This work presents a metamaterial absorber (MMA) for X- and Ku-bands with a metallic resonating patch on top and a ground plane separated by substrate FR-4 with a thickness of 0.053 λ at the lowest resonance frequency. The proposed MMA demonstrates perfect absorption of 99.42, 98.48, 98.92, and 99.34 % at 9.948, 13.26, 14.92, and 15.80 GHz, respectively at normal incidence. The proposed MMA demonstrates perfect absorption for a polarization and incident angle over a wide range of angles up to 45°. To understand the fundamental EM behavior of the metamaterial structure, equivalent circuit analysis was carried out, and the circuit outputs accorded with the simulation results. This article also compares various machine learning (ML) methods for optimizing the design and predictive modeling of MMAs, such as decision trees, K-nearest neighbors, random forests, extra trees (ET), bagging, LightGBM, XGBoost, hist gradient boosting, cat boost, and gradient boosting regressors. The primary objective is to assess the usefulness of each regressor technique in estimating the performance of MMAs using multiple tests ranging from TC-40 to TC-80 and performance metrics such as adjusted R-squared score, MSE, RMSE, and MAE, in which the ET regressor excels. Simulation results suggest that ML-based techniques can save simulation resources and time while still being an efficient tool for predicting absorber behavior at intermediate and subsequent frequencies.

Graphene and zinc oxide (ZnO) nanowires (NWs)-based photodetectors demonstrate excellent photodetection performance in the ultraviolet (UV) spectrum regime. This paper presents the design and analysis of a heterostructure model of p⁺-few-layer graphene (p⁺-FLG)/n^–-ZnO NWs-based UV photodetector. The design utilizes the unique properties of few-layer graphene to enhance light absorption and improve photodetector performance. The analysis under both self-biasing and conductive modes of operation reveals that the integrated electric field and the photovoltaic effect at the p⁺-FLG/n⁻-ZnO NWs hetero-interface create a rectifying behavior. The photodetector achieves an external photocurrent responsivity, external quantum efficiency, detectivity, and noise equivalent power of 0.12 A/W, 44.1%, 1.9 × 10⁹ Jones, and 5.6 × 10^–14 W, respectively, under UV illumination at 350 nm, 0 V bias, and 300 K. Additionally, the photodetector exhibits ultrafast photoswitching rise and fall times of 0.26 ns and a 3-dB cut-off frequency of 1.31 GHz. The comparative analysis with existing photodetectors demonstrates that the proposed model surpasses many in sensitivity, speed, and efficiency. The enhancement of charge collection with the applied reverse-biased voltage results in a response time of 0.16 ns, a peak photocurrent responsivity of 0.2 A/W, a maximum external quantum efficiency of 61%, a peak detectivity of 2.4 × 10⁹ Jones, and minimum noise equivalent power of 4.4 × 10^–14 W at − 0.5 V. The findings inspire the development of next-generation self-driving, highly efficient, broadband photodetectors, and other economically viable and multifunctional optoelectronic devices.

Semantic segmentation of high-resolution images from remote sensing is crucial across various sectors. However, due to limitations in computational resources and the complexity of network architectures, many sophisticated semantic segmentation models struggle with efficiency in real-world applications, leading to an interest in developing lightweight model like borders. These models often employ a dual-branch structure, which balances processing speed and performance effectively. Yet, this design typically falls short in leveraging shallow structural information to enrich the dual branches with comprehensive multiscale data. Additionally, the lightweight components struggle to capture the global contextual details of feature sets efficiently. When compared to state-of-the-art models, lightweight semantic segmentation models usually exhibit performance gaps. To address these issues, we introduce a novel approach that incorporates a deep-shallow interaction mechanism with an attention module to improve water body segmentation efficiency. This method spatially adjusts feature representations to better identify water-related data, utilizing a U-Net frame work to enhance the accuracy of edge detection in water zones by providing more precise local positioning information. The attention mechanism processes and merges low and high-level data separately in different dimensions, allowing for the effective distinction of water areas from their surroundings by blending spatial attributes with in-depth context insights. Experimental outcomes demonstrate a remarkable 95% accuracy, showcasing the proposed method’s superiority over existing models.

The automatic segmentation of water bodies from remote-sensing satellite images offers valuable insights into water resource management, flood monitoring, environmental changes, and urban development. However, extracting water bodies from satellite imagery can be challenging due to factors such as varying water body shapes, diverse environmental conditions, cloud cover, and shadows. These difficulties have a significant impact on waterbody segmentation, particularly in precisely maintaining high-quality segmented images and determining the boundaries of waterbodies. To overcome these issues, researchers have introduced several approaches; however, they suffer from precisely identifying the boundaries of waterbodies due to their irregular shapes. This difficulty is particularly pronounced in traditional threshold-based and machine-learning techniques, which often struggle to achieve accurate segmentation when confronted with complex structures, cluttered backgrounds, or objects of varying sizes and shapes. The objective of this research is to develop innovative deep-learning (DL) approaches to address these challenges and enhance the accuracy of waterbody segmentation in Remote sensing applications. This research introduces a deep learning model, namely AER U-Net architecture, which integrates advanced architectural elements into U-Net, such as residual blocks, self-attention mechanisms, and dropout layer, due to which the model significantly enhances segmentation accuracy and generalization capability. The architecture employs a contracting path consisting of convolutional layers, batch normalization, and activation layers to extract multi-scale features. Residual blocks improve feature learning efficiency while addressing the vanishing gradient issue through the inclusion of skip connections. Dropout layers in the encoder and bottleneck paths are incorporated for regularization, reducing the risk of overfitting. Additionally, the attention mechanism ensures precise refinement of skip connections, further improving segmentation performance. The model is trained using the Adam optimizer combined with a binary cross-entropy loss function, making it highly effective for binary segmentation tasks with an IoU score of 0.94, highlighting its effectiveness for practical environmental applications.

It is important in the rising demands to have efficient anomaly detection in camera surveillance systems for improving public safety in a complex environment. Most of the available methods usually fail to capture the long-term temporal dependencies and spatial correlations, especially in dynamic multi-camera settings. Also, many traditional methods rely heavily on large labeled datasets, generalizing poorly when encountering unseen anomalies in the process. We introduce a new framework to address such challenges by incorporating state-of-the-art deep learning models that improve temporal and spatial context modeling. We combine RNNs with GATs to model long-term dependencies across cameras effectively distributed over space. The Transformer-Augmented RNN allows for a better way than standard RNNs through self-attention mechanisms to improve robust temporal modeling. We employ a Multimodal Variational Autoencoder-MVAE that fuses video, audio, and motion sensor information in a manner resistant to noise and missing samples. To address the challenge of having a few labeled anomalies, we apply the Prototypical Networks to perform few-shot learning and enable generalization based on a few examples. Then, a Spatiotemporal Autoencoder is adopted to realize unsupervised anomaly detection by learning normal behavior patterns and deviations from them as anomalies. The methods proposed here yield significant improvements of about 10% to 15% in precision, recall, and F1-scores over traditional models. Further, the generalization capability of the framework to unseen anomalies, up to a gain of + 20% on novel event detection, represents a major advancement for real-world surveillance systems.