Search Results (192)

Background/Objectives: The early identification of skin cancer by standard RGB dermoscopy is a clinical difficulty because of the complex visual differences between impacted lesions and healthy tissue. Methods: For the biomedical challenge, a novel approach to signal processing and image reconstruction is introduced in this study, called the spectrum-aided visual enhancer (SAVE). The proposed SAVE mechanism aims at reconstructing the diagnostically relevant spectral information from the conventional RGB dermoscopic images using the principles of hyperspectral imaging (HSI) and band selection (BS). After quality control and pre-processing, the images in the ISIC2019 dataset were selected, with 865 images that contain basal cell carcinoma (BCC), seborrheic keratosis (SK), and actinic keratosis (AK) lesions. To reduce data leakage, the dataset was split into training, validation, and testing subsets of 70%, 20%, and 10%, respectively. Five supervised deep learning object detection models were trained and tested on the conventional RGB image dataset and on the SAVE-enhanced dataset. Five supervised deep learning object detection models, namely, YOLOv8, YOLOv10, YOLOv11, SSDLite, and SSD, were trained and tested on the conventional RGB image dataset and the SAVE-enhanced dataset. Additional repeated experimental assessments and statistical comparisons were also carried out to evaluate the improvement in performance. Results: The experimental results showed that the SAVE-based pre-processing always yielded better performance in terms of lesion detection than conventional RGB image processing. The SAVE framework for SSD was evaluated and compared with all other evaluated models and was found to be the most successful, with an accuracy of 96%, a precision of 97%, a recall of 96%, and an F1 score of 96%. Conclusions: The results indicate that the proposed SAVE framework could be a promising RGB-compatible spectral enhancement technique for boosting skin cancer detection and computer-aided dermatologic analysis with the aid of AI. Full article

The preparation of high-performance cadmium zinc telluride (CZT) radiation detector materials requires efficient ingot-level quality assessment before full downstream wafer testing. This study proposes a machine learning framework that predicts the product-level yield of test wafers from IV and double-sided spectral measurements of a limited number of standardized evaluation wafers from the same ingot. To address the small number of ingots and wafer-level variability, ingot-level aggregate, A/B-side consistency, threshold-ratio, and distributional features were combined with intra-ingot bootstrap augmentation. Among the evaluated regression models, Random Forest achieved the best held-out test performance under a leakage-safe protocol, with an MSE of 0.021, an MAE of 0.125, and a Pearson correlation coefficient of 0.646; XGBoost showed comparable performance, with an MSE of 0.023, an MAE of 0.128, and a Pearson correlation coefficient of 0.601. In a top-22% screening experiment, the average true yield of ingots selected by Random Forest and XGBoost reached 63.71% and 60.40%, respectively, exceeding the empirical Rule_IV_Abs baseline of 59.08%. These results indicate that the proposed framework can provide useful ranking and prioritization support for early CZT ingot screening, while remaining a decision-support tool rather than a replacement for wafer-level inspection. Full article

This study comprehensively investigates the degradation performance of a Mn-doped Zn₂SnO₄ photocatalyst based on time-dependent UV-Vis absorption spectra. Before machine learning modelling, the effects of experimental parameters such as UV–Vis measurement wavelength, reaction time, and Mn doping ratio were statistically validated using One-Way Analysis of Variance (ANOVA) and Multiple Linear Regression (MLR) methods. To overcome the limitations of linear models in representing complex physical systems, an optimized Multi-Layer Perceptron (MLP) architecture was developed to capture the system’s nonlinear dynamics with high accuracy. To validate the model’s out-of-sample prediction capability and prevent data leakage potentially arising from spectral data correlation, the “Leave-One-Doping-Level-Out” (LODLO) cross-validation strategy was applied, during which performance metrics of R²$=0.8889$ and $MSE=0.00238$ were recorded. To make the neural network’s decision-making mechanism transparent, a dual-validation explainability framework comprising Shapley Additive Explanations (SHAP) and Permutation Feature Importance analyses was employed. By quantifying the relative contributions of the experimental parameters to the model predictions, this approach revealed that the UV–Vis measurement wavelength was the dominant predictive variable, followed by the Mn doping ratio and reaction time. This study presents a transparent methodology that offers both strong predictive capability and physically grounded data to shed light on the complex interactions in doped semiconductor photocatalysts. Full article

