An interactive environment based on a task model

Author(s):  
C. Furet
Author(s):  
Qing Liao ◽  
Heyan Chai ◽  
Hao Han ◽  
Xiang Zhang ◽  
Xuan Wang ◽  
...  
Keyword(s):  

Metals ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 870
Author(s):  
Robby Neven ◽  
Toon Goedemé

Automating sheet steel visual inspection can improve quality and reduce costs during its production. While many manufacturers still rely on manual or traditional inspection methods, deep learning-based approaches have proven their efficiency. In this paper, we go beyond the state-of-the-art in this domain by proposing a multi-task model that performs both pixel-based defect segmentation and severity estimation of the defects in one two-branch network. Additionally, we show how incorporation of the production process parameters improves the model’s performance. After manually constructing a real-life industrial dataset, we first implemented and trained two single-task models performing the defect segmentation and severity estimation tasks separately. Next, we compared this to a multi-task model that simultaneously performs the two tasks at hand. By combining the tasks into one model, both segmentation tasks improved by 2.5% and 3% mIoU, respectively. In the next step, we extended the multi-task model using sensor fusion with process parameters. We demonstrate that the incorporation of the process parameters resulted in a further mIoU increase of 6.8% and 2.9% for the defect segmentation and severity estimation tasks, respectively.


Author(s):  
Jatin Arora ◽  
Claudio Maia ◽  
Syed Aftab Rashid ◽  
Geoffrey Nelissen ◽  
Eduardo Tovar

2017 ◽  
Vol 50 (4) ◽  
pp. 641-660 ◽  
Author(s):  
Naoko Taguchi ◽  
Qiong Li ◽  
Xiaofei Tang

2021 ◽  
Author(s):  
Tiancheng Yang ◽  
Shah Nazir

Abstract With the development and advancement of information technology, artificial intelligence (AI) and machine learning (ML) are applied in every sector of life. Among these applications, music is one of them which has gained attention in the last couple of years. The music industry is revolutionized with AIbased innovative and intelligent techniques. It is very convenient for composers to compose music of high quality using these technologies. Artificial intelligence and Music (AIM) is one of the emerging fields used to generate and manage sounds for different media like the Internet, games, etc. Sounds in the games are very effective and can be made more attractive by implementing AI approaches. The quality of sounds in the game directly impacts the productivity and experience of the player. With computer-assisted technologies, the game designers can create sounds for different scenarios or situations like horror and suspense and provide gamer information. The practical and productive audio of a game can guide visually impaired people during other events in the game. For the better creation and composition of music, good quality of knowledge about musicology is essential. Due to AIM, there are a lot of intelligent and interactive tools available for the efficiency and effective learning of music. The learners can be provided with a very reliable and interactive environment based on artificial intelligence. The current study has considered presenting a detailed overview of the literature available in the area of research. The study has demonstrated literature analysis from various perspectives, which will become evidence for researchers to devise novel solutions in the field.


Sign in / Sign up

Export Citation Format

Share Document