Search

The United States is the second-largest waste generator in the world, generating 4.9 pounds (2.2 kg) of Municipal Solid Waste (MSW) per person each day. The excessive amount of waste generated poses serious health and environmental risks, especially because of the prevalence of illegal dumping practices, including improper waste disposal in unauthorized areas. To clean up illegal dumping, the government spends approximately USD 600 per ton, which amounts to USD 178 billion per year. Municipalities face a critical challenge to detect and prevent illegal dumping activities. Current techniques to detect illegal dumping have limited accuracy in detection and do not support an integrated solution of detecting dumping, identifying the vehicle, and a decision algorithm notifying the municipalities in real-time. To tackle this issue, an innovative solution has been developed, utilizing a You Only Look Once (YOLO) detector YOLOv5 for detecting humans, vehicles, license plates, and trash. The solution incorporates DeepSORT for effective identification of illegal dumping by analyzing the distance between a human and the trash’s bounding box. It achieved an accuracy of 97% in dumping detection after training on real-time examples and the COCO dataset covering both daytime and nighttime scenarios. This combination of YOLOv5, DeepSORT, and the decision module demonstrates robust capabilities in detecting dumping. The objective of this web-based application is to minimize the adverse effects on the environment and public health. By leveraging advanced object detection and tracking techniques, along with a user-friendly web application, it aims to promote a cleaner, healthier environment for everyone by reducing improper waste disposal.

Residential Short-term load forecasting is an important basis for power department to make dispatching plan reasonably. A short-term load forecasting framework was proposed that is based on Balanced Iterative Reducing and Clustering using Hierarchies (BIRCH) clustering algorithm, Convolutional Neural Network (CNN), and Gated Recurrent Unit (GRU). In this framework, based on historical load data collected by smart meters, BIRCH clustering algorithm is adopted to cluster users into multiple user groups according to different users’ electricity consumption habits. A multivariate time series dataset composed of load data, time data, and climate data are into the CNN network, which is composed of a one-dimensional convolutional layer and a pooling layer. The CNN network is responsible for extracting the potential relationship and high dimensional characteristics of different variables. After that, the data are input into the GRU network, and the sequence characteristics of the time sequence data are studied. Finally, the short-term load prediction results are output from the full-connected layer. Taking the open dataset provided by the Commission for Energy Regulation (CER) of Ireland as an example, the Mean Absolute Percentage Error (MAPE) of the proposed method reached 2.932 1%. Compared with the prediction efficiency and accuracy of ANN network, CNN network, and CNN-GRU network under the same conditions, the experimental results showed that the proposed method has higher prediction accuracy and higher training efficiency.

Stroke has a high disability rate and fatality rate. It is of great clinical significance to study the automatic recognition and segmentation of stroke lesions. Convolutional neural network can not make use of time sequence correlation of medical image data, and has the problem of low feature utilization. Therefore, a bidirectional recurrent U-Net (BIRU-Net) model was proposed for segmentation of lesions. First, a recurrent neural network is introduced to replace part of the convolutional layer in U-Net with an improved attention convolutional gate recursive unit (ACGRU), so that the segmentation model is not only suitable for small-scale annotated medical image data sets, but also has the characteristics of long-term memory. Second, a dual-channel fusion training mechanism is adopted to input the forward and reverse slice data of a single view into BIRU-Net at the same time, and realize bidirectional feature fusion in the process of model forward propagation, effectively utilizing the bidirectional dependence of slice sequence. Finally, the segmentation results of each single view are refused to effectively utilize the spatial context information of data. The experimental results of ATLAS data set show that the DSC value of the proposed method reaches 62.58%. Compared with other methods at the present stage, the proposed method can segment the lesion region more accurately.

