The cultural heritage image classification represents one of the most important tasks in the process of digitalization. In this paper, a deep learning neural network was applied in order to classify images of architectural heritage belonging to ten categories, in particular: (i) bell tower, (ii) stained glass, (iii) vault, (iv) column, (v) outer dome, (vi) altar, (vii) apse, (viii) inner dome, (ix) flying buttress, and (x) gargoyle. The Convolutional neural network was used for image classification, with the same architecture applied on two sets of the data: the full dataset consisting of 10 categories as well as dataset with 5 different image categories. The results show that both architectures performed well and obtained accuracy of up to 90%.

The paper presents the possibility of using criterion programming and neuro-fuzzy modeling in determining the value of planning technical power losses. Proposed is an optimal control in normal mode power grids which considers the value of planned technical power losses. Improved method for determining normative values of technical energy losses using the criteria programming and neuro-fuzzy modeling is presented.

As traditional museums migrate to the virtual world, they offer wider access to the exhibit collections but often fail to present content of those collections in more engaging way. Game-based learning is one of the solutions to mitigate this inevitable transition and support active learning in the process. It is increasingly gaining interest from the cultural heritage scientific community for the purpose of promoting cultural heritage, raising awareness of its importance and motivating users to visit cultural institutions such as museums more often. There are numerous examples of serious games that are based on or contain heritage content. Tangible cultural heritage is more represented in the virtual worlds and mainly based on applications of 3D technology. Recently, intangible cultural heritage is gaining more visibility within cultural heritage scope as a domain in which game-based learning could assist in its preservation. This paper attempts to address pros and cons of game-based learning in general and reflect on the choices of using serious games in the museum environment.

Motivation and objective: Because biodiversity conservation in forest management planning is necessary for ensuring regular ecosystem functioning, resilience and sustainability, the specific objective of this research was to quantify biodiversity at the landscape level in a forest plantation. Case study: Vale de Sousa, Forest Intervention Zone (ZIF), is located in the North of Portugal. ZIFs were formed all over the county with the objective to prevent forest fires, desertification and the abandonment of rural areas. The total case study area is 14.773 ha, mainly covered by plantation forests. The predominant forest species are maritime pine (Pinus pinaster) and blue gum (Eucalyptus globulus) either as pure or mixed stands. Methods:Fuzzy-logic system can serve as a platform for bundling expert knowledge on estimating ecosystem services provision and examining the consequences of contradictory expert views. The method was used to evaluate biodiversity as was recently proposed and demonstrated by Biber et al. (2018) in the context of the European Union (EU) project ALTERFOR (Alternative models and robust decision-making for future forest management - https://www.alterfor-project.eu/key-facts.html). In this study, we applied a fuzzy-logic approach for testing three biodiversity indicators: resident birds, heterogeneity of tree species diameter, and tree and shrub species richness. This approach generates scores for the rotation period of each plantation species between 0 (very low) and 1 (very high) for biodiversity categories. It also allows qualitative value rules regarding the above indicators. Scores are established according to stakeholder’s knowledge and validated by experts. Initially, the scores for each indicator are expressed as coloured matrices, but a final fuzzy output of biodiversity is expressed as a score between 0 and 1. Results: Our fuzzy outputs demonstrated low scores for biodiversity in monoculture stands, but medium scores in mixed stands. Tree and shrub species richness and diameter heterogeneity have low scores in analysed plantations but need to be tested in other forest types. However, the score for resident birds had medium values in monoculture forests, but due to the low score of the other biodiversity indicators, the overall biodiversity score is low. Conclusion: The results demonstrate that monocultures have the lowest score for biodiversity due to the zero level of all biodiversity indicators after the clear cut. Mixed stands have different periods of clear cut and this contributes to a higher score for biodiversity in general (fuzzy output). The fuzzy-logic approach is a very useful tool that may contribute to include biodiversity conservation in forest management decisions. This approach can be potentially used for the assessment of other biodiversity indicators (e.g. deadwood, large trees) in other forest types (including semi-natural and natural forests).