Search

In this paper, we develop a novel local graph pooling method, namely the Separated Subgraph-based Hierarchical Pooling (SSHPool), for graph classification. To this end, we commence by assigning the nodes of a sample graph into different clusters, resulting in a family of separated subgraphs. We individually employ a local graph convolution units as the local structure to further compress each subgraph into a coarsened node, transforming the original graph into a coarsened graph. Since these subgraphs are separated by different clusters and the structural information cannot be propagated between them, the local convolution operation can significantly avoid the over-smoothing problem arising in most existing Graph Neural Networks (GNNs). By hierarchically performing the proposed procedures on the resulting coarsened graph, the proposed SSHPool can effectively extract the hierarchical global feature of the original graph structure, encapsulating rich intrinsic structural characteristics. Furthermore, we develop an end-to-end GNN framework associated with the proposed SSHPool module for graph classification. Experimental results demonstrate the superior performance of the proposed model on real-world datasets, significantly outperforming state-of-the-art GNN methods in terms of the classification accuracies.

In this paper, we propose a new model to learn Adaptive Kernel-based Representations (AKBR) for graph classification. Unlike state-of-the-art R-convolution graph kernels that are defined by merely counting any pair of isomorphic substructures between graphs and cannot provide an end-to-end learning mechanism for the classifier, the proposed AKBR approach aims to define an end-to-end representation learning model to construct an adaptive kernel matrix for graphs. To this end, we commence by leveraging a novel feature-channel attention mechanism to capture the interdependencies between different substructure invariants of original graphs. The proposed AKBR model can thus effectively identify the structural importance of different substructures, and compute the R-convolution kernel between pairwise graphs associated with the more significant substructures specified by their structural attentions. Since each row of the resulting kernel matrix can be theoretically seen as the embedding vector of a sample graph, the proposed AKBR model is able to directly employ the resulting kernel matrix as the graph feature matrix and input it into the classifier for classification (i.e., the SoftMax layer), naturally providing an end-to-end learning architecture between the kernel computation as well as the classifier. Experimental results show that the proposed AKBR model outperforms existing state-of-the-art graph kernels and deep learning methods on standard graph benchmarks.

Infrared and visible image fusion (IVF) plays an important role in intelligent transportation system (ITS). The early works predominantly focus on boosting the visual appeal of the fused result, and only several recent approaches have tried to combine the high-level vision task with IVF. However, they prioritize the design of cascaded structure to seek unified suitable features and fit different tasks. Thus, they tend to typically bias toward to reconstructing raw pixels without considering the significance of semantic features. Therefore, we propose a novel prior semantic guided image fusion method based on the dual-modality strategy, improving the performance of IVF in ITS. Specifically, to explore the independent significant semantic of each modality, we first design two parallel semantic segmentation branches with a refined feature adaptive-modulation (RFaM) mechanism. RFaM can perceive the features that are semantically distinct enough in each semantic segmentation branch. Then, two pilot experiments based on the two branches are conducted to capture the significant prior semantic of two images, which then is applied to guide the fusion task in the integration of semantic segmentation branches and fusion branches. In addition, to aggregate both high-level semantics and impressive visual effects, we further investigate the frequency response of the prior semantics, and propose a multi-level representation-adaptive fusion (MRaF) module to explicitly integrate the low-frequent prior semantic with the high-frequent details. Extensive experiments on two public datasets demonstrate the superiority of our method over the state-of-the-art image fusion approaches, in terms of either the visual appeal or the high-level semantics.

Multi-task learning solves multiple correlated tasks. However, conflicts may exist between them. In such circumstances, a single solution can rarely optimize all the tasks, leading to performance trade-offs. To arrive at a set of optimized yet well-distributed models that collectively embody different trade-offs in one algorithmic pass, this paper proposes to view Pareto multi-task learning through the lens of multi-task optimization. Multi-task learning is first cast as a multi-objective optimization problem, which is then decomposed into a diverse set of unconstrained scalar-valued subproblems. These subproblems are solved jointly using a novel multi-task gradient descent method, whose uniqueness lies in the iterative transfer of model parameters among the subproblems during the course of optimization. A theorem proving faster convergence through the inclusion of such transfers is presented. We investigate the proposed multi-task learning with multi-task optimization for solving various problem settings including image classification, scene understanding, and multi-target regression. Comprehensive experiments confirm that the proposed method significantly advances the state-of-the-art in discovering sets of Pareto-optimized models. Notably, on the large image dataset we tested on, namely NYUv2, the hypervolume convergence achieved by our method was found to be nearly two times faster than the next-best among the state-of-the-art.

Graph Auto-Encoders (GAEs) are powerful tools for graph representation learning. In this paper, we develop a novel Hierarchical Cluster-based GAE (HC-GAE), that can learn effective structural characteristics for graph data analysis. To this end, during the encoding process, we commence by utilizing the hard node assignment to decompose a sample graph into a family of separated subgraphs. We compress each subgraph into a coarsened node, transforming the original graph into a coarsened graph. On the other hand, during the decoding process, we adopt the soft node assignment to reconstruct the original graph structure by expanding the coarsened nodes. By hierarchically performing the above compressing procedure during the decoding process as well as the expanding procedure during the decoding process, the proposed HC-GAE can effectively extract bidirectionally hierarchical structural features of the original sample graph. Furthermore, we re-design the loss function that can integrate the information from either the encoder or the decoder. Since the associated graph convolution operation of the proposed HC-GAE is restricted in each individual separated subgraph and cannot propagate the node information between different subgraphs, the proposed HC-GAE can significantly reduce the over-smoothing problem arising in the classical convolution-based GAEs. The proposed HC-GAE can generate effective representations for either node classification or graph classification, and the experiments demonstrate the effectiveness on real-world datasets.

Graph Neural Networks (GNNs) are powerful tools for graph classification. One important operation for GNNs is the downsampling or pooling that can learn effective embeddings from the node representations. In this paper, we propose a new hierarchical pooling operation, namely the Edge-Node Attention-based Differentiable Pooling (ENADPool), for GNNs to learn effective graph representations. Unlike the classical hierarchical pooling operation that is based on the unclear node assignment and simply computes the averaged feature over the nodes of each cluster, the proposed ENADPool not only employs a hard clustering strategy to assign each node into an unique cluster, but also compress the node features as well as their edge connectivity strengths into the resulting hierarchical structure based on the attention mechanism after each pooling step. As a result, the proposed ENADPool simultaneously identifies the importance of different nodes within each separated cluster and edges between corresponding clusters, that significantly addresses the shortcomings of the uniform edge-node based structure information aggregation arising in the classical hierarchical pooling operation. Moreover, to mitigate the over-smoothing problem arising in existing GNNs, we propose a Multi-distance GNN (MD-GNN) model associated with the proposed ENADPool operation, allowing the nodes to actively and directly receive the feature information from neighbors at different random walk steps. Experiments demonstrate the effectiveness of the MD-GNN associated with the proposed ENADPool.

