Search Results (6,047)

Accurate and rapid detection of citrus leaf diseases is important for early diagnosis, precision orchard management, and the reduction of economic losses in citrus production. Automatic detection remains difficult because early lesions are often small and irregular. Several disease categories also share similar visual appearances, and localization is easily affected by veins, shadows, and cluttered backgrounds. To address these task-specific challenges, we propose HGSM-YOLO, where HGSM denotes the coordinated use of heterogeneous convolution, a GSConv-based slim neck, and multi-scale dilated local attention. The framework is built on YOLO11n because its 2.59 M-parameter and 6.4 GFLOP design provides a stringent compact baseline for edge-oriented improvement. The method follows a hierarchical design: C3k2-HetConv preserves lesion edges and local morphology in the backbone; the GSConv-based slim neck reduces part of the feature fusion cost; and an MSDA module in the high-resolution P3 branch enhances the context of small lesions. Following model selection on the validation split, the final locked models were evaluated once on the held-out test split, with HGSM-YOLO reaching 77.5% precision, 66.8% recall, 71.7% F1-score, 70.8% mAP@0.5, and 44.2% mAP@0.5:0.95, compared with 68.5%, 61.5%, 64.8%, 66.0%, and 40.2% for YOLO11n. A stratified outer five-fold cross-validation further yields 71.0% ± 1.4% mAP@0.5 and 44.4% ± 1.1% mAP@0.5:0.95 for HGSM-YOLO, versus 65.9% ± 1.1% and 40.2% ± 0.9% for YOLO11n. On the independent 1871-image citrus-leaf-disease-2 dataset, retraining under the same protocol gives 94.4% mAP@0.5 for HGSM-YOLO versus 92.2% for YOLO11n and 93.1% for the public Roboflow YOLOv11 reference model. The complete HGSM-YOLO architecture uses 7.2 GFLOPs, 2.82 M parameters, and runs at 90.9 FPS on the RTX 4090, compared with 6.4 GFLOPs, 2.59 M parameters, and 110.1 FPS for the baseline. Thus, the contribution provides a recall- and localization-oriented accuracy–efficiency trade-off rather than universal superiority in every individual metric. Full article

The rapid growth of distributed renewable generation and electric vehicles has increased the demand for flexible peak-shaving resources. Battery swapping stations (BSSs), which centrally manage standardized batteries under the battery-as-a-service model, can provide station-to-grid (S2G) services when aggregated by virtual power plants (VPPs). However, S2G adoption is influenced by contract design, market returns, subsidies, battery degradation, and heterogeneous consumer attitudes. This study develops a complex-network evolutionary diffusion model for VPP–BSS cooperation. The framework integrates a VPP profit-accounting module, a segmented Hotelling demand model, and an evolutionary game on a Newman–Watts small-world network. BSS strategies are updated through a partial asynchronous Fermi rule to reflect bounded rationality and investment inertia. Numerical simulations examine contract parameters, subsidy policies, consumer structures, exogenous variables, and network characteristics. The results show that S2G adoption follows an S-shaped trajectory but does not automatically reach full penetration. Successful diffusion requires a feasible combination of electricity prices, revenue sharing, settlement mechanisms, subsidies, consumer acceptance, and available battery capacity. The findings also reveal a trade-off between promoting BSS participation and maintaining VPP profitability, while robustness tests confirm the stability of the main conclusions. Full article

Labour markets across Europe increasingly describe workers through skills rather than job titles, and a growing number of large language model (LLM)-based tools now claim to extract these skills automatically from unstructured text at scale. Among these, ESCOX has gained particular traction for its open-source, taxonomy-aligned design, yet like any LLM-based system it remains susceptible to hallucination, prompt sensitivity, and non-deterministic output, risks that are rarely quantified before such tools are deployed in practice. The European Skills, Competences, Qualifications, and Occupations (ESCO) classification provides the standardised reference against which this risk can be measured, but no study has yet benchmarked an ESCO-aligned LLM extractor against an independent, expert-labelled dataset at scale. This study addresses that gap. Candidate skills generated by ESCOX are compared against reference skills already assigned to job vacancies on the EURES portal by national labour-market experts, using job-by-skill matrices to quantify agreement and skill co-occurrence networks to characterise how the two sets diverge structurally. Results reveal the extent to which ESCOX’s automatic output aligns with expert judgement and where systematic divergences occur. These findings offer HR practitioners, policymakers, and labour-market researchers an evidence-based basis for deciding when ESCOX’s output can be trusted directly and when expert oversight remains necessary. Full article

