Explainable spatio-temporal graph evolution learning with applications to dynamic brain network analysis during development.

Modeling dynamic interactions among network components is crucial to uncovering the evolution mechanisms of complex networks. Recently, spatio-temporal graph learning methods have achieved noteworthy results in characterizing the dynamic changes of inter-node relations (INRs). However, challenges remain: The spatial neighborhood of an INR is underexploited, and the spatio-temporal dependencies in INRs' dynamic changes are overlooked, ignoring the influence of historical states and local information. In addition, the model's explainability has been understudied. To address these issues, we propose an explainable spatio-temporal graph evolution learning (ESTGEL) model to model the dynamic evolution of INRs. Specifically, an edge attention module is proposed to utilize the spatial neighborhood of an INR at multi-level, i.e., a hierarchy of nested subgraphs derived from decomposing the initial node-relation graph. Subsequently, a dynamic relation learning module is proposed to capture the spatio-temporal dependencies of INRs. The INRs are then used as adjacent information to improve the node representation, resulting in comprehensive delineation of dynamic evolution of the network. Finally, the approach is validated with real data on brain development study. Experimental results on dynamic brain networks analysis reveal that brain functional networks transition from dispersed to more convergent and modular structures throughout development. Significant changes are observed in the dynamic functional connectivity (dFC) associated with functions including emotional control, decision-making, and language processing.

A Deep Dynamic Causal Learning Model to Study Changes in Dynamic Effective Connectivity during Brain Development.

OBJECTIVE: Brain dynamic effective connectivity (dEC), characterizes the information transmission patterns between brain regions that change over time, which provides insight into the biological mechanism underlying brain development. However, most existing methods predominantly capture fixed or temporally invariant EC, leaving dEC largely unexplored. METHODS: Herein we propose a deep dynamic causal learning model specifically designed to capture dEC. It includes a dynamic causal learner to detect time-varying causal relationships from spatio-temporal data, and a dynamic causal discriminator to validate these findings by comparing original and reconstructed data. RESULTS: Our model outperforms established baselines in the accuracy of identifying dynamic causalities when tested on the simulated data. When applied to the Philadelphia Neurodevelopmental Cohort, the model uncovers distinct patterns in dEC networks across different age groups. Specifically, the evolution process of brain dEC networks in young adults is more stable than in children, and significant differences in information transfer patterns exist between them. CONCLUSION: This study highlights the brain's developmental trajectory, where networks transition from undifferentiated to specialized structures with age, in accordance with the improvement of an individual's cognitive and information processing capability. SIGNIFICANCE: The proposed model consists of the identification and verification of dynamic causality, utilizing the spatio-temporal fusing information from fMRI. As a result, it can accurately detect dEC and characterize its evolution over age.

Highly Efficient Separation of Ethanol Amines and Cyanides via Ionic Magnetic Mesoporous Nanomaterials.

Simple and efficient sample pretreatment methods are important for analysis and detection of chemical warfare agents (CWAs) in environmental and biological samples. Despite many commercial materials or reagents that have been already applied in sample preparation, such as SPE columns, few materials with specificity have been utilized for purification or enrichment. In this study, ionic magnetic mesoporous nanomaterials such as poly(4-VB)@M-MSNs (magnetic mesoporous silicon nanoparticles modified by 4-vinyl benzene sulfonic acid) and Co2+@M-MSNs (magnetic mesoporous silicon nanoparticles modified by cobalt ions) with high absorptivity for ethanol amines (EAs, nitrogen mustard degradation products) and cyanide were successfully synthesized. The special nanomaterials were obtained by modification of magnetic mesoporous particles prepared based on co-precipitation using -SO3H and Co2+. The materials were fully characterized in terms of their composition and structure. The results indicated that poly(4-VB)@M-MSNs or Co2+@M-MSNs had an unambiguous core-shell structure with a BET of 341.7 m2·g-1 and a saturation magnetization intensity of 60.66 emu·g-1 which indicated the good thermal stability. Poly(4-VB)@M-MSNs showed selective adsorption for EAs while the Co2+@M-MSNs were for cyanide, respectively. The adsorption capacity quickly reached the adsorption equilibrium within the 90 s. The saturated adsorption amounts were MDEA = 35.83 mg·g-1, EDEA = 35.00 mg·g-1, TEA = 17.90 mg·g-1 and CN-= 31.48 mg·g-1, respectively. Meanwhile, the adsorption capacities could be maintained at 50-70% after three adsorption-desorption cycles. The adsorption isotherms were confirmed as the Langmuir equation and the Freundlich equation, respectively, and the adsorption mechanism was determined by DFT calculation. The adsorbents were applied for enrichment of targets in actual samples, which showed great potential for the verification of chemical weapons and the destruction of toxic chemicals.

