Abundant Information Research Articles

Porphyry-type mineral prospectivity mapping with imbalanced data via prior geological transfer learning

Mineral prospectivity mapping is crucial for identifying areas with economically valuable minerals. Therefore, several methods based on machine learning have been applied to predict the likelihood of mineral occurrences, especially deep learning (DL), which provides a flexible and precise approach to the use of continuous data. It allows the approximation of predictive variables with probability values related to new ore targets. However, in the early stages of mineral exploration, DL-based methods face a challenge related to class and sampling imbalance due to scarce mineral deposits, resulting in a lack of enough samples to train, limiting the model’s predictive ability. This work proposed a detailed and systematic framework to address imbalanced data issues with prior geological transfer learning and a weighted loss function. We exploited the abundant pixel information of input variables to develop a pretext geological classification and a feature data extraction task as an initializer for the trainable variables of the neural network. The proposed workflow was tested in a porphyry-rich Yukon (Canada) region and overperformed other state-of-the-art classification algorithms such as random forest, support vector machines, and logistic regression. Moreover, our results were contrasted against different geological reports, where our mineral prospectivity map was coherent with regional and local potential assessments of porphyry-type mineral occurrences. The quantitative metrics with a validation dataset suggested that the proposed method can effectively predict mineral prospective areas in different imbalanced data scenarios.

Rectified Binary Network for Single-Image Super-Resolution.

Binary neural network (BNN) is an effective approach to reduce the memory usage and the computational complexity of full-precision convolutional neural networks (CNNs), which has been widely used in the field of deep learning. However, there are different properties between BNNs and real-valued models, making it difficult to draw on the experience of CNN composition to develop BNN. In this article, we study the application of binary network to the single-image super-resolution (SISR) task in which the network is trained for restoring original high-resolution (HR) images. Generally, the distribution of features in the network for SISR is more complex than those in recognition models for preserving the abundant image information, e.g., texture, color, and details. To enhance the representation ability of BNN, we explore a novel activation-rectified inference (ARI) module that achieves a more complete representation of features by combining observations from different quantitative perspectives. The activations are divided into several parts with different quantification intervals and are inferred independently. This allows the binary activations to retain more image detail and yield finer inference. In addition, we further propose an adaptive approximation estimator (AAE) for gradually learning the accurate gradient estimation interval in each layer to alleviate the optimization difficulty. Experiments conducted on several benchmarks show that our approach is able to learn a binary SISR model with superior performance over the state-of-the-art methods. The code will be released at https://github.com/jwxintt/Rectified-BSR.

Comparing diversity and structure of freshwater fish assemblages using environmental DNA and gillnetting methods: A case study of a large deep reservoir in East China

Environmental DNA (eDNA) technology, as an alternative to traditional gillnet surveys, has attracted widespread attention. However, comparisons between eDNA and traditional methods regarding biodiversity and community structure have not yet been fully elucidated. This study compared the ability of eDNA and gillnets for fish monitoring in a large deep reservoir (Qiandao Lake) in East China. The results showed that eDNA exhibited higher taxonomic resolution and detection rates, and significantly larger species diversity and richness indices compared with traditional gillnetting methods. Using abundance and biomass datasets from gillnets revealed significant differences in fish community composition between gillnetting and eDNA survey methods. Gillnet abundance was dominated by small-sized fish species, while gillnet biomass was dominated by larger-sized ones, and the prevailing species detected in eDNA reads included the dominant species from gillnet abundance and biomass, as well as a medium-sized invasive alien fish (Lepomis macrochirus). Non-metric multidimensional scaling (NMDS) showed that the spatial distribution in abundance of fish species sampled by gillnetting was more dispersed than that using eDNA. The explanatory power with the gillnet abundance and biomass together as predictor variables of the eDNA reads increased moderately compared with taking them separately, and the fitting degree of quadratic functions was also improved somewhat compared to linear equations when using biomass to predict eDNA reads. Furthermore, the key environmental factors affecting fish communities differed between the two methods. Current research indicates that eDNA has advantages over gillnets in detecting fish species diversity, and it is recommended to combine it with traditional sampling methods. Under natural aquatic ecosystem conditions, the eDNA reads may comprehensively reflect the biomass and abundance information obtained through gillnetting, but their relationship is complex and requires further research. This study will provide guidance for biodiversity monitoring.

