In order to perform cutting-edge research like AI model training, a large amount of data needs to be accessed. However, data providers are often reluctant to share their data with researchers as these might contain personal data and thereby sharing may introduce serious risks with significant personal, institutional or societal impacts. Apart from the need to control these risks, data providers must also comply with regulations like GDPR, which creates an additional overhead that makes data sharing even less appealing to data providers. Technologies like anonymization can play a critical role when sharing data that may contain personal information by offering privacy preservation measures like face or license plate anonymization. Therefore, we propose a framework to support data sharing of personal data for research by integrating anonymization, risk assessment and automatic licence agreement generation. The framework offers a practical and efficient solution for organisations seeking to enhance data-sharing practices without compromising information security.

Social media are a valuable source of information during emergency situations. First responders and rescue teams can further improve their situation awareness and be able to act more effectively, when using information available in the form of social media posts made from the public. This work proposes a methodology supported by a toolflow, which combines machine learning techniques for identifying informative Twitter posts about ongoing incidents of various types, with a semi-automated way of dispatching information to first responders. Evaluation results show that the accuracy of detecting informative text and images posted on Twitter about ongoing emergency situations, exceeds 80%, while analysis performance is near real-time.

The forest's biodiversity consists of relations between trees, animals, the environment, and surrounding communities. Their existence required a certain balance both in number and composition. The diversity of the element itself creates a chain that connects each of the living things. Consistently, those mutual relationships are sometimes disturbed by pressures, whether man-made pressures or natural pressures. As a consequence of that event, the biodiversity loses its balance and becomes vulnerable to disaster. The fact that forest fire cases damage every living thing in the forest is becoming a massive issue in forest management. In some instances, the balance of forest biodiversity assembles an ecological resilience essential to the forest condition in combating disturbance. This paper reviews the biodiversity elements and their relationship to the extent to which elements will support ecological resilience. This is a review of 58 studies related to biodiversity balance and ecological resilience. The review discovered evidence that biodiversity components are connected and support each other. However, not every relation contributes to ecological resilience. As a result, we assess several biodiversity elements that might be useful in supporting ecological resilience, which are tree, environment, animal, and community. We also provide 2 case examples case to get the value of some biodiversity elements using a deep learning method.

Crime has been and still is one of the major threats and issues for every government and society around the world. Nowadays, a new generation of (cyber)criminals exploits modern and state-of-the-art technology and tools, especially social media channels, in order to achieve their malicious purposes. Thus, Law Enforcement Agencies (LEAs), analysts and security practitioners are facing the need to engage new methods and tools which can support them in the fight and prevention of crime by minimizing the prediction and response time. This paper focuses on two specific functionalities of a crime prediction and fighting software framework which assists LEAs to adopt and utilize emerging technologies such as Data mining and Big Data tools, Semantic Analysis, Visual Intelligence and more in the context of their everyday operations. In this light, the authors of this paper present an innovative Semantic Engine with a person fusion tool as well as an ontology visualization tool as parts of a discussed framework. Both of these tools are presented in detail in separate sections so that the readers can understand better their architecture and their integration into this common framework alongside with other tools. These two tools use state-of-the-art components and software libraries in order to offer robust and future proof solutions for LEAs. Also, they can be integrated and expanded in future research and commercial projects both as independent tools as well as parts of other integrated frameworks.

The extreme growth and adoption of Social Media, in combination with their poor governance and the lack of quality control over the digital content being published and shared, has led information veracity to a continuous deterioration. Current approaches entrust content verification to a single centralised authority, lack resilience towards attempts to successfully "game" verification checks, and make content verification difficult to access and use. In response, our ambition is to create an open, democratic, pluralistic and distributed ecosystem that allows easy access to various verification services (both internal and third-party), ensuring scalability and establishing trust in a completely decentralized environment. In fact, this is the ambition of the EU H2020 SocialTruth project. In this paper, we present the innovative project approach and the vision of effective online disinformation detection for various practical use-cases.

The emerging era of cloud services has already started and the concepts of Internet of Things (IoT) are ready to be introduced in the modern everyday life through the deployment of a large scope of novel applications. In this paper we present the concepts and ideas of the INLIFE project. The software produced by using the INLIFE platform can be seen as a hybrid of a typical e-health application and a typical recreational electronic game and this is one important differentiation of the INLIFE games and apps. The users play an attractive game like e.g. a strategy campaign or an MMORPG (Massively Multiplayer Online Role Playing Game) but the only way to collect the points or the resources they need in order to play, is to do something in their real life, namely "inlife". These valuable actions, that credit points to the players, are detected in an automatic way by using IoT sensors and actuators or by retrieving information from other monitoring systems like ADL (Activities of Daily Living) data.

