Search Results (3,526)

Quantum machine learning (QML) has emerged as a promising approach for enhancing image classification by exploiting quantum computational principles such as superposition and entanglement. However, practical applications on complex datasets like CIFAR-100 remain limited due to the low expressivity of shallow circuits and challenges in circuit optimization. In this study, we propose HQCNN–REGA—a novel hybrid quantum–classical convolutional neural network architecture that integrates data re-uploading and genetic algorithm optimization for improved performance. The data re-uploading mechanism allows classical inputs to be encoded multiple times into quantum states, enhancing the model’s capacity to learn complex visual features. In parallel, a genetic algorithm is employed to evolve the quantum circuit architecture by optimizing gate sequences, entanglement patterns, and layer configurations. This combination enables automatic discovery of efficient parameterized quantum circuits without manual tuning. Experiments on the MNIST and CIFAR-100 datasets demonstrate state-of-the-art performance for quantum models, with HQCNN–REGA outperforming existing quantum neural networks and approaching the accuracy of advanced classical architectures. In particular, we compare our model with classical convolutional baselines such as ResNet-18 to validate its effectiveness in real-world image classification tasks. Our results demonstrate the feasibility of scalable, high-performing quantum–classical systems and offer a viable path toward practical deployment of QML in computer vision applications, especially on noisy intermediate-scale quantum (NISQ) hardware. Full article

In the era of smart agriculture, accurate identification of plant species is critical for effective crop management, biodiversity monitoring, and the sustainable use of medicinal resources. However, existing deep learning approaches often underperform when applied to fine-grained plant classification tasks due to the lack of domain-specific, high-quality datasets and the limited representational capacity of traditional architectures. This study addresses these challenges by introducing a novel, well-curated leaf image dataset consisting of 39 classes of medicinal and aromatic plants collected from the Aromatic and Medicinal Plant Research Station in Odakkali, Kerala, India. To overcome performance bottlenecks observed with a baseline Convolutional Neural Network (CNN) that achieved only 44.94% accuracy, we progressively enhanced model performance through a series of architectural innovations. These included the use of a pre-trained VGG16 network, data augmentation techniques, and fine-tuning of deeper convolutional layers, followed by the integration of Squeeze-and-Excitation (SE) attention blocks. Ultimately, we propose a hybrid deep learning architecture that combines VGG16 with Batch Normalization, Gated Recurrent Units (GRUs), Transformer modules, and Dilated Convolutions. This final model achieved a peak validation accuracy of 95.24%, significantly outperforming several baseline models, such as custom CNN (44.94%), VGG-19 (59.49%), VGG-16 before augmentation (71.52%), Xception (85.44%), Inception v3 (87.97%), VGG-16 after data augumentation (89.24%), VGG-16 after fine-tuning (90.51%), MobileNetV2 (93.67), and VGG16 with SE block (94.94%). These results demonstrate superior capability in capturing both local textures and global morphological features. The proposed solution not only advances the state of the art in plant classification but also contributes a valuable dataset to the research community. Its real-world applicability spans field-based plant identification, biodiversity conservation, and precision agriculture, offering a scalable tool for automated plant recognition in complex ecological and agricultural environments. Full article

The increasing reliance on Medical Internet of Things (MIoT) devices introduces critical cybersecurity vulnerabilities, necessitating advanced, adaptive defense mechanisms. Recent cyber incidents—such as compromised critical care systems, modified therapeutic device outputs, and fraudulent clinical data inputs—demonstrate that these threats now directly impact life-critical aspects of patient security. In this paper, we introduce a machine learning-enabled Cognitive Cyber-Physical System (ML-CCPS), which is designed to identify and respond to cyber threats in MIoT environments through a layered cognitive architecture. The system is constructed on a feedback-looped architecture integrating hybrid feature modeling, physical behavioral analysis, and Extreme Learning Machine (ELM)-based classification to provide adaptive access control, continuous monitoring, and reliable intrusion detection. ML-CCPS is capable of outperforming benchmark classifiers with an acceptable computational cost, as evidenced by its macro F1-score of 97.8% and an AUC of 99.1% when evaluated with the ToN-IoT dataset. Alongside classification accuracy, the framework has demonstrated reliable behaviour under noisy telemetry, maintained strong efficiency in resource-constrained settings, and scaled effectively with larger numbers of connected devices. Comparative evaluations, radar-style synthesis, and ablation studies further validate its effectiveness in real-time MIoT environments and its ability to detect novel attack types with high reliability. Full article

