Search Results (26)

Knowledge tracing plays a crucial role in effectively representing learners’ understanding and predicting their future learning progress. However, existing deep knowledge tracing methods, reliant on the forgetting model and Rasch model, often fail to account for the varying rates at which learners forget different knowledge concepts and the variations in question embedding covering the same concept. To address these limitations, this paper introduces an enhanced deep knowledge tracing model that combines the transformer network model with two innovative components. The first component is a multiband attention mechanism, which comprehensively summarizes a learner’s past response history across various temporal scales. By computing attention weights using different decay rates, this mechanism adaptively captures both long-term and short-term interactions for different knowledge concepts. The second component utilizes a quantized question embedding module to effectively capture variations among questions addressing the same knowledge concept. This module represents these differences in a rich embedding space, avoiding overparameterization or overfitting issues. The proposed model is evaluated on popular benchmark datasets, demonstrating its superiority over existing knowledge tracing methods in accuracy. This enhancement holds potential for improving personalized learning systems by providing more precise insights into learners’ progress. Full article

Multifunctional integrated meta-devices are the demand of modern communication systems and are given a lot of attention nowadays. Most of the research has focused on either cross-polarization conversion (CPC) or linear-to-circular (LP–CP) conversion. However, simultaneously realizing multiple bands with good conversion efficiency remains crucial. This paper proposes a multiband and multifunctional dual reflective polarization converter surface capable of converting a linearly polarized (LP) wave into a circularly polarized (CP) wave, in frequency bands of 12.29–12.63 GHz, 16.08–24.16 GHz, 27.82–32.21 GHz, 33.75–38.74 GHz, and 39.70–39.79 GHz, with 3 dB axial ratio bandwidths of 2.7%, 40.15%, 14.6%, 13.76%, and 0.2%, respectively. Moreover, the converter is capable of achieving CPC with a polarization conversion ratio (PCR) that exceeds 95%, within the frequency ranges of 13.10–14.72 GHz, 25.43–26.00, 32.46–32.56 GHz, and 39.14–39.59 GHz. In addition, to identify the fundamental cause of the CPC and LP–CP conversion, a comprehensive theoretical investigation is provided. Furthermore, the surface current distribution patterns at different frequencies are investigated to analyze the conversion phenomena. A sample prototype consisting of 20 × 20 unit cells was fabricated and measured, verifying our design and the simulated results. The proposed structure has potential applications in satellite communications, radar, stealth technologies, and reflector antennas. Full article

Accurately extracting pixel-level buildings from high-resolution remote sensing images is significant for various geographical information applications. Influenced by different natural, cultural, and social development levels, buildings may vary in shape and distribution, making it difficult for the network to maintain a stable segmentation effect of buildings in different areas of the image. In addition, the complex spectra of features in remote sensing images can affect the extracted details of multi-scale buildings in different ways. To this end, this study selects parts of Xi’an City, Shaanxi Province, China, as the study area. A parallel encoded building extraction network (MARS-Net) incorporating multiple attention mechanisms is proposed. MARS-Net builds its parallel encoder through DCNN and transformer to take advantage of their extraction of local and global features. According to the different depth positions of the network, coordinate attention (CA) and convolutional block attention module (CBAM) are introduced to bridge the encoder and decoder to retain richer spatial and semantic information during the encoding process, and adding the dense atrous spatial pyramid pooling (DenseASPP) captures multi-scale contextual information during the upsampling of the layers of the decoder. In addition, a spectral information enhancement module (SIEM) is designed in this study. SIEM further enhances building segmentation by blending and enhancing multi-band building information with relationships between bands. The experimental results show that MARS-Net performs better extraction results and obtains more effective enhancement after adding SIEM. The IoU on the self-built Xi’an and WHU building datasets are 87.53% and 89.62%, respectively, while the respective F1 scores are 93.34% and 94.52%. Full article

