Two types of novel cellular neural networks based on mem-elements are proposed, namely, MC-CNN and EM-CNN. The MC-CNN lets a memcapacitor replace the conventional linear capacitor of a cellular neural network cell. Th...
详细信息
In this paper, we address the problem of person reidentification (re-id), which remains to be challenging due to view point changes, pose variations, different camera settings, etc. Different from common methods that ...
详细信息
ISBN:
(纸本)9781479961016
In this paper, we address the problem of person reidentification (re-id), which remains to be challenging due to view point changes, pose variations, different camera settings, etc. Different from common methods that concatenate descriptors extracted from different support regions and feature channels directly as a long vector, we encode the importance of different feature channels and support regions explicitly and propose a two-layer distance ensemble model called DeNet to measure the similarity between two images. The first layer of DeNet combines distances of different support regions while the second layer weights different feature channels. Weight parameters of DeNet are learnt under the large margin framework with the goal of maximizing the difference between distances of positive and negative matching pairs. Our method achieves very competitive results on the widely used VIPeR and PRID 450S datasets.
This study investigates the problem of event-based synchronisation of linear discrete-time dynamical networks. Leader-following and leaderless synchronisations are achieved by a distributed event-trigger strategy. It ...
详细信息
In memristor memory design,it is often concentrated on the feedback control effect and not much on the reliability and *** study adopt an adaptive write,read and erase method,and realize a more resilient memory operat...
详细信息
ISBN:
(纸本)9781467374439
In memristor memory design,it is often concentrated on the feedback control effect and not much on the reliability and *** study adopt an adaptive write,read and erase method,and realize a more resilient memory operation in the face of low yield in the nano-memory technology *** analyzing writing,reading and erasing strategies for our target memory cell,we present simulation results that show the feasibility of these writing,reading and erasing ***,the narrow current pulse stimulus is compared to the ramp current stimulus,and the latter one is shown to have a faster writing *** simulation results are based on a SPICE model built upon the TiO2 memristive device made in HP laboratory.
The two areas of picture languages and membrane computing were linked by array-rewriting P system in which array objects and context-free array-rewriting rules are used in order to generate picture languages. While re...
详细信息
In this paper, a novel interval type-2 fuzzy logic controller (IT2FLC) is proposed for controlling a mobile wheeled inverted pendulum(MWIP) with model uncertainties and external disturbances. The MWIP is a typical und...
详细信息
ISBN:
(纸本)9781467384155
In this paper, a novel interval type-2 fuzzy logic controller (IT2FLC) is proposed for controlling a mobile wheeled inverted pendulum(MWIP) with model uncertainties and external disturbances. The MWIP is a typical underactuated system which is generally composed of two subsystems, an invert pendulum and a mobile robot system. The IT2FLC proposed in this paper is composed of a balancing controller, a velocity controller and a yaw steering controller. The proposed integrated IT2FLC is linear combination of the three individual IT2FLCs which uses simplified type reduce method. The proposed controller has simple structure and requires less computation, also it is expected to have robustness to uncertainties and external disturbances in the practical implementation. Considering the model uncertainties and external disturbances, simulation results proved the effectiveness and robustness of the proposed IT2FLC compared with type-1 fuzzy logic controller (T1FLC).
This paper proposes a novel system for generating 1-D m-scroll, 2-D m×n-grid multi-scroll, 3-D m×n×l-grid multi-scroll chaotic attractors (GMSCAs) via switching piecewise linear (PWL) function. First, a...
详细信息
ISBN:
(纸本)9781467371902
This paper proposes a novel system for generating 1-D m-scroll, 2-D m×n-grid multi-scroll, 3-D m×n×l-grid multi-scroll chaotic attractors (GMSCAs) via switching piecewise linear (PWL) function. First, a third-order linear system satisfying certain conditions is introduced as the original system. Then, by adding stair function, saturated function series and hysteresis function series to the third-order linear system, respectively, GMSCAs are generated along a certain line, or plane, or in the whole state space. Besides, some basic dynamical behaviors of the controlled system are investigated and numerical simulations are given to verify the effectiveness of this method.
This paper proposes a systematically method for generating high-dimensional grid multi-scroll attractors (GMSAs), including 3-D, 4-D, 5-D and even higher-dimensional GMSAs. Firstly, based on a third-order linear syste...
详细信息
ISBN:
(纸本)9781467371902
This paper proposes a systematically method for generating high-dimensional grid multi-scroll attractors (GMSAs), including 3-D, 4-D, 5-D and even higher-dimensional GMSAs. Firstly, based on a third-order linear system, higher-order linear systems are constructed by introducing state feedback controllers. Then, switching piecewise linear (PWL) functions, including stair function and saturated series function, are introduced, respectively, to make the higher-order systems generate high-dimensional GMSAs. Besides, some basic dynamical properties of GMSA systems are investigated and numerical simulations are given to demonstrate the feasibility of the proposed method.
In this study we modified the local binary pattern operator (LBP) to obtain the robust invariant texture patterns for image texture classification. The modified method will be able to calculate patterns which are inva...
详细信息
Spiking neural P systems with anti-spikes (ASN P systems) are variant forms of spiking neural P systems, which are inspired by inhibitory impulses/spikes or inhibitory synapses. The typical feature of ASN P systems ...
详细信息
Spiking neural P systems with anti-spikes (ASN P systems) are variant forms of spiking neural P systems, which are inspired by inhibitory impulses/spikes or inhibitory synapses. The typical feature of ASN P systems is when a neuron contains both spikes and anti-spikes, spikes and anti-spikes wil immediately annihilate each other in a maximal way. In this paper, a restricted variant of ASN P systems, cal ed ASN P systems without anni-hilating priority, is considered, where the annihilating rule is used as the standard rule, i.e., it is not obligatory to use in the neuron associated with both spikes and anti-spikes. If the annihilating rule is used in a neuron, the annihilation wil consume one time unit. As a result, such systems using two categories of spiking rules (identified by (a, a) and (a,a^-)) can achieve Turing completeness as number accepting devices.
暂无评论