Antisense oligonucleotide (ASO) is a novel therapeutic platform for targeted cancer therapy. Previously, we have demonstrated that miR-146b-5p plays an important role in colorectal cancer progression. However, a safe and effective strategy for delivery of an ASO to its targeted RNA remains as a major hurdle in translational advances. Human umbilical cord mesenchymal cell (hUC-MSC)-derived exosomes were used as vehicles to deliver an anti-miR-146b-5p ASO (PMO-146b). PMO-146b was assembled onto the surface of exosomes (e) through covalent conjugation to an anchor peptide CP05 (P) that recognized an exosomal surface marker, CD63, forming a complex named ePPMO-146b. After ePPMO-146b treatment, cell proliferation, uptake ability, and migration assays were performed, and epithelial-mesenchymal transition progression was evaluated in vitro. A mouse xenograft model was used to determine the antitumor effect and distribution of ePPMO-146b in vivo. ePPMO-146b was taken up by SW620 cells and effectively inhibited cell proliferation and migration. The conjugate also exerted antitumor efficacy in a xenograft mouse model of colon cancer by systematic administration, where PPMO-146b was enriched in tumor tissue. Our study highlights the potential of hUC-MSC-derived exosomes anchored with PPMO-146b as a novel safe and effective approach for PMO backboned ASO delivery.Graphical AbstractSchematic illustration of the preparation of an exosomal anchor peptide (CP05)-PMO that conjugately binds to exosomes from hUC-MSCs (ePPMO-146b) and the antitumor effect of ePPMO-146b in CRC, which occurs through the inhibition of Smad signaling and epithelial-mesenchymal transition.

In this paper, a novel three-dimensional (3D) irregularshaped geometry-based stochastic model (IS-GBSM) is proposedfor sixth-generation (6G) millimeter wave (mmWave) massivemultiple-input multiple-output (MIMO) vehicle-to-vehicle(V2V) channels. To investigate the impact of vehicular trafficdensity (VTD) on channel statistics, clusters are divided into staticclusters and dynamic clusters, which are further distinguishedinto static/dynamic single/twin-clusters to capture the mixed bouncingpropagation. A new method, which integrates thevisibility region and birth-death process methods, is developedto model space-time-frequency (S-T-F) non-stationarity of V2Vchannels with time-space (T-S) consistency. The continuouslyarbitrary vehicular movement trajectory (VMT) and soft clusterpower handover are modeled to further ensure channel T-Sconsistency. From the proposed model, key channel statistics arederived. Simulation results show that S-T-F non-stationarity ofchannels with T-S consistency is modeled and the impacts of VTDand VMT on channel statistics are analyzed. The generality ofthe proposed model is validated by comparing simulation resultsand measurement/ray-tracing (RT)-based results.

In this work, we develop an Aligned Entropic Reproducing Kernel (AERK) for graph classification. We commence by performing the Continuous-time Quantum Walk (CTQW) on each graph structure, and computing the Averaged Mixing Matrix (AMM) to describe how the CTQW visit all vertices from a starting vertex. More specifically, we show how this AMM matrix allows us to compute a quantum Shannon entropy for each vertex of a graph. For pairwise graphs, the proposed AERK kernel is defined by computing a reproducing kernel based similarity between the quantum Shannon entropies of their each pair of aligned vertices. The analysis of theoretical properties reveals that the proposed AERK kernel cannot only address the shortcoming of neglecting the structural correspondence information between graphs arising in most existing R-convolution graph kernels, but also overcome the problem of neglecting the structural differences between pairs of aligned vertices arising in existing vertex-based matching kernels. Moreover, unlike existing classical graph kernels that only focus on the global or local structural information of graphs, the proposed AERK kernel can simultaneously capture both global and local structural information through the quantum Shannon entropies, reflecting more precise kernel based similarity measures between pairs of graphs. The above theoretical properties explain the effectiveness of the proposed kernel. The experimental evaluation on standard graph datasets demonstrates that the proposed AERK kernel is able to outperform state-of-the-art graph kernels for graph classification tasks., Comment: Corresponding author: Lu Bai, bailu@bnu.edu.cn; bailucs@cufe.edu.cn

Xue Song,1 Jiaqi Wang,2 Lu Bai,1 Wei Zou3 1The First Clinical Medical College, Heilongjiang University of Chinese Medicine, Harbin, People’s Republic of China; 2The Second Clinical Medical College, Heilongjiang University of Chinese Medicine, Harbin, People’s Republic of China; 3First Affiliated Hospital, Heilongjiang University of Chinese Medicine, Harbin, Heilongjiang, People’s Republic of ChinaCorrespondence: Wei Zou, The First Clinical Medical College, Heilongjiang University of Chinese Medicine, 26 Heping Road, Xiangfang District, Harbin, Heilongjiang, People’s Republic of China, Email kuangzou1965@163.comBackground: Migraine is a serious global health concern that imposed a huge economic burden on social health care. Over the past few decades, the analgesic effects of acupuncture have been widely recognized, and there is a growing body of research on acupuncture for migraine. Citation analysis is a branch of bibliometrics that helps researchers analyze and identify historical or landmark studies within the scientific literature. Currently, there is no analysis of the 100 most highly cited publications on acupuncture for migraine.Methods: The 100 most highly cited publications on acupuncture for migraine were screened using the Science Citation Index Expanded of the Web of Science Core Collection database. CiteSpace and VOSviewer programs were used for bibliometric analysis.Results: A total of 493 publications on acupuncture for migraine were identified. 100 of the most highly cited publications on acupuncture for migraine were published from 1984– 2020. These publications were cited 6142 times with an h-index of 44 and 84% were original articles. The highest frequency of citations was 416. A total of 335 authors were involved in the study with 37 lead authors. 212 institutions from 20 countries contributed to the 100 most highly cited publications. The most published studies came from the United States (n=36), followed by China (n=27) and Germany (n=

Radiation therapy is a primary and effective NasoPharyngeal Carcinoma (NPC) treatment strategy. The precise delineation of Gross Tumor Volumes (GTVs) and Organs-At-Risk (OARs) is crucial in radiation treatment, directly impacting patient prognosis. Previously, the delineation of GTVs and OARs was performed by experienced radiation oncologists. Recently, deep learning has achieved promising results in many medical image segmentation tasks. However, for NPC OARs and GTVs segmentation, few public datasets are available for model development and evaluation. To alleviate this problem, the SegRap2023 challenge was organized in conjunction with MICCAI2023 and presented a large-scale benchmark for OAR and GTV segmentation with 400 Computed Tomography (CT) scans from 200 NPC patients, each with a pair of pre-aligned non-contrast and contrast-enhanced CT scans. The challenge's goal was to segment 45 OARs and 2 GTVs from the paired CT scans. In this paper, we detail the challenge and analyze the solutions of all participants. The average Dice similarity coefficient scores for all submissions ranged from 76.68\% to 86.70\%, and 70.42\% to 73.44\% for OARs and GTVs, respectively. We conclude that the segmentation of large-size OARs is well-addressed, and more efforts are needed for GTVs and small-size or thin-structure OARs. The benchmark will remain publicly available here: https://segrap2023.grand-challenge.org, Comment: A challenge report of SegRap2023 (organized in conjunction with MICCAI2023)

