| Time | Event |
|---|---|
| 8:30 AM - 9:00 AM | Registration and Breakfast |
| 9:00 AM - 9:30 AM |
Opening speech: Dr. Belaid Bougadir: President of Cadi Ayyad university Dr. Hassan Ayyad: Director of ENSA Marrakech Dr. KC Santosh: Honorary chair Dr. Anas Abou El Kalam: General chair |
| 9:30 AM - 10:30 AM | Keynote speech: Dr. Djamila Aaouad |
| 10:45 AM - 12:30 PM | In person presentations |
| 12:30 PM - 1:30 PM | Lunch |
| 1:30 PM - 2:30 PM | Keynote speech: Dr. Abdeslam Jakjoud |
| 3:45 PM - 7:00 PM | Session I: Track I and Track II in Parallel (Online) |
| 7:00 PM - 7:15 PM | Tea break and networking |
| 7:30 PM - 8:30 PM | Cultural event |
| Time | Event |
|---|---|
| 8:30 AM - 9:30 AM | Registration and Breakfast |
| 9:30 AM - 10:30 AM | Keynote speech: Dr. Ravindra Hegadi |
| 10:45 AM - 1:45 PM | Session II: Track I and Track II in Parallel (Online) |
| 2:00 PM - 3:00 PM | Lunch |
| 3:00 PM - 4:00 PM | Keynote speech: Dr. Mo Medwani |
| 4:15 PM - 7:15 PM | Session III: Track I |
| 7:15 PM - 7:30 PM | Tea break and networking |
| 7:30 PM - 8:30 PM | Cultural event |
| Time | Event |
|---|---|
| 8:30 AM - 9:30 AM | Registration |
| 9:30 AM - 10:30 AM | Keynote speech: Dr. KC Santosh |
| 10:45 AM - 1:45 PM | Session III: Track II |
Session: I (Online) Track I: Advanced Computer Vision and Object Detection
| SoP | P Id | Title |
|---|---|---|
| 1 | 6 | Enhancing Deaf Communication: Nepali Sign Language Recognition using YOLOv8 and NepaNet |
| 2 | 10 | Lightweight Transformer with Graph Attention for UAV Image Super-Resolution |
| 3 | 36 | Vision-Based Obstacle Detection and Avoidance for Agricultural Drones Using YOLOv8 |
| 4 | 65 | Automated Car Damage Identification via YOLOv8 and Computer Vision Techniques |
| 5 | 49 | Text Extraction from Natural Scene Image using YOLO8 |
| 6 | 88 | Real-Time Underwater Crack Detection with YOLOv11 on Raspberry Pi for Marine Infrastructure Inspection |
| 7 | 102 | Bangladeshi License Plate Detection and Recognition Using YOLO Variants and Enhanced OCR with Model Interpretability |
| 8 | 107 | Benchmarking YOLOv11 and YOLOv12 for Peripheral Blood Cell Detection: Analysis of the impact of Model Scale and Dataset Quality |
| 9 | 22 | Efficient Image Encoding Approaches for Vision based IoT Systems |
| 10 | 55 | FreshDetect: Real-Time Fruit Freshness Evaluation Using Deep Learning |
| 11 | 92 | 3D Reconstruction: Depth Estimation of the UAV Based Fruit Trees with 2D images |
| 12 | 117 | Survey on Smart traffic flow architecture for autonomous vehicle |
| 13 | 86 | SwinRH-DeBlur: A Unified CNN-Swin Transformer Residual Hybrid Deblurrer for Realistic Motion Blur Removal |
| SoP | P Id | Title |
|---|---|---|
| 1 | 19 | Quantitative Texture Evaluation of Placental Ultrasound Images for Fetal Morbidity Analysis |
| 2 | 40 | Advancing Endoscopic Diagnosis: A Comparative Study of CNNs and Tuned Multimodal LLMs with Interpretable Insights |
| 3 | 43 | Deep Learning for Lung Cancer Classification: Evaluating CNNs with Saliency Maps and Grad-CAM on CT Scans |
| 4 | 44 | Custom and Hybrid CNN Architectures for Gastric Cancer Histopathology Image Classification: A Comparative Study on GCHTID |
| 5 | 41 | Hybrid Deep Learning Models for Multiclass Classification of Sperm Morphology Using CNN and Vision Transformer Architectures |