IntroductionIschemic stroke patients commonly experience disorder of consciousness (DOC), leading to poorer discharge outcomes and higher mortality risks. Therefore, the identification of applicable electrophysiological biomarkers is crucial for the rapid diagnosis and evaluation of post-stroke disorder of consciousness (PS-DOC), while providing supportive evidence for cerebral neurology.MethodsIn our study, we conduct microstate analysis on resting-state electroencephalography (EEG) of 28 post-stroke patients with awake consciousness and 28 patients with PS-DOC, calculating the temporal features of microstates. Furthermore, we extract the Lempel-Ziv complexity of microstate sequences and the delta/alpha power ratio of EEG on spectral. Statistical analysis is performed to examine the distinctions in features between the two groups, followed by inputting the distinctive features into a support vector machine for the classification of PS-DOC.ResultsBoth groups obtain four optimal topographies of EEG microstates, but notable distinctions are observed in microstate C. Within the PS-DOC group, there is a significant increase in the mean duration and coverage of microstates B and C, whereas microstate D displays a contrasting trend. Additionally, noteworthy variations are found in the delta/alpha ratio and Lempel-Ziv complexity between the two groups. The integration of the delta/alpha ratio with microstates’ temporal and Lempel-Ziv complexity features demonstrates the highest performance in the classifier (Accuracy = 91.07%).DiscussionOur results suggest that EEG microstates can provide insights into the abnormal brain network dynamics in DOC patients post-stroke. Integrating the temporal and Lempel-Ziv complexity microstate features with spectral features offers a deeper understanding of the neuro mechanisms underlying brain damage in patients with DOC, holding promise as effective electrophysiological biomarkers for diagnosing PS-DOC.

Vision transformer architectures attract widespread interest due to their robust representation capabilities of global features. Transformer-based methods as the encoder achieve superior performance compared to convolutional neural networks and other popular networks in many segmentation tasks for medical images. Due to the complex structure of the brain and the approximate grayscale of healthy tissue and lesions, lesion segmentation suffers from over-smooth boundaries or inaccurate segmentation. Existing methods, including the transformer, utilize stacked convolutional layers as the decoder to uniformly treat each pixel as a grid, which is convenient for feature computation. However, they often neglect the high-frequency features of the boundary and focus excessively on the region features. We propose an effective method for lesion boundary rendering called TransRender, which adaptively selects a series of important points to compute the boundary features in a point-based rendering way. The transformer-based method is selected to capture global information during the encoding stage. Several renders efficiently map the encoded features of different levels to the original spatial resolution by combining global and local features. Furthermore, the point-based function is employed to supervise the render module generating points, so that TransRender can continuously refine the uncertainty region. We conducted substantial experiments on different stroke lesion segmentation datasets to prove the efficiency of TransRender. Several evaluation metrics illustrate that our method can automatically segment the stroke lesion with relatively high accuracy and low calculation complexity.

To solve the problem that Dempster-Shafer (D-S) evidence theory gives combines results contrary to with facts when dealing with conflict evidence, a novel method of conflict evidence combination was proposed. First, the Spearman correlation coefficient is improved and the support between evidences is calculated, and original evidence is amended for the first time. Then, combined with the advantages of the interval distance based on fixed integrals, the uncertainty of evidence is analyzed, a new discount coefficient is determined, and original evidence body is secondarily revised. Finally, the fusion results are obtained by using the Dempster combination rule. The calculation and example analysis demonstrates that the proposed method can effectively fuse the evidence of conflict, and has a higher basic probability distribution than the classical improved algorithm. The proposed method was used for carbon/carbon composite sedimentation data, and a carbon/carbon composite sedimentation mass prediction model based on improved D-S evidence theory was established. Compared with several classical classifiers and the existing prediction model based on D-S evidence theory, this model is increased in accuraey by 5%~13%, which proves its validity.

