软件智能融合系列学术报告会—智能优化方法与应用

发布时间:2020-07-10 浏览次数:25

会议时间:2020.7.17全天9:00-17:00

会议形式:腾讯会议 QQ665276832获取密码

会议ID 426 891 270 

会议主题:智能优化方法与应用

主办单位:中国仿真学会智能仿真优化与调度专业委员会

广东省计算机学会软件工程专业委员会

承办单位:华南理工大学软件学院

主持人 :黄翰

探讨智能算法与软件工程的有机融合,运用智能算法解决软件工程领域的一些典型问题,实现智能化软件测试、智能化软件开发方法、智能化软件平台等。本次论坛是软件智能融合系列学术报告会之一,聚焦智能优化方法及其在软件工程领域的若干应用。此次论坛旨在为高校、研究所以及工业界从事智能软件工程相关方向的教师和研究人员提供一次交流和学习的机会,共同探讨相关领域各方向的科研动态及发展趋势,也为了吸引更多的年轻学者加入到这个主题的研究中来。本次研讨会很荣幸地邀请到来自中国矿业大学的巩敦卫教授、汕头大学的范衠教授、北京航空航天大学的路辉教授、University of Birmingham的李密青教授、The University of Exeter的李柯教授以及华南理工大学的向毅博士等介绍他们在基于进化算法的并行程序路径覆盖测试、基于进化计算的机器人系统设计、群智能算法参数调整策略及其在调度问题中的应用、软件缺陷预测模型、基于多目标优化的软件产品线测试及最优软件产品选择等领域的一些最新研究成果。

717,让我们相聚线上交流平台,一起来探讨软件智能融合与应用的前沿课题与技术。

诚挚邀请各位专家、老师与同学参加,期待您的光临!


会议议程:

日期

时间

内容

717日(上午)

8:40-9:00

黄翰教授致辞、宣布会议开始

9:00-10:00

巩敦卫 教授(中国矿业大学)

报告题目:并行程序路径覆盖测试的进化优化方法

10:00-11:00

范衠 教授(汕头大学)

报告题目:基于进化计算的机器人系统设计自动化研究

11:00-12:00

路辉 教授(北京航空航天大学)

报告题目:群智能算法参数调整策略及在调度问题中应用


12:00-14:00

午休

717日(下午)

14:00-15:00

李密青 教授(University of Birmingham

报告题目:Many-Objective Test Suite Generation for Software Product Lines

15:00-16:00

李珂 教授(The University of Exeter

报告题目:Are You Using the Right Model for Cross-Project Defect Prediction? Empirical study and Automated Algorithm Design

16:00-17:00

向毅 博士(华南理工大学)

报告题目:基于搜索的软件产品线配置问题:模型及算法研究

718日

9:00-12:30

自由交流与讨论



附专家简介:

敦卫教授,中国矿业大学教授、博士生导师,教育部“新世纪优秀人才支持计划”入选者,甘肃省“飞天学者”讲座教授。为江苏省自动化学会副秘书长,中国人工智能学会机器学习专委会委员,中国计算机学会软件工程专委会委员,中国自动化学会大数据专委会委员,校学术委员会委员。研究方向为优化问题智能求解、智能软件工程、智能感知与控制、数据智能解析与处理。主持国家“973”计划子课题、国家重点研发计划子课题、国家自然科学基金等8项。研究成果获2017年高等学校科学研究优秀成果奖自然科学二等奖和2018年江苏省科学技术二等奖(均排名第1);获授权发明专利16项;发表中科院一、二区期刊论文60余篇,其中,IEEE TEVCTCYBTASETR等汇刊论文22篇,入选ESI1%高被引论文3篇。

报告简介:并行程序是通过多个进程交互实现复杂计算任务的程序,该程序通常包含大量路径,其路径覆盖测试非常具有挑战性。将路径覆盖测试数据生成问题转化为优化问题并采用进化优化求解,是提高路径覆盖测试效率的重要途径。报告从并行程序调度序列选择、测试数据生成问题建模与进化求解、基于知识的测试数据生成进化算子设计等方面,介绍我们新近提出的并行程序路径覆盖测试进化优化方法。最后,指出我们准备进一步研究的问题。

---------------------------------------------------------------------------------------------------------------------------------



范衠教授,工学博士,教授,博士生导师,汕头大学工学院电子信息工程系主任,广东省数字信号与图像处理技术重点实验室主任,汕头市机器人与智能制造研究院执行院长,海外高层次青年人才联谊会第一届执委会副会长。国家高层次青年人才、广东省“扬帆计划”紧缺急需人才、中国侨界贡献奖创新人才、汕头市首届优秀人才青年英才。20045月获得密西根州立大学电子与计算机工程博士学位。2004年受聘于丹麦科技大学,历任助理教授和副教授。20124月至今受聘于汕头大学,20131月至今担任汕头大学工学院电子信息工程系主任,20149月至今担任广东省数字信号与图像处理技术重点实验室主任,20185月担任汕头市机器人与智能制造研究院执行院长。

