Advancing IIoT with Over-the-Air Federated Learning: The Role of Iterative Magnitude Pruning

The industrial Internet of Things (IIoT) under Industry 4.0 heralds an era of interconnected smart devices where data-driven insights and machine learning (ML) fuse to revolutionize manufacturing. A noteworthy development in IIoT is the integration of federated learning (FL), which addresses data privacy and security among devices. FL enables edge sensors, also known as peripheral intelligence units (PIUs) to learn and adapt using their data locally, without explicit sharing of confidential data, to facilitate a collaborative yet confidential learning process. However, the lower memory footprint and computational power of PIUs inherently require deep neural network (DNN) models that have a very compact size. Model compression techniques such as pruning can be used to reduce the size of DNN models by removing unnecessary connections that have little impact on the model's performance, thus making the models more suitable for the limited resources of PIUs. Targeting the notion of compact yet robust DNN models, we propose the integration of iterative magnitude pruning (IMP) of the DNN model being trained in an over-the-air FL (OTA-FL) environment for IIoT. We provide a tutorial overview and also present a case study of the effectiveness of IMP in OTA-FL for an IIoT environment. Finally, we present future directions for enhancing and optimizing these deep compression techniques further, aiming to push the boundaries of IIoT capabilities in acquiring compact yet robust and high-performing DNN models.

Design of an Efficient CSI Feedback Mechanism in Massive MIMO Systems: A Machine Learning Approach using Empirical Data

Massive multiple-input multiple-output (mMIMO) regime reaps the benefits of spatial diversity and multiplexing gains, subject to precise channel state information (CSI) acquisition. In the current communication architecture, the downlink CSI is estimated by the user equipment (UE) via dedicated pilots and then fed back to the gNodeB (gNB). The feedback information is compressed with the goal of reducing over-the-air overhead. This compression increases the inaccuracy of acquired CSI, thus degrading the overall spectral efficiency. This paper proposes a computationally inexpensive machine learning (ML)-based CSI feedback algorithm, which exploits twin channel predictors. The proposed approach can work for both time-division duplex (TDD) and frequency-division duplex (FDD) systems, and it allows to reduce feedback overhead and improves the acquired CSI accuracy. To observe real benefits, we demonstrate the performance of the proposed approach using the empirical data recorded at the Nokia campus in Stuttgart, Germany. Numerical results show the effectiveness of the proposed approach in terms of reducing overhead, minimizing quantization errors, increasing spectral efficiency, cosine similarity, and precoding gain compared to the traditional CSI feedback mechanism.

Industry 5.0 is Coming: A Survey on Intelligent NextG Wireless Networks as Technological Enablers

Industry 5.0 vision, a step toward the next industrial revolution and enhancement to Industry 4.0, envisioned the new goals of resilient, sustainable, and human-centric approaches in diverse emerging applications, e.g., factories-of-the-future, digital society. The vision seeks to leverage human intelligence and creativity in nexus with intelligent, efficient, and reliable cognitive collaborating robots (cobots) to achieve zero waste, zerodefect, and mass customization-based manufacturing solutions. However, the vision requires the merging of cyber-physical worlds through utilizing Industry 5.0 technological enablers, e.g., cognitive cobots, person-centric artificial intelligence (AI), cyberphysical systems, digital twins, hyperconverged data storage and computing, communication infrastructure, and others. In this regard, the convergence of the emerging computational intelligence (CI) paradigm and next-generation wireless networks (NGWNs) can fulfill the stringent communication and computation requirements of the technological enablers in the Industry 5.0 vision, which is the aim of this survey-based tutorial. In this article, we address this issue by reviewing and analyzing current emerging concepts and technologies, e.g., CI tools and frameworks, network-in-box architecture, open radio access networks, softwarized service architectures, potential enabling services, and others, essential for designing the objectives of CINGWNs to fulfill the Industry 5.0 vision requirements. Finally, we provide a list of lessons learned from our detailed review, research challenges, and open issues that should be addressed in CI-NGWNs to realize Industry 5.0.