A Demographic-Conditioned Variational Autoencoder for fMRI Distribution Sampling and Removal of Confounds.

Objective: fMRI and derived measures such as functional connectivity (FC) have been used to predict brain age, general fluid intelligence, psychiatric disease status, and preclinical neurodegenerative disease. However, it is not always clear that all demographic confounds, such as age, sex, and race, have been removed from fMRI data. Additionally, many fMRI datasets are restricted to authorized researchers, making dissemination of these valuable data sources challenging. Methods: We create a variational autoencoder (VAE)-based model, DemoVAE, to decorrelate fMRI features from demographics and generate high-quality synthetic fMRI data based on user-supplied demographics. We train and validate our model using two large, widely used datasets, the Philadelphia Neurodevel-opmental Cohort (PNC) and Bipolar and Schizophrenia Network for Intermediate Phenotypes (BSNIP). Results: We find that DemoVAE recapitulates group differences in fMRI data while capturing the full breadth of individual variations. Significantly, we also find that most clinical and computerized battery fields that are correlated with fMRI data are not correlated with DemoVAE latents. An exception are several fields related to schizophrenia medication and symptom severity. Conclusion: Our model generates fMRI data that captures the full distribution of FC better than traditional VAE or GAN models. We also find that most prediction using fMRI data is dependent on correlation with, and prediction of, demographics. Significance: Our DemoVAE model allows for generation of high quality synthetic data conditioned on subject demographics as well as the removal of the confounding effects of demographics. We identify that FC-based prediction tasks are highly influenced by demographic confounds.

A Demographic-Conditioned Variational Autoencoder for fMRI Distribution Sampling and Removal of Confounds.

Objective: fMRI and derived measures such as functional connectivity (FC) have been used to predict brain age, general fluid intelligence, psychiatric disease status, and preclinical neurodegenerative disease. However, it is not always clear that all demographic confounds, such as age, sex, and race, have been removed from fMRI data. Additionally, many fMRI datasets are restricted to authorized researchers, making dissemination of these valuable data sources challenging. Methods: We create a variational autoencoder (VAE)-based model, DemoVAE, to decorrelate fMRI features from demographics and generate high-quality synthetic fMRI data based on user-supplied demographics. We train and validate our model using two large, widely used datasets, the Philadelphia Neurodevelopmental Cohort (PNC) and Bipolar and Schizophrenia Network for Intermediate Phenotypes (BSNIP). Results: We find that DemoVAE recapitulates group differences in fMRI data while capturing the full breadth of individual variations. Significantly, we also find that most clinical and computerized battery fields that are correlated with fMRI data are not correlated with DemoVAE latents. An exception are several fields related to schizophrenia medication and symptom severity. Conclusion: Our model generates fMRI data that captures the full distribution of FC better than traditional VAE or GAN models. We also find that most prediction using fMRI data is dependent on correlation with, and prediction of, demographics. Significance: Our DemoVAE model allows for generation of high quality synthetic data conditioned on subject demographics as well as the removal of the confounding effects of demographics. We identify that FC-based prediction tasks are highly influenced by demographic confounds.

Multiview hyperedge-aware hypergraph embedding learning for multisite, multiatlas fMRI based functional connectivity network analysis.

