The paper presents theoretical results on the global exponential periodicity and stability of a class of memristor-based recurrent neural networks with multiple delays. The dynamic analysis in the paper employs the th...
详细信息
The paper presents theoretical results on the global exponential periodicity and stability of a class of memristor-based recurrent neural networks with multiple delays. The dynamic analysis in the paper employs the theory of differential equations with discontinuous right-hand side as introduced by Filippov. By using the inequality techniques and a useful Lyapunov functional, some new testable algebraic criteria are obtained for ensuring the existence and global exponential stability of periodic solution of the system. The model based on the memristor widens the application scope for the design of neural networks, and the new effective results also enrich the toolbox for the qualitative analysis of neural networks. (C) 2012 Elsevier Inc. All rights reserved.
In this paper, we propose a new method for online multiple people tracking, which combines the detection process and the single object tracking process, and establishes the interactions between them. The detector dete...
详细信息
In this paper, we propose a new method for online multiple people tracking, which combines the detection process and the single object tracking process, and establishes the interactions between them. The detector detects objects in the still images which ignores the sequential information. Meantime, the single object tracker does not use the category semantic information during tracking. To take both the sequential and semantic information into account, we exchange information among the detector and the trackers. More specifically, the trackers deliver sequential information to the detector by providing the detector with the extra proposals. The detector supplements each tracker with the robust semantic information by using bounding box regression to modify the tracking result. Besides, the interactions also happen among the trackers through the occlusion speculation, the perspective model interpretation and the trajectory merging process. The experimental results demonstrate that the proposed algorithm performs favorably against the state-of-the-art MOT methods. (C) 2020 Elsevier B.V. All rights reserved.
作者：
Man, JingtaoZeng, ZhigangXiao, Qiang
Key Laboratory of Image Information Processing and Intelligent Control Ministry of Education of China Wuhan China
Spatial deployment of large-scale heterogeneous multi-agent systems (HMASs) over desired 2D or 3D curves is investigated in this paper. With assumption that HMASs consist of numerous first-order agents (FOAs) and seco...
详细信息
The thesis studies the semi-global scaled edge-consensus of linear discrete-time multi-agent systems under both the directed networks and undirected networks, where the states of each edge are subject to input saturat...
详细信息
The fleet size and mix vehicle routing problem (FSMVRP) is a class of combinatorial optimization problem with wide-ranging applications in practice. The purpose of this problem is to manage the routes as well as the t...
详细信息
The fleet size and mix vehicle routing problem (FSMVRP) is a class of combinatorial optimization problem with wide-ranging applications in practice. The purpose of this problem is to manage the routes as well as the type of vehicles. In this paper, we apply a bio-inspired algorithm based on the concept of membrane computing (named BIBMA) to solve FSMVRP. In BIBMA, a cell-like framework and rules such as updating rules, communication rules, recording rules and selecting rules, are combined to improve the algorithm's global search capacities. We tested our method on several benchmark functions of FSMVRP, including 12 instances with fixed cost and 8 instances without fixed cost. Simulation results show that the proposed algorithm is valid to solve FSMVRP for high quality results.
Membrane algorithms （MAs）, which inherit from P systems, constitute a new parallel and distribute framework for approximate computation. In the paper, a membrane algorithm is proposed with the improvement that the i...
详细信息
Membrane algorithms （MAs）, which inherit from P systems, constitute a new parallel and distribute framework for approximate computation. In the paper, a membrane algorithm is proposed with the improvement that the involved parameters can be adaptively chosen. In the algorithm, some membranes can evolve dynamically during the computing process to specify the values of the requested parameters. The new algorithm is tested on a well-known combinatorial optimization problem, the travelling salesman problem. The em-pirical evidence suggests that the proposed approach is efficient and reliable when dealing with 11 benchmark instances, particularly obtaining the best of the known solutions in eight instances. Compared with the genetic algorithm, simulated annealing algorithm, neural net-work and a fine-tuned non-adaptive membrane algorithm, our algorithm performs better than them. In practice, to design the airline network that minimize the total routing cost on the CAB data with twenty-five US cities, we can quickly obtain high quality solutions using our algorithm.
