Looking for small universal computing devices is a natural and well investigated topic in computer science. Recently, this topic started to be considered also in the framework of (synchronized) spiking neural P system...
详细信息
Looking for small universal computing devices is a natural and well investigated topic in computer science. Recently, this topic started to be considered also in the framework of (synchronized) spiking neural P systems. In this work, it is focused on small universal spiking neural P systems working in a non-synchronized manner. Specifically, it is proved that there is an asynchronous spiking neural P system with 76 neurons that is equivalent to a universal register machine for computing functions. As generator of sets of numbers, a universal asynchronous spiking neural P system with 75 neurons is constructed.
Nonnegative matrix factorization (NMF) is an increasingly popular technique for data processing and analysis. For an incomplete data matrix, the weighted nonnegative matrix factorization (WNMF) is employed to decompos...
详细信息
Nonnegative matrix factorization (NMF) is an increasingly popular technique for data processing and analysis. For an incomplete data matrix, the weighted nonnegative matrix factorization (WNMF) is employed to decompose it. But the searching step size in WNMF is not optimal along the given searching direction. This paper studies the incomplete nonnegative matrix factorization (INMF) and proposes an accelerated algorithm. First, INMF is transformed into solving alternatively two nonnegative least squares (NNLS) problems. For each NNLS problem, the exact step size is chosen along the searching direction. Then, the complexity of NNLS problems is analyzed. Finally, experimental results show that the proposed method outperforms WNMF.
RNA-binding proteins (RBPs) are essential for gene expression, and the complex RNA-protein interaction mechanisms require analysis of global RNA information. Therefore, accurate prediction of RBP binding sites on full...
详细信息
Multisensor information plays an important pole in the target recognition and other application fields. Fusion performance is tightly depended on the fusion level selectes and the approach used. Feature level fusion i...
详细信息
Multisensor information plays an important pole in the target recognition and other application fields. Fusion performance is tightly depended on the fusion level selectes and the approach used. Feature level fusion is a potential and difficult fusion level. Bayesian fusion method is an important theory in feature level. A new method is presented to fuse infrared images and recognize object in the paper. Firstly,Bayesian principles, fusion mode and recognition decision function are described. Then, aiming at the features of mid-wave infrared image and long-wave infrared image, we use Bayesian probability to fuse them. Last, recognize target and background obtained with training and test pattern vectors. The experiment results show stability and feasibility of the fusion recognition using Bayesian decision theory in infrared image.
Visual localization is a crucial component in the application of mobile robot and autonomous *** retrieval is an efficient and effective technique in image-based localization *** to the drastic variability of environm...
详细信息
Visual localization is a crucial component in the application of mobile robot and autonomous *** retrieval is an efficient and effective technique in image-based localization *** to the drastic variability of environmental conditions,e.g.,illumination changes,retrievalbased visual localization is severely affected and becomes a challenging *** this work,a general architecture is first formulated probabilistically to extract domain-invariant features through multi-domain image ***,a novel gradientweighted similarity activation mapping loss(Grad-SAM)is incorporated for finer localization with high *** also propose a new adaptive triplet loss to boost the contrastive learning of the embedding in a self-supervised *** final coarse-to-fine image retrieval pipeline is implemented as the sequential combination of models with and without Grad-SAM *** experiments have been conducted to validate the effectiveness of the proposed approach on the CMU-Seasons *** strong generalization ability of our approach is verified with the RobotCar dataset using models pre-trained on urban parts of the CMU-Seasons *** performance is on par with or even outperforms the state-of-the-art image-based localization baselines in medium or high precision,especially under challenging environments with illumination variance,vegetation,and night-time ***,real-site experiments have been conducted to validate the efficiency and effectiveness of the coarse-to-fine strategy for localization.
In this paper, an improved formulation of optimal guidance law (OGL) based on genetic algorithms (GAs) is proposed. Linear quadratic optimal control theory is derived to consider terminal velocity maximisation, also G...
详细信息
Consensus in multi-agent systems means that reach an agreement among states of the whole ***,almost all the existed works on consensus have been in the description of the states of nodes,and fewer efforts have been de...
详细信息
ISBN:
(纸本)9781479947249
Consensus in multi-agent systems means that reach an agreement among states of the whole ***,almost all the existed works on consensus have been in the description of the states of nodes,and fewer efforts have been devoted to the consensus taking place on the edges of multi-agent *** this paper,we focus on the dynamics proceed on the edges and establish a discrete-time and a continuous-time edge consensus protocols respectively for directed multi-agent *** mapping the edge topology to its line graph of the original nodal topology,we analyze the consensus of the edge protocols rigorously,and get that both the discrete-time protocol and the continuous-time protocol of directed multi-agent systems can guarantee that an edge consensus is asymptotically reached for all initial states when the original directed system is strongly *** simulations are provided to show the effectiveness of both the discrete-time and the continuous-time models.
This article proposes a multi-agent deep reinforce-ment learning algorithm to control a fleet of unmanned surface vessels (USVs) that encircle and capture sea targets. First, a simulation environment for USVs is estab...
详细信息
In point cloud registration applications,noise and poor initial conditions lead to many false *** matches significantly degrade registration accuracy and speed.A penalty function is adopted in many robust point-to-poi...
详细信息
In point cloud registration applications,noise and poor initial conditions lead to many false *** matches significantly degrade registration accuracy and speed.A penalty function is adopted in many robust point-to-point registration methods to suppress the influence of false ***,after applying a penalty function,problems cannot be solved in their analytical forms based on the introduction of ***,most existing methods adopt the descending *** this paper,a novel iterative-reweighting-based method is proposed to overcome the limitations of existing *** proposed method iteratively solves the eigenvectors of a four-dimensional matrix,whereas the calculation of the descending method relies on solving an eight-dimensional ***,the proposed method can achieve increased computational *** proposed method was validated on simulated noise corruption data,and the results reveal that it obtains higher efficiency and precision than existing methods,particularly under very noisy *** results for the KITTI dataset demonstrate that the proposed method can be used in real-time localization processes with high accuracy and good efficiency.
A fuzzy creative works generation algorithm based on graph neural network is proposed. Firstly, the multi-label fuzzy creative data set is constructed. Secondly, fuzzy logical correlations between creative objects are...
详细信息
暂无评论