Ändra sökning
Länk till posten
Permanent länk

Direktlänk
Publikationer (7 of 7) Visa alla publikationer
Douaioui, K., Oucheikh, R. & Mabroukil, C. (2024). Blockchain-IIoT Integration: Revolutionizing Smart Manufacturing Process Monitoring. In: B. Benhala, A. Raihani & M. Qbadou (Ed.), 2024 4th International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET): . Paper presented at 2024 4th International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET), Fez, Morocco, May 16-17, 2024. IEEE
Öppna denna publikation i ny flik eller fönster >>Blockchain-IIoT Integration: Revolutionizing Smart Manufacturing Process Monitoring
2024 (Engelska)Ingår i: 2024 4th International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET) / [ed] B. Benhala, A. Raihani & M. Qbadou, IEEE, 2024Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

This paper examines the integration of Blockchain and the Industrial Internet of Things (IIoT) in manufacturing process monitoring. The proposed model emphasizes Blockchain's decentralization, cryptographic security, and smart contracts for enhanced security and efficiency. It addresses challenges like data security and scalability, showcasing the transformative potential of Blockchain-IIoT integration. In the end this work highlights future development opportunities in smart manufacturing.

Ort, förlag, år, upplaga, sidor
IEEE, 2024
Nyckelord
Blockchain, IIoT, Industry 4.0, Process Monitoring, Smart Manufacturing, Integration, Process control, Block-chain, Cryptographic security, Decentralisation, Industrial internet of thing, Manufacturing process
Nationell ämneskategori
Datavetenskap (datalogi) Produktionsteknik, arbetsvetenskap och ergonomi
Identifikatorer
urn:nbn:se:hj:diva-65695 (URN)10.1109/IRASET60544.2024.10549646 (DOI)2-s2.0-85197190523 (Scopus ID)979-8-3503-0950-8 (ISBN)
Konferens
2024 4th International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET), Fez, Morocco, May 16-17, 2024
Tillgänglig från: 2024-07-18 Skapad: 2024-07-18 Senast uppdaterad: 2024-07-18Bibliografiskt granskad
Douaioui, K., Oucheikh, R. & Mabrouki, C. (2024). Enhancing Supply Chain Resilience: A Deep Learning Approach to Late Delivery Risk Prediction. In: B. Benhala, A. Raihani & M. Qbadou (Ed.), 2024 4th International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET): . Paper presented at 2024 4th International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET), Fez, Morocco, May 16-17, 2024. IEEE
Öppna denna publikation i ny flik eller fönster >>Enhancing Supply Chain Resilience: A Deep Learning Approach to Late Delivery Risk Prediction
2024 (Engelska)Ingår i: 2024 4th International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET) / [ed] B. Benhala, A. Raihani & M. Qbadou, IEEE, 2024Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

This study introduces an innovative approach to predict late delivery risks, aiming to strengthen supply chain resilience through smart, data-driven strategies. The approach combines clustering using the Elbow method and multiclassification, incorporating advanced deep learning models like Neural Network(NN), Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM), and Bidirectional Long Short-Term Memory (Bi-LSTM). The findings highlight the effectiveness of the (CNN-LSTM) model in producing more accurate results, ultimately improving supply chain resilience, boosting customer satisfaction, and enabling proactive risk management.

Ort, förlag, år, upplaga, sidor
IEEE, 2024
Nyckelord
(Bi-LSTM), (CNN-LSTM), (NN), Clustering, Deep Learning, Elbow method, Late Delivery Risk, Supply Chain, Brain, Convolutional neural networks, Customer satisfaction, Learning systems, Risk management, Supply chains, (bidirectional long short-term memory), (convolutional neural network-long short-term memory), (neural network), Clusterings, Convolutional neural network, Neural-networks, Supply chain resiliences, Long short-term memory
Nationell ämneskategori
Datavetenskap (datalogi) Produktionsteknik, arbetsvetenskap och ergonomi
Identifikatorer
urn:nbn:se:hj:diva-65696 (URN)10.1109/IRASET60544.2024.10548074 (DOI)2-s2.0-85197134131 (Scopus ID)979-8-3503-0950-8 (ISBN)
Konferens
2024 4th International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET), Fez, Morocco, May 16-17, 2024
Tillgänglig från: 2024-07-18 Skapad: 2024-07-18 Senast uppdaterad: 2024-07-18Bibliografiskt granskad
Oualil, S., Oucheikh, R., El Kamili, M. & Berrada, I. (2021). Benchmarking Classical and AI-based Caching Strategies in Internet of Vehicles. In: 2021 IEEE International Conference on Communications Workshops, ICC Workshops 2021 - Proceedings: . Paper presented at 2021 IEEE International Conference on Communications Workshops, ICC Workshops 2021, 14 June 2021 through 23 June 2021. IEEE, Article ID 9473809.
Öppna denna publikation i ny flik eller fönster >>Benchmarking Classical and AI-based Caching Strategies in Internet of Vehicles
2021 (Engelska)Ingår i: 2021 IEEE International Conference on Communications Workshops, ICC Workshops 2021 - Proceedings, IEEE, 2021, artikel-id 9473809Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