Research on emotion recognition based on electroencephalogram (EEG) signals is important for human emotion detection and improvements in mental health. However, the importance of EEG signals from different brain regions and frequency bands for emotion recognition is different. For this problem, this paper proposes the Capsule–Transformer method for multi-region and multi-band EEG emotion recognition. First, the EEG features are extracted from different brain regions and frequency bands and combined into feature vectors which are input into the fully connected network for feature dimension alignment. Then, the feature vectors are inputted into the Transformer for calculating the self-attention of EEG features among different brain regions and frequency bands to obtain contextual information. Finally, utilizing capsule networks captures the intrinsic relationship between local and global features. It merges features from different brain regions and frequency bands, adaptively computing weights for each brain region and frequency band. Based on the DEAP dataset, experiments show that the Capsule–Transformer method achieves average classification accuracies of 96.75%, 96.88%, and 96.25% on the valence, arousal, and dominance dimensions, respectively. Furthermore, in emotion recognition experiments conducted on individual brain regions or frequency bands, it was observed that the frontal lobe exhibits the highest average classification accuracy, followed by the parietal, temporal, and occipital lobes. Additionally, emotion recognition performance is superior for high-frequency band EEG signals compared to low-frequency band signals. Full article

An extensive number of farmlands in the Poyang Lake region of China have been submerged due to the impact of flood disasters, resulting in significant agricultural economic losses. Therefore, it is of great importance to conduct the long-term temporal monitoring of flood-induced water body changes using remote sensing technology. However, the scarcity of optical images and the complex, fragmented terrain are pressing issues in the current water body extraction efforts in southern hilly regions, particularly due to difficulties in distinguishing shadows from numerous mountain and water bodies. For this purpose, this study employs Sentinel-1 synthetic aperture radar (SAR) data, complemented by water indices and terrain features, to conduct research in the Poyang Lake area. The results indicate that the proposed multi-source data water extraction method based on microwave remote sensing data can quickly and accurately extract a large range of water bodies and realize long-time monitoring, thus proving a new technical means for the accurate extraction of floodwater bodies in the Poyang Lake region. Moreover, the comparison of several methods reveals that CAU-Net, which utilizes multi-band imagery as the input and incorporates a channel attention mechanism, demonstrated the best extraction performance, achieving an impressive overall accuracy of 98.71%. This represents a 0.12% improvement compared to the original U-Net model. Moreover, compared to the thresholding, decision tree, and random forest methods, CAU-Net exhibited a significant enhancement in extracting flood-induced water bodies, making it more suitable for floodwater extraction in the hilly Poyang Lake region. During this flood monitoring period, the water extent in the Poyang Lake area rapidly expanded and subsequently declined gradually. The peak water area reached 4080 km² at the height of the disaster. The severely affected areas were primarily concentrated in Yongxiu County, Poyang County, Xinjian District, and Yugan County. Full article

Cropland abandonment is a worldwide problem that threatens food security and has significant consequences for the sustainable growth of the economy, society, and the natural ecosystem. However, detecting and mapping abandoned lands is challenging due to their diverse characteristics, like varying vegetation cover, spectral reflectance, and spatial patterns. To overcome these challenges, we employed Gaofen-6 (GF-6) imagery in conjunction with a Vision Transformer (ViT) model, harnessing self-attention and multi-scale feature learning to significantly enhance our ability to accurately and efficiently classify land covers. In Mianchi County, China, the study reveals that approximately 385 hectares of cropland (about 2.2% of the total cropland) were abandoned between 2019 and 2023. The highest annual abandonment occurred in 2021, with 214 hectares, followed by 170 hectares in 2023. The primary reason for the abandonment was the transformation of cropland into excavation activities, barren lands, and roadside greenways. The ViT’s performance peaked when multiple vegetation indices (VIs) were integrated into the GF-6 bands, resulting in the highest achieved results (F1 score = 0.89 and OA = 0.94). Our study represents an innovative approach by integrating ViT with 8 m multiband composite GF-6 imagery for precise identification and analysis of short-term cropland abandonment patterns, marking a distinct contribution compared to previous research. Moreover, our findings have broader implications for effective land use management, resource optimization, and addressing complex challenges in the field. Full article