Infrared and visible image fusion aims to extract complementary features to synthesize a single fused image. Many methods employ convolutional neural networks (CNNs) to extract local features due to its translation invariance and locality. However, CNNs fail to consider the image's non-local self-similarity (NLss), though it can expand the receptive field by pooling operations, it still inevitably leads to information loss. In addition, the transformer structure extracts long-range dependence by considering the correlativity among all image patches, leading to information redundancy of such transformer-based methods. However, graph representation is more flexible than grid (CNN) or sequence (transformer structure) representation to address irregular objects, and graph can also construct the relationships among the spatially repeatable details or texture with far-space distance. Therefore, to address the above issues, it is significant to convert images into the graph space and thus adopt graph convolutional networks (GCNs) to extract NLss. This is because the graph can provide a fine structure to aggregate features and propagate information across the nearest vertices without introducing redundant information. Concretely, we implement a cascaded NLss extraction pattern to extract NLss of intra- and inter-modal by exploring interactions of different image pixels in intra- and inter-image positional distance. We commence by preforming GCNs on each intra-modal to aggregate features and propagate information to extract independent intra-modal NLss. Then, GCNs are performed on the concatenate intra-modal NLss features of infrared and visible images, which can explore the cross-domain NLss of inter-modal to reconstruct the fused image. Ablation studies and extensive experiments illustrates the effectiveness and superiority of the proposed method on three datasets.

High-precision transit observations provide excellent opportunities for characterizing the physical properties of exoplanetary systems. These physical properties supply many pieces of information for unvealing the internal structure, external atmosphere, and dynamical history of the planets. We present revised properties of transiting systems WASP-35 and HAT-P-30/WASP-51 through analyzing newly available TESS photometry and ground-based observations obtained at 1m telescope of Yunnan Observatories as well as from the literature. The improved system parameters are consistent with the previous results. Furthermore, we find that HAT-P-30b/WASP-51b's transits show significant timing variation which cannot be explained by decaying orbit due to tidal dissipation and the R\o mer effect, while both apsidal precession and an additional perturbing body could reproduce this signal through our comprehensive dynamical simulations. Because both of them are valuable targets which are suitable for transmission spectroscopy, we make some predictions for atmospheric properties of WASP-35b and HAT-P-30b/WASP-51b based on newly derived system parameters., Comment: 22 pages, 11 figures,accepted by AJ on 2022 Mar 5

Batteries are recognized as one of the most important energy storage systems due to their high energy density. As one of the most promising next-generation high energy density storage devices, lithium metal batteries have reached momentum. However, the use of lithium metal meets many technical problems with conventional liquid electrolytes, which can be solved by using solid-state electrolytes. Solid-state electrolytes are thus a key component of all-solid-state lithium metal batteries, and their progress directly affects the industrialization of all-solid-state lithium metal batteries. The current research on solid-state electrolytes focuses on two major types of materials: polymers electrolytes and inorganic electrolytes. Polymer electrolytes are a promising class of materials due to their easy processing, lightweight, flexibility, and they provide a feasible solution to safety issues. In this thesis, we introduce phosphonate-containing polymers in polymer electrolytes. Those are very promising compounds because of their good thermal stability, their ability to bind to metals, and excellent flame retardancy. Those novel phosphonate-containing polymers used in polymer electrolytes could maintain the electrolyte-electrode contact interface, prevent the growth of lithium dendrites, increase the electrochemistry stability window, and improve battery safety because of fire-retardant property. This opens the possibility to safely apply Li-metal as a high-capacity anode, which could provide a valuable strategy towards high-performance all-solid-state lithium metal batteries., (SC - Sciences) -- UCL, 2022

In this paper, we propose a novel graph kernel, namely the Quantum-based Entropic Subtree Kernel (QESK), for Graph Classification. To this end, we commence by computing the Average Mixing Matrix (AMM) of the Continuous-time Quantum Walk (CTQW) evolved on each graph structure. Moreover, we show how this AMM matrix can be employed to compute a series of entropic subtree representations associated with the classical Weisfeiler-Lehman (WL) algorithm. For a pair of graphs, the QESK kernel is defined by computing the exponentiation of the negative Euclidean distance between their entropic subtree representations, theoretically resulting in a positive definite graph kernel. We show that the proposed QESK kernel not only encapsulates complicated intrinsic quantum-based structural characteristics of graph structures through the CTQW, but also theoretically addresses the shortcoming of ignoring the effects of unshared substructures arising in state-of-the-art R-convolution graph kernels. Moreover, unlike the classical R-convolution kernels, the proposed QESK can discriminate the distinctions of isomorphic subtrees in terms of the global graph structures, theoretically explaining the effectiveness. Experiments indicate that the proposed QESK kernel can significantly outperform state-of-the-art graph kernels and graph deep learning methods for graph classification problems.

In this work, we propose a family of novel quantum kernels, namely the Hierarchical Aligned Quantum Jensen-Shannon Kernels (HAQJSK), for un-attributed graphs. Different from most existing classical graph kernels, the proposed HAQJSK kernels can incorporate hierarchical aligned structure information between graphs and transform graphs of random sizes into fixed-sized aligned graph structures, i.e., the Hierarchical Transitive Aligned Adjacency Matrix of vertices and the Hierarchical Transitive Aligned Density Matrix of the Continuous-Time Quantum Walk (CTQW). For a pair of graphs to hand, the resulting HAQJSK kernels are defined by measuring the Quantum Jensen-Shannon Divergence (QJSD) between their transitive aligned graph structures. We show that the proposed HAQJSK kernels not only reflect richer intrinsic global graph characteristics in terms of the CTQW, but also address the drawback of neglecting structural correspondence information arising in most existing R-convolution kernels. Furthermore, unlike the previous Quantum Jensen-Shannon Kernels associated with the QJSD and the CTQW, the proposed HAQJSK kernels can simultaneously guarantee the properties of permutation invariant and positive definiteness, explaining the theoretical advantages of the HAQJSK kernels. Experiments indicate the effectiveness of the proposed kernels.

The enormous emission of carbon dioxide (CO2) from industries has triggered a series of environmental issues. In recent years, ionic liquids (ILs) as novel absorbents are widely used for CO2 capture owing to their low vapor pressure and tunable structures. IL‐modified adsorbents have the advantages of both ILs and porous supports, such as high CO2 selectivity and high specific surface area, which are novel agents to capture CO2 with broad application prospects. In this review, more than 140 IL‐modified adsorbents for CO2 capture in recent years were systematically summarized. The types of ILs including conventional ILs and functionalized ILs on CO2 separation performance of different IL hybrid adsorbents, and their adsorption mechanisms were also discussed. Finally, future perspectives on IL‐modified adsorbents for CO2 separation were further posed.