| 6 | 99 | Breast Cancer Classification in Ultrasound via ViT-CNN-ATS |
| 7 | 140 | Deep Learning-Based Brain Tumor Classification from Multi-Slice MRI: A Comparison of CNN Architectures |
| 8 | 141 | Deep Learning Approach for B-Cell Non-Hodgkin Lymphoma Subtype Classification Using Histopathological Image |
| 9 | 42 | FusionAI: A Dual-Modality Deep Learning Framework Combining CT Imaging and Biochemical Markers for Early Kidney Cancer Detection |
| 10 | 177 | Enhanced U-Net Architecture with VGG16 Backbone and Attention Mechanisms for Automated Nasal Sinus Disease Segmentation |
| 11 | 120 | Deep Learning-Based Diagnosis of Keratoconus: A Comparative Study of MobileNetV2, VGG16, and InceptionV3 Models |
| 12 | 170 | Brain Tumor Classification Using MobileNet-ViT with Visual Explainability through Grad-CAM |
| 13 | 85 | RetinaFormer: A Hybrid Vision Transformer-CNN Architecture for Diabetic Retinopathy Grading |
| 14 | 143 | Integrating Feature Reduction and Machine Learning for Breast Cancer Diagnosis: An LDA-Based Approach |
Session: II (Online) Track I: Deep Learning in Biomedical and Cognitive Sciences
| SoP | P Id | Title |
|---|---|---|
| 1 | 47 | Explainable Deep Learning for Multi-Class ECG Classification Using Hybrid Vision Transformer Models |
| 2 | 122 | Predicting the Outcome of rTMS Depression Therapy using EEG signals and CNN |
| 3 | 123 | Predicting the outcome of rTMS depression therapy using CQT and CNN |
| 4 | 111 | Deep Convolutional Architectures for EEG Classification: A Comparative Study with Temporal Augmentation and Confidence-Based Voting |
| 5 | 110 | Enhancing Code-Modulated Visual Evoked Potential Classification for Brain-Computer Interfaces with Laplacian Spatial Filters |
| 6 | 112 | M-NetTr: Transformer Architecture for Retinal Vascular Segmentation using Fundus Images |
| 7 | 81 | A Novel Approach for Classification of Different Types of Dementia Using Depthwise Separable Convolution Neural Network |
| 8 | 139 | Recognizing Cardiovascular Risk Patterns using Ensemble Learning Algorithms |
| 9 | 101 | A Unified Approach to Skin Cancer Classification and Stage Detection |
| 10 | 168 | Machine Learning-Based Dengue Diagnosis Using Clinical and Routine Hematological Data Without Antigen Testing: Evidence from Bangladesh |
| 11 | 94 | Diagnosis of Domestic Animal Skin Diseases: An Advanced Deep Architecture Approach |
| 12 | 96 | Benchmarking Deep Neural Network Architectures for Multi-Class Cardiac Condition Classification |
| SoP | P Id | Title |
|---|---|---|
| 1 | 61 | A Data Analysis on Diabetic Patients Using Data Mining Tools and Prediction Algorithms |
| 2 | 78 | Exploratory Analysis of Factors Influencing Cognitive Decline and the Classification of Diverse Health Domains Across Regional and Demographic Populations |
| 3 | 79 | Healthcare Facilities in India Across States/UTs Using Exploratory Data Analysis Concepts |
| 4 | 17 | Leveraging Deep Learning Model for Advanced Anomaly Detection in Apple Harvests in India |
| 5 | 71 | Sugarcane Disease Detection Using Machine Learning |
| 6 | 146 | Visual interpretable methods for skeleton Models |
| 7 | 151 | Delving into Deep Learning: Unrevealing Academic Horizons through metric study |
| 8 | 95 | Transparency in Fabric Defect Detection by Leveraging Explainable AI in Deep Learning Models |