Aiming at the problem that traditional anomaly detection model has poor recognition effect on a small number of abnormal samples under the condition of data imbalance, in this paper we proposed a support vector data description algorithm combined with improved diffusion maps (DM-SVDD), constructed a new model and applied it to industry abnormal detection. The diffusion mapping algorithm was improved by introducing Euclidean distance and Mahalanobis distance to construct a new neighbor graph. Combined with support vector data description algorithm for modeling, the new model improved the recognition performance of normal samples, and the detection performance of abnormal samples was better than that from traditional models. Experimental data were selected of polysilicon ingot data sets. The results show that for an unbalanced data set formed by fewer abnormal samples, compared with traditional anomaly detection model, the model proposed in this paper can increase G-Mean optimally by 15.73% and F-Score optimally by 19.37%, which meet the requirements of industrial anomaly detection. The model can be used to guide the actual production process and reduce production costs.

ObjectiveBrain-computer interface (BCI) can translate intentions directly into instructions and greatly improve the interaction experience for disabled people or some specific interactive applications. To improve the efficiency of BCI, the objective of this study is to explore the feasibility of an audio-assisted visual BCI speller and a deep learning-based single-trial event related potentials (ERP) decoding strategy.ApproachIn this study, a two-stage BCI speller combining the motion-onset visual evoked potential (mVEP) and semantically congruent audio evoked ERP was designed to output the target characters. In the first stage, the different group of characters were presented in the different locations of visual field simultaneously and the stimuli were coded to the mVEP based on a new space division multiple access scheme. And then, the target character can be output based on the audio-assisted mVEP in the second stage. Meanwhile, a spatial-temporal attention-based convolutional neural network (STA-CNN) was proposed to recognize the single-trial ERP components. The CNN can learn 2-dimentional features including the spatial information of different activated channels and time dependence among ERP components. In addition, the STA mechanism can enhance the discriminative event-related features by adaptively learning probability weights.Main resultsThe performance of the proposed two-stage audio-assisted visual BCI paradigm and STA-CNN model was evaluated using the Electroencephalogram (EEG) recorded from 10 subjects. The average classification accuracy of proposed STA-CNN can reach 59.6 and 77.7% for the first and second stages, which were always significantly higher than those of the comparison methods (p < 0.05).SignificanceThe proposed two-stage audio-assisted visual paradigm showed a great potential to be used to BCI speller. Moreover, through the analysis of the attention weights from time sequence and spatial topographies, it was proved that STA-CNN could effectively extract interpretable spatiotemporal EEG features.

In the quality analysis of polysilicon ingot batching, a two-stage genetic algorithm (NRS-SVM-GA) combining the NRS-SVM model with genetic algorithm (GA) was proposed to solve the problem of neighborhood radius and SVM parameter values in the processing of continuous data of polysilicon ingot batting with rough set-support vector machine (NRS-SVM) model. The first stage of the algorithm, by searching for a new neighborhood radius, a better reduction set is obtained. In the second stage the attribute reduction results from the first stage are adopted to, by searching the new parameters of SVM, train the classification model with higher accuracy. According to the purpose of each stage, the corresponding fitness function and termination conditions are put forward. The distinctive features of this method is to implement the NRS-SVM automatic feature extraction and classification prediction, and run the two stages independently to avoid the time consumption for the evaluation of reduction by classifiec. The experimental results of polysilicon ingot batching data set show that this method has shorter running time, stable output, less features, and higher classification accuracy than the standard genetic algorithm.

This research improves our understanding of entrepreneurial intention in the Chinese cultural context. Drawing on career construction theory, we received 408 valid surveys from rural Chinese dwellers and examined the relationships rural Chinese have among “face consciousness,” indecisiveness, career adaptability, and entrepreneurial intention. We found that those who are fearful of losing face are less likely to have entrepreneurial intentions, but one’s desire to gain face has no significant direct impact on entrepreneurial intention. In addition, face consciousness and an indecisive personality interact to influence career adaptability and, in turn, entrepreneurial intention. In sum, this study supports the career construction perspective on understanding the formation of entrepreneurial intention and offers theoretical, practical, and policy implications for entrepreneurial career counseling and training.