The market uptake of the 4th Generation networks is expected to support the increasing demand for wireless broadband services and ensure an enhanced mobile user experience. In this direction, the convergence of a wireless access network with an optical backhauling has been proposed. However, in such a converged architecture, the traditional fixed commitment of the backhaul resources does not prove to be as efficient, and novel dynamic schemes are required that consider both the needs of the base stations and the limitations of the passive optical network. This paper is concerned with the topic of resource allocation in two competing base stations that belong to different operators and share a common optical backhaul network infrastructure. An approach based on evolutionary game theory is proposed and employed, with a view to examining the interactions among the base stations and the passive optical network. Using the model of replicator dynamics, the proposed system design is proved to be asymptotically stable. In addition, this paper studies and reveals the extent to which time delay can have an impact on the proposed system design.

One of the most significant issues the research community has focused on during the last decades, is the reduction of the energy consumed in every aspect of everyday life. A standout amongst the most important factors of energy consumption is transportation. To this end, a lot of work in the field of Intelligent Transport Systems concentrates on enhancing energy efficiency. This trend was reinforced by the appearance of Fully Electric Vehicles (FEVs), where it is more crucial to increase their energy efficiency in any manner. Eco-routing refers to the choice of the most energy efficient route towards a destination and seems very promising for reducing everyday energy consumption. In this paper, we present a novel method for predicting energy consumption levels, based on machine learning techniques. In addition, addressing the problem of ever increasing amounts of tracking data acquired from vehicles, we introduce a clustering based prediction method and apply it on real world measurements in order to evaluate its performance.

The recently deployed 4G access technology promises to satisfy the increasing demand of bandwidth consuming applications by providing high network capacity, low latency and seamless mobility. Towards this direction, concept solutions concerning the integration of wireless and optical networks have been proposed. However, the majority of these approaches assume the conventional fixed commitment of resources to the base stations, an inefficient and costly process, especially in case the Passive Optical Network (PON) belongs to a different operator. As a result, new, more dynamic backhaul resource allocation approaches are required. In this paper, the authors study the problem of committing resources of the backhaul network to a base station by employing evolutionary game theory in order to model the interactions between the subscribers and the base station. The asymptotic stability of the proposed scheme is proven under the replicator dynamics model. Finally, the impact of time delay in the proposed scheme is also investigated.

Fully Electric Vehicles (FEVs) represent a promising solution for the reduction of fuel consumption, air and noise pollution in urban areas. However, the commercial viability of FEVs is at stake if the associated issues of autonomy are not dealt with effectively. Project EcoGem - Cooperative Advanced Driver Assistance System for Green Cars - advocates that the success and user acceptability of FEVs will predominantly depend on their electrical energy consumption rate and the corresponding degree of autonomy that they can offer. EcoGem aims at providing efficient ICT-based solutions to this great issue, by designing and developing a FEV-oriented highly-intelligent Advanced Driver Assistance System, equipped with suitable monitoring, learning, reasoning and management capabilities that will help increase the FEV's autonomy and energy efficiency.

The present paper introduces the innovative concept of a new type of services, called ambient community services (ACS). The ACS concept utilizes information that resides in communities of mobile terminals, such as location, speed, sensor-related data or user-created multimedia content. After the collection, processing and filtering of these data, a number of innovative, heterogeneous value-added applications can be provided to the end-users, such as the provision of vehicular traffic conditions. ACS advances the social networking by allowing users to form cooperative, service-enabling communities. This paper includes a thorough description of the state-of- the-art, the proposed system architecture and communication flow, potential enabled applications, important implementation aspects, as well as future research activities.

This paper analyzes the concept of Anonymous Real-Time Mobile Community (ART-MC) services, which enables the real-time collection of information residing in a community of mobile terminals, which can then be processed and delivered to a service requesting terminal. An example application is the provision of real-time information concerning road-traffic conditions, based on the location and velocity of mobile terminals. The ART-MC concept requires the deployment of an appropriate software client at the terminal side, as well as the deployment of an ART-MC Server at the network side. The proposed architecture is presented and explained in detail. Anonymity and privacy issues are addressed, and an extensive analysis regarding scalability is given. Finally, additional example applications of the ART-MC concept are listed.

This paper discusses the problem of user preference modelling in the context of next generation terminals operating in heterogeneous environments. It includes an approach to the definition, mathematical formulation and solution of this problem. Indicative results of the proposed solution method are presented in the framework of a real-life scenario, which simulates a day in the life of an ordinary user