Semen analysis is an important analysis for male infertility primary investigation and manual semen analysis is a conventional method to assess it. Manual semen analysis has been revealed with accuracy and precision limitations due to noncompliance to guidelines and procedures. Sperm motility and concentration are the main indicators for pregnancy and conception rate hence they were selected for parameters prediction. Convolutional neural network (CNN) has benefited computer vision application industry in recent years and has been widely applied in computer vision research tasks. In this paper, three-dimensional CNN (3DCNN) was designed to extract motion and temporal features, which are vital for sperm motility prediction. For sperm concentration, since two-dimensional CNN (2DCNN) is efficient in recognizing and extracting spatial features, well-established Residual Network (ResNet) architecture was adopted and customized for sperm concentration prediction. Multimodal learning approach is a technique to aggregate learnt features from different deep learning architecture that adopted other forms of modalities, which could provide deep learning model with better insights on their tasks. Hence, a multimodal learning deep learning architecture was designed to receive both image-based (frames extracted from video samples) and video-based (stacked frames pre-processed from video samples) input that could provide well-extracted spatial and temporal features for sperm parameters prediction. The results obtained using the proposed methodology have surpassed other similar research works who used deep learning approach. For sperm motility, its best achieved average mean absolute error (MAE) was 8.048, and sperm concentration obtained a competent Pearson’s correlation coefficient (RP) value of 0.853.

Supervised machine learning has been widely applied in healthcare, yet few studies emphasize feature selection's role in enhancing predictive accuracy. Identifying research that exclusively employs feature selection for GDM detection remains challenging. This study designs an optimized supervised learning framework using Recursive Feature Elimination (RFE) to improve early GDM detection and assist medical professionals in patient evaluation. RFE systematically ranks features by iteratively removing the least relevant ones until no further improvement through various estimators. The selected features are then used to build several frameworks based on five well established machine learning models. Results indicate that the integration of Recursive Feature Elimination (RFE) with a Random Forest as both estimator and classifier achieves the highest accuracy (97.31%) and F1-score (96.6%). These findings demonstrate RFE’s effectiveness in optimizing feature selection, enhancing model accuracy, and reducing computational cost through utilizing 6 number of features. In conclusion, incorporating RFE within supervised learning frameworks significantly improves GDM detection. This research contributes to developing automated diagnostic tools that assist healthcare professionals in evaluating patient health and predicting diseases, ultimately enhancing early diagnosis and improving patient outcomes, especially for pregnant women at risk of GDM.

The excellent quality of color fundus photograph is crucial for the ophthalmologist to process the correct diagnosis and for convolutional neural network (CNN) models to optimize output classification. As a result of main causes as acquire devises efficiency and experience of a physician most fundus photographs can have uneven illuminance, blur, and bad contrast, in addition to micro-features of retinal diseases, which need to force their contrast. Fundus photograph quality assessment method is proposed to find out the perfect enhanced color fundus Technique in fundoscopy photographs-based CNN model. Five photograph quality measurements, in addition to five CNN metrics, were used as standard in this study. In this research innovative approach combining photograph quality measurement and CNN metrics analysis is proposed to find out the best enhance method that is set for the multiclass CNN model. The contrast enhancement techniques are evaluated using 267 color fundus photographs divided into three retina diseases cases were downloaded from the open-source database “FIGSHARE”. The study outcome showed that the presented system (single-CNN) can determine well the contrast enhancement method, as well as the low-quality fundus photograph then it can boost CNN metrics to achieve superior.

Accurate recognition of complex human activities from wearable sensors plays a critical role in sports analytics and human performance monitoring. However, the high dimensionality and redundancy of raw inertial data can hinder model performance and interpretability. This study proposes a hybrid feature selection framework that combines Minimum Redundancy Maximum Relevance (MRMR) and Regularized Neighborhood Component Analysis (RNCA) to improve classification accuracy while reducing computational complexity. Multi-sensor inertial data were collected from field hockey players performing six activity types. Time- and frequency-domain features were extracted from four body-mounted inertial measurement units (IMUs), resulting in 432 initial features. MRMR, combined with Pearson correlation filtering (|ρ| > 0.7), eliminated redundant features, and RNCA further refined the subset by learning supervised feature weights. The final model achieved a test accuracy of 92.82% and F1-score of 86.91% using only 83 features, surpassing the MRMR-only configuration and slightly outperforming the full feature set. This performance was supported by reduced training time, improved confusion matrix profiles, and enhanced class separability in PCA and t-SNE visualizations. These results demonstrate the effectiveness of the proposed two-stage feature selection method in optimizing classification performance while enhancing model efficiency and interpretability for real-time human activity recognition systems.

Colorectal cancer is one of the most common cancers in the world, and it is also one of the leading causes of mortality from cancer. Over time, polyp development on the inner lining of the colon or rectum may progress to cancer. Due to the differences in size, shape, and color, this is a difficult undertaking polyp texture and differences between several forms of hard polyps mimics. Colonoscopy is the most effective way to detect polyps. Screening and detection are possible, but they are operator-dependent, time-consuming, and prone to errors. Polyp segmentation method based on the convolutional neural network is developed and to enhance the performance of the method. In this study, polyp segmentation algorithm was developed using Python as the main programming language which was applied with TensorFlow and OpenCV on Kvasir-SEG datasets. DeepLabv3+ model was used to train the filters and pooling operations were applied to images to segment the polyps. The data obtained was further analysed and evaluated the performance analysis. As a result, the developed algorithm was tested and shows an average accuracy 0.7215 and average IoU score 0.7240 for 20 epochs. As a conclusion, the algorithm developed is able to segment the polyps and it can be further developed with large number of data to improve the accuracy.