Spiking neural P systems (SN P systems, for short) are a class of parallel and distributed computation models inspired from the way the neurons process and communicate information by means of spikes. In this paper, we...
详细信息
Spiking neural P systems (SN P systems, for short) are a class of parallel and distributed computation models inspired from the way the neurons process and communicate information by means of spikes. In this paper, we consider a new variant of SN P systems, where each synapse instead of neuron has a set of spiking rules, and the neurons contain only spikes;when the number of spikes in a given neuron is "recognized" by a rule on a synapse leaving from it, the rule is enabled;at a computation step, at most one enabled spiking rule is applied on a synapse, and spikes are removed from a neuron if the maximum number of spikes that the applied spiking rules on the synapses starting from this neuron consume is. The computation power of this variant of SN P systems is investigated. Specifically, we prove that such SN P systems can generate or accept any set of Turing computable natural numbers. This result gives an answer to an open problem formulated in Theor. Comput. Sci., vol. 529, pp. 82-95, 2014.
The zero-voltage vector (ZVV) method is widely employed to restart a free-running permanent magnet synchronous machine (PMSM) stably in a sensorless drive system due to its simple implementation. However, in the conve...
详细信息
The zero-voltage vector (ZVV) method is widely employed to restart a free-running permanent magnet synchronous machine (PMSM) stably in a sensorless drive system due to its simple implementation. However, in the conventional method, it is hard to determine the action time and interval time of ZVV pulses, which may result in overcurrent. Moreover, the estimation accuracy is susceptible to current measurement noise. To cope with these problems, an enhanced ZVV method based on two feedback loops is proposed. With the proposed strategy, an inner closed loop is constructed to regulate the action time of the ZVV pulse by keeping the current amplitude at the reference value, which prevents the overcurrent. Meanwhile, the reference value of the current amplitude is adjusted automatically based on the outer loop to determine a suitable interval time of the ZVV pulse. Furthermore, the phase-locked loop technique is exploited to extract rotor speed and position. The feasibility of the proposed method is verified under simulation and experimental results with a 5.5 kW sensorless PMSM drive system.
Weakly-supervised semantic segmentation based on image-level annotations has difficulty exploring pixel-level information. Most approaches adopt Class Activation Maps (CAM) to localize initial object regions, called s...
详细信息
Weakly-supervised semantic segmentation based on image-level annotations has difficulty exploring pixel-level information. Most approaches adopt Class Activation Maps (CAM) to localize initial object regions, called seeds. To cover more potential object parts, seeds-expansion methods raise concern for artificial mask generation. Due to the seeds simply focus on discriminative regions, it is a challenge to spread seeds to the integral object. To tackle this problem, we propose a Cascade Semantic Erasing Network (CSENet) to expand seeds effectively and reasonably. In particular, CSENet sequentially stacks the semantic erasing stage to erase discriminative areas progressively. It forces the network to exploit rel-evant feature response for non-discriminative object districts. Moreover, CSENet directly suppresses seeds on the Class Activation Maps (CAM), which have stronger semantics, rather than on the Intermediate Feature Maps (IFM). Under semantic guidance, proposed erasing strategy correctly spreads seeds regions to the intra-class regions and meanwhile, prohibits from extending to the unexpected inter-class areas. Extensive experiments demonstrate the effectiveness of proposed CSENet. More specif-ically, our approach achieves 62.3% and 63.4% mIoU on PASCAL VOC 2012 validation and test set, respectively. (c) 2020 Elsevier B.V. All rights reserved.
Membrane systems are parallel molecular computing models basing on processing multisets of objects in cell-like membrane structures. Inspired by brane calculi, membrane systems with peripheral proteins which differ fr...
详细信息
Membrane systems are parallel molecular computing models basing on processing multisets of objects in cell-like membrane structures. Inspired by brane calculi, membrane systems with peripheral proteins which differ from conventional membrane systems have been investigated. In order to get the possibility to solve computationally hard problems in polynomial time, cell division rule is introduced into this model, which is endowed with the ability of generating an exponential workspace in a linear time. In this paper, a solution for SAT problem by this model is presented.
暂无评论