Search Results (571)

A reactive agent operating in a complex environment must classify its perceived state and select an action under uncertainty. This uncertainty may arise from sensor noise, ambiguous perceptual configurations, or the limited separability of the action regions induced by the agent’s policy. We propose a hybrid classical–quantum architecture for a reactive agent in which the perceived state, represented as a classical sensor vector, is mapped onto a quantum feature space. In this space, learned conceptualizations or rule-defined perceptual regions are represented as reference states, and similarities between the current perception and such references are used to support action selection. The architecture is evaluated on a public wall-following robot dataset. Two implementations are considered: (i) a quantum-kernel classifier based on ZZ feature maps and (ii) an illustrative quantum circuit that explicitly encodes sensor conditions into qubits and performs measurement-based action selection. The experimental evaluation is intended as an offline proxy for reactive decision-making, not as a demonstration of a complete closed-loop robotic controller or of quantum advantage. The results show that the proposed framework can represent perceptual ambiguity and connect quantum-state measurement to the selection of discrete reactive actions. Full article

Background/Objectives: Epilepsy is a prevalent chronic neurological disorder, and electroencephalography (EEG) remains essential for its diagnosis and long-term monitoring. Although deep learning-based automatic seizure detection has advanced considerably, existing models typically require extensive parameters and computational resources, limiting their deployment on resource-constrained platforms. Methods: In this study, we propose CosFNet, a hybrid lightweight architecture integrating cosine convolution with an FNet encoder, a Fourier-transform-based token-mixing encoder. The cosine convolution frontend parameterizes convolutional kernels with the cosine function to efficiently capture local spatiotemporal features. The FNet backend replaces traditional self-attention with a parameter-free two-dimensional discrete Fourier transform, enabling global mixing across temporal tokens and hidden feature dimensions with fast Fourier transform-based efficiency. With these advances, the model contains only 19,458 learnable parameters. Results: On the publicly available CHB-MIT dataset, CosFNet achieves a mean segment-level sensitivity of 97.60%, a specificity of 97.12%, an event-level sensitivity of 98.59%, a false detection rate (FDR) of 0.82/h, and an area under the receiver operating characteristic curve (AUC) of 97.87%. On our collected SH-SDU dataset, it attains a mean sensitivity of 92.87%, specificity of 94.74%, an event-level sensitivity of 99.41%, and an AUC of 96.29%. Conclusions: CosFNet achieves competitive detection performance with significantly low complexity, offering a viable pathway toward clinical deployment in resource-limited environments. Full article

