Search

Solar energy provides one of the most favorable options regarding the transition to clean energy sources. The parameters of a photovoltaic (PV) system play determine its performance under various scenarios. The PV model parameter estimation is an example of nonlinear planning. This study proposes a novel use of the established Smell Agent Optimizer (SAO) algorithm to anticipate the undefined parameters of the PV model's single-diode and two-diode equivalent circuits. This study aims to create a precise PV model that can accurately characterize its performance under changing operational conditions. The desired objective function is defined as the square of the mean squared error between the model's current-voltage curve and the measured curve. [ABSTRACT FROM AUTHOR]

Air quality forecasting is a critical environmental challenge with significant implications for public health and urban planning. Conventional machine learning models, although quite effective, require data collection, which can be hampered by issues relating to privacy and data security. Federated Learning (FL) overcomes these limitations by enabling model training across decentralized data sources without compromising data privacy. This study describes a federated learning approach to predict the Air Quality Index (AQI) based on data from several Internet of Things (IoT) sensors located in different urban locations. The proposed approach trains a model using data from different sensors while preserving the privacy of each data source. The model uses local computational resources at the sensor level during the initial data processing and training, sharing only the model updates to the central location. The results show that the performance of the proposed FL model is comparable to a centralized model and ensures better data privacy with reduced data transmission requirements. This study opens new doors to real-time, scalable, and efficient air quality monitoring systems. The proposed method is quite significant for smart city initiatives and environmental monitoring, as it provides a solid framework for using IoT technology while preserving privacy. [ABSTRACT FROM AUTHOR]

This study addresses the critical challenge of real-time identification of tomato leaf diseases using edge computing. Traditional plant disease detection methods rely on centralized cloud-based solutions that suffer from latency issues and require substantial bandwidth, making them less viable for real-time applications in remote or bandwidth-constrained environments. In response to these limitations, this study proposes an on-the-edge processing framework employing Convolutional Neural Networks (CNNs) to identify tomato diseases. This approach brings computation closer to the data source, reducing latency and conserving bandwidth. This study evaluates various pre-trained models, including MobileNetV2, InceptionV3, ResNet50, and VGG19 against a custom CNN, training and validating them on a comprehensive dataset of tomato leaf images. MobileNetV2 demonstrated exceptional performance, achieving an accuracy of 98.99%. The results highlight the potential of edge AI to revolutionize disease detection in agricultural settings, offering a scalable, efficient, and responsive solution that can be integrated into broader smart farming systems. This approach not only improves disease detection accuracy but can also provide actionable insights and timely alerts to farmers, ultimately contributing to increased crop yields and food security. [ABSTRACT FROM AUTHOR]

The robustness and longevity of agricultural robots, specifically those utilizing caterpillar tracks for coconut harvesting, are based on understanding their strain, stress, and load thresholds. This study delves into the deformation characteristics of caterpillar track systems, pinpointing critical structural vulnerabilities and potential points of failure. Through a meticulous analysis of the maximum allowed strain and stress thresholds, this study unravels crucial insights to enhance performance and reliability in coconut field operations. Leveraging the power of ANSYS for structural analysis and simulation under varied constraints, this study aims to fortify the structural integrity of agricultural robots. By offering valuable insights and solutions, this study paves the way for advancements in agricultural robotics technology, ensuring that these machines can endure rigorous tasks while maintaining peak functionality. [ABSTRACT FROM AUTHOR]

Combining Intelligent Reflecting Surfaces (IRSs) with Non-Orthogonal Multiple Access (NOMA) effectively enhances communication. This study introduces a NOMA-assisted Downlink Transmission (DT) system, emphasizing Energy Efficiency (EE) optimization. EE, crucial in Wireless Communications (WCs), measures data transmission relative to energy consumption. This study focuses on a Deep Deterministic Policy Gradient (DDPG) algorithm that intelligently adjusts IRS phase-shift matrices and access point beamforming in NOMA DT. Beamforming directs signals to users for optimal strength and quality, while phase shift control enhances signal coverage and quality. Strategic IRS placement improves user signal transmissions. The simulation results demonstrate significantly improved EE compared to other algorithms, such as Deep Q Network (DQN) and Proximal Policy Optimization (PPO), showcasing the effectiveness of the combined IRS and NOMA approach in enhancing communication systems' EE. [ABSTRACT FROM AUTHOR]

With the dramatic increase in mobile users and wireless devices accessing the network, the performance of 5G wireless communication systems is severely challenged. Reconfigurable Intelligent Surface (RIS) has received much attention as one of the promising technologies for 6G due to its ease of deployment, low power consumption, and low price. This study aims to improve accuracy, reliability, and the capacity to estimate channel characteristics between transmitter and receiver. However, this is practically challenging for the following reasons. Due to the lack of active components for baseband signal processing, low-cost passive RIS elements can only reflect incident signals but without the capability to transmit/receive pilot signals for channel estimation as active transceivers in conventional wireless communication systems. This study presents different channel estimation methods for RIS-MIMO systems that use deep learning techniques. [ABSTRACT FROM AUTHOR]

Organizing automobiles in a city is challenging due to the sensitive data that need to be disclosed. Information that can be utilized to identify a car and provide some useful characteristics about it is among the large amount of data that can be collected from an automobile. This operation will be easier if the vehicles are placed on a specific platform based on the smart city concept. Even if sensors and cameras are installed around the roads and the city, having the vehicle information will be more useful. The current study tries to demonstrate how it is feasible to improve vehicle autonomy by initially enhancing the vehicle's energetic performance, based on the smart city idea. Intelligent control topology serves as the foundation for the exposed energy management protocol. The suggested concept is created and the associated results are displayed using the Matlab Simulink platform. [ABSTRACT FROM AUTHOR]