Search Results (89)

Soil erosion-prone areas require effective microbial treatments to improve soil bacterial communities and functional traits. Understanding the driving effects of different microbial interventions on soil ecology is essential for restoration efforts. Single and combined microbial treatments were applied to soil. Bacterial community structure was analyzed via 16S IRNA high-throughput sequencing, and functional groups were predicted using FAPROTAX. Soil microbial carbon, nitrogen, metabolic entropy, and enzymatic activity were assessed. Microbial Carbon and Metabolic Activity: The Arbuscular mycorrhizal fungi (AMF) and Bacillus mucilaginosus (BM) (AMF.BM) treatment exhibited the highest microbial carbon content and the lowest metabolic entropy. The microbial carbon-to-nitrogen ratio ranged from 1.27 to 3.69 across all treatments. Bacterial Community Composition: The dominant bacterial phyla included Firmicutes, Proteobacteria, Acidobacteria, Bacteroidetes, and Actinobacteria. Diversity and Richness: The AMF and Trichoderma harzianum (TH) (AMF.TH) treatment significantly reduced diversity, richness, and phylogenetic diversity indices, while the AMF.BM treatment showed a significantly higher richness index (p < 0.05). Relative Abundance of Firmicutes: Compared to the control, the AMF, TH.BM, and TH treatments decreased the relative abundance of Firmicutes, whereas the AMF.TH treatment increased their relative abundance. Environmental Correlations: Redundancy and correlation analyses revealed significant correlations between soil organic matter, magnesium content, and sucrase activity and several major bacterial genera. Functional Prediction: The AMF.BM treatment enhanced the relative abundance and evenness of bacterial ecological functions, primarily driving nitrification, aerobic ammonia oxidation, and ureolysis. Microbial treatments differentially influence soil bacterial communities and functions. The AMF.BM combination shows the greatest potential for ecological restoration in erosion-prone soils. Full article

The Adaptive Cross Ivy (ACIVY) algorithm is a novel bio-inspired metaheuristic that emulates ivy plant growth behaviors for complex optimization problems. While the original Ivy Optimization Algorithm (IVYA) demonstrates a competitive performance, it suffers from limited inter-individual information exchange, inadequate directional guidance for local optima escape, and abrupt exploration–exploitation transitions. To address these limitations, ACIVY integrates three strategic enhancements: the crisscross strategy, enabling horizontal and vertical crossover operations for improved population diversity; the LightTrack strategy, incorporating positional memory and repulsion mechanisms for effective local optima escape; and the Top-Guided Adaptive Mutation strategy, implementing ranking-based mutation with dynamic selection pools for smooth exploration–exploitation balance. Comprehensive evaluations on the CEC2017 and CEC2022 benchmark suites demonstrate ACIVY’s superior performance against state-of-the-art algorithms across unimodal, multimodal, hybrid, and composite functions. ACIVY achieved outstanding average rankings of 1.25 (CEC2022) and 1.41 (CEC2017 50D), with statistical significance confirmed through Wilcoxon tests. Practical applications in engineering design optimization and UAV path planning further validate ACIVY’s robust performance, consistently delivering optimal solutions across diverse real-world scenarios. The algorithm’s exceptional convergence precision, solution reliability, and computational efficiency establish it as a powerful tool for challenging optimization problems requiring both accuracy and consistency. Full article

The internal quality detection is extremely important. To solve the challenges of walnut quality detection, we presented the first comprehensive investigation of walnut quality detection method using X-ray imaging and deep learning model. An X-ray machine vision system was designed, and a walnut kernel detection (called WKD) dataset was constructed. Then, an effective walnut kernel detection network (called WKNet) was developed by employing Transformer, GhostNet, and criss-cross attention (called CCA) module to the YOLO v5s model, aiming to solve the time consuming and parameter redundancy issues. The WKNet achieved an mAP_0.5 of 0.9869, precision of 0.9779, and recall of 0.9875 for walnut kernel detection. The inference time per image is only 11.9 ms. Extensive comparison experiments with the state-of-the-art (SOTA) deep learning models demonstrated the advanced nature of WKNet. The online test of walnut internal quality detection also shows satisfactory performance. The innovative combination of X-ray imaging and WKNet provide significant implications for walnut quality control. Full article

Indoor image semantic segmentation technology is applied to fields such as smart homes and indoor security. The challenges faced by semantic segmentation techniques using RGB images and depth maps as data sources include the semantic gap between RGB images and depth maps and the loss of detailed information. To address these issues, a multi-head self-attention mechanism is adopted to adaptively align features of the two modalities and perform feature fusion in both spatial and channel dimensions. Appropriate feature extraction methods are designed according to the different characteristics of RGB images and depth maps. For RGB images, asymmetric convolution is introduced to capture features in the horizontal and vertical directions, enhance short-range information dependence, mitigate the gridding effect of dilated convolution, and introduce criss-cross attention to obtain contextual information from global dependency relationships. On the depth map, a strategy of extracting significant unimodal features from the channel and spatial dimensions is used. A lightweight skip connection module is designed to fuse low-level and high-level features. In addition, since the first layer contains the richest detailed information and the last layer contains rich semantic information, a feature refinement head is designed to fuse the two. The method achieves an mIoU of 53.86% and 51.85% on the NYUDv2 and SUN-RGBD datasets, which is superior to mainstream methods. Full article