Background: Breast cancer remains a leading cause of cancer-related mortality, and reliable computational decision support is increasingly viewed as a complement to expert pathological assessment rather than a replacement for it. Variational quantum classifiers (VQCs) and Quantum Support Vector Machines (QSVMs) have recently been promoted as candidate models for medical classification, yet most published comparisons rely on internal hold-out validation alone and report only a single point estimate of discrimination, omitting calibration, decision-analytic value, and explainability—three ingredients that any clinically credible model must furnish. Methods: We assembled a complete quantum–classical machine learning pipeline and evaluated it under a deliberately stringent protocol designed to expose, rather than conceal, the limitations of current Noisy Intermediate-Scale Quantum (NISQ)-era models. The analytical hypothesis was conservative and stated in advance; in light of saturated classical baselines on this benchmark, we did not anticipate a quantum advantage in raw discrimination, and we framed the study as a methodological probe rather than as a competition. Using the Wisconsin Diagnostic Breast Cancer (WDBC) dataset (n = 569) for development and an independent Wisconsin Original (WBC) cohort (n = 683) for external validation, we benchmarked five classical learners (XGBoost, LightGBM, CatBoost, RandomForest, RBF-SVM), two quantum models (an eight-qubit VQC implemented in PennyLane and a ZZ-feature-map QSVM implemented in Qiskit), and a stacked hybrid ensemble. The evaluation framework combined Optuna-driven hyperparameter optimisation, internal–external cross-validation, and external validation on the independent WBC cohort. Robustness and interpretability were then probed through circuit depth and embedding rotation ablation, depolarising noise stress tests, learning curve and feature stability analysis, decision curve analysis, and dual SHAP-based explanations covering both a direct tree-based explanation and a quantum surrogate. Reporting followed the TRIPOD + AI guideline. Results: On the internal test partition, RBF-SVM achieved the highest discrimination (AUC = 0.998), with XGBoost, LightGBM, CatBoost, the hybrid ensemble, and the VQC clustering between 0.992 and 0.996; the QSVM with a ZZ-fidelity kernel underperformed substantially (AUC = 0.727). Pairwise tests for correlated ROC curves indicated that most differences among top models were not statistically significant. On the external WBC cohort, model rankings reorganised, as RBF-SVM (AUC = 0.986, 95% CI 0.946–0.997), RandomForest (0.985, 95% CI 0.945–0.996), VQC (0.983, 95% CI 0.942–0.995), and the hybrid ensemble (0.982, 95% CI 0.941–0.995) all retained near-ceiling discrimination with extensively overlapping confidence intervals. Ablation analysis demonstrated that the choice of embedding rotation is decisive—Z-rotation embeddings collapsed VQC performance to chance levels (AUC ≈ 0.50), whereas X- and Y-rotations preserved it. Depolarising noise up to p = 0.10 had a negligible effect on the VQC, and SHAP analyses converged on worst concave points, mean concave points, and worst area as the dominant predictors across both classical and quantum models. Decision curve analysis showed positive net benefit for both classical and hybrid models across the clinically meaningful threshold range, exceeding both the treat-all and treat-none reference strategies throughout. Conclusions: In the present regime, the principal contribution of QML is not raw discrimination—modern classical learners are already at the data ceiling—but the construction of a rigorous, reproducible, externally validated, and interpretable benchmarking framework in which quantum models can be fairly compared with their classical counterparts. Because evaluation was confined to curated benchmark datasets rather than real-world clinical populations, the interpretability and net benefit findings reported here should be read as benchmark-level evidence and not as a demonstration of readiness for clinical deployment. Full article

Maize seed quality and kernel morphological traits are important determinants of grain utilization and are influenced by both genetic factors and growing-season conditions. This study evaluated the stability of seed quality and kernel morphological traits in two commercial maize hybrids (Costanza and LG 3535) across four growing seasons, three row spacing systems, and two plant density levels. Seed quality traits (protein, fat, ash, starch, crude fiber, and moisture content) and kernel morphological traits (length, width, and thickness) were evaluated using univariate and multivariate statistical analyses. Significant effects of hybrid, growing season, row spacing, and their interactions were detected for most evaluated traits. Growing-season variability influenced seed composition and kernel morphology, while row spacing and plant density further contributed to trait expression. Costanza exhibited greater stability for most traits, particularly starch content and kernel morphology, whereas LG 3535 showed more variable responses across growing seasons and row spacing combinations. Correlation and multivariate analyses revealed strong associations among starch content, kernel width, and kernel thickness, whereas protein, ash, and crude fiber were less closely associated with kernel size traits. These findings demonstrate the importance of hybrid × growing-season interactions in shaping maize kernel characteristics and highlight the value of multi-environment evaluation for identifying hybrids with stable kernel quality traits under Mediterranean production conditions. Full article

