Accurate identification and classification of agricultural fields is essential for analyzing the crop growth, agricultural resource management, and supporting decision-making in precision farming. The current study, using the remote sensing images to classify the agricultural lands using the You Only Look Once (YOLO) V8 approach. The dataset consists of multiple classes like forests, river, sealake, highway, pasture, residential, industrial and the permanent crop. Various versions of YOLO V8, namely the nano, small, and medium versions of the deep learning (DL) model are used in classification of the sensor images. The impact of the hyperparameters like the number of epochs, optimizers, learning rate, momentum and weight decay are analyzed across all the versions of YOLO V8. The experimental outcome demonstrates the performance of each model concerning to the accuracy, precision, recall. Based on the experimental performance the YOLO V8 model is efficient in precisely recognizing various land cover, that result in offering a scalable and efficient approach for real-time agricultural field identification. From the experimental results, it can be stated that the medium variant has achieved the highest top_1 accuracy value of 99% at 50 epochs while nano and small variant achieves accuracy value of 98.60% and 98.50% at same epochs value respectively.
Energy storage systems (ESS) are seeing rapid market growth due to the changing worldwide landscape of electricity distribution and consumption. An ESS must possess the capability to oversee the functioning of the system’s modules under abnormal circumstances, while also having the ability to supervise, manage, and optimize the performance of one or more battery modules. At present, the condition of batteries is assessed based on two factors: the level of charge (SOC) and the overall condition (SOH). By using these two characteristics, it becomes feasible to compute the anticipated battery lifespan and evaluate a battery’s efficiency. The assessment of SOH is a crucial determinant in guaranteeing the effectiveness, dependability, and security of batteries in electric vehicles (EVs). Nevertheless, the safety issues resulting from the imprecise estimation and forecasting of battery health status have garnered significant attention in academic circles. This study presents a comprehensive evaluation of several SOH monitoring techniques. In order to achieve this objective, various scientific and technical literatures are examined and the corresponding methodologies are categorized into distinct groupings. The groupings are categorized based on the manner in which the procedure is executed: methods and techniques used in experiments and models. This paper provides a comprehensive overview of the benefits and drawbacks of several SOH assessment and prediction techniques, along with the associated obstacles in SOH estimation.
24 January 2025 in International Journal of Imaging Systems and Technology
A critical area is weather prediction, which has a direct application in agriculture, transport, disaster response, and energy control. The traditional techniques for weather forecasting sometimes fail to produce reliable results and are hardly scalable. This paper introduces an OSP-DNN fluid dynamics-based methodology for meteorological purposes, such as reliable and efficient weather prediction. Compared with asymmetric or indefinite matrices that can introduce adverse im pacts on neural networks, the proposed model takes advantage of the properties of SPD matrices to improve the learning efficiency and robustness of neural net works. The two investigated models include the baseline Positive Definite Neural Network (PDNN) and the optimized version (OSP-DNN). Compared to other methods, their efficiency is assessed in terms of accuracy, computational speed, and robustness to different data sets. The approach includes parametric simula tion of climate patterns, learning over mock data sets, and evaluation steps. The solutions presented to prove that the OSP-DNN is more precise than the tradi tional approach and improves the baseline PDNN by up to 25% with favorable time complexity. Experimental and numerical models are compared, and the consequence of the real-world small-scale models for practical problems is de scribed. This work lays the ground norms for the integration of mathematical structures within machine learning frameworks in the gap between theory and practice.
An innovative battery management system (BMS) is crucial for verifying the credibility and safety of electric vehicles (EVs) and other electrical devices. The precise state of health (SOH) estimation of the Lithium-ion batteries (LIBs) holds great importance in a BMS. Battery SOH is often committed by the utilization of suitable data-driven approaches and metrics. This study presents an alternative approach for examining the SOH of batteries through the use of a gated recurrent unit (GRU) as an estimating method. Finally, the Oxford battery datasets is subjected to both training and testing procedures. The validity of the proposed method's adaptability is shown by tests managed to estimate the SOH of a battery cell. The performance of our proposed method is validated on the battery dataset of Oxford, where the average RMSE is 0.31%.Graphical Abstract—