Recently, functional magnetic resonance imaging (fMRI) based functional connectivity network (FCN) analysis via graph convolutional networks (GCNs) has shown promise for automated diagnosis of brain diseases by regarding the FCNs as irregular graph-structured data. However, multiview information and site influences of the FCNs in a multisite, multiatlas fMRI scenario have been understudied. In this paper, we propose a Class-consistency and Site-independence Multiview Hyperedge-Aware HyperGraph Embedding Learning (CcSi-MHAHGEL) framework to integrate FCNs constructed on multiple brain atlases in a multisite fMRI study. Specifically, for each subject, we first model brain network as a hypergraph for every brain atlas to characterize high-order relations among multiple vertexes, and then introduce a multiview hyperedge-aware hypergraph convolutional network (HGCN) to extract a multiatlas-based FCN embedding where hyperedge weights are adaptively learned rather than employing the fixed weights precalculated in traditional HGCNs. In addition, we formulate two modules to jointly learn the multiatlas-based FCN embeddings by considering the between-subject associations across classes and sites, respectively, i.e., a class-consistency module to encourage both compactness within every class and separation between classes for promoting discrimination in the embedding space, and a site-independence module to minimize the site dependence of the embeddings for mitigating undesired site influences due to differences in scanning platforms and/or protocols at multiple sites. Finally, the multiatlas-based FCN embeddings are fed into a few fully connected layers followed by the soft-max classifier for diagnosis decision. Extensive experiments on the ABIDE demonstrate the effectiveness of our method for autism spectrum disorder (ASD) identification. Furthermore, our method is interpretable by revealing ASD-relevant brain regions that are biologically significant.

Exploring General Intelligence via Gated Graph Transformer in Functional Connectivity Studies.

Functional connectivity (FC) as derived from fMRI has emerged as a pivotal tool in elucidating the intricacies of various psychiatric disorders and delineating the neural pathways that underpin cognitive and behavioral dynamics inherent to the human brain. While Graph Neural Networks (GNNs) offer a structured approach to represent neuroimaging data, they are limited by their need for a predefined graph structure to depict associations between brain regions, a detail not solely provided by FCs. To bridge this gap, we introduce the Gated Graph Transformer (GGT) framework, designed to predict cognitive metrics based on FCs. Empirical validation on the Philadelphia Neurodevelopmental Cohort (PNC) underscores the superior predictive prowess of our model, further accentuating its potential in identifying pivotal neural connectivities that correlate with human cognitive processes.

Magnetic mesoporous Fe3O4@nSiO2@mSiO2 nanoparticles for high-throughput mass spectrometry detection of hydrolyzed products of organophosphorus nerve agents.

Rapid and accurate detection of hydrolyzed products of organophosphorus nerve agents (OPNAs) is an important method to effectively confirm the use of these agents. OPNAs are rapidly hydrolyzed to the methyl phosphonates (MPs) in the environment, which can be used as environmental traceability marker for OPNAs. Herein, magnetic mesoporous materials combined with real-time in situ mass spectrometry (MS) were used to achieve high-throughput detection of MPs. Novel magnetic mesoporous nanoparticles Fe3O4@nSiO2@mSiO2 were synthesized via co-condensation of tetraethyl orthosilicate and cetyltrimethylammonium bromide (CTAB) on the surface of nonporous silica-coated Fe3O4 under alkaline conditions. CTAB templates were removed by the reflux of ethanol (0.0375 mM ammonium nitrate) to form mesoporous SiO2, which has a large specific surface area of 549 m2 g-1 and an excellent magnetization strength of 59.6 emu g-1. A quick, cost-effective, rugged, and safe magnetic preparation method, magnetic QuEChERS, was established with magnetic mesoporous nanoparticles (Fe3O4@nSiO2@mSiO2) as adsorption materials for direct analysis in real-time and tandem MS (DART-MS/MS) of MPs in environmental samples. The method exhibits good linearity (R2 > 0.992) in the range of 20.0-4.00 µg mL-1, the limits of detection were <5.00 ng mL-1, the limits of quantification were <20.0 ng mL-1, and the extraction recoveries were 70.2-98.1%, with relative standard deviations (RSDs) in the range of 1.97-10.6%. Additionally, using this method, analysis of 70 environmental samples could be completed within 20 min. Then, the M-QuEChERS-DART-MS/MS method was applied to the 52nd Organisation for the Prohibition of Chemical Weapons (OPCW) environmental spiked samples analysis, where the accuracy was 95.2-116%, and the RSD was 1.16-7.83%. The results demonstrated that Fe3O4@nSiO2@mSiO2 based on the QuEChERS method can quickly and efficiently remove the matrix of environmental samples and when coupled with the DART-MS/MS can achieve high-throughput determination of MPs in environmental samples.

