Fusion of heterogeneous industrial data using polygon generation & deep learning
Analysis of industrial data imposes several challenges. These data are acquired from heterogeneous sources such as sensors, cameras, IoT, etc, and are stored in different structures and formats with different sampling frequencies. They are also stored in isolated silos in different locations which h...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-09-01
|
| Series: | Results in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590123023003614 |
| _version_ | 1797682443001528320 |
|---|---|
| author | Mohamed Elhefnawy Mohamed-Salah Ouali Ahmed Ragab Mouloud Amazouz |
| author_facet | Mohamed Elhefnawy Mohamed-Salah Ouali Ahmed Ragab Mouloud Amazouz |
| author_sort | Mohamed Elhefnawy |
| collection | DOAJ |
| description | Analysis of industrial data imposes several challenges. These data are acquired from heterogeneous sources such as sensors, cameras, IoT, etc, and are stored in different structures and formats with different sampling frequencies. They are also stored in isolated silos in different locations which hinders their exploitation. Therefore, there is a clear need to integrate these disconnected data silos at different processing levels and make them clean, easily accessible, and fully exploitable. This paper proposes a data fusion method that merges heterogeneous sources of data at raw, information, and decision levels using polygon generation and deep learning (DL) techniques. An innovative polygon generation technique is proposed to preprocess each data source and convert it into powerful representations that capture all possible relationships in the data, thus extracting the maximum knowledge and achieving better prediction accuracy of the corresponding DL method. The proposed method is targeting challenging data modeling problems found in industrial processes. It is validated successfully using a case study in the realm of process system engineering. The results obtained demonstrate that the proposed fusion method is more accurate, with a minimum of 20% improvement, compared to other methods previously used in the literature. |
| first_indexed | 2024-03-11T23:59:46Z |
| format | Article |
| id | doaj.art-176e0c7fec984d52ab7d266549729d69 |
| institution | Directory Open Access Journal |
| issn | 2590-1230 |
| language | English |
| last_indexed | 2024-03-11T23:59:46Z |
| publishDate | 2023-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Engineering |
| spelling | doaj.art-176e0c7fec984d52ab7d266549729d692023-09-18T04:30:29ZengElsevierResults in Engineering2590-12302023-09-0119101234Fusion of heterogeneous industrial data using polygon generation & deep learningMohamed Elhefnawy0Mohamed-Salah Ouali1Ahmed Ragab2Mouloud Amazouz3Department of Mathematics and Industrial Engineering, Polytechnique Montréal, 2500 Chemin de Polytechnique, Montréal, Québec, H3T 1J4, Canada; CanmetENERGY-Natural Resources Canada, 1615 Lionel Boulet Blvd., P.O. Box 4800, Varennes, Québec, J3X 1P7, CanadaDepartment of Mathematics and Industrial Engineering, Polytechnique Montréal, 2500 Chemin de Polytechnique, Montréal, Québec, H3T 1J4, CanadaDepartment of Mathematics and Industrial Engineering, Polytechnique Montréal, 2500 Chemin de Polytechnique, Montréal, Québec, H3T 1J4, Canada; CanmetENERGY-Natural Resources Canada, 1615 Lionel Boulet Blvd., P.O. Box 4800, Varennes, Québec, J3X 1P7, Canada; Faculty of Electronic Engineering, Menoufia University, 32952, Menouf, Egypt; Corresponding author. Department of Mathematics and Industrial Engineering, Polytechnique Montréal, Canada.CanmetENERGY-Natural Resources Canada, 1615 Lionel Boulet Blvd., P.O. Box 4800, Varennes, Québec, J3X 1P7, CanadaAnalysis of industrial data imposes several challenges. These data are acquired from heterogeneous sources such as sensors, cameras, IoT, etc, and are stored in different structures and formats with different sampling frequencies. They are also stored in isolated silos in different locations which hinders their exploitation. Therefore, there is a clear need to integrate these disconnected data silos at different processing levels and make them clean, easily accessible, and fully exploitable. This paper proposes a data fusion method that merges heterogeneous sources of data at raw, information, and decision levels using polygon generation and deep learning (DL) techniques. An innovative polygon generation technique is proposed to preprocess each data source and convert it into powerful representations that capture all possible relationships in the data, thus extracting the maximum knowledge and achieving better prediction accuracy of the corresponding DL method. The proposed method is targeting challenging data modeling problems found in industrial processes. It is validated successfully using a case study in the realm of process system engineering. The results obtained demonstrate that the proposed fusion method is more accurate, with a minimum of 20% improvement, compared to other methods previously used in the literature.http://www.sciencedirect.com/science/article/pii/S2590123023003614Data fusionDecision fusionDeep learningPolygon generationEnergy efficiencyProcess system engineering |
| spellingShingle | Mohamed Elhefnawy Mohamed-Salah Ouali Ahmed Ragab Mouloud Amazouz Fusion of heterogeneous industrial data using polygon generation & deep learning Results in Engineering Data fusion Decision fusion Deep learning Polygon generation Energy efficiency Process system engineering |
| title | Fusion of heterogeneous industrial data using polygon generation & deep learning |
| title_full | Fusion of heterogeneous industrial data using polygon generation & deep learning |
| title_fullStr | Fusion of heterogeneous industrial data using polygon generation & deep learning |
| title_full_unstemmed | Fusion of heterogeneous industrial data using polygon generation & deep learning |
| title_short | Fusion of heterogeneous industrial data using polygon generation & deep learning |
| title_sort | fusion of heterogeneous industrial data using polygon generation amp deep learning |
| topic | Data fusion Decision fusion Deep learning Polygon generation Energy efficiency Process system engineering |
| url | http://www.sciencedirect.com/science/article/pii/S2590123023003614 |
| work_keys_str_mv | AT mohamedelhefnawy fusionofheterogeneousindustrialdatausingpolygongenerationampdeeplearning AT mohamedsalahouali fusionofheterogeneousindustrialdatausingpolygongenerationampdeeplearning AT ahmedragab fusionofheterogeneousindustrialdatausingpolygongenerationampdeeplearning AT mouloudamazouz fusionofheterogeneousindustrialdatausingpolygongenerationampdeeplearning |