Although face recognition has received a lot of attention and development in recent years, it is one of the research hotspots due to the low efficiency of Single Sample Per Person (SSPP) information in face recognition. In order to solve this problem, this article proposes a face recognition method based on virtual sample generation and multi-scale feature extraction. First, in order to increase the training sample information, a new NMF-MSB virtual sample generation method is proposed by combining the Non-negative Matrix Factorization (NMF) reconstruction strategy with Mirror transform(M), Sliding window(S), and Bit plane(B) sample extension methods. Second, a feature extraction method (named WPD-HOG-P) based on Wavelet Packet Decomposition, Histograms of Oriented Gradients, and image Pyramid is proposed. The proposed WPD-HOG-P method is beneficial to multi-scale facial image feature extraction. Finally, based on the extracted WPD-HOG-P features, the recognition model is established by using a grid search optimization support vector machine. Experimental results on ORL and FERET data sets show that the proposed method has higher recognition rates and lower computational complexity than the benchmark methods.

Background. There has been a gradual trend towards younger ageing of acute cerebral infarction in recent years. Atherosclerotic plaque rupture followed by dislodgement of emboli and resulting arterial embolism is an important mechanism for the development of acute cerebral infarction. Traditional independent risk factors for cerebral infarction have received attention from clinicians, but the risk factors for large artery atherosclerotic cerebral infarction are still unclear. Various blood biomarkers have an important role in the early diagnosis of large artery atherosclerotic cerebral infarction. Objective. To assess the diagnostic predictive value of a group of biomarkers for large artery atherosclerotic cerebral infarction. Methods. Lipoprotein-associated phospholipase A2 (LP-PLA2), trypsin-like protein (TPS), serum amyloid A (SAA), and supersensitive C-reactive protein (hs-CRP) levels were measured in the case group (30 cases) and control group (54 cases), respectively. Results. The differences in the general data between the two groups were not statistically significant (P>0.05). Logistic regression and ROC curve analysis showed that Lp-PLA2, TPS, and SAA were positively associated with the diagnosis of large atherosclerotic cerebral infarction (P

With the continuous improvement of machine learning methods, building the interatomic machine learning potential (MLP) based on the datasets from quantum mechanics calculations has become an effective technical approach to improving the accuracy of classical molecular dynamics simulation. The Spectral Neighbor Analysis Potential (SNAP) is one of the most commonly used machine learning potentials. It uses the bispectrum to encode the local environment of each atom in the lattice. The hyperparameter jmax controls the mapping complexity and precision between the local environment and the bispectrum descriptor. As the hyperparameter jmax increases, the description will become more accurate, but the number of parameters in the bispectrum descriptor will increase dramatically, increasing the computational complexity. In order to reduce the computational complexity without losing the computational accuracy, this paper proposes a two-level ensemble feature selection method (EFS) for a bispectrum descriptor, combining the perturbation method and the feature selector ensemble strategy. Based on the proposed method, the feature subset is selected from the original dataset of the bispectrum descriptor for building the dimension-reduced MLP. As a method application and validation, the data of Fe, Ni, Cu, Li, Mo, Si, and Ge metal elements are used to train the linear regression model based on SNAP for predicting these metals’ atomic energies and forces them to evaluate the performance of the feature subsets. The experimental results show that, compared to the features of SNAP and qSNAP, the training complexity improvement of our EFS method on the qSNAP feature is more effective than SNAP. Compared with the existing methods, when the feature subset size is 0.7 times that of the original features, the proposed EFS method based on the SSWRP ensemble strategy can achieve the best performance in terms of stability, achieving an average stability of 0.94 across all datasets. The training complexity of the linear regression model is reduced by about half, and the prediction complexity is reduced by about 30%.

