Publications Scientifiques

Permanent URI for this communityhttps://dspace.univ-boumerdes.dz/handle/123456789/10

Browse

Subject: search.filters.subject.Identification

Search Results

Now showing 1 - 6 of 6
  • No Thumbnail Available
    Item
    Identity recognition based on palmprints : the preliminary results
    (IEEE, 2022) Amrouni, Nadia; Benzaoui, Amir; Adjabi, Insaf
    Private and automatic recognition in many applications, such as forensic, access control, and surveillance systems, has become necessary in recent years. Biometrics, which treats individuals' identification based on physical or behavioral characteristics, has emerged as an effective automated identification technology, offering more properties and advantages than conventional protection. The use of palmprints in biometric authentication has dramatically increased and has been used extensively in management systems for businesses, Internet of Thinks, and individuals. In this field, the palmprint is considered a new modality, a unique entity that is stable over time and has a rich information structure. As part of this work, the local binary pattern descriptor (LBP) was used and tested under several configurations to extract the palmprint modality's optimal and efficient characteristics. As preliminary results, our experiments on the IITD Palmprint V1 database exhibit impressive performance
  • No Thumbnail Available
    Item
    A Modified elman network with memory units for system identification
    (2018) Ladjouzi, Samir; Grouni, Said; Soufi, Youcef
    In this paper we propose a modified Elman network structure called memory Elman neural network. The idea of this new architecture is based on adding memory units to the neurons of the classic Elman network. These memory units are trainable temporal elements that make the output history-sensitive. By virtue of this capacity, this new architecture can take into account the past information of the neurons and use them in order to accomplish the task of the network. In order to show the performance of this new network, some dynamical systems are used for identification and results are compared with the conventional Elman network
  • No Thumbnail Available
    Item
    Valorisationof microbial biodiversity : Characterization of a milk-clotting enzyme produced byBacillus velezensis FK6Astrain isolated from Algerian dairy farm soil in light of its usein the manufacture of hard cooked cheeses
    (2021) Boumediene, F.; Talantikite, S.; Haddad, S.; Nouani, A.; Triki, S.; Belbraouet, S.
    A strain known as FK6A, which produces a milk-clotting enzyme isolated from the soil of an Algerian dairy factory, was identified as Bacillus velezensis based on morphology and internal transcription spacer sequence. Phylogenetic and sequencing analysis of 16S rDNA gene showed a 100% identity match between the tested strainand the Bacillusvelezensis in the database (Code MH368142). This strain produced an active extracellular protease purified by partial purification using ammonium sulfate fractionation(40–80% saturation) followed by chromatography of molecular exclusion, which revealed the existence of tow active peaks. The optimal activity was observed at pH 5.7; 75°C and 40 mM of CaCl2. The clotting enzyme has been shown to be a metalloprotease inhibited by EDTA. The highly proteolytic activity of the Bacillus velezensis extracts observed on the curds appears a few minutes after the appearance of a firm coagulum reflected by the appearance of an abundant serum.Thus, to solve this problem and to inhibit proteolytic activity, the curds were cooked after brewing during the manufacturing process
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    Generalized dynamical fuzzy model for identification and prediction
    (2014) Saad Saoud, Lyes; Rahmoune, Fayçal; Tourtchine, Victor; Baddari, Kamel
    In this paper, the development of an improved Takagi Sugeno (TS) fuzzy model for identification and chaotic time series prediction of nonlinear dynamical systems is proposed. This model combines the advantages of fuzzy systems and Infinite Impulse Response (IIR) filters, which are autoregressive moving average models, to create internal dynamics with just the control input. The structure of Fuzzy Infinite Impulse Response (FIIR) is presented, and its learning algorithm is described. In the proposed model, the Butterworth analogue prototype filters are estimated using the obtained membership functions. Based on the founding orders of the analogue filters, the IIR filters could be constructed. The IIR filters are introduced to each TS fuzzy rule which produces local dynamics. Gustafson-Kessel (GK) clustering algorithm is used to generate the clusters which will be used to find the number of the IIR parameters for each rule. The hybrid genetic algorithm and simplex method are used to identify the consequence parameters. The stability of the obtained model is studied. To demonstrate the performance of this modeling method, three examples have been chosen. Comparative results between the FIIR model on one hand, and the traditional TS fuzzy model, the neural networks and the neuro-fuzzy network on the other hand. The results show that the proposed method provides promising identification results
  • No Thumbnail Available
    Item
    A novel theory of reference reactive current identification based on the per unit system used for the active filters
    (2008) Abdelkhalek, Othmane; Benachaiba, C.; Benslimane, T.; Haidas, M.
    This paper, presents a new method of reactive current identification. The principle is based on the transformation of the voltage and current of the electrical supply network to the per unit system. The fundamental of the current is then obtained by extraction. This new method is compared to that of the theory pq. Interesting results were obtained with a satisfactory power factor correction