Search

Operators of modern mobile networks are faced with significant challenges in providing the requested level of service to an ever increasing number of user entities. Advanced machine learning techniques based on deep architectures and appropriate learning methods are recognized as promising ways of tackling the said challenges in many aspects of mobile networks, such as mobile data and mobility analysis, network control, network security and signal processing. Having firstly presented the background of deep learning and related technologies, the paper goes on to present the architectures used for deployment of deep learning in mobile networks. The paper continues with an overview of applications and services related to the new generation of mobile networks that employ deep learning methods. Finally, the paper presents practical use case of modulation classification as implementation of deep learning in an application essential for modern spectrum management. We complete this work by pinpointing future directions for research.

The concept of Smart City started its development path around two to three decades ago; it has been mainly influenced and driven by radical changes in technological, social and business environments. Big Data, Internet of Things and Networked Cyber-Physical Systems, together with the concepts of Cloud, Fog and Edge Computing, have tremendous impact on the development of Smart City, reforming its frame and tasks and redefining its requirements and challenges. We consider feasible architectures of the IT infrastructure and signal processing, taking into account aspects of Big Data, followed by summary of benefits and main challenges, like security of infrastructure and private data. As a practical example we present a public safety application of multi-sensor imaging system: a smart device with target detection subsystem based on artificial intelligence used for activation of target tracking. The experiments have been performed in the cities of Abu Dhabi and Belgrade, which have very different environment. The experiments have shown the effects of videostreaming compression on thermal imagers and the importance of distributed processing power that optimizes requirements for amount of transmitted data and delay.

This paper is described different strategies for traffic control and simulation, namely - Vehicle Actuated (VA) compared to Fixed Time (FT) traffic control. We are comparing and evaluating the impact of FT and adaptive traffic signal control strategies for one of the biggest and busiest intersections in Tashkent, the capital of Uzbekistan. The parameters used for comparing these strategies are the average vehicle travel times and average vehicle queue lengths. TRL TRANSYT 15 software was used to determine the fixed signal timing plan based on intersection geometry, inter-green matrix, and traffic flow. PTV VISSIM software is used for VA algorithm development and simulation to get the maximum and average vehicle travel times as well as queue lengths. It is shown that the parameter optimization can reduce the queue lengths down to 65% and the travel time down to 51%. [ABSTRACT FROM AUTHOR]

This paper presents a literature overview of Fuzzy Relational Database Models with emphasis on the role of functional dependencies in logical designing and modeling. The aim is the analysis of recent results in this field. Fuzzy set theory is widely applied for the classical relational database extensions resulting in numerous contributions. This is because fuzzy sets and fuzzy logic are powerful tool for manilupating imprecise and uncertain information. A significant body of research in efficient designing FRDM has been developed over the last decades. Knowing the set of functional dependencies, database managers have a chance to normalize the same eliminating redundancy and data anomalies. In this paper we have considered the most important results in this field. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new algorithm for distributed spectrum sensing and channel selection in cognitive radio networks based on consensus. The algorithm operates within a multi-agent reinforcement learning scheme. The proposed consensus strategy, implemented over a directed, typically sparse, time-varying low-bandwidth communication network, enforces collaboration between the agents in a completely decentralized and distributed way. The motivation for the proposed approach comes directly from typical cognitive radio networks' practical scenarios, where such a decentralized setting and distributed operation is of essential importance. Specifically, the proposed setting provides all the agents, in unknown environmental and application conditions, with viable network-wide information. Hence, a set of participating agents becomes capable of successful calculation of the optimal joint spectrum sensing and channel selection strategy even if the individual agents are not. The proposed algorithm is, by its nature, scalable and robust to node and link failures. The paper presents a detailed discussion and analysis of the algorithm's characteristics, including the effects of denoising, the possibility of organizing coordinated actions, and the convergence rate improvement induced by the consensus scheme. The results of extensive simulations demonstrate the high effectiveness of the proposed algorithm, and that its behavior is close to the centralized scheme even in the case of sparse neighbor-based inter-node communication. [ABSTRACT FROM AUTHOR]