Search Results (51)

Tea cultivation faces significant threats from red spider mite (RSM: Oligonychus coffeae) infestations, which reduce yields and economic viability in major tea-producing regions. Current automated detection methods rely on supervised deep learning models requiring extensive labeled data, limiting scalability for smallholder farmers. This article proposes AIM-Net (AI-based Infestation Mapping Network) by evaluating SwAV (Swapping Assignments between Views), a self-supervised learning framework, for classifying RSM infestation severity (Mild, Moderate, Severe) using a geo-referenced, field-acquired dataset of RSM infested tea-leaves, Cam-RSM. The methodology combines SwAV pre-training on unlabeled data with fine-tuning on labeled subsets, employing multi-crop augmentation and online clustering to learn discriminative features without full supervision. Comparative analysis against a fully supervised ResNet-50 baseline utilized 5-fold cross-validation, assessing accuracy, F1-scores, and computational efficiency. Results demonstrate SwAV’s superiority, achieving 98.7% overall accuracy (vs. 92.1% for ResNet-50) and macro-average F1-scores of 98.3% across classes, with a 62% reduction in labeled data requirements. The model showed particular strength in Mild_RSM-class detection (F1-score: 98.5%) and computational efficiency, enabling deployment on edge devices. Statistical validation confirmed significant improvements (p < 0.001) over baseline approaches. These findings establish self-supervised learning as a transformative tool for precision pest management, offering resource-efficient solutions for early infestation detection while maintaining high accuracy. Full article

Battery-swapping stations (BSSs) are pivotal for supplying energy to electric heavy-duty trucks. However, their operations face challenges in accurate demand forecasting for battery-swapping and fair revenue allocation. This study proposes an optimization strategy for the economic operation of BSSs that optimizes revenue allocation and load balancing to enhance financial viability and grid stability. First, factors including geographical environment, traffic conditions, and truck characteristics are incorporated to simulate swapping behaviors, supporting the construction of an accurate demand-forecasting model. Second, an optimization problem is formulated to maximize the weighted difference between BSS revenue and squared load deviations. An economic operations strategy is proposed based on an adaptive Shapley value. It enables precise evaluation of differentiated member contributions through dynamic adjustment of bias weights in revenue allocation for a strategy that aligns with the interests of multiple stakeholders and market dynamics. Simulation results validate the superior performance of the proposed algorithm in revenue maximization, peak shaving, and valley filling. Full article

Entanglement swapping is a crucial step in quantum communication, generating long-distance entanglements between quantum users for quantum network applications, such as distributed quantum computing. This study focuses on the efficiency of entanglement swapping strategies in quantum networks, particularly in multi-user concurrent quantum communication. Since multi-user concurrent quantum communication consists of multiple point-to-point quantum communications, we first analyze the challenges faced by existing entanglement swapping strategies in this scenario and then propose Parallel Segment Entanglement Swapping (PSES) to address them. PSES utilizes a tree-like model to divide the path into segments and execute entanglement swapping in parallel across them, thereby enhancing the generation rate of long-distance entanglement. Furthermore, we analyze the impact of resource contention on entanglement swapping in multi-user concurrent quantum communication and propose Multi-user PSES (M-PSES) to alleviate this negative impact. M-PSES leverages the entanglement swapping trigger signal and resource locking mechanisms to mitigate resource contention. The simulation results show that PSES performs superiorly to existing entanglement swapping strategies in point-to-point quantum communication, and M-PSES can achieve better performance than PSES in multi-user concurrent quantum communication. Full article

The visual nature of Sign Language datasets raises privacy concerns that hinder data sharing, which is essential for advancing deep learning (DL) models in Sign Language recognition and translation. This study evaluated two anonymization techniques, realistic avatar synthesis and face swapping (FS), designed to anonymize the identities of signers, while preserving the semantic integrity of signed content. A novel metric, Identity Anonymization with Expressivity Preservation (IAEP), is introduced to assess the balance between effective anonymization and the preservation of facial expressivity crucial for Sign Language communication. In addition, the quality evaluation included the LPIPS and FID metrics, which measure perceptual similarity and visual quality. A survey with deaf participants further complemented the analysis, providing valuable insight into the practical usability and comprehension of anonymized videos. The results show that while face swapping achieved acceptable anonymization and preserved semantic clarity, avatar-based anonymization struggled with comprehension. These findings highlight the need for further research efforts on securing privacy while preserving Sign Language understandability, both for dataset accessibility and the anonymous participation of deaf people in digital content. Full article

