Browsing by Author "Lejdel, Brahim"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Deep learning for seismic data semantic segmentation
    (University of Eloued جامعة الوادي, 2022-01-24) Naoui, Mohammed Anouar; Lejdel, Brahim; Kazar, Okba; Berrehouma, Ridha
    Drilling for oil and gas is an expensive and time-consuming process. Companies in the oil and gas industry invest millions of dollars in an effort to improve their understanding of subsurface components, and using traditional workflows for interpreting large volumes of seismic data is an important part of this effort. Manually defining links between geological characteristics and seismic patterns is required by geoscientists. As a result, geologists and oil and gas industry businesses resorted to a seismic survey, in which seismic waves provide a wealth of information about what is inside the earth without the need to dig. The main of this paper concerns the identification of salt layers of a seismic image by a computer which often coexist with gas and oil under the ground by proposing a deep Learning for seismic analysis.We propose U-net architecture to discover seismic data. Moreover, we study the data augmentation with U-net architecture. The result of data augmentation can perform 10 % the U-net architecture model.
  • No Thumbnail Available
    Item
    Machine Learning Based Indoor Localization using Wi-Fi and Smartphone in a Shopping Malls
    (University of Eloued جامعة الوادي, 2022-01-24) Maaloul, Kamel; Lejdel, Brahim
    The availability of sensors in smartphones has led to indoor positioning solutions. However, the accuracy of these techniques remains uneven as a straightforward solution to indoor positioning. Solutions based on Wi-Fi signal strength work in favor of the idea of controlling infrastructure costs. Our work attempts to explore other learning algorithms and make more robust trade-offs between accuracy and power.Our work also focuses on using classification-based learning algorithms to achieve higher accuracy. By using methods to select the appropriate model and using more complex on-device learning algorithms. Accurate indoor positioning, based on general sensors and user permission, allows for a great location based experience. Machine learning (ML) based methods are also used to improve the quality and efficiency of services.To verify the accuracy of the models, we reviewed the algorithms using several comparisons between a variety of machine learning approaches.We have verified the system’s performance using measurements of a smartphone’s Wi-Fi RSS (Really Simple Syndication) sensor. Evaluation results show that the gradient boosting method achieves the best internal feature localization accuracy of more than 95%.