Search Results (243)

The time series prediction of visibility in terms of various meteorological variables, such as relative humidity, temperature, atmospheric pressure, and wind speed, is presented in this paper using Single-Variable Regression Analysis (SVRA), Artificial Neural Network (ANN), and Hybrid Adaptive Neuro-fuzzy Inference System (ANFIS) techniques for several sub-tropical locations. The initial method used for the prediction of visibility in this study was the SVRA, and the results were enhanced using the ANN and ANFIS techniques. Throughout the study, neural networks with various algorithms and functions were trained with different atmospheric parameters to establish a relationship function between inputs and visibility for all locations. The trained neural models were tested and validated by comparing actual and predicted data to enhance visibility prediction accuracy. Results were compared to assess the efficiency of the proposed systems, measuring the root mean square error (RMSE), coefficient of determination (R²), and mean bias error (MBE) to validate the models. The standard statistical technique, particularly SVRA, revealed that the strongest functional relationship was between visibility and RH, followed by WS, T, and P, in that order. However, to improve accuracy, this study utilized back propagation and hybrid learning algorithms for visibility prediction. Error analysis from the ANN technique showed increased prediction accuracy when all the atmospheric variables were considered together. After testing various neural network models, it was found that the ANFIS model provided the most accurate predicted results, with improvements of 31.59%, 32.70%, 30.53%, 28.95%, 31.82%, and 22.34% over the ANN for Durban, Cape Town, Mthatha, Bloemfontein, Johannesburg, and Mahikeng, respectively. The neuro-fuzzy model demonstrated better accuracy and efficiency by yielding the finest results with the lowest RMSE and highest R² for all cities involved compared to the ANN model and standard statistical techniques. However, the statistical performance analysis between measured and estimated visibility indicated that the ANN produced satisfactory results. The results will find applications in Optical Wireless Communication (OWC), flight operations, and climate change analysis. Full article

The one-dimensional (1D) Sb(III)-based organic–inorganic hybrid perovskite (AImd)₂¹_∞[SbI₅] (AImd = 1-allylimidazolium) crystallizes in the orthorhombic, centrosymmetric space group Pnma. The structure consists of corner-sharing [SbI₆] octahedra forming 1D chains separated by allylimidazolium cations. Void analysis through Mercury CSD software confirmed a densely packed lattice with a calculated void volume of 1.1%. Integrated quantum theory of atoms in molecules (QTAIM) and non-covalent interactions index (NCI) analyses showed that C–H···I interactions between the cations and the ¹_∞[SbI₅]²⁻ network predominantly stabilize the supramolecular assembly followed by N–H···I hydrogen bonds. The calculated growth morphology (GM) model fits very well to the experimental morphology. UV–Vis diffuse reflectance spectroscopy allowed us to determine the optical band gap to 3.15 eV. Density functional theory (DFT) calculations employing the B3LYP, CAM-B3LYP, and PBE0 functionals were benchmarked against experimental data. CAM-B3LYP best reproduced Sb–I bond lengths, while PBE0 more accurately captured the HOMO–LUMO gap and the associated electronic descriptors. These results support the assignment of an inorganic-to-organic [Sb–I] → π* charge-transfer excitation, and clarify how structural dimensionality and cation identity shape the material’s optoelectronic properties. Full article

This work presents a hybrid optical fiber detector by combining the sensing mechanism of the fiber Bragg grating (FBG) and the light extinction method to enable the simultaneous measurement of dust concentration and temperature. Compared with the existing dust concentration sensors, the proposed detector offers three key advantages: intrinsic safety, dual-parameter measurement capability, and potentially network-based monitoring. The critical sensing components of the proposed detector consist of two optical collimators and an FBG. Using the extinction effect of light between the two collimators, the dust concentration and temperature are simultaneously determined by monitoring the intensity and the wavelength of the FBG reflectance spectrum, respectively. The measurement feasibility has been evaluated demonstrating that the two parameters of interest can be effectively sensed with minimally coupled outputs of ±3 pm and ±0.1 mW, respectively. Calibration experiments demonstrate that the change in the intensity of light from the FBG is exponentially related to the dust concentration variation with fitting coefficients equal to 0.948, 0.946, and 0.945 for 200 meshes, 300 meshes, and 400 meshes, respectively. The detector’s relative measurement errors were validated against the weighing method, confirming low measurement deviations. Full article