主要研究方向为:人工智能、机器人、群体智能、计算智能、设计自动化、机器学习、机器视觉。主持完成丹麦技术创新局3项国家级科技项目,培养3名博士生获得丹麦科技大学博士学位。目前已主持包括国家自然科学基金面上项目和中央军委科技委基础研究项目在内的国家和省部级科研项目7项,承担项目总经费1400多万元。共发表国际期刊会议论文150多篇,其中SCI检索论文50多篇,EI检索论文100多篇;申请专利30余项,已获授权专利8项,其中授权发明专利1项,授权实用新型专利7项,软件著作权2项;出版中文专著和英文专著各1部,代表性成果在《IEEE Transactions on Image Processing》、《IEEE Transactions on Evolutionary Computation》、《IEEE Transactions on Industrial Electronics》、《IEEE Transactions on Automation Science and Engineering》等国际顶级期刊发表。多次受邀在重要的国内国际会议(如GECOOWCCICECECOLE等)上做主题演讲。目前担任IEEE高级会员、广东省图象图形学会常务理事、中国人工智能学会智能机器人专委会执行委员、中国仿真学会智能仿真优化与调度专委会委员、中国自动化学会大数据专委会委员、广东省图象图形学会计算机视觉专委会委员、中国图象图形学学会文档图像分析与识别专委会委员、广东省科协智能制造学会联合体第一届专家委员会委员,是国家自然科学基金、教育部科技奖励、教育部长江学者等项目的评审专家。

报告简介:大力发展智能机器人产业以实现‘机器换人’已经成为继续促进我国经济发展,实现经济转型升级的必然选择。目前国内机器人在性能上普遍难以达到国外同类机器人水平,造成该现象的主要原因是我国在机器人系统的设计上缺乏一套系统化的持续优化和自动设计的方法。如何形成一套机器人系统智能设计框架,使设计的机器人系统在性能上接近、达到、并超过国际上同类产品的水平,是本报告将要探讨的一个问题。 本报告主要从以下三个方面:1.机器人系统多角度建模;2.融合进化计算和机器学习的机器人系统优化问题求解;3.机器人系统设计中的知识自动提取与应用,对机器人系统的设计自动化进行阐述。

---------------------------------------------------------------------------------------------------------------------------------


辉教授,女,北京航空航天大学电子信息工程学院,博导。多年来一直从事信息系统仿真、测试、性能评估与智能决策等技术领域的研究工作,重点以航空电子系统、无线电导航系统等为对象开展理论研究和工程研制,研制的“电子设备综合测试与模拟验证平台”、“飞行数据管理仿真系统”、“基于被测设备模型的测试描述语言”等成果应用于新舟60等实际工程。主持/参与国家级、省部级等课题40余项,发表学术论文80余篇,出版著作3部,授权发明专利和软件著作权多项。获省部级科学技术进步奖二等奖1项、省部级科学技术进步奖三等奖3项。

报告简介:工程领域中的很多实际问题,如测试任务调度问题、卫星星座构型问题等都可以被归纳为一个组合优化问题,群体智能算法是解决组合优化问题的有效手段。针对不同的实际问题,群体智能算法需要考虑实际问题特性进行适应性设计,算法参数需要根据问题特性进行自适应控制,从而提升其求解性能。报告从群智能算法的个体状态和种群状态出发,分别基于强化学习和闭环系统理论研究群智能算法的参数调整框架,从单目标优化和多目标优化的角度探讨参数控制策略。

---------------------------------------------------------------------


Dr Miqing Li(李密青)is an assistant professor at School of Computer Science at the University of Birmingham. His research is principally on multi-objective optimisation, where he focuses on developing population-based randomised algorithms (mainly evolutionary algorithms) for both general challenging problems (e.g. many-objective optimisation, constrained optimisation, robust optimisation, expensive optimisation) and specific challenging problems (e.g. those in software engineering, system engineering, product disassembly, post-disaster response, neural architecture search, reinforcement learning for games).Dr Li has published over 50 research papers in scientific journals and international conferences. Some of his papers, since published, have been amongst the most cited papers in corresponding journals such as IEEE Transactions on Evolutionary Computation, Artificial Intelligence, ACM Transactions on Software Engineering and Methodology, IEEE Transactions on Parallel and Distribution Systems, ACM Computing Surveys. His work has received the Best Student Paper Award/Best Paper Award nomination in EC mainstream conferences, CEC, GECCO, and SEAL.Dr Li is the founding chair of the IEEE CIS Task Force on Many-Objective Optimisation.