Improvement of the Estimation of the Vertical Crustal Motion Rate at GNSS Campaign Stations Based on the Information of GNSS Reference Stations

With the enrichment of GNSS data and the improvement in data processing accuracy, GNSS technology has been widely applied in fields such as crustal deformation. The Crustal Movement Observation Network of China (CMONOC) has provided decades of Global Navigation Satellite System (GNSS) data and related data products for crustal deformation research on the Chinese mainland. The coordinate time series of continuously observed reference stations contain abundant information on crustal movements. In contrast, the coordinate time series of periodically observed campaign stations have limited data, making it difficult to separate or remove instantaneous non-tectonic movements from the time series, as performed with reference stations, to obtain a stable and reliable crustal movement velocity field. To address this issue, this paper proposes a method to improve the estimation of crustal movement velocity at campaign stations using the information of neighboring reference stations. This method constructs a Delaunay triangulation of reference stations and fits the periodic movement of each campaign station using an inverse distance weighted interpolation algorithm based on the reference station information. The crustal movement velocity of the campaign stations is then estimated after removing the periodic movement. This method was verified by its application to the estimation of the vertical motion rate at some reference and campaign stations in Yunnan Province. The results show that the accuracy of vertical motion rate estimation for virtual and real campaign stations improved by an average of 24.4% and 9.6%, respectively, demonstrating the effectiveness of the improved method, which can be applied to estimate crustal movement velocity at campaign stations in other areas.

Ultrasonic Assessment of Liver Fibrosis Using One-Dimensional Convolutional Neural Networks Based on Frequency Spectra of Radiofrequency Signals with Deep Learning Segmentation of Liver Regions in B-Mode Images: A Feasibility Study.

The early detection of liver fibrosis is of significant importance. Deep learning analysis of ultrasound backscattered radiofrequency (RF) signals is emerging for tissue characterization as the RF signals carry abundant information related to tissue microstructures. However, the existing methods only used the time-domain information of the RF signals for liver fibrosis assessment, and the liver region of interest (ROI) is outlined manually. In this study, we proposed an approach for liver fibrosis assessment using deep learning models on ultrasound RF signals. The proposed method consisted of two-dimensional (2D) convolutional neural networks (CNNs) for automatic liver ROI segmentation from reconstructed B-mode ultrasound images and one-dimensional (1D) CNNs for liver fibrosis stage classification based on the frequency spectra (amplitude, phase, and power) of the segmented ROI signals. The Fourier transform was used to obtain the three kinds of frequency spectra. Two classical 2D CNNs were employed for liver ROI segmentation: U-Net and Attention U-Net. ROI spectrum signals were normalized and augmented using a sliding window technique. Ultrasound RF signals collected (with a 3-MHz transducer) from 613 participants (Group A) were included for liver ROI segmentation and those from 237 participants (Group B) for liver fibrosis stage classification, with a liver biopsy as the reference standard (Fibrosis stage: F0 = 27, F1 = 49, F2 = 51, F3 = 49, F4 = 61). In the test set of Group A, U-Net and Attention U-Net yielded Dice similarity coefficients of 95.05% and 94.68%, respectively. In the test set of Group B, the 1D CNN performed the best when using ROI phase spectrum signals to evaluate liver fibrosis stages ≥F1 (area under the receive operating characteristic curve, AUC: 0.957; accuracy: 89.19%; sensitivity: 85.17%; specificity: 93.75%), ≥F2 (AUC: 0.808; accuracy: 83.34%; sensitivity: 87.50%; specificity: 78.57%), and ≥F4 (AUC: 0.876; accuracy: 85.71%; sensitivity: 77.78%; specificity: 94.12%), and when using the power spectrum signals to evaluate ≥F3 (AUC: 0.729; accuracy: 77.14%; sensitivity: 77.27%; specificity: 76.92%). The experimental results demonstrated the feasibility of both the 2D and 1D CNNs in liver parenchyma detection and liver fibrosis characterization. The proposed methods have provided a new strategy for liver fibrosis assessment based on ultrasound RF signals, especially for early fibrosis detection. The findings of this study shed light on deep learning analysis of ultrasound RF signals in the frequency domain with automatic ROI segmentation.