Photoacoustic spectroscopy (PAS) is a highly sensitive and non-destructive technique widely used for trace gas detection; however, the simultaneous quantification of methane (CH₄), ethane (C₂H₆), and ethylene (C₂H₄) remains challenging due to severe spectral cross-interference and non-linear responses across broad concentration ranges. In this work, we propose a high-precision, end-to-end detection framework based on a Deep Kernel Extreme Learning Machine (DKELM) optimized using a Mutation–Chaotic Particle Swarm Optimization (MCPSO) algorithm. To enhance diagnostic information in the photoacoustic signals, a multi-scale wavelet transform based on a db4 wavelet basis with 5-layer decomposition and a Heursure soft threshold strategy is first employed for denoising and enhancing absorption features. To address the hyperparameter sensitivity and local-optimum trapping inherent in deep models, the MCPSO algorithm integrates hybrid chaotic initialization, adaptive mutation probability control, Cauchy-based perturbation, temperature-controlled mutation amplitude, and elite-guided population updating. The proposed MCPSO-DKELM model is evaluated on an expanded dataset of 470 mixed-gas spectra and benchmarked against other frameworks, including the previously reported SVM-CPSO-KELM architecture. The experimental results demonstrate that MCPSO-DKELM achieves stable, segmentation-free quantification across the full dynamic range, with an average detection error below 3.5% and the maximum relative error constrained to under 15%, which represents a substantial improvement over existing approaches. Thus, the combination of deep kernel feature extraction and mutation–chaotic global optimization provides a robust and reliable solution for simultaneous multi-component hydrocarbon gas analysis in complex industrial environments. Full article

Hybrid RF-FSO-THz communication systems are promising candidates for future Internet of Things (IoT) and 6G networks because they combine the robustness of radio frequency links, the high-capacity potential of Free-Space Optical communications, and the ultra-wideband capabilities of terahertz transmission. Adaptive channel selection in such systems depends on multiple correlated environmental and physical-layer variables, including distance, rain intensity, humidity, visibility, turbulence strength, signal-to-noise ratio, channel capacity, and energy-efficiency metrics. This paper presents a physics-supported benchmark framework for supervised adaptive channel selection in hybrid RF-FSO-THz systems and systematically investigates the impact of linear and nonlinear dimensionality-reduction techniques on predictive performance, statistical robustness, computational complexity, and physical interpretability. A multi-scenario dataset comprising 5000 samples was generated using calibrated RF, FSO, and THz propagation models under clear, rain, fog, and worst-case environmental conditions. Principal Component Analysis (PCA) and Kernel PCA were evaluated together with Random Forest, Support Vector Machines (SVMs), XGBoost, Gradient Boosting (GB), Multi-Layer Perceptron (MLP), Logistic Regression, and Decision Trees. The results demonstrate that PCA preserves nearly all predictive capabilities while reducing the original 33-dimensional feature space by approximately 81.8%, maintaining accuracies close to 97–98% with the best-performing classifiers. Statistical significance analysis confirms that PCA introduces only modest degradations, whereas Kernel PCA consistently reduces the predictive performance while increasing memory requirements and inference latency. Additional environmental-only validation experiments indicate that adaptive channel selection remains highly learnable even when only pre-selection environmental descriptors are available, partially mitigating concerns regarding self-consistency bias. Overall, the results suggest that PCA provides an advantageous compromise among predictive accuracy, computational efficiency, statistical robustness, and physical interpretability for supervised adaptive channel selection in physics-supported hybrid wireless communication systems. Full article