STAR-RIS-Assisted Hybrid NOMA mmWave Communication: Optimization and Performance Analysis

Simultaneously reflecting and transmitting reconfigurable intelligent surfaces (STAR-RIS) has recently emerged as prominent technology that exploits the transmissive property of RIS to mitigate the half-space coverage limitation of conventional RIS operating on millimeter-wave (mmWave). In this paper, we study a downlink STAR-RIS-based multi-user multiple-input single-output (MU-MISO) mmWave hybrid non-orthogonal multiple access (H-NOMA) wireless network, where a sum-rate maximization problem has been formulated. The design of active and passive beamforming vectors, time and power allocation for H-NOMA is a highly coupled non-convex problem. To handle the problem, we propose an optimization framework based on alternating optimization (AO) that iteratively solves active and passive beamforming sub-problems. Channel correlations and channel strength-based techniques have been proposed for a specific case of two-user optimal clustering and decoding order assignment, respectively, for which analytical solutions to joint power and time allocation for H-NOMA have also been derived. Simulation results show that: 1) the proposed framework leveraging H-NOMA outperforms conventional OMA and NOMA to maximize the achievable sum-rate; 2) using the proposed framework, the supported number of clusters for the given design constraints can be increased considerably; 3) through STAR-RIS, the number of elements can be significantly reduced as compared to conventional RIS to ensure a similar quality-of-service (QoS).

Towards On-Device AI and Blockchain for 6G enabled Agricultural Supply-chain Management

6G envisions artificial intelligence (AI) powered solutions for enhancing the quality-of-service (QoS) in the network and to ensure optimal utilization of resources. In this work, we propose an architecture based on the combination of unmanned aerial vehicles (UAVs), AI and blockchain for agricultural supply-chain management with the purpose of ensuring traceability, transparency, tracking inventories and contracts. We propose a solution to facilitate on-device AI by generating a roadmap of models with various resource-accuracy trade-offs. A fully convolutional neural network (FCN) model is used for biomass estimation through images captured by the UAV. Instead of a single compressed FCN model for deployment on UAV, we motivate the idea of iterative pruning to provide multiple task-specific models with various complexities and accuracy. To alleviate the impact of flight failure in a 6G enabled dynamic UAV network, the proposed model selection strategy will assist UAVs to update the model based on the runtime resource requirements.

Real-Time Trash Detection for Modern Societies using CCTV to Identifying Trash by utilizing Deep Convolutional Neural Network

To protect the environment from trash pollution, especially in societies, and to take strict action against the red-handed people who throws the trash. As modern societies are developing and these societies need a modern solution to make the environment clean. Artificial intelligence (AI) evolution, especially in Deep Learning, gives an excellent opportunity to develop real-time trash detection using CCTV cameras. The inclusion of this project is real-time trash detection using a deep model of Convolutional Neural Network (CNN). It is used to obtain eight classes mask, tissue papers, shoppers, boxes, automobile parts, pampers, bottles, and juices boxes. After detecting the trash, the camera records the video of that person for ten seconds who throw trash in society. The challenging part of this paper is preparing a complex custom dataset that took too much time. The dataset consists of more than 2100 images. The CNN model was created, labeled, and trained. The detection time accuracy and average mean precision (mAP) benchmark both models' performance. In experimental phase the mAP performance and accuracy of the improved CNN model was superior in all aspects. The model is used on a CCTV camera to detect trash in real-time.