Thyroid-DETR: Thyroid nodule detection model with transformer in ultrasound images

Deep learning-based object detection methods using ultrasound images to assist clinicians in rapid and accurate diagnosis of thyroid nodules has been an attractive area of research. Despite the great progress made by object detectors, these may still produce unsatisfactory performance due to certain factors, such as the presence of abundant background information and significant nodule size variations in ultrasound images of thyroid nodules. In this study, we draw on the idea of a Transformer and design a powerful thyroid nodule ultrasound imaging detection model, namely Thyroid-DETR. The proposed Thyroid-DETR has the following features: (i) a deformable convolution v2 is introduced flexibly capture small nodules of irregular shapes and small sizes, (ii) a multi-head self-attention structure is designed to acquire and learn broader correlated information in the shallow layer, (iii) a dual-stream training structure with BatchFormerV2 is developed to fully capture the effective information of medical images; (iv) fine-tuning methods to optimize the model are used to improve the diagnostic accuracy for detecting thyroid nodules. To evaluate the efficacy and effectiveness of the proposed approach. Extensive experiments and comprehensive comparisons are conducted on real thyroid nodule ultrasound images from the hospital. The results show that our method significantly outperforms the state-of-the-art methods.

Beyond Nyquist: A Comparative Analysis of 3D Deep Learning Models Enhancing MRI Resolution.

High-spatial resolution MRI produces abundant structural information, enabling highly accurate clinical diagnosis and image-guided therapeutics. However, the acquisition of high-spatial resolution MRI data typically can come at the expense of less spatial coverage, lower signal-to-noise ratio (SNR), and longer scan time due to physical, physiological and hardware limitations. In order to overcome these limitations, super-resolution MRI deep-learning-based techniques can be utilised. In this work, different state-of-the-art 3D convolution neural network models for super resolution (RRDB, SPSR, UNet, UNet-MSS and ShuffleUNet) were compared for the super-resolution task with the goal of finding the best model in terms of performance and robustness. The public IXI dataset (only structural images) was used. Data were artificially downsampled to obtain lower-resolution spatial MRIs (downsampling factor varying from 8 to 64). When assessing performance using the SSIM metric in the test set, all models performed well. In particular, regardless of the downsampling factor, the UNet consistently obtained the top results. On the other hand, the SPSR model consistently performed worse. In conclusion, UNet and UNet-MSS achieved overall top performances while RRDB performed relatively poorly compared to the other models.

Deciphering the role of SlWRKY36 and SlWRKY51 in salt stress tolerance via modulating ion homeostasis and proline biosynthesis

Soil salinity caused by NaCl is a major challenge to agricultural crops worldwide. For this, two WRKY transcription factors were evaluated for their role in salt stress tolerance in tomato plants (Solanum lycopersicum; Sl). SlWRKY36 and SlWRKY51 provided novel insight into the regulatory mechanism in tomato against salt stress via virus-induced gene silencing (VIGS). Salt stress significantly reduced chlorophyll-a, an abundant form of chlorophyll content to 6.0 and 5.1 mg/g and proline content to 0.06 mg/g and 0.09 mg/g respectively in SlWRKY36 and SlWRKY51 silenced tomato plants. This shows that salt stress affected proline content that act as osmo-protectant and damaged photosynthetic pigments in silenced SlWRKY36 and SlWRKY51 tomato plants. Similarly, the concentrations of Na+/ K+ ratio also showed a significantly higher trend 14 days after salt stress with 5.5 mg/g and 8.9 mg/g concentration at 200 mM for SlWRKY36 and SlWRKY51 showing silencing promotes Na+/K+ ion ratio under salt stress. Also, salt stress responsive genes such as salt overly sensitive SOS1 and Na+/H+ exchanger NHX1 displayed lower transcript level in silenced plants at 200 mM salt stress showing their negative regulation by SlWRKY36 and SlWRKY51 gene silencing. Collectively, these findings suggest for the first time the role of SlWRKY36 and SlWRKY51 as positive regulators of salt stress tolerance by managing ion homeostasis, proline content and photosynthetic machinery via transcriptional reprogramming. Overall, SlWRKY36 and SlWRKY51 were explored as potential candidates for engineering salt tolerance in tomato crop plants.

