Viewpoint-Adaptive Representation Disentanglement Network for Change Captioning.

Change captioning is to describe the fine-grained change between a pair of images. The pseudo changes caused by viewpoint changes are the most typical distractors in this task, because they lead to the feature perturbation and shift for the same objects and thus overwhelm the real change representation. In this paper, we propose a viewpoint-adaptive representation disentanglement network to distinguish real and pseudo changes, and explicitly capture the features of change to generate accurate captions. Concretely, a position-embedded representation learning is devised to facilitate the model in adapting to viewpoint changes via mining the intrinsic properties of two image representations and modeling their position information. To learn a reliable change representation for decoding into a natural language sentence, an unchanged representation disentanglement is designed to identify and disentangle the unchanged features between the two position-embedded representations. Extensive experiments show that the proposed method achieves the state-of-the-art performance on the four public datasets. The code is available at https://github.com/tuyunbin/VARD.

Identification of adaptor proteins by incorporating deep learning and PSSM profiles.

Adaptor proteins, also known as signal transduction adaptor proteins, are important proteins in signal transduction pathways, and play a role in connecting signal proteins for signal transduction between cells. Studies have shown that adaptor proteins are closely related to some diseases, such as tumors and diabetes. Therefore, it is very meaningful to construct a relevant model to accurately identify adaptor proteins. In recent years, many studies have used a position-specific scoring matrix (PSSM) and neural network methods to identify adaptor proteins. However, ordinary neural network models cannot correlate the contextual information in PSSM profiles well, so these studies usually process 20×N (N > 20) PSSM into 20×20 dimensions, which results in the loss of a large amount of protein information; This research proposes an efficient method that combines one-dimensional convolution (1-D CNN) and a bidirectional long short-term memory network (biLSTM) to identify adaptor proteins. The complete PSSM profiles are the input of the model, and the complete information of the protein is retained during the training process. We perform cross-validation during model training and test the performance of the model on an independent test set; in the data set with 1224 adaptor proteins and 11,078 non-adaptor proteins, five indicators including specificity, sensitivity, accuracy, area under the receiver operating characteristic curve (AUC) metric and Matthews correlation coefficient (MCC), were employed to evaluate model performance. On the independent test set, the specificity, sensitivity, accuracy and MCC were 0.817, 0.865, 0.823 and 0.465, respectively. Those results show that our method is better than the state-of-the art methods. This study is committed to improve the accuracy of adaptor protein identification, and laid a foundation for further research on diseases related to adaptor protein. This research provided a new idea for the application of deep learning related models in bioinformatics and computational biology.

Kernel Adaptive Filtering Over Complex Networks.

This brief is concerned with the problem of kernel adaptive filtering for a complex network. First, a coupled kernel least mean square (KLMS) algorithm is developed for each node to uncover its nonlinear measurement function by using a series of input-output data. Subsequently, an upper bound is derived for the step-size of the coupled KLMS algorithm to guarantee the mean square convergence. It is shown that the upper bound is dependent on the coupling weights of the complex network. Especially, an optimal step size is obtained to achieve the fastest convergence speed and a suboptimal step size is presented for the purpose of practical implementations. Besides, a coupled kernel recursive least square (KRLS) algorithm is further proposed to improve the filtering performance. Finally, simulations are provided to verify the validity of the theoretical results.

Spin Polarization of Mn Could Enhance Grain Boundary Sliding in Mg.

Segregation of rare earth alloying elements are known to segregate to grain boundaries in Mg and suppress grain boundary sliding via strong chemical bonds. Segregation of Mn, however, has recently been found to enhance grain boundary sliding in Mg, thereby boosting its ductility. Taking the Mg (2¯114) twin boundary as an example, we performed a first-principles comparative study on the segregation and chemical bonding of Y, Zn, and Mn at this boundary. We found that both Y-4d and Mn-3d states hybridized with the Mg-3sp states, while Zn-Mg bonding was characterized by charge transfer only. Strong spin-polarization of Mn pushed the up-spin 3d states down, leading to less anisotropic Mn-Mg bonds with more delocalized charge distribution at the twin boundary, and thus promotes grain boundary plasticity, e.g., grain boundary sliding.

Deblurring Dynamic Scenes via Spatially Varying Recurrent Neural Networks.

Deblurring images captured in dynamic scenes is challenging as the motion blurs are spatially varying caused by camera shakes and object movements. In this paper, we propose a spatially varying neural network to deblur dynamic scenes. The proposed model is composed of three deep convolutional neural networks (CNNs) and a recurrent neural network (RNN). The RNN is used as a deconvolution operator on feature maps extracted from the input image by one of the CNNs. Another CNN is used to learn the spatially varying weights for the RNN. As a result, the RNN is spatial-aware and can implicitly model the deblurring process with spatially varying kernels. To better exploit properties of the spatially varying RNN, we develop both one-dimensional and two-dimensional RNNs for deblurring. The third component, based on a CNN, reconstructs the final deblurred feature maps into a restored image. In addition, the whole network is end-to-end trainable. Quantitative and qualitative evaluations on benchmark datasets demonstrate that the proposed method performs favorably against the state-of-the-art deblurring algorithms.

