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.

Although the end of Moore’s law has been predicted for many years, the capacity to store information in information and communication technology is still progressing in ways we could not imagine. Hence, the museum environments are also benefiting from improvements in data collection, storage and processing as well as allowing the great body of information within cultural heritage domain to be applied through interesting processes in the museums, one of which is game-based learning. Although, concept of employing games in the learning process is known for a long-time research teams in game-based learning and in the CH field in general often lack unified approach with results that are extended globally and team effort contributing to a larger systematically organized body of knowledge. In this paper we identify advantages and disadvantages of game-based learning application in the museums. By doing this we attempt to tackle promotion of cultural heritage, raise awareness of its importance and motivate users to visit cultural institutions such as museums more often.

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).

Cultural heritage sites in Bosnia and Herzegovina (BiH), a country rich in religious buildings and ancient structures, are in constant need of preservation and reconstruction. In addition, tangible cultural heritage has been subject to war destruction and the only feasible option for reconstructing some of them is digitalization. On the contrary, the intangible cultural heritage encompassing oral traditions and expressions, traditional skills, as well as science and habits related to nature and world are a vital expression of cultural heritage and in the need of preservation. Over the past years, with the availability of technology and the identified research interest and the potential, significant progress has been made towards the preservation of cultural heritage. Motivated by these facts, this state-of-the-art report summarizes recent trends and discusses its value to the society. This paper therefore, gives an overview of the tools and the current state of digitalization of cultural heritage sites in BiH in an attempt of contributing to its preservation.

This paper describes relevant classification methods applied to the cultural heritage context. In particular, a categorisation of the classification methods is provided according to tangible and intangible cultural heritage, where movable and immovable objects can be in the focus. A short description of each method is reported for each cultural heritage category in terms of feature representation, classification approach and obtained results. The proposed survey can be useful in the research community of pattern recognition and visual computing for exploring the current literature about the topic. It will hopefully provide new insights for the advancement of knowledge discovery in cultural heritage.

: We use machine learning techniques to build predictive models for anomaly detection in the Border Gateway Protocol (BGP). Imbalanced datasets of network anomalies pose limitations to building predictive models for anomaly detection. In order to achieve better classification performance measures, we use resampling methods to balance classes in the datasets. We use undersampling, oversampling and combination techniques to change class distributions of the datasets. In this paper we build predictive models based on preprocessed network anomaly datasets of known Internet network anomalies and observe improvement in classifier performance measures compared to those reported in our previous work. We propose to use resampling combination techniques on datasets along with Decision Tree and Naïve Bayes classifiers in order to achieve the best trade-off between (1) the F-measure and the length of model training time, and (2) avoiding overfitting and loss of information.

Selection of an adequate tool for accurate short-term load forecasting task is becoming more important for electric utilities. Machine learning techniques are proving useful for short-term electricity load forecasting. In this paper we evaluate performance of several machine learning algorithms applied to electricity load datasets. We evaluated performance of SMOreg, and Additive regression algorithms for load forecasting using electricity consumption datasets. We also performed an Artificial Neural Networks (ANN) analysis on short-term load forecasting.

Border Gateway Protocol (BGP), which enables Internet interconnectivity, is susceptible to various anomalous events that may affect the Internet performance. Understanding the nature of anomalous events (unintentional or malicious) and their effects helps classify future events and improve the Internet robustness. Determining the rate and causes of these anomalous events is important for assessing loss of data and connectivity. BGP update messages contain network reachability information stored in a Routing Information Base (RIB). In this paper, we use datasets of known malicious attacks and a power outage event and employ machine learning algorithms to identify traffic anomalies.

Changes in the network topology such as large-scale power outages or Internet worm attacks are events that may induce routing information updates. Border Gateway Protocol (BGP) is by Autonomous Systems (ASes) to address these changes. Network reachability information, contained in BGP update messages, is stored in the Routing Information Base (RIB). Recent BGP anomaly detection systems employ machine learning techniques to mine network data. In this paper, we evaluated performance of several machine learning algorithms for detecting Internet anomalies using RIB. Naive Bayes (NB), Support Vector Machine (SVM), and Decision Tree (J48) classifiers are employed to detect network traffic anomalies. We evaluated feature discretization and feature selection using three data sets of known Internet anomalies.