Rain streaks degrade the quality of optical images and seriously affect the effectiveness of subsequent vision-based algorithms. Although the applications of a convolutional neural network (CNN) and self-attention mechanism (SA) in single image deraining have shown great success, there are still unresolved issues regarding the deraining performance and the large computational load. The work in this paper fully coordinates and utilizes the advantages between CNN and SA and proposes a hybrid content-aware deraining network (CAD) to reduce complexity and generate high-quality results. Specifically, we construct the CADBlock, including the content-aware convolution and attention mixer module (CAMM) and the multi-scale double-gated feed-forward module (MDFM). In CAMM, the attention mechanism is used for intricate windows to generate abundant features and simple convolution is used for plain windows to reduce computational costs. In MDFM, multi-scale spatial features are double-gated fused to preserve local detail features and enhance image restoration capabilities. Furthermore, a four-token contextual attention module (FTCA) is introduced to explore the content information among neighbor keys to improve the representation ability. Both qualitative and quantitative validations on synthetic and real-world rain images demonstrate that the proposed CAD can achieve a competitive deraining performance. Full article

In remote sensing, object classification often suffers from severe degradation caused by atmospheric turbulence and low-signal conditions. Traditional image reconstruction approaches are computationally expensive and fragile under such conditions. In this work, we propose a novel image-free classification framework using single-pixel imaging (SPI), which directly classifies targets from 1D measurements without reconstructing the image. A learnable sampling matrix is introduced for structured light modulation, and a hybrid CNN-Transformer network (Hybrid-CTNet) is employed for robust feature extraction. To enhance resilience against turbulence and enable efficient deployment, we design a $(N+1)\times L$ hybrid strategy that integrates convolutional and Transformer blocks in every stage. Extensive simulations and optical experiments validate the effectiveness of our approach under various turbulence intensities and sampling rates as low as 1%. Compared with existing image-based and image-free methods, our model achieves superior performance in classification accuracy, computational efficiency, and robustness, which is important for potential low-resource real-time remote sensing applications. Full article

This paper presents SE2-LET-VINS, an enhanced Visual–Inertial Simultaneous Localization and Mapping (VI-SLAM) system built upon the classic Visual–Inertial Navigation System for Monocular Cameras (VINS-Mono) framework, designed to improve localization accuracy and robustness in complex environments. By integrating Lightweight Neural Network (LET-NET) for high-quality feature extraction and Special Euclidean Group in 2D (SE2) optical flow tracking, the system achieves superior performance in challenging scenarios such as low lighting and rapid motion. The proposed method processes Inertial Measurement Unit (IMU) data and camera data, utilizing pre-integration and RANdom SAmple Consensus (RANSAC) for precise feature matching. Experimental results on the European Robotics Challenges (EuRoc) dataset demonstrate that the proposed hybrid method improves localization accuracy by up to 43.89% compared to the classic VINS-Mono model in sequences with loop closure detection. In no-loop scenarios, the method also achieves error reductions of 29.7%, 21.8%, and 24.1% on the MH_04, MH_05, and V2_03 sequences, respectively. Trajectory visualization and Gaussian fitting analysis further confirm the system’s good robustness and accuracy. SE2-LET-VINS offers a robust solution for visual–inertial navigation, particularly in demanding environments, and paves the way for future real-time applications and extended capabilities. Full article

This study addresses the challenges of characterizing aerosol optical depth (AOD) dynamics from satellite observations, which are often hindered by data gaps and variability. A long short-term memory (LSTM) network was trained on an extended AOD dataset from Sicily to capture temporal patterns. The trained model was then applied to AOD data from distinct geographical regions: Cluj-Napoca and the central Mediterranean Sea. While the LSTM effectively captured general seasonal trends, it tended to smooth extreme AOD events. To mitigate this, a post-processing algorithm was developed to enhance the representation of AOD peaks and valleys. This enhancement method refines the characterization of historical AOD, providing a more accurate representation of observed atmospheric variability, particularly in capturing high and low AOD episodes. The results demonstrate the efficacy of the hybrid approach in improving the characterization of AOD dynamics across different regions. Full article

Structural health monitoring (SHM) plays a vital role in ensuring the safety, durability, and performance of civil infrastructure. This review delves into the significant advancements in optical fiber sensor (OFS) technologies such as Fiber Bragg Gratings, Distributed Temperature Sensing, and Brillouin-based systems, which have emerged as powerful tools for enhancing SHM capabilities. Offering high sensitivity, resistance to electromagnetic interference, and real-time distributed monitoring, these sensors present a superior alternative to conventional methods. This paper also explores the integration of OFSs with Artificial Intelligence (AI), which enables automated damage detection, intelligent data analysis, and predictive maintenance. Through case studies across key infrastructure domains, including bridges, tunnels, high-rise buildings, pipelines, and offshore structures, the review demonstrates the adaptability and scalability of these sensor systems. Moreover, the role of SHM is examined within the broader context of civil and urban infrastructure, where IoT connectivity, AI-driven analytics, and big data platforms converge to create intelligent and responsive infrastructure. While challenges remain, such as installation complexity, calibration issues, and cost, ongoing innovation in hybrid sensor networks, low-power systems, and edge computing points to a promising future. This paper offers a comprehensive amalgamation of current progress and future directions, outlining a strategic path for next-generation SHM in resilient urban environments. Full article

