Loading...
Please wait, while we are loading the content...
Similar Documents
Automatic Time and Motion Study Using Deep Learning
| Content Provider | Scilit |
|---|---|
| Author | Hernandez, Jefferson Lopez, Sofia Valarezo, Gabriela Abad, Andres G. |
| Copyright Year | 2021 |
| Description | Measuring the performance of manual-labour activities is a key element of work scheduling and resource management. This measurement is usually performed using a data-collection methodology called a time and motion study (TMS). Many industries still rely on human effort to execute TMSs, which can be time-consuming, error-prone, and expensive. In this chapter, the authors introduce an automatic alternative to human-performed TMS that works at two levels of abstraction: micro-actions – defined as the movement of a specific body part – and macro-actions – defined as the combination of successive micro-actions. For this, the authors leverage recent advancements in deep learning. Specifically, they employ an encoder-decoder-based classifier to perform micro-action recognition, and a continuous-time hidden Markov model to perform macro-action recognition. They show how the proposed system can compute productivity indicators such as worker availability, worker performance, and overall labor effectiveness; and hand-usage indicators such as hand speed and handedness. Book Name: Cyber-Physical, IoT, and Autonomous Systems in Industry 4.0 |
| Related Links | https://api.taylorfrancis.com/content/chapters/edit/download?identifierName=doi&identifierValue=10.1201/9781003146711-10&type=chapterpdf |
| Ending Page | 162 |
| Page Count | 16 |
| Starting Page | 147 |
| DOI | 10.1201/9781003146711-10 |
| Language | English |
| Publisher | Informa UK Limited |
| Publisher Date | 2021-11-04 |
| Access Restriction | Open |
| Subject Keyword | Book Name: Cyber-physical, Iot, and Autonomous Systems in Industry 4.0 Worker Automatic Motion Defined |
| Content Type | Text |
| Resource Type | Chapter |
