Wrapping practical problems into a machine learning framework: Using water pipe failure prediction as a case study
| Autor: | Yang Wang, Fang Chen, Jianlong Zhou, Jinjun Sun |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2017 |
| Předmět: |
General Computer Science
Computer science business.industry 05 social sciences 0801 Artificial Intelligence and Image Processing 0803 Computer Software 0906 Electrical and Electronic Engineering Process (computing) 020207 software engineering 02 engineering and technology Machine learning computer.software_genre Domain (software engineering) Set (abstract data type) Workflow 0202 electrical engineering electronic engineering information engineering Water pipe Work flow 0501 psychology and cognitive sciences Artificial intelligence Data mining business computer 050107 human factors |
| Popis: | Despite the recognised value of machine learning (ML) techniques and high expectation of applying ML techniques within various applications, users often find it difficult to effectively apply ML techniques in practice because of complicated interfaces between ML algorithms and users. This paper presents a work flow of wrapping practical problems into an ML framework. The water pipe failure prediction is used as a case study to show that the applying process can be divided into various steps: obtain domain data, interview with domain experts, clean/pre-process and preview original domain data, extract ML features, set up ML models, explain ML results and make decisions, as well as make feedback to the system based on decision making. In this process, domain experts and ML developers need to collaborate closely in order to make this workflow more effective. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|