A Multi-RNN Research Topic Prediction Model Based on Spatial Attention and Semantic Consistency-Based Scientific Influence Modeling.

Computer science discipline includes many research fields, which mutually influence and promote each other's development. This poses two great challenges of predicting the research topics of each research field. One is how to model fine-grained topic representation of a research field. The other is how to model research topic of different fields and keep the semantic consistency of research topics when learning the scientific influence context from other related fields. Unfortunately, the existing research topic prediction approaches cannot handle these two challenges. To solve these problems, we employ multiple different Recurrent Neural Network chains which model research topics of different fields and propose a research topic prediction model based on spatial attention and semantic consistency-based scientific influence modeling. Spatial attention is employed in field topic representation which can selectively extract the attributes from the field topics to distinguish the importance of field topic attributes. Semantic consistency-based scientific influence modeling maps research topics of different fields to a unified semantic space to obtain the scientific influence context of other related fields. Extensive experiment results on five related research fields in the computer science (CS) discipline show that the proposed model is superior to the most advanced methods and achieves good topic prediction performance.

Cross-Modal Search for Social Networks via Adversarial Learning.

Cross-modal search has become a research hotspot in the recent years. In contrast to traditional cross-modal search, social network cross-modal information search is restricted by data quality for arbitrary text and low-resolution visual features. In addition, the semantic sparseness of cross-modal data from social networks results in the text and visual modalities misleading each other. In this paper, we propose a cross-modal search method for social network data that capitalizes on adversarial learning (cross-modal search with adversarial learning: CMSAL). We adopt self-attention-based neural networks to generate modality-oriented representations for further intermodal correlation learning. A search module is implemented based on adversarial learning, through which the discriminator is designed to measure the distribution of generated features from intramodal and intramodal perspectives. Experiments on real-word datasets from Sina Weibo and Wikipedia, which have similar properties to social networks, show that the proposed method outperforms the state-of-the-art cross-modal search methods.

Hydrogen-Enhanced Vacancy Diffusion in Metals.

Vacancy diffusion is fundamental to materials science. Hydrogen atoms bind strongly to vacancies and are often believed to retard vacancy diffusion. Here, we use a potential-of-mean-force method to study the diffusion of vacancies in Cu and Pd. We find H atoms, instead of dragging, enhance the diffusivity of vacancies due to a positive hydrogen Gibbs excess at the saddle-point: that is, the migration saddle attracts more H than the vacancy ground state, characterized by an activation excess ΓHm ≈ 1 H, together with also-positive migration activation volume Ωm and activation entropy Sm. Thus, according to the Gibbs adsorption isotherm generalized to the activation path, a higher µH significantly lowers the migration free-energy barrier. This is verified by ab initio grand canonical Monte Carlo simulations and direct molecular dynamics simulations. This trend is believed to be generic for migrating dislocations, grain boundaries, and so on that also have a higher capacity for attracting H atoms due to a positive activation volume at the migration saddles.

Cross-Media Semantic Correlation Learning Based on Deep Hash Network and Semantic Expansion for Social Network Cross-Media Search.

Cross-media search from large-scale social network big data has become increasingly valuable in our daily life because it can support querying different data modalities. Deep hash networks have shown high potential in achieving efficient and effective cross-media search performance. However, due to the fact that social network data often exhibit text sparsity, diversity, and noise characteristics, the search performance of existing methods often degrades when dealing with this data. In order to address this problem, this article proposes a novel end-to-end cross-media semantic correlation learning model based on a deep hash network and semantic expansion for social network cross-media search (DHNS). The approach combines deep network feature learning and hash-code quantization learning for multimodal data into a unified optimization architecture, which successfully preserves both intramedia similarity and intermedia correlation, by minimizing both cross-media correlation loss and binary hash quantization loss. In addition, our approach realizes semantic relationship expansion by constructing the image-word relation graph and mining the potential semantic relationship between images and words, and obtaining the semantic embedding based on both internal graph deep walk and an external knowledge base. Experimental results demonstrate that DHNS yields better cross-media search performance on standard benchmarks.

Low-Light Image Enhancement via a Deep Hybrid Network.