Weitong Song,1 Lu Bai,1 Yuya Yang,1 Yongchao Wang,2 Pingxiang Xu,1,3 Yuming Zhao,1 Xuelin Zhou,1,3 Xiaorong Li,1,3 Ming Xue1,3 1Department of Pharmacology, School of Basic Medical Sciences, Capital Medical University, Beijing, People’s Republic of China; 2CAS Key Laboratory for Biomedical Effects of Nanomaterials and Nanosafety, CAS Center for Excellence in Nanoscience, National Center for Nanoscience and Technology of China, Beijing, People’s Republic of China; 3Beijing Laboratory for Biomedical Detection Technology and Instrument, Beijing, People’s Republic of ChinaCorrespondence: Ming Xue, Department of Pharmacology, School of Basic Medical Sciences, Capital Medical University, Youanmen, Beijing, 100069, People’s Republic of China, Tel +8610-83950416, Fax +8610-83911520, Email xuem@ccmu.edu.cnPurpose: We designed a novel isoliquiritigenin (ISL) loaded micelle prepared with DSPE-PEG2000 as the drug carrier modified with the brain-targeting polypeptide angiopep-2 to improve the poor water solubility and low bioavailability of ISL for the treatment of acute ischemic stroke.Methods: Thin film evaporation was used to synthesize the ISL micelles (ISL-M) modified with angiopep-2 as the brain targeted ligands. The morphology of the micelles was observed by the TEM. The particle size and zeta potential were measured via the nanometer particle size analyzer. The drug loading, encapsulation and in vitro release rates of micelles were detected by the HPLC. The UPLC-ESI-MS/MS methods were used to measure the ISL concentrations of ISL in plasma and main tissues after intravenous administration, and compared the pharmacokinetics and tissue distributions between ISL and ISL-M. In the MCAO mice model, the protective effects of ISL and ISL-M were confirmed via the behavioral and molecular biology experiments.Results: The results showed that the drug loading of ISL-M was 7.63 ± 2.62%, the encapsulation efficiency was 68.17 ± 6.23%, the particle size was 40.87 ± 4.82 nm

Deep learning is attracting interest across a variety of domains, including natural language processing, speech recognition, and computer vision. However, model training is time-consuming and requires huge computational resources. Existing works on the performance prediction of deep neural networks, which mostly focus on the training time prediction of a few models, rely on analytical models and result in high relative errors. %Optimizing task scheduling and reducing job failures in data centers are essential to improve resource utilization and reduce carbon emissions. This paper investigates the computational resource demands of 29 classical deep neural networks and builds accurate models for predicting computational costs. We first analyze the profiling results of typical networks and demonstrate that the computational resource demands of models with different inputs and hyperparameters are not obvious and intuitive. We then propose a lightweight prediction approach DNNAbacus with a novel network structural matrix for network representation. DNNAbacus can accurately predict both memory and time cost for PyTorch and TensorFlow models, which is also generalized to different hardware architectures and can have zero-shot capability for unseen networks. Our experimental results show that the mean relative error (MRE) is 0.9% with respect to time and 2.8% with respect to memory for 29 classic models, which is much lower than the state-of-the-art works.

Event extraction, the technology that aims to automatically get the structural information from documents, has attracted more and more attention in many fields. Most existing works discuss this issue with the token-level multi-label classification framework by distinguishing the tokens as different roles while ignoring the writing styles of documents. The writing style is a special way of content organizing for documents and it is relative fixed in documents with a special field (e.g. financial, medical documents, etc.). We argue that the writing style contains important clues for judging the roles for tokens and the ignorance of such patterns might lead to the performance degradation for the existing works. To this end, we model the writing style in documents as a distribution of argument roles, i.e., Role-Rank Distribution, and propose an event extraction model with the Role-Rank Distribution based Supervision Mechanism to capture this pattern through the supervised training process of an event extraction task. We compare our model with state-of-the-art methods on several real-world datasets. The empirical results show that our approach outperforms other alternatives with the captured patterns. This verifies the writing style contains valuable information that could improve the performance of the event extraction task., Comment: This paper has been submitted to Pattern Recognition Letters

To alleviate the challenges of building Knowledge Graphs (KG) from scratch, a more general task is to enrich a KG using triples from an open corpus, where the obtained triples contain noisy entities and relations. It is challenging to enrich a KG with newly harvested triples while maintaining the quality of the knowledge representation. This paper proposes a system to refine a KG using information harvested from an additional corpus. To this end, we formulate our task as two coupled sub-tasks, namely join event extraction (JEE) and knowledge graph fusion (KGF). We then propose a Collaborative Knowledge Graph Fusion Framework to allow our sub-tasks to mutually assist one another in an alternating manner. More concretely, the explorer carries out the JEE supervised by both the ground-truth annotation and an existing KG provided by the supervisor. The supervisor then evaluates the triples extracted by the explorer and enriches the KG with those that are highly ranked. To implement this evaluation, we further propose a Translated Relation Alignment Scoring Mechanism to align and translate the extracted triples to the prior KG. Experiments verify that this collaboration can both improve the performance of the JEE and the KGF., Comment: Under review by IEEE Transactions on Knowledge and Data Engineering (TKDE)

New solid polymer electrolytes are of particular interest for next-generation high-energy batteries since they can overcome the limited voltage window of conventional polyether-based electrolytes. Herein, a flame-retardant phosphorus-containing polymer, poly(dimethyl(methacryloyloxy)methyl phosphonate) (PMAPC1) is introduced as a promising polymer matrix. Free-standing membranes are easily obtained by mixing PMAPC1 with lithium bis(trifluoromethanesulfonyl)imide (LiTFSI) and a small amount of acetonitrile (AN). LiTFSI/AN mixed aggregates are formed that act as plasticizers and enable ionic conductivities up to 1.6 × 10–3 S cm–1 at 100 °C. The high content of LiTFSI used in our electrolytes leads to the formation of a stable LiF solid-electrolyte interphase, which can effectively suppress Li dendrites and the chemical degradation of AN in contact with Li. Accordingly the electrolyte membranes exhibit a wide electrochemical stability window above 4.7 V versus Li+/Li and fire-retardant properties due to the presence of the phosphorus-containing polymer. Atomistic molecular modeling simulations have been performed to determine the structure of the electrolytes on the microscopic scale and to rationalize the trends in ionic conductivity and the transport regime as a function of the electrolyte composition. Finally, our electrolyte membranes enable stable cycling performance for LiFePO4|PMAPC1 + LiTFSI + AN|Li batteries.

