Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2410.16748 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916448779108352 |
|---|---|
| author | Fitsilis, Panos Tsoutsa, Paraskevi Damasiotis, Vyron Kyriatzis, Vasileios |
| author_facet | Fitsilis, Panos Tsoutsa, Paraskevi Damasiotis, Vyron Kyriatzis, Vasileios |
| contents | This article analyzes around 200 online articles to identify trends within Industry 5.0 using artificial intelligence techniques. Specifically, it applies algorithms such as LDA, BERTopic, LSA, and K-means, in various configurations, to extract and compare the central themes present in the literature. The results reveal a convergence around a core set of themes while also highlighting that Industry 5.0 spans a wide range of topics. The study concludes that Industry 5.0, as an evolution of Industry 4.0, is a broad concept that lacks a clear definition, making it difficult to focus on and apply effectively. Therefore, for Industry 5.0 to be useful, it needs to be refined and more clearly defined. Furthermore, the findings demonstrate that well-known AI techniques can be effectively utilized for trend identification, particularly when the available literature is extensive and the subject matter lacks precise boundaries. This study showcases the potential of AI in extracting meaningful insights from large and diverse datasets, even in cases where the thematic structure of the domain is not clearly delineated. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_16748 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Uncovering Key Trends in Industry 5.0 through Advanced AI Techniques Fitsilis, Panos Tsoutsa, Paraskevi Damasiotis, Vyron Kyriatzis, Vasileios Artificial Intelligence I.1; K.1 This article analyzes around 200 online articles to identify trends within Industry 5.0 using artificial intelligence techniques. Specifically, it applies algorithms such as LDA, BERTopic, LSA, and K-means, in various configurations, to extract and compare the central themes present in the literature. The results reveal a convergence around a core set of themes while also highlighting that Industry 5.0 spans a wide range of topics. The study concludes that Industry 5.0, as an evolution of Industry 4.0, is a broad concept that lacks a clear definition, making it difficult to focus on and apply effectively. Therefore, for Industry 5.0 to be useful, it needs to be refined and more clearly defined. Furthermore, the findings demonstrate that well-known AI techniques can be effectively utilized for trend identification, particularly when the available literature is extensive and the subject matter lacks precise boundaries. This study showcases the potential of AI in extracting meaningful insights from large and diverse datasets, even in cases where the thematic structure of the domain is not clearly delineated. |
| title | Uncovering Key Trends in Industry 5.0 through Advanced AI Techniques |
| topic | Artificial Intelligence I.1; K.1 |
| url | https://arxiv.org/abs/2410.16748 |