%0 Conference Paper %B The 36th International Conference on Advanced Information Networking and Applications (AINA – 2022), April 13 - 15, 2022, Sydney, Australia %D 2022 %T Applying Machine Learning and Dynamic Resource Allocation Techniques in Fifth Generation Networks %A Christos Bouras %A Evangelos Michos %A Ioannis Prokopiou %X According to Internet of Things (IoT) Analytics, soon, the online devices in IoT networks will range from 25 up to 50 billion. Thus, it is expected that IoT will require more effective and efficient analysis methods than ever before with the use of Machine Learning (ML) powered by Fifth Generation (5G) networks. In this paper, we incorporate the K-means algorithm inside a 5G network infrastructure to better associate devices with Base Stations (BSs). We use multiple datasets consisting of user distribution in our area of focus and propose a Dynamic Resource Allocation (DRA) technique to learn their movement and predict the optimal position, RB usage and optimize their resource allocation. Users can experience significantly higher data rates and extended coverage with minimized interference and in fact, the DRA mechanism can mitigate the need for small cell infrastructure and prove a cost-effective solution, due to the resources transferred within the network. %B The 36th International Conference on Advanced Information Networking and Applications (AINA – 2022), April 13 - 15, 2022, Sydney, Australia %V 1 %P 662-673 %G eng %0 Book Section %B Advances in Engineering Research, Nova Science Publishers %D 2022 %T An Introduction of Upcoming Radio Resource Management Techniques for 5G Networks %A Christos Bouras %A Vasileios Kokkinos %A Apostolos Gkamas %A Evangelos Michos %A Ioannis Sina %A Ioannis Prokopiou %A Foivos Allayiotis %X 5G networks are the next generation of mobile internet connectivity, that are able to offer vastly increased speeds, more reliable connections, minimal latency and more supported devices. 5G networks are expected to supercharge Internet of Things (IoT) technology, so as to provide the infrastructure needed in order to support and transfer large data amounts that will enable a smarter and more connected world. To this direction, 5G incorporates many technologies and mechanisms that aid towards the overall goal, such as Multiple-Input and Multiple-Output (MIMO), Downlink (DL) and Uplink (UL) Decoupling (DUDe) and Machine Learning (ML). These technologies can significantly help towards more efficient resource allocation inside the next generation networks, offering increased spectral efficiency and data rates, better signal coverage, reduced latencies and many more. In this chapter, we will provide insights over the aforementioned technologies through firstly a literature review and later on by analyzing their architecture and their models. We will explain how these technologies can be taken advantage of in order to support the 5G networks and why they are core components of future networks, as it is expected that also 5G and Beyond networks will capitalize on them. %B Advances in Engineering Research, Nova Science Publishers %V 46 %P 147-188 %G eng %& 3 %0 Conference Paper %B The 36th International Conference on Information Networking (ICOIN), Jan. 12 – 15, 2022, Bangkok, Thailand %D 2022 %T An online real-time face recognition system for police purposes %A Christos Bouras %A Evangelos Michos %X In general, face recognition algorithms are often utilized in order to identify or authenticate a human through a camera feed. However, face recognition algorithms must adapt to real-life uncertainties and noisy environments. This work targets upon extending the existing work of facial recognition algorithms by proposing an online platform that can be used from the police forces towards effective real-time human recognition. The approach on facial recognition is to use and extend the Haar Cascade algorithm for real-time purposes, which is widely considered one for the most efficient and used algorithms for that cause. As for the criminal identification, it will made possible through image pattern recognition between the provided criminal’s image and snapshots of identified faces from the livestream feed. The platform will include a live feed section with different options for video filters, enabling the user to select the best filter, depending on relevant situation of the physical surroundings for better recognition. %B The 36th International Conference on Information Networking (ICOIN), Jan. 12 – 15, 2022, Bangkok, Thailand %G eng %0 Journal Article %J Land, MDPI 2021 %D 2021 %T MAES_GR: A Web-Based, Spatially Enabled Field Survey Platform for the MAES Implementation in Greece %A Ioannis Kokoris %A Vasileios Kokkinos %A Evangelos Michos %A Rafail Kalogeropoulos %A Marios Charalambides %A Agisilaos Kounelis %A Eleni Iliadou %A Christos K. Damianidis %A Giorgos Mallinis %A Christos Bouras %A Panayotis Dimopoulos %X This study presents a standardized approach to collecting, registering, and reporting