Faculty of Sciences and Technology

Permanent URI for this communityhttps://dspace.univ-ghardaia.edu.dz.dz/handle/123456789/58

Browse

Has files: YesSubject: search.filters.subject.Deep Learning

Search Results

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    A multi source/task deep learning system for non-invasive detection and estimation of coronary artery stenosis
    (university of ghardaia, 2026) Hocine Harrouzi; Houdaifa Yahia-cherif
    Cardiovascular disease is the leading cause of death worldwide, and coronary artery disease is its most common form. To diagnose it, clinicians rely on X-ray coronary angiog- raphy, but interpreting these images manually is slow and prone to disagreement between experts. Most deep-learning tools address the three sub-tasks (outlining the vessels, find- ing the narrowing or stenosis, and measuring its severity through quantitative coronary analysis, QCA) with separate models trained one after another. A few combined models exist for CT scans, but for X-ray angiography no single network yet produces all three out- puts at once, fuses additional non-image data, and reports its own confidence. This thesis builds and compares three designs of increasing ambition, termed flows, on a 200-patient dataset. Flow 1 is a baseline in which three separate models run in sequence: a U-Net that outlines the vessels, a detector that finds the stenosis, and a stage that measures it. Because each is trained independently, an error early in the chain propagates and is amplified, which is the central weakness this baseline exposes. Flow 2 is the core contri- bution: a single model, GCT-Net, that performs all three tasks together. One shared MaxViT encoder feeds three heads, two that outline the vessels and the stenosis and one that measures the stenosis by focusing only on the detected lesion. A stop-gradient prevents the measuring head from distorting the detection, and the three task losses are balanced automatically rather than by hand. Flow 3 extends GCT-Net into a multi-source model. Alongside the angiogram, it incorporates two inputs a cardiologist also consults, the ECG and the written procedural report, merging them through a lightweight fusion layer (FiLM). It adds four report-derived heads and wraps the measurements in reliable confidence intervals, broadening the output at a small cost in image accuracy. The results show the benefit of joint optimisation: Flow 2 raises the stenosis overlap score (Dice) from 0.465 to 0.610 and lowers the measurement errors from 18.9 pp and 5.7 mm to 11.73 pp and 4.51 mm in a single pass, while Flow 3 trades a little accuracy for broader clinical output. The model is also validated on a separate public dataset (ARCADE), reaching a Dice of 0.523 on 300 unseen images, and is deployed as a web application that converts raw DICOM archives into a structured QCA report.
  • No Thumbnail Available
    Item
    Speech Denoising Using Diffusion Model Technique
    (university of ghardaia, 2026) Laouar Meriem; Zahouani Sarra
    Speech is the primary medium for human communication, yet it is almost always degraded by background noise in real-world environments. This noise reduces intelligibility and harms the performance of critical applications such as automatic speech recognition, telecommunications, and audio streaming. Speech denoising, therefore, plays a vital role in restoring clean speech and ensuring reliable human-machine interaction. This thesis explores diffusion-based generative models for speech denoising, focusing on the DiffWave architecture. The objective is to build a system that produces high-quality enhanced speech while operating fast enough for real-world deployment. To this end, two diffusion step configurations are compared: T=50 and T=200. Although T=200 provides a finer discretization, T=50 achieves better generalization on unseen data (SI-SDR: 10.93 dB vs 9.94 dB), with an optimal inference step of t=5. This is primarily because T=50 was trained for significantly longer (240,000 iterations compared to 65,000 for T=200) due to GPU constraints, allowing it to converge more effectively. To overcome inference latency, Denoising Diffusion Implicit Models (DDIM) are integrated, reducing sampling steps from 50 to just 3. This achieves a real- time factor (RTF) of 0.0732, corresponding to 13.7× real-time performance, with a minimal quality loss of only -0.64 dB. A key contribution is the evaluation on Arabic speech. Although trained exclusively on English digits, the model achieves its best performance on the Arabic dataset (SI-SDR = 3.94 dB), with the majority of test samples showing improvement after processing, confirming strong cross-lingual generalization. This is attributed to the model’s ability to learn latent acoustic representations that transcend language boundaries. The model was also evaluated on French speech using the Common Voice dataset, demonstrating clear cross-lingual generalization capabilities with promis- ing results that support its effectiveness in diverse linguistic environments. The model is also validated on real-world recordings from office, street, and cafeteria environments, confirming its practical applicability beyond controlled laboratory conditions. These results demonstrate that the proposed approach offers a practical, fast, and language-robust solution for speech denoising, suitable for real-time applications.
  • No Thumbnail Available
    Item
    Deep Learning for Real-Time Predictive Maintenance and Adaptive Control in Industrial IoT
    (university of ghardaia, 2026) BENSAHA Aya; KELLOU Ikram
    In the context of Industry 4.0 and the Industrial Internet of Things (IIoT), predictive maintenance has become a major challenge due to the increasing com- plexity of industrial systems and the continuous generation of real-time sensor data. This thesis presents an intelligent framework that combines Deep Learning and Deep Reinforcement Learning techniques for Remaining Useful Life (RUL) prediction and adaptive maintenance decision-making.The proposed framework consists of two complementary stages. In the first stage, a hybrid CNN-LSTM model is developed to learn degradation features and temporal dependencies from multivariate aircraft engine sensor signals. In the second stage, the predicted RUL is used by a Soft Actor-Critic (SAC) reinforcement learning agent to sup- port adaptive maintenance optimization and decision-making.The framework is evaluated using the NASA C-MAPSS datasets under multiple operating condi- tions. Experimental results demonstrate accurate RUL prediction and reliable maintenance decision-making, leading to a reduction in unexpected failures and unnecessary maintenance interventions. The obtained results highlight the poten- tial of integrating predictive analytics and adaptive control to support intelligent maintenance management in Industrial IoT environments.