Hydrogen is a promising carbon-neutral fuel for future internal combustion engines due to its wide flammability range, high flame speed, and absence of carbon-based emissions. However, its high reactivity significantly increases susceptibility to abnormal combustion phenomena such as knock and pre-ignition, which can compromise engine efficiency, durability, and operational stability. Accurate detection and characterization of knock in hydrogen-fueled spark-ignition engines remain challenging due to the highly transient, broadband, and cycle-dependent nature of abnormal combustion-induced pressure oscillations. Conventional knock indicators based solely on time-domain pressure oscillations or fixed-band frequency analysis are limited in their ability to capture transient resonance behavior and cyclic variability. This study presents an integrated frequency- and time–frequency-domain methodology for knock detection using high-resolution in-cylinder pressure data acquired from a single-cylinder research engine operating under hydrogen port fuel injection (PFI). A discrete Fast Fourier Transform (DFFT) approach applied at stationary points of dynamically windowed pressure signals enables accurate identification of dominant resonance modes while minimizing spectral leakage. A Gaussian-based adaptive windowing strategy is introduced to capture combustion-driven cyclic variations more effectively. Short-Time Fourier Transform (STFT) and sum-based spectral analysis further provide detailed time–frequency localization of transient knock events. The proposed methodology demonstrates a clear separation between normal combustion and knock conditions, enabling reliable cycle-by-cycle identification of abnormal combustion events under varying operating conditions. The experimentally observed resonance frequencies are validated against theoretical predictions using Draper’s acoustic resonance equation, supporting the physical interpretation of knock-induced pressure oscillations. The results demonstrate that the proposed adaptive spectral methodology significantly improves knock detection accuracy compared to conventional indicators and provides a robust framework for advanced knock diagnostics, engine calibration, and combustion control in hydrogen-fueled engines. Full article

Knee Osteoarthritis (KOA) is a leading contributor to global physical disability, where delayed diagnosis often results in irreversible joint damage and socio-economic cost. Early diagnosis remains challenging due to subtle radiographic biomarkers and limited access to specialized expertise, particularly in distributed healthcare settings. Within the evolving landscape of the Future Internet, characterized by Internet of Medical Things (IoMT), edge–cloud computing, and intelligent digital health infrastructures, there is an increasing demand for scalable, low-latency, and explainable AI-driven diagnostic solutions. In this work, we propose a Dual-Stream Wavelet Fusion Network (DS-WFN) alongside a distributed edge-cloud architectural roadmap tailored for deployment in distributed and edge-enabled healthcare ecosystems. The framework integrates a spatial morphological stream with a spectral wavelet stream, augmented by an Adaptive Wavelet Selection Mechanism (AWSM). The AWSM dynamically selects optimal frequency bases (Haar, Symlet, Daubechies) to preserve fine-grained diagnostic features typically lost in conventional CNN architectures. An Adaptive Spatial Alignment (ASA) module further ensures efficient fusion of heterogeneous representations, enabling robust feature integration across computational nodes. Experimental results across a five-fold patient-isolated cross-validation protocol demonstrate that the DS-WFN achieves a mean classification accuracy of 76.3% (95% CI: 71.6–80.8%) and a macro-averaged F1-score of 0.747 (95% CI: 0.697–0.795), consistently outperforming single-stream baselines while preventing patient-level data leakage. Furthermore, Grad-CAM visualizations provide interpretable outputs aligned with clinical diagnostic criteria, supporting trustworthy AI integration into digital healthcare workflows. Furthermore, we disclose a methodological framework for edge-based implementation, highlighting how localized inference ensures data sovereignty and real-time clinical support. By combining multiscale signal processing with deep learning under a Future Internet paradigm, this work contributes a scalable, explainable, and edge-ready diagnostic framework for early KOA detection, enabling intelligent, connected, and resource-efficient healthcare services. Full article

Yield estimation in sugarcane systems remains a major challenge in tropical regions due to the reliance on destructive, labor-intensive, and spatially limited field measurements. Although remote sensing has been widely used for crop monitoring, its predictive performance is often constrained when spectral information is used in isolation. This study proposes a data fusion framework integrating multitemporal Sentinel-2 spectral bands with meteorological variables to improve sugarcane biomass prediction under tropical conditions. A commercial field was monitored throughout the 2022–2023 growing season, and machine learning models, including random forest (RF), support vector machine (SVM), and multiple linear regression (MLR), were developed to estimate stem, foliage, and total biomass. To reduce potential spatial data leakage caused by spatial autocorrelation within the field, model performance was evaluated using Spatial Block Cross-Validation. Results showed that integrating spectral and meteorological data consistently improved predictive performance compared to spectral-only and weather-only scenarios. Spectral bands exhibited stronger relationships with biomass than derived vegetation indices, while maximum temperature and solar radiation were identified as key drivers of biomass variability. RF combined with spectral–weather fusion achieved the highest predictive performance, reaching R² values up to 0.95, RMSE values as low as 5296.35, and rRMSE values close to 18% for stem biomass, consistently outperforming SVM and MLR. In contrast, spectral-only scenarios produced lower predictive accuracy and higher prediction errors across all biomass variables. This study provides one of the first field-scale implementations under humid tropical conditions in southeastern Mexico, where georeferenced yield data remain scarce. Full article

