Contactless visualization of latent fingerprints has gained considerable attention for crime scene investigations as it can offer an option to collect traces using non-invasive and non-destructive treatment. Considering the complex structure of fingerprint development methods and the tedious process steps performed in these methods, new approaches to acquire, store, transfer, and analyze latent fingerprints practically without requiring any deep knowledge and expertise are needed. This paper proposes a new contactless latent fingerprint development method that uses a camera embedded in a mobile device and the apparatus used to increase the latent fingerprint’s visibility. The enhancement approach is presented in order to make the fingerprint collected with the designed apparatus usable and valid. As a result, an alternative system design for latent fingerprint development and enhancement is described in detail. Two state-of-art fingerprint matchers are used to measure the verification performance of the acquired latent fingerprint. It has been seen that latent fingerprints can be developed with contactless methods using optical treatments alone from reflective and non-porous surfaces. Furthermore, the stages of detecting, developing, and acquiring latent fingerprints from reflective and non-porous surfaces are carried out using the suggested development method without the requirement for forensic professionals. The suggested enhancement approach allows for the direct use of the enhanced fingerprint in the biometric identification/verification system by extracting distinctive properties from the latent fingerprint.

U-Net-based deep learning models have garnered significant attention in recent years due to their strong denoising capabilities in image restoration tasks. This study critically evaluates both the strengths and limitations of these models, with a particular focus on their architectural design and constituent components, in an effort to further advance denoising performance. Based on the insights derived from these analyses, a novel architecture–termed U-Tunnel-Net–is proposed. The model is trained on the UNS and Waterloo datasets, each augmented with Rayleigh-distributed speckle noise at four distinct intensity levels (\(\sigma\) = 0.10, 0.25, 0.50, and 0.75), and evaluated on the UNS, BSD68, and Set12 datasets. Performance assessment is conducted using peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and runtime as evaluation metrics. Leveraging a novel network design strategy and a newly introduced convolutional block, U-Tunnel-Net consistently achieves superior performance compared to other U-Net-based denoising models. A key architectural innovation lies in the repositioning of the pooling operation within the Tunnel Blocks, which differentiates the proposed model from conventional U-Net variants. Experimental results on both benchmark and real-world datasets confirm that U-Tunnel-Net outperforms several state-of-the-art denoising methods.

Successfully tackling many urgent challenges in socio-economically critical domains, such as public health and sustainability, requires a deeper understanding of causal relationships and interactions among a diverse spectrum of spatio-temporally distributed entities. In these applications, the ability to leverage spatio-temporal data to obtain causally based situational awareness and to develop informed forecasts to provide resilience at different scales is critical. While the promise of a causally grounded approach to these challenges is apparent, the core data technologies needed to achieve these are in the early stages and lack a framework to help realize their potential. In this article, we argue that there is an urgent need for a novel paradigm of spatio-causal research built on computational advances in spatio-temporal data and model integration, causal learning and discovery, large scale data- and model-driven simulations, emulations, and forecasting, as well as spatio-temporal data-driven and model-centric operational recommendations, and effective causally driven visualization and explanation. We thus provide a vision, and a road map, for spatio-causal situation awareness, forecasting, and planning.

Fingerprint recognition systems have relied on fragile workflows based on minutiae extraction, which suffer from significant performance losses under real-world conditions such as sensor diversity and low image quality. This study introduces a fully minutiae-free fingerprint recognition framework based on self-supervised Vision Transformers. A systematic evaluation of multiple DINOv2 model variants is conducted, and the proposed system ultimately adopts the DINOv2-Base Vision Transformer as the primary configuration, as it offers the best generalization performance trade-off under conditions of limited fingerprint data. Larger variants are additionally analyzed to assess scalability and capacity limits. The DINOv2 pretrained network is fine-tuned using self-supervised domain adaptation on 64,801 fingerprint images, eliminating all classical enhancement, binarization, and minutiae extraction steps. Unlike the single-sensor protocols commonly used in the literature, the proposed approach is extensively evaluated in a heterogeneous testbed with a wide range of sensors, qualities, and acquisition methods, including 1631 unique fingers from 12 datasets. The achieved EER of 5.56% under these challenging conditions demonstrates clear cross-sensor superiority over traditional systems such as VeriFinger (26.90%) and SourceAFIS (41.95%) on the same testbed. A systematic comparison of different model capacities shows that moderate-scale ViT models provide optimal generalization under limited-data conditions. Explainability analyses indicate that the attention maps of the model trained without any minutiae information exhibit meaningful overlap with classical structural regions (IoU = 0.41 ± 0.07). Openly sharing the full implementation and evaluation infrastructure makes the study reproducible and provides a standardized benchmark for future research.

Research on brain cancer indicates that the severity of the disease varies according to tumor types and their specific characteristics. Accurate identification of tumor locations, extraction of distinctive features, and correct classification are of critical importance. In this study, brain tumors were detected using three different deep learning models developed on a dataset created within the scope of the TBP project and seven additional public datasets. All three models are based on Convolutional Neural Network (CNN) architectures for tumor detection. The first model is a baseline CNN; the second incorporates the Genetic Algorithm (GA), a traditional approach for hyperparameter optimization; and the third combines the CNN with the Slime Mold Algorithm (SMA), a recently proposed metaheuristic technique. Hybrid methods that achieve higher performance than baseline CNNs in binary tumor classification are presented and discussed. Experimental results were comparatively analyzed and visualized through graphs and tables. Compared to other CNN-based studies in the literature, the proposed approach improved accuracy by approximately 1–10%. Similarly, when compared with other machine learning (ML) and deep learning (DL) algorithms, excluding CNNs, performance gains ranged between 1% and 13%. The CNN+SMA model achieved the most consistent and notable improvements across all datasets. Although hybrid models generally require more computational resources due to their complex training structures, they tend to achieve higher accuracy and facilitate parameter optimization more effectively than single-model approaches.