The digital transformation of agrifood systems demands an integrated infrastructure to ensure traceability, trust, and intelligent decision-making across complex and heterogeneous value chains. METROFOOD-IT, a large-scale national research infrastructure in food metrology aligned with the ESFRI METROFOOD-RI, addresses these challenges by combining advanced experimental facilities with a comprehensive digital ecosystem. This paper focuses on the IT kernel of METROFOOD-IT and presents an integrated architectural model that brings together four key technological paradigms: data acquisition through Internet of Things (IoT) and laboratory infrastructures, an Open Data Platform for interoperability and sharing, blockchain-based notarization for integrity and provenance, and Artificial Intelligence (AI) for knowledge extraction and decision support. Rather than describing these components in isolation, the paper abstracts from their implementation within the Italian National Recovery and Resilience Plan (NRRP) project METROFOOD-IT to distill a coherent and reusable architectural pattern in which data management, trust enforcement, and intelligent analytics are tightly coupled. Five explicit design principles are identified and articulated: federated data with centralized metadata, selective on-chain anchoring, user-unobtrusive trust infrastructure, explainability as a first-class architectural concern, and machine learning as the backbone of decision-making. Two empirical case studies—one centered on explainable AI for hyperspectral crop nitrogen assessment and the other on IoT-driven sustainable agriculture monitoring secured by distributed ledger technology—serve a dual role: they motivate and shape the architectural pattern, and they exemplify the operational regimes the resulting design supports. A reference deployment on the Ethereum Sepolia public test network, grounded on an IBM Power E1050 and IBM Storage Scale enterprise substrate, provides quantitative evidence for the proposed hybrid on-chain/off-chain pattern with streaming hash-only notarization. The architecture illustrates how research infrastructures can evolve into integrated digital platforms that enable transparent, verifiable, and scalable agrifood systems, and offers a foundation for generalizable design principles in data-intensive and trust-sensitive settings. Full article

Monitoring genetic gain is critical for evaluating breeding program performance. This study assessed genetic trends in the Zambia national maize breeding program using historical data (2001–2017) from 2225 hybrids tested across years and locations. Best linear unbiased estimates (BLUEs) were calculated, and genetic trends were determined by regressing entry means on first-year testing data. Mean heritability was moderate for grain yield, plant height, and ear height, and high for anthesis and silking dates, indicating strong reliability for flowering traits. Significant positive genetic gains were observed for most traits except days to silking. Grain yield (GY) increased at 0.021 t ha⁻¹ per year (0.85% annually), reflecting progress but remaining below levels required to meet regional future production demands. Plant and ear height increased by more than 1.3 cm annually, suggesting directional selection for taller plant architecture. Grain texture declined by 1.28% per year, indicating a shift toward flint-type kernels. Anthesis date and ears per plant showed minimal genetic variation. Regression models explained more than 15% of the total variation in plant height, ear height, ear number, and grain texture, confirming consistent genetic progress. Although measurable gains were achieved, the study’s baseline indicates that accelerating yield improvement will require rapid-cycle breeding, enhanced trait heritability, modern breeding tools, and a strategic reallocation of resources to sustain long-term impact. Full article

Selecting suitable maize hybrids and appropriately increasing planting density is a crucial strategy for improving maize yield under subsurface drip irrigation. A two-year field experiment was conducted to assess the impacts of two maize hybrids (Zhengdan 958, ZD958; Jingke 968, JK968) and four planting densities of 60,000 (PD1), 75,000 (PD2), 90,000 (PD3), and 105,000 plants ha⁻¹ (PD4), on maize growth indices, ear leaf photosynthetic parameters, nitrogen content, grain yield, and yield components. The results indicated that with increasing planting density, the plant height of ZD958 initially increased and then decreased, whereas that of JK968 continued to increase. The leaf area index of both hybrids consistently increased, while stem diameter, rind puncture strength, and stalk breaking strength gradually decreased. Dry matter accumulation initially increased and then decreased, peaking at PD3. Ear leaf nitrogen content, relative chlorophyll content, net photosynthetic rate, and stomatal conductance all decreased with increasing planting density, while intrinsic water use efficiency (iWUE) first increased and then declined, reaching its maximum at PD3. Notably, iWUE of JK968 was significantly higher than that of ZD958 during the dough stage (p < 0.01). Ear traits, including ear length, ear diameter, kernels per ear, and grain weight per ear, all decreased continuously with increasing planting density. Grain yield followed a unimodal curve, peaking at the PD3 treatment, with two-year average yields of 12.7 and 13.5 t ha⁻¹ for ZD958 and JK968, respectively. JK968 exhibited significantly higher leaf area index, stem diameter, rind puncture strength, stalk breaking strength, ear length, kernels per ear, grain weight per ear, and grain yield compared to ZD958 (p < 0.01), demonstrating superior tolerance to high planting density and enhanced source–sink coordination. In conclusion, in the North China Plain, JK968 planted at a density of 90,000 plants ha⁻¹ can synergistically optimize population structure, improve stalk mechanical strength, and enhance photosynthetic efficiency, under subsurface drip irrigation. Full article