The promotion of enhanced well-being among children and collaboration among families, schools, and communities is paramount and is a pressing concern in the global education sector. This necessitates that preschool teachers possess the necessary competencies for effective family-preschool partnerships (FPPs). This study explored the competencies necessary for Chinese kindergarten teachers to engage in FPP using behavioral event interviews with 30 participants. Thematic analysis identified key competency traits, and independent samples t-tests with Bonferroni correction compared collaboration competencies between outstanding and typical teachers, as well as across different career stages. Consequently, a comprehensive crisscrossing competency framework consisting of four quadrants was developed. This framework distinguishes between high-performance and general traits, as well as between stable and variable traits that may evolve across career stages. High-performance traits such as communication, expression, and relationship management should be prioritized in the training and recruitment of early childhood educators involved in FPP. In contrast, intrinsic qualities that foster successful FPP, such as child orientation, should be cultivated early and sustained throughout a teacher’s career. From a developmental perspective, this framework provides a crucial foundation for evaluating and training kindergarten teachers in the competencies essential for fostering effective FPP. Full article

Background/Objectives: The growing demand for esthetic, less painful, and more comfortable orthodontic treatment has led to increasing use of aligner systems. Initially used for less complicated malocclusions, aligners are now being incorporated into complex treatment plans, including cases involving impacted teeth. While aligners are a popular alternative to traditional fixed appliances, they still have limitations. This study aims to evaluate the effectiveness of aligner-based orthodontic treatment in patients with impacted or significantly ectopic canines. Methods: This study was conducted in accordance with the PRISMA guidelines. The search terms used were as follows: ‘Clear Aligner’ OR ‘Invisalign’ AND ‘Impacted Canine’ OR ‘Impacted Tooth’ OR ‘Ectopic Tooth’ OR ‘Ectopic Canine.’ A total of 1101 records were identified, of which 170 articles underwent screening. Fifteen articles were assessed for eligibility, and ultimately six case reports and one three-dimensional finite element analysis (FEA) study were included for both quantitative and qualitative synthesis. Results: According to the studies, additional appliances are often required to achieve favorable outcomes when treating impacted canines with aligner systems. Temporary anchorage devices (TADs) were used in 5 out of 9 reported cases for canine traction into the dental arch. In three cases, TADs were combined with sectional wires implemented as cantilevers. Elastics were used in 6 out of 9 cases for traction to the opposite arch, and in 5 out of 9 cases as interarch elastics attached to the aligners. Interarch elastics were applied in various ways, either directly to the aligners or to primary canines using hidden buttons inside pontics or dovetail hooks. Elastics were also anchored to the lower arch with class II, class III, or cross-arch (criss-cross) mechanics. Conclusions: This review highlights the promising potential of aligner systems in the treatment of impacted canines. However, additional auxiliaries, such as TADs, sectional wires, or elastics remain nearly essential for initial canine traction. Aligner systems offer versatile treatment options, and the possibility of reduced treatment time represents a valuable area for future research. Full article

Hybrid evolutionary approaches have gained significant attention for solving complex optimization problems, but their potential for optimizing the low-dimensional latent space of generative adversarial networks (GANs) remains underexplored. This paper proposes a novel improved crisscross optimization (ICSO) algorithm, a hybrid evolutionary approach that integrates crisscross optimization and perturbation mechanisms to find the suitable latent vector. The ICSO algorithm treats the quality and diversity as separate objectives, balancing them through a normalization strategy, while a gradient regularization term (i.e., GP) is introduced into the discriminator’s objective function to stabilize training and mitigate gradient-related issues. By combining the global and local search capabilities of particle swarm optimization (PSO) with the rapid convergence of crisscross optimization, ICSO efficiently explores and exploits the latent space. The extensive experiments demonstrate that ICSO outperforms state-of-the-art algorithms in optimizing the latent space of various classical GANs across multiple datasets. Furthermore, the practical applicability of ICSO is validated through its integration with StyleGAN3 for generating unmanned aerial vehicle (UAV) images, showcasing its effectiveness in real-world engineering applications. This work not only advances the field of GAN optimization but also provides a robust framework for applying hybrid evolutionary algorithms to complex generative modeling tasks. Full article