A swarm of unmanned aerial vehicles (UAVs) often rely on exceptional wireless coverage of embedded or flush-mounted antennas or arrays, especially in long-range communication. While arrays offer significant range and beam steerability control, they often suffer from size, weight, and power (SWaP) limitations. On the other hand, achieving a wideband, high-gain, and beam-steerable response from a single antenna is highly desired for its compact SWaP characteristics. In this study, a cube-shaped cavity antenna excited by a monopole feed is designed, fabricated, and measured. The proposed antenna operates from 4.1 to 5.56 GHz with a 30.22% fractional bandwidth and a peak gain of 8 dBi. In addition, a frequency-selective surface (FSS) is developed to replace the metallic faces of the cavity, enabling 360° electronic beam steerability. Thermal analysis of the FSS-based cavity design is conducted to determine its maximum power handling capability, revealing a maximum power handling capability of 1.3 KW continuous. In addition, the maximum rating currents of the FSS diodes can be reached only at 165 W, limiting the maximum power handling to only 165 W in the case of using the diodes used in this analysis. The antenna prototype is successfully fabricated, and the radiation pattern is experimentally measured, showing a strong agreement between the simulated and measured results. The electronic steerability of the proposed antenna indicates its suitability for 5G new radio and UAV applications. Full article

To effectively address the challenges of imbalanced equipment utilization, frequent congestion, and poor economic benefits faced by charging and swapping stations (ICSSs), this paper innovatively proposes a comprehensive scheduling strategy that combines user behavior regulation and battery management. In terms of user regulation, an intention-reshaping model for changing user cognition is proposed to equalize the use of charging and swapping (CAS) equipment, easing ICSS congestion. Moreover, an off-station scheduling model for electric vehicles (EVs) is developed to enhance overall ICSS revenue. Within the battery management terms, the suggested inventory battery threshold adjustment method and charging strategy by charging time segmentation are employed to ensure consistent inventory battery supply and cost-effective battery charging. Finally, a two-stage scheduling strategy of in-station and off-station scheduling is suggested for the ICSS, and an improved northern goshawk optimization algorithm (INGO) is used to solve it. The results showed that this strategy reduced the overall congestion of ICSSs by 34% and increased the average annual net revenue by 64%. The goal of alleviating congestion and improving the economic efficiency of ICSSs has been achieved. Full article

In the era of noisy intermediate-scale quantum (NISQ) computing, the limited connectivity between qubits is one of the common physical limitations faced by current quantum computing devices. Quantum circuit mapping methods transform quantum circuits into equivalent circuits that satisfy physical connectivity constraints by remapping logical qubits, making them executable. The optimization problem of quantum circuit mapping has NP-hard computational complexity, and existing heuristic mapping algorithms still have significant potential for optimization in terms of the number of quantum gates generated. To reduce the number of SWAP gates inserted during mapping, the solution space of the mapping problem is represented as a tree structure, and the mapping process is equivalent to traversing this tree structure. To effectively and efficiently complete the search process, a beam search framework (BSF) is proposed for solving quantum circuit mapping. By iteratively selecting, expanding, and making decisions, high-quality target circuits are generated. Experimental results show that this method can significantly reduce the number of inserted SWAP gates on medium to large circuits, achieving an average reduction of 44% compared to baseline methods, and is applicable to circuits of various sizes and complexities. Full article