Introduction: Winter wheat plays a crucial role in ensuring food security and sustainable agriculture. Accurate identification and recognition of winter wheat in remote sensing images are essential for monitoring crop growth and yield estimation. In recent years, attention-based convolutional neural networks have shown promising results in various image recognition tasks. Therefore, this study aims to explore the application of attention-based convolutional neural networks for winter wheat identification on GF-2 high-resolution images and propose improvements to enhance recognition accuracy. Method: This study built a multi-band winter wheat sample dataset based on GF-2 images. In order to highlight the characteristics of winter wheat, this study added two bands, NDVI and NDVI_increase, to the dataset and proposed a SUNet network model. In this study, the batch normalization layer was added to the basic structure of the UNet convolutional network to speed up network convergence and improve accuracy. In the jump phase, shuffle attention was added to the shallow features extracted from the coding structure for feature optimization and spliced with the deep features extracted by upsampling. The SUNet made the network pay more attention to the important features to improve winter wheat recognition accuracy. In order to overcome the sample imbalance problem, this study used the focus loss function instead of the traditional cross-entropy loss function. Result: The experimental data show that its mean intersection over union, overall classification accuracy, recall, F1 score and kappa coefficient are 0.9514, 0.9781, 0.9707, 0.9663 and 0.9501, respectively. The results of these evaluation indicators are better than those of other comparison methods. Compared with the UNet, the evaluation indicators have increased by 0.0253, 0.0118, 0.021, 0.0185, and 0.0272, respectively. Conclusion: The SUNet network can effectively improve winter wheat recognition accuracy in multi-band GF-2 images. Furthermore, with the support of a cloud platform, it can provide data guarantee and computing support for winter wheat information extraction. Full article

The burning of straw is a very destructive process that threatens people’s livelihoods and property and causes irreparable environmental damage. It is therefore essential to detect and control the burning of straw. In this study, we analyzed Sentinel-2 data to select the best separation bands based on the response characteristics of clouds, smoke, water bodies, and background (vegetation and bare soil) to the different bands. The selected bands were added to the red, green, and blue bands (RGB) as training sample data. The band that featured the highest detection accuracy, RGB_Band6, was finally selected, having an accuracy of 82.90%. The existing object detection model cannot directly handle multi-band images. This study modified the input layer structure based on the YOLOv5s model to build an object detection network suitable for multi-band remote sensing images. The Squeeze-and-Excitation (SE) network attention mechanism was introduced based on the YOLOv5s model so that the delicate features of smoke were enhanced, and the Convolution + Batch normalization + Leaky ReLU (CBL) module was replaced with the Convolution + Batch normalization + Mish (CBM) module. The accuracy of the model was improved to 75.63%, which was 1.81% better than before. We also discussed the effect of spatial resolution on model detection and where accuracies of 84.18%, 73.13%, and 45.05% for images of 60-, 20-, and 10-m resolution, respectively, were realized. The experimental results demonstrated that the accuracy of the model only sometimes improved with increasing spatial resolution. This study provides a technical reference for the monitoring of straw burning, which is vital for both the control of straw burning and ways to improve ambient air quality. Full article

Piezoelectric Laterally Vibrating Resonators (LVRs) have attracted significant attention as a potential technology for next-generation wafer-level multi-band filters. Piezoelectric bilayer structures such as Thin-film Piezoelectric-on-Silicon (TPoS) LVRs which aim to increase the quality factor (Q) or aluminum nitride and silicon dioxide (AlN/SiO₂) composite membrane for thermal compensation have been proposed. However, limited studies have investigated the detailed behaviors of the electromechanical coupling factor (K²) of these piezoelectric bilayer LVRs. Herein, AlN/Si bilayer LVRs are selected as an example, we observed notable degenerative valleys in K² at specific normalized thicknesses using two-dimensional finite element analysis (FEA), which has not been reported in the previous studies of bilayer LVRs. Moreover, the bilayer LVRs should be designed away from the valleys to minimize the reduction in K². Modal-transition-induced mismatch between electric and strain fields of AlN/Si bilayer LVRs are investigated to interpret the valleys from energy considerations. Furthermore, the impact of various factors, including electrode configurations, AlN/Si thickness ratios, the Number of Interdigitated Electrode (IDT) Fingers (NFs), and IDT Duty Factors (DFs), on the observed valleys and K² are analyzed. These results can provide guidance for the designs of piezoelectric LVRs with bilayer structure, especially for LVRs with a moderate K² and low thickness ratio. Full article

