Transit search algorithm based on oscillation exploitation factor and Roche limit for wireless sensor network deployment optimization DOI Creative Commons

Yu-Xuan Xing,

Jie-Sheng Wang, Siwen Zhang

et al.

Artificial Intelligence Review, Journal Year: 2024, Volume and Issue: 58(1)

Published: Nov. 27, 2024

To optimize the deployment of nodes in Wireless Sensor Networks (WSN) and effectively control network node energy consumption, thereby improving quality perception services, a Transit search algorithm based on oscillation exploitation factor Roche limit is proposed. The limit-inspired approach enhances stellar phase algorithm, accelerating convergence rate mid-to-late stages iteration while ensuring adequate exploration solution space. Subsequently, five weakening development factors are introduced to refine algorithm's improve its fine-tuning accuracy. validate effectiveness these strategies, various approaches applied coverage, waste consumption two models WSN deployment, with connectivity recorded. comparison reveals optimal improved SEROTS, which coverage by 1.34% obstacle-free model compared original TS rates reduced 2.05% 0.00016%, respectively. In obstacle model, increases 1.49%, decrease 6.96% 0.0004%, demonstrate efficiency optimizing SEROTS four optimization algorithms: Egret Swarm Optimization Algorithm (ESOA), Honey Badger (HBA), Sparrow Search (SSA) Differential Evolution (DE). Two selected, integrating three objectives into single objective function. Simulation results indicate that performs best both models, an improvement 0.53% 0.79% over second-best Furthermore, proposed strategies simulation from other studies, achieving higher 1.57%, 3.33%, 0.87%, 3.81% 0.21%, Finally, experiments discuss application large-scale scenarios, verifying feasibility optimization.

Language: Английский

Determining Signatures for Energy Mix Produced by Photovoltaic Systems and Wind Turbines DOI Creative Commons
Branislav Šarkan, Jacek Caban, Arkadiusz Małek

et al.

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(4), P. 1800 - 1800

Published: Feb. 10, 2025

The article contains an analysis of power generation by a photovoltaic system with peak 3 MWp and wind turbine 3.45 MW. acquired time series generated was analyzed using traditional modern analytical methods. these two Renewable Energy Sources characterized separately then their mix. In this article, the signature defined as in state space over period one month. extracted from results cluster analysis. experiment clustering carried out into 10 classes. K-Means algorithm used to determine clusters variant without prior labeling classes method learning participation teacher. way, trajectories process were determined 10-state space. Knowing which class each data record belongs to, frequencies staying determined. computational presented may have great practical application balancing grid powered energy produced renewable sources.

Language: Английский

Citations

0
Defining Signatures for Intelligent Vehicles with Different Types of Powertrains DOI Creative Commons
Arkadiusz Małek, Andrzej Marciniak,

Dariusz Kroczyński

et al.

World Electric Vehicle Journal, Journal Year: 2025, Volume and Issue: 16(3), P. 135 - 135

Published: March 1, 2025

This article presents a straightforward and effective way of adding the Internet Vehicles function to vehicles with different drive systems. By equipping vehicle transmission device that communicates vehicle’s on-board diagnostics system, current parameters operation can be read. allows for wireless application installed on mobile device. The related together location data from Global Positioning System are transferred cloud server. In this way, each system acquires function. Using setup, short trips in urban conditions were carried out an internal combustion engine plug-in hybrid vehicle. then processed using KNIME analytical platform. Signatures characterizing two types systems created. obtained results analyzed various tools experimentally validated. presented method is universally applicable quick recognition based signatures implementing k-means analysis. Acquiring processing used obtain important information about itself, road infrastructure, immediate surroundings, which translate into increased safety.

Language: Английский

Citations

0
Integration of Federated Learning and Blockchain in Healthcare: A Tutorial DOI Creative Commons
Yahya Shahsavari, Oussama Abderrahmane Dambri, Yaser Baseri

et al.

Published: April 18, 2024

Wearable devices and medical sensors revolutionize health monitoring, raising concerns about data privacy in Machine Learning (ML) for healthcare.This tutorial explores Federated (FL) Blockchain (BC) integration, offering a secure privacy-preserving approach to healthcare analytics.FL enables decentralized model training on local at institutions, keeping patient localized.This facilitates collaborative development without compromising privacy.However, FL introduces vulnerabilities.BC, with its tamper-proof ledger smart contracts, provides robust framework learning FL.After presenting taxonomy the various types of used ML applications, concise review techniques use cases, this three integration architectures balancing decentralization, scalability, reliability data.Furthermore, it investigates how Blockchain-based (BCFL) enhances security collaboration disease prediction, image analysis, drug discovery.By providing FL, blockchain, their along BCFL paper serves as valuable resource researchers practitioners seeking leverage these technologies ML.It aims accelerate advancements analytics, ultimately improving outcomes.

Language: Английский

Citations

1
Transit search algorithm based on oscillation exploitation factor and Roche limit for wireless sensor network deployment optimization DOI Creative Commons

Yu-Xuan Xing,

Jie-Sheng Wang, Siwen Zhang

et al.

Artificial Intelligence Review, Journal Year: 2024, Volume and Issue: 58(1)

Published: Nov. 27, 2024

To optimize the deployment of nodes in Wireless Sensor Networks (WSN) and effectively control network node energy consumption, thereby improving quality perception services, a Transit search algorithm based on oscillation exploitation factor Roche limit is proposed. The limit-inspired approach enhances stellar phase algorithm, accelerating convergence rate mid-to-late stages iteration while ensuring adequate exploration solution space. Subsequently, five weakening development factors are introduced to refine algorithm's improve its fine-tuning accuracy. validate effectiveness these strategies, various approaches applied coverage, waste consumption two models WSN deployment, with connectivity recorded. comparison reveals optimal improved SEROTS, which coverage by 1.34% obstacle-free model compared original TS rates reduced 2.05% 0.00016%, respectively. In obstacle model, increases 1.49%, decrease 6.96% 0.0004%, demonstrate efficiency optimizing SEROTS four optimization algorithms: Egret Swarm Optimization Algorithm (ESOA), Honey Badger (HBA), Sparrow Search (SSA) Differential Evolution (DE). Two selected, integrating three objectives into single objective function. Simulation results indicate that performs best both models, an improvement 0.53% 0.79% over second-best Furthermore, proposed strategies simulation from other studies, achieving higher 1.57%, 3.33%, 0.87%, 3.81% 0.21%, Finally, experiments discuss application large-scale scenarios, verifying feasibility optimization.

Language: Английский

Citations

0