MAIANet: Signal modulation in cassava leaf disease classification

Cassava is the third largest source of carbohydrates for human consumption worldwide; however, it is highly susceptible to viral and bacterial diseases, which pose a significant threat to food security. The advancement of deep learning algorithms in precision agriculture holds the key to enabling the early classification of plant diseases, thereby leading to enhanced crop yields and ultimately stabilizing food security. In the coarse-grained label discrimination task of weak supervision learning, high-quality semantic features contain abundant semantic description information, which plays a crucial role in constructing a precise description of plant disease discrimination in tanglesome field circumstances and directly influences the performance of neural networks. Thus, a multiattention IBN anti-aliasing neural network (MAIANet) was proposed to improve the classification accuracy of cassava leaf disease classification by improving the feature quality in the coarseness label classification task. The proposed MAIANet neural network includes two innovative approaches. First, the multiattention method was designed to scale the feature signals twice to adjust the angular frequency of the feature signals in the residual branch for optimal feature fitting within the residual unit. Second, the anti-aliasing block extracts the high-frequency component feature and optimizes the quantization result of the pooling operation to depress the aliasing signal in the down-sampled feature maps. When the proposed method was tested and validated on the cassava dataset, the results showed that the prediction accuracy of the proposed method significantly improved, with an accuracy of 95.83 %, a loss of 1.720, and an F1-score of 0.9585, outperforming V2-ResNet-101, EfficientNet-B5, RepVGG-B3g4, and AlexNet with significant margins. Based on the above experimental results, the proposed algorithm is suitable for classifying cassava leaf diseases.

Interior-point policy optimization based multi-agent deep reinforcement learning method for secure home energy management under various uncertainties

Improving the efficiency of home energy management (HEM) is of great significance in reducing resource waste and prompting renewable energy consumption. With the development of advanced HEM systems and internet-of-things technology, more residents are willing to participate in the electricity market through a demand response mechanism, which can not only reduce the electricity bill but also stabilize the operation of the main grid through peak shaving and valley filling. However, the uncertainties from household appliance parameters, user behaviors, penetrated renewable energy, and electricity prices render the HEM problem a non-trivial task. Although previous deep reinforcement learning (DRL) methods have no requirement for system dynamics due to their model-free and data-driven merits, the unrestricted action space may violate the physical constraints of various devices, and few works have concentrated on this area before. To solve the above challenges, this paper proposes a novel interior-point policy optimization-based multi-agent DRL algorithm to optimize the home energy scheduling procedure while guaranteeing safety during its operation. Besides, a time-series prediction model based on a non-stationary Transformer neural network is proposed to predict the future trend of solar generation and electricity price, which can provide the agents with abundant information to make better decisions. The superior performance of our proposed predictive-control coupled method is demonstrated through extensive numerical experiments, which achieves more precise prediction results, near-zero constraint violations, and better trade-offs between cost and safety than several benchmark methods.

Structures of LIG1 uncover the mechanism of sugar discrimination against 5′-RNA-DNA junctions during ribonucleotide excision repair

Ribonucleotides in DNA cause several types of genome instability and can be removed by ribonucleotide excision repair (RER) that is finalized by DNA ligase 1 (LIG1). However, the mechanism by which LIG1 discriminates the RER intermediate containing a 5'-RNA–DNA lesion generated by RNase H2-mediated cleavage of ribonucleotides remains unknown. Here, we determine X-ray structures of LIG1/5'-rG:C at the initial step of ligation where AMP is bound to the active site of the ligase, and uncover a large conformational change downstream the nick resulting in a shift at Arg(R)871 residue in the Adenylation domain of the ligase. Furthermore, we demonstrate a diminished ligation of the nick DNA substrate with a 5'-ribonucleotide in comparison to an efficient end joining of the nick substrate with a 3'-ribonucleotide by LIG1. Finally, our results demonstrate that mutations at the active site residues of the ligase and LIG1 disease-associated variants significantly impact the ligation efficiency of RNA–DNA heteroduplexes harboring “wrong” sugar at 3'- or 5'-end of nick. Collectively, our findings provide a novel atomic insight into proficient sugar discrimination by LIG1 during processing of the most abundant form of DNA damage in cells, genomic ribonucleotides, during initial step of the RER pathway.

