Abstract
Great advances in stitching high-quality retinal images have been made in recent years. On the other hand, very few studies have been carried out on low-resolution retinal imaging. This work investigates the challenges of low-resolution retinal images obtained by the D-EYE smartphone-based fundus camera. The proposed method uses homography estimation to register and stitch low-quality retinal images into a cohesive mosaic. First, a Siamese neural network extracts features from a pair of images, after which the correlation of their feature maps is computed. This correlation map is fed through four independent CNNs to estimate the homography parameters, each specializing in different corner coordinates. Our model was trained on a synthetic dataset generated from the Microsoft Common Objects in Context (MSCOCO) dataset; this work added an important data augmentation phase to improve the quality of the model. Then, the same is evaluated on the FIRE retina and D-EYE datasets for performance measurement using the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM). The obtained results are promising: the average PSNR was 26.14 dB, with an SSIM of 0.96 on the D-EYE dataset. Compared to the method that uses a single neural network for homography calculations, our approach improves the PSNR by 7.96 dB and achieves a 7.86% higher SSIM score.

Abstract
Objectives: As epilepsy management medical devices emerge as potential technological solutions for prediction and prevention of sudden death in epilepsy (SUDEP), there is a gap in understanding the features and priorities that should be included in the design of these devices. This study aims to bridge the gap between current technology and emerging needs by leveraging insights from persons with epilepsy (PWE) and caregivers (CG) on current epilepsy management devices and understanding how SUDEP awareness influences preferences and design considerations for potential future solutions. Methods: Two cross-sectional surveys were designed to survey PWE and CG on medical device design features, SUDEP awareness, and participation in medical device research. Data analysis included both qualitative thematic analysis and quantitative statistical analysis. Results: The survey revealed that among 284 responses, CG were more aware of SUDEP than PWE. Comfort was identified as the primary concern regarding wearable medical devices for epilepsy management with significant differences between PWE and CG regarding acceptance and continuous use preferences. The thematic analysis identified integration with daily life, aesthetic and emotional resonance, adaptability to seizure characteristics, and user-centric design specifications as crucial factors to be considered for enhanced medical device adoption. The integration of a companion app is seen as an important tool to enhance communication and data sharing. Discussion: This study reveals that while SUDEP awareness can promote the development of future SUDEP predictive and preventive medical devices, these should be designed to mitigate its impact on daily life and anxiety of both PWE and CG. Comfort and acceptance are seen as key priorities to support continuous use and are seen as a technical requirement of future medical devices for SUDEP prediction and prevention. Widespread adoption requires these technologies to be customizable to adapt to different lifestyles and social situations. A holistic approach should be used in the design of future medical devices to capture several dimensions of PWE and CG epilepsy management journey and uphold communication between healthcare professionals, PWE and CG. Conclusion: Data from this study highlight the importance of considering user preferences and experiences in the design of epilepsy management medical devices with potential applicability for SUDEP prediction and prevention. By employing user-centered design methods this research provides valuable insights to inform the development of future SUDEP prediction and prevention devices.

Abstract
Demand Driven Material Requirements Planning argues that production replenishment orders should be scheduled on the shop floor according to the buffers' on-hand inventory. However, the actual performance impact of this remains largely unknown. Using discrete event simulation, this study compares scheduling based on the on-hand inventory, with scheduling based on the inventory net flow position. Results of our study show that scheduling based on the former performs best, particularly when multiple production orders are simultaneously generated and progress independently on the shop floor. Our finds give hints that are important to both, industrial practice and software development for production planning and control.

Abstract
Reconfigurable Intelligent Surfaces (RIS) are an enabling technology widely investigated towards 6G. The viability of large active metasurfaces is constrained by the RF performance, cost, and power consumption. The number of switches per unit cell is a key design parameter that designers aim to minimize following cost and power consumption drivers. However, an efficient use of the aperture is ultimately required and although a one-to-one correspondence between number of switches and phase-quantization bits seems intuitive, one may question its impact. Here we present a full-wave evaluation of a 30x30 1-bit reflective RIS, implemented considering two pin diodes per unit cell. The RIS allows scanning up to 60 degrees from 28 to 29 GHz with a maximum aperture efficiency of 22%. This superior performance provides tantalizing evidence that the multiple switches per bit approach should not be discarded a priori due to its apparent higher complexity.

Abstract
Lung cancer is a significant global health concern, and accurate classification of lung nodules plays a crucial role in its early detection and treatment. This paper evaluates and compares the performance of Vision Transformer (ViT) and Convolutional Neural Network (CNN) models for lung nodule classification using the Pylung tool proposed in this work. The study aims to address the lack of research on ViT in lung nodule classification and proposes ViT as an alternative to CNN. The Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) dataset is utilized for training and evaluation. The Pylung tool is employed for dataset preprocessing and comparison of models. Three models, ViT, VGG16, and ResNet50, are analyzed, and their hyperparameters are optimized using Optuna. The results show that ViT achieves the highest accuracy (99.06%) in nodule classification compared to VGG16 (98.71%) and ResNet50 (98.46%). The study contributes by introducing ViT as a model for lung nodule classification, presenting the Pylung tool for model comparison, and suggesting further investigations to improve the accuracy. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

Abstract
Precision agriculture (PA) has advanced agricultural practices, offering new opportunities for crop management and yield optimization. The use of unmanned aerial vehicles (UAVs) in PA enables high-resolution data acquisition, which has been adopted across different agricultural sectors. However, its application for decision support in chestnut plantations remains under-represented. This study presents the initial development of a methodology for segmenting chestnut burrs from UAV-based imagery to estimate its productivity in point cloud data. Deep learning (DL) architectures, including U-Net, LinkNet, and PSPNet, were employed for chestnut burr segmentation in UAV images captured at a 30 m flight height, with YOLOv8m trained for comparison. Two datasets were used for training and to evaluate the models: one newly introduced in this study and an existing dataset. U-Net demonstrated the best performance, achieving an F1-score of 0.56 and a counting accuracy of 0.71 on the proposed dataset, using a combination of both datasets during training. The primary challenge encountered was that burrs often tend to grow in clusters, leading to unified regions in segmentation, making object detection potentially more suitable for counting. Nevertheless, the results show that DL architectures can generate masks for point cloud segmentation, supporting precise chestnut tree production estimation in future studies.