European Journal Of Advances In Engineering And Technology
Published December 31, 2022 | Version v1
Journal article Open

Design of an Internet Data Access Filtering System based on Convolutional Neural Networks (EfficientNet)

Authors/Creators

  • 1. Laboratory of Computer Science Engineering and Automation, University of Douala, P. O. Box 1872 Douala, Cameroon

Description

ABSTRACT

This paper consists in proposing a system for filtering access to data on the Internet, in a "general public" context, via the design of a plugin with the objective of improving the processing and control of dynamic information disseminated in web content. The aim of this approach is to determine which resources are relevant to a user. We have studied and proposed a hybrid method between browser plugin technology (content-based filtering) and convolutional neural network technology (efficient net). The working principle of our algorithm will be the detection and classification of a so-called illegal image. To present good results, we used Web Scraping technology to design our training database; the training of our model was based on EfficientNetb7, the Spyder Anaconda development environment and the Python programming language. During testing, the CNN results we obtained were very encouraging as they allowed us to assess the achievement of our objectives at 95%.

Files

EJAET-9-12-32-39.pdf

Files (271.3 kB)

Name Size Download all
md5:912794b5998689fbf8ce9144ea7fbdec
271.3 kB Preview Download

Additional details

References

  • [1]. M. Belkheir, "Le filtrage de 1 Information sur Internet," DEA SIC synthesis note, ENSSIB, Lyon, 1995.
  • [2]. P. Lassalle. "Study of the scaling of segmentation and classification algorithms in remote sensing for the processing of massive volumes of data," PhD thesis, University of Toulouse, Nov.2015.
  • [3]. A. Belloui, "L'usage des concepts du web sémantique dans le filtrage d'information collaboratif", Master's thesis, National Institute of Computer Science, Algiers, 2008.
  • [4]. J. Leskovec, A. Rajaraman, J. Ullman, "Mining of Massive Datasets", 2nd Edition, 2014, pp 307-340.
  • [5]. F. Ricci, L. Rokach, B. Shapira and P. B. Kantor. "Recommender Systems Handbook," in proc. Springer editors, 2011.
  • [6]. E. NEGRE. "Bypassing web filtering using an SSH tunnel," internet: https://interstices.info/les-systemes-de-recommandation-categorisation/, Sept. 2018 [Jan. 20, 2022].
  • [7]. H. Michel, "Qu'est Ce Que Le Deep Learning (Apprentissage Profond)," Internet: https://ledatascientist.com/deep-learning-apprentissage-profond/, Jan. 13, 2019 [Sept. 20, 2020].
  • [8]. K. Djamila, "Using neural networks as a tool for datamining: Generating a behavioural model of a physical process from data," Master's thesis, University of Batna 2, 2012.
  • [9]. M. Zakaria, "Image classification with convolutional neural networks," Master's thesis, Abou Bakr Belkaid Tlemcen University, Algiers, 2017.
  • [10]. N. Srivastava, C. Hinton, A. Krizhevsky, I. Sutskever and R. Salakhutdinov, "Dropout: A Simple Way to Prevent Neural Networks from overfitting," Journal of Machine Learning Research, vol. 15, 2014, pp 1929-1958.
  • [11]. Mehdi Yedroudj, Marc Chaumont, and Frédéric Comby. How to Augment a Small Learning Set for Improving the Performances of a CNN-Based Steganalyzer? In Proceedings of Media Watermarking, Security, and Forensics, MWSF'2018, Part of IS&T International Symposium on Electronic Imaging, EI'2018, page 7, Burlingame, California, USA, 28 January - 2 February 2018.
  • [12]. A. G. HOWARD, "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications " Internet : https://ledatascientist.com/deep-learning-apprentissage deep/ , Jan. 13, 2019 [Sept. 20, 2020].
  • [13]. Mehdi Yedroudj, Marc Chaumont, Frederic Comby, Ahmed Oulad Amara, and Patrick Bas. Pixels-off: Data-Augmentation Complementary Solution for DeepLearning Steganalysis. In Proceedings of the 2020 ACM Workshop on Information Hiding and Multimedia Security, IHMSec '20, page 39-48, Virtual Conference due to Covid (Formerly Denver, CO, USA), June 2020.
  • [14]. Han CAI, Ji LIN, Song HAN, "Efficient Method for Deeplearning", Computer Vision and Pattern Recognition, 2022, Pages 159-190.
  • [15]. Kamilaris ANDREAS, Prenafeta-BOLDU, Francesc XAVIER and Augusti FONTS, "Deeplearning in agriculture", Magazine article, 2018, pp 70-90.
  • [16]. Sara MEFTAH, Nasredine Semmar, Youssef Tamaazoust, Hassane Essafi, "Exploration Transfer learning for social network text analysis", Conference on Natural Language Processing - TALN-RECITAL 2019, 2019.
  • [17]. Tom KELDENICH, "Data Augmentation, rapidly improving your Deep Learning", Internet: https://inside-machinelearning.com/data-augmentation-ameliorer quickly-his-modele-of-deep-learning//, Feb. 22, 2021 [Jul. 21, 2022].