Search

Predicting treatment medicines is a key task in many intelligent healthcare systems. Prediction of treatment medicines can assist doctors in making informed prescription decisions for patients according to their Electronic Health Records (EHRs). However, predicting treatment medicines is a challenging task due to the following reasons: (1) heterogeneous nature of EHR data that typically includes laboratory results, treatment records, disease conditions, and demographic information; (2) complex correlations among EHR sequences, including inter-correlations between sequences and temporal intra-correlations within each sequence; (3) temporal dynamics of these correlations changing with disease progression. In this paper, we predict treatment medicines for patients with dual adaptive sequential networks (DASNet). Specifically, DASNet is designed with three components. First, a decomposed adaptive long short-term memory network (DA-LSTM) is designed to capture the intra- and inter-correlations in multiple heterogeneous temporal sequences. Then, we develop an attentive meta learning network (AT-MetaNet) to learn dynamic weight parameters for DA-LSTM, thus enabling it to model various correlation structures. Finally, we employ an attentive fusion network (AT-FuNet) to incorporate historical information and collectively fuse representation embeddings of heterogeneous data to predict treatment medicines. Our results on the public MIMIC-III dataset covering 11 medical conditions demonstrate that the proposed end-to-end model can achieve the state-of-the-art prediction performance while providing clinically useful insights. [ABSTRACT FROM AUTHOR]

Existing self-supervised methods pose one-shot video object segmentation (O-VOS) as pixel-level matching to enable segmentation mask propagation across frames. However, the two tasks are not fully equivalent since O-VOS is more reliant on semantic correspondence rather than accurate pixel matching. To remedy this issue, we explore a new self-supervised framework that integrates pixel-level correspondence learning with semantic-level adaptation. The pixel-level correspondence learning is performed through photometric reconstruction of adjacent RGB frames during offline training, while semantic-level adaption operates at test-time by enforcing a bi-directional agreement of the predicted segmentation masks. In addition, we further propose a new network architecture with multi-perspective feature mining mechanism which can not only enhance reliable features but also suppress noisy ones to facilitate more robust image matching. By training the network using the proposed self-supervised framework, we achieve state-of-the-art performance on widely adopted datasets, further closing up the gap between self-supervised learning methods and their fully supervised counterparts. [ABSTRACT FROM AUTHOR]

Lorenz system is depicted by chemical reaction equations of an ideal formal chemical reaction network, and a series of reversible reactions are added into chemical reaction network in order to construct a cluster of hyper-Lorenz system. DNA as a universal substrate for chemical dynamics can approximate arbitrary dynamical characteristics of ideal formal chemical reaction network through auxiliary DNA strands and displacement reactions. Based on Lyapunov's stableness theory, a novel synchronization strategy is proposed. A 6-dimensional hyper-Lorenz system is taken as examples for simulation and shows that DNA strands displacement reactions can implement the synchronization of ideal formal chemical reaction networks. Numerical simulations indicate that synchronization based on DNA strand displacement is robust to the detection of DNA strand concentration, control of reaction rate, and noise. [ABSTRACT FROM AUTHOR]

Analog DNA strand displacement circuits can be used to build artificial neural network due to the continuity of dynamic behavior. In this study, DNA implementations of novel catalysis, novel degradation and adjustment reaction modules are designed and used to build an analog DNA strand displacement reaction network. A novel adaptive linear neuron (ADALINE) is constructed by the ordinary differential equations of an ideal formal chemical reaction network, which is built by reaction modules. When reaction network approaches equilibrium, the weights of the ADALINE are updated without learning algorithm. Simulation results indicate that, ADALINE based on the analog DNA strand displacement circuit has ability to implement the learning function of the ADALINE based on the ideal formal chemical reaction networks, and fit a class of linear function. [ABSTRACT FROM AUTHOR]

