Unmanned aerial vehicles (UAVs) are being used for monitoring natural disasters. To promptly assess the severity of the disaster, it is advantageous to analyze the disaster scenes with the on-board computer in real ti...
详细信息
ISBN:
(数字)9798350360325
ISBN:
(纸本)9798350360332
Unmanned aerial vehicles (UAVs) are being used for monitoring natural disasters. To promptly assess the severity of the disaster, it is advantageous to analyze the disaster scenes with the on-board computer in real time. Various AI segmentation models with high accuracy are developed mainly for offline processing. They require significant memory capacity and computational power. However, on-device AI has the challenge of compressing high-precision models due to the limited memory size and the small computation power. In this research, we develop a lightweight disaster semantic segmentation model for UAV on-device intelligence. From a simple FANet as our baseline, we apply various optimization, such as compact backbone, lightweight attention block, quantization, knowledge distillation, and post processing. With our optimized model, we can reduce 84.2% of the inference time while achieving 0.5% increase in accuracy compared to the baseline model.
This paper presents a recursive clustering scheme that uses a genetic algorithm-based search in a dichotomous partition space. The proposed algorithm makes no assumption on the number of clusters present in the datase...
详细信息
This paper presents a recursive clustering scheme that uses a genetic algorithm-based search in a dichotomous partition space. The proposed algorithm makes no assumption on the number of clusters present in the dataset; instead it recursively uncovers subsets in the data until all isolated and separated regions have been classified as clusters. A test of spatial randomness serves as a termination criteria for the recursive process. Within each recursive step, a genetic algorithm searches the partition space for an optimal dichotomy of the dataset. A simple binary representation is used for the genetic algorithm, along with classical selection, crossover and mutation operators. Results of clustering on test cases, ranging from simple datasets in 2-D to large multidimensional datasets compare favorably with state of the art approaches in genetic algorithm-driven clustering.
A complete fault tolerant control solution calls for a nonlinear adaptive controller with universal approximation capability and guaranteed stability. To fulfill this requirement we propose the use of neural networks ...
详细信息
A complete fault tolerant control solution calls for a nonlinear adaptive controller with universal approximation capability and guaranteed stability. To fulfill this requirement we propose the use of neural networks trained online under a globalized dual heuristic programming architecture supervised by a decision logic capable of identifying controller malfunctions in early stages and providing new avenues with greater probability of convergence using information from a dynamic model bank. The classification and distinction of controller malfunctions and of the faults in the system is achieved through three independent quality indexes. Proof-of-the-concept simulations of nonlinear plants demonstrate the approach legitimacy
Power system stabilizers (PSSs) are used to generate supplementary control signals to excitation systems in order to damp out local and inter-area oscillations. In this paper, a modified particle swarm optimization (P...
详细信息
Power system stabilizers (PSSs) are used to generate supplementary control signals to excitation systems in order to damp out local and inter-area oscillations. In this paper, a modified particle swarm optimization (PSO) algorithm with a small population is presented for the design of optimal PSSs. The small population based PSO (SPPSO) is used to determine the optimal parameters of several PSSs simultaneously in a multi-machine power system. In order to maintain a dynamic search process, the idea of particle regeneration in the population is also proposed. Optimal PSS parameters are determined for the power system subjected to small and large disturbances. The effectiveness of the PSSs parameters determined by the SPPSO algorithm is observed in damping out the power system oscillations fast after a disturbance. The advantage of the proposed approach is its convergence in fewer evaluations and lesser computations are required per evaluation. Results obtained with the SPPSO optimized PSSs parameters are compared against published PSS parameters for the Kundur's two area power system
This paper addresses the challenges of the fusion of two random vectors with imprecisely known stochastic dependency. This problem mainly occurs in decentralized estimation, e.g. of a distributed phenomenon, where the...
详细信息
This paper addresses the challenges of the fusion of two random vectors with imprecisely known stochastic dependency. This problem mainly occurs in decentralized estimation, e.g. of a distributed phenomenon, where the stochastic dependencies between the individual states are not stored. To cope with such problems we propose to exploit parameterized joint densities with both Gaussian marginals and Gaussian mixture marginals. Under structural assumptions these parameterized joint densities contain all information about the stochastic dependencies between their marginal densities in terms of a generalized correlation parameter vector ξ̱. The parameterized joint densities are applied to the prediction step and the measurement step under imprecisely known correlation leading to a whole family of possible estimation results. The resulting density functions are characterized by the generalized correlation parameter vector ξ̱. Once this structure and the bounds of these parameters are known, it is possible to find bounding densities containing all possible density functions, i.e., conservative estimation results.