Edge caching has emerged as a promising approach to deal with the redundant traffic, to improve the Quality of Service (QoS) and to optimize the energy use in Internet of Vehicles (IoV). However, the intrinsic storage limitations of edge servers pose a critical challenge for IoV edge caching scheme. To solve these issues, several caching policy management techniques have been proposed in literature. In this paper, we perform a systematic comparison among the recent Artificial Intelligence (AI) based caching approaches and the classical caching techniques for IoV. Our objective is to provide a roadmap for choosing the best caching strategy for a given constrained environment. Through a practical scenario, the simulation results show that AI-based edge caching methods achieve high performance in terms of total content access cost and edge hit rate while maintaining a relatively low average delay. On the other hand, hash routing strategies tend to maximize the edge hit rate to the detriment of delivery latency.

Ort, förlag, år, upplaga, sidor
IEEE, 2021
Serie
IEEE International Conference on Communications Workshops, ICC, ISSN 1938-1883
Nyckelord
Caching strategy, content replacement, edge caching, information-centric networks, Internet of Vehicle, Quality of service, Vehicle to vehicle communications, Average delay, Caching policy, Caching technique, Critical challenges, Redundant traffic, Routing strategies, Storage limitation, Artificial intelligence
Nationell ämneskategori
Data- och informationsvetenskap
Identifikatorer
urn:nbn:se:hj:diva-54360 (URN)10.1109/ICCWorkshops50388.2021.9473809 (DOI)2-s2.0-85112850625 (Scopus ID)9781728194417 (ISBN)
Konferens
2021 IEEE International Conference on Communications Workshops, ICC Workshops 2021, 14 June 2021 through 23 June 2021
Tillgänglig från: 2021-08-30 Skapad: 2021-08-30 Senast uppdaterad: 2021-08-30Bibliografiskt granskad
Oucheikh, R., Fri, M., Fedouaki, F. & Hain, M. (2021). Deep anomaly detector based on spatio-temporal clustering for connected autonomous vehicles. In: L. Foschini & M. El Kamili (Ed.), Ad Hoc Networks: 12th EAI International Conference, ADHOCNETS 2020, Paris, France, November 17, 2020, Proceedings. Paper presented at 12th EAI International Conference, ADHOCNETS 2020, Paris, France, November 17, 2020 (pp. 201-212). Springer
Öppna denna publikation i ny flik eller fönster >>Deep anomaly detector based on spatio-temporal clustering for connected autonomous vehicles
2021 (Engelska)Ingår i: Ad Hoc Networks: 12th EAI International Conference, ADHOCNETS 2020, Paris, France, November 17, 2020, Proceedings / [ed] L. Foschini & M. El Kamili, Springer, 2021, s. 201-212Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

Connected Autonomous Vehicles (CAV) are expected to revolutionize the transportation sector. However, given that CAV are connected to internet, they face a principal challenge to ensure security, safety and confidentiality. It is highly valuable to provide a real-time and proactive anomaly detection approach for Vehicular Ad hoc Network (VANET) exchanged data since such an approach helps to trigger prompt countermeasures to be undertaken allowing the damage avoidance. Recent machine learning methods show great efficiency, especially due to their capacity to handle nonlinear problems. However, an accurate anomaly detection in a space–time series is a challenging problem because of the heterogeneity of space–time data and the spatio-temporal correlations. An anomalous behavior can be seen as normal in different context. Thus, using one deep learning model to classify the observations into normal and abnormal or to identify the type of the anomaly is usually not efficient for large high-dimensional multi-variate time-series datasets. In this paper, we propose a stepwise method in which the time-series data are clustered on spatio-temporal clusters using Long Short Term Memory (LSTM) auto-encoder for dimension reduction and Grey Wolf Optimizer based clustering. Then, the anomaly detection is performed on each cluster apart using a hybrid method consisting of Auto-Encoder for feature extraction and Convolution Neural Network for classification. The results shows an increase in the accuracy by 2% in average and in the precision by approximately 1.5%.