Interpretable Cognitive Ability Prediction: A Comprehensive Gated Graph Transformer Framework for Analyzing Functional Brain Networks.

Graph convolutional deep learning has emerged as a promising method to explore the functional organization of the human brain in neuroscience research. This paper presents a novel framework that utilizes the gated graph transformer (GGT) model to predict individuals' cognitive ability based on functional connectivity (FC) derived from fMRI. Our framework incorporates prior spatial knowledge and uses a random-walk diffusion strategy that captures the intricate structural and functional relationships between different brain regions. Specifically, our approach employs learnable structural and positional encodings (LSPE) in conjunction with a gating mechanism to efficiently disentangle the learning of positional encoding (PE) and graph embeddings. Additionally, we utilize the attention mechanism to derive multi-view node feature embeddings and dynamically distribute propagation weights between each node and its neighbors, which facilitates the identification of significant biomarkers from functional brain networks and thus enhances the interpretability of the findings. To evaluate our proposed model in cognitive ability prediction, we conduct experiments on two large-scale brain imaging datasets: the Philadelphia Neurodevelopmental Cohort (PNC) and the Human Connectome Project (HCP). The results show that our approach not only outperforms existing methods in prediction accuracy but also provides superior explainability, which can be used to identify important FCs underlying cognitive behaviors.

Enhancing the Performance of the p-n Heterostructure Electrolyte for Solid Oxide Fuel Cells via A-Site-Deficiency Engineering.

Semiconductor ionic electrolytes are attracting growing interest for developing low-temperature solid oxide fuel cells (LT-SOFCs). Our recent study has proposed a p-n heterostructure electrolyte based on perovskite oxide BaCo0.4Fe0.4Zr0.1Y0.1O3-δ (BCFZY) and ZnO, achieving promising fuel cell performance. Herein, to further improve the performance of the heterostructure electrolyte, an A-site-deficiency strategy is used to solely modify BCFZY for regulating the ionic conduction and catalytic activity of the heterostructure. Two new electrolytes, B0.9CFZY-ZnO and B0.8CFZY-ZnO, were developed and systematically studied. The results show that the two samples gain improved ionic conductivity and auxiliary catalytic activity after A-site deficiency as a result of the increment of the surface and interface oxygen vacancies. The single cells with B0.9CFZY-ZnO and B0.8CFZY-ZnO exhibit enhanced peak power outputs at 450-550 °C compared to the cell based on B1.0CFZY-ZnO (typically, 745 and 795 vs 542 mW cm-2 at 550 °C). Particular attention is paid to the impact of A-site deficiency on the interface energy band alignment between BxCFZY and ZnO, which suggests that the p-n heterojunction effect of BxCFZY-ZnO for charge carrier regulation can be tuned by A-site deficiency to enable high proton transport while avoiding fuel cell current leakage. This study thus confirms the feasibility of A-site-deficiency engineering to optimize the performance of the heterostructure electrolyte for developing LT-SOFCs.

Identifiability in Functional Connectivity May Unintentionally Inflate Prediction Results.

