Knee osteoarthritis (KOA) is a widespread degenerative joint disease that affects millions globally. While manual interpretation of X-ray images remains common in clinical practice, it is time-consuming and prone to subjective errors. In this study, we propose a hybrid automated diagnostic model for KOA detection using feature extraction from Convolutional Neural Networks (CNNs) combined with traditional feature selection methods. The hybrid Feature Selection (FS) strategy includes Mutual Information (MI), Linear Discriminant Analysis (LDA),Analysis of Variance(ANOVA), and K-means clustering. In addition, advanced deep learning architectures such as ResNet and EfficientNet were incorporated for benchmarking purposes to evaluate the effectiveness of the proposed hybrid model. To enhance the robustness of the proposed model , advance deep learning architectures were also considered for comparative analysis. The model received training and validated using a publicly available X-ray dataset containing 3,815 images obtained from the Kaggle repository. After preprocessing and balancing the dataset, we extracted deep features via a retrained CNN and selected the most informative features using the hybrid (FS) strategy. The proposed model achieved a prediction accuracy of (98%), The novelty of this work lies in integrating deep learning with multiple statistical feature selection techniques within a unified hybrid framework for early KOA detection accuracy and reducing diagnostic workload but also enhances model generalizability and robustness. The study also acknowledges limitations such as dataset imbalance and lack of external validation.
In the literature, three-stage switching networks have been considered for nodes in elastic optical networks, where switches with spectrum conversion capability are placed in the first and third stages (wavelength–space–wavelength—WSW) or only in the second stage (space–wavelength–space—SWS). This paper proposes three-stage switching networks where the switches with spectrum conversion functions are located only in the first stage (wavelength–space–space—WSS) or only in the third stage (space–space–wavelength—SSW). For these networks, the strict-sense non-blocking conditions are derived and proved, and the number of elements required for their construction is assessed. It turns out that the proposed networks can be constructed with 50% fewer tunable spectrum converters than in the WSW networks, and this reduction is even greater in the case of the SWS networks.