordered representation for rapid predictions. To enhance result accuracy, we conduct a thorough analysis of model errors and introduce a specialized index structure named Learned Index Forest (LIF). The experimental results show that, compared to representative approaches, Leanor can effectively filter out non-neighboring vectors within IVFPQ, leading to a substantial enhancement in retrieval efficiency. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

SRE-KGC : A Knowledge Graph Completion Model Based on Hidden Graph Structure and Relational Semantic Enhancement

SRE-KGC : A Knowledge Graph Completion Model Based on Hidden...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Lu, Sijun Xu, Guoyan Sun, Shuangyang College of Computer Science and Software Engineering Hohai University Nanjing China

ISBN: (纸本)9781665410205

Knowledge Graph Completion (KGC) endeavors to use existing knowledge graph data for predicting missing elements in triples. Recently, due to the efficiency of graph neural networks (GNNs) in capturing topological structures and the effectiveness of text descriptions in supplementing semantic information, numerous models integrating graph structures and entity descriptions have emerged. However, these approaches typically focus on aggregating neighboring feature information and overlook mining hidden structural information. Furthermore, they often append textual descriptions to entities independently without considering the semantics within specific relations. Hence, we propose the SRE-KGC model to address these challenges. First, while aggregating neighbors, we analyze and mine the hidden structure in the neighborhood from the perspective of entities and relations;then we introduced a dual-layer attention mechanism to extract the most pertinent textual information towards relations from both the relational semantic level and the neighbor semantic level respectively;finally, the two learned features are fused and sent to the decoder for scoring. Experiments demonstrate that our model delivers superior performance. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Study on the Rainfall-flood Association Pattern Database Based on Image Features 7

Study on the Rainfall-flood Association Pattern Database Bas...

引用

7th IEEE International Conference on Big Data and Artificial Intelligence, BDAI 2024

作者： Yu, Yufeng Cai, Difei Wu, Panqi Liu, Weifu Wang, Xuhang Hohai University College of Computer Science and Software Engineering Nanjing China

ISBN: (纸本)9798350352009

Precipitation images can clearly reflect the rainfall spatio-temporal features and play an important role in hydrological analysis and flood forecasting. However, it is challenging to mine the association response relationship between rainfall and flood events. This paper proposed a rainfall-flood association pattern database construction method based on rainfall image features. First, the rainfall pattern database and flood pattern database are constructed respectively through the steps of hydrological process segmentation, feature extraction, similarity measurement and cluster analysis. Additionally, association rule mining algorithm is used to conduct rainfall-flood association pattern mining and consrtuct the rainfall-flood association pattern database. The experimental results in the Jialing River basin show that the method proposed in this paper can effectively mine the rainfall-flood association pattern database and provide technical support for intelligent flood prediction based on historical scene patterns. © 2024 IEEE.

关键词： Rain

来源：评论

学校读者我要写书评

暂无评论

Leveraging computer Vision for Automatic Modulation Classification: Insights from Spectrum and Constellation Diagram Analysis 27th

Leveraging Computer Vision for Automatic Modulation Classifi...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Zhao, Wenjie Luo, Qiuming College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China

ISBN: (纸本)9783031783821

Automated modulation recognition is a challenging task in communication systems. Leveraging recent advancements in transfer learning, this paper proposes a novel method for automatic modulation recognition using transferred computer vision models. The method allows fine-tuning of the vision models to recognize modulation signals through spectrum and constellation diagrams. Experiments on the Radioml dataset demonstrate that the proposed method outperforms recent traditional methods by 8.97%, with an average accuracy of 0.5732. An ablation study confirms the effectiveness of using spectrum and constellation diagrams. This study verifies the feasibility of transferring vision models to AMC tasks. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Signal modulation

来源：评论

学校读者我要写书评

暂无评论

Variable Length Motif Mining Method based on Suffix Array Index 3

Variable Length Motif Mining Method based on Suffix Array In...

引用

3rd International Conference on Artificial Intelligence, Human-computer Interaction and Robotics, AIHCIR 2024

作者： Wang, Jimin Zhu, Ying Sun, Jiahao College of Computer Science and Software Engineering Hohai University Nanjing China

ISBN: (纸本)9798331534035

Existing time series variable-length motif mining algorithms based on suffix arrays suffer from long running times and are prone to premature termination of matching due to variations in individual characters, which hampers the discovery of longer motifs. To address these issues, we propose a novel time series variable-length motif mining algorithm based on suffix array indexing. This algorithm employs PAA and SAX methods for the symbolic representation of time series data, while the DC3 algorithm is utilized for the rapid construction of suffix arrays. Similarity matching is performed based on edit distance, enabling the extraction of variable-length motifs. This approach facilitates the identification of longer motifs with an edit distance less than specified parameters. Experimental results demonstrate that, compared to representative algorithms, our method significantly enhances mining accuracy, maximizes motif length, and improves time efficiency. © 2024 IEEE.

关键词： Indexing (materials working)

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：