Background: Optical coherence tomography (OCT) is limited by inherent speckle noise, degrading retinal microarchitecture visualization and pathological analysis. Existing denoising methods inadequately balance noise suppression and structural preservation, necessitating advanced solutions for clinical OCT reconstruction. Methods: We propose MFFA-GAN, a generative adversarial network integrating multilevel feature fusion and an efficient local attention (ELA) mechanism. It optimizes cross-feature interactions and channel-wise information flow. Evaluations on three public OCT datasets compared traditional methods and deep learning models using PSNR, SSIM, CNR, and ENL metrics. Results: MFFA-GAN achieved good performance (PSNR:30.107 dB, SSIM:0.727, CNR:3.927, ENL:529.161) on smaller datasets, outperforming benchmarks and further enhanced interpretability through pixel error maps. It preserved retinal layers and textures while suppressing noise. Ablation studies confirmed the synergy of multilevel features and ELA, improving PSNR by 1.8 dB and SSIM by 0.12 versus baselines. Conclusions: MFFA-GAN offers a reliable OCT denoising solution by harmonizing noise reduction and structural fidelity. Its hybrid attention mechanism enhances clinical image quality, aiding retinal analysis and diagnosis. Full article

The growing reliance on natural gas in urban China has heightened the urgency of maintaining pipeline integrity, particularly in environments prone to disruption by nearby construction activities. In this study, we present a practical approach for the real-time classification of distributed fiber optic monitoring signals, leveraging a hybrid framework that combines the feature learning capacity of a one-dimensional convolutional neural network (1D-CNN) with the classification robustness of a support vector machine (SVM). The proposed method effectively distinguishes various pipeline-related events—such as minor leakage, theft attempts, and human movement—by automatically extracting their vibration patterns. Notably, it addresses the common shortcomings of softmax-based classifiers in small-sample scenarios. When tested on a real-world dataset collected via the DAS3000 system from Hangzhou Optosensing Co., Ltd., the model achieved a high classification accuracy of 99.92% across six event types, with an average inference latency of just 0.819 milliseconds per signal. These results demonstrate its strong potential for rapid anomaly detection in pipeline systems. Beyond technical performance, the method offers three practical benefits: it integrates well with current monitoring infrastructures, significantly reduces manual inspection workloads, and provides early warnings for potential pipeline threats. Overall, this work lays the groundwork for a scalable, machine learning-enhanced solution aimed at ensuring the operational safety of critical energy assets. Full article

Hydrogels are three-dimensional network structures composed of hydrophilic polymers that can swell in water and are very similar to soft tissues such as connective tissue or the extracellular matrix. DNA hydrogels are particularly notable for biomedical applications due to their high biocompatibility, physiological stability, molecular recognition, biodegradability, easy functionalization, and low immunogenicity. Based on these advantages, stimuli-responsive DNA hydrogels that have the property of reversibly changing their structure in response to various microenvironments or molecules are attracting attention as smart nanomaterials that can be applied to biosensing and material transfer, such as in the case of cells and drugs. As DNA nanotechnology advances, DNA can be hybridized with a variety of nanomaterials, from inorganic nanomaterials such as gold nanoparticles (AuNPs) and quantum dots (QDs) to synthetic polymers such as polyacrylamide (PAAm) and poly(N-isopropylacrylamide) (pNIPAM). These hybrid structures exhibit various optical and chemical properties. This review discusses recent advances and remaining challenges in biomedical applications of stimuli-responsive smart DNA hydrogel-based systems. It also highlights various types of hybridized DNA hydrogel, explores various response mechanism strategies of stimuli-responsive DNA hydrogel, and provides insights and prospects for biomedical applications such as biosensing and drug delivery. Full article