Contexts play an important role in salient object detection (SOD). High-level contexts describe the relations between different parts/objects and thus are helpful for discovering the specific locations of salient objects while low-level contexts could provide the fine detail information for delineating the boundary of the salient objects. However, the way of perceiving/leveraging rich contexts has not been fully investigated by existing SOD works. The common context extraction strategies (e.g., leveraging convolutions with large kernels or atrous convolutions with large dilation rates) do not consider the effectiveness and efficiency simultaneously and may cause sub-optimal solutions. In this paper, we devote to exploring an effective and efficient way to learn rich contexts for accurate SOD. Specifically, we first build a dense context exploration (DCE) module to capture dense multi-scale contexts and further leverage the learned contexts to enhance the features discriminability. Then, we embed multiple DCE modules in an encoder-decoder architecture to harvest dense contexts of different levels. Furthermore, we propose an attentive skip-connection to transmit useful features from the encoder part to the decoder part for better dense context exploration. Finally, extensive experiments demonstrate that the proposed method achieves more superior detection results on the six benchmark datasets than 18 state-of-the-art SOD methods. [ABSTRACT FROM AUTHOR]

At present, huge amounts of data are being produced every second, a situation that will gradually overwhelm current storage technology. DNA is a storage medium that features high storage density and long-term stability and is now considered to be a feasible storage solution. Errors are easily made during the sequencing and synthesis of DNA, however. In order to reduce the error rate, novel uncorrelated address constrain are reported, and a Damping Multi-Verse Optimizer (DMVO)algorithm is proposed to construct a set of DNA coding, which is used as the non-payload. The DMVO algorithm exchanges objects through black/white holes in order to achieve a stable state and adds damping factors as disturbances. Compared with previous work, the coding set obtained by the DMVO algorithm is larger in size and of higher quality. The results of this study reveal that the size of the DNA storage coding set obtained by the DMVO algorithm increased by 4–16 percent, and the variance of the melting temperature decreased by 3–18 percent. [ABSTRACT FROM AUTHOR]

DNA strand displacement is introduced in this study and used to construct an analog DNA strand displacement chaotic system based on six reaction modules in nanoscale size. The DNA strand displacement circuit is employed in encryption as a chaotic generator to produce chaotic sequences. In the encryption algorithm, we convert chaotic sequences to binary ones by comparing the concentration of signal DNA strand. Simulation results show that the encryption scheme is sensitive to the keys, and key space is large enough to resist the brute-force attacks, furthermore algorithm has a high capacity to resist statistic attack. Based on robustness analysis, our proposed encryption scheme is robust to the DNA strand displacement reaction rate control, noise and concentration detection to a certain extent. [ABSTRACT FROM AUTHOR]

With the development of information technology, huge amounts of data are produced at the same time. How to store data efficiently and at low cost has become an urgent problem. DNA is a high-density and persistent medium, making DNA storage a viable solution. In a DNA data storage system, the first consideration is how to encode the data effectively into code words. However, DNA strands are prone to non-specific hybridization during the hybridization reaction process and are prone to errors during synthesis and sequencing. In order to reduce the error rate, a thermodynamic minimum free energy (MFE) constraint is proposed and applied to the construction of coding sets for DNA storage. The Brownian multi-verse optimizer (BMVO) algorithm, based on the Multi-verse optimizer (MVO) algorithm, incorporates the idea of Brownian motion and Nelder–Mead method, and it is used to design a better DNA storage coding set. In addition, compared with previous works, the coding set has been increasing by 4%–50% in size and has better thermodynamic properties. With the improvement of the quality of the DNA coding set, the accuracy of reading and writing and the robustness of the DNA storage system are also enhanced. [ABSTRACT FROM AUTHOR]

Ideal formal chemical reaction network is an effective programming language to design complex system dynamical behavior. In this article, a coupled hyper-chaotic Lorenz system can be described by the ordinary differential equations of an ideal formal reaction network, which is constructed by catalysis, annihilation and adjust reaction modules, where the variables of system are represented by the difference in concentration of two chemical species. The ideal formal reaction network can be implemented by DNA strand displacement reaction network. Through Lyapunov exponent, we have analyzed hyper-chaotic dynamical behavior of coupled Lorenz system. In discussion and analysis, we have analyzed effect of noise, reaction rate control error and concentration detection error to DNA strand displacement reaction network. [ABSTRACT FROM AUTHOR]