Currency recognition is a vital pillar for the financial independence of visually impaired individuals, yet existing solutions often struggle with the trade-off between architectural complexity and real-time performance. This paper introduces a lightweight hybrid framework specifically engineered for Saudi Riyal banknote identification. The primary contribution lies in the strategic integration of MobileNetV2 for deep feature extraction with a kernel-based Support Vector Machine to enhance classification boundaries. Furthermore, this study addresses a significant data gap by curating an updated dataset that includes the 20 SR denomination, which is largely missing from current public repositories. Methodologically, the framework emphasizes computational efficiency without compromising precision, achieving a robust test accuracy of 98.16. By prioritizing a streamlined architecture, this work provides a scalable and effective solution for mobile-based assistive technologies, fostering greater accessibility and autonomy for the visually impaired community in Saudi Arabia. Full article

To address the issues of severe noise interference, limited classification capability of linear classifiers, and difficulty in adaptively optimizing classifier parameters in rolling bearing fault diagnosis, this paper proposes a hybrid diagnostic model integrating the multi−scale convolutional neural network and rime ice optimization algorithm optimized kernel extreme learning machine. The method first employs the synchrosqueezed wavelet transform to convert raw vibration signals into high−resolution time−frequency images, effectively enhancing the visualization of fault impact features. Then, the multi−scale convolutional neural network is used to extract preliminary features from the time−frequency images, and the kernel extreme learning machine is introduced to replace the Softmax linear classifier in traditional convolutional neural networks, thereby constructing a nonlinear decision boundary to more effectively separate complex fault patterns. Finally, the rime algorithm is introduced to optimize the regularization coefficient and kernel parameters of the kernel extreme learning machine, enabling the kernel extreme learning machine to perform fault classification with an optimal nonlinear decision boundary. Experimental results on the bearing datasets from Huazhong University of Science and Technology and Case Western Reserve University show that the proposed method achieves classification accuracies of 99.75% and 99.83%, respectively, outperforming several comparison models. Furthermore, noise robustness experiments demonstrate that the proposed model maintains an accuracy of approximately 90% under low signal−to−noise ratio (SNR) conditions, outperforming all comparison models and demonstrating high classification accuracy under strong noise. Full article

High-Frequency Trading (HFT) dashboards require rapid reception, aggregation, and visualization of order book and trade update streams that may arrive at multi-million message rates. Conventional CPU-based and CPU-GPU hybrid visualization pipelines can suffer from significant delays during periods of burst due to CPU-mediated rendering, synchronization, kernel launch overhead, and copies on the host. This paper presents a visualization pipeline that is entirely resident on the graphics processor with zero-copy access to NIC accessible pinned buffers, persistent CUDA processing, fused stage execution of the parse-aggregate pipeline, and persistent CUDA OpenGL buffer interoperation. The goal is not to reach production status but rather to see whether host-to-host data movement can be decreased and whether the stages of GPU processing can be consolidated to improve latency, throughput and frame cadence in controlled HFT-style workloads. The evaluated workstation achieved a mean ingest-to-pixel latency of 6.3 ms using the proposed design compared to 29.4 ms for the current design, with sustained throughput of 10.2 million messages per second, which is 20 times greater than the current design, and a steady-state range of 185 to 192 frames per second with a burst floor of 178 frames per second for the proposed design. The improvement observed can be attributed to both the zero-copy ingestion and fused persistent kernel execution. Based on the obtained results, the proposed method of use of this technique in the implementation of real-time financial visualization under the proposed conditions is possible. More general testing is still required on other NICs, other generations of GPUs and PCIe configurations, workload traces, and actual exchange feeds. Full article