Objective: We aimed to establish a scoring system to predict the risk of breast cancer-related lymphedema. Methods: From April 2017 to December 2018, 533 patients who previously underwent surgery for breast cancer were enrolled in this cross-sectional study. Univariate analysis was performed to explore and define the risk factors. A scoring system was then established on the basis of odds ratio values in the regression analysis. Results: The additive scoring system values ranged from 6 to 22. The receiver operating characteristic (ROC) curve of this scoring system showed a sensitivity and specificity of 83.3% and 57.3%, respectively, to predict the risk of lymphedema at a cut-off of 15.5 points; the area under the curve was 0.736 (95% confidence interval: 0.662–0.811), with χ2 = 5.134 (P = 0.274) for the Hosmer–Lemeshow test. Conclusions: The predictive efficiency and accuracy of the scoring system were acceptable, and the system could be used to predict and screen groups at high risk for breast cancer-related lymphedema. Keywords: Breast cancer lymphedema, Breast neoplasms, China, Cross-sectional studies, Lymphedema, Risk factors, ROC curve

Due to the narrow time window for the treatment of acute ischemic stroke, the stroke lesion area in the patient must be identified as quickly and accurately as possible to evaluate the risks and get the most timely and effective treatment. Therefore, there is great clinical significance in the study of automatic identification and segmentation methods for stroke lesions. In this paper, we propose a partitioning-stacking prediction fusion (PSPF) method based on an improved attention U-net to solve the problems of 3D-CNN-based networks, including their high computational cost and insufficient training data, and to achieve accurate segmentation of 3D stroke lesions. Our proposed PSPF method includes three steps in the first part. In Step 1, partitioning, we partition the slices obtained in a certain plane direction by slicing a Magnetic Resonance Imaging (MRI) into subsets according to the 2D graph similarity, then use each partitioned subset to perform training and prediction separately. In Step 2, stacking, we stack the 2D slice results of all subsets according to the position order in MRI before slicing and partitioning to form a 3D lesion result. In Step 3, fusion, we use soft voting to fuse the three orthogonal planes' 3D results that were obtained voxel by voxel in Steps 1 and 2. In the second part, we propose an improved attention U-net, which uses the features from three different scales to generate the attention gating coefficients that further improve training efficiency and segmentation accuracy. We implement a 6-fold cross-validation on the Anatomical Tracings of Lesions After Stroke (ATLAS) dataset to validate our method and model using metrics such as Dice Coefficient (DC), F2 score, and Area under Precision-Recall curve (APR). The results show that compared to the existing methods, our proposed method can not only improve the segmentation precision on unbalanced data but also improve the detailed performance of lesion segmentation. Our proposed method and model are generalized and accurate, demonstrating the good potential for clinical routines. The source codes and models in our method have been made publicly available at [available.upon.acceptance].

The recommendation algorithm based on Singular Value Decomposition (SVD)++ is a widely used algorithm for its good prediction performance. However, with the rapid increase of data in smart societies, the poor computational performance of the SVD++ recommendation algorithm becomes a prominent disadvantage, for it takes a longer time to optimize the objective function during constructing the prediction model. The learning rate function is a significant factor in the prediction model based on the SVD++ recommendation algorithm. It can directly affect the convergence speed of the prediction model and the performance of the model. The traditional model uses an exponential function, natural exponential function or piecewise constant as its learning rate function. In this paper, a novel adaptive learning rate (ALR) function is proposed, which combines the exponential with linear functions, and the function is applied to the SVD++ recommendation algorithm. The highlights of the paper are as follows. First, with a larger initial value, the proposed function descends quicker and tends to the end with a less step. Second, the theoretical properties of the proposed learning rate function are verified through theoretical analysis, including the theoretical proof of its convergence and the iteration speed comparison. Compared to the existing learning rate functions, the proposed ALR function works better on the convergence speed through mathematical derivation. Finally, the novel ALR function is applied to the SVD++ recommendation algorithm as recommendation model ALRSVD++. Some existing learning rate methods are used as benchmarks for illustrating the computation and prediction performances of proposed ALR function and its ALRSVD++ model. Experimental results demonstrated that the SVD++ recommendation algorithm based on the proposed ALR function improved computational efficiency of the training model ALRSVD++ significantly. Especially, to the larger size training dataset, the iterations and training time based on the proposed ALR function and ALRSVD++ model reduced in a great deal, without greatly sacrificing the recommendation performance.