field-survey data for baseline MAES (Mapping and Assessment of Ecosystems and their Services) information in Greece. This is accomplished through a web-based platform (MAES_GR) exclusively developed under the relevant, nation-wide LIFE-IP 4 NATURA project. Based on the European Commission’s guidance for ecosystem condition (EC) and ecosystem services (ES) MAES studies, we conceptualized and structured an online platform to support EC and ES assessments, integrating all relevant fields of information needed for registering EC and ES parameters. A novel algorithm calculating EC was also developed and it is available as an integral part of the platform. The use of the MAES_GR platform was evaluated during nationwide field surveys efforts, increasing time efficiency and reducing costs. Field recording of EC and ES pinpoint spatial priorities for ecosystem restoration, conservation and sustainable development. This work highlights that MAES implementation can be favored by the use of technology tools such as mobile survey platforms, developed according to scientific needs and policy guidelines. Such tools, apart from the data inventory phase, can be used for data analysis, synthesis and extraction, providing timely, standardized information suitable for reporting at the local, regional, national and European Union scale. %B Land, MDPI 2021 %V 10 %G eng %N 4 %0 Conference Paper %B The 36th International Conference on Information Networking (ICOIN), Jan. 12 – 15, 2022, Bangkok, Thailand (to appear) %D 2021 %T An Online Real – Time Face Recognition System for Police Purposes %A Christos Bouras %A Evangelos Michos %X In general, face recognition algorithms are often utilized in order to identify or authenticate a human through a camera feed. However, face recognition algorithms must adapt to real-life uncertainties and noisy environments. This work targets upon extending the existing work of facial recognition algorithms by proposing an online platform that can be used from the police forces towards effective real-time human recognition. The approach on facial recognition is to use and extend the Haar Cascade algorithm for real-time purposes, which is widely considered one for the most efficient and used algorithms for that cause. As for the criminal identification, it will made possible through image pattern recognition between the provided criminal’s image and snapshots of identified faces from the livestream feed. The platform will include a live feed section with different options for video filters, enabling the user to select the best filter, depending on relevant situation of the physical surroundings for better recognition. %B The 36th International Conference on Information Networking (ICOIN), Jan. 12 – 15, 2022, Bangkok, Thailand (to appear) %G eng %0 Conference Paper %B The Sixteenth International Conference on Networking and Services (ICNS 2020), September 27, 2020 - October 01, 2020, Lisbon, Portugal %D 2020 %T GuideMe: A Networked Application for Indoor Orientation and Guidance %A Christos Bouras %A Eirini Barri %A Apostolos Gkamas %A Christina Koulouri %A Evangelos Michos %A Spyridon Katsampiris %X Today’s indoor navigational systems are more and more in demand, commonly used for applications such as smart cities, robots and visually impaired people. As far as outdoor navigation is concerned, the Global Positioning System (GPS) technology is still one of the most (if not the most) commonly used approaches. Even though it is still considered an ideal solution for navigating in outdoor areas, challenges and problems arise when GPS is considered for navigation inside buildings due to obstacles (e.g., shopping malls, hospitals, etc.) and because signals cannot be absorbed by the building walls. To tackle the aforementioned issue, other technologies have emerged aimed at indoor navigation, such as Wireless-Fidelity (Wi-Fi), Bluetooth and sensors. This paper’s contribution is towards indoor navigation and, more specifically, it targets designing and developing a tracking and navigation system aimed at people that experience difficulties in indoor orientation using a wearable device. The user takes direction from the wearable device for the indoor orientation through voice commands helping him to avoid obstacles. The central part of the system is a device that provides the ability to navigate and find a route by voice commands, based on the device's location and orientation capabilities. %B The Sixteenth International Conference on Networking and Services (ICNS 2020), September 27, 2020 - October 01, 2020, Lisbon, Portugal %G eng %0 Conference Paper %B The Sixteenth International Conference on Networking and Services (ICNS 2020), September 27, 2020 - October 01, 2020 , Lisbon, Portugal (to appear) %D 2020 %T GuideMe: A Networked Application for Indoor Orientation and Guidance %A Eirini Barri %A Christos Bouras %A Apostolos Gkamas %A Christina Koulouri %A Evangelos Michos %A Spyridon Katsampiris %X Today’s indoor navigational systems are more