As life expectancy increases, pension plans face growing longevity risk. Standardized longevity-linked securities such as survivor contracts allow pension plans to transfer this risk to capital markets. However, more consensus is needed on the appropriate mortality model and premium principle to price these contracts. This paper investigates the impact of the mortality model and premium principle choice on the pricing, risk measurement, and modeling of survivor contracts. We present a framework for evaluating risk measures associated with survivor contracts, specifically survivor forwards (S-forward) and survivor swaps (S-swaps). We analyze how the mortality model and premium principle assumptions affect pricing and risk measures (value-at-risk and expected shortfall). Four mortality models (Lee–Carter, Renshaw–Haberman, Cairns–Blake–Dowd, and M6) and eight premium principles (Wang, proportional hazard, dual power, Gini, exponential, standard deviation, variance, and median absolute deviation) are considered. Our analysis highlights the need to refine mortality models and premium principles to enhance pricing accuracy and risk management. We also suggest regulators and practitioners incorporate expected shortfall alongside value-at-risk to capture tail risks and improve capital allocation. Full article

Conventional motorcycles with internal combustion engines have significantly contributed to air pollution in Southeast Asia, posing challenges to achieving the ambitious net-zero emissions targets ratified by ASEAN member countries. In response, ASEAN countries have begun to adopt electric vehicles to achieve this ambitious target, especially electric motorcycles (EMs). However, the implementation of EMs faced several obstacles, notably limited battery range and insufficient charging infrastructure. Addressing these issues requires a huge investment from EM users and infrastructure providers. The government also plays a significant role in improving the investment climate for the EM ecosystem by providing financial incentives. This research aimed to model cost variables to evaluate the cost-effectiveness of government subsidies for EMs and their charging infrastructure in Malaysia using an equivalent annual cost (EAC) model and determine whether increasing battery capacity or increasing charging infrastructure would be more favorable. Data were collected through interviews with EM dealers, government agency, electric vehicle experts, and surveys of EM users in Malaysia, supplemented with secondary data through research articles, government regulations, and current news related to EM policies implemented in Malaysia. Surveys and interviews with relevant stakeholders were conducted to identify cost variables that influenced EM ownership and operation of EM infrastructure. This study found that Scenario 1 (subsidize EM purchases and charging infrastructure while excluding the battery purchase subsidy) was an optimal subsidy strategy for the government. Scenario 1 also reduced the EAC value, which is a cost burden for EM users, by 10.06% (for battery swap system users) and 5.84% (for direct charging system users). Additionally, this study also found that encouraging the use of EMs with battery swap systems was more profitable than EMs with direct charging systems. The findings of this research provide some insights about the most cost-efficient subsidy scenario for overcoming the obstacles, fostering a win–win situation for both EM users and the government. Thus, accelerating EM adoption forms part of the government’s goal to achieve net-zero emissions. Full article

Wireless sensor networks deployed in energy-constrained environments face critical challenges relating to sustainability and protection. This paper introduces an innovative blockchain-powered safe energy-swapping protocol that enables sensor nodes to voluntarily and securely trade excess energy, optimizing usage and prolonging lifespan. Unlike traditional centralized management schemes, the proposed approach leverages blockchain technology to generate an open, immutable ledger for transactions, guaranteeing integrity, visibility, and resistance to manipulation. Employing smart contracts and a lightweight Proof-of-Stake consensus mechanism, computational and power costs are minimized, making it suitable for WSNs with limited assets. The system is built using NS-3 to simulate node behavior, energy usage, and network dynamics, while Python manages the blockchain architecture, cryptographic security, and trading algorithms. Sensor nodes checked their power levels and broadcast requests when energy fell under a predefined threshold. Neighboring nodes with surplus power responded with offers, and intelligent contracts facilitated secure exchanges recorded on the blockchain. The Proof-of-Stake-based consensus process ensured efficient and secure validation of transactions without the energy-intensive need for Proof-of-Work schemes. The simulation results indicated that the proposed approach reduces wastage and significantly boosts network resilience by allowing nodes to remain operational longer. A 20% increase in lifespan is observed compared to traditional methods while maintaining low communication overhead and ensuring secure, tamper-proof trading of energy. This solution provides a scalable, safe, and energy-efficient answer for next-generation WSNs, especially in applications like smart cities, precision agriculture, and environmental monitoring, where autonomy of energy is paramount. Full article

