Early detection and timely breast cancer treatment improve survival rates and patients’ quality of life. Hence, many computer-assisted techniques based on artificial intelligence are being introduced into the traditional diagnostic workflow. This inclusion of automatic diagnostic systems speeds up diagnosis and helps medical professionals by relieving their work pressure. This study proposes a breast cancer detection framework based on a deep convolutional neural network. To mine useful information about breast cancer through breast histopathology images of the 40× magnification factor that are publicly available, the BreakHis dataset and IDC(Invasive ductal carcinoma) dataset are used. Pre-trained convolutional neural network (CNN) models EfficientNetB0, ResNet50, and Xception are tested for this study. The top layers of these architectures are replaced by custom layers to make the whole architecture specific to the breast cancer detection task. It is seen that the customized Xception model outperformed other frameworks. It gave an accuracy of 93.33% for the 40× zoom images of the BreakHis dataset. The networks are trained using 70% data consisting of BreakHis 40× histopathological images as training data and validated on 30% of the total 40× images as unseen testing and validation data. The histopathology image set is augmented by performing various image transforms. Dropout and batch normalization are used as regularization techniques. Further, the proposed model with enhanced pre-trained Xception CNN is fine-tuned and tested on a part of the IDC dataset. For the IDC dataset training, validation, and testing percentages are kept as 60%, 20%, and 20%, respectively. It obtained an accuracy of 88.08% for the IDC dataset for recognizing invasive ductal carcinoma from H&E-stained histopathological tissue samples of breast tissues. Weights learned during training on the BreakHis dataset are kept the same while training the model on IDC dataset. Thus, this study enhances and customizes functionality of pre-trained model as per the task of classification on the BreakHis and IDC datasets. This study also tries to apply the transfer learning approach for the designed model to another similar classification task.

Trypanosoma evansi infection has started to become a wide spread phenomena around the camel-rearing areas of North Africa and the Middle East. The disease caused by trypanosomes is locally known as “Surra” and it can seriously impact not only the health of domestic animals but the local economy as well. After taking over the management of a farm containing approximately 700 camels, it was found that a large number were suffering from trypanosome infection and it was of the utmost importance to find the source of this infection. An extensive dive into the records and observations were initially made to identify the infected population. Under closer inspection it was found that the infection was limited mostly to female individuals that had undergone extended reproductive analysis or treatment. Blood samples were taken from each of the individuals for buffy coat test and blood smears. Among the total number of tested camels (n = 590), almost 40% were infected with trypanosomes. The number and percentage of infection correlate with the number of fertility and pregnancy treatments that the camels had undergone. The most severely infected group, underwent between 17 and 20 instances of treatment or tests, had an infection rate of almost 90%. The devastating effect of trypanosomiasis on camel pregnancy and birth were also verified with 61% of all abortions and 82% of all neonatal deaths coming from trypanosome infected individuals. These results clearly demonstrate how damaging iatrogenic infections of T. evansi can be and how simply they could have been prevented.

Clean water is essential for human health and life, and assessing its potability is critical for safeguarding public well-being. Machine Learning (ML) algorithms have been widely used for water potability classification based on various water quality parameters. However, the performance of these models strongly depends on effective hyperparameter tuning, which remains both challenging and resource-intensive. This study addresses this issue by proposing the Firefly Optimization Algorithm (FOA) to optimize the Support Vector Classifier (SVC) for water potability classification. Traditional hyperparameter tuning methods, such as GridSearchCV and RandomizedSearchCV, often lack the efficiency and effectiveness needed for achieving optimal model performance. In contrast, the proposed FOA-based approach provides a robust solution, demonstrating superior results compared with traditional methods. Model performance was evaluated using accuracy, precision, recall, F1-score, and Area Under the Curve (AUC). The FOA-tuned SVC achieved an accuracy of 0.6773 and an AUC of 0.7065, outperforming models tuned with conventional methods. These findings highlight the potential of nature-inspired optimization techniques, such as the Firefly algorithm, to enhance ML model performance and offer a promising approach to water potability classification.