Beyond REM: A New Approach to the Use of Image Classifiers for the Management of 6G Networks.

The management of cellular networks, particularly within the environment rapidly advancing to 6G, presents considerable challenges due to the highly dynamic radio environment. Traditional tools such as Radio Environment Maps (REMs) have proven inadequate for real-time network changes, underlining the need for more sophisticated solutions. In response to these challenges, this work introduces a novel approach that harnesses the unprecedented power of state-of-the-art image classifiers for network management. This method involves the generation of Network Synthetic Images (NSIs), which are enriched heat maps that precisely reflect varying cellular network operating states. Created from user location traces linked with Key Performance Indicators (KPIs), NSIs are strategically designed to meet the intricate demands of 6G networks. This research delves deep into a comprehensive analysis of the diverse factors that could potentially impact the successful application of this methodology in the realm of 6G. The results from this investigation, coupled with a comparative assessment against traditional REM usage, emphasize the superior performance of this innovative method. Additionally, a case study involving an automatic network diagnosis scenario validates the effectiveness of this approach. The findings reveal that a generic Convolutional Neural Network (CNN), one of the most powerful tools in the arsenal of modern image classifiers, delivers enhanced performance, even with a reduced demand for positioning accuracy. This contributes significantly to the real-time, robust management of cellular networks as we transition into the era of 6G.

Active Learning Methodology for Expert-Assisted Anomaly Detection in Mobile Communications.

Due to the great complexity, heterogeneity, and variety of services, anomaly detection is becoming an increasingly important challenge in the operation of new generations of mobile communications. In many cases, the underlying relationships between the multiplicity of parameters and factors that can cause anomalous behavior are only determined by human expert knowledge. On the other hand, although automatic algorithms have a great capacity to process multiple sources of information, they are not always able to correctly signal such abnormalities. In this sense, this paper proposes the integration of both components in a framework based on Active Learning that enables enhanced performance in anomaly detection tasks. A series of tests have been conducted using an online anomaly detection algorithm comparing the proposed solution with a method based on the algorithm output alone. The obtained results demonstrate that a hybrid anomaly detection model that automates part of the process and includes the knowledge of an expert following the described methodology yields increased performance.

Cellular Network Radio Monitoring and Management through Virtual UE Probes: A Study Case Based on Crowded Events.

Although log processing of network equipment is a common technique in cellular network management, several factors make said task challenging, especially during mass attendance events. The present paper assesses classic methods for cellular network measurement and acquisition, showing how the use of on-the-field user probes can provide relevant capabilities to the analysis of cellular network performance. Therefore, a framework for the deployment of this kind of system is proposed here based on the development of a new hardware virtualization platform with radio frequency capabilities. Accordingly, an analysis of the characteristics and requirements for the use of virtual probes was performed. Moreover, the impact that social events (e.g., sports matches) may have on the service provision was evaluated through a real cellular scenario. For this purpose, a long-term measurement study during crowded events (i.e., football matches) in a stadium has been conducted, and the performances of different services and operators under realistic settings has been evaluated. As a result, several considerations are presented that can be used for better management of future networks.

Measuring Key Quality Indicators in Cloud Gaming: Framework and Assessment Over Wireless Networks.

Cloud Gaming is a cutting-edge paradigm in the video game provision where the graphics rendering and logic are computed in the cloud. This allows a user's thin client systems with much more limited capabilities to offer a comparable experience with traditional local and online gaming but using reduced hardware requirements. In contrast, this approach stresses the communication networks between the client and the cloud. In this context, it is necessary to know how to configure the network in order to provide service with the best quality. To that end, the present work defines a novel framework for Cloud Gaming performance evaluation. This system is implemented in a real testbed and evaluates the Cloud Gaming approach for different transport networks (Ethernet, WiFi, and LTE (Long Term Evolution)) and scenarios, automating the acquisition of the gaming metrics. From this, the impact on the overall gaming experience is analyzed identifying the main parameters involved in its performance. Hence, the future lines for Cloud Gaming QoE-based (Quality of Experience) optimization are established, this way being of configuration, a trendy paradigm in the new-generation networks, such as 4G and 5G (Fourth and Fifth Generation of Mobile Networks).

A Multivariate Time-Series Based Approach for Quality Modeling in Wireless Networks.

This work presents a method for estimating key quality indicators (KQIs) from measurements gathered at the nodes of a wireless network. The procedure employs multivariate adaptive filtering and a clustering algorithm to produce a KQI time-series suitable for post-processing by the network management system. The framework design, aimed to be applied to 5G and 6G systems, can cope with a nonstationary environment, allow fast and online training, and provide flexibility for its implementation. The concept's feasibility was evaluated using measurements collected from a live heterogeneous network, and initial results were compared to other linear regression techniques. Suggestions for modifications in the algorithms are also described, as well as directions for future research.

Location-Awareness for Failure Management in Cellular Networks: An Integrated Approach.