Potatoes are one of the world’s most widely cultivated crops, but their yield is coming under mounting pressure from early blight, a fungal disease caused by Alternaria solani. Early detection and accurate identification are key to effective disease management and yield protection. This paper introduces a novel deep learning framework called ZeroShot CNN, which integrates convolutional neural networks (CNNs) and ZeroShot Learning (ZSL) for the efficient classification of seen and unseen disease classes. The model utilizes convolutional layers for feature extraction and employs semantic embedding techniques to identify previously untrained classes. Implemented on the Kaggle potato disease dataset, ZeroShot CNN achieved 98.50% accuracy for seen categories and 99.91% accuracy for unseen categories, outperforming conventional methods. The hybrid approach demonstrated superior generalization, providing a scalable, real-time solution for detecting agricultural diseases. The success of this solution validates the potential in harnessing deep learning and ZeroShot inference to transform plant pathology and crop protection practices. Full article

Wheat is one of the important grain crops, and spike counting is crucial for predicting spike yield. However, in complex farmland environments, the wheat body scale has huge differences, its color is highly similar to the background, and wheat ears often overlap with each other, which makes wheat ear detection work face a lot of challenges. At the same time, the increasing demand for high accuracy and fast response in wheat spike detection has led to the need for models to be lightweight function with reduced the hardware costs. Therefore, this study proposes a lightweight wheat ear detection model, CML-RTDETR, for efficient and accurate detection of wheat ears in real complex farmland environments. In the model construction, the lightweight network CSPDarknet is firstly introduced as the backbone network of CML-RTDETR to enhance the feature extraction efficiency. In addition, the FM module is cleverly introduced to modify the bottleneck layer in the C2f component, and hybrid feature extraction is realized by spatial and frequency domain splicing to enhance the feature extraction capability of wheat to be tested in complex scenes. Secondly, to improve the model’s detection capability for targets of different scales, a multi-scale feature enhancement pyramid (MFEP) is designed, consisting of GHSDConv, for efficiently obtaining low-level detail information and CSPDWOK for constructing a multi-scale semantic fusion structure. Finally, channel pruning based on Layer-Adaptive Magnitude Pruning (LAMP) scoring is performed to reduce model parameters and runtime memory. The experimental results on the GWHD2021 dataset show that the ${\mathrm{AP}}_{50}$ of CML-RTDETR reaches 90.5%, which is an improvement of 1.2% compared to the baseline RTDETR-R18 model. Meanwhile, the parameters and GFLOPs have been decreased to 11.03 M and 37.8 G, respectively, resulting in a reduction of 42% and 34%, respectively. Finally, the real-time frame rate reaches 73 fps, significantly achieving parameter simplification and speed improvement. Full article

In this study, Hf_0.5Zr_0.5O₂ (HZO) thin-films were deposited using a Co-plasma atomic layer deposition (CPALD) process that combined both remote plasma and direct plasma, for the development of ferroelectric memory devices. Ferroelectric capacitors with a symmetric hybrid TiN/W/HZO/W/TiN electrode structure, incorporating W electrodes as insertion layers, were fabricated. Rapid thermal annealing (RTA) was subsequently employed to control the crystalline phase of the films. The electrical and structural properties of the capacitors were analyzed based on the RTA temperature, and the presence, thickness, and position of the W insertion electrode layer. Consequently, the capacitor with 5 nm-thick W electrode layers inserted on both the top and bottom sides and annealed at 700 °C exhibited the highest remnant polarization (2P_r = 61.0 μC/cm²). Moreover, the symmetric hybrid electrode capacitors annealed at 500–600 °C also exhibited high 2P_r values of approximately 50.4 μC/cm², with a leakage current density of approximately 4 × 10⁻⁵ A/cm² under an electric field of 2.5 MV/cm. The findings of this study are expected to contribute to the development of electrode structures for improved performance of HZO-based ferroelectric memory devices. Full article

