Target detecting algorithm in infrared image is drawing extensive attention both at home and abroad, expecially when the infrared images own complex backgrounds and low resolution. How to make sure of the accuracy of ...
详细信息
In the "standard" way of simulating register machines by spiking neural P systems (in short, SN P systems), one neuron is associated with each instruction of the register machine that we want to simulate. In...
详细信息
This paper presents an active disturbance rejection guidance method using quadratic transition for the atmospheric ascent guidance problem. The quadratic transition is designed from the current flight states with a re...
详细信息
Spiking neural P systems with weights(WSN P systems,for short)are a new variant of spiking neural P systems,where the rules of a neuron are enabled when the potential of that neuron equals a given *** is known that WS...
详细信息
Spiking neural P systems with weights(WSN P systems,for short)are a new variant of spiking neural P systems,where the rules of a neuron are enabled when the potential of that neuron equals a given *** is known that WSN P systems are universal by simulating register ***,in these universal systems,no bound is considered on the number of neurons and *** this work,a restricted variant of WSN P systems is considered,called simple WSN P systems,where each neuron has only one *** complexity parameter,the number of neurons,to construct a universal simple WSN P system is *** is proved that there is a universal simple WSN P system with 48 neurons for computing functions;as generator of sets of numbers,there is an almost simple(that is,each neuron has only one rule except that one neuron has two rules)and universal WSN P system with 45 neurons.
Pandemic influenza A (H1N1) has spread rapidly across the globe. In the event of pandemic influenza A (H1N1), decision-makers are required to act in the face of substantial uncertainties. Simulation models can be used...
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 system...
详细信息
This is a survey of two approaches to intelligentcontrol. The approaches are based on the author’s previous and ongoing projects in the Maximum Clique Problem (MCP) and the Crowd Dynamics. The ideas came from comput...
详细信息
Addressing insufficient supervision and improving model generalization are essential for multi-label classification with incomplete annotations, i.e. , partial and single positive labels. Recent studies incorporate ps...
Addressing insufficient supervision and improving model generalization are essential for multi-label classification with incomplete annotations, i.e. , partial and single positive labels. Recent studies incorporate pseudo-labels to provide additional supervision and enhance model generalization. However, the noise in pseudo-labels generated by the model tends to accumulate, resulting in confirmation bias during training. Self-correction methods, commonly used approaches for mitigating confirmation bias, rely on model predictions but remain susceptible to confirmation bias caused by visual confusion, including both visual ambiguity and similarity. To reduce visual confusion, we propose a prompt-guided consistency learning (PGCL) framework designed for two incomplete labeling settings. Specifically, we introduce an intra-category supervised contrastive loss, which imposes consistency constraints on reliable positive class samples in the feature space of each category, rather than across the feature space of all categories, as in traditional inter-category supervised contrastive loss. Building on this, the distinction between true positive and visual confusion samples for each category is enhanced through label-level contrasting of the same category. Additionally, we develop a class-specific semantic decoupling module that leverages CLIP’s strong vision-language alignment capability, since the proposed contrastive loss requires high-quality label-level representations as contrastive samples. Extensive experimental results on multiple datasets demonstrate that our method can effectively address the problems of two incomplete labeling settings and achieve state-of-the-art performance.
In propositional normal default logic, given a default theory(?, D) and a well-defined ordering of D, there is a method to construct an extension of(?, D) without any injury. To construct a strong extension of(?, D) g...
详细信息
In propositional normal default logic, given a default theory(?, D) and a well-defined ordering of D, there is a method to construct an extension of(?, D) without any injury. To construct a strong extension of(?, D) given a well-defined ordering of D, there may be finite injuries for a default δ∈ D. With approximation deduction ?s in propositional logic, we will show that to construct an extension of(?, D) under a given welldefined ordering of D, there may be infinite injuries for some default δ∈ D.
In the last decades,as a typical nonlinear system,active magnetic bearings(AMB) system has been widely applied in manufacturing systems.A sliding mode control(SMC) scheme for the AMB system is proposed with the distur...
详细信息
ISBN:
(数字)9789887581536
ISBN:
(纸本)9781665482561
In the last decades,as a typical nonlinear system,active magnetic bearings(AMB) system has been widely applied in manufacturing systems.A sliding mode control(SMC) scheme for the AMB system is proposed with the disturbance observation of the linear extended state observer(LESO) in this *** chattering of the AMB system has been reduced by LESO-SMC by at least 60%.Sufficient BIBO(bounded input-bounded output) stability conditions of the closed-loop AMB system governed by the proposed LESO-SMC are derived by Lyapunov ***,experiments are conducted to verify the effectiveness and superiority of the proposed LESO-SMC than conventional SMC.
暂无评论