Central heating systems often rely on uniform regulation, making it difficult to meet the differentiated comfort demands of users and frequently leading to overheating. This paper proposes an end-to-end, data-driven framework that systematically couples density-adaptive clustering with dynamic response modeling for precision heating control. First, an adaptive DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm is developed, which automatically determines its parameters via k-distance graph initialization, differential evolution optimization, and hierarchical clustering post-processing. Without requiring a pre-set cluster number, it consistently identifies four typical daily room temperature fluctuation patterns. Validated on 120-day data from a residential community in Luoyang, the first four clusters cover over 80% of users, and the clustering quality approaches that of manually optimized conventional methods. Second, multi-input ARX (Autoregressive with Exogenous Inputs) models are built for the representative user of each cluster to characterize dynamic responses to supply water temperature, flow rate, and outdoor temperature. Rolling prediction for the entire community achieves an RMSE of 0.24 °C and an R² of 0.93. Finally, a differentiated regulation strategy combining main-cluster supply temperature control and small-cluster flow compensation is designed. Simulation results demonstrate that this strategy drives the room temperatures of all clusters significantly toward the 20 °C comfort target, with a marked reduction in standard deviation. The primary contribution of this study lies in the construction of a reproducible, closed-loop pipeline—from raw room temperature data to demand-based regulation logic—offering a quantitative basis for central heating systems transitioning from passive balancing to data-driven, classified control. Full article

Journaling can support mental health and self-reflection, but traditional journaling requires users to act simultaneously as reflector, facilitator, and recorder, which may increase cognitive load and potentially hinder sustained practice or contribute to rumination. This study proposes the Reflective Conversational Journal (RCJ), an AI-based system in which AI supports facilitation and recording while users focus on reflection. Grounded in cognitive load theory, Rogers’ person-centered counseling principles, and Socratic questioning, RCJ was designed around three principles: contextual connectivity, structured recording, and empathy and questioning. A prototype integrating an AI agent, a template engine, and a client application was developed as a context-aware human–AI interaction system. Four experts in journaling and psychological counseling evaluated RCJ over one week and completed a post-use evaluation comprising Likert-scale items and open-ended questions. The mean score across the nine design-validity and implementation-fidelity items was 4.67/5 (SD = 0.48). Experts perceived contextual linking as useful for recognizing behavioral patterns and automatic structuring as helpful for reducing recording burden. However, limited depth in questions and interaction fatigue from frequent questioning were identified as areas for improvement. The findings provide preliminary evidence of design validity and implementation fidelity rather than objective evidence of cognitive-load reduction or clinical effectiveness. RCJ operationalizes a complementary human–AI role structure in which AI supports facilitation and recording while the user retains the reflector role. Full article

As the scaling of silicon-based devices approaches physical limits, two-dimensional transition-metal dichalcogenide field-effect transistors (2D TMD FETs) have emerged as promising candidates for logic devices in the post-Moore era. However, their design optimization relies heavily on computationally intensive TCAD simulations, thereby limiting efficient exploration of multidimensional parameter spaces. This paper proposes an efficient automated design framework for 2D TMD FETs under small-sample conditions and validates it using a monolayer MoS₂ FET as a case study. The framework integrates device design, physics-based simulation, performance prediction, and inverse design, establishing a bidirectional mapping between device parameters and electrical performance. Target-driven closed-loop optimization is achieved through TCAD-based feedback validation. Results demonstrate that, using a dataset comprising 300 TCAD samples, the forward model achieves an average coefficient of determination (${\mathrm{R}}^2$) of 0.9503. TCAD revalidation of the inverse-designed devices yields an average mean absolute error (MAE) of 0.0464 and an average mean absolute percentage error (MAPE) of 5.46% for performance metrics. Regarding computational efficiency, while a single TCAD simulation takes approximately 25 to 50 min, the trained model performs inference in under 50 ms, achieving a speedup of at least $3\times {10}^4$ during the inference phase. Accounting for the generation of the 300 TCAD samples and the training of both forward and inverse models, the framework’s one-time computational cost ranges from 160.27 to 285.27 h. Once the cumulative number of design tasks exceeds approximately 342 to 385, the total computational cost falls below that of direct TCAD simulation, with the computational advantage becoming increasingly significant as the number of tasks grows. Consequently, this method is highly suitable for large-scale parameter sweeps, device screening, and multi-objective, high-frequency design iterations. It drastically reduces repetitive TCAD calls, offering a scalable solution for the efficient, automated design of 2D TMD FETs. Full article

