The emerging integration of Internet of Things (IoT) and AI has unlocked numerous opportunities for innovation across diverse industries. However, growing privacy concerns and data isolation issues have inhibited this promising advancement. Unfortunately, traditional centralized Machine Learning (ML) methods have demonstrated their limitations in addressing these hurdles. In response to this ever-evolving landscape, Federated Learning (FL) has surfaced as a cutting-edge ML paradigm, enabling collaborative training across decentralized devices. FL allows users to jointly construct AI models without sharing their local raw data, ensuring data privacy, network scalability, and minimal data transfer. One essential aspect of FL revolves around proficient knowledge aggregation within a heterogeneous environment. Yet, the inherent characteristics of FL have amplified the complexity of its practical implementation compared to centralized ML. This survey delves into three prominent clusters of FL research contributions: personalization, optimization, and robustness. The objective is to provide a well-structured and fine-grained classification scheme related to these research areas through a unique methodology for selecting related work. Unlike other survey papers, we employed a hybrid approach that amalgamates bibliometric analysis and systematic scrutinizing to find the most influential work in the literature. Therefore, we examine challenges and contemporary techniques related to heterogeneity, efficiency, security, and privacy. Another valuable asset of this study is its comprehensive coverage of FL aggregation strategies, encompassing architectural features, synchronization methods, and several federation motivations. To further enrich our investigation, we provide practical insights into evaluating novel FL proposals and conduct experiments to assess and compare aggregation methods under IID and non-IID data distributions. Finally, we present a compelling set of research avenues that call for further exploration to open up a treasure of advancement.
Recent advances in hardware and communication technologies have accelerated the deployment of billions of wireless sensors. This transformation has created a wide range of applications adapted to the evolving trends of our daily life requirements. Wireless sensor networks (WSNs) could be deployed in several target areas including buildings, forests, oceans, and smart cities. Nevertheless, finding the optimal location for each sensor node is a challenging task, typically when the environment involves heterogeneous obstacles. Many approaches and methods have been proposed to deal with the problem of WSN deployment, each addressing one or more objectives and constraints, such as network coverage, lifetime, connectivity, and energy consumption. The purpose of this survey paper is to provide the needed background to understand and study the WSNs deployment problem with a focus on its two key aspects: the optimization model and the solving methods based on artificial intelligence (AI). Additionally, it covers recent works on WSNs deployment and identifies their advantages and limitations. Furthermore, simulation experiments were carried out to compare the performance of widely used algorithms in the context of WSNs deployment problem, primarily genetic algorithm, particle swarm optimization, flower pollination, and ant colony optimization. Finally, this paper discusses and highlights several open challenges and research issues that must be explored in the future.
Wireless Sensors Network (WSN) are essential to ensure data collection and monitor in real time buildings and their environments. In general, the collected data are of paramount importance especially to optimize resource consumption and to improve the indoor user's comfort. However, the reliability of smart buildings depends on the completeness and the relevance of the collected information, which needs an optimal sensor deployment inside buildings to ensure an efficient coverage of the area of interest. However, this problem has been widely studied in free space, but it became more complex when the sensors positions must take into account in the presence of heterogeneous obstacles. To tackle this problem, ISOD framework built a multiobjective optimization algorithm, exploits BIM database information including the physical properties of the used materials in the obstacles, and deploys dynamically the optimal WSN configuration. The effectiveness of ISOD has been showed on different scenarios and the results showed that ISOD deployments have a maximum coverage with a reliable connectivity.
8 August 2011 in International Journal of Communication Systems