In the background of artificial intelligence, the realization of smooth communication between people and machines has become the goal pursued by people. Mel spectrograms is a common method used in speech emotion recognition, focusing on the low-frequency part of speech. In contrast, the inverse Mel (IMel) spectrogram, which focuses on the high-frequency part, is proposed to comprehensively analyze emotions. Because the convolutional neural network-stacked sparse autoencoder (CNN-SSAE) can extract deep optimized features, the Mel-IMel dual-channel complementary structure is proposed. In the first channel, a CNN is used to extract the low-frequency information of the Mel spectrogram. The other channel extracts the high-frequency information of the IMel spectrogram. This information is transmitted into an SSAE to reduce the number of dimensions, and obtain the optimized information. Experimental results show that the highest recognition rates achieved on the EMO-DB, SAVEE, and RAVDESS datasets were 94.79%, 88.96%, and 83.18%, respectively. The conclusions are that the recognition rate of the two spectrograms was higher than that of each of the single spectrograms, which proves that the two spectrograms are complementary. The SSAE followed the CNN to get the optimized information, and the recognition rate was further improved, which proves the effectiveness of the CNN-SSAE network.

Consciousness is frequently assessed in acutely brain-injured patients. However, a direct measure of consciousness based on neurological examinations and behavioral observations is time-consuming and costly in medical labors. This paper aims to explore effective quantitative electroencephalography (EEG) measures to facilitate the objective assessment of consciousness. We do two studies in this paper. In the first study, the EEG signals recorded from 27 cerebral hemorrhage patients are analyzed to explore whether the phase synchrony index is effective in distinguishing the states of consciousness in cerebral hemorrhage patients. In the second study, 14 EEG recordings from four ischemic stroke patients, who have experienced more than two types of conscious disturbance, are studied to complement the analysis of the longitudinal value of the phase synchrony index. In both studies, a weighted sum of the six quantitative EEG features is analyzed on its correlation with the level of consciousness, and a linear regression model is built for the correlation analysis. In the first study, the phase synchrony index of the left and the right hemispheres (PSI-LR) in the beta band has shown a significant correlation with the level of consciousness in cerebral hemorrhage patients (Pearson correlation coefficients p = 0.500 and Spearman correlation coefficients p = 0.400). In the second study, PSI-LR also shows a high correlation with the longitudinal changes of consciousness in ischemic stroke patients (Pearson correlation coefficients p = 0.884 and Spearman correlation coefficients p = 0.887). Furthermore, the linear regression model combining the six quantitative EEG (QEEG) features shows a determination coefficient of 44.2% in cerebral hemorrhage patients and 83.8% in longitudinal ischemic stroke investigations, respectively. The PSI-LR is an effective indicator in not only identifying the disturbance of consciousness in cerebral hemorrhage patients, but also monitoring the changes of consciousness in ischemic stroke patients. A linear combination of the six QEEG features investigated in this paper is a new measure to improve the assessment of consciousness.

Accurate behavioral assessments of consciousness are crucial in guiding management as they provide diagnostic and prognostic information, but they are challenging since different clinical scales lead to varying results for the same patient. This paper aimed to investigate the phase synchrony index in differentiating the states of consciousness (wakefulness, somnolence, stupor, light coma, middle coma, and deep coma) in ischemic stroke. We evaluated whether the quantitative electroencephalography (EEG) measure, phase synchrony index of the left and right hemispheres, can facilitate the assessment of consciousness in stroke patients. This paper included 82 patients with ischemic stroke admitted for inpatient rehabilitation. The phase synchrony index of the left and right hemispheres was computed in the alpha band (8-12 Hz) and beta band (13-30 Hz), respectively. The associations between the phase synchrony index of the left and right hemispheres in two frequency bands with the clinical states, including the level of consciousness and the National Institutes of Health Stroke Scale score were analyzed. For further assessments of phase synchrony of the left and right hemispheres (PSI-LR), four local phase synchrony indexes in the beta band were also evaluated. The experiments result showed that PSI-LRs in the beta band correlated significantly with the level of consciousness of ischemic stroke patient and the National Institutes of Health Stroke Scale score, and they can identify the impaired consciousness in ischemic stroke patients with an accuracy of 84.15%. Compared with local phase synchrony, the phase synchrony index of channel FP1 and channel FP2 exhibited a more significant correlation with the level of consciousness than the other three local phase synchrony measures. These results suggest that the novel quantitative EEG measure, PSI-LR provides a new objective way to assess the level of consciousness in ischemic stroke patients.

