Remote Sensing Image of The Landsat 8-9 Compressive Sensing via Non-Local Low-Rank Regularization with the Laplace Function.

Utilizing low-rank prior data in compressed sensing (CS) schemes for Landsat 8-9 remote sensing images (RSIs) has recently received widespread attention. Nevertheless, most CS algorithms focus on the sparsity of an RSI and ignore its low-rank (LR) nature. Therefore, this paper proposes a new CS reconstruction algorithm for Landsat 8-9 remote sensing images based on a non-local optimization framework (NLOF) that is combined with non-convex Laplace functions (NCLF) used for the low-rank approximation (LAA). Since the developed algorithm is based on an approximate low-rank model of the Laplace function, it can adaptively assign different weights to different singular values. Moreover, exploiting the structural sparsity (SS) and low-rank (LR) between the image patches enables the restored image to obtain better CS reconstruction results of Landsat 8-9 RSI than the existing models. For the proposed scheme, first, a CS reconstruction model is proposed using the non-local low-rank regularization (NLLRR) and variational framework. Then, the image patch grouping and Laplace function are used as regularization/penalty terms to constrain the CS reconstruction model. Finally, to effectively solve the rank minimization problem, the alternating direction multiplier method (ADMM) is used to solve the model. Extensive numerical experimental results demonstrate that the non-local variational framework (NLVF) combined with the low-rank approximate regularization (LRAR) method of non-convex Laplace function (NCLF) can obtain better reconstruction results than the more advanced image CS reconstruction algorithms. At the same time, the model preserves the details of Landsat 8-9 RSIs and the boundaries of the transition areas.

Twin support vector regression for characterizing uncertainty in surface reconstruction.

Surface reconstruction plays a pivotal role in various fields, including reverse engineering, and oil and gas exploration. However, errors in available data and insufficient surface morphology information often introduce uncertainty into the reconstruction. It is crucial to accurately characterize and visualize the uncertainty in surface reconstruction for risk analysis and planning further data collection. To this end, this paper proposes an uncertainty characterization method based on twin support vector regression. First, various modeling data are effectively integrated and the information contained in the high-confidence sample is efficiently utilized through the uncertainty interval generated by quantiles and upper/lower bound constraints. Second, well-path points are incorporated by imposing inequality constraints on the corresponding prediction points. Finally, in order to reduce computation time, the problem of uncertainty characterization is formulated as two smaller-scale quadratic programming. The results obtained from a real fault dataset and a synthetic dataset validate the effectiveness of the proposed method. When well data are available, the generated uncertainty envelopes are constrained by well data, which can partially mitigate reconstruction uncertainties.

Temporal Dynamic Synchronous Functional Brain Network for Schizophrenia Classification and Lateralization Analysis.

Available evidence suggests that dynamic functional connectivity can capture time-varying abnormalities in brain activity in resting-state cerebral functional magnetic resonance imaging (rs-fMRI) data and has a natural advantage in uncovering mechanisms of abnormal brain activity in schizophrenia (SZ) patients. Hence, an advanced dynamic brain network analysis model called the temporal brain category graph convolutional network (Temporal-BCGCN) was employed. Firstly, a unique dynamic brain network analysis module, DSF-BrainNet, was designed to construct dynamic synchronization features. Subsequently, a revolutionary graph convolution method, TemporalConv, was proposed based on the synchronous temporal properties of features. Finally, the first modular test tool for abnormal hemispherical lateralization in deep learning based on rs-fMRI data, named CategoryPool, was proposed. This study was validated on COBRE and UCLA datasets and achieved 83.62% and 89.71% average accuracies, respectively, outperforming the baseline model and other state-of-the-art methods. The ablation results also demonstrate the advantages of TemporalConv over the traditional edge feature graph convolution approach and the improvement of CategoryPool over the classical graph pooling approach. Interestingly, this study showed that the lower-order perceptual system and higher-order network regions in the left hemisphere are more severely dysfunctional than in the right hemisphere in SZ, reaffirmings the importance of the left medial superior frontal gyrus in SZ. Our code was available at: https://github.com/swfen/Temporal-BCGCN.

A Traditional Chinese Medicine Syndrome Classification Model Based on Cross-Feature Generation by Convolution Neural Network: Model Development and Validation.

BACKGROUND: Nowadays, intelligent medicine is gaining widespread attention, and great progress has been made in Western medicine with the help of artificial intelligence to assist in decision making. Compared with Western medicine, traditional Chinese medicine (TCM) involves selecting the specific treatment method, prescription, and medication based on the dialectical results of each patient's symptoms. For this reason, the development of a TCM-assisted decision-making system has lagged. Treatment based on syndrome differentiation is the core of TCM treatment; TCM doctors can dialectically classify diseases according to patients' symptoms and optimize treatment in time. Therefore, the essence of a TCM-assisted decision-making system is a TCM intelligent, dialectical algorithm. Symptoms stored in electronic medical records are mostly associated with patients' diseases; however, symptoms of TCM are mostly subjectively identified. In general electronic medical records, there are many missing values. TCM medical records, in which symptoms tend to cause high-dimensional sparse data, reduce algorithm accuracy. OBJECTIVE: This study aims to construct an algorithm model compatible for the multidimensional, highly sparse, and multiclassification task of TCM syndrome differentiation, so that it can be effectively applied to the intelligent dialectic of different diseases. METHODS: The relevant terms in electronic medical records were standardized with respect to symptoms and evidence-based criteria of TCM. We structuralized case data based on the classification of different symptoms and physical signs according to the 4 diagnostic examinations in TCM diagnosis. A novel cross-feature generation by convolution neural network model performed evidence-based recommendations based on the input embedded, structured medical record data. RESULTS: The data set included 5273 real dysmenorrhea cases from the Sichuan TCM big data management platform and the Chinese literature database, which were embedded into 60 fields after being structured and standardized. The training set and test set were randomly constructed in a ratio of 3:1. For the classification of different syndrome types, compared with 6 traditional, intelligent dialectical models and 3 click-through-rate models, the new model showed a good generalization ability and good classification effect. The comprehensive accuracy rate reached 96.21%. CONCLUSIONS: The main contribution of this study is the construction of a new intelligent dialectical model combining the characteristics of TCM by treating intelligent dialectics as a high-dimensional sparse vector classification task. Owing to the standardization of the input symptoms, all the common symptoms of TCM are covered, and the model can differentiate the symptoms with a variety of missing values. Therefore, with the continuous improvement of disease data sets, this model has the potential to be applied to the dialectical classification of different diseases in TCM.