Edge Intelligence in Softwarized 6G: Deep Learning-enabled Network Traffic Predictions

The 6G vision is envisaged to enable agile network expansion and rapid deployment of new on-demand microservices (i.e., visibility services for data traffic management, mobile edge computing services) closer to the network's edge IoT devices. However, providing one of the critical features of network visibility services, i.e., data flow prediction in the network, is challenging at the edge devices within a dynamic cloud-native environment as the traffic flow characteristics are random and sporadic. To provide the AI-native services for the 6G vision, we propose a novel edge-native framework to provide an intelligent prognosis technique for data traffic management in this paper. The prognosis model uses long short-term memory (LSTM)-based encoder-decoder deep learning, which we train on real time-series multivariate data records collected from the edge $\mu$-boxes of a selected testbed network. Our result accurately predicts the statistical characteristics of data traffic and verify against the ground truth observations. Moreover, we validate our novel framework model with two performance metrics for each feature of the multivariate data.

Reconfigurable Intelligent Surfaces: Potentials, Applications, and Challenges for 6G Wireless Networks

Reconfigurable intelligent surfaces (RISs), with the potential to realize a smart radio environment, have emerged as an energy-efficient and a cost-effective technology to support the services and demands foreseen for coming decades. By leveraging a large number of low-cost passive reflecting elements, RISs introduce a phase-shift in the impinging signal to create a favorable propagation channel between the transmitter and the receiver.~\textcolor{black}{In this article, we provide a tutorial overview of RISs for sixth-generation (6G) wireless networks. Specifically, we present a comprehensive discussion on performance gains that can be achieved by integrating RISs with emerging communication technologies. We address the practical implementation of RIS-assisted networks and expose the crucial challenges, including the RIS reconfiguration, deployment and size optimization, and channel estimation. Furthermore, we explore the integration of RIS and non-orthogonal multiple access (NOMA) under imperfect channel state information (CSI). Our numerical results illustrate the importance of better channel estimation in RIS-assisted networks and indicate the various factors that impact the size of RIS. Finally, we present promising future research directions for realizing RIS-assisted networks in 6G communication.

Backhaul-Aware Intelligent Positioning of UAVs and Association of Terrestrial Base Stations for Fronthaul Connectivity

The mushroom growth of cellular users requires novel advancements in the existing cellular infrastructure. One way to handle such a tremendous increase is to densely deploy terrestrial small-cell base stations (TSBSs) with careful management of smart backhaul/fronthaul networks. Nevertheless, terrestrial backhaul hubs significantly suffer from the dense fading environment and are difficult to install in a typical urban environment. Therefore, this paper considers the idea of replacing terrestrial backhaul network with an aerial network consisting of unmanned aerial vehicles (UAVs) to provide the fronthaul connectivity between the TSBSs and the ground core-network (GCN). To this end, we focus on the joint positioning of UAVs and the association of TSBSs such that the sum-rate of the overall system is maximized. In particular, the association problem of TSBSs with UAVs is formulated under communication-related constraints, i.e., bandwidth, number of connections to a UAV, power limit, interference threshold, UAV heights, and backhaul data rate. To meet this joint objective, we take advantage of the genetic algorithm (GA) due to the offline nature of our optimization problem. The performance of the proposed approach is evaluated using the unsupervised learning-based k-means clustering algorithm. We observe that the proposed approach is highly effective to satisfy the requirements of smart fronthaul networks.

New Normal: Cooperative Paradigm for Covid-19 Timely Detection and Containment using Internet of Things and Deep Learning

The spread of the novel coronavirus (COVID-19) has caused trillions of dollars in damages to the governments and health authorities by affecting the global economies. The purpose of this study is to introduce a connected smart paradigm that not only detects the possible spread of viruses but also helps to restart businesses/economies, and resume social life. We are proposing a connected Internet of Things ( IoT) based paradigm that makes use of object detection based on convolution neural networks (CNN), smart wearable and connected e-health to avoid current and future outbreaks. First, connected surveillance cameras feed continuous video stream to the server where we detect the inter-object distance to identify any social distancing violations. A violation activates area-based monitoring of active smartphone users and their current state of illness. In case a confirmed patient or a person with high symptoms is present, the system tracks exposed and infected people and appropriate measures are put into actions. We evaluated the proposed scheme for social distancing violation detection using YOLO (you only look once) v2 and v3, and for infection spread tracing using Python simulation.