Filled skutterudite compounds have gained attention recently as an innovative platforms for studying intriguing low-temperature superconducting properties. Regarding the symmetry of the superconducting gap, contradicting findings from several experiments have been made for LaRu${}_4$As${}_{12}$ and its isoelectronic counterpart, LaOs${}_4$As${}_{12}$. In this vein, we report comprehensive bulk and microscopic results on LaOs${}_4$As${}_{12}$ utilizing specific heat analysis and muon-spin rotation/relaxation ($\mu$SR) measurements. Bulk superconductivity with $T_C$ = 3.2 K was confirmed by heat capacity. The superconducting ground state of the filled-skutterudite LaOs${}_4$As${}_{12}$ compound is found to have two key characteristics: superfluid density exhibits saturation type behavior at low temperature, which points to a fully gapped superconductivity with gap value of $2\Delta /k_B{T}_C$ = 3.26; additionally, the superconducting state does not show any sign of spontaneous magnetic field, supporting the preservation of time-reversal symmetry. These results open the door for the development of La-based skutterudites as special probes for examining the interplay of single- and multiband superconductivity in classical electron–phonon systems. Full article

Nowadays, different machine learning approaches, either conventional or more advanced, use input from different remote sensing imagery for land cover classification and associated decision making. However, most approaches rely heavily on time-consuming tasks to gather accurate annotation data. Furthermore, downloading and pre-processing remote sensing imagery used to be a difficult and time-consuming task that discouraged policy makers to create and use new land cover maps. We argue that by combining recent improvements in deep learning with the use of powerful cloud computing platforms for EO data processing, specifically the Google Earth Engine, we can greatly facilitate the task of land cover classification. For this reason, we modify an efficient semantic segmentation approach (U-TAE) for a satellite image time series to use, as input, a single multiband image composite corresponding to a specific time range. Our motivation is threefold: (a) to improve land cover classification performance and at the same time reduce complexity by using, as input, satellite image composites with reduced noise created using temporal median instead of the original noisy (due to clouds, calibration errors, etc.) images, (b) to assess performance when using as input different combinations of satellite data, including Sentinel-2, Sentinel-1, spectral indices, and ALOS elevation data, and (c) to exploit channel attention instead of the temporal attention used in the original approach. We show that our proposed modification on U-TAE (mIoU: 57.25%) outperforms three other popular approaches, namely random forest (mIoU: 39.69%), U-Net (mIoU: 55.73%), and SegFormer (mIoU: 53.5%), while also using fewer training parameters. In addition, the evaluation reveals that proper selection of the input band combination is necessary for improved performance. Full article

Because of its ability to objectively reflect people’s emotional states, electroencephalogram (EEG) has been attracting increasing research attention for emotion classification. The classification method based on spatial-domain analysis is one of the research hotspots. However, most previous studies ignored the complementarity of information between different frequency bands, and the information in a single frequency band is not fully mined, which increases the computational time and the difficulty of improving classification accuracy. To address the above problems, this study proposes an emotion classification method based on dynamic simplifying graph convolutional (SGC) networks and a style recalibration module (SRM) for channels, termed SGC-SRM, with multi-band EEG data as input. Specifically, first, the graph structure is constructed using the differential entropy characteristics of each sub-band and the internal relationship between different channels is dynamically learned through SGC networks. Second, a convolution layer based on the SRM is introduced to recalibrate channel features to extract more emotion-related features. Third, the extracted sub-band features are fused at the feature level and classified. In addition, to reduce the redundant information between EEG channels and the computational time, (1) we adopt only 12 channels that are suitable for emotion classification to optimize the recognition algorithm, which can save approximately 90.5% of the time cost compared with using all channels; (2) we adopt information in the θ, α, β, and γ bands, consequently saving 23.3% of the time consumed compared with that in the full bands while maintaining almost the same level of classification accuracy. Finally, a subject-independent experiment is conducted on the public SEED dataset using the leave-one-subject-out cross-validation strategy. According to experimental results, SGC-SRM improves classification accuracy by 5.51–15.43% compared with existing methods. Full article

