Search Results (150)

Cluster Validity Indices (CVIs) act as a pivotal tool in machine learning for assisting in the determination of the optimal number of clusters. Nevertheless, traditional CVIs often exhibit subpar performance when confronted with the complex characteristics prevalent in real-world data, such as inter-cluster overlap, outliers and uneven density distribution. To address this challenge, this paper proposes a multiplicative, adaptive and robust Cluster Validity Index, designated as the Robust Adaptive (RA) index. This index takes the kernel density function of sample points as the fundamental tool and reconstructs its two core components: in the measurement of intra-cluster compactness, the concept of density quantiles is incorporated, which markedly enhances its robustness against outliers; in the measurement of inter-cluster separability, a density-based Jeffrey divergence method is developed to effectively characterize inter-cluster differences in overlapping datasets. To mitigate the impact of bandwidth selection on kernel density estimation, this study adopts strategies including Scott’s and Silverman’s heuristic algorithms, thus enabling adaptive learning of the inherent distribution characteristics of data. For experimental validation, a comprehensive set of experiments was conducted on both synthetic and real-world datasets. The results show that, in comparison with the classical indices (CH, DB, SIL, I) that demonstrate prominent performance on overlapping datasets, the RA index delivers superior performance in scenarios involving mild to moderate overlap, uneven density distribution and the presence of outliers. Among nine synthetic datasets, the RA index correctly identified the optimal number of clusters in eight cases, achieving a high success rate of 88.89% and outperforming all the comparative indices. On eight real-world datasets with diverse scales, dimensionalities and inherent structural features, the RA index was also verified to be the most robust and effective metric among the five participating indices for comparison. Meanwhile, its failure on complex datasets such as S-set4 and Iris, which contain both severe inter-cluster overlap and outliers, also indicates that density-based CVIs have inherent limitations when faced with data structures characterized by high overlap and faint cluster boundaries. This finding points to a clear direction for future research: constructing novel CVIs from the perspective of sparse matrices may serve as a feasible breakthrough path to address such limitations. Full article

Synthetic Aperture Radar (SAR) is one of mainstream remote sensing techniques, offering all-weather, day-and-night operational capabilities. However, throughout the processes of signal transmission, propagation, and reception, it is difficult to ensure that the amplitude and phase of the SAR signal strictly follow a linear frequency modulation (LFM) characteristic. The resulting signal distortion often leads to main lobe broadening and sidelobe elevation, degrading the focusing performance of SAR images. Traditionally, this issue has been addressed primarily through SAR system internal calibration and pre-distortion compensation, which makes it challenging to maintain the signal in an ideal state over the long term. At the same time, many simplified SAR systems also lack an internal calibration design, such as low-cost UAV-borne SAR payloads. In this paper, we propose a novel signal distortion compensation method based on SAR image data. Without relying on SAR system calibration signals, this method estimates and compensates for signal distortion directly using SAR image data, thereby improving SAR image focusing performance, achieving a resolution closer to the theoretical bandwidth and lower sidelobe. The processing and analysis of both manned and unmanned airborne SAR image data and calibration signals demonstrate that the proposed method effectively compensates for signal distortion phases, achieving performance comparable to that of real-time calibration-signal-based methods. Full article

