The study of neuroimaging is a very important tool in the diagnosis of central nervous system tumors. This paper presents the evaluation of seven deep convolutional neural network (CNN) models for the task of brain tumor classification. A generic CNN model is implemented and six pre-trained CNN models are studied. For this proposal, the dataset utilized in this paper is Msoud, which includes Fighshare, SARTAJ, and Br35H datasets, containing 7023 MRI images. The magnetic resonance imaging (MRI) in the dataset belongs to four classes, three brain tumors, including Glioma, Meningioma, and Pituitary, and one class of healthy brains. The models are trained with input MRI images with several preprocessing strategies applied in this paper. The CNN models evaluated are Generic CNN, ResNet50, InceptionV3, InceptionResNetV2, Xception, MobileNetV2, and EfficientNetB0. In the comparison of all CNN models, including a generic CNN and six pre-trained models, the best CNN model for this dataset was InceptionV3, which obtained an average Accuracy of 97.12%. The development of these techniques could help clinicians specializing in the early detection of brain tumors.

Early and accurate identification of brain tumors is essential for determining effective treatment strategies and improving patient outcomes. Artificial intelligence (AI) and deep learning (DL) techniques have shown promise in automating diagnostic tasks based on magnetic resonance imaging (MRI). This study evaluates the performance of four pre-trained deep convolutional neural network (CNN) architectures for the automatic multi-class classification of brain tumors into four categories: Glioma, Meningioma, Pituitary, and No Tumor. The proposed approach utilizes the publicly accessible Brain Tumor MRI Msoud dataset, consisting of 7023 images, with 5712 provided for training and 1311 for testing. To assess the impact of data availability, subsets containing 25%, 50%, 75%, and 100% of the training data were used. A stratified five-fold cross-validation technique was applied. The CNN architectures evaluated include DeiT3_base_patch16_224, Xception41, Inception_v4, and Swin_Tiny_Patch4_Window7_224, all fine-tuned using transfer learning. The training pipeline incorporated advanced preprocessing and image data augmentation techniques to enhance robustness and mitigate overfitting. Among the models tested, Swin_Tiny_Patch4_Window7_224 achieved the highest classification Accuracy of 99.24% on the test set using 75% of the training data. This model demonstrated superior generalization across all tumor classes and effectively addressed class imbalance issues. Furthermore, we deployed and benchmarked the best-performing DL model on embedded AI platforms (Jetson AGX Xavier and Orin Nano), demonstrating their capability for real-time inference and highlighting their feasibility for edge-based clinical deployment. The results highlight the strong potential of pre-trained deep CNN and transformer-based architectures in medical image analysis. The proposed approach provides a scalable and energy-efficient solution for automated brain tumor diagnosis, facilitating the integration of AI into clinical workflows.

Deep vein thrombosis is a condition associated with substantial morbidity and a high risk of pulmonary embolism, underscoring the need for rapid and reliable diagnostic solutions. Although machine learning and deep learning techniques are increasingly being applied for clinical decision support, comprehensive analyses of their contributions to early detection, risk prediction, and monitoring remain limited. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses 2020 guidelines, we conducted a systematic search in ScienceDirect, IEEE Xplore, Scopus, and Web of Science for studies published between January 2014 and March 2025. Eligible studies applied machine learning or deep learning approaches for the early prediction, monitoring, or risk assessment of deep vein thrombosis, or described reference datasets for algorithm development. Two authors independently extracted data and evaluated methodological quality using the Quality Assessment of Diagnostic Accuracy Studies-2 framework. The included studies were categorized into four domains: Early prediction, monitoring, risk assessment, and reference datasets. In total, 66 studies met the inclusion criteria. Recent advances include deep learning-assisted ultrasound interpretation and real-time implementation of machine learning algorithms. While most studies demonstrated a low overall risk of bias, recurring limitations were identified in terms of patient selection, reporting practices, and validation strategies. Dataset harmonization and external validation were infrequently performed, and documentation of data provenance and class imbalance handling was inconsistent. Machine learning and deep learning approaches demonstrate considerable potential to accelerate accurate diagnoses and facilitate individualized risk stratification; however, their translation into routine practice requires standardized datasets, rigorous external validation, and integration into existing clinical workflows. This review consolidates a decade of research, links methodological quality to clinical applicability, and provides a task-oriented roadmap for advancing machine learning-enabled diagnostics and monitoring in the context of deep vein thrombosis.

Solar trackers represent a significant advancement in enhancing the efficiency of solar energy collection. This study describes the development and implementation of a passive solar tracker featuring a single horizontal axis of rotation and an innovative guide slot mechanism. The tracker is designed to be used with solar radiation-capturing devices. The guide slot mechanism is specifically engineered for a designated date, location, and period to follow the solar trajectory accurately. A contact follower moves along the guide slot, which drives a tracker disk to rotate by the solar trajectory. The mechanism is activated by the movement of a liquid container attached to a spring, thereby storing potential energy. The container releases the liquid through a mechanical valve that regulates the container’s movement, while the guide slot mechanism converts this movement into controlled rotational motion, which is transferred to a mobile structure mounting the solar panel. Notably, the majority of materials utilized in this construction are recycled. Furthermore, the solar tracker proposed in this work is designed to be operable by individuals with limited prior knowledge on the topic, emphasizing the primary contribution of this study: its potential to revolutionize energy collection in developing countries and marginalized urban areas. No similar systems are found upon comparison with existing models in the literature. Experiments conducted with a static solar panel and the same panel integrated into the passive solar tracker revealed a 30.87% improvement in energy collection efficiency over static solar panels.

Brain tumors, encompassing subtypes with distinct progression and risk profiles, are a serious public health concern. Magnetic resonance imaging (MRI) is the primary imaging modality for non-invasive assessment, providing the contrast and detail necessary for diagnosis, subtype classification, and individualized care planning. In this paper, we evaluate the capability of modern deep learning models to classify gliomas as high-grade (HGG) or low-grade (LGG) using reduced training data from MRI scans. Utilizing the BraTS 2019 best-slice dataset (2185 images in two classes, HGG and LGG) divided in two folders, training and testing, with different images obtained from different patients, we created subsets including 10%, 25%, 50%, 75%, and 100% of the dataset. Six deep learning architectures, DeiT3_base_patch16_224, Inception_v4, Xception41, ConvNextV2_tiny, swin_tiny_patch4_window7_224, and EfficientNet_B0, were evaluated utilizing three-fold cross-validation (k = 3) and increasingly large training datasets. Explainability was assessed using Grad-CAM. With 25% of the training data, DeiT3_base_patch16_224 achieved an accuracy of 99.401% and an F1-Score of 99.403%. Under the same conditions, Inception_v4 achieved an accuracy of 99.212% and a F1-Score of 99.222%. Considering how the models performed across both data subsets and their compute demands, Inception_v4 struck the best balance for MRI-based glioma classification. Both convolutional networks and vision transformers achieved superior discrimination between HGGs and LGGs, even under data-limited conditions. Architectural disparities became increasingly apparent as training data diminished, highlighting unique inductive biases and efficiency characteristics. Even with a relatively limited amount of training data, current deep learning (DL) methods can achieve reliable performance in classifying gliomas from MRI scans. Among the architectures evaluated, Inception_v4 offered the most consistent balance between accuracy, F1-Score, and computational cost, making it a strong candidate for integration into MRI-based clinical workflows.