hh.sePublications
Change search
Link to record
Permanent link

Direct link
Atoui, M. Amine
Publications (4 of 4) Show all publications
Abuella, M., Atoui, M. A., Nowaczyk, S., Johansson, S. & Faghani, E. (2024). Spatial Clustering Approach for Vessel Path Identification. IEEE Access, 12, 66248-66258
Open this publication in new window or tab >>Spatial Clustering Approach for Vessel Path Identification
Show others...
2024 (English)In: IEEE Access, E-ISSN 2169-3536, Vol. 12, p. 66248-66258Article in journal (Refereed) Published
Abstract [en]

This paper addresses the challenge of identifying the paths for vessels with operating routes of repetitive paths, partially repetitive paths, and new paths. We propose a spatial clustering approach for labeling the vessel paths by using only position information. We develop a path clustering framework employing two methods: a distance-based path modeling and a likelihood estimation method. The former enhances the accuracy of path clustering through the integration of unsupervised machine learning techniques, while the latter focuses on likelihood-based path modeling and introduces segmentation for a more detailed analysis. The result findings highlight the superior performance and efficiency of the developed approach, as both methods for clustering vessel paths into five clusters achieve a perfect F1-score. The approach aims to offer valuable insights for route planning, ultimately contributing to improving safety and efficiency in maritime transportation. © 2013 IEEE.

Place, publisher, year, edition, pages
Piscataway, NJ: IEEE, 2024
Keywords
average nearest neighbor distance, hierarchical clustering, likelihood estimation, maritime transportation, Spatial clustering, vessel path identification
National Category
Computer and Information Sciences Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:hh:diva-53417 (URN)10.1109/ACCESS.2024.3399116 (DOI)2-s2.0-85193027599 (Scopus ID)
Funder
Vinnova
Available from: 2024-05-30 Created: 2024-05-30 Last updated: 2024-05-30Bibliographically approved
Lou, C. & Atoui, M. A. (2024). Unknown Health States Recognition with Collective-Decision-Based Deep Learning Networks in Predictive Maintenance Applications. Mathematics, 12(1), Article ID 89.
Open this publication in new window or tab >>Unknown Health States Recognition with Collective-Decision-Based Deep Learning Networks in Predictive Maintenance Applications
2024 (English)In: Mathematics, E-ISSN 2227-7390, Vol. 12, no 1, article id 89Article in journal (Refereed) Published
Abstract [en]

At present, decision-making solutions developed based on deep learning (DL) models have received extensive attention in predictive maintenance (PM) applications along with the rapid improvement of computing power. Relying on the superior properties of shared weights and spatial pooling, convolutional neural networks (CNNs) can learn effective representations of health states from industrial data. Many developed CNN-based schemes, such as advanced CNNs that introduce residual learning and multi-scale learning, have shown good performance in health states recognition tasks under the assumption that all the classes are known. However, these schemes have no ability to deal with new abnormal samples that belong to state classes not part of the training set. In this paper, a collective decision framework for different CNNs is proposed. It is based on a one-vs.-rest network (OVRN) to simultaneously achieve classification of known and unknown health states. OVRNs learn class-specific discriminative features and enhance the ability to reject new abnormal samples incorporated to different CNNs. According to the validation results on the public dataset of the Tennessee Eastman process (TEP), the proposed CNN-based decision schemes incorporating an OVRN have outstanding recognition ability for samples of unknown heath states while maintaining satisfactory accuracy on known states. The results show that the new DL framework outperforms state-of-the-art CNNs, and the one based on residual and multi-scale learning has the best overall performance. © 2023 by the authors.

Place, publisher, year, edition, pages
Basel: MDPI, 2024
Keywords
classification, convolutional neural network, one-vs.-rest network, predictive maintenance, unknown heath states
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
urn:nbn:se:hh:diva-52487 (URN)10.3390/math12010089 (DOI)2-s2.0-85182197617 (Scopus ID)
Available from: 2024-01-26 Created: 2024-01-26 Last updated: 2024-01-26Bibliographically approved
Abuella, M., Atoui, M. A., Nowaczyk, S., Johansson, S. & Faghani, E. (2023). Data-Driven Explainable Artificial Intelligence for Energy Efficiency in Short-Sea Shipping. In: Gianmarco De Francisci Morales; Claudia Perlich; Natali Ruchansky; Nicolas Kourtellis; Elena Baralis; Francesco Bonchi (Ed.), Machine Learning and Knowledge Discovery in Databases: Applied Data Science and Demo Track: European Conference, ECML PKDD 2023, Turin, Italy, September 18–22, 2023, Proceedings, Part VII. Paper presented at European Conference, ECML PKDD 2023, Turin, Italy, September 18–22, 2023 (pp. 226-241). Cham: Springer, 14175
Open this publication in new window or tab >>Data-Driven Explainable Artificial Intelligence for Energy Efficiency in Short-Sea Shipping
Show others...
2023 (English)In: Machine Learning and Knowledge Discovery in Databases: Applied Data Science and Demo Track: European Conference, ECML PKDD 2023, Turin, Italy, September 18–22, 2023, Proceedings, Part VII / [ed] Gianmarco De Francisci Morales; Claudia Perlich; Natali Ruchansky; Nicolas Kourtellis; Elena Baralis; Francesco Bonchi, Cham: Springer, 2023, Vol. 14175, p. 226-241Conference paper, Published paper (Refereed)
Abstract [en]

