Search

This paper presents a portable inertial measurement unit (IMU)-based motion sensing system and proposed an adaptive gait phase detection approach for non-steady state walking and multiple activities (walking, running, stair ascent, stair descent, squat) monitoring. The algorithm aims to overcome the limitation of existing gait detection methods that are time-domain thresholding based for steady-state motion and are not versatile to detect gait during different activities or different gait patterns of the same activity. The portable sensing suit is composed of three IMU sensors (wearable sensors for gait phase detection) and two footswitches (ground truth measurement and not needed for gait detection of the proposed algorithm). The acceleration, angular velocity, Euler angle, resultant acceleration, and resultant angular velocity from three IMUs are used as the input training data and the data of two footswitches used as the training label data (single support, double support, swing phase). Three methods 1) Logistic Regression (LR), 2) Random Forest Classifier (RF), and 3) Artificial Neural Network (NN) are used to build the gait phase detection models. The result shows our proposed gait phase detection with Random Forest Classifier can achieve 98.94% accuracy in walking, 98.45% in running, 99.15% in stair-ascent, 99.00% in stair-descent, and 99.63% in squatting. It demonstrates that our sensing suit can not only detect the gait status in any transient state but also generalize to multiple activities. Therefore, it can be implemented in real-time monitoring of human gait and control of assistive devices.

This paper is concerned with the stability and periodicity for a class of impulsive neural networks with delays. By means of the Fixed point theory, Lyapunov functional and analysis technique, some sufficient conditions of exponential stability and periodicity are obtained. We can see that impulses do contribution to the stability and periodicity. An example is given to demonstrate the effectiveness of the obtained results.

In this paper, the existence and global exponential stability of periodic solution is investigated for a class of impulsive bidirectional associative memories neural networks that possesses a Cohen-Grossberg dynamics incorporating variable delays and time-variant coefficients. By using compressive mapping and Lyapunov functional, sufficient conditions are obtained to guarantee the existence and uniqueness of the periodic solution and its global exponential stability. We can see that impulses contribute to the existence and stability of periodic solution for this system. Some comparisons and examples are given to demonstrate the effectiveness of the obtained results. The model studied in this paper is a generalization of some existing models in literature, including Hopfield neural networks, BAM neural networks with impulse and time delays, Cohen-Grossberg neural networks, and thus, the main results of this paper generalize some results in literature.

In this paper, we investigate impulsive effects on the stability of BAM type Cohen-Grossberg neural networks with variable delays and obtain some sufficient conditions ensuring exponential stability of the impulsive variable delays system on time scales. The results extend and improve some recent works for impulsive neural networks as well as non-impulsive neural networks(or on time scales).

This paper analyses the existence and globally exponential stability of a class of cellular neural networks with distributed delays, with assuming global Lipschitz conditions on the activation functions, applying the idea of vector Lyapunov function, Young inequality and Halanay differential inequality with delay, some sufficient conditions are obtained to ensure the equilibrium point.

By Lyapunov function and Halanay inequality etc., a class of the BAM type Cohen-Grossberg neural network with delays and impulsive is considered on time scales. It obtained some sufficient conditions about the existence of equilibrium point, globally exponential stability and globally exponentially robust stability. We can see the impulses do contribution to the exponential stability and robust stability. At last, some applications and examples can be demonstrate the results.

A class of impulsive neural networks with distributed delays is studied in this paper. With assuming global Lipschitz conditions on the activation functions, applying idea of vector Lyapunov function, combining Young inequality and Halanay differential inequality with delay, sufficient conditions are obtained for the existence of unique and global exponential stable equilibrium of the distributed delay neural networks.

In this paper, a class of impulsive neural networks with time-varying delays is considered to study the globally exponential stability New sufficient conditions for globally exponential stability are obtained by using the vector Lyapunov function, Young inequality and Halanay differential inequality with delay.

In this paper, with assuming global Lipschitz conditions on the activation functions, applying idea of vector Lyapunov function, Young inequality and Halanay differential inequality with delay, the global exponential stability of the equilibrium point for a class of Cohen-Grossberg neural networks with time-varying delays and impulses is investigated, the sufficient conditions for globally exponential stability of neural networks are obtained.

In this paper, a class of BAMtype Cohen-Grossberg neural networks with delays are studied. Some sufficient conditions ensuring global exponential stability of the system are obtained on time scales. The results extend and improve some recent works for neural networks.

In this paper, the main purpose is to study the global exponential stability of the equilibrium point for a class of cellular neural networks with impulses and distributed delays. With the assumption of global Lipschitz conditions on the activation function, applying idea of vector Lyapunov function, combining Halanay differential inequality with delay, a sufficient condition for globally exponential stability of neural networks is obtained.