| 9 | 48 | Low Resource Multimodal Translation of Nepali Spoken Words into Emotion-Conditioned Sign Language Avatars. |
| 10 | 82 | GenZ Phrase Translation using Multi-model Machine Learning Approach |
| 11 | 75 | A Hybrid Approach for Telugu Script Identification in Multilingual Digital Document Images |
Session: III (Online) Track I: Secure and Ethical AI Applications
| SoP | P Id | Title |
|---|---|---|
| 1 | 171 | AI-Driven Predictive Policing and Facial Recognition in Rajasthan: A Critical Analysis of the Abhay Command Center |
| 2 | 172 | In-Depth Web Vulnerability Assessment via Open-Source Intelligence Techniques |
| 3 | 74 | Comparative Analysis of Deep Learning and Machine Learning Approaches for the Detection of Hardware Trojans |
| 4 | 183 | DeepSecure-A CNN and LSTM based approach for DeepFake detection |
| 5 | 76 | Advancing Person Authentication: Integrating Face and Finger Vein Biometrics Using DCNN-Based Feature Fusion |
| 6 | 174 | Singularity in Neural Trainings |
| 7 | 103 | AI-Assisted Semi-Supervised Framework for Efficient Annotation of Suspicious Activities in Computer Lab CCTV Footage |
| 8 | 178 | A Smart Multi Plant Disease Detection Utilizing AI through Website and WhatsApp Chatbot |
| 9 | 93 | Deep Learning-Based Image Captioning with ResNet-50 and GRU for Assistive Applications |
| 10 | 38 | Snap to Cook — AI Recipe Generator from Food Image Using Residual Network: ResNet101 |
| 11 | 25 | Robust Feature Learning for Adversarial Defense: A Margin-Based Supervised Contrastive Framework |
| 12 | 176 | Explainable AI Driven Prediction for Betel Leaf Disease Classification using Grad-CAM |
| SoP | P Id | Title |
|---|---|---|
| 1 | 77 | Efficient Segmentation and Analysis Automation of LiDAR Data |
| 2 | 116 | Design and Evaluation of a Multi-Agent RAG System for Automated Knowledge Extraction and Task Generation |
| 3 | 129 | Multimodal Deep Learning Framework for Automated Detection and Classification of Lung Diseases Using 3D CT Scans and Clinical Data |
| 4 | 84 | Deep Learning Based Multi-Class Human Fall Detection System using K-Fall dataset for Wearable Devices |
| 5 | 113 | Attention-Based Hybrid ViT-ResNet Model for Bangladeshi Mango Classification |
| 6 | 184 | Brain Cancer Detection using Deep Learning Models Empowered by ensemble approach |
| 7 | 124 | Multimodal Suicide Risk Detection on Social Media using Deep Learning and Transformer Architectures |
| 8 | 175 | Air-Written Digit Recognition with CNN(ResNet-18) and BiLSTM: A Spatio-Temporal Approach on ISI-Air Dataset |
| 9 | 80 | A Code-mixed Hausa-English Parallel QA Corpus for Bilingual Question Answering: Design, Implementation, and Evaluation |
| 10 | 98 | Efficient Lung CT Volume Reduction through Adaptive Seed Point Detection for Slice Discarding |
Session: IV (In person)
| SoP | P Id | Title |
|---|---|---|
| 1 | 118 | Mono Temporal Buffer-Based Spatial Generalization in CNNs for Damage Detection Post Flood using High-Resolution Aerial Imagery |
| 2 | 142 | An integrated approach for recognition of plant leaf disease using CNN and SVM |
| 3 | 169 | Enhancing Data Security with the Innovative MLADE Framework for Multi-Level Encryption |
| 4 | 173 | Uncertainty-Quantification and ML Explainability for Cervical Cancer Classification |
| 5 | 182 | AI-driven Framework for Enhancing Security and Quality of Service in Avionics Systems |