Functional magnetic resonance (fMRI) is an invaluable tool in studying cognitive processes in vivo. Many recent studies use functional connectivity (FC), partial correlation connectivity (PC), or fMRI-derived brain networks to predict phenotypes with results that sometimes cannot be replicated. At the same time, FC can be used to identify the same subject from different scans with great accuracy. In this paper, we show a method by which one can unknowingly inflate classification results from 61% accuracy to 86% accuracy by treating longitudinal or contemporaneous scans of the same subject as independent data points. Using the UK Biobank dataset, we find one can achieve the same level of variance explained with 50 training subjects by exploiting identifiability as with 10,000 training subjects without double-dipping. We replicate this effect in four different datasets: the UK Biobank (UKB), the Philadelphia Neurodevelopmental Cohort (PNC), the Bipolar and Schizophrenia Network for Intermediate Phenotypes (BSNIP), and an OpenNeuro Fibromyalgia dataset (Fibro). The unintentional improvement ranges between 7% and 25% in the four datasets. Additionally, we find that by using dynamic functional connectivity (dFC), one can apply this method even when one is limited to a single scan per subject. One major problem is that features such as ROIs or connectivities that are reported alongside inflated results may confuse future work. This article hopes to shed light on how even minor pipeline anomalies may lead to unexpectedly superb results.

Angle Basis: a Generative Model and Decomposition for Functional Connectivity.

Functional connectivity (FC) is one of the most common inputs to fMRI-based predictive models, due to a combination of its simplicity and robustness. However, there may be a lack of theoretical models for the generation of FC. In this work, we present a straightforward decomposition of FC into a set of basis states of sine waves with an additional jitter component. We show that the decomposition matches the predictive ability of FC after including 5-10 bases. We also find that both the decomposition and its residual have approximately equal predictive value, and when combined into an ensemble, exceed the AUC of FC-based prediction by up to 5%. Additionally, we find the residual can be used for subject fingerprinting, with 97.3% same-subject, different-scan identifiability, compared to 62.5% for FC. Unlike PCA or Factor Analysis methods, our method does not require knowledge of a population to perform its decomposition; a single subject is enough. Our decomposition of FC into two equally-predictive components may lead to a novel appreciation of group differences in patient populations. Additionally, we generate synthetic patient FC based on user-specified characteristics such as age, sex, and disease diagnosis. By creating synthetic datasets or augmentations we may reduce the high financial burden associated with fMRI data acquisition.

Rapid detection of carbamate nerve agent analogues using dually functionalized gold nanoclusters.

Carbamate nerve agents (CMNAs) are a type of lethal cholinesterase inhibitor with one or more quaternary amine centres and aromatic rings. CMNAs have been recently added to the Annex on Chemicals of the Chemical Weapons Convention (CWC) and Schedules of Controlled Chemicals of China. In this study, a rapid, sensitive and selective method was developed for the fluorescence detection of ambenonium chloride (AC) through host-guest and electrostatic dual interactions between AC and cyclodextrin/11-mercaptoundecanoic acid (CD/MUA) dually functionalized gold nanoclusters (AuNCs). Through this method, AC was detected with a limit of detection of 10.0 ng/mL. Method evaluation showed high selectivity towards AC over other related compounds. The practical applicability was verified, as satisfactory recoveries were obtained for AC spiked in river water and urine, as well as Proficiency Test samples from Organisation for the Prohibition of Chemical Weapons (OPCW). In addition, a fluorescence sensing array comprising four AuNCs was designed to distinguish six carbamates and structurally similar compounds. This method provides a potential approach for the rapid, sensitive and selective recognition and detection of CMNAs.

A Hybrid Trust Model against Insider Packet Drop Attacks in Wireless Sensor Networks.

Quick and accurate detection of inside packet drop attackers is of critical importance to reduce the damage they can have on the network. Trust mechanisms have been widely used in wireless sensor networks for this purpose. However, existing trust models are not effective because they cannot distinguish between packet drops caused by an attack and those caused by normal network failure. We observe that insider packet drop attacks will cause more consecutive packet drops than a network abnormality. Therefore, we propose the use of consecutive packet drops to speed up the detection of inside packet drop attackers. In this article, we describe a new trust model based on consecutive drops and develop a hybrid trust mechanism to seamlessly integrate the new trust model with existing trust models. We perform extensive OPNET (Optimized Network Engineering Tool) simulations using a geographic greedy routing protocol to validate the effectiveness of our new model. The simulation results show that our hybrid trust model outperforms existing trust models for all types of inside packet drop attacks, not only in terms of detection speed and accuracy as it is designed for, but also in terms of other important network performance metrics, such as packet delivery rate, routing reliability, and energy efficiency.