In recent years, neural architecture search (NAS) has been proposed for automatically designing neural network architectures, which searches for network architectures that outperform novel human-designed convolutional neural network (CNN) architectures. Related research has always been a hot topic. This paper proposes a multi-objective evolutionary algorithm called the elitist non-dominated sorting crisscross algorithm (elitist NSCA) and applies it to neural architecture search, which considers two optimization objectives: the accuracy and network parameters. In the algorithm, an innovative search space borrowed from the latest residual block and dense connection is proposed to ensure the quality of the compact architectures. A variable-length crisscross optimization strategy, which creatively iterates the evolution through inter-individual horizontal crossovers and intra-individual vertical crossovers, is employed to simultaneously optimize the microstructure parameters and macroscopic architecture of the CNN. In addition, a corresponding mutation operator is added pertinently based on the performance of the proxy model, and the elitist strategy is improved through pruning to reduce the impact of abnormal fitnesses. The experimental results on multiple datasets show that the proposed algorithm has a higher accuracy and robustness than those of certain state-of-the-art algorithms. Full article

With the rapid development and widespread application of drones across various fields, drone recognition and classification at medium and long distances have become increasingly important yet challenging tasks. This paper proposes a novel network architecture called AECM-Net, which integrates an adaptive feature fusion (AF) module, an efficient channel attention (ECA), and a criss-cross attention (CCA) mechanism-enhanced multi-scale feature extraction module (MSC). The network employs both Mel-frequency cepstral coefficients (MFCCs) and Gammatone cepstral coefficients (GFCC) as input features, utilizing the AF module to adaptively adjust fusion weights of different feature maps while incorporating ECA channel attention to emphasize key channel features and CCA mechanism to capture long-range dependencies. To validate our approach, we construct a comprehensive dataset containing various drone models within a 50-m range and conduct extensive experiments. The experimental results demonstrate that our proposed AECM-Net achieves superior classification performance with an average accuracy of 95.2% within the 50-m range. These findings suggest that our proposed architecture effectively addresses the challenges of medium and long-range drone acoustic signal recognition through its innovative feature fusion and enhancement mechanisms. Full article

Electricity theft, emerging as one of the severe cyberattacks in smart grids, causes significant economic losses. Due to the powerful expressive ability of deep neural networks (DNN), supervised and unsupervised DNN-based electricity theft detection (ETD) schemes have experienced widespread deployment. However, existing works have the following weak points: Supervised DNN-based schemes require abundant labeled anomalous samples for training, and even worse, cannot detect unseen theft patterns. To avoid the extensively labor-consuming activity of labeling anomalous samples, unsupervised DNNs-based schemes aim to learn the normality of time-series and infer an anomaly score for each data instance, but they fail to capture periodic features effectively. To address these challenges, this paper proposes a novel periodicity-enhanced deep one-class classification framework (PE-DOCC) based on a periodicity-enhanced transformer encoder, named Periodicformer encoder. Specifically, within the encoder, a novel criss-cross periodic attention is proposed to capture both horizontal and vertical periodic features. The Periodicformer encoder is pre-trained by reconstructing partially masked input sequences, and the learned latent representations are then fed into a one-class classification for anomaly detection. Extensive experiments on real-world datasets demonstrate that our proposed PE-DOCC framework outperforms state-of-the-art unsupervised ETD methods. Full article

Global optimization problems, prevalent across scientific and engineering disciplines, necessitate efficient algorithms for navigating complex, high-dimensional search spaces. Drawing inspiration from the resilient and adaptive growth strategies of moss colonies, the moss growth optimization (MGO) algorithm presents a promising biomimetic approach to these challenges. However, the original MGO can experience premature convergence and limited exploration capabilities. This paper introduces an enhanced bio-inspired algorithm, termed crisscross moss growth optimization (CCMGO), which incorporates a crisscross (CC) strategy and a dynamic grouping parameter, further emulating the biological mechanisms of spore dispersal and resource allocation in moss. By mimicking the interwoven growth patterns of moss, the CC strategy facilitates improved information exchange among population members, thereby enhancing offspring diversity and accelerating convergence. The dynamic grouping parameter, analogous to the adaptive resource allocation strategies of moss in response to environmental changes, balances exploration and exploitation for a more efficient search. Key findings from rigorous experimental evaluations using the CEC2017 benchmark suite demonstrate that CCMGO consistently outperforms nine established metaheuristic algorithms across diverse benchmark functions. Furthermore, in a real-world application to a three-channel reservoir production optimization problem, CCMGO achieves a significantly higher net present value (NPV) compared to benchmark algorithms. This successful application highlights CCMGO’s potential as a robust and adaptable tool for addressing complex, real-world optimization challenges, particularly those found in resource management and other nature-inspired domains. Full article

