Browsing by Author "Vieira, Pedro"
Now showing 1 - 10 of 79
Results Per Page
Sort Options
- 5GMEDE-5G mobile edge computing with enriched radio network information servicesPublication . Akman, A.; Monteiro, V.; Marques, P.; Rodriguez, J.; Vieira, Pedro; Marques, H.; Abdalla, A.5G has a number of challenges to solve. Higher data usage and processing power necessities have emerged from the increasing number of mobile users as well as mobile applications becoming more and more demanding. There is a significant need to reduce the latency of the mobile network while cutting down on energy consumption. Backhaul traffic needs to be optimized to avoid setting up costly backhaul connections. Many loT scenarios have conflicting requirements; the need for cheap and low complexity devices vs the need for processing power. Operators need to come up with value added services to avoid being dumb-pipe operators. The answer to these challenges and more require cloud-computing capabilities within the Radio :Access Network (RAN) as well as a platform for mobile operators and third-party application providers to utilize these computing capabilities. This is where Mobile Edge Computing (MEC), one of the key emerging technologies for 5G, comes into play. The 5GMEDE project proposes to not only develop and demonstrate a complete MEC solution, including the MEC framework, Base Station services and applications to run on top, but also offers innovative features like constraint based mobile edge selection, using data analytics to enrich and refine real-time radio network information and utilizing Software Defined Wireless Networks (SDWN) concepts to improve mobility and resource allocation services to enable operators.
- Abdominal MRI synthesis using styleGAN2-ADAPublication . Gonçalves, Bernardo; Vieira, Pedro; Vieira, AnaThe lack of labeled medical data still poses one of the biggest issues when creating Deep Learning models in the medical field. Modern data augmentation techniques like the generation of synthetic images have gained a special interest. In recent years there has been a significant improvement in GANs. StyleGAN2 achieves impressive results in the generation of natural images. StyleGAN2-ADA was created to respond to the lack of training data when training an image synthesis model, which is very frequent in the medical field. Some works used styleGAN to generate melanomas, breast cancer histological images, and MR and CT images. In this work, we apply, for the first time, a styleGAN2-ADA to a small dataset of abdominal MRI with 1.3k images. From the augmentation pipeline created by the authors of styleGAN2-ADA, we removed all augmentations except the geometric transformations and pixel blitting operations. We trained our network for 70 hours. Our generated dataset has a precision score of 59,33 % and a FID score of 18,14. We conclude that the styleGAN2-ADA is a viable solution to generate MRI using a small dataset.
- An efficient approach for capacity savings using load balancing in dual layer 3G wireless networksPublication . Pedro, Tiago; Martins, André; Rodrigues, António; Vieira, PedroIn order to survive in a highly competitive market, mobile network operators have to be as efficient as possible in managing their resources. This is particularly relevant in what concerns the capacity available at their sites. This work aims to give the operators a method to improve longevity of their sites. This was achieved using a Load Balancing algorithm, which takes into consideration the Channel Element usage of sites and sets an Received Signal Code Power threshold value for each one. Its evaluation is done by using a Traffic Forecast algorithm, based on a fitting method, in order to obtain an estimate of when the sites' capacity limit is reached, before and after applying Load Balancing. The used input data consisted of real traffic statistics, including geo-located indicators. During the course of this work it was possible to develop a semi-automatic method for network optimization using geo-located data, thus making a contribute to the development of national research on Self-Organizing Networks. This project was developed in collaboration with a Portuguese telecommunications consulting company, Celfinet, which provided valuable supervision and guidance. Using the suggested method it is predicted that, after a year of implementation, it is possible to achieve savings of about 70% in capacity expansions in the network.
