Sensors最新文献

Automated visual inspection of safety-critical metal assemblies such as automotive door lock strikes remains challenging due to their complex three-dimensional geometry, highly reflective surfaces, and scarcity of defect samples. While 3D sensing technologies are often constrained by cost and speed, traditional 2D optical methods struggle with severe imaging artifacts and poor generalization under few-shot conditions. This work constructs a complete system integrating defect imaging, generation, and detection. It proposes an integrated framework through the co-design of an image acquisition system and deep generative models to holistically enhance defect perception capability. First, we develop an imaging system using dome illumination and a small-aperture lens to acquire high-quality images of non-planar metal surfaces. Subsequently, we introduce a dual-stage generation strategy: stage one employs an improved FastGAN with Dynamic Multi-Granularity Fusion Skip-Layer Excitation (DMGF-SLE) and perceptual loss to efficiently generate high-quality local defect patches; stage two utilizes Poisson image editing and an optimized loss function to seamlessly fuse defect patches into specified locations of normal images. This strategy avoids modeling the complete complex background, concentrating computational resources on creating realistic defects. Experiments on a dedicated dataset demonstrate that our method can efficiently generate realistic defect samples under few-shot conditions, achieving 11-24% improvement in Fréchet Inception Distance (FID) scores over baseline models. The generated synthetic data significantly enhances downstream detection performance, increasing YOLOv8's mAP@50:95 from 50.4% to 60.5%. Beyond proposing individual technical improvements, this research provides a complete, synergistic, and deployable system solution-from physical imaging to algorithmic generation-delivering a computationally efficient and practically viable technical pathway for defect detection in highly reflective, non-planar metal components.

This article presents an experimental investigation of the effect of water aging on the static mechanical behavior and damage mechanisms of bio-based sandwich structures with auxetic cores using acoustic emission (AE) monitoring. Both the skins and the core are manufactured by 3D printing using polylactic acid (PLA) reinforced with short flax fibers. Four auxetic core configurations, differing in the number of unit cells across the core width, are considered. The specimens are immersed in water at room temperature to characterize their absorption behavior, which follows a Fickien's diffusion law model with different saturation levels. Static three-point bending tests are performed at various immersion times to evaluate the influence of moisture on mechanical performance. The results show a progressive degradation of mechanical properties with increasing water exposure time, with the four-cell core configuration exhibiting the highest mechanical performance. Acoustic emission (AE) monitoring is employed to analyze damage evolution as a function of hydrothermal aging. AE parameters such as amplitude, energy, and cumulative event count are used to identify and classify the different damage mechanisms. This approach highlights the effectiveness of acoustic emission for structural health monitoring and for assessing the durability of auxetic core sandwich structures subjected to moisture.

This paper proposes an acoustic analysis system to help improve saxophone performance skills. The system combines direct support for performance movements by a robot with indirect support by presenting performance information. By sensing the performance audio and performing real-time acoustic analysis, the system presents the learner with information about their performance and their playing habits. The performance information presented to the learner includes pitch, volume, and playing timing. For performance habit analysis, a Markov model with pitch as the state and an internal probability parameter that indicates the quality of the performance evaluation as the pitch transitions are defined. In the experiment, we conducted a pilot study targeting experienced saxophone players and a beginner saxophone player to verify the effectiveness of the proposed system. The experiment showed that the MAE of the played pitch was significantly reduced by using the proposed system.

In the sensor array signal reception system, improving the accuracy of weak-signal detection is crucial. Traditional fixed-step algorithms struggle to balance the convergence rate (CR) and low steady-state error (SSE) owing to their inherent trade-off limitations. To address this limitation, we propose a novel variable-step-size least-mean-square (VSS-LMS) algorithm based on a modified versoria function, specifically redesigned to enhance curvature characteristics. This approach establishes dynamic coupling between error statistics and step-size factors through nonlinear mapping. It derives closed-loop equations governing parameters (α, β, and γ) relative to the smoothed instantaneous error correlation function. Consequently, an adaptive feedback system is constructed to achieve real-time adjustment through optimal step-size generation. The optimal parameters (α, β, and γ) are determined through empirical enumeration and analysis of their impact on algorithmic performance. Comparative evaluations against established VSS-LMS algorithms confirm performance: the proposed algorithm accelerates convergence while maintaining a low SSE, and exhibits robust signal recovery capabilities under low-SNR conditions with diverse interference types.