Camera sensors often fail to capture clear images or videos in a poorly lit environment. In this paper, we propose a trainable hybrid network to enhance the visibility of such degraded images. The proposed network consists of two distinct streams to simultaneously learn the global content and the salient structures of the clear image in a unified network. More specifically, the content stream estimates the global content of the low-light input through an encoder-decoder network. However, the encoder in the content stream tends to lose some structure details. To remedy this, we propose a novel spatially variant recurrent neural network (RNN) as an edge stream to model edge details, with the guidance of another auto-encoder. The experimental results show that the proposed network favorably performs against the state-of-the-art low-light image enhancement algorithms.

Low Rank Subspace Clustering via Discrete Constraint and Hypergraph Regularization for Tumor Molecular Pattern Discovery.

Tumor clustering is a powerful approach for cancer class discovery which is crucial to the effective treatment of cancer. Many traditional clustering methods such as NMF-based models, have been widely used to identify tumors. However, they cannot achieve satisfactory results. Recently, subspace clustering approaches have been proposed to improve the performance by dividing the original space into multiple low-dimensional subspaces. Among them, low rank representation is becoming a popular approach to attain subspace clustering. In this paper, we propose a novel Low Rank Subspace Clustering model via Discrete Constraint and Hypergraph Regularization (DHLRS). The proposed method learns the cluster indicators directly by using discrete constraint, which makes the clustering task simple. For each subspace, we adopt Schatten -norm to better approximate the low rank constraint. Moreover, Hypergraph Regularization is adopted to infer the complex relationship between genes and intrinsic geometrical structure of gene expression data in each subspace. Finally, the molecular pattern of tumor gene expression data sets is discovered according to the optimized cluster indicators. Experiments on both synthetic data and real tumor gene expression data sets prove the effectiveness of proposed DHLRS.

Variance-Constrained State Estimation for Nonlinearly Coupled Complex Networks.

This paper studies the state estimation problem for nonlinearly coupled complex networks. A variance-constrained state estimator is developed by using the structure of the extended Kalman filter, where the gain matrix is determined by optimizing an upper bound matrix for the estimation error covariance despite the linearization errors and coupling terms. Compared with the existing estimators for linearly coupled complex networks, a distinct feature of the proposed estimator is that the gain matrix can be derived separately for each node by solving two Riccati-like difference equations. By using the stochastic analysis techniques, sufficient conditions are established which guarantees the state estimation error is bounded in mean square. A numerical example is provided to show the effectiveness and applicability of the proposed estimator.

Water-n-BuOH solvothermal synthesis of ZnAl-LDHs with different morphologies and its calcined product in efficient dyes removal.

In this study, water-n-BuOH mixed solvents were used to synthesize the ZnAl-layered double hydroxides (ZnAl-LDHs) via hydrothermal method. The XRD, FT-IR, SEM, ICP and CHN analyses revealed that the type of intercalated anions, the layer Zn/Al ratios, and morphologies of the LDHs depended on the ratio of V(water)/V(n-BuOH) in the mixed solvents. When the ratio of V(water)/V(n-BuOH) is 3 or 0.3, the as-prepared LDHs had 3D "silk flowers" (ZnAl-LDH-3) or "Sedimentary rock" morphology (ZnAl-LDH-0.3). Adsorption properties of dyes on calcined LDHs were studied. Compared with ZnAl-LDO-0.3 and ZnAl-LDO-w (calcined from the LDHs obtained in pure water), ZnAl-LDO-3 showed much better adsorption efficiency for anionic dyes thanks to its much larger BET-specific surface area. The sorption kinetics for dyes was appropriately described by the pseudo-second-order model and sorption isotherms can be fitted more satisfactorily by the Langmuir model. With the increasing concentrations of dyes from 10mg/L to 400mg/L, the maximum absorption capacities of ZnAl-LDO-3 were 1540mg/g (2.21mmol/g) for congo red, 1153mg/g (3.52mmol/g) for methyl orange and 390mg/g (0.63mmol/g) for active red (X-3B), respectively. The adsorption dyes onto the external surface is still the main mechanism for LDO adsorbents. The ZnAl-LDO-3 was a potential adsorbent for dyeing wastewater treatment.

Radiation-Induced Helium Nanobubbles Enhance Ductility in Submicron-Sized Single-Crystalline Copper.

The workability and ductility of metals usually degrade with exposure to irradiation, hence the phrase "radiation damage". Here, we found that helium (He) radiation can actually enhance the room-temperature deformability of submicron-sized copper. In particular, Cu single crystals with diameter of 100-300 nm and containing numerous pressurized sub-10 nm He bubbles become stronger, more stable in plastic flow and ductile in tension, compared to fully dense samples of the same dimensions that tend to display plastic instability (strain bursts). The sub-10 nm He bubbles are seen to be dislocation sources as well as shearable obstacles, which promote dislocation storage and reduce dislocation mean free path, thus contributing to more homogeneous and stable plasticity. Failure happens abruptly only after significant bubble coalescence. The current findings can be explained in light of Weibull statistics of failure and the beneficial effects of bubbles on plasticity. These results shed light on plasticity and damage developments in metals and could open new avenues for making mechanically robust nano- and microstructures by ion beam processing and He bubble engineering.