Induction motors are critical in modern industry, powering over 70% of industrial processes. Reliable operation is essential to minimize downtime and ensure production continuity. This paper proposes an integrated multimodal methodology for fault diagnosis and prognosis in induction motors, based on an extended Pearson and Gain feature fusion framework. The approach preprocesses vibration, current, voltage, torque, and speed signals through denoising, normalization, synchronization, and sliding-window segmentation. Over 200 features per window are extracted across time, frequency, envelope, wavelet, harmonic, slip-based, and MCSA domains. A key innovation is correlation-driven multimodal fusion, combining Pearson correlation, spectral coherence, cross-spectral energy, and mutual information to produce Gain-enhanced features with improved discriminative capability. Fault diagnosis is performed using RF, SVM, XGBoost, and MLP models, with time-aware data splitting to avoid temporal leakage. Prognosis employs a continuous Degradation Index (DI) modeled via Gaussian Process Regression for uncertainty-aware prediction, with failure probability and Remaining Useful Life (RUL) estimated from DI thresholds. Experimental results demonstrate that the proposed methodology achieves diagnostic accuracy above 97%, enhances feature relevance, and provides stable long-term prognostic performance, offering a robust framework for predictive maintenance of induction motors. Full article

Frequency-hopping (FH) signals appear as small rectangular pulses in time-frequency spectrograms. At low signal-to-noise ratios (SNRs), noise along the frequency axis, caused by short-time Fourier transform (STFT) spectral leakage, blurs pulse boundaries, while the varying scales of hop rectangles exceed the capacity of a single receptive field. This paper presents YOLO11-FH, a modified YOLO11 detector that introduces two signal-processing-motivated modules. A FreqSmoothBlock (FSB) uses a $(3,1)$ depthwise convolution to smooth exclusively along the frequency axis, while adding only $5C$ parameters. A TFMultiResBlock (TFMRB) fuses three parallel dilated convolution branches (dilation rates of 1, 2, and 3) to cover different hop scales, replacing a heavier C3k2 module. The detection head is further simplified by halving the Bottleneck repeat count and disabling the deep submodule at the P5 scale. On a simulated FH dataset (SNRs ranging from $-15$ dB to $-10$ dB, five jamming types), YOLO11-FH achieves 96.04% mean average precision (mAP)@0.5 and 76.18% mAP@0.5:0.95, outperforming the YOLO11n baseline by 0.95 and 2.91 percentage points (pp) with 2.9% fewer parameters. Full article

This study used UV-Vis absorption spectroscopy to investigate the interactions of flavonoids—baicalein (with ortho-dihydroxyl on the A-ring) and apigenin (with 4′-monohydroxyl on the B-ring)—with metal ions (Co²⁺, Ce⁴⁺) and membrane–mimetic systems (CTAB/SDS micelles, liposomes, vesicles). It revealed how flavonoid spectral properties related to molecular structure and microenvironment. Key findings were as follows: pH affected absorption spectra by altering phenolic hydroxyl protonation. Metal chelation depended on hydroxyl position: baicalein’s A-ring ortho-dihydroxyl formed a stable charge-transfer complex with Cu²⁺. In acidic medium, apigenin reduced Ce(IV) more effectively than baicalein, which contradicted the classic antioxidant role of ortho-dihydroxyl groups. This showed that reaction microenvironments could change hydroxyl reactivity and electron transfer paths. Membrane–mimetic systems (liposomes/vesicles) raised apparent pKa, enhanced solubility and stability. The study first quantified distinct ΔpKa values for different flavonoids (e.g., quercetin vs. baicalein), which were linked to intramolecular H-bonding and membrane preference. Quercetin’s B-ring ortho-dihydroxyl enabled the formation of hydrophobic interfacial anions in nanocarriers under alkaline pH, ensuring high stability. Kaempferol showed sustained leakage. These findings provided a basis for structure-guided flavonoid carrier design, bioavailability, and antioxidant delivery. By integrating reaction microenvironment, membrane interface effects, and carrier stability, this work clarified flavonoid bioactivity mechanisms and supported targeted delivery strategies. Full article