and more in demand, commonly used for applications such as smart cities, robots and visually impaired people. As far as outdoor navigation is consider, the Global Positioning System (GPS) technology is still one of the most (if not the most) commonly used approaches. Even though it is still considered an ideal solution for navigating in outdoor areas, challenges and problems arise when GPS is considered for navigation inside buildings due to obstacles (e.g., shopping malls, hospitals, etc.) and because signals cannot be absorbed by the building walls. To tackle the aforementioned issue, other technologies have emerged aimed at indoor navigation, such as Wireless-Fidelity (Wi-Fi), Bluetooth and sensors. This paper’s contribution is towards indoor navigation and more specifically, it targets at designing and developing a tracking and navigation system aimed at people that experience difficulties in indoor orientation using a wearable device. The user takes direction from the wearable device for the indoor orientation through voice commands helping him to avoid obstacles. The central part of the system is a device that provides the ability to navigate and route by voice commands, based on the device's location and orientation capabilities. %B The Sixteenth International Conference on Networking and Services (ICNS 2020), September 27, 2020 - October 01, 2020 , Lisbon, Portugal (to appear) %G eng %0 Journal Article %J Tourism: An International Interdisciplinary Journal, Institute for Tourism, Zagreb, Croatia, 2020 %D 2020 %T An online tool on sustainable water management %A Christos Bouras %A Vasileios Kokkinos %A Evangelos Michos %X Water demand strains supply capacity in the Mediterranean coastal areas, affecting negatively the maintenance of natural and cultural heritage. Tackling this subject, the “Coastal areas sustainable tourism water management in the Mediterranean - CASTWATER” project aims to support sustainable tourism water management in Mediterranean (MED) coastal areas, by improving the monitoring and assessment of the water sustainability performance of tourism. To this end, the elaboration of an online tool to monitor and assess sustainable tourism water management was envisaged and developed, primarily addressed to tourism sector small and medium-sized enterprises (SMEs). The CASTWATER online tool was designed to so as to provide two different functionalities. On the one hand, SMEs can self-evaluate their performance in sustainable water management and efficiently acknowledge possible actions that promote water efficiency in their tourism establishments. On the other hand, the tool measures, at both regional and local level, the levels of good governance and the effectiveness of water-tourism policies in order to improve sustainable water management. The approach presented in this work is heavily based on the initial technical specifications and end-user feedback, aiding SMEs in understanding, comparing, assessing and rating their performance regarding water efficiency and sustainable water manag %B Tourism: An International Interdisciplinary Journal, Institute for Tourism, Zagreb, Croatia, 2020 %V 68, Νο4 %P 450-465 %G eng %0 Journal Article %J International Journal of Wireless Networks and Broadband Technologies (IJWNBT), IGI Global %D 2020 %T A Resource - efficient Approach on User Association in 5G Networks using Downlink and Uplink Decoupling %A Christos Bouras %A Evangelos Michos %X A user-centered network model can significantly optimize connectivity issues between a user and the corresponding Base Station (BS). This paper shall evaluate the User Centric (UC) model targeted for Fifth Generation telecommunication systems and will attempt to optimize communication between users and BSs. The authors suggest a resource-aware mechanism that targets at improving coverage through the network decoupling into two separate and independent uplink and downlink networks. Our mechanism shall fully respect each user’s initially requested throughput demands and aims to solve the network user – BS association problem with efficient resource management techniques. Simulations revealed that the mechanism perfectly preserves Quality of Service (QoS) and offers increased data rates in favor of ultimate user coverage, in both scenarios. Additionally, Frequency Range 2 offers an increased amount of resources, both increased data rates and higher amounts of devices that are covered by the overall network. %B International Journal of Wireless Networks and Broadband Technologies (IJWNBT), IGI Global %V 9 %P 43 - 59 %G eng %N 2 %0 Conference Paper %B The Sixteenth International Conference on Networking and Services (ICNS 2020), September 27, 2020 - October 01, 2020 , Lisbon, Portugal %D 2020 %T Text to Speech through Bluetooth for People with Special Needs Navigation %A Eirini Barri %A Christos Bouras %A Apostolos Gkamas %A Christina Koulouri %A Evangelos Michos %A Spyridon Katsampiris %X As far as outdoor navigation is considered, the Global Positioning