Shadows degrade image quality and complicate interpretation, underscoring the importance of accurate shadow detection for many image analysis tasks. However, due to the complex backgrounds and variable shadow characteristics of remote sensing images (RSIs), existing methods often struggle with accurately detecting shadows of various scales and misclassifying dark, non-shaded areas as shadows. To address these issues, we proposed a comprehensive shadow detection network called MAMNet. Firstly, we proposed a multi-scale spatial channel attention fusion module, which extracted multi-scale features incorporating both spatial and channel information, allowing the model to flexibly adapt to shadows of different scales. Secondly, to address the issue of false detection in non-shadow areas, we introduced a criss-cross attention module, enabling non-shadow pixels to be compared with other shadow and non-shadow pixels in the same row and column, learning similar features of pixels in the same category, which improved the classification accuracy of non-shadow pixels. Finally, to address the issue of important information from the other two modules being lost due to continuous upsampling during the decoding phase, we proposed an auxiliary branch module to assist the main branch in decision-making, ensuring that the final output retained the key information from all stages. The experimental results demonstrated that the model outperformed the current state-of-the-art RSI shadow detection method on the aerial imagery dataset for shadow detection (AISD). The model achieved an overall accuracy (OA) of 97.50%, an $F_1$ score of 94.07%, an intersection over union (IOU) of 88.87%, a precision of 95.06%, and a BER of 4.05%, respectively. Additionally, visualization results indicated that our model could effectively detect shadows of various scales while avoiding false detection in non-shadow areas. Therefore, this model offers an efficient solution for shadow detection in aerial imagery. Full article

RGB-T salient object detection (SOD) has received considerable attention in the field of computer vision. Although existing methods have achieved notable detection performance in certain scenarios, challenges remain. Many methods fail to fully utilize high-frequency and low-frequency features during information interaction among different scale features, limiting detection performance. To address this issue, we propose a method for RGB-T salient object detection that enhances performance through wavelet transform and channel-wise attention fusion. Through feature differentiation, we effectively extract spatial characteristics of the target, enhancing the detection capability for global context and fine-grained details. First, input features are passed through the channel-wise criss-cross module (CCM) for cross-modal information fusion, adaptively adjusting the importance of features to generate rich fusion information. Subsequently, the multi-scale fusion information is input into the feature selection wavelet transforme module (FSW), which selects beneficial low-frequency and high-frequency features to improve feature aggregation performance and achieves higher segmentation accuracy through long-distance connections. Extensive experiments demonstrate that our method outperforms 22 state-of-the-art methods. Full article

Achieving precise target localization for UAVs is a complex problem that is often discussed. In order to achieve precise spatial localization of targets by UAVs and to solve the problems of premature convergence and easy to fall into local optimum in the original dung beetle algorithm, an error handling method based on the coordinate transformation of an airborne measurement system and the dung beetle optimization with crisscross and 3 Sigma Rule optimization (CCDBO) is proposed. Firstly, the total standard deviation is calculated by integrating the carrier position, the attitude angle, the pod azimuth, the pitch angle, and the given alignment error of the pod’s orientation. Subsequently, the Taylor series expansion method is adopted to linearize the approximated coordinate transformation process and simplify the error propagation model. Finally, in order to further improve the positioning accuracy, a target position correction strategy with the improved dung beetle optimization algorithm is introduced. The simulation and flight experiment results show that this method can significantly reduce the target positioning error of UAVs and improve the positioning accuracy by 20.42% on average compared with that of the original dung beetle algorithm, which provides strong support for the high-precision target observation and identification of UAVs in complex environments. Full article

An unescapable trend of hyperspectral image (HSI) has been toward classification with high accuracy and splendid performance. In recent years, Transformers have made remarkable progress in the HSI classification task. However, Transformer-based methods still encounter two main challenges. First, they concentrate on extracting spectral information and are incapable of using spatial information to a great extent. Second, they lack the utilization of multiscale features and do not sufficiently combine the advantages of the Transformer’s global feature extraction and multiscale feature extraction. To tackle these challenges, this article proposes a new solution named the hybrid-scale dual-domain Transformer with crisscrossed interaction (HSD²Former) for HSI classification. HSD²Former consists of three functional modules: dual-dimension multiscale convolutional embedding (D²MSCE), mixed domainFormer (MDFormer), and pyramid scale fusion block (PSFB). D²MSCE supersedes conventional patch embedding to generate spectral and spatial tokens at different scales, effectively enriching the diversity of spectral-spatial features. MDFormer is designed to facilitate self-enhancement and information interaction between the spectral domain and spatial domain, alleviating the heterogeneity of the spatial domain and spectral domain. PSFB introduces a straightforward fusion manner to achieve advanced semantic information for classification. Extensive experiments conducted on four datasets demonstrate the robustness and significance of HSD²Former. The classification evaluation indicators of OA, AA, and Kappa on four datasets almost exceed 98%, reaching state-of-the-art performance. Full article