Real-time varying matrix inversion is widely used in the fields of science and engineering, e.g., image processing, signal processing and robot technology, etc. In this paper, a nonlinearity activated noise-tolerant z...
详细信息
ISBN:
(纸本)9789881563958
Real-time varying matrix inversion is widely used in the fields of science and engineering, e.g., image processing, signal processing and robot technology, etc. In this paper, a nonlinearity activated noise-tolerant zeroing neural network (NANTZNN) is constructed and employed to the time-dependent matrix inversion in the noisy environment. Compared with the gradient approach related neural network (GNN) and the existing noise-tolerant zeroing neural network (NTZNN), the proposed NANTZNN model is activated by specially-constructed nonlinear activation functions, and thus possesses the better convergence performance. Additionally, theoretical analyses are provided to guarantee the convergence of the proposed model. Finally, simulations are conducted to demonstrate the efficiency and superiority of the NANTZNN model for time-dependent matrix inversion, as compared with the NTZNN model.
Real-time varying matrix inversion is widely used in the fields of science and engineering, e.g., image processing, signal processing and robot technology, etc. In this paper, a nonlinearity activated noise-tolerant z...
详细信息
Real-time varying matrix inversion is widely used in the fields of science and engineering, e.g., image processing, signal processing and robot technology, etc. In this paper, a nonlinearity activated noise-tolerant zeroing neural network(NANTZNN) is constructed and employed to the time-dependent matrix inversion in the noisy environment. Compared with the gradient approach related neural network(GNN) and the existing noise-tolerant zeroing neural network(NTZNN), the proposed NANTZNN model is activated by specially-constructed nonlinear activation functions, and thus possesses the better convergence performance. Additionally, theoretical analyses are provided to guarantee the convergence of the proposed model. Finally, simulations are conducted to demonstrate the efficiency and superiority of the NANTZNN model for time-dependent matrix inversion,as compared with the NTZNN model.
computer generated forces (CGF) simulations have entities as actors in their simulation. A type of CGF in which the entities have limited autonomy is semi- automated forces (SAF). The SAF system for this thesis resear...
详细信息
computer generated forces (CGF) simulations have entities as actors in their simulation. A type of CGF in which the entities have limited autonomy is semi- automated forces (SAF). The SAF system for this thesis research is OneSAF, a near real- time SAF that offers raw data collection of the entities in a particular simulation scenario. The data collection files vary in size from 500 kilobytes to larger than four gigabytes. Entity behavior property verification (BPV) is an integral part of SAF simulation software testing. The purpose for this research is to provide immediate feedback to the system user/developer as to what an entity had done in a scenario. From the simulation point of view, it provides answers to questions like "Did the entity route shortest distance to destination" From the developer's point of interest, the BPV can provide insight to flaws in the model, such as a vehicle crossing a river where a bridge does not exist. Automated BPV (ABPV) takes one step further by minimizing "hard coding" of tools that process collection files. ABPV allows portability of the product of this thesis to other systems. ABPV Tools (ABPVT) of this thesis is designed to run in Linux and Windows and will be included in future distributions of OneSAF as an intricate part of the testing suite.
暂无评论