Unexpected machine failures in industrial environments lead to high maintenance costs, unplanned downtime, and safety risks. This study proposes a proactive predictive model using a hybrid of eXtreme Gradient Boosting (XGBoost) and Neural Networks (NN) to forecast machine failures. A synthetic dataset capturing recent breakdown history and time since last failure was used to simulate industrial scenarios. To address class imbalance, SMOTE and class weighting were applied, alongside a focal loss function to emphasize difficult-to-classify failures. The XGBoost model was tuned via GridSearchCV, while the NN model utilized ReLU-activated hidden layers with dropout. Evaluation using stratified 5-fold cross-validation showed that the NN achieved an F1-score of 0.7199 and a recall of 0.9545 for the minority class. XGBoost attained a higher PR AUC of 0.7126 and a more balanced precision–recall trade-off. Sample predictions demonstrated strong recall (100%) for failures, but also a high false positive rate, with most prediction probabilities clustered between 0.50–0.55. Additional benchmarking against Logistic Regression, Random Forest, and SVM further confirmed the superiority of the proposed hybrid model. Model interpretability was enhanced using SHAP and LIME, confirming that recent breakdowns and time since last failure were key predictors. While the model effectively detects failures, further improvements in feature engineering and threshold tuning are recommended to reduce false alarms and boost decision confidence. Full article

This review article compiled previous reports in the fabrication of hydroquinone (HQ) electrochemical sensors using differently modified electrodes. The electrode materials, which are also called electrocatalysts, play a crucial role in electrochemical detection of biomolecules and toxic substances. Metal oxides, MXenes, carbon-based materials such as reduced graphene oxide (rGO), carbon nanotubes (CNTs), layered double hydroxides (LDH), metal sulfides, and hybrid composites were extensively utilized in the fabrication of HQ sensors. The electrochemical performance, including limit of detection, linearity, sensitivity, selectivity, stability, reproducibility, repeatability, and recovery for real-time sensing of the HQ sensors have been discussed. The limitations, challenges, and future directions are also discussed in the conclusion section. It is believed that the present review article may benefit researchers who are involved in the development of HQ sensors and catalyst preparation for electrochemical sensing of other toxic substances. Full article

Reservoir-induced landslides threaten infrastructures and downstream communities, making continuous deformation monitoring vital. Time-series InSAR, notably the SBAS algorithm, provides high-precision surface-displacement mapping but suffers from voids due to layover/shadow effects and temporal decorrelation. Existing deep-learning approaches often operate on fixed-size patches or ignore irregular spatio-temporal dependencies, limiting their ability to recover missing pixels. With this objective, a hybrid spatio-temporal Graph Attention (ST-GAT) framework was developed and trained on SBAS-InSAR values using 24 influential features. A unified spatio-temporal graph is constructed, where each node represents a pixel at a specific acquisition time. The nodes are connected via inverse distance spatial edges to their K-nearest neighbors, and they have bidirectional temporal edges to themselves in adjacent acquisitions. The two spatial GAT layers capture terrain-driven influences, while the two temporal GAT layers model annual deformation trends. A compact MLP with per-map bias converts the fused node embeddings into normalized LOS estimates. The SBAS-InSAR results reveal LOS deformation, with 48% of missing pixels and 20% located near the Dasu dam. ST D-GAT reconstructed fully continuous spatio-temporal displacement fields, filling voids at critical sites. The model was validated and achieved an overall R² (0.907), ρ (0.947), per-map R² ≥ 0.807 with RMSE ≤ 9.99, and a ROC-AUC of 0.91. It also outperformed the six compared baseline models (IDW, KNN, RF, XGBoost, MLP, simple-NN) in both RMSE and R². By combining observed LOS values with 24 covariates in the proposed model, it delivers physically consistent gap-filling and enables continuous, high-resolution landslide monitoring in radar-challenged mountainous terrain. Full article