Dynamic weighted hypergraph convolutional network for brain functional connectome analysis.

The hypergraph structure has been utilized to characterize the brain functional connectome (FC) by capturing the high order relationships among multiple brain regions of interest (ROIs) compared with a simple graph. Accordingly, hypergraph neural network (HGNN) models have emerged and provided efficient tools for hypergraph embedding learning. However, most existing HGNN models can only be applied to pre-constructed hypergraphs with a static structure during model training, which might not be a sufficient representation of the complex brain networks. In this study, we propose a dynamic weighted hypergraph convolutional network (dwHGCN) framework to consider a dynamic hypergraph with learnable hyperedge weights. Specifically, we generate hyperedges based on sparse representation and calculate the hyper similarity as node features. The hypergraph and node features are fed into a neural network model, where the hyperedge weights are updated adaptively during training. The dwHGCN facilitates the learning of brain FC features by assigning larger weights to hyperedges with higher discriminative power. The weighting strategy also improves the interpretability of the model by identifying the highly active interactions among ROIs shared by a common hyperedge. We validate the performance of the proposed model on two classification tasks with three paradigms functional magnetic resonance imaging (fMRI) data from Philadelphia Neurodevelopmental Cohort. Experimental results demonstrate the superiority of our proposed method over existing hypergraph neural networks. We believe our model can be applied to other applications in neuroimaging for its strength in representation learning and interpretation.

Latent Similarity Identifies Important Functional Connections for Phenotype Prediction.

OBJECTIVE: Endophenotypes such as brain age and fluid intelligence are important biomarkers of disease status. However, brain imaging studies to identify these biomarkers often encounter limited numbers of subjects but high dimensional imaging features, hindering reproducibility. Therefore, we develop an interpretable, multivariate classification/regression algorithm, called Latent Similarity (LatSim), suitable for small sample size but high feature dimension datasets. METHODS: LatSim combines metric learning with a kernel similarity function and softmax aggregation to identify task-related similarities between subjects. Inter-subject similarity is utilized to improve performance on three prediction tasks using multi-paradigm fMRI data. A greedy selection algorithm, made possible by LatSim's computational efficiency, is developed as an interpretability method. RESULTS: LatSim achieved significantly higher predictive accuracy at small sample sizes on the Philadelphia Neurodevelopmental Cohort (PNC) dataset. Connections identified by LatSim gave superior discriminative power compared to those identified by other methods. We identified 4 functional brain networks enriched in connections for predicting brain age, sex, and intelligence. CONCLUSION: We find that most information for a predictive task comes from only a few (1-5) connections. Additionally, we find that the default mode network is over-represented in the top connections of all predictive tasks. SIGNIFICANCE: We propose a novel prediction algorithm for small sample, high feature dimension datasets and use it to identify connections in task fMRI data. Our work can lead to new insights in both algorithm design and neuroscience research.

Distance Correlation-Based Brain Functional Connectivity Estimation and Non-Convex Multi-Task Learning for Developmental fMRI Studies.

OBJECTIVE: Resting-state functional magnetic resonance imaging (rs-fMRI)-derived functional connectivity (FC) patterns have been extensively used to delineate global functional organization of the human brain in healthy development and neuropsychiatric disorders. In this paper, we investigate how FC in males and females differs in an age prediction framework. METHODS: We first estimate FC between regions-of-interest (ROIs) using distance correlation instead of Pearson's correlation. Distance correlation, as a multivariate statistical method, explores spatial relations of voxel-wise time courses within individual ROIs and measures both linear and nonlinear dependence, capturing more complex between-ROI interactions. Then, we propose a novel non-convex multi-task learning (NC-MTL) model to study age-related gender differences in FC, where age prediction for each gender group is viewed as one task, and a composite regularizer with a combination of the non-convex l2,1-2 and l1-2 terms is introduced for selecting both common and task-specific features. RESULTS AND CONCLUSION: We validate the effectiveness of our NC-MTL model with distance correlation-based FC derived from rs-fMRI for predicting ages of both genders. The experimental results on the Philadelphia Neurodevelopmental Cohort demonstrate that our NC-MTL model outperforms several other competing MTL models in age prediction. We also compare the age prediction performance of our NC-MTL model using FC estimated by Pearson's correlation and distance correlation, which shows that distance correlation-based FC is more discriminative for age prediction than Pearson's correlation-based FC. SIGNIFICANCE: This paper presents a novel framework for functional connectome developmental studies, characterizing developmental gender differences in FC patterns.