Hybrid NenG/ZSM‐5 Towards Highly Selective and Efficient Photocatalysis for Generation of Leucodopaminechrome and Gluconic Acid Under Solar Light

AbstractGlucose, an abundant and renewable form of biomass, has garnered significant attention in research for its conversion into high‐value chemicals such as gluconic acid. Traditional methods for biomass transformation typically involve high energy input, elevated temperature, pressure, and costly systems. In contrast, photocatalysis emerges as a promising approach to produce organic molecules under mild conditions, harnessing energy from natural sunlight or lamps. This study presents the nitrogen‐enriched graphene with zeolite second Mobil–5 (NenG/ZSM‐5) photocatalyst, evaluated for generating high‐value chemicals (gluconic acid and leucodopaminechrome) under solar light irradiation. The NenG/ZSM‐5 photocatalyst, synthesized from nitrogen‐doped graphene and ZSM‐5, successfully converted dopamine into leucodopaminechrome (71.54 %) — a critical step in dopamine regeneration and transformed glucose into gluconic acid (85 %). The addition of ZSM‐5 to NenG provided stability and enhanced product selectivity. The outstanding performance of the NenG/ZSM‐5 photocatalyst can be attributed to its heightened solar light harvesting potential, appropriate energy band gap, and uniformly arranged π‐electron channels. This research focuses on solar conversion of glucose to gluconic acid and dopamine regeneration, with potential for further exploration in the research domain.

A streamlined framework for BEV-based 3D object detection with prior masking

In the field of autonomous driving, perception tasks based on Bird's-Eye-View (BEV) have attracted considerable research attention due to their numerous benefits. Despite recent advancements in performance, efficiency remains a challenge for real-world implementation. In this study, we propose an efficient and effective framework that constructs a spatio-temporal BEV feature from multi-camera inputs and leverages it for 3D object detection. Specifically, the success of our network is primarily attributed to the design of the lifting strategy and a tailored BEV encoder. The lifting strategy is tasked with the conversion of 2D features into 3D representations. In the absence of depth information in the images, we innovatively introduce a prior mask for the BEV feature, which can assess the significance of the feature along the camera ray at a low cost. Moreover, we design a lightweight BEV encoder, which significantly boosts the capacity of this physical-interpretation representation. In the encoder, we investigate the spatial relationships of the BEV feature and retain rich residual information from upstream. To further enhance performance, we establish a 2D object detection auxiliary head to delve into insights offered by 2D object detection and leverage the 4D information to explore the cues within the sequence. Benefiting from all these designs, our network can capture abundant semantic information from 3D scenes and strikes a balanced trade-off between efficiency and performance.

DCFF-Net: Deep Context Feature Fusion Network for High-Precision Classification of Hyperspectral Image

Hyperspectral images (HSI) contain abundant spectral information. Efficient extraction and utilization of this information for image classification remain prominent research topics. Previously, hyperspectral classification techniques primarily relied on statistical attributes and mathematical models of spectral data. Deep learning classification techniques have recently been extensively utilized for hyperspectral data classification, yielding promising outcomes. This study proposes a deep learning approach that uses polarization feature maps for classification. Initially, the polar co-ordinate transformation method was employed to convert the spectral information of all pixels in the image into spectral feature maps. Subsequently, the proposed Deep Context Feature Fusion Network (DCFF-NET) was utilized to classify these feature maps. The model was validated using three open-source hyperspectral datasets: Indian Pines, Pavia University, and Salinas. The experimental results indicated that DCFF-NET achieved excellent classification performance. Experimental results on three public HSI datasets demonstrated that the proposed method accurately recognized different objects with an overall accuracy (OA) of 86.68%, 94.73%, and 95.14% based on the pixel method, and 98.15%, 99.86%, and 99.98% based on the pixel-patch method.

A novel sequential estimation framework for battery state of health and remaining useful life based on sparse and limited data

Battery State of Health (SOH) estimation and Remaining Useful Life (RUL) prediction are significant for battery management systems in both electric vehicles and energy storage systems. Various battery Health Indicators (HIs) and abundant health information are generally utilized for SOH and RUL estimation. However, HIs and health information may not be available for various reasons such as sensor installation limitations, computational burden and communication delay of the system. To overcome the issue of sparse and limited data acquisition in real applications, this study proposed a novel battery SOH and RUL sequential estimation framework only utilizing sparse segments of time series voltage data. The Extreme Learning Machine (ELM) and Long Short Term Memory (LSTM) network are applied for SOH estimation and RUL prediction respectively. Locally Weighted Scatterplot Smoothing (LOWESS) is used for both data smoothing and sparse data reconstruction. Three common battery datasets are fully investigated for validation. The experiment results show well estimation accuracies in both battery SOH and RUL, demonstrating the effectiveness of the framework in limited data prediction. Several popular SOH and RUL estimation algorithms and two state-of-the-art works are compared to further elaborate the superiority of the proposed framework.

