Cruise ships transfer diverse populations between different countries, offering unique travel experiences to thousands of people worldwide. The benefits of cruises in tourism and national economies are apparent; however, the closed environment of cruise ships can easily become an incubator of infectious diseases, spreading rapidly among passengers. Health recommendations and protocols have been issued by proper organizations to enable disease spread control, especially after COVID-19 (SARS-CoV-2) pandemic; however, their effective application by the ship’s crew still constitutes a challenge, considering the application scale. This chapter aims to provide a foundational model toward an automatic system contributing to disease spread monitoring and control in cruise ships. Such a system would contribute to limiting the dependencies on the human factor, and consequently to passengers’ safety. Also, it provides an overview of state-of-the-art disease monitoring and decision-making systems, as well as simulation methods enabling the prediction of disease evolution, considered as components of that model. A summary of research directions and conclusions are derived from the review study performed, offering a useful reference for future research.

The quality of a 3D model depends on the object digitization process, which is usually characterized by a tradeoff between volume resolution and scanning speed, i.e., higher resolution scans require longer scanning times. Aiming to improve the quality of lower resolution 3D models, this paper proposes a novel approach to 3D model reconstruction from an initially coarse point cloud (PC) representation of an object. The main contribution of this paper is the introduction of a novel periodic activation function, named Wave-shaping Neural Activation (WNA), in the context of implicit neural representations (INRs). The use of the WNA function in a multilayer perceptron (MLP) can enhance the learning of continuous functions describing object surfaces given their coarse 3D representation. Then, the trained MLP can be regarded as a continuous implicit representation of the 3D representation of the object, and it can be used to reconstruct the originally coarse 3D model with higher detail. The proposed methodology is experimentally evaluated by two case studies in different application domains: a) reconstruction of complex human tissue structures for medical applications; b) reconstruction of ancient artifacts for cultural heritage applications. The experimental evaluation, which includes comparisons with state-of-the-art approaches, verifies the effectiveness and improved performance of the WNA-based INR for 3D object reconstruction.

Creating accessible museums and exhibitions is a key factor to today’s society that strives for inclusivity. Visually-impaired people can benefit from manually examining pieces of an exhibition to better understand the features and shapes of these objects. Unfortunately, this is rarely possible, since such items are usually behind protective barriers due to their rarity, worn condition, and/or antiquity. Nevertheless, this can be achieved by 3D printed replicas of these collections. The fabrication of copies through 3D printing is much easier and less time-consuming compared to the manual replication of such items, which enables museums to acquire copies of other exhibitions more efficiently. In this paper, an accessibility-oriented methodology for reconstructing exhibits from sparse 3D models is presented. The proposed methodology introduces a novel periodic and parametric activation function, named WaveShaping (WS), which is utilized by a multi-layer perceptron (MLP) to reconstruct 3D models from coarsely retrieved 3D point clouds. The MLP is trained to learn a continuous function that describes the coarse representation of a 3D model. Then, the MLP is regarded as a continuous implicit representation of the model; hence, it can interpolate data points to refine and restore regions of the model. The experimental evaluation on 3D models taken from the ShapeNet dataset indicates that the novel WS activation function can improve the 3D reconstruction performance for given coarse point cloud model representations.Keywords3D reconstructionMachine LearningCultural Heritage