Recent advances in deep learning have witnessed the wide application of convolutional neural networks (CNNs), Transformer models, and Mamba models in optical remote sensing image (ORSI) analysis, particularly for salient object detection (SOD) tasks in disaster warning, urban planning, and military surveillance. Although existing methods improve detection accuracy by optimizing feature extraction and attention mechanisms, they still face limitations when dealing with the inherent challenges of ORSI. These challenges mainly manifest as complex backgrounds, extreme scale variations, and topological irregularities, which severely affect detection performance. However, the deeper underlying issue lies in how to effectively align and integrate local detail features with global semantic information. To tackle these issues, we propose the Trans-Mamba Hybrid Network with Semantic Feature Alignment (TSFANet), a novel architecture that exploits intrinsic correlations between semantic information and detail features. Our network comprises three key components: (1) a Trans-Mamba Semantic-Detail Dual-Stream Collaborative Module (TSDSM) that combines CNNs-Transformer and CNNs-Mamba in a hybrid dual-branch encoder to capture both global context and multi-scale local features; (2) an Adaptive Semantic Correlation Refinement Module (ASCRM) that leverages semantic-detail feature correlations for guided feature optimization; and 3) a Semantic-Guided Adjacent Feature Fusion Module (SGAFF) that aligns and refines multi-scale semantic features. Extensive experiments on three public RSI-SOD datasets demonstrate that our method consistently outperforms 30 state-of-the-art approaches, effectively accomplishing the task of salient object detection in remote sensing imagery. Full article

Underwater optical images are crucial in marine exploration. However, capturing these images directly often results in color distortion, noise, blurring, and other undesirable effects, all of which originate from the unique physical and chemical properties of underwater environments. Hence, various factors need to be comprehensively considered when processing underwater optical images that are severely degraded under complex lighting conditions. Most existing methods resolve one issue at a time, making it challenging for these isolated techniques to maintain consistency when addressing multiple degradation factors simultaneously, often leading to unsatisfactory visual outcomes. Motivated by the global modeling capability of the Transformer, this paper introduces TFCNet, a complex hybrid-architecture network designed for underwater optical image enhancement and restoration. TFCNet combines the benefits of the Transformer in capturing long-range dependencies with the local feature extraction potential of convolutional neural networks, resulting in enhanced restoration results. Compared with baseline methods, the proposed approach demonstrated consistent improvements, where it achieved minimum gains of 0.3 dB in the PSNR and 0.01 in the SSIM and a 0.8 reduction in the RMSE. TFCNet exhibited a commendable performance in complex underwater optical image enhancement and restoration tasks by effectively rectifying color distortion, eliminating marine snow noise to a certain degree, and restoring blur. Full article

As sensor technology integrates into modern life, diverse sensing devices have become essential for collecting critical data that enables human–machine interfaces such as autonomous vehicles and healthcare monitoring systems. However, the growing number of sensor devices places significant demands on network capacity, which is constrained by the limitations of radio frequency (RF) technology. RF-based communication faces challenges such as bandwidth congestion and interference in densely populated areas. To overcome these challenges, a combination of RF with free-space optical (FSO) communication is presented. FSO is a laser-based wireless solution that offers high data rates and secure communication, similar to fiber optics but without the need for physical cables. However, FSO is highly susceptible to atmospheric turbulence and conditions such as fog and smoke, which can degrade performance. By combining the strengths of both RF and FSO, a hybrid FSO/RF system can enhance network reliability, ensuring seamless communication in dynamic urban environments. This review examines hybrid FSO/RF systems, covering both theoretical models and real-world applications. Three categories of hybrid systems, namely hard switching, soft switching, and relay-based mechanisms, are proposed, with graphical models provided to improve understanding. In addition, multi-platform applications, including autonomous, unmanned aerial vehicles (UAVs), high-altitude platforms (HAPs), and satellites, are presented. Finally, the paper identifies key challenges and outlines future research directions for hybrid communication networks. Full article

In future hybrid fiber and radio access networks, wavelength division multiplexing passive optical networks (WDM-PON) based fifth-generation (5G) fronthaul systems are anticipated to coexist with current protocols, potentially leading to non-linearity impairment due to stimulated Raman scattering (SRS). To meet the loss budget requirements of 5G fronthaul networks, this paper investigates the power changes induced by SRS in WDM-PON based 5G fronthaul systems. The study examines wavelength allocation schemes utilizing both the C-band and O-band, with modulation formats including non-return-to-zero (NRZ), optical double-binary (ODB), and four-level pulse amplitude modulation (PAM4). Simulation results indicate that SRS non-linearity impairment causes a power depletion of 1.3 dB in the 20 km C-band link scenario, regardless of whether the modulation formats are 25 Gb/s or 50 Gb/s NRZ, ODB, and PAM4, indicating that the SRS-induced power changes are largely independent of both modulation formats and modulation rates. This effect occurs when only the upstream and downstream wavelengths of the 5G fronthaul are broadcast. However, when the 5G fronthaul wavelengths coexist with previous protocols, the maximum power depletion increases significantly to 10.1 dB. In the O-band scenario, the SRS-induced maximum power depletion reaches 1.5 dB with NRZ, ODB, and PAM4 modulation formats at both 25 Gb/s and 50 Gb/s. Based on these analyses, the SRS non-linearity impairment shall be fully considered when planning the wavelengths for 5G fronthaul transmission. Full article