A 3D hierarchical cross-modality interaction network using transformers and convolutions for brain glioma segmentation in MR images.

Precise glioma segmentation from multi-parametric magnetic resonance (MR) images is essential for brain glioma diagnosis. However, due to the indistinct boundaries between tumor sub-regions and the heterogeneous appearances of gliomas in volumetric MR scans, designing a reliable and automated glioma segmentation method is still challenging. Although existing 3D Transformer-based or convolution-based segmentation networks have obtained promising results via multi-modal feature fusion strategies or contextual learning methods, they widely lack the capability of hierarchical interactions between different modalities and cannot effectively learn comprehensive feature representations related to all glioma sub-regions. To overcome these problems, in this paper, we propose a 3D hierarchical cross-modality interaction network (HCMINet) using Transformers and convolutions for accurate multi-modal glioma segmentation, which leverages an effective hierarchical cross-modality interaction strategy to sufficiently learn modality-specific and modality-shared knowledge correlated to glioma sub-region segmentation from multi-parametric MR images. In the HCMINet, we first design a hierarchical cross-modality interaction Transformer (HCMITrans) encoder to hierarchically encode and fuse heterogeneous multi-modal features by Transformer-based intra-modal embeddings and inter-modal interactions in multiple encoding stages, which effectively captures complex cross-modality correlations while modeling global contexts. Then, we collaborate an HCMITrans encoder with a modality-shared convolutional encoder to construct the dual-encoder architecture in the encoding stage, which can learn the abundant contextual information from global and local perspectives. Finally, in the decoding stage, we present a progressive hybrid context fusion (PHCF) decoder to progressively fuse local and global features extracted by the dual-encoder architecture, which utilizes the local-global context fusion (LGCF) module to efficiently alleviate the contextual discrepancy among the decoding features. Extensive experiments are conducted on two public and competitive glioma benchmark datasets, including the BraTS2020 dataset with 494 patients and the BraTS2021 dataset with 1251 patients. Results show that our proposed method outperforms existing Transformer-based and CNN-based methods using other multi-modal fusion strategies in our experiments. Specifically, the proposed HCMINet achieves state-of-the-art mean DSC values of 85.33% and 91.09% on the BraTS2020 online validation dataset and the BraTS2021 local testing dataset, respectively. Our proposed method can accurately and automatically segment glioma regions from multi-parametric MR images, which is beneficial for the quantitative analysis of brain gliomas and helpful for reducing the annotation burden of neuroradiologists.

An efficient channel recurrent Criss-cross attention network for epileptic seizure prediction

Epilepsy is a chronic disease caused by repeated abnormal discharge of neurons in the brain. Accurately predicting the onset of epilepsy can effectively improve the quality of life for patients with the condition. While there are many methods for detecting epilepsy, EEG is currently considered one of the most effective analytical tools due to the abundant information it provides about brain activity. The aim of this study is to explore potential time-frequency and channel features from multi-channel epileptic EEG signals and to develop a patient-specific seizure prediction network. In this paper, an epilepsy EEG signal classification algorithm called Channel Recurrent Criss-cross Attention Network (CRCANet) is proposed. Firstly, the spectrograms processed by the short-time fourier transform is input into a Convolutional Neural Network (CNN). Then, the spectrogram feature map obtained in the previous step is input into the channel attention module to establish correlations between channels. Subsequently, the feature diagram containing channel attention characteristics is input into the recurrent criss-cross attention module to enhance the information content of each pixel. Finally, two fully connected layers are used for classification. We validated the method on 13 patients in the public CHB-MIT scalp EEG dataset, achieving an average accuracy of 93.8 %, sensitivity of 94.3 %, and specificity of 93.5 %. The experimental results indicate that CRCANet can effectively capture the time-frequency and channel characteristics of EEG signals while improving training efficiency.

