2022 IEEE 2nd International Conference on Software Engineering and Artificial Intelligence (SEAI)最新文献

Semantic Inheritance and Overloading 语义继承和重载

2022 IEEE 2nd International Conference on Software Engineering and Artificial Intelligence (SEAI) Pub Date : 2022-06-10 DOI: 10.1109/seai55746.2022.9832076

Ping Zhu, Pohua Lv, Jin Shi, Xuetao Jiang, Weiming Zou, Yirong Ma

{"title":"Semantic Inheritance and Overloading","authors":"Ping Zhu, Pohua Lv, Jin Shi, Xuetao Jiang, Weiming Zou, Yirong Ma","doi":"10.1109/seai55746.2022.9832076","DOIUrl":"https://doi.org/10.1109/seai55746.2022.9832076","url":null,"abstract":"Humanoid reasoning and computing are the crucial research objectives of computing thinking, so semantic understanding and explicit representation are the basis steps for computing thinking. However, at present, there is no mature and systematic theory and engineering technology to fully describe massive multi-dimensional semantic expressions of natural language. Then the semantic inheritance and overloading theory was proposed to describe the semantic superposition and synthesis processing of the input vocabularies in this paper. Taking the clause as the basic semantic unit, the semantics were integrated by the local semantics of the clause itself and the global semantics of the cross clauses. The semantic frameworks were represented by the core vocabulary sequence of the clause, and the unified semantic representation grammar of the semantic frameworks to explicitly describe the local semantics and global semantics was studied; From the perspective of big data engineering, according to the unified grammar, the semantic annotation was chose as the initial step, the semantic scene based on the pattern matching of semantic frameworks was divided, the implementation technologies of semantic inheritance and overloading theory between scenes on the base of the observed language representation phenomenon were put forward, and the core algorithms of machine humanoid resolving primary mathematics application problems were realized, the effectiveness of semantic inheritance and overloading theory was preliminarily verified. The advantage was that the implementation could make full use of the power of the cloud computing to do semantic annotation and semantic framework pattern matching in parallel, and explore the engineering way to achieve natural language semantic understanding and computing thinking.","PeriodicalId":290416,"journal":{"name":"2022 IEEE 2nd International Conference on Software Engineering and Artificial Intelligence (SEAI)","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116623200","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

A Object-augmented Semantic Mapping System for Indoor Mobile Robots 室内移动机器人对象增强语义映射系统

2022 IEEE 2nd International Conference on Software Engineering and Artificial Intelligence (SEAI) Pub Date : 2022-06-10 DOI: 10.1109/seai55746.2022.9832075

Xueyuan Song, Xu Liang, Zuo Zhijiang, Zhou Huaidong

引用次数: 0

G-Computation Demonstration in Estimating Causal Effects with Time-Dependent Confounding 时间相关混杂估计因果效应的g计算论证

2022 IEEE 2nd International Conference on Software Engineering and Artificial Intelligence (SEAI) Pub Date : 2022-06-10 DOI: 10.1109/seai55746.2022.9832345

Fuhao Liu, Yongmin Shuai, Xin Zhang, Yunfei Xiong, Yong Zeng

{"title":"G-Computation Demonstration in Estimating Causal Effects with Time-Dependent Confounding","authors":"Fuhao Liu, Yongmin Shuai, Xin Zhang, Yunfei Xiong, Yong Zeng","doi":"10.1109/seai55746.2022.9832345","DOIUrl":"https://doi.org/10.1109/seai55746.2022.9832345","url":null,"abstract":"Longitudinal studies, common in medical research, belong observational studies that collect data about subjects repeatedly over a period of time. In longitudinal data, exposure and confounding change over time, so longitudinal data cannot be studied with research methods that target cross-sectional data. When estimating the causal effect of time-varying exposure on outcomes of interest measured later, standard methods cannot give consistent estimates if there are time-dependent confounders. g-computation provides new ideas for solving time-dependent confounding. This article describes and demonstrates a step-by-step approach, using g-computation to adjust time-dependent confounding, and marginal structural model (MSM) to estimate the causal effect of time-varying exposure, implemented through $mathrm{R}$ code. Meanwhile, this paper briefly outlines the relevant theoretical knowledge of the method, including g-computation and time-dependent confounding, and uses the generated simulation data to test the feasibility of the method and compare the performance of different methods.","PeriodicalId":290416,"journal":{"name":"2022 IEEE 2nd International Conference on Software Engineering and Artificial Intelligence (SEAI)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116514095","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Surrogate-Assisted Task Selection for Evolutionary Multitasking Optimization 进化多任务优化中的代理辅助任务选择

2022 IEEE 2nd International Conference on Software Engineering and Artificial Intelligence (SEAI) Pub Date : 2022-06-10 DOI: 10.1109/seai55746.2022.9832367