Finite-Time Consensus for Multiagent Systems With Cooperative and Antagonistic Interactions.

This paper deals with finite-time consensus problems for multiagent systems that are subject to hybrid cooperative and antagonistic interactions. Two consensus protocols are constructed by employing the nearest neighbor rule. It is shown that under the presented protocols, the states of all agents can be guaranteed to reach an agreement in a finite time regarding consensus values that are the same in modulus but may not be the same in sign. In particular, the second protocol can enable all agents to reach a finite-time consensus with a settling time that is not dependent upon the initial states of agents. Simulation results are given to demonstrate the effectiveness and finite-time convergence of the proposed consensus protocols.

Robust consensus tracking control for multiagent systems with initial state shifts, disturbances, and switching topologies.

This paper deals with the consensus tracking control issues of multiagent systems and aims to solve them as accurately as possible over a finite time interval through an iterative learning approach. Based on the iterative rule, distributed algorithms are proposed for every agent using its nearest neighbor knowledge, for which the robustness problem is addressed against initial state shifts, disturbances, and switching topologies. These uncertainties are dynamically changing not only along the time axis but also the iteration axis. It is shown that the matrix norm conditions can be developed to achieve the convergence of the considered consensus tracking objectives, for which necessary and sufficient conditions are presented in terms of linear matrix inequalities to guarantee their feasibility in the sense of the spectral norm. Furthermore, simulation examples are given to illustrate the effectiveness and robustness of the obtained consensus tracking results.

Tracking algorithms for multiagent systems.

This paper is devoted to the consensus tracking issue on multiagent systems. Instead of enabling the networked agents to reach an agreement asymptotically as the time tends to infinity, the consensus tracking between agents is considered to be derived on a finite time interval as accurately as possible. We thus propose a learning algorithm with a gain operator to be determined. If the gain operator is designed in the form of a polynomial expression, a necessary and sufficient condition is obtained for the networked agents to accomplish the consensus tracking objective, regardless of the relative degree of the system model of agents. Moreover, the H∞ analysis approach is introduced to help establish conditions in terms of linear matrix inequalities (LMIs) such that the resulting processes of the presented learning algorithm can be guaranteed to monotonically converge in an iterative manner. The established LMI conditions can also enable the iterative learning processes to converge with an exponentially fast speed. In addition, we extend the learning algorithm to address the relative formation problem for multiagent systems. Numerical simulations are performed to demonstrate the effectiveness of learning algorithms in achieving both consensus tracking and relative formation objectives for the networked agents.

On the energetic dependence of charge separation in low-band-gap polymer/fullerene blends.

The energetic driving force required to drive charge separation across donor/acceptor heterojunctions is a key consideration for organic optoelectronic devices. Herein we report a series of transient absorption and photocurrent experiments as a function of excitation wavelength and temperature for two low-band-gap polymer/fullerene blends to study the mechanism of charge separation at the donor/acceptor interface. For the blend that exhibits the smallest donor/acceptor LUMO energy level offset, the photocurrent quantum yield falls as the photon excitation energy is reduced toward the band gap, but the yield of bound, interfacial charge transfer states rises. This interplay between bound and free charge generation as a function of initial exciton energy provides key evidence for the role of excess energy in driving charge separation of direct relevance to the development of low-band-gap polymers for enhanced solar light harvesting.

Data-driven control for relative degree systems via iterative learning.

Iterative learning control (ILC) is a kind of effective data-driven method that is developed based on online and/or offline input/output data. The main purpose of this paper is to supply a unified 2-D analysis approach for both continuous-time and discrete-time ILC systems with relative degree. It is shown that the 2-D Roesser system framework can be established for general ILC systems regardless of relative degree, under which convergence conditions can be provided to guarantee both asymptotic stability and monotonic convergence of the ILC processes. In particular, conditions for the monotonic convergence of ILC can be given in terms of linear matrix inequalities, and formulas for the updating law can be derived simultaneously. Simulation results are presented to illustrate the effectiveness of ILC determined through the 2-D design approach in dealing with the higher order relative degree problem of ILC systems, as well as the robustness of such ILC against uncertainties.

Benzotrithiophene--a planar, electron-rich building block for organic semiconductors.

Several functionalized benzo[1,2-b:3,4-b':5,6-d'']trithiophenes have been synthesized and characterized. The fully planar and highly electron-rich material shows great promise as the donor constituent in donor-acceptor type copolymers for use in organic electronics. As a proof of concept, a copolymer with the electron acceptor, 2,1,3-benzothiadiazole, has been prepared. Side-chain modifications have been employed to adjust both the electron-rich character of the monomer and the solubility and processability of the polymer.