Carbonaceous materials are used as the anode for rechargeable lithium-ion batteries (LIBs), however, lithium dendrites are easily formed during cycling due to the low lithium insertion potential (~0.1 V versus Li+/Li). As alternative anodes, transition metal oxides based on conversion mechanism have attached much attention. But the high lithiation potential (>1.0 V vs. Li+/Li) usually leads to a low output voltage and energy density when used in a full cell configuration. Herein, Zn-substituted Co3O4 submicron spheres are successfully synthesized by a facile solvothermal reaction and subsequent calcination method. When used as the anode for LIB, the optimized sample shows a specific capacity of 686 mAh g−1 at 0.8 A g−1 after 500 cycles, and a specific capacity of 692.9 mAh g−1 at a higher current density of 3.2 A g−1 in a half-cell. Thanks to the controlled Zn substitution, the discharge voltage plateau is 0.16 V lower than that of the pure Co3O4 anode at a current density of 0.4 A g−1. Further investigation of the 0.5Zn-Co3O4//LiCoO2 full cells also displays a high capacity (400.7 mAh g−1 after 200 cycles at 0.4 A g−1) and an excellent rate capability (658.1 mAh g−1 at 1.6 A g−1) compared with the Co3O4//LiCoO2 full cells. This work confirms that substituting suitable metal elements into sub-micron conversion based anodes can reduce the voltage plateau, which is of great significance for the practical applications in high performance energy storage devices.

In this paper, we present Conjoint Attentions (CAs), a class of novel learning-to-attend strategies for graph neural networks (GNNs). Besides considering the layer-wise node features propagated within the GNN, CAs can additionally incorporate various structural interventions, such as node cluster embedding, and higher-order structural correlations that can be learned outside of GNN, when computing attention scores. The node features that are regarded as significant by the conjoint criteria are therefore more likely to be propagated in the GNN. Given the novel Conjoint Attention strategies, we then propose Graph conjoint attention networks (CATs) that can learn representations embedded with significant latent features deemed by the Conjoint Attentions. Besides, we theoretically validate the discriminative capacity of CATs. CATs utilizing the proposed Conjoint Attention strategies have been extensively tested in well-established benchmarking datasets and comprehensively compared with state-of-the-art baselines. The obtained notable performance demonstrates the effectiveness of the proposed Conjoint Attentions., Comment: Conference on Neural Information Processing Systems (NeurIPS 2021), Implementation: https://github.com/he-tiantian/CATs

Solid polymer electrolytes are prepared by mixing various amounts of lithium bis(trifluoromethanesulfonyl)imide with poly(vinylidene fluoride-co-vinyl dimethyl phosphonate) statistical copolymers with different compositions. Such copolymers are obtained by conventional radical copolymerization of vinylidene fluoride (VDF) with vinyl dimethyl phosphonate (VDMP) initiated by peroxides. A morphological study of the obtained solid polymer electrolytes (SPEs) shows that only samples prepared from the copolymer with the lower amount of VDMP (16 mol%) result in the formation of homogeneous electrolytes while aggregates of lithium salts are observed for the other copolymers. The best ionic conductivity values are accordingly observed for the copolymers with the lower VDMP amount and are reaching 5 × 10−3 mS cm−1 at 100 °C. The dependence of the ionic conductivity versus temperature suggests that the ionic conductivity is controlled by the motion of polymer segments. Indeed, the ionic conductivity can be increased by adding a small amount of trimethylphosphate plasticizer and can reach 1.9 × 10−2 mS cm−1 at 20 °C. Finally, the prepared SPEs exhibit a high electrochemical stability and a good resistance to flame because of the presence of fire-retardant phosphate groups in their structure.

The standardization process of the fifth generation (5G) wireless communications has recently been accelerated and the first commercial 5G services would be provided as early as in 2018. The increasing of enormous smartphones, new complex scenarios, large frequency bands, massive antenna elements, and dense small cells will generate big datasets and bring 5G communications to the era of big data. This paper investigates various applications of big data analytics, especially machine learning algorithms in wireless communications and channel modeling. We propose a big data and machine learning enabled wireless channel model framework. The proposed channel model is based on artificial neural networks (ANNs), including feed-forward neural network (FNN) and radial basis function neural network (RBF-NN). The input parameters are transmitter (Tx) and receiver (Rx) coordinates, Tx-Rx distance, and carrier frequency, while the output parameters are channel statistical properties, including the received power, root mean square (RMS) delay spread (DS), and RMS angle spreads (ASs). Datasets used to train and test the ANNs are collected from both real channel measurements and a geometry based stochastic model (GBSM). Simulation results show good performance and indicate that machine learning algorithms can be powerful analytical tools for future measurement-based wireless channel modeling.

In this paper, we develop a new graph kernel, namely the Hierarchical Transitive-Aligned kernel, by transitively aligning the vertices between graphs through a family of hierarchical prototype graphs. Comparing to most existing state-of-the-art graph kernels, the proposed kernel has three theoretical advantages. First, it incorporates the locational correspondence information between graphs into the kernel computation, and thus overcomes the shortcoming of ignoring structural correspondences arising in most R-convolution kernels. Second, it guarantees the transitivity between the correspondence information that is not available for most existing matching kernels. Third, it incorporates the information of all graphs under comparisons into the kernel computation process, and thus encapsulates richer characteristics. By transductively training the C-SVM classifier, experimental evaluations demonstrate the effectiveness of the new transitive-aligned kernel. The proposed kernel can outperform state-of-the-art graph kernels on standard graph-based datasets in terms of the classification accuracy.

Automatically learning thematic clusters in network data has long been a challenging task in machine learning community. A number of approaches have been proposed to accomplish it, utilizing edges, vertex features, or both aforementioned. However, few of them consider how the quantification of dichotomous inclination w.r.t. network topology and vertex features may influence vertex-cluster preferences, which deters previous methods from uncovering more interpretable latent groups in network data. To fill this void, we propose a novel probabilistic model, dubbed Relational Thematic Clustering with Mutually Preferred Neighbors (RTCMPN). Different from prevalent approaches which predetermine the learning significance of edge structure and vertex features, RTCMPN can further learn the latent preferences indicating which neighboring vertices are more possible to be in the same cluster, and the dichotomous inclinations describing how relative significance w.r.t. edge structure and vertex features may impact the association between pairwise vertices. Therefore, cluster structure implanted with edge structure, vertex features, neighboring preferences, and vertex-vertex dichotomous inclinations can be learned by RTCMPN. We additionally derive an effective Expectation-Maximization algorithm for RTCMPN to infer the optimal model parameters. RTCMPN has been compared with several strong baselines on various network data. The remarkable results validate the effectiveness of RTCMPN.