Hybrid snakehead (Channa argus × Channa maculata) is a major cultured freshwater fish in China, but standardized health monitoring using serum biochemistry is limited by the lack of species-specific reference intervals. This study established reference intervals for 20 serum biochemical parameters in hybrid snakehead reared under 27 °C for 90 days. The body weights of the sampled fish ranged from 50 g to 160 g and were exempted from diseases by health check. All parameters were measured using an automated analyzer with commercial reagent kits. Most parameters exhibited non-normal, right-skewed distributions, and only total protein (TP) was normally distributed. Smoothed bootstrap resampling and kernel density estimation were applied to extract the main peak distribution and reduce bias from outliers and long tails. Species-specific reference intervals were established based on the main peak data, providing more reliable physiological baselines than conventional percentiles. Correlation analysis revealed coordinated changes among liver function, nutrient metabolism, tissue damage, and digestive enzymes. These results provide a standardized tool for health assessment, subclinical disease diagnosis, and comparative analysis in juvenile hybrid snakehead maintained at an optimal temperature in indoor mesocosm systems. Full article

Maize is one of the most important agricultural crops worldwide, due to its high production potential and the multiple uses of its products. In the context of the need to maintain high yields and preserve soil fertility, the use of green manures together with mineral fertilizers can represent a sustainable solution. For this purpose, during the period 2024–2025, at the Turda Agricultural Research and Development Station (Cluj, Romania), a field experiment was carried out to evaluate the effect of two cover crops used as green manures, white lupin (Lupinus albus) and phacelia (Phacelia sp.), on the Turda 344 maize hybrid. Within each agrofund (classical, after lupin, and after phacelia), five fertilization variants were tested, consisting of basic fertilization and the supplementary application of mineral fertilizers and biostimulants. The results highlighted the major influence of climatic conditions on yield and grain quality, with the experimental year having a significant effect on the main parameters analyzed. In 2024, under basic fertilization, lupin and phacelia increased grain yield by 8.0% and 1.4%, respectively, compared with the classic agrofund, while in 2025, phacelia maintained a yield advantage of 1.4%. The highest yields were obtained in 2025, when climatic conditions were more favorable, and additional fertilization with ammonium nitrate determined the highest values, reaching 9748 kg/ha in the phacelia agrofund (+6.3% compared with the basic fertilization), 9544 kg/ha in the lupine agrofund (+7.2%), and 9612 kg/ha in the classical agrofund (+6.3%). Additional nitrogen application also led to the highest values of thousand kernel weight, highlighting the essential role of nitrogen in the grain filling process. Grain quality analysis showed that variations in starch and protein content had an inverse evolution between the two experimental years, suggesting the influence of climatic conditions and nitrogen availability on grain composition. Full article

Deterministic radio wave propagation models provide high accuracy in complex outdoor environments but remain computationally impractical for large-scale network planning and spectrum management. In contrast, empirical and hybrid models offer low complexity at the expense of reduced accuracy, systematic bias, and limited terrain sensitivity. This paper proposes a unified delta learning framework that enhances fast baseline propagation models by learning a data-driven correction toward a deterministic Parabolic Equation Modeling (PEM) reference. A key novelty lies in a compact, physics-informed feature representation that replaces the full terrain profile with an 18-dimensional vector combining local geometric descriptors, global terrain characteristics, and baseline responses, enabling accurate correction with low-dimensional input. The study also provides the first systematic investigation of delta-based correction across multiple widely used propagation models. The framework is evaluated for free-space propagation, ITU-R P.1546, ITU-R P.1812, and ITU-R P.452 using ridge regression, kernel ridge regression, gradient boosting regression trees, and a neural network model. Model performance is assessed in terms of error reduction, bias mitigation, robustness across learning algorithms, and profile-level generalization to previously unseen propagation paths within the considered terrain categories. Results show substantial error reduction, with up to twofold improvement for simpler baseline models and consistent gains for hybrid models, while preserving computational efficiency. Full article