Accurate instance segmentation of oranges in complex orchard environments is crucial for obtaining clean regions of interest (ROIs). Coarse region extraction may include non-target pixels from leaves, shadows, background, and adjacent fruits, thereby increasing boundary pixel mixing in subsequent hyperspectral-assisted observation. This study proposes an improved lightweight YOLO11n-Seg method as an RGB-based visual front-end for cleaner single-fruit ROI extraction. Its contribution lies in the task-oriented integration of three complementary components: a Local Deformable Convolution Backbone (LDC-Backbone) for representing irregular and occluded fruit contours, a Boundary-Guided GSConv (BG-GSConv) module for efficiently fusing shallow boundary details with deep semantic features, and an ROI-Purity-Oriented Dice Boundary Loss for constraining mask integrity and boundary adherence. Evaluated on a complex orchard dataset, the improved model achieved a Mask mAP@0.5 of 0.962, a Mask mAP@0.5:0.95 of 0.692, a Box mAP@0.5 of 0.942, and an inference speed of 101 FPS with 3.20 M parameters. Background leakage analysis further showed that the proposed model reduced the inclusion of non-fruit pixels in extracted ROIs, supporting cleaner mask-based single-fruit region extraction. Preliminary ROI-based reflectance observation indicated that the reflectance curves obtained from the improved-model ROIs were closer to those of manually referenced pure ROIs than those obtained from the baseline extraction. These results suggest that the proposed method can serve as a real-time RGB-based front-end for cleaner single-fruit ROI extraction and later hyperspectral-assisted sampling. Complete closed-loop spectral quality modeling with paired RGB–HSI data remains a direction for future work. Full article

Hyperspectral anomaly detection (HAD) aims to identify rare targets without relying on prior target knowledge. However, background spectra in hyperspectral images often lie on highly complex and nonlinear manifolds, making accurate modeling challenging. Although models with strong nonlinear approximation capabilities, such as Kolmogorov–Arnold Networks (KANs), provide a promising solution for capturing such complexity, self-supervised reconstruction-based HAD methods still suffer from a fundamental issue known as anomaly leakage. When the model has high representation capacity, anomalous signatures tend to be partially reconstructed, which reduces residual contrast and degrades detection performance. To address this issue, we propose a Blind-Spot KAN-based background reconstruction network with prior purification (BKP-Net), which mitigates anomaly leakage from both data and model perspectives. Specifically, we first introduce a Background Prior Purification (BPP) module to construct a cleaner background prior. This module suppresses and replaces potential outlier pixels through spatial clustering and robust weighted mean estimation. We then design a Blind-Spot KAN-based Reconstruction backbone (BKCN) to model complex nonlinear background characteristics while preventing direct information flow from the center pixel, thereby reducing anomaly leakage during reconstruction. In addition, separable convolutions are employed to enhance spatial–spectral feature representation, followed by an attention-guided fusion mechanism to suppress cross-domain interference. Furthermore, a band-wise Guided Reconstruction Refinement (GRR) strategy is introduced in the detection phase to improve structural consistency between the reconstructed background and the original hyperspectral image, leading to more reliable anomaly discrimination. Experimental results on four hyperspectral datasets demonstrate that the proposed method achieves competitive performance compared with several representative traditional and deep learning-based detectors. Full article

GaN-on-Si light-emitting devices have been widely studied in the field of opto-electronics, while their optical performance and characterization accessibility are severely limited by the strong visible light absorption of the native silicon substrate. Conventional substrate transfer technologies often suffer from inherent thermal, optical, or mechanical bottlenecks. In this study, we developed a robust wafer-level substrate transfer strategy for 8-inch green GaN-on-Si light-emitting device wafers, utilizing a hybrid planarization process combined with SiO₂–SiO₂ direct bonding. The hybrid planarization precisely eliminated the 900 nm macroscopic steps, achieving sub-nanometer surface roughness for high-yield wafer bonding. We systematically investigated the physical evolution during substrate removal. Results indicate that the removal of the thick native silicon and high-stress buffer layers effectively released the additional in-plane biaxial compressive stress within the multiple quantum wells (MQWs), thereby mitigating the quantum-confined Stark effect (QCSE). Benefiting from the elimination of the light-absorbing silicon substrate and the incorporation of a built-in back-surface reflector (BSR), the transferred devices achieved a remarkable 1.9-fold enhancement in relative optical performance, albeit with an inherent trade-off of increased reverse leakage current while preserving basic diode functionality. Furthermore, optothermal dynamic analysis at high injection levels suggests a potential localized thermal bottleneck at the thick SiO₂ bonding interface, where a hypothesized heat-induced spectral red shift may counteract the carrier-screening blue shift. This work provides a feasible wafer-level substrate transfer process for GaN-on-Si devices and offers systematic experimental insights into stress relaxation and optothermal behaviors during the substrate transfer process. Full article