Water and mud inrush represent some of the most catastrophic geological hazards encountered in tunnel engineering. Underground Magnetic Resonance Sounding (UMRS) holds significant potential for prospecting hydrogeological parameters within adverse geological bodies. The implementation of the method is limited, however, by the challenge of undesired frequency offsets between the assumed and true Larmor frequencies and poor signal-to-noise ratios in the tunnel environment. For the adaptation of UMRS to the tunnel environments, accurate modeling considering the off-resonance effects and magnitude enhancement of received signals is required. The traditional UMRS application assumes that on-resonance excitation is valid for any circumstance. Neglecting the effects of undesired frequency offsets produces a significant influence on amplitudes and phases of UMRS signals, as demonstrated by our models. Moving beyond the on-resonance excitation condition, we focus on a primary study of a novel multi-off-resonance excitation method using a broadband pulse, in which the off-resonance effects are exploited for improving signal magnitudes of UMRS. To implement the method we proposed, a new excitation pulse with several spectral peaks in a finite bandwidth is presented. Each spectral peak of the excitation spectrum contributes to the response voltage according to its spectral amplitude and offsets to Larmor frequency. The spectrum of the new excitation pulse can be modulated according to demands. The feasibility of the excitation pulse and method are supported by synthetic experiments using three different pulse parameters. Significant magnitude enhancement in the sounding curves is presented in the occurrence of undesired frequency offsets with different magnitudes. Furthermore, the method we proposed provides signal enhancement for the deeper water occurrence in the presence of an undesired frequency offset. We note that the present study is a theoretical and numerical proof-of-concept investigation. Experimental validation, including laboratory-scale physical model tests and field tunnel measurements, is planned as future work once suitable transmitter instrumentation becomes available. Full article

During flood disasters, on-site operations often face the “triple disruption” of network outages, power cuts and blocked roads. This renders terrestrial cellular infrastructure inoperable and disrupts communication links. Satellite internet can partially restore emergency communications thanks to its wide-area coverage and resistance to ground damage. However, limited computing power, memory and unstable bandwidth at the terminal prevent cloud-based flood segmentation from providing near-real-time situational awareness. This paper therefore proposes a lightweight semantic flood segmentation framework for emergency terminals that uses satellite internet. This comprises a parallel dual-branch design with a lightweight U-Net-style convolutional neural network (CNN) branch for local boundary details and a compact Transformer branch for global context. A dynamic gated fusion mechanism (DGFM) balances local texture and global information adaptively. Experiments on the public synthetic aperture radar (SAR) dataset Sen1Floods11 demonstrate that the hybrid architecture strikes a balance between accuracy and inference efficiency. The proposed method combines gated fusion with quality-aware training. Compared to a lightweight CNN baseline and state-of-the-art segmentation models using the same protocol, the proposed configuration (Hybrid-Gated with Quality-Aware Training) achieves the highest mean intersection over union and F1 score among the compared fusion variants, while maintaining competitive false alarm and risk-sensitive performance under deployment constraints. This aligns with the preferences of emergency decision makers. The framework provides a deployable perception module for emergency systems supported by low-orbit satellites and terrestrial networks under triple-disruption conditions. Full article

The fact that a large Gabor bandwidth promotes measurement accuracy has motivated research on Global Navigation Satellite System (GNSS) meta-signals, which are obtained by jointly processing components from different frequencies. When two side-band components are considered, the resulting meta-signal has characteristics close to that of a pure carrier and measurement ambiguities can arise: a third signal in between side-band components can alleviate this problem and help estimating the integer ambiguities. This paper provides a framework for the generation of measurements from triple-component GNSS meta-signals with the goal of reducing the ambiguity problem. The whole meta-signal is at first decomposed as two dual-component meta-signals with the central component used as pivot. Measurements on the dual-component meta-signals are computed using the synthetic approach based on the Hatch-Melbourne-Wübbena (HMW) combination. Triple-component pseudoranges are then obtained as the narrow lane combination of the pseudoranges from the dual-component meta-signals. Theoretical results have been supported through experimental analyses based on measurements from two Septentrio PolaRx5S multi-frequency, multi-constellation receivers set up in a zero-baseline configuration. Results based on the Galileo E5a, E5b and E6 components show the effectiveness of the proposed framework. Full article