Ort, förlag, år, upplaga, sidor
Springer, 2021
Serie
Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering ; 345
Nyckelord
Connected autonomous vehicles, Anomaly detection, Vehicular Ad hoc network, Deep learning
Nationell ämneskategori
Datavetenskap (datalogi)
Identifikatorer
urn:nbn:se:hj:diva-51992 (URN)10.1007/978-3-030-67369-7_15 (DOI)2-s2.0-85101399478 (Scopus ID)978-3-030-67368-0 (ISBN)978-3-030-67369-7 (ISBN)
Konferens
12th EAI International Conference, ADHOCNETS 2020, Paris, France, November 17, 2020
Tillgänglig från: 2021-03-08 Skapad: 2021-03-08 Senast uppdaterad: 2021-03-15Bibliografiskt granskad
Oucheikh, R., Pettersson, T. & Löfström, T. (2021). Product verification using OCR classification and Mondrian conformal prediction. Expert systems with applications, 188, Article ID 115942.
Öppna denna publikation i ny flik eller fönster >>Product verification using OCR classification and Mondrian conformal prediction
2021 (Engelska)Ingår i: Expert systems with applications, ISSN 0957-4174, E-ISSN 1873-6793, Vol. 188, artikel-id 115942Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

The retail sector is undergoing an apparent digital transformation that completely revolutionises shopping operations. To stay competitive, retailer stakeholders are forced to rethink and improve their business models to provide an attractive personalised experience to consumers. The self-service checkout process is at the heart of this transformation and should be designed to identify the products accurately and detect any possible anomalous behaviour. In this paper, we introduce a product verification system based on OCR classification and Mondrian conformal prediction. The proposed system includes three components: OCR reading, text classification and product verification. By using image data from existing grocery stores, the system can detect anomalies with high performance, even when there is partial text information on the products. This makes the system applicable for reducing shrinkage loss (caused, for example, by employee theft or shoplifting) in grocery stores by identifying fraudulent behaviours such as barcode switching and miss-scan. Additionally, OCR reading with NLP classification shows that it is in itself a powerful classifier of products.

Ort, förlag, år, upplaga, sidor
Elsevier, 2021
Nyckelord
OCR classification, Retail product verification, Mondrian conformal prediction, Smart self-checkout system
Nationell ämneskategori
Datavetenskap (datalogi)
Identifikatorer
urn:nbn:se:hj:diva-54840 (URN)10.1016/j.eswa.2021.115942 (DOI)000768193500002 ()2-s2.0-85117127725 (Scopus ID)HOA;;770314 (Lokalt ID)HOA;;770314 (Arkivnummer)HOA;;770314 (OAI)
Forskningsfinansiär
KK-stiftelsen, DATAKIND 20190194Vinnova, Airflow 2018-03581
Tillgänglig från: 2021-10-08 Skapad: 2021-10-08 Senast uppdaterad: 2022-03-31Bibliografiskt granskad
Oucheikh, R., Löfström, T., Ahlberg, E. & Carlsson, L. (2021). Rolling cargo management using a deep reinforcement learning approach. Logistics, 5(1), Article ID 10.
Öppna denna publikation i ny flik eller fönster >>Rolling cargo management using a deep reinforcement learning approach
2021 (Engelska)Ingår i: Logistics, ISSN 2305-6290, Vol. 5, nr 1, artikel-id 10Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

Loading and unloading rolling cargo in roll-on/roll-off are important and very recurrent operations in maritime logistics. In this paper, we apply state-of-the-art deep reinforcement learning algorithms to automate these operations in a complex and real environment. The objective is to teach an autonomous tug master to manage rolling cargo and perform loading and unloading operations while avoiding collisions with static and dynamic obstacles along the way. The artificial intelligence agent, representing the tug master, is trained and evaluated in a challenging environment based on the Unity3D learning framework, called the ML-Agents, and using proximal policy optimization. The agent is equipped with sensors for obstacle detection and is provided with real-time feedback from the environment thanks to its own reward function, allowing it to dynamically adapt its policies and navigation strategy. The performance evaluation shows that by choosing appropriate hyperparameters, the agents can successfully learn all required operations including lane-following, obstacle avoidance, and rolling cargo placement. This study also demonstrates the potential of intelligent autonomous systems to improve the performance and service quality of maritime transport.