Cattle–yak, a hybrid of yak and cattle, exhibits significant heterosis but male infertility, hindering heterosis fixation. Although extensive research has been conducted on transcriptional mechanisms in the testes of cattle–yak, the understanding of their translational landscape remains limited. In this study, we characterized the translational landscape of yak and cattle–yak based on Ribo-seq technology integrated with RNA-seq data. The results revealed that gene expression was not fully concordant between transcriptional and translational levels, whereas cattle–yak testes exhibited a stronger correlation across these two regulatory layers. Notably, genes that were differentially expressed at the translational level only (MEIOB, MEI1, and SMC1B) were mainly involved in meiosis. A total of 4,236 genes with different translation efficiencies (TEs) were identified, and the TEs of most of the genes gradually decreased as the mRNA expression level increased. Further research revealed that genes with higher TE had a shorter coding sequence (CDS) length, lower GC content, and higher normalized minimum free energy in the testes of yaks, but this characteristic was not found in cattle–yaks. We also identified upstream open reading frames (uORFs) in yak and cattle–yak testes, and the sequence characteristics of translated uORFs and untranslated uORFs were markedly different. In addition, we identified several short polypeptides that may play potential roles in spermatogenesis. In summary, our study uncovers distinct translational dysregulations in cattle–yak testes, particularly affecting meiosis, which provides novel insights into the mechanisms of spermatogenesis and male infertility in hybrids. Full article

The advent of quantum computing has introduced new opportunities for enhancing classical machine learning architectures. In this study, we propose a novel hybrid model, the HQDNN (Hybrid Quantum–Deep Neural Network), designed for the automatic detection of fake news. The model integrates classical fully connected neural layers with a parameterized quantum circuit, enabling the processing of textual data within both classical and quantum computational domains. To assess its effectiveness, we conducted experiments on the widely used LIAR dataset utilizing Term Frequency–Inverse Document Frequency (TF-IDF) features, as well as transformer-based DistilBERT embeddings. The experimental results demonstrate that the HQDNN achieves a superior recall performance—92.58% with TF-IDF and 94.40% with DistilBERT—surpassing traditional machine learning models such as Logistic Regression, Linear SVM, and Multilayer Perceptron. Additionally, we compare the HQDNN with SetFit, a recent CPU-efficient few-shot transformer model, and show that while SetFit achieves higher precision, the HQDNN significantly outperforms it in recall. Furthermore, an ablation experiment confirms the critical contribution of the quantum component, revealing a substantial drop in performance when the quantum layer is removed. These findings highlight the potential of hybrid quantum–classical models as effective and compact alternatives for high-sensitivity classification tasks, particularly in domains such as fake news detection. Full article

The escalating threat of climate change has intensified the global urgency to accurately predict carbon dioxide (CO₂) emissions for sustainable development, particularly in developing economies experiencing rapid industrialization and globalization. Traditional Extreme Learning Machines (ELMs) offer rapid learning but often yield unstable performance due to random parameter initialization. This study introduces a novel hybrid model, Red-Billed Blue Magpie Optimizer-tuned ELM (RBMO-ELM) which harnesses the intelligent foraging behavior of red-billed blue magpies to optimize input-to-hidden layer weights and biases. The RBMO algorithm is first benchmarked on 15 functions from the CEC2015 test suite to validate its optimization effectiveness. Subsequently, RBMO-ELM is applied to predict Indonesia’s CO₂ emissions using a multidimensional dataset that combines economic, technological, environmental, and globalization-driven indicators. Empirical results show that the RBMO-ELM significantly surpasses several state-of-the-art hybrid models in accuracy (higher R²) and convergence efficiency (lower error). A permutation-based feature importance analysis identifies social globalization, GDP, and ecological footprint as the strongest predictors underscoring the socio-economic influences on emission patterns. These findings offer both theoretical and practical implications that inform data-driven Artificial Intelligence (AI) and Machine Learning (ML) applications in environmental policy and support sustainable governance models. Full article