Accurate wind speed forecasting is critical for reliable wind-power integration, yet it remains challenging due to the strongly non-stationary and inherently multi-scale nature of atmospheric processes. While deep learning models—such as LSTM, GRU, and Transformer architectures—achieve competitive short- and medium-term performance, they frequently suffer from spectral bias, hyperparameter sensitivity, and reduced generalization under heterogeneous operating regimes. To address these limitations, we propose a multi-scale spectral–recurrent framework, termed RFF-RNN, which integrates multi-band Random Fourier Feature (RFF) encodings with parameterizable recurrent backbones. A key innovation of our approach is the deliberate relaxation of strict shift-invariance constraints; by jointly optimizing spectral frequencies, phase biases, and bandwidth scales alongside the neural weights, the framework dynamically shapes a fully data-driven spectral embedding. To ensure robust adaptation, we employ a two-stage optimization strategy combining gradient-based inner-loop learning with outer-loop Bayesian hyperparameter tuning. Our extensive evaluations on a controlled synthetic benchmark and six geographically diverse real-world wind datasets (spanning the USA, China, and the Netherlands) demonstrate the superiority of the proposed framework. Statistical validation via the Friedman test confirms that RFF-enhanced models—particularly RFF-GRU and RFF-LSTM—systematically outperform standard recurrent networks and state-of-the-art Transformer architectures (Autoformer and FEDformer). The proposed approach yields significantly lower error metrics (MAE and RMSE) and higher explained variance ($R^2$), while exhibiting remarkable resilience against error accumulation at extended forecasting horizons. Full article

Lightweight multi-rotor unmanned aerial vehicles (UAVs) have shown great potential in flexible Earth observation, but they impose strict restrictions on payload, volume, and power consumption. Traditional pulse-Doppler synthetic aperture radar (SAR) systems offer high imaging performance but suffer from high peak power and large volume, making them unsuitable for lightweight UAV platforms. To meet the low-power demand, most existing lightweight UAV SAR systems adopt frequency-modulated continuous-wave (FMCW) schemes, which are compact and low cost yet limited by a low range resolution, poor anti-interference ability, and single imaging modes. Therefore, it is urgent to develop an SAR system that combines the high performance of pulse radar with the lightweight advantage of FMCW radar. To this end, this paper proposes a compact, low-power Ka-band pulse-Doppler SAR system for multi-rotor UAVs. With 1.2 GHz bandwidth and highly integrated RF and antenna design, the system achieves miniaturization and low power consumption while maintaining high-resolution imaging capability. Furthermore, two-step waveform error correction and a signal predistortion method are presented to compensate amplitude and phase errors and improve the purity of the transmitted signal. Experimental results show that the proposed system can obtain clear SAR images with a resolution better than 0.3 m, providing a practical high-performance pulse-SAR solution for lightweight UAV platforms. Full article

Sub-band errors are inevitable in synthetic bandwidth synthetic aperture radar (SAR) systems due to differences in signal paths and frequency responses of the components used for different sub-bands, which degrade imaging performance if not properly compensated. In this paper, a prominent-reflector-based sub-band error estimation method is proposed for synthetic bandwidth SAR. Based on the analysis of the sources and impacts of sub-band errors, the proposed method estimates and compensates the errors in three steps, corresponding to time-delay error, amplitude error, and phase error. By leveraging the stable reflective properties of prominent reflectors in the scene, the proposed method directly derives sub-band error estimates from focused sub-band images in the time domain. Compared to existing methods, the proposed method achieved robust, high-accuracy performance while requiring less execution time. The effectiveness and efficiency of the proposed method are validated using real data collected by a Ka-band synthetic bandwidth SAR system. Full article

Event-based sensors provide sparse, motion-centric measurements that can reduce data bandwidth and enable always-on perception on resource-constrained edge devices. This paper presents an event-based machine vision framework for smart-home AIoT that couples a Dynamic Vision Sensor (DVS) with compute-efficient algorithms for (i) human/object detection, (ii) 2D human pose estimation, (iii) hand posture recognition for human–machine interfaces. The main methodological contributions are timestamp-based, polarity-agnostic recency encoding that preserves moving-edge structure while suppressing static background, and task-specific network optimizations (architectural reduction and mixed-bit quantization) tailored to sparse event images. With a fixed downstream network, the recency encoding improves action recognition accuracy over temporal accumulation (0.908 vs. 0.896). In a 24 h indoor monitoring experiment (640 × 480), the raw DVS stream is about 30× smaller than conventional CMOS video and remains about 5× smaller after standard compression. For human detection, the optimized event processing reduces computation from 5.8 G to 81 M FLOPs and runtime from 172 ms to 15 ms (more than 11× speed-up). For pose estimation, a pruned HRNet reduces model size from 127 MB to 19 MB and inference time from 70 ms to 6 ms on an NVIDIA Titan X while maintaining a comparable accuracy (mAP from 0.95 to 0.94) on MS COCO 2017 using synthetic event streams generated by an event simulator. For hand posture recognition, a compact CNN achieves 99.19% recall and 0.0926% FAR with 14.31 ms latency on a single i5-4590 CPU core using 10-frame sequence voting. These results indicate that event-based sensing combined with lightweight inference is a practical approach to privacy-friendly, real-time perception under strict edge constraints. Full article