The maritime industry is under pressure to increase energy efficiency for climate change mitigation. Navigational data, combining vessel operational and environmental measurements from onboard instruments and external sources, are critical for achieving this goal. Short-sea shipping presents a unique challenge due to the significant influence of surrounding landscape characteristics. With high-resolution onboard data increasingly accessible through IoT devices, appropriate data representations and AI/ML analytical tools are needed for effective decision support. The aim of this study is to investigate the fuel consumption estimation model’s role in developing an energy efficiency decision support tool. ML models that lacking explainability may neglect important factors and essential constraints, such as the need to meet arrival time requirements. Onboard weather measurements are compared to external forecasts, and our findings demonstrate the necessity of eXplainable Artificial Intelligence (XAI) techniques for effective decision support. Real-world data from a short-sea passenger vessel in southern Sweden, consisting of 1754 voyages over 15 months (More of data description and code sources of this study can be found in the GitHub repository at https://github.com/MohamedAbuella/ST4EESSS), are used to support our conclusions.  © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Place, publisher, year, edition, pages
Cham: Springer, 2023
Series
Lecture Notes in Computer Science, ISSN 0302-9743, E-ISSN 1611-3349 ; 14175
Keywords
Short-sea shipping, Energy efficiency, Explainability, Spatio-temporal aggregation
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:hh:diva-51888 (URN)10.1007/978-3-031-43430-3_14 (DOI)2-s2.0-85174447269 (Scopus ID)978-3-031-43429-7 (ISBN)978-3-031-43430-3 (ISBN)
Conference
European Conference, ECML PKDD 2023, Turin, Italy, September 18–22, 2023
Projects
Research projects within Aware Intelligent Systems
Funder
Vinnova
Available from: 2023-11-02 Created: 2023-11-02 Last updated: 2023-12-07Bibliographically approved
Lou, C., Atoui, M. A. & Li, X. (2023). Recent deep learning models for diagnosis and health monitoring: a review of researches and future challenges. Transactions of the Institute of Measurement and Control
Open this publication in new window or tab >>Recent deep learning models for diagnosis and health monitoring: a review of researches and future challenges
2023 (English)In: Transactions of the Institute of Measurement and Control, ISSN 0142-3312, E-ISSN 1477-0369Article in journal (Refereed) Epub ahead of print
Abstract [en]

As an important branch of machine learning, deep learning (DL) models with multiple hidden layer structures have the ability to extract highly representative features from the input. At present, fault detection and diagnosis (FDD) and health monitoring solutions developed based on DL models have received extensive attention in academia and industry along with the rapid improvement of computing power. Therefore, this paper focuses on a comprehensive review of DL model–based FDD and health monitoring schemes in view of common problems of industrial systems. First, brief theoretical backgrounds of basic DL models are introduced. Then, related publications are discussed about the development of DL and graphical models in the industrial context. Afterwards, public data sets are summarized, which are associated with several research papers. More importantly, suggestions on DL model–based diagnosis and health monitoring solutions and future developments are given. Our work will have a positive impact on the selection and design of FDD solutions based on DL and graphical models in the future. © The Author(s) 2023.

Place, publisher, year, edition, pages
London: Sage Publications, 2023
Keywords
Deep learning, graphical probabilistic models, health monitoring, fault diagnosis, big data
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:hh:diva-49884 (URN)10.1177/01423312231157118 (DOI)000950021400001 ()2-s2.0-85150937696 (Scopus ID)
Available from: 2023-01-29 Created: 2023-01-29 Last updated: 2023-04-21Bibliographically approved
Organisations

Search in DiVA

Show all publications