Publications Scientifiques

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

Browse

Subject: search.filters.subject.Convolutional Neural Network (CNN)

Search Results

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Convolution neural network deployment for plant leaf diseases detection
    (Springer, 2023) Cherifi, Dalila; Bayou, Meroua; Benmalek, Assala; Mechti, Ines; Bekkouche, Abdelghani; Bekkour, Belkacem; Amine, Chaima; Ahmed, Halak
    The automated identification of plant diseases based on plant leaves is a huge breakthrough. Furthermore, early and accurate detection of plant diseases positively impacts crop productivity and quality. However, managing the accessibility of early plant disease detection is crucial. This work has environmental goals aiming to save plants from different threatening diseases by providing early detection of the affected leaves. We studied the performance of different Convolutional Neural Network (CNN) architectures in predicting 26 diseases for 14 plant species. The work studied the complexity of the system and compared the two main deep learning frameworks, TensorFlow and PyTorch, to get the most accurate results with higher accuracy. Using the “New PlantVillage Dataset” from Kaggle [1], the TensorFlow models achieved an accuracy of 90,94% for the basic CCN architecture, and 95,59% for the Transfer Learning architecture with VGG19. Whereas the PyTorch models achieved an accuracy of 93,47% for the basic CCN architecture, and 98,53% for the Transfer Learning architecture with ResNet34. Finally, after examining the feasibility of the model’s implementation and discussing the main problems that may be encountered, the models were deployed in a mobile application using the Tflite and torch mobile flutter SDK to let them as an internal feature in the mobile without the need for any access to the cloud, which is known as edge AI
  • No Thumbnail Available
    Item
    Prediction models for epilepsy detection on the EEG signal
    (IEEE, 2022) Cherifi, Dalila; Zenati, Hichem; Ouchene, Mohamed Amine; Merbouti, Mohammed Abdenacer; Ibrahim, Dyhia; Boubchir, Larbi
    Epilepsy is a neurological illness characterized by abnormal brain activity, resulting in seizures or episodes of odd behavior, feelings, and in some cases, loss of awareness. In this work, we propose a comparison between three deep learning models: Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) and bidirectional LSTM for epileptic seizure detection using EEG data which is the most common technique used for Epilepsy diagnosis. The objective of this work is to define the most suitable model for this sensitive task and to reach the highest possible accuracy. To evaluate the performance of the proposed methods, many experiments are conducted to study the effect of some parameters and using two categorical combinations of an EEG dataset. As a result, we reached a prediction accuracy of 90.26% with CNN, 86.17% with LSTM but the Bi-LSTM model consistently outperformed the other models reaching more than 98% accuracy. Finally, these results demonstrate the possibility of detecting the epileptic seizures while maintaining model interpretability, which may contribute to a better understanding of brain dynamics and enhance predictive performances
  • No Thumbnail Available
    Item
    Text-Independent Speaker Identification using Mel-Frequency Energy Coefficients and Convolutional Neural Networks
    (IEEE, 2020) Abdiche, Déhia; Harrar, Khaled
    Automatic Speaker Identification (ASI) is a biometric technique, which had achieved reliability in real applications, with standard feature extraction methods such as Linear Predictive Cepstral Coefficients (LPCC), Perceptual Linear Prediction (PLP), and modeling methods such as Gaussian mixture model (GMM), etc. However, the success of these manual approaches was quickly hampered by the emergence of big data, and the inability of scientists to manipulate large amounts of data, which led researchers to move towards automatic methods such as deep neural networks. In this work, a Convolutional Neural Network (CNN) is suggested for speaker identification in text-independent mode. Mel-Frequency Energy Coefficients (MFEC) method was used for extracting the characteristics of audio signals and the obtained coefficients were injected into the convolutional neural network model for classification (identification). In addition, a comparison was made between the proposed method and the existing traditional methods. Experimental results show that the proposed structure resulted in a speaker identification rate of 97.89%, which is much higher than the rates obtained in the old state of the art methods.