The classification of hyperspectral images (HSIs) is a hot topic in the field of remote sensing technology. In recent years, convolutional neural network (CNN) has achieved great success for HSI classification. Howeve...
详细信息
The classification of hyperspectral images (HSIs) is a hot topic in the field of remote sensing technology. In recent years, convolutional neural network (CNN) has achieved great success for HSI classification. However, CNN has to do a great effort in parameters tuning which is time-consuming. Furthermore, a large number of samples are required to train CNN, nevertheless, it is expensive to obtain enough training samples from HSIs. In this paper, we propose a novel classification approach based on deep forest. To reduce the dimension of hyperspectral data, principal component analysis (PCA) is performed during the pre-processing. In contrast to the CNN, our method has fewer hyper-parameters and faster training speed. To the best of our knowledge, this is among the first deep forest-based hyperspectral spectral information classification. Extensive experiments are conducted on two real-world HSI datasets to show the proposed method is significantly superior to the state-of-the-art methods.
A bacteria-immunity system model is formulated to describe the interaction between bacteria and immune cells with quorum sensing. Time delay is introduced to study this system. The stability and the conditions for the...
详细信息
This paper presents a general six degrees of freedom(6-DOF) robot arm control system based on Linux and field-programmable gate array(FPGA).The system provides a friendly human-computer interaction *** can complete pa...
详细信息
This paper presents a general six degrees of freedom(6-DOF) robot arm control system based on Linux and field-programmable gate array(FPGA).The system provides a friendly human-computer interaction *** can complete palletizing,handling and other processes through simple programming of the interactive *** adopt industrial personal computer(IPC) as the controller to accomplish the kinematics calculation,design motion control board connected with the controller and the servo system,and use the servo system to implement the motion of the robot *** kinematics calculation and trajectory generation based on cubic polynomial are developed based on the Linux system,which improves the portability of the *** a normal method is adopted in updating trajectory points to improve *** control board is designed based on FPGA,which with the characteristic of parallel computing raises the running speed of the robot arm.
In this work, we propose a new scheme to estimate the algebraic connectivity of the graph describing the network topology of a multi-agent system. We consider network topologies modeled by undirected graphs. The main ...
详细信息
Piezoelectric geophones are vibration detectors that convert vibration acceleration signals into electrical signals. High performance piezoelectric materials can improve the sensitivity of piezoelectric geophone and m...
详细信息
Piezoelectric geophones are vibration detectors that convert vibration acceleration signals into electrical signals. High performance piezoelectric materials can improve the sensitivity of piezoelectric geophone and meet the need of high-resolution seismic data acquisition. The comprehensive performance of relaxor piezoelectric single crystal PMN-PT is more superior than PZT, and it is potential to be applied to high sensitivity and small volume geophones. In this paper, the central compressed geophone core model based on PMN-PT was established and theoretically analyzed. Then, a multiphysics simulation model was set up in COMSOL for simulation calculation. Finally, experimental verification was carried out. The results show that using PMN-PT in geophone core design can improve the sensitivity of the model by more than 120% compared with the traditional PZT material. The PMN-PT has the potential to be applied to high sensitivity and small volume geophones.
A single satellite navigation system can get high accuracy in general environment, but when the ground satellite navigation receiver is in complex environment, single system navigation often results in poor location r...
详细信息
A single satellite navigation system can get high accuracy in general environment, but when the ground satellite navigation receiver is in complex environment, single system navigation often results in poor location results due to the visible satellite less than four. If multiple constellation fusion navigation is used, the number of visible satellites can be increased, thus improving the positioning results. However, the use of all visible satellites in location calculation will bring a huge amount of calculation, which seriously affects the real-time performance of navigation and positioning. Therefore, a reasonable selection of star selection method is urgently needed in the integrated navigation system. Based on the two performance indexes of balanced geometric accuracy factor (GDOP) and star selection efficiency, fast star selection algorithm based on equivalent distance error is proposed in this paper. The experimental results show that the method can effectively improve the efficiency of multi constellation star selection of the premise of high precision.
This paper concerns disturbance rejection for a repetitive-control system(RCS) with unknown time-varying uncertainties and nonlinearity. The design of the RCS is based on the concept of equivalent input disturbance...
详细信息
ISBN:
(纸本)9781538629185
This paper concerns disturbance rejection for a repetitive-control system(RCS) with unknown time-varying uncertainties and nonlinearity. The design of the RCS is based on the concept of equivalent input disturbance(EID). First, an EID estimator is constructed through a state observer with dynamic coefficient matrix that effectively estimates the total effect of the uncertainties and nonlinearity on the output of the plant. Next, a robust globally uniformly ultimately bounded stability condition for the EID-based RCS is derived in the form of a linear matrix inequality. Then, the methods of designing a modified repetitive controller, a state-feedback controller, and an EID estimator are explained. Finally, simulation results demonstrate the validity of the method.
A new type of rehabilitation robot that can follow the user side-by-side is designed for aiding the elderly and disabled. The Human Following Rehabilitation Robot (HFRR) consists of a metal armrest, a set of sensors a...
A new type of rehabilitation robot that can follow the user side-by-side is designed for aiding the elderly and disabled. The Human Following Rehabilitation Robot (HFRR) consists of a metal armrest, a set of sensors and a differential mobile base. By predicting the user's speed in the future through the user's current walking speed and the preset path, the problem of human following side-by-side is converted to a problem of keeping a certain lateral distance from the predicted trajectory. Linearizing the tracking error model, the nonholonomic mobile robot (NMR) can maintain a certain lateral distance from the trajectory by using Model Predictive control (MPC) and then follow the user side-by-side. The simulation and experimental results show the proposed controller can obtain good performance in this problem.
TinySLAM algorithm is a simple 2D laser SLAM algorithm. However, in practical applications, it has higher error rate of mapping because of its simple filter. In this paper, an improved TinySLAM algorithm is proposed f...
详细信息
TinySLAM algorithm is a simple 2D laser SLAM algorithm. However, in practical applications, it has higher error rate of mapping because of its simple filter. In this paper, an improved TinySLAM algorithm is proposed for simultaneous location and mapping. By adding a simple filter before the Monte Carlo simulation and then fusing the information from the odometer, the error in the positioning process can be reduced. Moreover, the introduced hybrid map cell model that can be compatible with ROS system, improves the response to dynamic obstacles, and reduces the mapping error rate further. Simulation using ROS system and Stage software is performed, from which the results show that the proposal has good effects comparing with TinySLAM, and the error rate is reduced so that the map built is closer to the actual environment.
Ant colony optimization (ACO) has been shown effectiveness for solving combinatorial optimization problems. Inspired by the basic principles of ACO, this paper proposes a novel evolutionary algorithm, called probabili...
详细信息
暂无评论