This study investigates the effects of ultrasonic nanocrystalline surface modification (UNSM) on the formation of nitride layers in Ti-6Al-4V alloy during ion-plasma nitriding (IPN). Various UNSM parameters, including vibration amplitude, static load, and processing temperature, were systematically varied to evaluate their influence on microstructure, hardness, elastic modulus, and tribological behavior. The results reveal that pre-treatment with optimized UNSM conditions significantly enhances nitrogen diffusion, leading to the formation of dense and uniform TiN/Ti₂N layers. Samples pre-treated under high-load and elevated-temperature UNSM exhibited the greatest improvements in surface hardness (up to 25%), elastic modulus (up to 18%), and wear resistance, with a reduced and stabilized friction coefficient (~0.55). Scanning electron microscopy (SEM) and X-ray diffraction (XRD) analyses confirmed microstructural densification, grain refinement, and increased nitride phase intensity. These findings demonstrate not only the scientific relevance but also the practical potential of UNSM as an effective surface activation technique. The hybrid UNSM + IPN approach may serve as a promising method for extending the service life of load-bearing biomedical implants and engineering components subjected to intensive wear. Full article

Background/Objectives: Smartphone addiction (SA) and gaming addiction (GA) have become risk factors for individuals of all ages in recent years. Especially during adolescence, it has become very difficult for parents to control this situation. Physical activity and the effective use of free time are the most important factors in eliminating such addictions. This study aimed to test a new machine learning method by combining routine regression analysis with the gradient-boosting machine (GBM) and random forest (RF) methods to analyze the relationship between SA and GA with leisure time management (LTM) and the enjoyment of physical activity (EPA) among adolescents. Methods: This study presents the results obtained using our developed GBM + RF hybrid model, which incorporates LTM and EPA scores as inputs for predicting SA and GA, following the preprocessing of data collected from 1107 high school students aged 15–19 years. The results were compared with those obtained using routine regression results and the lasso, ElasticNet, RF, GBM, AdaBoost, bagging, support vector regression (SVR), K-nearest neighbors (KNN), multi-layer perceptron (MLP), and light gradient-boosting machine (LightGBM) models. In the GBM + RF model, probability scores obtained from GBM were used as input to RF to produce final predictions. The performance of the models was evaluated using the R², mean absolute error (MAE), and mean squared error (MSE) metrics. Results: Classical regression analyses revealed a significant negative relationship between SA scores and both LTM and EPA scores. Specifically, as LTM and EPA scores increased, SA scores decreased significantly. In contrast, GA scores showed a significant negative relationship only with LTM scores, whereas EPA was not a significant determinant of GA. In contrast to the relatively low explanatory power of classical regression models, ML algorithms have demonstrated significantly higher prediction accuracy. The best performance for SA prediction was achieved using the Hybrid GBM + RF model (MAE = 0.095, MSE = 0.010, R² = 0.9299), whereas the SVR model showed the weakest performance (MAE = 0.310, MSE = 0.096, R² = 0.8615). Similarly, the Hybrid GBM + RF model also showed the highest performance for GA prediction (MAE = 0.090, MSE = 0.014, R² = 0.9699). Conclusions: These findings demonstrate that classical regression analyses have limited explanatory power in capturing complex relationships between variables, whereas ML algorithms, particularly our GBM + RF hybrid model, offer more robust and accurate modeling capabilities for multifactorial cognitive and performance-related predictions. Full article

Multi-focus image fusion (MFIF) is an image-processing method that aims to generate fully focused images by integrating source images from different focal planes. However, the defocus spread effect (DSE) often leads to blurred or jagged focus/defocus boundaries in fused images, which affects the quality of the image. To address this issue, this paper proposes a novel model that embeds the Kolmogorov–Arnold network with convolutional layers in parallel within the U-Net architecture (KCUNet). This model keeps the spatial dimensions of the feature map constant to maintain high-resolution details while progressively increasing the number of channels to capture multi-level features at the encoding stage. In addition, KCUNet incorporates a content-guided attention mechanism to enhance edge information processing, which is crucial for DSE reduction and edge preservation. The model’s performance is optimized through a hybrid loss function that evaluates in several aspects, including edge alignment, mask prediction, and image quality. Finally, comparative evaluations against 15 state-of-the-art methods demonstrate KCUNet’s superior performance in both qualitative and quantitative analyses. Full article