Upland cotton (Gossypium hirsutum) is one of the most recalcitrant species for in vitro plant regeneration through somatic embryogenesis. Callus from only a few cultivars can produce embryogenic callus (EC), but the mechanism is not well elucidated. Here we screened a cultivar, CRI24, with high efficiency of EC produce. The expression of genes relevant to EC production was analyzed between the materials easy to or difficult to produce EC. Quantitative PCR showed that CRI24, which had a 100% EC differentiation rate, had the highest expression of the genes GhLEC1, GhLEC2, and GhFUS3. Three other cultivars, CRI12, CRI41, and Lu28 that formed few ECs expressed these genes only at low levels. Each of the genes involved in auxin transport (GhPIN7) and signaling (GhSHY2) was most highly expressed in CRI24, with low levels in the other three cultivars. WUSCHEL (WUS) is a homeodomain transcription factor that promotes the vegetative-to-embryogenic transition. We thus obtained the calli that ectopically expressed Arabidopsis thaliana Wus (AtWus) in G. hirsutum cultivar CRI12, with a consequent increase of 47.75% in EC differentiation rate compared with 0.61% for the control. Ectopic expression of AtWus in CRI12 resulted in upregulation of GhPIN7, GhSHY2, GhLEC1, GhLEC2, and GhFUS3. AtWus may therefore increase the differentiation potential of cotton callus by triggering the auxin transport and signaling pathways.

Early and timely diagnosis of stroke is critical for effective treatment, and the electroencephalogram (EEG) offers a low-cost, non-invasive solution. However, the shortage of high-quality patient EEG data often hampers the accuracy of diagnostic classification methods based on deep learning. To address this issue, our study designed a deep data amplification model named Progressive Conditional Generative Adversarial Network with Efficient Approximating Self Attention (PCGAN-EASA), which incrementally improves the quality of generated EEG features. This network can yield full-scale, fine-grained EEG features from the low-scale, coarse ones. Specially, to overcome the limitations of traditional generative models that fail to generate features tailored to individual patient characteristics, we developed an encoder with an effective approximating self-attention mechanism. This encoder not only automatically extracts relevant features across different patients but also reduces the computational resource consumption. Furthermore, the adversarial loss and reconstruction loss functions were redesigned to better align with the training characteristics of the network and the spatial correlations among electrodes. Extensive experimental results demonstrate that PCGAN-EASA provides the highest generation quality and the lowest computational resource usage compared to several existing approaches. Additionally, it significantly improves the accuracy of subsequent stroke classification tasks. [ABSTRACT FROM AUTHOR]

Abstract Phosphorus in crucial for all living organisms. In vertebrate, cellular phosphate homeostasis is partly controlled by XPR1, a poorly characterized inositol pyrophosphate-dependent phosphate exporter. Here, we report the cryo-EM structure of human XPR1, which forms a loose dimer with 10 transmembrane helices (TM) in each protomer. The structure consists of a scaffold domain (TM1, TM3-4) and a core domain (TM2, TM5-10) structurally related to ion-translocating rhodopsins. Bound phosphate is observed in a tunnel within the core domain at a narrow point that separates the tunnel into intracellular and extracellular vestibules. This site contains a cluster of basic residues that coordinate phosphate and a conserved W573 essential for export function. Loss of inositol pyrophosphate binding is accompanied by structural movements in TM9 and the W573 sidechain, closing the extracellular vestibule and blocking phosphate export. These findings provide insight into XPR1 mechanism and pave the way for further in-depth XPR1 studies.