Currently, insulation faults in the DC system of photovoltaic (PV) power stations are handled by a full shutdown strategy of inverters, and fault branch localization relies on manual inspection, resulting in low efficiency and poor accuracy, leading to prolonged unplanned outages and substantial power generation losses. This paper proposes an integrated solution combining high-precision insulation monitoring and intelligent fault line selection, which ensures the reliability of line selection criteria through improved measurement accuracy and achieves automatic fault isolation via optimized line selection strategies. The paper analyzes the mathematical essence of the ill-conditioned measurement equations of the traditional bridge method under severe single-pole grounding faults, establishes a dual-channel heteroscedastic noise model, and utilizes the inherent physical constraint that the sum of the positive and negative pole-to-ground voltages always equals the bus voltage to transform the ill-posed inverse problem into an equality-constrained optimal estimation problem, deriving an analytical solution in the sense of constrained least squares. A collaborative monitoring strategy of “balanced bridge monitoring first, unbalanced bridge precision measurement afterward” is proposed. An automatic fault line selection and isolation algorithm based on sequential branch switching is designed, which leverages the operational characteristic that PV systems allow short-term branch interruption, enabling automatic identification and isolation of faulty branches and automatic restoration of non-faulty branches without installing any leakage current sensors. Experimental results show that under severe fault conditions with a single-pole insulation resistance as low as 22 kΩ, the proposed method limits the error to within 5%; the proposed line selection strategy can complete identification and isolation of all faulty branches within at most two rounds of switching. Full article

Rapid three-dimensional electromagnetic field simulation in stratified marine environments is essential for underwater target sensing system design. This paper presents a Physics-Informed Deep Operator Network (PI-DeepONet) that integrates analytical Sommerfeld integral solutions with seafloor experimental measurements to establish a validated, mesh-free forward modeling framework for extremely low-frequency (ELF) electromagnetic propagation. The architecture uses Fourier feature encoding to resolve multiscale dipole fields and incorporates Maxwell’s divergence constraint through automatic differentiation. The model is evaluated using a tiered validation strategy that combines analytical benchmarks, controlled seafloor experiments, and comparison with a purely data-driven DeepONet. The results show close agreement across stratified marine scenarios, improved accuracy and physical consistency from the embedded constraint, and substantially faster pointwise inference than conventional finite element solvers. Analysis of near-field discrepancies further identifies seabed anisotropy and environmental uncertainty as important sources of model–experiment mismatch, thereby clarifying the framework’s applicability and limitations for marine sensing-system design. Full article

This study contrasts the Ganhwa Seon (看話禪) practice theories of Dahui Zonggao, Gaofeng Yuanmiao, and Mengshan Deyi with the focused attention/open monitoring (FA/OM) model proposed by Lutz et al. and the three-family model developed by Dahl et al., both of which are meditation classification frameworks based on cognitive mechanisms. Although these two frameworks have served as standard models in comparative meditation research, their criteria are based primarily on the sati tradition of Theravāda Buddhism and on Tibetan meditation and therefore have difficulty fully accounting for the principles of East Asian Seon practice. Using the Dahui Pujue Chanshi Shu, Gaofeng Yuanmiao Chanshi Chanyao, and Mengshan Heshang Fayu Lüelu as primary sources, this study compares Ganhwa Seon with the two meditation frameworks along five axes: attentional structure, core mechanism, the status of faith (信心), patterns of progression, and epistemological premises. The analysis shows that the huatou, as a conceptually irresolvable question, is neither a determinate object of FA nor the absence of an object characteristic of OM. Yiqing (疑情) operates not by stabilizing attention but by continuously deepening the question. The process by which yiqing condenses into a mass of doubt (疑團) eliminates the very separation between observer and object and thus differs from the investigation-based self-inquiry of the deconstructive family. Faith constitutes the basis on which yiqing arises, and therefore classifications organized solely around attentional functions have difficulty capturing this constitutive relationship. Progress in practice likewise has a nonlinear structure, involving not the gradual automatization of a technique but a leap into sudden enlightenment (頓悟) through the crisis of the silver mountain and iron wall. The cognitive crisis here is not an incidental by-product but an intentionally designed mechanism. Furthermore, the Eight Don’ts (八不得), by excluding introspective observation and rational analysis, indicate the need for a new approach to existing research methodologies that have presupposed introspective self-report. In conclusion, this study proposes that Ganhwa Seon be treated as a distinct unit of analysis in comparative meditation research. Rather than replacing existing classification frameworks, this proposal aims to broaden and supplement their attentional-function-based classification axes toward a more pluralistic classification model. Full article

