Potholes are a major concern for road infrastructure, traffic safety, and vehicle maintenance. Manual inspection methods for pothole detection are labor-intensive, time-consuming, and often inefficient for large road networks. This study evaluates and compares the performance of YOLOv5 and Single Shot Detector (SSD) models for automated pothole detection under diverse weather and lighting conditions. Using the Multi-Weather-Based Dataset (MWBD), images captured during daytime, twilight, and nighttime were annotated with bounding boxes and enhanced through data augmentation techniques such as shearing and flipping. Experimental results indicate that YOLOv5 achieves a precision of 92.2%, recall of 89.2%, F1-score of 90.7%, and mAP@0.5 of 90.0%, while SSD achieves a precision of 88.5%, recall of 92.0%, F1-score of 90.2%, and mAP@0.5 of 91.4%. The comparative analysis demonstrates that both models are effective in detecting potholes across varied road textures and environmental conditions, with trade-offs between precision and recall. This study highlights the suitability of deep learning-based object detection models for automated road inspection, reducing human effort, enhancing maintenance efficiency, and improving road safety. The novelty lies in the systematic comparison of YOLOv5 and SSD under multi-weather conditions, providing practical guidance for intelligent transportation systems.

Anemia is a common condition among adults, particularly in children and pregnant women. Anemia is defined as a lack of healthy red blood cells or hemoglobin. Early identification of anemia is critical for excellent health and well-being, which contributes to the sustainable development goals (SDGs), notably SDG 3. The intrusive way to detecting anemia has several hurdles, including anxiety and cost, which impedes health development. With the advent of technology, it is critical to create non-invasive techniques to diagnose anemia that can minimize costs while also improving detection efficacy. A distinct non-invasive technique is developed in this study employing machine learning (ML) models. This study's dataset contains 4260 observations of non-anemic (0) and anemic (1) children. To train the dataset, six (6) different ML models were employed: k-Nearest Neighbor (KNN), decision tree (DT), logistic regression (LR), nave bayes (NB), random forest (RF), and kernel-support vector machine (KSVM). The DT and RF models obtained the highest accuracy of 99.92%, followed by the KNN at 98.98%. The ML models used in this study produced substantial results. The models also received high marks on performance evaluation metrics such as accuracy, recall, F1-score, and Area Under the Curve-Receiver Operating Characteristics (AUC-ROC). When compared to the other ML models, the DT and RF had the best precision (1.000), recall (0.9987), F1-score (0.9994), and AUC-ROC (0.9994) ratings. According to the findings, ML models are crucial in the detection of anemia using a non-invasive technique, which is critical for health facilities to boost efficiency and quality healthcare. Various machine learning models were used in this study to detect anemia in children using palm images. Finally, the findings confirm earlier studies on the effectiveness of ML algorithms as a non-invasive means of detecting iron deficiency anemia.