In this paper, with assuming global Lipschitz conditions on the activation functions, applying idea of vector Lyapunov function, Young inequality and Halanay differential inequality with delay, the global exponential stability of the equilibrium point for a class of cellular neural networks with distributed delays and large impulses is investigated, the sufficient conditions for globally exponential stability of neural networks are obtained.

The main purpose of this paper is to study the globally exponential stability of the equilibrium point for a class of cellular neural networks with distributed delays and large impulses. With assuming global Lipschitz conditions on the activation functions, applying idea of vector Lyapunov function, combining Halanay differential inequality with delay, the sufficient conditions for globally exponential stability of neural networks are obtained.

The main purpose of this paper is to study the globally exponential stability of the equilibrium point for a class of impulsive neural networks with time-varying delays. Without assuming global Lipschitz conditions on the activation functions, applying idea of vector Lyapunov function, combining Halanay differential inequality with delay, the sufficient conditions for globally exponential stability of neural networks are obtained.

This paper is concerned with the stability and periodicity for a class of impulsive neural networks with delays. By means of the Fixed point theory, Lyapunov functional and analysis technique, some sufficient conditions of exponential stability and periodicity are obtained. We can see that impulses do contribution to the stability and periodicity. An example is given to demonstrate the effectiveness of the obtained results.

The main purpose of this paper is to study the globally exponential stability of the equilibrium point for a class of impulsive neural networks with time-varying delays. Without assuming global Lipschitz conditions on the activation functions, applying idea of vector Lyapunov function, combining Young inequality and Halanay differential inequality with delay, the sufficient conditions for globally exponential stability of neural networks are obtained.

This paper is concerned with a class of neural networks with delays and impulses. Some sufficient conditions are obtained for the existence and globally exponential stability of a unique equilibrium solution without assuming the activation function to be bounded, monotonic or differentiable. An example is given to demonstrate the effectiveness of the obtained results.

In this paper, a class of impulsive neural networks with time-varying delays is studied. Without assumption of global Lipschitz conditions on the activation functions, applying idea of vector Lyapunov function, combining Halanay differential inequality with delay, a sufficient condition for globally exponential stability of the equilibrium is obtained

In this paper , With assumption of global Lipschitz conditions on the activation functions, by Lyapunov function and Halanay differential inequality with delay, we study a class of cellular neural networks with distributed delays and large impulses. It obtained a sufficient condition for globally exponential stability of the equilibrium point.

Stitch partition is a prominent problem of embroidery information restoring. This paper concerns several relative algorithms and presents their applicability and limitation. Combined the characteristics of stitch with BP neural network, a stitch partition algorithm is provided. An experiment is given in the end. The algorithm has been applied to an embroidery CAD system which has gotten reputation among end users.

In this paper we study the globally exponential stability of a class of neural networks with time-varying delays. Applying idea of vector Lyapunov function, Young inequality and Halanay differential inequality with delay, the sufficient conditions for the existence and globally exponential stability of the equilibrium point are obtained

By Lyapunov function and Halanay inequality, a class of the BAM type Cohen-Grossberg neural network with delays and impulsive is considered. It obtained some sufficient conditions about the existence of equilibrium point, globally exponential stability and globally exponentially robust stability. We can see the impulses do contribution to the exponential stability and robust stability.At last, an example can be demonstrate the results.

Employing general Halanay inequalities, Dinipsilas derivative and functional analysis techniques, several global exponential stability criteria of the equilibrium point are established for a class of delayed reaction-diffusion recurrent neural networks. These criteria are only dependent on the parameters of the system. The results correct some errors of the earlier publication.

Some sufficient conditions are obtained for the global exponential stability of a solution and existence of the periodic solution to the general bidirectional associative memory (BAM) neural networks with distributed delay and impulsive by using the Lyapunov functional and some inequality technique. These results are helpful for designing a globally exponential stable and periodic oscillatory BAM neural network, and the conditions can be easily applied in practice. An example is also given to illustrate our results.

By using the method of Lyapunov function and analysis technique, a model for bidirectional associative memory with impulsive is studied. Sufficient conditions are obtained for the existence and uniformly stability of a unique equilibrium solution . We can see that impulses do contribute to systempsilas uniformly stability. This stability property is independent of the stability of continuous-time BAM model.

This paper is concerned with the stability of the impulsive Cohen-Grossberg neural networks with variable delays. By means of matrices theory, Lyapunov function and analysis technique, sufficient conditions are obtained for the uniform stability of a unique equilibrium solution of this system. We can see that impulses do contribution to system's uniform stability, so the impulsive system is stable whether the corresponding continuous-time system is stable or not. As the applications of the main theorems, some uniform stability criteria are established for several well known impulsive ecological models with variable delays.

In this paper, a model of impulsive general BAMs neural networks is first formulated.We investigate impulsive effects on the stability of BAMs neural networks with variable delays and obtain some sufficient conditions ensuring exponential stability of the impulsive variable delays system.The results extend and improve some recent works for impulsive neural networks as well as non-impulsive neural networks.