System (GPS) technology is still one of the most (if not the most) commonly used approaches. Even though it is still considered an ideal solution for navigating in outdoor areas, challenges and problems arise when GPS is considered for navigation inside buildings due to the fact that GPS signals cannot penetrate walls/ceilings (e.g., shopping malls, hospitals, etc.) and because signals can be absorbed by the building walls. This paper’s contribution is navigation system that assists people with special needs using an audio guidance system that incorporates input from a voice recognition system. The central part of the system is a device that is able to identify the position and orientation of the person that carries it and provide the ability to navigate and route by voice commands. The suggested voice synthesis system is used, so as to guide the user through obstacles in indoor locations. The information of the precise location and.orientation of the device is made available to the whole system, through the building’s network infrastructure, so that the user’s mobile phone, been connected to the same network and also to the user’s headset through BLE, is able to send audio commands. For the voice commands, Google Cloud Text-ToSpeech (TTS) will be used, supposed that an online connection is active on the user’s device. %B The Sixteenth International Conference on Networking and Services (ICNS 2020), September 27, 2020 - October 01, 2020 , Lisbon, Portugal %G eng %0 Conference Paper %B The 14th International Conference on Broad - Band Wireless Computing, Communication and Applications (BWCCA - 2019), Antwerp, Belgium %D 2019 %T Efficient 5G Network Decoupling using dynamic Modulation and Coding Scheme Selection %A Christos Bouras %A Vasileios Kokkinos %A Evangelos Michos %X The transmission power limitations in telecommunication systems are tackled by using low code rates and high order modulation schemes, thus achieving high spectral efficiency with lower costs per bit. This paper evaluates the User-Centric model for Fifth Generation wireless telecommunication systems, attempting to efficiently improve user terminal-Base Station communication aspects. We propose a resource-aware method of improving network coverage across all layers by choosing to decouple the overall network into two separate uplink and downlink networks. The algorithm fully respects each user’s throughput demands and solves the User Equipment – Base Station association problem efficiently by choosing the appropriate Modulation and Coding Scheme that maximizes spectral efficiency inside each macro cell coverage area. Results are evaluated for both acceptable frequency ranges defined in 5G New Radio protocol interfaces (namely, Frequency Range 1 and Frequency Range 2) and show that the proposed Modulation and Coding Scheme-based mechanism offers perfect Quality of Service preservation and augmented data rates in favor of ultimate user coverage, in both scenarios. Additionally, due to the extended resources Frequency Range 2 provides, the equivalent simulation not only offers increased data rates compared to Frequency Range 1, but also a lower number of devices unsupported by the mechanism. %B The 14th International Conference on Broad - Band Wireless Computing, Communication and Applications (BWCCA - 2019), Antwerp, Belgium %P 253-265 %8 November 7 - 9 %G eng %0 Conference Paper %B International Symposium on Networks, Computers and Communications (ISNCC' 19) - Wireless and Mobile Networks %D 2019 %T Resource-Efficient Decoupling in Ultra-Dense 5G Networks %A Christos Bouras %A Vasileios Kokkinos %A Evangelos Michos %X The evolution of 5G mobile networks is expected to be comprised of small cell deployments within spitting distance of existing macrocell infrastructures. The small cells adoption, which promises to offer an economical solution for improved coverage and data rate, appears to be the key factor at improving network cooperation and system performance. In this paper, we evaluate the User-Centric model for 5G networks, targeted at improving communication between user terminal and Base Stations across all layers. We suggest a cost-effective, resource-aware method for improved mobile outdoor coverage and overall network capacity while fully respecting the user’s Quality of Service, by decoupling the overall network into downlink and uplink networks. The proposed algorithm determines how the network users in both networks will efficiently connect to a Base Station. The network performances are evaluated in terms of data rates enhancements, association outcome and preservation of the Quality of Service for each user. Our low-complexity algorigthm ultimately manages to serve the vast majority of the users placed inside an ultra-dense network and achieve perfect preservation of Quality of Service, regardless of the number of active users. %B International Symposium on Networks, Computers and Communications (ISNCC' 19) - Wireless and Mobile Networks %8 June 18-20 %G eng