Lu Lu Bai,1,2,* Jin Peng Du,1 Xu Kai Xue,1,* Ding Jun Hao,1 Wen Tao Wang1 1Department of Spine Surgery, Honghui Hospital, Xi’an Jiaotong University, Xi’an, Shaanxi 710054, People’s Republic of China; 2Graduate School, Xi’an Medical University, Xi’an, Shaanxi, 710021, People’s Republic of China*These authors contributed equally to this workCorrespondence: Wen Tao WangDepartment of Spine Surgery, Honghui Hospital, Xi’an Jiaotong University, Youyidong Road, Xi’an, Shaanxi 710054, People’s Republic of ChinaTel/Fax +86-29-87800002Email w15686024394@163.comBackground: Ankylosing spondylitis with Andersson lesions is not rare, but its potential pathogenesis and natural course remain unclear.Case Description: We describe a case of CT image changes in ankylosing spondylitis from fracture to Andersson lesions. A 40-year-old man with a 23-year history of ankylosing spondylitis presented with acute back pain after a slight fall, and the CT showed a T12 fracture; the patient refused surgery for 12 months. The process from fracture to Andersson lesions was characterized by CT, including the subsequent interbody bone graft with internal fixation and successful bone fusion at the last follow-up. Histopathologic analysis showed degenerative fibrocartilage tissue calcification, necrotic intervertebral disc tissue, fibrovascular hyperplasia, and focal accumulation of inflammatory cells.Conclusion: Aseptic inflammation and persistent instability caused by a fracture contributed in the course from fracture to Andersson lesions in ankylosing spondylitis. CT can accurately track the pathological process, and interbody fusion via the posterior pedicle lateral approach can achieve satisfactory effectiveness, good fusion and kyphosis correction.Keywords: ankylosing spondylitis, Andersson lesions, CT

Joint-event-extraction, which extracts structural information (i.e., entities or triggers of events) from unstructured real-world corpora, has attracted more and more research attention in natural language processing. Most existing works do not fully address the sparse co-occurrence relationships between entities and triggers, which loses this important information and thus deteriorates the extraction performance. To mitigate this issue, we first define the joint-event-extraction as a sequence-to-sequence labeling task with a tag set composed of tags of triggers and entities. Then, to incorporate the missing information in the aforementioned co-occurrence relationships, we propose a Cross-Supervised Mechanism (CSM) to alternately supervise the extraction of either triggers or entities based on the type distribution of each other. Moreover, since the connected entities and triggers naturally form a heterogeneous information network (HIN), we leverage the latent pattern along meta-paths for a given corpus to further improve the performance of our proposed method. To verify the effectiveness of our proposed method, we conduct extensive experiments on four real-world datasets as well as compare our method with state-of-the-art methods. Empirical results and analysis show that our approach outperforms the state-of-the-art methods in both entity and trigger extraction., Comment: Accepted by ICPR 2020

Room temperature ionic liquids (RTILs) are known to exhibit high CO2 solubility, which makes them interesting candidates for separation and purification of mixed gas streams. Particularly, RTILs based on imidazoles have shown very promising results. However, membranes of the corresponding poly(RT-IL)s are inherently brittle, which makes them too fragile for use in freestanding membranes. Therefore, copolymers of N-vinylimidazole (VIm) and butyl acrylate (BuA) were prepared, showing reactivity ratios of rBuA = 1.91–2.02 and rVIm = 0.094–0.10. The prepared copolymers of poly(VIm-co-BuA) with a copolymer composition of 24:76 had sufficiently low Tg (−6.6 °C) and were flexible enough to be used for membrane preparation. The copolymer was quarternized and crosslinked in a one-pot reaction into thin film membranes employing a mixture of mono and difunctional alkyl halides. Membranes were prepared using a mixture of 1:8, 1:2 and 1:0 of 1,6-dibromohexane and 1-bromobutane, resulting in different degrees of crosslinking. The one-pot process additionally allows incorporation of up to 16 wt% free RTIL (BMIM Tf2N) in the 1:0 ratio membranes. All membranes were tested for CO2 permeability (33.7–54.38 barrer), and for selectivity towards N2 and CH4. By varying the crosslinking degree, it was observed that CO2 permeability increased with decreasing the degree of crosslinking. Finally, films prepared with free RTIL led to an improvement of the gas separation performance, with CO2 permeability increased from 33.71 to 38.77 barrer and CO2/N2 permselectivity increased from 20.81 to 27.82.

We formalize networks with evolving structures as temporal networks and propose a generative link prediction model, Generative Link Sequence Modeling (GLSM), to predict future links for temporal networks. GLSM captures the temporal link formation patterns from the observed links with a sequence modeling framework and has the ability to generate the emerging links by inferring from the probability distribution on the potential future links. To avoid overfitting caused by treating each link as a unique token, we propose a self-tokenization mechanism to transform each raw link in the network to an abstract aggregation token automatically. The self-tokenization is seamlessly integrated into the sequence modeling framework, which allows the proposed GLSM model to have the generalization capability to discover link formation patterns beyond raw link sequences. We compare GLSM with the existing state-of-art methods on five real-world datasets. The experimental results demonstrate that GLSM obtains future positive links effectively in a generative fashion while achieving the best performance (2-10\% improvements on AUC) among other alternatives., Comment: accepted by World Wide Web Journal

Multi-label learning studies the problem where an instance is associated with a set of labels. By treating single-label learning problem as one task, the multi-label learning problem can be casted as solving multiple related tasks simultaneously. In this paper, we propose a novel Multi-task Gradient Descent (MGD) algorithm to solve a group of related tasks simultaneously. In the proposed algorithm, each task minimizes its individual cost function using reformative gradient descent, where the relations among the tasks are facilitated through effectively transferring model parameter values across multiple tasks. Theoretical analysis shows that the proposed algorithm is convergent with a proper transfer mechanism. Compared with the existing approaches, MGD is easy to implement, has less requirement on the training model, can achieve seamless asymmetric transformation such that negative transfer is mitigated, and can benefit from parallel computing when the number of tasks is large. The competitive experimental results on multi-label learning datasets validate the effectiveness of the proposed algorithm.

In this work, we develop a novel framework to measure the similarity between dynamic financial networks, i.e., time-varying financial networks. Particularly, we explore whether the proposed similarity measure can be employed to understand the structural evolution of the financial networks with time. For a set of time-varying financial networks with each vertex representing the individual time series of a different stock and each edge between a pair of time series representing the absolute value of their Pearson correlation, our start point is to compute the commute time matrix associated with the weighted adjacency matrix of the network structures, where each element of the matrix can be seen as the enhanced correlation value between pairwise stocks. For each network, we show how the commute time matrix allows us to identify a reliable set of dominant correlated time series as well as an associated dominant probability distribution of the stock belonging to this set. Furthermore, we represent each original network as a discrete dominant Shannon entropy time series computed from the dominant probability distribution. With the dominant entropy time series for each pair of financial networks to hand, we develop a similarity measure based on the classical dynamic time warping framework, for analyzing the financial time-varying networks. We show that the proposed similarity measure is positive definite and thus corresponds to a kernel measure on graphs. The proposed kernel bridges the gap between graph kernels and the classical dynamic time warping framework for multiple financial time series analysis. Experiments on time-varying networks extracted through New York Stock Exchange (NYSE) database demonstrate the effectiveness of the proposed approach., Comment: Previously, the original version of this manuscript appeared as arXiv:1902.09947v2, that was submitted as a replacement by a mistake. Now, that article has been replaced to correct the error, and this manuscript is distinct from that article

