Autism Spectrum Disorders (ASDs) are neurodevelopmental conditions that usually manifest during childhood. It is a multi-symptom disorder, and its symptoms overlap with several other disorders. The early detection of these disorders is conducive to more successful treatment outcomes, as treatment is more effective before the disorder becomes severe. However, the conventional diagnostic procedures are quite time-consuming, with a typical confirmation period of several months with different specialists in speech and neurology. Recent advances in artificial intelligence (AI), specifically machine learning (ML) and deep learning (DL), have demonstrated considerable potential in addressing the diagnostic challenges associated with autism spectrum disorders (ASDs). In this paper, we propose a range of machine learning models, including a support vector machine (SVM), convolutional neural network (CNN), residual networks (ResNet), and vision transformers (ViT), to detect ASDs based on magnetic resonance images (MRI). The SVM model, in terms of accuracy, outperforms the other similar works, achieving a score of 94.03%.
Flying Ad-Hoc Networks (FANETs), commonly referred to as drones or Unmanned Aerial Vehicles (UAVs), are increasingly transforming various industries by supporting numerous applications. In this context, a UAV can function as a cloud service provider, offering services such as memory, computing, and network connectivity to consumer UAVs. This work introduces an innovative 5G-enabled UAV-Cloud Architecture empowered by deep learning for service selection. The architecture integrates two main modules: (i) A game theory-based module, which establishes an interactive game between provider and consumer UAVs, generating datasets to guide consumer UAVs in selecting suitable providers; and (ii) A deep learning-based module, leveraging the generated datasets to predict optimal service providers. Numerical simulations validate the proposed architecture, highlighting its superior prediction accuracy, reduced time and message complexity, and minimized service discovery and consumption delays compared to existing methods. These advancements are attributed to the synergy of game theory, deep learning, and 5G communication capabilities.
1 January 2022 in International Journal of Organizational and Collective Intelligence
Blood cancer (leukemia) is one of the most serious diseases that affect blood-forming tissues. It usually involves white blood cells. The early detection of this severe disease helps doctors to provide efficient treatment. However, the discovery of this sickness at its first stages is often not easy due to similar morphological characteristics of malignant and healthy blood cells. Flow cytometry was the only used technique for early detection of leukemia, but it is very expensive and usually unavailable in hospitals. Deep learning is a machine learning technique that teaches computers to do what comes naturally to humans learn by examples. In the last few years, deep learning has achieved great successes to solve concrete problems. In particular, it has proven successful in medical imaging classification. In this work, we propose a Convolutional Neural Network (CNN) experiment for the classification of malignant white blood cells from normal ones using a dataset of microscopic images. The proposed approach leads to a balanced model that reaches a high level accuracy.
16 October 2019 in Communications in Computer and Information Science