- An enhanced capacity model based on network measurements for a multi-service 3G systemPublication . Parracho, Diogo; Duarte, David; Pinto, Iola; Vieira, PedroWith the ongoing growth on mobile networks utilization, new challenges come up in order to achieve a better efficient resource network management. The purpose of this paper is to present a multi-service platform based on admission curves for Third Generation (3G) and beyond mobile networks, depending on some cell characteristics, which are calculated based on real measurements. The model considers admission curves based on the Multidimensional Erlang-B model, which defines the maximum limit of resource utilization for a given Quality of Service (QoS), and will manage traffic between several services. The proposed method takes different specific constraints for each traffic environment based on network performance. To estimate the cell characteristics, for Voice and Packet Switched (PS) Release 99 (R99) services, a method is proposed, based on the Multiple Linear Regression model and dependent on Key Performance Indicators (KPI) taken from a live mobile network. For High Speed Downlink Packet Access (HSDPA) service, a different approach is set since there is a well defined time to transmit data (Transmission Time Interval (TTI)) along with other important features, like Channel Quality Indicator (CQI) and Block Error Rate (BLER), to be considered.
- An enhanced proposal in neighbor list planning for LTE SON radio access networksPublication . Duarte, D.; Martins, A.; Vieira, Pedro; Rodrigues, A.; Silva, N.Nowadays, a coexistence of 2nd Generation (2G), 3rd Generation (3G) and 4th Generation (4G) networks is being witnessed. Due to this situation, it became evident the need for Self-Organizing Networks (SON), which aims to automate most of the associated radio planning and optimization tasks. Within SON, this paper presents the latest work around an algorithm that optimizes the Neighbor Cell List (NCL) for Long Term Evolution (LTE) evolved NodeBs (eNBs). The algorithm is based on intra-site distance, its antenna orientation (azimuth/elevation), radiation pattern and overlap areas between cells. The research initial steps were already published (Duarte, D.; Vieira, P.; Rodrigues, A.; Martins, A.; Oliveira, N.; Varela, L., “Neighbour List Optimization for Real LTE Radio Networks,” Wireless and Mobile, 2014 IEEE Asia Pacific Conference on, pp.183,187, 28-30 Aug. 2014).
- An improved capacity model based on radio measurements for a 4G and beyond wireless networkPublication . Parracho, Diogo; Duarte, David; Pinto, Iola; Vieira, PedroThe mobile networks utilization is increasingly high, which implies a efficient resource network management coupled with a realistic capacity model. The aim of this paper is to present a capacity platform for Fourth Generation (4G) mobile networks, based on real measurements. The core of the proposed method is the deployment of a Multiple Linear Regression (MLR) model, based on propagation conditions, channel quality and delays for a specific cell. Information about how to locate the resource bottleneck and the related handling suggestions are provided. This approach outputs the maximum cell throughput at the busy hour, under realistic conditions. The method was developed using real data extracted from a live mobile network.
- An ubiquitous 2.6 GHz radio propagation model for wireless networks using self-supervised learning from satellite imagesPublication . Sousa, Marco; Vieira, Pedro; Queluz, Maria Paula; Rodrigues, AntónioThe performance of any Mobile Wireless Network (MWN) is dependent on the appropriate level of radio coverage, with Path Loss (PL) models being a valuable resource for its evaluation. Recently, advancements in Machine Learning (ML) and Deep Neural Networks (DNNs) have been applied to radio propagation to produce new data-driven PL models. Notoriously, these advancements have also allowed the inclusion of non-classical inputs, such as satellite images. However, data-driven PL models are often developed under the assumption that training and test data distributions are similar, which is a weak assumption in real-world scenarios. Thus, generalization (i.e., the model’s ability to perform on different data distributions) is a crucial aspect of data-driven PL models in the context of Mobile Network Operators (MNOs). This paper proposes a new data-driven PL model, the Ubiquitous Satellite Aided Radio Propagation (USARP) model, developed to enhance the geographical generalization capabilities of empirical PL models, by using satellite images. The USARP model considers self-supervised learning to extract general data representations of the radio environment from satellite images, improving the PL prediction Root Mean Square Error (RMSE) of the 3rd Generation Partnership Project (3GPP) PL model in the order of 9 dB, and for a data distribution distinct from the training data. Moreover, it was demonstrated the potential of the USARP model in terms of geographical and radio environment generalization. Although the generalization capabilities of ML regression algorithms are limited, the chosen USARP architecture and the use of regularization techniques had a positive impact on its geographical generalization performance.
