Search

Deep learning techniques are revolutionizing the analysis of remote sensing imagery for mangrove land use and land change studies. These methods improve the accuracy and efficiency of identifying changes in mangrove forests, providing valuable insights for environmental monitoring and conservation efforts. This study presents an in-depth analysis of land cover changes on Hainan Island, China, over 30 years from 1993 to 2023, using Landsat 5 imagery. Through the classification of land cover into six distinct categories—barren/agriculture, urban/infrastructure, high vegetation, low vegetation, water, and clouds—we examined the temporal shifts and trends in the island's landscape. An accuracy assessment using high-resolution Landsat Satellite imagery provided validation for the classification method, achieving an accuracy of over 70%. The results revealed a notable urban expansion and recuperation of high vegetation areas, indicating a strong interaction between human activities and natural ecosystems. The study underscores the dynamic nature of land cover influenced by both anthropogenic and natural factors and highlights the importance of remote sensing in environmental monitoring. Future work will involve the adoption of newer satellite technologies and machine learning techniques to enhance the precision of land cover classification, integrate additional ecological data, and employ predictive modeling for sustainable land management strategies. The continuation of these efforts is crucial for informing policy decisions to ensure the preservation of Hainan's rich biodiversity and natural resources.

This research endeavor delves into the utilization of non-orthogonal multiple access (NOMA) techniques within the context of optical wireless sensor networks (OWSNs). The study entails an exploration of the viability of integrating NOMA into OWSNs and introduces a novel architectural framework that amalgamates successive interference cancellation (SIC) and superposition coding methodologies. This amalgamation aims to enhance the overall performance and spectral efficiency of the network. The investigation meticulously assesses the performance of the proposed architecture, employing diverse metrics such as bit error rate (BER), outage probability, and environmental impact. Empirical results underscore the commendable precision of the NOMA-based architecture when juxtaposed with conventional orthogonal multiple access (OMA) approaches. This distinction is particularly pronounced in scenarios involving a substantial number of sensor nodes. Furthermore, the research undertakes a comprehensive scrutiny of varying system parameters, such as user densities and power allocation factors, to gauge their influence on network accuracy. The discerned outcomes elucidate NOMA’s capacity to augment the operational efficacy of optical wireless sensor connections. The proposed architectural paradigm thus emerges as a promising avenue for optimizing resource allocation and utilization within OWSNs, imparting newfound potential to a spectrum of applications spanning industrial automation, environmental monitoring, and smart city implementations.

In recent years, ozone (O3) has gradually become the primary pollutant plaguing urban air quality. Accurate and efficient ozone prediction is of great significance to the prevention and control of ozone pollution. The air quality monitoring network provides multisource pollutant concentration monitoring data for ozone prediction, but ozone prediction based on multisource monitoring data still faces the challenges of each station’s series of data. Aiming at the problems of low prediction accuracy and low computational efficiency in traditional atmospheric ozone concentration prediction, ozone concentration prediction using dual series decomposition was proposed by variational mode decomposition (VMD), ensemble empirical mode decomposition (EEMD), and long short-term memory (LSTM). First, the historical data series of Nanjing air quality monitoring stations is decomposed by VMD, and then the EEMD algorithm is applied to the residual of VMD to obtain several characteristic intrinsic mode function (IMF) components; each characteristic IMF component is trained by LSTM to obtain the prediction result of each component, and then the final result can be obtained by linear superposition. The proposed method achieved the best results with R2 = 99%, MSE = 5.38, MAE = 4.54, and MAPE = 3.12. Because LSTM has strong adaptive learning ability and good memory function, it has the learning advantage of long-term memory for long-term data, and the prediction results are more accurate. According to the data, the proposed method is superior to the baseline models in terms of statistical metrics. As a result, the proposed hybrid method can serve as a reliable model for ozone forecasting.

The technology of visual servoing, with the digital twin as its driving force, holds great promise and advantages for enhancing the flexibility and efficiency of smart manufacturing assembly and dispensing applications. The effective deployment of visual servoing is contingent upon the robust and accurate estimation of the vision-motion correlation. Network-based methodologies are frequently employed in visual servoing to approximate the mapping between 2D image feature errors and 3D velocities, offering promising avenues for improving the accuracy and reliability of visual servoing systems. These developments have the potential to fully leverage the capabilities of digital twin technology in the realm of smart manufacturing. However, obtaining sufficient training data for these methods is challenging, and thus improving model generalization to reduce data requirements is imperative. To address this issue, we offer a learning-based approach for estimating Jacobian matrices of visual servoing that organically combines an extreme learning machine (ELM) and a differential evolutionary algorithm (DE). In the first stage, the pseudoinverse of the image Jacobian matrix is approximated using the ELM, which solves the problems associated with traditional visual servoing and is resistant to outside influences such as image noise and mistakes in camera calibration. In the second stage, differential evolution is utilized to select input weights and hidden layer bias and to determine ELM’s output weights. Experimental results conducted on a digital twin operating platform for 4-DOF robot with an eye-in-hand configuration demonstrate better performance than classical visual servoing and traditional ELM-based visual servoing in various cases.

Barnacles Mating Optimizer (BMO) is a new metaheuristic algorithm that suffers from slow convergence and poor efficiency due to its limited capability in exploiting the search space and exploring new promising regions. Addressing these shortcomings, this paper introduces Elitist Barnacles Mating Optimizer (eBMO). Unlike BMO, eBMO exploits the elite exponential probability (Pelite) to decide whether to intensify search process via swap operator or to diversify search by randomly exploring new regions. Furthermore, eBMO uses Chebyshev map instead of random numbers to generate quality S-boxes. Experimental results of eBMO on the generation of 8 × 8 substitution-box are competitive against other existing works.