This paper introduces a decoupled dual-element array antenna designed to address the challenges of mutual coupling between elements. To tackle this issue, a neutralization line is strategically incorporated to suppres...
详细信息
In this article, a novel method is proposed to facilitate the design of compact, low-profile, pattern reconfigurable antennas with fixed or switchable circular polarization (CP) for Internet of Vehicles (IoV) applicat...
详细信息
Pruning refers to the elimination of trivial weights from neural networks. The sub-networks within an overparameterized model produced after pruning are often called Lottery tickets. This research aims to generate win...
详细信息
Deep learning models for computer vision applications specifically and for machine learning generally are now the state of the art. The growth of size and complexity of neural networks has made them more and more reli...
详细信息
Deep learning models for computer vision applications specifically and for machine learning generally are now the state of the art. The growth of size and complexity of neural networks has made them more and more reliable, yet in greater need of computational power and memory as is evident from the heavy reliance on graphical processing units and cloud computing for training them. As the complexity of deep neural networks increases, the need for fast processing neural networks in real-time embedded applications at the edge also increases and accelerating them using reconfigurable hardware suggests a solution. In this work, a convolutional neural network based on the inception net architecture is first optimized in software and then accelerated by taking advantage of field programmable gate array (FPGA) parallelism. Genetic algorithm augmented training is proposed and used on the neural network to produce an optimum model from the first training run without re-training iterations. Quantization of the network parameters is performed according to the weights of the network. The resulting neural network is then transformed into hardware by writing the register transfer level (RTL) code for FPGAs with exploitation of layer parallelism and a simple trial-and-error allocation of resources with the help of the roofline model. The approach is simple and easy to use as compared to many complex existing methods in literature and relies on trial and error to customize the FPGA design to the model needed to work on any computer vision or multimedia application deep learning model. Simulation and synthesis are performed. The results prove that the genetic algorithm reduces the number of back-propagation epochs in software and brings the network closer to the global optimum in terms of performance. Quantization to 16 bits also shows a reduction in network size by almost half with no performance drop. The synthesis of our design also shows that the Inception-based classifier is cap
A Negative Group Delay (NGD) prototype filter design based on the reciprocal transfer function of a low-pass Butterworth filter of a given order, is presented. The out-of-band gain of the prototype transfer function i...
详细信息
Solar power is mostly influenced by solar irradiation,weather conditions,solar array mismatches and partial shading ***,before installing solar arrays,it is necessary to simulate and determine the possible power *** p...
详细信息
Solar power is mostly influenced by solar irradiation,weather conditions,solar array mismatches and partial shading ***,before installing solar arrays,it is necessary to simulate and determine the possible power *** power point tracking is needed in order to make sure that,at any time,the maximum power will be extracted from the photovoltaic ***,maximum power point tracking is not a suitable solution for mismatches and partial shading *** overcome the drawbacks of maximum power point tracking due to mismatches and shadows,distributed maximum power point tracking is util-ized in this *** solar farm can be distributed in different ways,including one DC-DC converter per group of modules or per *** this paper,distributed maximum power point tracking per module is implemented,which has the highest *** technology is applied to electric vehicles(EVs)that can be charged with a Level 3 charging station in<1 ***,the problem is that charging an EV in<1 hour puts a lot of stress on the power grid,and there is not always enough peak power reserve in the existing power grid to charge EVs at that ***,a Level 3(fast DC)EV charging station using a solar farm by implementing distributed maximum power point tracking is utilized to address this ***,the simulation result is reported using MATLAB®,LTSPICE and the System Advisor *** results show that the proposed 1-MW solar system will provide 5 MWh of power each day,which is enough to fully charge~120 EVs each ***,the use of the proposed photovoltaic system benefits the environment by removing a huge amount of greenhouse gases and hazardous *** example,instead of supplying EVs with power from coal-fired power plants,1989 pounds of CO_(2) will be eliminated from the air per hour.
The work presented in this paper has great significance in improving electromagnetic models based on the strong coupling between the magnetic and electric fields transient equations while considering a realistic rando...
详细信息
We construct a predictor-feedback cooperative adaptive cruise control (CACC) design with integral action, which achieves simultaneous compensation of long, actuation and communication delays, for platoons of heterogen...
详细信息
We construct a predictor-feedback cooperative adaptive cruise control (CACC) design with integral action, which achieves simultaneous compensation of long, actuation and communication delays, for platoons of heterogeneous vehicles whose dynamics are described by a third-order linear system with input delay. The key ingredients in our design are an underlying predictor-feedback law that achieves actuation delay compensation and an integral term of the difference between the delayed (by an amount equal to the respective communication delay) and current speed of the preceding vehicle. The latter, essentially, creates a virtual spacing variable, which can be regulated utilizing only delayed position and speed measurements from the preceding vehicle. We establish individual vehicle stability, string stability, and regulation for vehicular platoons, under the control design developed. The proofs rely on combining an input-output approach (in the frequency domain), with derivation of explicit solutions for the closed-loop systems, and they are enabled by the actuation and communication delays-compensating property of the design. We demonstrate numerically the control and model parameters' conditions of string stability, while we also present simulation results, in realistic scenarios, including a scenario in which the leading vehicle's trajectory is obtained from NGSIM data. All case studies confirm the effectiveness of the design developed. IEEE
This study introduces an adaptive integral sliding mode disturbance observer (AISMDOB)-based robust bidirectional platoon control method, aiming to ensure mesh stability in vehicular systems. Most existing platoon con...
详细信息
This study introduces an adaptive integral sliding mode disturbance observer (AISMDOB)-based robust bidirectional platoon control method, aiming to ensure mesh stability in vehicular systems. Most existing platoon control studies only focus on error propagation stability in either the longitudinal or lateral direction, neglecting the uncertainties in kinematics and dynamics of vehicular systems. The study proposes new coupled spacing error dynamics derived from vehicle kinematics and extended look-ahead-based coupled spacing errors to ensure both the longitudinal and lateral error propagation stability (that is, mesh stability) and are subsequently utilized to develop the novel AISMDOB, which improves the existing integral sliding mode disturbance observers (ISMDOBs) by incorporating adaptive estimation of unknown disturbance bounds while preserving their advantages. The AISMDOB-based platoon control method is then proposed using both robust kinematic and dynamic controllers to effectively compensate for the kinematic disturbances and dynamic model uncertainties, thereby reducing chattering phenomenon and ensuring the asymptotic convergence of spacing and velocity errors. Additionally, the proposed method can prevent cutting-corner behaviors during cornering maneuvers by utilizing the coupled spacing error dynamics. Simulation and experimental results verify the effectiveness of the proposed method through comparison with ISMDOB-based, sliding mode control (SMC)-based, and previous extended look-ahead-based methods. IEEE
暂无评论