An efficient algorithm for data transmission certainty in IIoT sensing network: A priority-based approach.

This paper proposes a novel cache replacement technique based on the notion of combining periodic popularity prediction with size caching. The popularity, size, and time updates characteristics are used to calculate the value of each cache item. When it comes to content replacement, the information with the least value is first eliminated. Simulation results show that the proposed method outperforms the current algorithms in terms of cache hit rate and delay. The hit rate of the proposed scheme is 15.3% higher than GDS, 17.3% higher than MPC, 20.1% higher than LRU, 22.3% higher than FIFO, and 24.8% higher than LFU when 350 different categories of information are present. In real-world industrial applications such as including supply chain management, smart manufacturing, automation energy optimization, intelligent logistics transportation, and e-healthcare applications, it offers a foundation for the selection of caching algorithms.

An intelligent algorithm for energy efficiency optimization in software-defined wireless sensor networks for 5G communications.

Wireless communications have lately experienced substantial exploitation because they provide a lot of flexibility for data delivery. It provides connection and mobility by using air as a medium. Wireless sensor networks (WSN) are now the most popular wireless technologies. They need a communication infrastructure that is both energy and computationally efficient, which is made feasible by developing the best communication protocol algorithms. The internet of things (IoT) paradigm is anticipated to be heavily reliant on a networking architecture that is currently in development and dubbed software-defined WSN. Energy-efficient routing design is a key objective for WSNs. Cluster routing is one of the most commonly used routing techniques for extending network life. This research proposes a novel approach for increasing the energy effectiveness and longevity of software-defined WSNs. The major goal is to reduce the energy consumption of the cluster routing protocol using the firefly algorithm and high-efficiency entropy. According to the findings of the simulation, the suggested method outperforms existing algorithms in terms of system performance under various operating conditions. The number of alive nodes determined by the proposed algorithm is about 42.06% higher than Distributed Energy-Efficient Clustering with firefly algorithm (DEEC-FA) and 13.95% higher than Improved Firefly Clustering IFCEER and 12.05% higher than another referenced algorithm.

Enhancing IoT Healthcare with Federated Learning and Variational Autoencoder.

The growth of IoT healthcare is aimed at providing efficient services to patients by utilizing data from local hospitals. However, privacy concerns can impede data sharing among third parties. Federated learning offers a solution by enabling the training of neural networks while maintaining the privacy of the data. To integrate federated learning into IoT healthcare, hospitals must be part of the network to jointly train a global central model on the server. Local hospitals can train the global model using their patient datasets and send the trained localized models to the server. These localized models are then aggregated to enhance the global model training process. The aggregation of local models dramatically influences the performance of global training, mainly due to the heterogeneous nature of patient data. Existing solutions to address this issue are iterative, slow, and susceptible to convergence. We propose two novel approaches that form groups efficiently and assign the aggregation weightage considering essential parameters vital for global training. Specifically, our method utilizes an autoencoder to extract features and learn the divergence between the latent representations of patient data to form groups, facilitating more efficient handling of heterogeneity. Additionally, we propose another novel aggregation process that utilizes several factors, including extracted features of patient data, to maximize performance further. Our proposed approaches for group formation and aggregation weighting outperform existing conventional methods. Notably, significant results are obtained, one of which shows that our proposed method achieves 20.8% higher accuracy and 7% lower loss reduction compared to the conventional methods.

Expand and Shrink: Federated Learning with Unlabeled Data Using Clustering.

The amalgamation of the Internet of Things (IoT) and federated learning (FL) is leading the next generation of data usage due to the possibility of deep learning with data privacy preservation. The FL architecture currently assumes labeled data samples from a client for supervised classification, which is unrealistic. Most research works in the literature focus on local training, update receiving, and global model updates. However, by principle, the labeling must be performed on the client side because the data samples cannot leave the source under the FL principle. In the literature, a few works have proposed methods for unlabeled data for FL using "class-prior probabilities" or "pseudo-labeling". However, these methods make either unrealistic or uncommon assumptions, such as knowing class-prior probabilities are impractical or unavailable for each classification task and even more challenging in the IoT ecosystem. Considering these limitations, we explored the possibility of performing federated learning with unlabeled data by providing a clustering-based method of labeling the sample before training or federation. The proposed work will be suitable for every type of classification task. We performed different experiments on the client by varying the labeled data ratio, the number of clusters, and the client participation ratio. We achieved accuracy rates of 87% and 90% by using 0.01 and 0.03 of the truth labels, respectively.

A Hybrid Energy Harvesting Design for On-Body Internet-of-Things (IoT) Networks.

The Internet-of-things (IoT) has been gradually paving the way for the pervasive connectivity of wireless networks. Due to the ability to connect a number of devices to the Internet, many applications of IoT networks have recently been proposed. Though these applications range from industrial automation to smart homes, healthcare applications are the most critical. Providing reliable connectivity among wearables and other monitoring devices is one of the major tasks of such healthcare networks. The main source of power for such low-powered IoT devices is the batteries, which have a limited lifetime and need to be replaced or recharged periodically. In order to improve their lifecycle, one of the most promising proposals is to harvest energy from the ambient resources in the environment. For this purpose, we designed an energy harvesting protocol that harvests energy from two ambient energy sources, namely radio frequency (RF) at 2.4 GHz and thermal energy. A rectenna is used to harvest RF energy, while the thermoelectric generator (TEG) is employed to harvest human thermal energy. To verify the proposed design, extensive simulations are performed in Green Castalia, which is a framework that is used with the Castalia simulator in OMNeT++. The results show significant improvements in terms of the harvested energy and lifecycle improvement of IoT devices.