In an autonomous robotic space debris removal mission, an essential sensor used for navigation is an FMCW radar designed for close-range relative navigation. To achieve the required range performance, minimizing RF leakage between the transmitter (Tx) and receiver (Rx) antennas is essential for the accurate detection of the range and velocity of the targeted space debris. Antennas positioned above the metallic satellite front face are highly susceptible to RF leakage, primarily caused by surface current propagation and lateral waves traveling parallel to the platform. This study presents two lightweight, single-layer planar metamaterials—a novel compact electromagnetic bandgap (EBG) and a non-uniform high-impedance surface (HIS)—optimized to suppress both surface waves and interact with space waves within the 9.3–9.8 GHz frequency range. These designs address strict size, weight, and power (SWaP) constraints while ensuring compatibility with extreme space conditions and resistance to mechanical shocks. Experimental validation indicates that a minimum Tx/Rx isolation improvement of 10 dB is achieved using the HIS, and 20 dB is achieved using the EBG across the radar’s operational bandwidth (5%). Full article

The rapid advancement of Artificial Intelligence Generated Content (AIGC) has significantly accelerated the evolution of Deepfake technology, thereby introducing escalating social risks due to its potential misuse. In response to these adverse effects, researchers have developed defensive measures, including passive detection and proactive forensics. Although passive detection has achieved some success in identifying Deepfakes, it encounters challenges such as poor generalization and decreased accuracy, particularly when confronted with anti-forensic techniques and adversarial noise. As a result, proactive forensics, which offers a more resilient defense mechanism, has garnered considerable scholarly interest. However, existing proactive forensic methodologies often fall short in terms of visual quality, detection accuracy, and robustness. To address these deficiencies, we propose a novel proactive forensic approach that utilizes pseudo-Zernike moment robust watermarking. This method is specifically designed to enhance the detection and analysis of face swapping by transforming facial data into a binary bit stream and embedding this information within the non-facial regions of video frames. Our approach facilitates the detection of Deepfakes while preserving the visual integrity of the video content. Comprehensive experimental evaluations have demonstrated the robustness of this method against standard signal processing operations and its superior performance in detecting Deepfake manipulations. Full article

Current face-swapping methods often suffer from issues of detail blurriness and artifacts in generating high-quality images due to the inherent complexity in detail processing and feature mapping. To overcome these challenges, this paper introduces the Amazing Face Transformer (AmazingFT), an advanced face-swapping model built upon Generative Adversarial Networks (GANs) and Transformers. The model is composed of three key modules: the Face Parsing Module, which segments facial regions and generates semantic masks; the Amazing Face Feature Transformation Module (ATM), which leverages Transformers to extract and transform features from both source and target faces; and the Amazing Face Generation Module (AGM), which utilizes GANs to produce high-quality swapped face images. Experimental results demonstrate that AmazingFT outperforms existing state-of-the-art (SOTA) methods, significantly enhancing detail fidelity and occlusion handling, ultimately achieving movie-grade face-swapping results. Full article

Face swapping or face replacement is a challenging task that involves transferring a source face to a target face while maintaining the target’s facial motion and expression. Although many studies have made a lot of encouraging progress, we have noticed that most of the current solutions have the problem of blurred images, abnormal features, and unnatural pictures after face swapping. To solve these problems, in this paper, we proposed a composite face-swapping generation network, which includes a face extraction module and a feature fusion generation module. This model retains the original facial expression features, as well as the background and lighting of the image while performing face swapping, making the image more realistic and natural. Compared with other excellent models, our model is more robust in terms of face identity, posture verification, and image quality. Full article

Current video face-swapping technologies face challenges such as poor facial fitting and the inability to handle obstructions. This paper introduces Amazing FaceSwap (AmazingFS), a novel framework for producing cinematic quality and realistic face swaps. Key innovations include the development of a Source-Target Attention Mechanism (STAM) to improve face-swap quality while preserving target face expressions and poses. We also enhanced the AdaIN style transfer module to better retain the identity features of the source face. To address obstructions like hair and glasses during face-swap synthesis, we created the AmazingSeg network and a small dataset AST. Extensive qualitative and quantitative experiments demonstrate that AmazingFS significantly outperforms other SOTA networks, achieving amazing face swap results. Full article