This paper proposes a new approach which combines unsupervised and supervised learning for training recurrent neural networks (RNNs). In this approach, the weights between input and hidden layers were determined accor...
详细信息
This paper proposes a new approach which combines unsupervised and supervised learning for training recurrent neural networks (RNNs). In this approach, the weights between input and hidden layers were determined according to an unsupervised procedure relying on the Kohonen algorithm and the weights between hidden and output layers were updated according to a supervised procedure based on dynamic gradient descent method. The simulation results show that the proposed method performs well in comparison with the back propagation through time algorithm.
This work describes a visual odometry by minimizing a quadrifocal constraint in order to calculate the position of an autonomous vehicle (Cycab). This method can also reject outliers corresponding to moving objects su...
详细信息
This work describes a visual odometry by minimizing a quadrifocal constraint in order to calculate the position of an autonomous vehicle (Cycab). This method can also reject outliers corresponding to moving objects such as occlusions and illumination changes. An iterative non-linear trajectory estimation approach is formulated and it is based on a quadrifocal relationship between the image intensities within adjacent views of the stereo pair. The technique is applied to recovering the trajectory of a moving vehicle in a video sequence.
The aim of the paper is to assess the feasibility of impedance measurements for meat aging detection. The carried investigations are dedicated to the aging of the meat of beef. An investigation was carried out for the...
详细信息
The aim of the paper is to assess the feasibility of impedance measurements for meat aging detection. The carried investigations are dedicated to the aging of the meat of beef. An investigation was carried out for the detection of the age of meat using 2 cases of storage in the fridge, unpacked meat, exposed in the air of the fridge (Up) and vacuum-packed meat, conserved in closed box (Vp). The measurements show a depressed semicircle in the admittance plane similar to the equivalent circuit consisting of a combination of a Constant Phase Element (CPE) and two resistors. The resistance R E various is directly proportional to meat volume resistivity. The volume resistivity is constant for Vp meat, this is due to the conservation of the same situation in the surface of contact with the electrode, this situation change for the Up meat, the volume resistivity is increasing in a linear way because the surface of contact with electrode become more dry over time. The change due to R ct is inversely proportional to the factor number of electrons involved and exchange current. The factor n.i 0 decreases over time for the Up meat, This is consistent because when the meat becomes drier, the loss of liquids causes the decrease of conductivity and proportionally the decrease of the number of electrons involved and the exchange current. For the second case (Vp), the humidity causes the decrease of the number of electrons involved and the exchange current. The impedance is inversely proportional to the double layer capacitance that is consistent with the experiments. The impedance increase for the Up meat and decrease in the second case. The change due to Cdl is directly proportional to the change of meat permittivity ε r .
This paper presents two strategies of nonlinear predictive control based on a Takagi-Sugeno fuzzy model. The first one introduces a fuzzy logic-based modeling methodology, where a nonlinear system is divided into a nu...
详细信息
This paper presents two strategies of nonlinear predictive control based on a Takagi-Sugeno fuzzy model. The first one introduces a fuzzy logic-based modeling methodology, where a nonlinear system is divided into a number of linear subsystems. So the linear model based predictive control (MPC) technique is used for each subsystem. In the second one, the fuzzy model is considered as a nonlinear model of the system and the control signal is obtained by minimizing either the cumulative differences or the instant difference between set-point and fuzzy model output. The efficiency of these two fuzzy model predictive control (FMPC) approaches is demonstrated through two examples.
In this paper, we propose a design of a current controlled Quadrature Sinusoidal Oscillator. The proposed circuit employs three optimized Multi-output translinear second generation current conveyer (MCCII). The oscill...
详细信息
In this paper, we propose a design of a current controlled Quadrature Sinusoidal Oscillator. The proposed circuit employs three optimized Multi-output translinear second generation current conveyer (MCCII). The oscillation condition and the oscillation frequency are independently controllable. The proposed Quadrature Oscillator frequency can be tuned in the range of [198 MHz –261 MHz] by a simple variation of a DC current. PSpice simulation results are performed using CMOS 0.35 μm process of AMS.