Cloud storage continues to experience recurring provider-side breaches, raising concerns about the confidentiality and recoverability of user data. This study addresses this challenge by introducing an Artificial Intelligence (AI)-driven hybrid architecture for secure, reconstruction-resistant multi-cloud storage. The system applies telemetry-guided fragmentation, where fragment sizes are dynamically predicted from real-time bandwidth, latency, memory availability and disk I/O, eliminating the predictability of fixed-size fragmentation. All payloads are compressed, encrypted with AES-128 and dispersed across independent cloud providers, while two encrypted fragments are retained within a VeraCrypt-protected local vault to enforce a distributed trust threshold that prevents cloud-only reconstruction. Synthetic telemetry was first used to evaluate model feasibility and scalability, followed by hybrid telemetry integrating real Microsoft system traces and Cisco network metrics to validate generalization under realistic variability. Across all evaluations, XGBoost and Random Forest achieved the highest predictive accuracy, while Neural Network and Linear Regression models provided moderate performance. Security validation confirmed that partial-access and cloud-only attack scenarios cannot yield reconstruction without the local vault fragments and the encryption key. These findings demonstrate that telemetry-driven adaptive fragmentation enhances predictive reliability and establishes a resilient, zero-trust framework for secure multi-cloud storage. Full article

The Social Internet of Things (SIoT) enables collaborative service provisioning among interconnected devices by leveraging socially inspired trust relationships. This paper proposes a socially driven SIoT protocol for trust-aware service selection, enabling dynamic friendship formation and ranking among distributed service-providing devices based on observed execution behavior. The protocol integrates detection accuracy, round-trip time (RTT), processing time, and device characteristics within a graph-based friendship model and employs PageRank-based scoring to guide service selection. Industrial computer vision workloads are used as a representative testbed to evaluate the proposed SIoT trust-evaluation framework under realistic execution and network constraints. In homogeneous environments with comparable service-provider capabilities, friendship scores consistently favor higher-accuracy detection pipelines, with F1-scores in the range of approximately 0.25–0.28, while latency and processing-time variations remain limited. In heterogeneous environments comprising resource-diverse devices, trust differentiation reflects the combined influence of algorithm accuracy and execution feasibility, resulting in clear service-provider ranking under high-resolution and high-frame-rate workloads. Experimental results further show that reducing available network bandwidth from 100 Mbps to 10 Mbps increases round-trip communication latency by approximately one order of magnitude, while detection accuracy remains largely invariant. The evaluation is conducted on a physical SIoT testbed with three interconnected devices, forming an 11-node, 22-edge logical trust graph, and on synthetic trust graphs with up to 50 service-providing nodes. Across all settings, service-selection decisions remain stable, and PageRank-based friendship scoring is completed in approximately 20 ms, incurring negligible overhead relative to inference and communication latency. Full article

The present work addresses the critical challenge of designing a lightweight antenna suitable for remote sensing applications specifically aimed at the identification of buried objects from Unmanned Aerial Vehicles (UAVs). The stability of the phase center and the radiation pattern are critical factors for enabling synthetic aperture radar (SAR) processing on moving platforms. The presented antenna structure is characterized by a simple, lightweight geometry, and allows for achieving a fractional bandwidth of nearly 100% with an excellent stability of the radiation pattern, that exhibits minimal variation within the operating band of the antenna. Specifically, the gain is in the range 4.4–6.3 dBi and the group delay spread is about 200 ps in the frequency range 1–2 GHz. We illustrate numerical simulations and measurements of an antenna prototype that validate the proposed approach, demonstrating the suitability of the design for the intended operational scenario. Full article

