Project FMEA for Recognizing Difficulties in Machine Learning Application System Development
Project FMEA for Recognizing Difficulties in Machine Learning Application System Development
复制标题
DOI：
10.23919/picmet53225.2022.9882797
复制
发表时间：
2022-08
期刊：
影响因子：
--
通讯作者：
N. Uchihira
中科院分区：
文献类型：
--
作者：
N. Uchihira
数字化转型（DX）正在各行各业中蔓延。人工智能，特别是机器学习，对于有效使用DX中收集和存储的数据是不可避免的，并且利用机器学习的系统已经在各个行业和公司中开发出来。机器学习应用系统的开发与传统的IT系统开发有很多不同的难点。因此，软件工程（特别是项目管理）的MLAS成为这些天来最重要的问题之一。我们根据各种文献和访谈对MLAS开发的难点进行了分类，并创建了一个由12个类别组成的难度图。这张难度图的独特之处在于介绍了难度与双重MLAS开发过程（实施过程和开发过程）之间的关系。然后，我们提出了一种基于MLAS项目FMEA（故障模式影响分析）的利益相关者之间的表达和共享这些困难的方法。所提出的方法进行评估，使用两个说明性的MLA的例子。
Digital Transformation (DX) is spreading across all industries. AI, especially machine learning, is inevitable for effective use of data collected and stored in DX, and systems that utilize machine learning have been developed in various industries and companies. The development of machine learning application systems (MLASs) has many difficulties different from the traditional IT system development. Therefore, software engineering (especially project management) for MLASs becomes one of the most important issues in these days. We classified the difficulties of MLAS development based on various documents and interviews, and created a difficulty map consisting of 12 categories. Unique features of this difficulty map include introduction of relationship between difficulties and the dual MLAS development process (implementation process and exploitation process). Then, we propose a method of expressing and sharing these difficulties among stakeholders based on MLAS Project FMEA (Failure Mode Effect Analysis). The proposed method is evaluated using two illustrative MLA examples.