Recent years have seen the proliferation of different techniques for outdoor and, especially, indoor positioning. Still being a field in development, localization is expected to be fully pervasive in the next few years. Although the development of such techniques is driven by the commercialization of location-based services (e.g., navigation), its application to support cellular management is considered to be a key approach for improving its resilience and performance. When different approaches have been defined for integrating location information into the failure management activities, they commonly ignore the increase in the dimensionality of the data as well as their integration into the complete flow of networks failure management. Taking this into account, the present work proposes a complete integrated approach for location-aware failure management, covering the gathering of network and positioning data, the generation of metrics, the reduction in the dimensionality of such data, and the application of inference mechanisms. The proposed scheme is then evaluated by system-level simulation in ultra-dense scenarios, showing the capabilities of the approach to increase the reliability of the supported diagnosis process as well as reducing its computational cost.

Smart Tree: An Architectural, Greening and ICT Multidisciplinary Approach to Smart Campus Environments.

At present, climate change, pollution, and uncontrolled urbanism threaten not only natural ecosystems, but also the urban environment. Approaches to mitigate these challenges and able to provide an alternative for the use of the space are deemed to be multidisciplinary, combining architecture, vegetation integration, circular economy and information and communications technologies (ICT). University campuses are a key scenario to evaluate such solutions as their student and research community is intrinsically willing to support these experiences and provide a wide knowledge on the fields necessary for their design and implementation. However, the creation of areas combining usability and sustainability is commonly lacking a multidisciplinary approach combining all these different perspectives. Hence, the present work aims to overcome this limitation by the development of a novel integrated approach for campus spaces for co-working and leisure, namely a "Smart Tree", where novel architecture, furniture design, flora integration, environmental sensoring and communications join together. To this end, a survey of the literature is provided, covering related approaches as well as general principles behind them. From this, the general requirements and constraints for the development of the Smart Tree area are identified, establishing the main interactions between the architecture, greening and ICT perspectives. Such requirements guide the proposed system design and implementation, whose impact on the environment is analyzed. Finally, the research challenges and lessons learned for their development are identified in order to support future works.

The Campus as a Smart City: University of Málaga Environmental, Learning, and Research Approaches.

For the past few years, the concept of the Internet of Things (IoT) has been a recurrent view of the technological environment where nearly every object is expected to be connected to the network. This infrastructure will progressively allow one to monitor and efficiently manage the environment. Until recent years, the IoT applications have been constrained by the limited computational capacity and especially by efficient communications, but the emergence of new communication technologies allows us to overcome most of these issues. This situation paves the way for the fulfillment of the Smart-City concept, where the cities become a fully efficient, monitored, and managed environment able to sustain the increasing needs of its citizens and achieve environmental goals and challenges. However, many Smart-City approaches still require testing and study for their full development and adoption. To facilitate this, the university of Málaga made the commitment to investigate and innovate the concept of Smart-Campus. The goal is to transform university campuses into "small" smart cities able to support efficient management of their area as well as innovative educational and research activities, which would be key factors to the proper development of the smart-cities of the future. This paper presents the University of Málaga long-term commitment to the development of its Smart-Campus in the fields of its infrastructure, management, research support, and learning activities. In this way, the adopted IoT and telecommunication architecture is presented, detailing the schemes and initiatives defined for its use in learning activities. This approach is then assessed, establishing the principles for its general application.

Rectal neuroendocrine carcinoma: case report of a rare entity and perspective review of promising agents.

Neuroendocrine neoplasms (NENs) comprise a heterogeneous group of tumours, which can be classified into neuroendocrine tumours (NETs), neuroendocrine carcinomas (NECs) and mixed neuroendocrine non-neuroendocrine neoplasms (MiNENs). To date, there is no consensus regarding the optimal therapy, which usually depends on the primary location and classification, according to morphological features of differentiation and proliferation rates. Nevertheless, multidisciplinary strategies combining medical treatments and locoregional strategies have yielded better efficacy results. Here, we report the case of a patient diagnosed with a nonfunctional rectal NECs with metastatic widespread to pelvic lymph nodes and bilateral lung metastases. The patient received three cycles of platinum-etoposide, concomitantly with palliative radiotherapy. Although CT scan after three cycles showed a significant partial response, there was an early fatal progression only 3 months after having stopped systemic therapy. As formerly described in the literature, this case highlights the aggressive behaviour of NECs, rare tumours that often present in advanced stages at diagnosis. Lately, new insights into the molecular biology of NECs have unveiled the possibility of using novel drugs, such as targeted agents or immunotherapy, in molecularly selected subgroups of patients. In this review, we discuss the current management of this rare entity and provide an overview of the most relevant molecular findings, whilst illustrating the potential value that prescreening panels can offer, searching for actionable targets (MSI/dMMR, PD-L1, BRAFv600E) to guide therapy with promising agents that could fill a void in this disease.