Phishing attacks often rely on impersonating a legitimate entity, such as a well-known company or a bank, with the intent to deceive individuals. A common tactic used by cybercriminals to conduct such an attack is to register a specific domain to host a phishing website on it. In this paper, we propose BadDomains, a system for the early detection of phishing domains' registration. BadDomains utilizes domain registry data about newly registered domains combined with knowledge about the current phishing situation, such as information about the most frequent impersonation targets, or suspicious domain contact information. An analysis of .pl phishing domain registry data, combined with the authors' CSIRT operational experience, helped in the design of new features. It also facilitated the extension of features already used in other solutions. The system's evaluation has been performed using information from .pl Top Level Domain (TLD) registry combined with CERT Polska's (Polish national CSIRT) public list of phishing domains, used as a ground truth. BadDomains has been compared to a similar detection system designed for .eu TLD called Premadoma, which was adapted to this work. The results showed that BadDomains achieved higher F1 scores than Premadoma. After operational deployment, the system proved to provide timely detections, uncovering unknown phishing domains.

High-intensity interval training (HIIT) provides substantial cardiovascular benefits; however, precise monitoring typically requires expensive devices. These systems are feasible in research laboratories but are costly for schools and the fitness industry. Low-cost, validated devices are required to facilitate broader implementation. A cross-sectional study was conducted with 213 students (173 men and 40 women) from the Catholic University of Valencia, Spain. The participants completed an HIIT protocol consisting of five 3 min blocks. Heart rate (HR) was recorded using a Moofit HW401 armband (ANT+ technology). Ratings of perceived exertion (RPE, Omni-Res scale) and the Wint index were also obtained. Pearson correlations were computed between reserve heart rate (HRr), RPE, and Wint index during the warm-up phases (T1, T2) and HIIT, stratified by sex, age, and body mass index (BMI). HRr was strongly correlated with the Wint index (r = 0.95, p < 0.0001) and moderately correlated with RPE (r = 0.235, p = 0.001). No significant sex differences were observed (men 83.66 ± 8.18% vs. women 82.31 ± 10.89%; p > 0.05). Correlations were weaker in participants with extreme BMI values (n < 10, obese). The Moofit HW401 armband showed consistent agreement between HRr, RPE, and Wint index during HIIT, supporting its practical use for group monitoring in educational settings, pending formal validation against gold standards.

As a non-contact identification technology, RFID (Radio Frequency Identification) is widely used in various Internet of Things applications. However, RFID systems are highly vulnerable to diverse attacks due to the openness of communication links between readers and tags, leading to serious security and privacy concerns. Numerous RFID authentication protocols have been designed that employ hash functions and symmetric cryptography to secure communications. Despite these efforts, such schemes generally exhibit limitations in key management flexibility and scalability, which significantly restricts their applicability in large-scale RFID deployments. Confronted with this challenge, public key cryptography offers an effective solution. Taking into account factors such as parameter size, computational complexity, and resistance to quantum attacks, the NTRU algorithm emerges as one of the most promising choices. Since the NTRU signature algorithm is highly complex and requires large parameters, there are currently only a few NTRU encryption-based RFID authentication protocols available, all of which exhibit significant security flaws-such as supporting only one-way authentication, failing to address public key distribution, and so on. Moreover, performance evaluations of the algorithm in these contexts are often incomplete. This paper proposes a mutual authentication protocol for RFID based on the NTRU encryption algorithm to address security and privacy issues. The security of the protocol is analyzed using the BAN-logic tools and some non-formalized methods, and it is further validated through simulation with the AVISPA tool. With the parameter set (N, p, q) = (443, 3, 2048), the NTRU algorithm can provide 128 bits of post-quantum security strength. This configuration not only demonstrates greater foresight at the theoretical security level but also offers significant advantages in practical energy consumption and computation time when compared to traditional algorithms such as ECC, making it a highly competitive candidate in the field of post-quantum cryptography.