AGNet: Automatic generation network for skin imaging reports.

Medical imaging has been increasingly adopted in the process of medical diagnosis, especially for skin diseases, where diagnoses based on skin pathology are extremely accurate. The diagnostic reports of skin pathology images has the distinguishing features of extreme repetitiveness and rigid formatting. However, reports written by inexperienced radiologists and pathologists can have a high error rate, and even experienced clinicians can find the reporting task both tedious and time-consuming. To address this challenge, this paper studies the automatic generation of diagnostic reports based on images of skin pathologies. A novel deep learning-based image caption framework named the automatic generation network (AGNet), which is an effective network for the automatic generation of skin imaging reports, is proposed. The proposed AGNet consists of four parts: (1) the image model that extracts features and classifies images; (2) the language model that codes data and generates words using comprehensible language; (3) the attention module that connects the "tail" of the image model and the "head" of the language model, and computes the relationship between images and captions; (4) the embedding and labeling module that processes the input caption data. In case study, The AGNet is verified on a skin pathological image dataset and compared with several state-of-the-art models. The results show that the AGNet achieves the highest scores of the evaluation metrics of image caption among all comparison models, demonstrating the promising performance of the proposed method.

Brain Functional Connectivity Analysis via Graphical Deep Learning.

OBJECTIVE: Graphical deep learning models provide a desirable way for brain functional connectivity analysis. However, the application of current graph deep learning models to brain network analysis is challenging due to the limited sample size and complex relationships between different brain regions. METHOD: In this work, a graph convolutional network (GCN) based framework is proposed by exploiting the information from both region-to-region connectivities of the brain and subject-subject relationships. We first construct an affinity subject-subject graph followed by GCN analysis. A Laplacian regularization term is introduced in our model to tackle the overfitting problem. We apply and validate the proposed model to the Philadelphia Neurodevelopmental Cohort for the brain cognition study. RESULTS: Experimental analysis shows that our proposed framework outperforms other competing models in classifying groups with low and high Wide Range Achievement Test (WRAT) scores. Moreover, to examine each brain region's contribution to cognitive function, we use the occlusion sensitivity analysis method to identify cognition-related brain functional networks. The results are consistent with previous research yet yield new findings. CONCLUSION AND SIGNIFICANCE: Our study demonstrates that GCN incorporating prior knowledge about brain networks offers a powerful way to detect important brain networks and regions associated with cognitive functions.

Age-Aware Utility Maximization in Relay-Assisted Wireless Powered Communication Networks.

This article investigates a relay-assisted wireless powered communication network (WPCN), where the access point (AP) inspires the auxiliary nodes to participate together in charging the sensor, and then the sensor uses its harvested energy to send status update packets to the AP. An incentive mechanism is designed to overcome the selfishness of the auxiliary node. In order to further improve the system performance, we establish a Stackelberg game to model the efficient cooperation between the AP-sensor pair and auxiliary node. Specifically, we formulate two utility functions for the AP-sensor pair and the auxiliary node, and then formulate two maximization problems respectively. As the former problem is non-convex, we transform it into a convex problem by introducing an extra slack variable, and then by using the Lagrangian method, we obtain the optimal solution with closed-form expressions. Numerical experiments show that the larger the transmit power of the AP, the smaller the age of information (AoI) of the AP-sensor pair and the less the influence of the location of the auxiliary node on AoI. In addition, when the distance between the AP and the sensor node exceeds a certain threshold, employing the relay can achieve better AoI performance than non-relaying systems.