In this paper we investigate the leader follower motion coordination of multiple nonholonomic mobile robots. A combination of the virtual vehicle and trajectory tracking approach is used to derive the formation archit...
详细信息
In this paper we investigate the leader follower motion coordination of multiple nonholonomic mobile robots. A combination of the virtual vehicle and trajectory tracking approach is used to derive the formation architecture. A virtual vehicle is steered in such away it stabilizes to a shifted reference position/heading deflned by the leader, the velocity of the virtual vehicle is then provided for further use in designing control law for the follower independent from the measurement of leader's velocity. Position tracking control is then constructed for the follower to track the virtual vehicle using the backstepping and Lyapunov direct design technique. Simulations are provided to show the effectiveness of the proposed approach.
We develop new control approach to position synchronization of lagrangian systems based on emergent consenus algorithms. The proposed control approach works to accomplish multi-robot systems synchronization. The contr...
详细信息
We develop new control approach to position synchronization of lagrangian systems based on emergent consenus algorithms. The proposed control approach works to accomplish multi-robot systems synchronization. The control strategy is to synchronize the angular position and the velocity of each robot in the group. The cooperative strategy only requires local neighbor-to-neighbor information exchange between systems and does not assume the existence of an explicit leader in the team. A combination of the lyapunov-based techniques and graph theory have been used to establish the multi-robot system asymptotic stability. The developed control combines trajectory tracking and coordination algorithms. To address the time delays problem in the cooperative network communication, the suggested synchronization control law is shown to synchronize multiple robots as well as to track given trajectory, taking into account the presence of the time delay. To this end, Krasovskii functional method has been used to deal with the delay-dependent stability problem.
Progress in low power Very Large Scale Integration (VLSI) design open up possibilities of powering wireless devises from scavenged ambient energy. An energy management system should be designed to manage the harvested...
详细信息
ISBN:
(纸本)9781457704130
Progress in low power Very Large Scale Integration (VLSI) design open up possibilities of powering wireless devises from scavenged ambient energy. An energy management system should be designed to manage the harvested energy. DC to DC converters represent the key element in energy management systems. Knowing the diversity of DC-DC converters generally designed for specific applications, basic converters are under scope in this paper. Operation principles and simulation patterns of basic DC to DC converters are first presented. Parameter simulation occurring the effect of duty cycle, inductance, capacity and switch polarisation is studied in depth. The gaol of this paper is to show main parameters effect on output voltage behaviour. Simulation results show that the main parameters in DC-DC converters design play a key role to avoid extra-lose of harvested energy.
For linear plants, IMC have been shown good robustness properties against disturbances and model mismatches. However, when uncertain processes are concerned, the original IMC structure cannot be directly used for cont...
详细信息
ISBN:
(纸本)9781457704130
For linear plants, IMC have been shown good robustness properties against disturbances and model mismatches. However, when uncertain processes are concerned, the original IMC structure cannot be directly used for control system implementation. In this paper, an internal multiple model control (IMMC) based on linear model's library is introduced. This approach supposes the definition of a set of local models developed within each cluster. Such decomposition is obtained using the fuzzy c-means (FCM) clustering algorithm. Then the gap metric concept has been designed as a criterion to analyze the relationships among candidate models to get a reduced model bank.
In this paper wavelet decomposition is combined with autoregressive models to analyze and predict climate time series such as solar radiation and photovoltaic cell temperature. The method is tested on climate paramete...
详细信息
ISBN:
(纸本)9781457704130
In this paper wavelet decomposition is combined with autoregressive models to analyze and predict climate time series such as solar radiation and photovoltaic cell temperature. The method is tested on climate parameters for analysis, and solar radiation and cell temperature for prediction. The work effectiveness is evaluated by the prediction of the electric energy produced by a 100 Wp photovoltaic panel. Finally, the performance of predictor is measured by standardized error.
暂无评论