Timely durian leaf disease detection is critical for Vietnam’s agricultural productivity, yet traditional methods remain labor-intensive and error-prone. This study proposes a hybrid pipeline integrating deep transfer learning with binary Particle Swarm Optimization (PSO) for efficient disease classification. Three lightweight backbones, such as MobileNetV3-Large, EfficientNet-B0, and EfficientNetV2-B0 to extract 128-dimensional features from a real-world Vietnamese durian dataset (2595 images, 6 classes), which PSO then prunes using five-fold support vector machine (SVM) cross-validation fitness. The optimized subsets were evaluated across five machine learning (ML) classifiers, achieving up to 92.6
This study examines how environmental knowledge, environmental concerns, attitudes toward energy conservation, and perceived monetary benefits affect two types of energy conservation behaviors, i.e., curtailment behavior and purchase behavior. Using survey data from 405 consumers, partial least squares structural equation modeling shows that knowledge about energy conservation and concern about energy shortages shape attitude toward energy conservation, leading to curtailment behavior and purchasing energy-efficient appliances (EEAs). Furthermore, attitude and curtailment behavior sequentially mediate the effects of knowledge about energy conservation and concern about energy shortages on EEA purchase behavior, with perceived monetary benefits strengthening the attitude-purchase behavior relationship. While necessary condition analysis identifies general environmental concern as necessary for developing a favorable energy conservation attitude, importanceperformance map analysis suggests that improving knowledge about conservation should be prioritized in policy initiatives. These insights provide implications for policymakers and practitioners, including manufacturers and retailers, by identifying multiple pathways and influencing mechanisms for promoting consumers' energy conservation behaviors through curtailment and EEA purchases.
Recently, environment reconstruction (ER) in integrated sensing and communication (ISAC) systems has emerged as a promising approach for achieving high-resolution environmental perception. However, the initial results obtained from ISAC systems are coarse and often unsatisfactory due to the high sparsity of the point clouds and significant noise variance. To address this problem, we propose a noise-sparsity-aware diffusion model (NSADM) post-processing framework. Leveraging the powerful data recovery capabilities of diffusion models, the proposed scheme exploits spatial features and the additive nature of noise to enhance point cloud density and denoise the initial input. Simulation results demonstrate that the proposed method significantly outperforms existing model-based and deep learning-based approaches in terms of Chamfer distance and root mean square error.
Ensuring reliable transmission and secure communication remains a critical challenge for next-generation wireless networks, particularly in the context of sixth-generation (6G) and Internet of Things (IoT) systems. This article investigates the reliability and physical layer security (PLS) of active reconfigurable intelligent surface (ARIS)-assisted dual-hop relaying in nonorthogonal multiple access (NOMA) networks over Nakagami- $m$ fading channels. We develop a comprehensive system model where a base station (BS) communicates with two users via a relay and an ARIS in the presence of a potential eavesdropper. Closed-form expressions for outage probability (OP) and intercept probability (IP) are derived for both near and far users, capturing the effects of ARIS configuration, power allocation, and channel fading. Extensive Monte Carlo simulations confirm the accuracy of the analytical results and reveal that increasing the number of ARIS elements, optimizing amplification factors, and carefully allocating power can significantly enhance both reliability and secrecy performance. The findings provide valuable insights for the design of robust and secure ARIS-assisted NOMA networks in practical wireless environments.
Cell-free massive multiple-input multiple-output (MIMO)-aided integrated sensing and communication (ISAC) systems are investigated where distributed access points jointly serve users and sensing targets. We demonstrate that only a subset of access points (APs) has to be activated for both tasks, while deactivating redundant APs is essential for power savings. This motivates joint active AP selection and power control for optimizing energy efficiency. The resultant problem is a mixed-integer nonlinear program (MINLP). To address this, we propose a model-based Branch-and-Bound approach as a strong baseline to guide a semi-supervised heterogeneous graph neural network (HetGNN) for selecting the best active APs and the power allocation. Comprehensive numerical results demonstrate that the proposed HetGNN reduces power consumption by 20-25 % and runs nearly 10,000 times faster than model-based benchmarks.