Kaiyuan Huang, Xiaojun Wang, Yiqiao Cai

{"title":"Surrogate-Assisted Task Selection for Evolutionary Multitasking Optimization","authors":"Kaiyuan Huang, Xiaojun Wang, Yiqiao Cai","doi":"10.1109/seai55746.2022.9832367","DOIUrl":"https://doi.org/10.1109/seai55746.2022.9832367","url":null,"abstract":"In the evolution algorithm, evolutionary multi-task optimization (EMTO) is recently proposed as a novel optimization paradigm for simultaneously solving multiple optimization tasks. However, in most of the existing EMTO algorithms, each offspring is evaluated selectively for only one task that is randomly assigned. This will lead to the negative transfer if the relatedness between tasks is lower. Based on this consideration, a novel surrogate-assisted task selection (SATS) method is proposed to assign a proper task to the offspring for evaluation by a collaborative multioutput Gaussian process surrogate (CoMOGP). The main purpose of SATS is to exploit the relatedness across tasks by jointly learning a surrogate model that is used for predicting the skill factor of each offspring, which will alleviate negative transfer. By incorporating the proposed SATS into a representative EMTO, multifactorial evolution algorithm (MFEA), an improved EMTO algorithm, termed SATS-EMO, is presented. Experimental results on a suite of single-objective multitasking benchmark problems have demonstrated the effectiveness of SATS for EMTO.","PeriodicalId":290416,"journal":{"name":"2022 IEEE 2nd International Conference on Software Engineering and Artificial Intelligence (SEAI)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127709449","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Research on Battlefield-Oriented Flight Ad Hoc Network Based on Mobile Edge Computing 基于移动边缘计算的面向战场的飞行自组网研究

2022 IEEE 2nd International Conference on Software Engineering and Artificial Intelligence (SEAI) Pub Date : 2022-06-10 DOI: 10.1109/seai55746.2022.9832189

Sicong Yu, Yang Fan, Huiji Zheng, Caihong Ma

引用次数: 0

Multi-scale Context Enhancement Network for Object Detection 目标检测的多尺度上下文增强网络

2022 IEEE 2nd International Conference on Software Engineering and Artificial Intelligence (SEAI) Pub Date : 2022-06-10 DOI: 10.1109/seai55746.2022.9832140

Yanan Wang, Yingdong Ma

引用次数: 0

A Method to Evaluate the Health of OSS Projects Based on the PSR Model and Combination Weighting 基于PSR模型和组合加权的OSS项目健康度评价方法

2022 IEEE 2nd International Conference on Software Engineering and Artificial Intelligence (SEAI) Pub Date : 2022-06-10 DOI: 10.1109/seai55746.2022.9832291

Hongbing Wang, Ziming Wu

{"title":"A Method to Evaluate the Health of OSS Projects Based on the PSR Model and Combination Weighting","authors":"Hongbing Wang, Ziming Wu","doi":"10.1109/seai55746.2022.9832291","DOIUrl":"https://doi.org/10.1109/seai55746.2022.9832291","url":null,"abstract":"With the rapid development of open-source software (OSS), an increasing number of enterprises and developers have gradually joined OSS projects. OSS development has become a growing trend. For users, developers, and managers of OSS projects, understanding the health status of a project is conducive to making correct decisions and preventing the risks caused by a decline in the project's health. Therefore, an effective method is needed to evaluate the health of OSS projects. Based on the pressure state response (PSR) model, this paper propose a health evaluation model for OSS projects, defines t he healthof OSS projects from the three levels of pressure, state and response, and selects scientific, reasonable a nd representative indicators. The weight of each index is determined by the combination weighting method, which combines AHP and the entropy method. The health of the project is quantitatively analyzed, and the overall health score of a project is calculated. In addition, to verify the effectiveness of the proposed evaluation model, we conduct an empirical experiment based on real project data on the GitHub open-source platform. The experiment results and analysis show that our evaluation model can effectively reflect the health status of OSS projects.","PeriodicalId":290416,"journal":{"name":"2022 IEEE 2nd International Conference on Software Engineering and Artificial Intelligence (SEAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131080893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Image Enhancement for Rotation Sushi Plates Detection in Smart Multi-Platform Billing System 智能多平台计费系统中旋转寿司盘检测的图像增强

2022 IEEE 2nd International Conference on Software Engineering and Artificial Intelligence (SEAI) Pub Date : 2022-06-10 DOI: 10.1109/seai55746.2022.9832218

Patchariya Piya-Aromrat, Y. Limpiyakorn

引用次数: 1

Transfer Learning-Based Detection of Endometrial Cancer Lesion Regions on MRI Images 基于迁移学习的子宫内膜癌MRI病灶区域检测

2022 IEEE 2nd International Conference on Software Engineering and Artificial Intelligence (SEAI) Pub Date : 2022-06-10 DOI: 10.1109/seai55746.2022.9832165

Wei-Lung Mao, Liu Xiong, Zhifang Li, Yongping Lin

引用次数: 0

Research on Fast Handoff Algorithm of Multimedia Services in WLAN 无线局域网多媒体业务快速切换算法研究

2022 IEEE 2nd International Conference on Software Engineering and Artificial Intelligence (SEAI) Pub Date : 2022-06-10 DOI: 10.1109/seai55746.2022.9832073

Long Ma

引用次数: 0