- Analysis and optimization of 5G coverage predictions using a beamforming antenna model and real drive test measurementsPublication . Sousa, Marco; Alves, André; Vieira, Pedro; Queluz, Maria Paula; Rodrigues, AntónioThe ability to estimate radio coverage accurately is fundamental for planning and optimizing any wireless network, notably when a new generation, as the 5(th) Generation (5G), is in an early deployment phase. The knowledge acquired from radio planning of previous generations must be revisited, particularly the used path loss and antennas models, as the 5G propagation is intrinsically distinct. This paper analyses a new beamforming antenna model and distinct path loss models - 3(rd) Generation Partnership Project (3GPP) and Millimetre-Wave Based Mobile Radio Access Network for Fifth Generation Integrated Communications (mmMAGIC) - applying them to evaluate 5G coverage in 3-Dimensional (3D) synthetic and real scenarios, for outdoor and indoor environments. Further, real 5G Drive Tests (DTs) were used to evaluate the 3GPP path loss model accuracy in Urban Macro (UMa) scenarios. For the new antenna model, it is shown that the use of beamforming with multiple vertical beams is advantageous when the Base Station (BS) is placed below the surrounding buildings; in regular UMa surroundings, one vertical beam provides adequate indoor coverage and a maximized outdoor coverage after antenna tilt optimization. The 3GPP path loss model exhibited a Mean Absolute Error (MAE) of 21.05 dB for Line-of-Sight (LoS) and 14.48 dB for Non-Line-of-Sight (NLoS), compared with real measurements. After calibration, the MAE for LoS and NLoS decreased to 5.45 dB and 7.51 dB, respectively. Moreover, the non-calibrated 3GPP path loss model led to overestimations of the 5G coverage and user throughput up to 25% and 163%, respectively, when compared to the calibrated model predictions. The use of Machine Learning (ML) algorithms resulted in path loss MAEs within the range of 4.58 dB to 5.38 dB, for LoS, and within the range of 3.70 dB to 5.96 dB, for NLoS, with the Random Forest (RF) algorithm attaining the lowest error.
- Antenna tilt optimization using a novel QoE model based on 3G radio measurementsPublication . Pedras, V.; Sousa, M.; Vieira, Pedro; Queluz, M. P.; Rodrigues, A.This paper presents a novel Quality of Experience model (QoE), for 3G voice calls; it estimates a user perceived quality, in a Mean Opinion Score (MOS) scale, by evaluating several Radio Frequency (RF) channel metrics. Real Drive Test (DT) data with MOS measurements have been used as reference data, in order to produce a new MOS prediction model, using machine learning techniques. The new developed model enables the application of QoE as a possible network optimization criteria. Furthermore, it is showcased a generic framework to optimize antenna physical parameters. Using this framework, an algorithm was implemented which empowers the network MOS estimation by using the developed QoE model. A Root Mean Square Error (RMSE) of 9% was achieved, on the MOS prediction, using the developed model. Concerning the MOS antenna physical parameters optimization, it resulted in an average network performance gain of 5% comparatively to a interference control generic approach.
- Automated joint access and backhaul planning for 5G millimeter-wave small cell networksPublication . Marques, Beatriz; Sousa, Marco; Vieira, Pedro; Queluz, Maria Paula; Rodrigues, A.Mobile backhauling, small cells and millimeter waves (mmWaves) are key important technologies to support the next-generation cellular networks. The 5th generation (5G) radio networks introduce several different elements from the previous generations and hence, network planning became even more complex. In this work, the focus is on creating a radio network planning algorithm towards 5G mmWave small cell architectures. The algorithm is divided between the radio access network and the backhaul network. The former aims to find optimal locations for small cells to guarantee coverage requirements, while the latter creates backhaul links between the small cells according to a specific topology, and chooses which of them should be gateways. The results give some insights on base station (BS) and gateway density, and demonstrate that the topology most likely to meet Quality of Service (QoS) requirements, while minimizing the number of gateways, is the mesh network. However, tree and star topologies are also useful in certain scenarios. The work also includes a comparison between the 28 GHz and 60 GHz frequency bands, which are two common candidates for mmWave backhauling.