Boron-dipyrromethene (BODIPY) dyes belong to a class of organoboron compounds that have become ubiquitous for researchers in areas of fluorescence imaging, photodynamic therapy, and optoelectronics. The intrinsic qualities of BODIPY dyes and their meso-modified structural analogs, Aza-BODIPY dyes, have propelled their recent increase in use in biomedical applications. The two scaffolds have high quantum yields, narrow absorption, and emission bandwidths with large Stokes’ shifts, and high photostability and thermal stability. Because their properties are independent of solvent polarity and dye functionality, they can be tuned to promote novel analytical methods, resulting in the adaptation of the physicochemical and spectral properties of the dyes. In this review of BODIPY and Aza-BODIPY scaffolds, we will summarize their spectral properties, synthetic methods of preparation, and applications reported between 2014 and 2025. This review aims to summarize the advances in chemosensing, especially pH sensor development, and the advances in NIR-II window bioimaging probes. We hope that this succinct overview of Aza-BODIPY scaffolds will highlight their untapped potential, elucidating insights that may catalyze novel ideas in the physical organic realm of BODIPY. Full article

Federated Graph Neural Networks (FedGNNs) have emerged as a promising paradigm for decentralized graph learning across distributed data silos. However, the influence of underlying communication topologies on model accuracy and efficiency remains underexplored. This study presents a topology-aware benchmarking framework for federated GNNs, systematically evaluating the impact of network structure and aggregation strategy on performance and communication overhead. The proposed framework functions as a synthetic, communication-level digital twin that emulates Federated Learning interactions and topology-dependent dynamics under controlled conditions. Four learning schemes—Centralized, Local, FedAvg, and FedAvg-Fedadam—were assessed across three representative topologies: Barabási–Albert (BA), Watts–Strogatz (WS), and Erdős–Rényi (ER). Results demonstrate that centralized training achieved the highest mean ROC-AUC (0.63), while FedAvg-Fedadam attained the best F1-score (0.038), balancing local adaptation and global convergence. Among topologies, BA and WS yielded higher average AUC values (approximately 0.57 and 0.56, respectively) than ER (approximately 0.39). Communication analysis revealed FedAvg as the most efficient strategy, requiring only approximately 3.8 × 10⁵ bytes cumulatively. These findings highlight key trade-offs between accuracy, robustness, and communication efficiency in federated graph learning and provide empirical guidance for topology-aware optimization of distributed GNNs. While the experiments rely on representative synthetic topologies, the insights offer indicative relevance and potential applicability to Internet-of-Things (IoT), vehicular, and cyber-physical networks, where communication structure and bandwidth constraints critically influence collaborative intelligence. By modeling canonical connectivity patterns and releasing our code and data, the proposed benchmarking framework offers a reproducible basis for comparing emerging federated graph architectures under constrained communication conditions. Full article

To obtain radar images of a group of small space objects or to resolve individual elements of complex space objects in near-Earth orbit, a radar system must have high spatial resolution. High range resolution is achieved by using complex probing signals with a wide spectrum bandwidth. Achieving high angular resolution for small or complex space objects is based on the inverse synthetic aperture antenna effect. Among the various classes of complex signals, only two have found practical application in Inverse Synthetic Aperture Radar (ISAR) systems so far: the Linear Frequency-Modulated signal (chirp) and the Stepped-Frequency signal. Over the coherent integration interval of the echo signals, which corresponds to the ISAR aperture synthesis time, the combined correlation characteristics of the signal ensemble are analyzed. A high level of integral correlation noise in the ensemble of probing signals degrades the quality of the radar image. Therefore, a probing signal with a Zero Autocorrelation Zone (ZACZ) is highly relevant for ISAR applications. In this work, through simulation, radar images of a complex space object were obtained using both chirp and ZACZ probing signals. A comparative analysis of the correlation characteristics of the echo signals and the resulting radar images of the complex space object was performed. Full article