Automatic modulation recognition (AMR) identifies the modulation scheme of received radio frequency (RF) signals under unknown channel conditions and underpins spectrum monitoring and signal demodulation in wireless systems. Under low signal-to-noise ratio (SNR), multipath fading, and limited observation length, however, the discriminative features of modulated signals are severely attenuated, degrading recognition robustness. We propose MSTFFNet, a multi-scale time-frequency fusion network that addresses these challenges with two designs. First, it fuses the raw in-phase/quadrature (I/Q) signal with its short-time Fourier transform (STFT) time-frequency map at the token level through dual-stream heterogeneous encoding, capturing complementary temporal and spectral features. Second, rather than relying on external SNR ground truth, the network self-estimates an SNR-bin probability from the I/Q features and generates a channel-quality embedding that conditions the classifier, requiring no SNR label at inference. On the RadioML2016.10a and 10b benchmark datasets, MSTFFNet achieves overall accuracies of 67.33% and 70.87%, outperforming state-of-the-art methods by 3.53% and 5.33%, with improvements of 5.91% and 9.52% in the low-SNR regime. These results demonstrate improved recognition performance across the SNR conditions represented in the two synthetic RadioML2016 benchmarks, particularly at low SNR. Full article

This article describes a new hardware/software alert system designed to assist elderly people and prevent falls due to bed-exit events at night. To assist the elderly during the night, it is important to implement automatic lighting activation in the bedroom. This helps reduce the risk of falls when they need to, for example, go to the bathroom. The caregiver can be alerted immediately via Wi-Fi, during the night, providing immediate assistance to the elderly person. The developed HW/SW system combines a passive infrared motion sensing device, a light sensor, and dedicated hardware based on the ESP32-C6 RISC-V microcontroller that communicates via Wi-Fi with a developed Android dedicated App, which the caregiver can access using a tablet or smartphone. Nighttime falls remain one of the most serious health problems for older people. The main innovative contribution of this work is the development of a low-cost preventive battery-free assistive system that does not require an internet access contract, preserves the elderly person’s privacy, and promptly alerts the caregiver whenever the elderly person gets out of bed during the night. The system is directly integrated with automated lighting, preventing the elderly person from walking in the dark and without appropriate aid. The system also supports the caregiver by generating alerts through an open-source mobile App. Full article

This paper studies the automatic berthing control of an unmanned surface vessel under cyber attacks. An adaptive neural-network-based fault-tolerant control method is developed. Unknown vessel dynamics, external disturbances, measurement noise, and cyber attacks are considered at the same time. First, the signal scaling, bias, and power-type distortion caused by cyber attacks are described by a unified nonlinear measurement model. The model has a known structure and unknown parameters. It converts different attack effects into structured uncertainties. Based on the corrupted position and attitude measurements, the tracking errors are defined. The vessel heading is reconstructed by integrating the unaffected yaw-rate signal. A Nussbaum-type function is introduced to handle the unknown gain in the measurement channel. A first-order filter is used to generate a smooth approximation of the virtual control signal. A neural network is then employed to approximate the unknown vessel dynamics. Adaptive laws are designed to estimate the composite uncertainties and external disturbances. Lyapunov analysis shows that all closed-loop signals remain bounded. The berthing tracking errors ultimately converge to a compact set around the origin. Finally, a berthing simulation with time-varying cyber attacks, measurement noise, and marine disturbances is conducted to evaluate the proposed method. Full article