Counterfactual thinking describes a psychological phenomenon that people re-infer the possible results with different solutions about things that have already happened. It helps people to gain more experience from mistakes and thus to perform better in similar future tasks. This paper investigates the counterfactual thinking for agents to find optimal decision-making strategies in multi-agent reinforcement learning environments. In particular, we propose a multi-agent deep reinforcement learning model with a structure which mimics the human-psychological counterfactual thinking process to improve the competitive abilities for agents. To this end, our model generates several possible actions (intent actions) with a parallel policy structure and estimates the rewards and regrets for these intent actions based on its current understanding of the environment. Our model incorporates a scenario-based framework to link the estimated regrets with its inner policies. During the iterations, our model updates the parallel policies and the corresponding scenario-based regrets for agents simultaneously. To verify the effectiveness of our proposed model, we conduct extensive experiments on two different environments with real-world applications. Experimental results show that counterfactual thinking can actually benefit the agents to obtain more accumulative rewards from the environments with fair information by comparing to their opponents while keeping high performing efficiency., Comment: This paper is accepted by ICDM'19 as a short paper

With the increasing popularity of consumer wearable devices augmented with sensing capabilities (smart bands, smart watches), there is a significant focus on extracting meaningful information about human behaviour through large scale real-world wearable sensor data. The focus of this work is to develop techniques to detect human activities, utilising a large dataset of wearable data where no ground truth has been produced on the actual activities performed. We propose a deep learning variational auto encoder activity recognition model - Motion2Vector. The model is trained using large amounts of unlabelled human activity data to learn a representation of a time period of activity data. The learned activity representations can be mapped into an embedded activity space and grouped with regards to the nature of the activity type. In order to evaluate the proposed model, we have applied our method on public dataset - The Heterogeneity Human Activity Recognition (HHAR) dataset. The results showed that our method can achieve improved result over the HHAR dataset. In addition, we have collected our own lab-based activity dataset. Our experimental results show that our system achieves good accuracy in detecting such activities, and has the potential to provide additional insights in understanding the real-world activity in the situations where there is no ground truth available.

We develop a novel method for measuring the similarity between complete weighted graphs, which are probed by means of discrete-time quantum walks. Directly probing complete graphs using discrete-time quantum walks is intractable due to the cost of simulating the quantum walk. We overcome this problem by extracting a commute-time minimum spanning tree from the complete weighted graph. The spanning tree is probed by a discrete time quantum walk which is initialised using a weighted version of the Perron-Frobenius operator. This naturally encapsulates the edge weight information for the spanning tree extracted from the original graph. For each pair of complete weighted graphs to be compared, we simulate a discrete-time quantum walk on each of the corresponding commute time minimum spanning trees, and then compute the associated density matrices for the quantum walks. The probability of the walk visiting each edge of the spanning tree is given by the diagonal elements of the density matrices. The similarity between each pair of graphs is then computed using either a) the inner product or b) the negative exponential of the Jensen-Shannon divergence between the probability distributions. We show that in both cases the resulting similarity measure is positive definite and therefore corresponds to a kernel on the graphs. We perform a series of experiments on publicly available graph datasets from a variety of different domains, together with time-varying financial networks extracted from data for the New York Stock Exchange. Our experiments demonstrate the effectiveness of the proposed similarity measures.

In this paper, we develop a new aligned vertex convolutional network model to learn multi-scale local-level vertex features for graph classification. Our idea is to transform the graphs of arbitrary sizes into fixed-sized aligned vertex grid structures, and define a new vertex convolution operation by adopting a set of fixed-sized one-dimensional convolution filters on the grid structure. We show that the proposed model not only integrates the precise structural correspondence information between graphs but also minimises the loss of structural information residing on local-level vertices. Experiments on standard graph datasets demonstrate the effectiveness of the proposed model., Comment: arXiv admin note: text overlap with arXiv:1809.01090

Feature selection has been proven a powerful preprocessing step for high-dimensional data analysis. However, most state-of-the-art methods tend to overlook the structural correlation information between pairwise samples, which may encapsulate useful information for refining the performance of feature selection. Moreover, they usually consider candidate feature relevancy equivalent to selected feature relevancy, and some less relevant features may be misinterpreted as salient features. To overcome these issues, we propose a new feature selection method using structural correlation between pairwise samples. Our idea is based on converting the original vectorial features into structure-based feature graph representations to incorporate structural relationship between samples, and defining a new evaluation measure to compute the joint significance of pairwise feature combinations in relation to the target feature graph. Furthermore, we formulate the corresponding feature subset selection problem into a least square regression model associated with a fused lasso regularizer to simultaneously maximize the joint relevancy and minimize the redundancy of the selected features. To effectively solve the optimization problem, an iterative algorithm is developed to identify the most discriminative features. Experiments demonstrate the effectiveness of the proposed approach.

In epidemiologic studies, researchers are commonly interested in quantifying geospatial effects on the incidence of disease to illustrate health disparities potentially attributable to environmental, demographic, and/or socioeconomic factors. The current research we focus on the development of advanced statistical modeling methods to determine how the pattern of disease outcome changes over geographical location. We first extend and illustrate the utility of MapGAM, a user-friendly R package that provides a unified framework for estimating, predicting and drawing inference on covariate-adjusted spatial effects using individual-level data. The package also facilitates visualization of spatial effects via automated mapping procedures. MapGAM estimates covariate-adjusted spatial associations with a univariate outcome using generalized additive models that include a non-parametric bivariate smooth term of geolocation parameters. Estimation and mapping methods are implemented for continuous, discrete, and right-censored survival data.Next, we note that smoothing approaches commonly implemented in generalized additive models and used in spatial analyses assume the amount of smoothing to be equal across geographical regions. The result is that some regions tend to be under-smoothed, while others are over-smoothed. We extend the work of Yue, etc. (2010) in the context of brain imaging analysis and propose a hierarchical Bayesian adaptive thin-plate spline that allows for spatial smoothing of continuous, binary and count outcomes along with the ability to adjust for potential confounding factors. The proposed method allows for the amount of smoothing to flexibly vary depending on the local extent of spatial effect by using nonstationary spatial Gaussian Markov random fields. Performance of the approach is evaluated via simulation and the proposed methodology is applied to an epidemiologic study investigating spatial heterogeneity in the risk of preterm birth among Massachuse