Ort, förlag, år, upplaga, sidor
MDPI, 2021
Nyckelord
deep reinforcement learning, cargo management for roll-on/roll-off ships, autonomous tug master, agent based reinforcement learning, collision avoidance
Nationell ämneskategori
Datavetenskap (datalogi)
Identifikatorer
urn:nbn:se:hj:diva-51990 (URN)10.3390/logistics5010010 (DOI)000645584600001 ()GOA;;726130 (Lokalt ID)GOA;;726130 (Arkivnummer)GOA;;726130 (OAI)
Forskningsfinansiär
KK-stiftelsen, DATAKIND 20190194
Anmärkning

Special Issue: Applications of AI and Machine Learning Models for Logistics and Supply Chain Management.

Tillgänglig från: 2021-03-08 Skapad: 2021-03-08 Senast uppdaterad: 2021-05-17Bibliografiskt granskad
Oucheikh, R., Fri, M., Fedouaki, F. & Hain, M. (2020). Deep real-time anomaly detection for connected autonomous vehicles. In: Elhadi M. Shakshuki & Ansar Yasar (Ed.), Procedia Computer Science: . Paper presented at 11th International Conference on Emerging Ubiquitous Systems and Pervasive Networks, EUSPN 2020, 2 November 2020 through 5 November 2020 (pp. 456-461). Elsevier, 177
Öppna denna publikation i ny flik eller fönster >>Deep real-time anomaly detection for connected autonomous vehicles
2020 (Engelska)Ingår i: Procedia Computer Science / [ed] Elhadi M. Shakshuki & Ansar Yasar, Elsevier, 2020, Vol. 177, s. 456-461Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

Connected and autonomous vehicles (CAV) are expected to change the landscape of the automotive market. They are autonomous decision-making systems that process streams of observations coming from different external and on-board sensors. CAV like any other cyber-physical objects are prone to signal interference, hardware deterioration, software errors, power instability, and cyberattacks. To avoid these anomalies which can be fatal, it is mandatory to design a robust real-time technique to detect them and identify their sources. In this paper, we propose a deep learning approach which consists of hierarchic models to firstly extract the signal features using an LSTM auto-encoder, then perform an accurate classification of each signal sequence in real-time. In addition, we investigated the impact of the model parameter tuning on the anomaly detection and the advantage of channel boosting through three scenarios. The model achieves an accuracy of 95.5% and precision of 94.2%.

Ort, förlag, år, upplaga, sidor
Elsevier, 2020
Serie
Procedia Computer Science, ISSN 1877-0509 ; 177
Nyckelord
Anomaly detection, Channel boosting, Connected autonomous vehicles (CAV), Deep learning, Decision making, Deterioration, Learning systems, Long short-term memory, Security of data, Signal processing, Automotive markets, Autonomous decision, Cyber physicals, Learning approach, Model parameter tuning, On-board sensors, Real-time anomaly detections, Real-time techniques, Autonomous vehicles
Nationell ämneskategori
Data- och informationsvetenskap
Identifikatorer
urn:nbn:se:hj:diva-51870 (URN)10.1016/j.procs.2020.10.062 (DOI)2-s2.0-85099885335 (Scopus ID)
Konferens
11th International Conference on Emerging Ubiquitous Systems and Pervasive Networks, EUSPN 2020, 2 November 2020 through 5 November 2020
Tillgänglig från: 2021-02-11 Skapad: 2021-02-11 Senast uppdaterad: 2021-03-15Bibliografiskt granskad
Organisationer
Identifikatorer
ORCID-id: ORCID iD iconorcid.org/0000-0001-9996-9759

Sök vidare i DiVA

Visa alla publikationer