报告简介A Software Product Line (SPL) is a set of products built from a number of features, the set of valid products being defined by a feature model. Typically, it does not make sense to test all products defined by an SPL and one instead chooses a set of products to test (test selection) and, ideally, derives a good order in which to test them (test prioritisation). Since one cannot know in advance which products will reveal faults, test selection and prioritisation are normally based on objective functions that are known to relate to likely effectiveness or cost. This article introduces a new technique, the grid-based evolution strategy (GrES), which considers several objective functions that assess a selection or prioritisation and aims to optimise on all of these. The problem is thus a many-objective optimisation problem. We use a new approach, in which all of the objective functions are considered but one (pairwise coverage) is seen as the most important. We also derive a novel evolution strategy based on domain knowledge. The results of the evaluation, on randomly generated and realistic feature models, were promising, with GrES outperforming previously proposed techniques and a range of many-objective optimisation algorithms.

---------------------------------------------------------------------------------------------------------------------------------


Ke Li (李柯) is a Senior Lecturer (Associate Professor) in Computer Science at the Department of Computer Science, University of Exeter. His current research interests include the data-driven optimisation, automatic problem solving, machine learning and applications in software engineering, water engineering and biosciences. He was recently awarded a prestigious UKRI Future Leaders Fellowship. He has been founding chair of IEEE Computational Intelligence Society Task Force on Decomposition-based Techniques in EC with the EC Technical Committee. He is currently served as a Associate Editor for IEEE Transactions on Evolutionary Computation and International Journal of Machine Learning and Cybernetics.

报告简介Dat-driven defect prediction has become increasingly important in software engineering process. Since it is not uncommon that data from a software project is insufficient for training a reliable defect prediction model, transfer learning that borrows data/knowledge from other projects to facilitate the model building at the current project, namely cross-project defect prediction (CPDP), is naturally plausible. Most CPDP techniques involve two major steps, i.e., transfer learning and classification, each of which has at least one parameter to be tuned to achieve their optimal performance. This practice fits well with the purpose of automated parameter optimization. However, there is a lack of thorough understanding about what are the impacts of automated parameter optimization on various CPDP techniques. In this talk, we present the first empirical study that looks into such impacts on 62 CPDP techniques, 13 of which are chosen from the existing CPDP literature while the other 49 ones have not been explored before. We build defect prediction models over 20 real-world software projects that are of different scales and characteristics. Our findings demonstrate that: (1) Automated parameter optimization substantially improves the defect prediction performance of 77% CPDP techniques with a manageable computational cost. Thus more efforts on this aspect are required in future CPDP studies. (2) Transfer learning is of ultimate importance in CPDP. Given a tight computational budget, it is more cost-effective to focus on optimizing the parameter configuration of transfer learning algorithms (3) The research on CPDP is far from mature where it is ‘not difficult’ to find a better alternative by making a combination of existing transfer learning and classification techniques. In addition empirical study, we also propose an automated model discovery tool, dubbed BiLO-CPDP, which is the first of its kind to formulate the automated CPDP model discovery from the perspective of bi-level programming. From our experiments on 20 projects and comparison with 21 existing CPDP techniques along with Auto-Sklearn (a state-of-the-art AutoML tool), we find that BiLO-CPDP champions better prediction performance than all other 21 existing CPDP techniques on 70% of the projects, while being overwhelmingly superior to Auto-Sklearn and its single-level optimization variant on all cases.

---------------------------------------------------------------------------------------------------------------------------------


毅博士,男,华南理工大学软件学院助理研究员。2018年博士毕业于中山大学,并于同年获得ACM中国广州分会优秀博士论文奖。近三年来,主要研究智能算法及其在软件工程的应用。在相关研究领域有较充分的研究基础和较好的工作积累。目前,以第一/通讯作者发表学术论文20多篇,其中ACM/IEEE Transactions 汇刊论文8篇。标志性成果发表/录用在演化计算领域的权威期刊IEEE Transactions on Evolutionary Computation, IEEE Transactions on CyberneticsEuropean Journal of Operational Research等,以及软件工程领域的权威期刊ACM Transactions on Software Engineering and Methodology, Empirical Software Engineering和软件学报等。在演化计算与软件工程交叉学科领域的研究成果,得到国内外同行的好评和关注。代表作多次入选ESI1%高引论文。目前,主持国家自然科学基金项目、广东省自然科学基金项目、广州市科技计划项目、中国博士后科学基金项目、中央高校基本科研业务费专项基金项目等5项。

报告简介:在软件工程研究领域,很多问题本质上是优化问题。演化计算(EC)是求解这类问题的有效方法之一。本报告重点关注基于搜索的软件产品线配置问题。首先介绍该问题的背景、研究现状及数学模型,然后重点介绍如何设计有效的演化算法求解该问题及其衍生问题,即带约束和偏好的软件产品线配置问题。最后,总结EC在软件工程领域的应用研究所面临的一些挑战并给出相应的应对措施。



TOP