Efficient self-attention mechanism and structural distilling model for Alzheimer's disease diagnosis.

Structural magnetic resonance imaging (sMRI) is commonly used for the identification of Alzheimer's disease because of its keen insight into atrophy-induced changes in brain structure. Current mainstream convolutional neural network-based deep learning methods ignore the long-term dependencies between voxels; thus, it is challenging to learn the global features of sMRI data. In this study, an advanced deep learning architecture called Brain Informer (BraInf) was developed based on an efficient self-attention mechanism. The proposed model integrates representation learning, feature distilling, and classifier modeling into a unified framework. First, the proposed model uses a multihead ProbSparse self-attention block for representation learning. This self-attention mechanism selects the first ⌊lnN⌋ elements that can represent the overall features from the perspective of probability sparsity, which significantly reduces computational cost. Subsequently, a structural distilling block is proposed that applies the concept of patch merging to the distilling operation. The block reduces the size of the three-dimensional tensor and further lowers the memory cost while preserving the original data as much as possible. Thus, there was a significant improvement in the space complexity. Finally, the feature vector was projected into the classification target space for disease prediction. The effectiveness of the proposed model was validated using the Alzheimer's Disease Neuroimaging Initiative dataset. The model achieved 97.97% and 91.89% accuracy on Alzheimer's disease and mild cognitive impairment classification tasks, respectively. The experimental results also demonstrate that the proposed framework outperforms several state-of-the-art methods.

Dietary vitamin A, C, and E intake and subsequent fracture risk at various sites: A meta-analysis of prospective cohort studies.

BACKGROUND: This study aimed to provide reliable estimates for dietary antioxidant vitamin (vitamins A, C, and E) intake and their effect on fracture risk at various sites. METHODS: The PubMed, EMBASE, and Cochrane Library databases were searched to identify prospective cohort studies published throughout October 2019. The pooled relative risk (RR) with its 95% confidence interval (CI) was calculated using a random-effects model. RESULTS: In total, 13 prospective cohort studies involving 384,464 individuals were selected for this meta-analysis. The summary RR indicated that increased antioxidant vitamin intake was associated with a reduced fracture risk (RR: 0.92; 95% CI: 0.86-0.98; P = .015). When stratified by the vitamin types, increased vitamin E intake was found to be associated with a reduced fracture risk (RR: 0.66; 95% CI: 0.46-0.95; P = .025), whereas increased vitamin A and C intake did not affect this risk. Increased antioxidant vitamin intake was associated with a reduced fracture risk, irrespective of fracture sites (HR: 0.90; 95% CI: 0.86-0.94; P < .001); however, it did not affect hip fracture risk. Furthermore, increased antioxidant vitamin intake was associated with a reduced fracture risk in men (RR: 0.81; 95% CI: 0.68-0.96; P = .017) and combined men and women (RR: 0.83; 95%CI: 0.73-0.93; P = .002); however, it did not affect fracture risk in women. CONCLUSION: Fracture risk at any site is significantly reduced with increased antioxidant vitamin intake, especially vitamin E intake and in men.

Dynamic Changes of NDVI in the Growing Season of the Tibetan Plateau During the Past 17 Years and Its Response to Climate Change.

The fragile alpine vegetation in the Tibetan Plateau (TP) is very sensitive to environmental changes, making TP one of the hotspots for studying the response of vegetation to climate change. Existing studies lack detailed description of the response of vegetation to different climatic factors using the method of multiple nested time series analysis and the method of grey correlation analysis. In this paper, based on the Normalized Difference Vegetation Index (NDVI) of TP in the growing season calculated from the MOD09A1 data product of Moderate-resolution Imaging Spectroradiometer (MODIS), the method of multiple nested time series analysis is adopted to study the variation trends of NDVI in recent 17 years, and the lag time of NDVI to climate change is analyzed using the method of Grey Relational Analysis (GRA). Finally, the characteristics of temporal and spatial differences of NDVI to different climate factors are summarized. The results indicate that: (1) the spatial distribution of NDVI values in the growing season shows a trend of decreasing from east to west, and from north to south, with a change rate of -0.13/10° E and -0.30/10° N, respectively. (2) From 2001 to 2017, the NDVI in the TP shows a slight trend of increase, with a growth rate of 0.01/10a. (3) The lag time of NDVI to air temperature is not obvious, while the NDVI response lags behind cumulative precipitation by zero to one month, relative humidity by two months, and sunshine duration by three months. (4) The effects of different climatic factors on NDVI are significantly different with the increase of the study period.