An effective multi-modal adaptive contextual feature information fusion method for Chinese long text classification

Chinese long text classification plays a vital role in Natural Language Processing. Compared to Chinese short texts, Chinese long texts contain more complex semantic feature information. Furthermore, the distribution of these semantic features is uneven due to the varying lengths of the texts. Current research on Chinese long text classification models primarily focuses on enhancing text semantic features and representing Chinese long texts as graph-structured data. Nonetheless, these methods are still susceptible to noise information and tend to overlook the deep semantic information in long texts. To address the above challenges, this study proposes a novel and effective method called MACFM, which introduces a deep feature information mining method and an adaptive modal feature information fusion strategy to learn the semantic features of Chinese long texts thoroughly. First, we present the DCAM module to capture complex semantic features in Chinese long texts, allowing the model to learn detailed high-level representation features. Then, we explore the relationships between word vectors and text graphs, enabling the model to capture abundant semantic information and text positional information from the graph. Finally, we develop the AMFM module to effectively combine different modal feature representations and eliminate the unrelated noise information. The experimental results on five Chinese long text datasets show that our method significantly improves the accuracy of Chinese long text classification tasks. Furthermore, the generalization experiments on five English datasets and the visualized results demonstrate the effectiveness and interpretability of the MACFM model.

Vitamin E: overview of history of discovery, mechanism of action, role and deficiency

Vitamin E, a collective term for tocopherols and tocotrienols, is vital for numerous biological functions, particularly due to its antioxidant properties. Tocopherols and tocotrienols share a common structure but differ in their side chains, influencing their bioactivities. Despite extensive research highlighting the potential in treating neurodegenerative diseases, cardiovascular disorders, and cancer, the clinical application of vitamin E is often limited by its poor bioavailability. Dietary sources of vitamin E include vegetable oils, nuts, seeds, and certain animal products, with α-tocopherol being the most abundant form in plasma. High doses of vitamin E can interact with medications like aspirin and warfarin, necessitating medical supervision. Deficiency in vitamin E, particularly in children, can lead to significant health issues, emphasizing the importance of adequate intake. This review explores the chemical properties, historical discovery, bioavailability, dietary sources, recommended intakes, and biological activities of vitamin E, highlighting its therapeutic potential and the challenges in its application.

Endmember extraction and abundance estimation algorithm based on double-compressed sampling

Based on double-compressed sampling, a hyperspectral spectral unmixing algorithm (SU_DCS) is proposed, which could directly complete the endmember extraction and abundance estimation. On the basis of the linear mixed model (LMM), we designed spatial and spectral sampling matrices, obtained spatial and spectral measurement data, and constructed a joint unmixing model containing endmember and abundance information. By using operator separation and Lagrangian multiplier algorithm, the endmember matrix, abundance matrix and remixing image can be quickly obtained by matrix operation. The parameters of the unmixing algorithm, including regularization parameter, convergence threshold and spatial sampling rate, are determined using synthetic simulated hyperspectral data. The proposed algorithm is applied to two kinds of real hyperspectral data, with or without ground truth, in order to verify the effectiveness and reliability of the algorithm. Firstly, we provide the performance of the algorithm on real datasets without ground truth. Compared with algorithm VCA_FCLS and algorithm CPPCA_VCA_FCLS, the endmember spectral curve extracted by the proposed SU_DCS is almost consistent with that obtained by VCA_FCLS, and is more smooth than that of obtained by CPPCA_VCA_FCLS. Additionally, the abundance estimation map estimated by the SU_DCS has consistency with the results obtained by VCA_FCLS. Moreover, the proposed SU_DCS has higher peak signal-to-noise ratio (PSNR) for remixing images with higher computational efficiency. Secondly, we provide the performance of the proposed algorithm on four real datasets with ground truth, including dataset Cuprite, dataset Samson, dataset Jasper and dataset Urban. We provide the results of endmember extraction and abundance estimation from the compressed data under different sampling rate conditions. The extracted endmember maintains good consistency with the true spectral curves, and the estimated abundance map can also maintain good spatial consistency with the ground truth. The comparison results with other four comparative algorithms also indicate that the proposed algorithm can obtain relatively accurate endmembers and abundance information from compressed data, the reliability and validity of the proposed algorithm have been proved. In summary, the main innovation of the proposed algorithm is that it can extract endmembers and estimate abundance with high accuracy from a small amount of measurement data.