Hybrid AI architectures are emerging as a powerful solution for complex decision support systems (DSS) that must handle uncertainty, heterogeneous data, and large-scale integration. Traditional AI methods are limited in addressing real-world multidimensional challenges. This paper analyzes hybrid AI systems that combine symbolic approaches (rule-based reasoning, interpretability) with sub-symbolic methods (machine learning, neural networks) to improve flexibility and robustness. A modular framework is proposed, consisting of data preprocessing, knowledge representation, inference, and learning components, enabling both offline training and real-time decision-making. The study highlights key challenges such as scalability, knowledge integration, and computational efficiency. Experimental results demonstrate that hybrid models outperform standalone AI techniques in accuracy, precision, recall, and efficiency, especially in dynamic and uncertain environments. The paper concludes by suggesting future directions, including explainable AI and scalable distributed architectures.
Riyaz Mohammed, Pooja Agarwal· International Journal of Art...· 0 citations
Image classification is a major area in computer vision, driven by rapid advances in deep learning. Over the last decade, convolutional neural networks (CNNs) and their variants have achieved high performance in applications such as medical diagnosis, autonomous driving, industrial inspection, remote sensing, and biometrics. However, choosing the right model remains challenging due to trade-offs between accuracy, computational cost, efficiency, and robustness. This paper presents a comparative study of different deep learning architectures, including classical CNNs, deep hierarchical models, residual and dense networks, and compound-scaled architectures. Using a common evaluation framework and standard datasets, the study analyzes performance based on key design factors such as depth, width, receptive field, skip connections, and normalization. Theoretical concepts like convolution operations, residual learning, and optimization are also discussed.The results show that deeper networks provide better representation, while residual connections and compound scaling improve training stability and efficiency. Lightweight models perform well in resource-limited and real-time environments. Overall, the study offers practical guidance for selecting suitable architectures and highlights future research areas such as neural architecture search, self-supervised learning, and efficient model deployment.
Riyaz Mohammed· International Journal of App...· 0 citations