Personalized federated learning (pFL) aims to address data heterogeneity by training client-specific models. However, it faces two critical challenges under few-shot conditions. First, existing methods often overlook the hierarchical structure of neural representations, limiting their ability to balance generalization and personalization. Second, recent approaches incorporate representation-level inductive biases that typically rely on rigid assumptions, such as fixed perturbation patterns or compact class clusters, making them vulnerable to distribution shifts in federated environments. To overcome these limitations, we propose pFedH2A, a novel hierarchical framework incorporating brain-inspired mechanisms, tailored for personalized federated learning in few-shot scenarios. First, we design a dual-branch hypernetwork (DHN) that employs two structurally distinct branches to generate aggregation weights. Each branch is biased toward capturing either low-level shared features or high-level personalized representations, enabling fine-grained personalization by mimicking the brain's division of perceptual and representational processing. Second, we introduce a relation-aware module that learns an adaptive similarity function for each client, supporting few-shot classification by measuring whether a pair of samples belongs to the same class without relying on rigid prototype assumptions. Extensive experiments on public image classification datasets demonstrate that pFedH2A outperforms existing pFL baselines under few-shot scenarios, validating its effectiveness.

Soil organic matter (SOM) is a key indicator of arable land quality and the global carbon cycle; accurate regional-scale SOM estimation is vitally significant for sustainable agricultural development and climate change research. This study evaluates a multisource data-fusion approach for improving cropland SOM prediction in Yucheng City, Shandong Province, China. We applied a Local Energy Weighted Discrete Wavelet Transform (LEW-DWT) to fuse multi-temporal Landsat 8 imagery (2014-2023). Quantitative analysis (e.g., Information Entropy and Average Gradient) demonstrated that LEW-DWT effectively preserved high-frequency spatial details and texture features of fragmented croplands better than traditional DWT and simple splicing methods. These were combined with 41 environmental predictors to construct composite Ev-Tn-Mm features (environmental variables, temporal NDVI features, and multi-temporal multispectral information). Random Forest (RF) and Convolutional Neural Network (CNN) models were trained and compared to assess the contribution of the fused data to SOM mapping. Key findings are: (1) Comparative analysis showed that the LEW-DWT fusion strategy achieved the lowest spectral distortion and highest spatial fidelity. Using the fused multitemporal dataset, the CNN attained the highest predictive performance for SOM (R² = 0.49). (2) Using the Ev-Tn-Mm features, the CNN achieved R² = 0.62, outperforming the RF model (R² = 0.53). Despite the limited sample size, the optimized shallow CNN architecture effectively extracted local spatial features while mitigating overfitting. (3) Variable importance analysis based on the RF model reveals that mean soil moisture is the primary single variable influencing the SOM, (relative importance 15.22%), with the NDVI phase among time-series features (1.80%) and the SWIR1 band among fused multispectral bands (1.38%). (4) By category, soil moisture-related variables contributed 45.84% of total importance, followed by climatic factors. The proposed multisource fusion framework offers a practical solution for regional SOM digital monitoring and can support precision agriculture and soil carbon management.

Reservoir boundary distance measurement is a key technology in geosteering drilling. In this field, it is difficult to balance detection precision and depth. This paper proposes a method to measure reservoir boundary distance using a drill-attached impulse sound source equipped with a reflector. The COMSOL Multiphysics (COMSOL) is used to construct a while-drilling reservoir model with a reflector and verify the model's effectiveness through the real-axis integration method. Under this model, the dimensions of the reflector are analyzed, the relative ranging error under different distances is calculated, and source distance combinations and reservoir interface dip angles are considered. Moreover, the effectiveness of this method is verified through the results of ranging for two sets of actual geological parameters. These results show that the rotating parabolic reflector (depth 45 mm, opening radius 12.2 mm) has a good energy bunching effect. When the dominant excitation frequency of the sound source is 8 kHz, and the source distance combination is 2 m and 4 m, the minimum relative ranging error for the reservoir boundary at 7 m is 2.1%. The relative error becomes smaller when the reservoir boundary dip angle and source distance are smaller. When the source distance is 2 m or 7 m, and the dip angle is between [-20, 20] degrees, the relative error is below 15%. Simulations with actual formation parameters indicate that the proposed method attains good ranging precision.