The problem of saving soil resources and their reclamation measures under current climate change conditions attracts the world community’s close attention. It is relevant in the Syr Darya River’s lowlands, where the secondary soil salinization processes have intensified. The demand for robust methods to assess soil salinity is high, and the primary purpose of this study was to develop a quantitative analysis method for soil salinity estimation. We found a correspondence between the sum of salts in a topsoil layer to the Landsat 8 data in the Tasseled cap transformation of the image values. After testing several methods, we built a prediction model. The K-nearest neighborhood (KNN) model with a coefficient of determination equal to 0.96 using selected predictors proved to be the most appropriate for soil salinity assessment. We also performed a quantitative assessment of soil salinity. A significant increase in a salt-affected area and the mean soil sum expressing an intensification of secondary soil salinization from 2018 to 2021 was found. The increasing temperature values, decreasing soil moisture, and agricultural use affect the extension of salt-affected ground areas in the study area. Thus, the soil moisture trend in the Qazaly irrigation zone is negative and declining, with the highest peaks in early spring. The maximum temperature has a mean value of 15.6 °C (minimum = −15.1 °C, maximum = 37.4 °C) with an increasing trend. These parameters are evidence of climate change that also affects soil salinization. PCA transformation of the Landsat-8 satellite images helped to remove redundant spectral information from multiband datasets and map soil salinity more precisely. This approach simultaneously extends mapping opportunities involving visible and invisible bands and results in a smaller dataset. Full article

Pine wilt disease (PWD) can cause destructive death in many species of pine trees within a short period. The recognition of infected pine trees in unmanned aerial vehicle (UAV) forest images is a key technology for automatic monitoring and early warning of pests. This paper collected UAV visible and multispectral images of Korean pines (Pinus koraiensis) and Chinese pines (P. tabulaeformis) infected by PWD and divided the PWD infection into early, middle, and late stages. With the open-source annotation tool, LabelImg, we labeled the category of infected pine trees at each stage. After coordinate-correction preprocessing of the ground truth, the Korean pine and Chinese pine datasets were established. As a means of detecting infected pine trees of PWD and determining different infection stages, a multi-band image-fusion infected pine tree detector (MFTD) based on deep learning was proposed. Firstly, the Halfway Fusion mode was adopted to fuse the network based on four YOLOv5 variants. Simultaneously, the Backbone network was initially designed as a dual branching network that includes visible and multispectral subnets. Moreover, the features of visible and multispectral images were extracted. To fully utilize the features of visible and multispectral images, a multi-band feature fusion transformer (MFFT) with a multi-head attention mechanism and a feed-forward network was constructed to enhance the information correlation between visible and multispectral feature maps. Finally, following the MFFT module, the two feature maps were fused and input into Neck and Head to predict the categories and positions of infected pine trees. The best-performing MFTD model achieved the highest detection accuracy with mean average precision values (mAP@50) of 88.5% and 86.8% on Korean pine and Chinese pine datasets, respectively, which improved by 8.6% and 10.8% compared to the original YOLOv5 models trained only with visible images. In addition, the average precision values (AP@50) are 87.2%, 93.5%, and 84.8% for early, middle, and late stages on the KP dataset and 81.2%, 92.9%, and 86.2% on the CP dataset. Furthermore, the largest improvement is observed in the early stage with 14.3% and 11.6%, respectively. The results show that MFTD can accurately detect the infected pine trees, especially those at the early stage, and improve the early warning ability of PWD. Full article

Accurate surface defect extraction of apples is critical for their quality inspection and marketing purposes. Using multi-band images, this study proposes a detection method for apple surface defects with a combination of machine vision and deep learning. Five single bands, 460, 522, 660, 762, and 842 nm, were selected within the visible and near-infrared. By using a near-infrared industrial camera with optical filters, five single-band images of an apple could be obtained. To achieve higher accuracy of defect extraction, an improved U-Net was designed based on the original U-Net network structure. More specially, the partial original convolutions were replaced by dilated convolutions with different dilated rates, and an attention mechanism was added. The loss function was also redesigned during the training process. Then the traditional algorithm, the trained U-Net and the trained improved U-Net were used to extract defects of apples in the test set. Following that, the performances of the three methods were compared with that of the manual extraction. The results show that the near-infrared band is better than the visible band for defects with insignificant features. Additionally, the improved U-Net is better than the U-Net and the traditional algorithm for small defects and defects with irregular edges. On the test set, for single-band images at 762 nm, the improved U-Net had the best defect extraction with an mIoU (mean intersection over union) and mF1-score of 91% and 95%, respectively. Full article