To address the challenge of rapid and precise obstacle avoidance for unmanned aerial vehicles (UAVs) in complex urban environments, rugged canyons, and other unstructured environments, this paper proposes a vision-based navigation algorithm. By combining the strengths of deep reinforcement learning (DRL) and convolutional neural networks (CNNs), this algorithm enables efficient navigation and obstacle avoidance in dynamic environments. First, to improve training efficiency, an autoencoder is used to extract latent spatial vectors from depth images, which are then used as input features for DRL. Second, an artificial potential field (APF) is introduced into the reward function to enhance obstacle avoidance performance in dynamic environments. Third, a CNN-based adaptive mode-switching mechanism is designed to meet navigation requirements under different environmental conditions. This mechanism can automatically identify environmental features based on real-time input data and dynamically adjust the UAV’s navigation strategy. To evaluate the proposed method, simulation experiments were conducted in static and dynamic scenarios, together with a preliminary indoor flight test. Under the evaluated conditions, the proposed method achieved favorable navigation success rates and path efficiency compared with the selected visual DRL baselines. The results also indicate cross-scenario transferability to the tested environments without environment-specific retraining. Full article

The increasing complexity of residential energy systems and the growing penetration of distributed resources require practical energy-management solutions that extend beyond conventional metering. This paper presents the design and implementation of a real-time Internet of Things (IoT)-based energy-management system for monitoring and controlling household energy consumption under different operating conditions. The proposed system adopts a dual-processor architecture, in which a primary microcontroller performs time-critical electrical measurements and low-level load switching, while a secondary processor operates as a local IoT gateway for data handling, rule-based control decisions, local visualization, and message queuing telemetry transport (MQTT)-based cloud communication through a 4G link. The contribution of this work is not associated with the individual use of dual processing, cellular communication, cloud monitoring, load shedding, or backup power, as these technologies have been previously reported in smart-metering and home energy-management systems. Instead, the study focuses on their coordinated integration within a residential-scale prototype that combines calibrated per-load monitoring, priority-based load control, outage-resilient reporting, and credit-aware load restriction. The system measures voltage, current, active and apparent power, power factor, and energy consumption for individual loads and supports centralized visualization through a cloud-based dashboard. The prototype was experimentally evaluated under three representative scenarios: overload, main power outage, and low-credit operation. In the overload scenario, automatic priority-based load shedding reduced the total load by up to 75%. During power outages, a battery-supported subsystem maintained monitoring and communication for real-time outage reporting. In the low-credit scenario, non-essential loads were disconnected when the user balance fell below a predefined threshold, while essential loads remained energized. The results demonstrate that the implemented prototype can provide integrated monitoring, local rule-based control, cloud reporting, and backup-supported operation within a unified residential energy-management platform. Full article

Fake news often manipulates fine-grained knowledge elements such as entities, events, claims, temporal expressions, attributes, and source credibility. Existing information extraction methods usually require task-specific annotations or focus on generic named entities, making them less effective for open-domain fake news scenarios where labeled data are scarce and logical inconsistencies are subtle. This paper proposes HPDO-KEE, a hierarchical prompting framework with dynamic optimization for knowledge element extraction and feature enhancement in fake news detection. The method first defines a fake-news-oriented schema covering entities, events, claims, attribute–value pairs, relations, contradictions, and user authority. It then designs a four-layer prompt consisting of task description, core information, structure awareness, and demonstration assistance. The revised implementation distinguishes offline prompt-template rewriting from input-adaptive demonstration retrieval and automatic schema-validation retries during inference. Domain-aware demonstration selection, strict JSON constraints, redundancy removal, contradiction-candidate verification, and type correction are incorporated to improve extraction accuracy, format compliance, and stability. Experiments on CoNLL03, ACE2005, and DuEE2.0 show that HPDO-KEE achieves F1 scores of 88.9%, 82.6%, 80.3%, and 78.6% on named entity, entity, event, and Chinese event extraction tasks, respectively. Full article