Major depressive disorder remains difficult to diagnose objectively, as routine assessment is still largely dependent on clinical interview and rating scales. Resting-state electroencephalography (EEG) is an attractive complementary modality because it is non-invasive, low-cost, and compatible with wearable sensing, but many reported EEG classification results are weakened by segment-level leakage and unclear subject identity handling. This study evaluates whether depression can be distinguished from healthy controls using a compact eight-channel resting-state EEG configuration under a strictly leakage-free subject-wise protocol. Using a widely used public EEG dataset, we first corrected a previously overlooked subject-identity ambiguity by constructing a class-aware composite key, yielding 56 valid unique participants. We then applied ten repeated subject-wise holdout splits and compared five compact baselines spanning Extra Trees and a multi-layer perceptron on asymmetry-aware spectral features and three convolutional networks on raw signals, including the EEG-specific EEGNet and ShallowConvNet architectures. Uncertainty was quantified through 95% bootstrap confidence intervals of the mean across repeats. The best model, an Extra Trees classifier using eight-channel spectral and asymmetry features, achieved a mean balanced accuracy of 93.5% with a 95% bootstrap confidence interval of 89.6% to 96.8% and a mean area under the receiver operating characteristic curve of 98.6% with a 95% bootstrap confidence interval of 96.2% to 100.0%. A connectivity ablation showed that inter-channel coherence was informative in isolation but did not improve performance when naively fused with spectral features. A feature-selection ablation did not show evidence that the 90-dimensional spectral representation was dominated by noisy or uninformative dimensions under this evaluation protocol. These results support compact, subject-wise evaluated EEG screening pipelines while highlighting the importance of rigorous leakage control. Full article

The output voltage harmonics of electric vehicle (EV) charging converters directly affect grid power quality. This paper proposes a harmonic analysis method based on geometric algebra (GA), which employs a multivector representation of signals and least squares estimation to accurately extract fundamental, integer-order, and inter-harmonics. A coupling coefficient is defined to quantify the phase correlation between frequency components. Based on measured data, harmonic characteristics under four typical operating conditions are analyzed, and an adaptive PID controller is designed to dynamically adjust the virtual resistance for harmonic suppression. The results show that the GA method significantly reduces spectral leakage under non-integer-period sampling conditions, with amplitude estimation errors below ±2%. The total harmonic distortion (THD) decreases with increasing active power and increases with reactive power injection. The droop coefficient exhibits a non-monotonic effect, while reducing the proportional gain raises the THD. Adaptive control reduces the average THD by 14.0–28.5% with a total response time of less than 0.05 s. The coupling coefficient $C_{13}$ is strongly positively correlated with THD and negatively correlated with the maximum Lyapunov exponent computed using the Rosenstein small-data method (correlation coefficient −0.85), confirming the intrinsic relationship between coupling and stability. Compared with fast Fourier transform (FFT) and other methods, GA achieves higher accuracy under short data records and non-integer-period sampling. This paper provides a complete theoretical framework and engineering solution for harmonic suppression in charging converters. Full article

Leak localization and maintenance in water distribution networks (WDNs) are essential for reducing water losses and operating costs; however, they usually require extensive monitoring and large datasets. This work proposes a methodology that combines topological sectorization of a hydraulic node network and deep learning techniques to improve leak location by selecting representative nodes to reduce the spatial dimensionality of the WDNs. The network is partitioned using a Spectral Clustering algorithm to identify key nodes based on a weighted criterion that considers pressure variability, flow rate, and proximity to the centroid. Subsequently, a Bidirectional Long Short-Term Memory (Bi-LSTM) neural network classifies the cluster and sub-cluster where a leak occurs, using pressure and flow time series simulated in EPANET. This methodology was validated on the L-Town network, achieving an accuracy of 99.94% for cluster classification and 99.82% for sub-clusters, with a validation loss of 0.024%. During validation with 117 unseen leakage scenarios, the model reached an overall effectiveness of 85%. Moreover, Spectral Clustering outperformed K-Means in preserving physical connectivity. These results confirm the efficiency of the proposed methodology and highlight its potential for application in other hydraulic networks. Full article