DNA computing, the combination of computer science and molecular biology, is a burgeoning research field that holds promise for many applications. The accuracy of DNA computing is determined by reliable DNA sequences, the quality of which affects the accuracy of hybridization reactions. Evaluating the sequences obtained from the previous combination constraints in NUPACK for simulation experiments, we find that the concentration of the sequences after entering solution was significantly lower than that before entering solution, which should affect the accuracy of DNA hybridization reactions. Therefore, in this study, we propose a new constraint, a triplet-bases unpaired constraint, which can be combined with other constraints to form a new combination constraint. In addition, we combine the Harmony Search algorithm with the Whale Optimization Algorithm (WOA) to present a new algorithm, termed HSWOA, which we used to design DNA sequences that meet the new combination constraint. Finally, compared with previous findings, our result shows that our algorithm not only improves the efficiency of hybridization reactions but also yields a better fitness value. [ABSTRACT FROM AUTHOR]

Massively parallel sequencing, a popular and efficient sequencing method, produces a tremendous number of sequences from multiple individual samples. Labeling sequences with barcodes (tags) prevents them from being unrecoverable or confused during sequencing, replication, and oligonucleotide synthesis. In view of DNA barcode set design, we propose a tabu variable neighborhood search (TVNS) to design DNA barcode sets. We propose using sequences with the maximum sum of edit distances as the basis for building the neighborhood structures of TVNS. We adopt an exhaustive search to complete local searches built from these structures. The algorithm switches between neighborhoods built from different seed data. Compared with previous designs, our proposed algorithm is effective for designing DNA barcode sets and improving the lower bound of DNA barcode sets. [ABSTRACT FROM AUTHOR]

Deoxyribonucleic acid (DNA) strand displacement can be used to build complex functional circuits due to its highly modular and programmable properties. While DNA strand displacement is most often used to solve logic problems, it can also be used to compute the roots of equations. In this paper, we present the design of novel architectures for catalysis, degradation, and annihilation in ideal formal reaction modules, and we translate these reaction modules to DNA networks. These ideal formal or DNA reaction modules are suitable for building analog circuits for solving tasks. The computing analog DNA circuits are assessed by solving a linear equation, a one-variable quadratic equation, and a set of two simultaneous linear equations. The results were evaluated by simulation. [ABSTRACT FROM AUTHOR]

Recently, single-image super-resolution has made great progress due to the development of deep convolutional neural networks (CNNs). The vast majority of CNN-based models use a predefined upsampling operator, such as bicubic interpolation, to upscale input low-resolution images to the desired size and learn nonlinear mapping between the interpolated image and ground truth high-resolution (HR) image. However, interpolation processing can lead to visual artifacts as details are over smoothed, particularly when the super-resolution factor is high. In this paper, we propose a deep recurrent fusion network (DRFN), which utilizes transposed convolution instead of bicubic interpolation for upsampling and integrates different-level features extracted from recurrent residual blocks to reconstruct the final HR images. We adopt a deep recurrence learning strategy and, thus, have a larger receptive field, which is conducive to reconstructing an image more accurately. Furthermore, we show that the multilevel fusion structure is suitable for dealing with image super-resolution problems. Extensive benchmark evaluations demonstrate that the proposed DRFN performs better than most current deep learning methods in terms of accuracy and visual effects, especially for large-scale images, while using fewer parameters. [ABSTRACT FROM AUTHOR]

Following the completion of the human genome project, a large amount of high-throughput bio-data was generated. To analyze these data, massively parallel sequencing, namely next-generation sequencing, was rapidly developed. DNA barcodes are used to identify the ownership between sequences and samples when they are attached at the beginning or end of sequencing reads. Constructing DNA barcode sets provides the candidate DNA barcodes for this application. To increase the accuracy of DNA barcode sets, a particle swarm optimization (PSO) algorithm has been modified and used to construct the DNA barcode sets in this paper. Compared with the extant results, some lower bounds of DNA barcode sets are improved. The results show that the proposed algorithm is effective in constructing DNA barcode sets. [ABSTRACT FROM AUTHOR]