The physics-based phase variable model of permanent magnet synchronous machines is developed for the simulation study of machine control. The parameters of the physics-based phase variable model, inductances and flux ...
详细信息
The physics-based phase variable model of permanent magnet synchronous machines is developed for the simulation study of machine control. The parameters of the physics-based phase variable model, inductances and flux linkages are calculated from the solutions of nonlinear FE computation covering a complete AC cycle to consider the geometry details, the rotor position, the armature currents, and the magnetization nonlinearity. In the previously developed model, the impact of the armature currents on inductances is ignored considering the fact that field of PM machines is dominated by permanent magnets. In the improved model, presented in this paper, the variation of inductances with the armature currents is evaluated and added to meet the demand from those control applications which require highly accurate inductances. In this paper, three issues associated with the development of the improved model are presented. First is the method used to describe the inductances variation with the armature currents. L(thetas, i d , i q ) is used instead of L(thetas, i a , i b , i c ) ; the reasons are thoroughly explained. Second is the verification of the improved model, given by the comparison of the improved model with the FE model. Third is the comparison between the previous model and the improved model, clarifying the validity of each model from the application point of view.
Contrast enhancement has an important role in image processing applications. Conventional contrast enhancement techniques either fail to produce satisfactory results for a broad variety of low-contrast images, or cann...
详细信息
Contrast enhancement has an important role in image processing applications. Conventional contrast enhancement techniques either fail to produce satisfactory results for a broad variety of low-contrast images, or cannot be automatically applied to different images, because their parameters must be specified manually to produce a satisfactory result for a given image. This paper describes a new automatic method for contrast enhancement. The basic procedure is to first group the histogram components of a low-contrast image into the proper number of bins according to a selected criterion, then redistribute these bins uniformly over the grayscale, and finally ungroup the previously grouped gray-levels. Accordingly, this new technique is named gray-level grouping (GLG). GLG not only produces results superior to conventional contrast enhancement techniques, but is also fully automatic in most circumstances, and is applicable to a broad variety of images
A compact UWB planar antenna fed with a microstrip-line is proposed. The new design is composed of a square patch with a small size of 26 mm × 20 mm. with three rectangular slots and fed by 50 Ω microstrip trans...
详细信息
A compact UWB planar antenna fed with a microstrip-line is proposed. The new design is composed of a square patch with a small size of 26 mm × 20 mm. with three rectangular slots and fed by 50 Ω microstrip transmission line and a reduced ground-plane which have a T-shaped slot. It is intended to be used in Microwave Imaging applications that cover the ultra-wideband (UWB) frequency band. A wider bandwidth of around 3.98 - 17.26GHZ with stable radiation pattern is achieved. The proposed antenna has excellent characteristics, low profile and cost-effective compared to existing UWB antennas. The UWB antenna is designed and analyzed using CST Microwave Studio and HFSS software in transient mode to verify antenna parameters improvements.
We present an integrated wideband directional coupler for millimeter-wave applications implemented in low-cost silicon technologies. It is constructed using broad-side coupled coplanar waveguides (CPW), taking advanta...
详细信息
We present an integrated wideband directional coupler for millimeter-wave applications implemented in low-cost silicon technologies. It is constructed using broad-side coupled coplanar waveguides (CPW), taking advantage of available multiple metal layers in silicon technologies. A prototype coupler was designed and fabricated using a commercial 0.18mu digital CMOS technology with low-resistivity epi substrate. It achieves a 10-40 GHz frequency range (3-dB bandwidth) with 7 dB to 10 dB coupling and more than 10 dB directivity. Measurement results match well with electromagnetic simulation
In this paper a new technique for the design of combinational circuits for low power is introduced. According to this technique, we bypass blocks of logic when their function is not required, using low delay and area ...
详细信息
In this paper a new technique for the design of combinational circuits for low power is introduced. According to this technique, we bypass blocks of logic when their function is not required, using low delay and area overhead components (transmission gates). The internal state of these blocks is kept unchanged, so the switching activity of the circuit is minimized, resulting to low power consumption. The proposed idea is applied in the design of a carry-save array multiplier with significant power saving.
暂无评论