The rapid evolution of communication networks in recent decades has intensified the need for advanced Network and Service Management (NSM) strategies to address the growing demands for efficiency, scalability, enhanced performance, and reliability of these networks. Large Language Models (LLMs) have received tremendous attention due to their unparalleled capabilities in various Natural Language Processing (NLP) tasks and generating context-aware insights, offering transformative potential for automating diverse communication NSM tasks. Contrasting existing surveys that consider a single network domain, this survey investigates the integration of LLMs across different communication network domains, including mobile networks and related technologies, vehicular networks, cloud-based networks, and fog/edge-based networks. First, the survey provides foundational knowledge of LLMs, explicitly detailing the generic transformer architecture, general-purpose and domain-specific LLMs, LLM model pre-training and fine-tuning, and their relation to communication NSM. Under a novel taxonomy of network monitoring and reporting, AI-powered network planning, network deployment and distribution, and continuous network support, we extensively categorize LLM applications for NSM tasks in each of the different network domains, exploring existing literature and their contributions thus far. Then, we identify existing challenges and open issues, as well as future research directions for LLM-driven communication NSM, emphasizing the need for scalable, adaptable, and resource-efficient solutions that align with the dynamic landscape of communication networks. We envision that this survey serves as a holistic roadmap, providing critical insights for leveraging LLMs to enhance NSM.

In this paper, the problem of active node selection for localization tasks, in Internet of Things (IoT) sensing applications, is addressed. IoT plays a significant role in realizing the concept of smart environments, such as in environmental, infrastructural, industrial, disaster, or threat monitoring. Several IoT sensing nodes can be deployed within an area to collect regional information for the purpose of achieving a common contextual goal. Active node selection proves useful in mitigating common IoT-related issues like resource allocation, network lifetime, and the confidence in the collected data, by having the right sensors active at a given time. Current active node selection schemes prove inefficient when adapted to localization tasks, as they-(1) are usually designed for general monitoring, not localization, (2) do not dynamically exploit data readings in the selection process, and (3) are mostly designed for systems with nodes having sensing ranges. To address these challenges, we propose a novel Data-driven Active Node Selection approach that-(1) dynamically uses data readings from current active nodes to select future ones, (2) assesses the area coverage achieved by a group of nodes while considering range-free sensors, (3) considers parameters like residual energy, power cost, and data confidence levels in the selection process, and (4) combines group-based and individual-based selection mechanisms to enhance the localization process in terms of time and power consumption. These considerations are integrated into a two-phase active node selection mechanism that uses genetic and greedy algorithms to select optimum groups for localization tasks. The efficacy of the proposed approach is validated through an example of radioactive source localization by using real-life and synthetic datasets, and by comparing the proposed approach to existing benchmarks. The results demonstrate the ability of the proposed approach to perform faster localization at low energy cost, even with smaller number of active nodes.

In target localization applications, readings from multiple sensing agents are processed to identify a target location. The localization systems using stationary sensors use data fusion methods to estimate the target location, whereas other systems use mobile sensing agents (UAVs, robots) to search the area for the target. However, such methods are designed for specific environments, and hence are deemed infeasible if the environment changes. For instance, the presence of walls increases the environment’s complexity and affects the collected readings and the mobility of the agents. Recent works explored Deep Reinforcement Learning (DRL) as an efficient and adaptable approach to tackle the target search problem. However, such methods are either designed for single-agent systems or for non-complex environments. This work proposes two novel Multi-Agent DRL models for target localization through search in complex environments. The first model utilizes Proximal Policy Optimization, Convolutional Neural Networks, Convolutional AutoEncoders to create embeddings, and a shaped reward function using Breadth First Search to obtain cooperative agents that achieve fast localization at low cost. The second model improves the first model in terms of computational complexity by replacing the shaped reward with a simple sparse reward, subject to the availability of Expert Demonstrations. Expert demonstrations are used in Demonstration Cloning, a novel method that utilizes demonstrations to guide the learning of new agents. The proposed models are tested on a scenario of radioactive target localization, and benchmarked with existing methods, showing efficacy in terms of localization time and cost, in addition to learning speed and stability.

Workers recruitment remains a significant issue in Mobile Crowdsourcing (MCS), where the aim is to recruit a group of workers that maximizes the expected Quality of Service (QoS). Current recruitment systems assume that a pre-defined pool of workers is available. However, this assumption is not always true, especially in cold-start situations, where a new MCS task has just been released. Additionally, studies show that up to 96% of the available candidates are usually not willing to perform the assigned tasks. To tackle these issues, recent works use Online Social Networks (OSNs) and Influence Maximization (IM) to advertise about the desired MCS tasks through influencers, aiming to build larger pools. However, these works suffer from several limitations, such as 1) the lack of group-based selection methods when choosing influencers, 2) the lack of a well-defined worker recruitment process following IM, 3) and the non-dynamicity of the recruitment process, where the workers who refuse to perform the task are not substituted. In this paper, an Influence-and Interest-based Worker Recruitment System (IIWRS), using OSNs, is proposed. The proposed system has two main components: 1) an MCS-, group-, and interest-based IM approach, using a Genetic Algorithm, to select a set of influencers from the network to advertise about the MCS tasks, and 2) a dynamic worker recruitment process which considers the social attributes of workers, and is able to substitute those who do not accept to perform the assigned tasks. Empirical studies are performed using real-life datasets, while comparing IIWRS with existing benchmarks.

Cardiac ultrasound (US) scanning is one of the most commonly used techniques in cardiology to diagnose the health of the heart and its proper functioning. During a typical US scan, medical professionals take several images of the heart to be classified based on the cardiac views they contain, with a focus on high-quality images. However, this task is time consuming and error prone. Therefore, it is necessary to consider ways to automate these tasks and assist medical professionals in classifying and assessing cardiac US images. Machine learning (ML) techniques are regarded as a prominent solution due to their success in the development of numerous applications aimed at enhancing the medical field, including addressing the shortage of echography technicians. However, the limited availability of medical data presents a significant barrier to the application of ML in the field of cardiology, particularly regarding US images of the heart. This paper addresses this challenge by introducing the first open graded dataset for Cardiac Assessment and ClassificaTion of UltraSound (CACTUS), which is available online. This dataset contains images obtained from scanning a CAE Blue Phantom and representing various heart views and different quality levels, exceeding the conventional cardiac views typically found in literature. Additionally, the paper introduces a Deep Learning (DL) framework consisting of two main components. The first component is responsible for classifying cardiac US images based on the heart view using a Convolutional Neural Network (CNN) architecture. The second component uses the concept of Transfer Learning (TL) to utilize knowledge from the first component and fine-tune it to create a model for grading and assessing cardiac images. The framework demonstrates high performance in both classification and grading, achieving up to 99.43% accuracy and as low as 0.3067 error, respectively. To showcase its robustness, the framework is further fine-tuned using new images representing additional cardiac views and also compared to several other state-of-the-art architectures. The framework's outcomes and its performance in handling real-time scans were also assessed using a questionnaire answered by cardiac experts.