Yuanyuan Zheng,1 Hong Zhang,2 Yuping Hu,2 Lu Bai,1 Jingyi Xue1 1Department of Pharmacology, School of Basic Medical Sciences, Capital Medical University, Beijing 100069, People’s Republic of China; 2Department of Chemistry and Biology, School of Pharmaceutical Sciences, Capital Medical University, Beijing 100069, People’s Republic of China Background: Myocardial infarction (MI) is a leading cause of death worldwide. Therefore, nanoparticles that applied for specific diagnosis of the infarcted area and/or local myocardial delivery of therapeutic agents, are highly desired. Materials and methods: Herein, we developed the MnO-based nanoparticles, with magnetic resonance (MR) and near-infrared fluorescence imaging modalities as an MR imaging contrast agent and potential drug vehicle for the detection and treatment of MI. The chemophysical characteristics, targeting ability toward infarcted myocardium, biodistribution, and biocompatibility of the MnO-based nanoparticles were studied. Results: It was found that the MnO-based dual-modal nanoparticles possess high r1 relaxivity and induced no notable in vitro or in vivo toxicity. In a rat model of MI, these nanoparticles represent a very promising MR imaging contrast agent for sensitive and specific detection of the infarcted area, more importantly, without cardiotoxicity, the major defect of conventional Mn-based contrasts. Moreover, ex vivo near-infrared fluorescence imaging indicated that the MnO nanoparticles preferentially accumulate in the infarcted myocardium, which makes them an ideal drug vehicle for MI treatment. Conclusion: In summary, the use of these MnO nanoparticles as a T1-weighted MR imaging contrast agent and potential drug vehicle to target the infarcted myocardium may provide new opportunities for accurate detection of myocardial infarct and treatment of ischemic heart diseases. Keywords: Cy5.5 conjugated MnO nanoparticles, Dual-modal nanoprobe, Near-infrared fluorescence imaging, Myo

This paper investigates the characteristics of reflected and transmitted fields of a vector Bessel vortex beam through multilayered isotropic media on the basis of the vector angular spectrum expansion and presents the effects of media on intensity, phase, and polarization. The method is verified by studying the reflection and transmission on a single interface at vertical incidence. For both paraxial and nonparaxial incident beam cases, numerical simulations of the field components and the time-averaged Poynting vector power density of the reflected and transmitted beams for the three-layered media are presented and discussed in detail. It is shown that as the incident angle increases, the magnitude distribution of the reflected beams illustrates significant distortions and no longer represents similar patterns to that of the incident beam, whereas the magnitude distribution of the transmitted beams can maintain similar profiles to the incident beam, apart from the notable distortion of the central ring. For the same incident angle, the effects of media on the magnitude distribution for the nonparaxial case are more evident than those for the paraxial case. The results of phase distribution and polarization of the reflected and transmitted fields show that as the incident angle increases, the distortion of the phase distribution and polarization for the reflected fields are more significant and the topological charge cannot be preserved.

Based on the angular spectrum expansion and the 4x4 transfer matrix method, an investigation into the reflection, transmission, and absorption of vortex beams in an inhomogeneous magnetized plasma slab is presented. The reflected and transmitted electric fields are expressed by the inverse Fourier transform of the product of the reflected and transmitted coefficients and the angular spectrum amplitude of the incident beam. The intensity profiles, as well as the distortion of OAM states in both the reflected and transmitted beams are simulated and discussed. Through this investigation it could be concluded that both the incident angle and the plasma parameters have significant impact on the magnitudes of reflected and transmitted intensities, and the distortion of OAM states. The effects of the magnetic field and the incident angle on the reflectance, transmittance, and absorptance of the power have also been reported.

Dongqi Gao, Jingjing Zhang, Lu Bai, Fubo Li, Yi Dong, Qingshan Li Department of Oncology, Affiliated Hospital of Chengde Medical University, Chengde 067000, China Background: Non-small-cell lung cancer (NSCLC) has one of the highest mortality rates among cancers worldwide, with a poor prognosis. Previous studies have reported that melittin, an active component of apitoxin, exerts anti-inflammatory and antitumor effects via vascular endothelial growth factor or FoxO1. Methods: CCK8, flow cytometry assay and Western blotting were performed to evaluate the effect of melittin on NSCLC. Results: The present study demonstrates that melittin activated caspase-2 by inhibiting miR-183 expression and, thus, induced NSCLC apoptosis in both NCI-H441 cancer cell line assays and an in vivo xenograft model. The results of the cell-based assays showed that melittin (2 µg/mL) robustly suppressed miR-183 expression level and resulted in decreased invasion and migration abilities of NCI-H441 cells. Additionally, a flow cytometry assay and Western blotting showed that melittin induced NSCLC NCI-H441 cell apoptosis along with significant elevation of caspase-2 and Bax, which are regulators of cell apoptosis, and reduced Bcl-2 protein expression compared with dimethyl sulfoxide control. Furthermore, subcutaneous injection of melittin (5 mg/kg) significantly suppressed NSCLC tumor growth compared with vehicle group tumors, determined through tumor size and weight. Conclusion: Taken together, the aforementioned findings contribute to identification of a novel therapeutic target in the treatment of NSCLC, in patients diagnosed with a high expression of miR-183. Moreover, this article provides solid evidence for the inhibitory effect of melittin on NSCLC cancer cell growth. Keywords: miR-183, melittin, NSCLC, caspase 2, apoptosis

Most recent works model the market structure of the stock market as a correlation network of the stocks. They apply pre-defined patterns to extract correlation information from the time series of stocks. Without considering the influences of the evolving market structure to the market index trends, these methods hardly obtain the market structure models which are compatible with the market principles. Advancements in deep learning have shown their incredible modeling capacity on various finance-related tasks. However, the learned inner parameters, which capture the essence of the finance time series, are not further exploited about their representation in the financial fields. In this work, we model the financial market structure as a deep co-investment network and propose a Deep Co-investment Network Learning (DeepCNL) method. DeepCNL automatically learns deep co-investment patterns between any pairwise stocks, where the rise-fall trends of the market index are used for distance supervision. The learned inner parameters of the trained DeepCNL, which encodes the temporal dynamics of deep co-investment patterns, are used to build the co-investment network between the stocks as the investment structure of the corresponding market. We verify the effectiveness of DeepCNL on the real-world stock data and compare it with the existing methods on several financial tasks. The experimental results show that DeepCNL not only has the ability to better reflect the stock market structure that is consistent with widely-acknowledged financial principles but also is more capable to approximate the investment activities which lead to the stock performance reported in the real news or research reports than other alternatives., Comment: accepted by ICBK 2018

This paper proposes a new Quantum Spatial Graph Convolutional Neural Network (QSGCNN) model that can directly learn a classification function for graphs of arbitrary sizes. Unlike state-of-the-art Graph Convolutional Neural Network (GCNN) models, the proposed QSGCNN model incorporates the process of identifying transitive aligned vertices between graphs, and transforms arbitrary sized graphs into fixed-sized aligned vertex grid structures. In order to learn representative graph characteristics, a new quantum spatial graph convolution is proposed and employed to extract multi-scale vertex features, in terms of quantum information propagation between grid vertices of each graph. Since the quantum spatial convolution preserves the grid structures of the input vertices (i.e., the convolution layer does not change the original spatial sequence of vertices), the proposed QSGCNN model allows to directly employ the traditional convolutional neural network architecture to further learn from the global graph topology, providing an end-to-end deep learning architecture that integrates the graph representation and learning in the quantum spatial graph convolution layer and the traditional convolutional layer for graph classifications. We demonstrate the effectiveness of the proposed QSGCNN model in relation to existing state-of-the-art methods. The proposed QSGCNN model addresses the shortcomings of information loss and imprecise information representation arising in existing GCN models associated with the use of SortPooling or SumPooling layers. Experiments on benchmark graph classification datasets demonstrate the effectiveness of the proposed QSGCNN model.