Deep learning-based methods have made remarkable progress for stereo matching in terms of accuracy. However, two issues still hinder producing a perfect disparity map: (1) blurred boundaries and the discontinuous continuous region on estimation maps, (2) lack effective means to restore resolution precisely. In this paper, we propose utilize multiple frequency inputs an attention mechanism const...

data envelopment analysis (dea) is a mathematical technique to evaluate the performance of firms with multiple inputs and outputs. in conventional dea models, the efficiency scores of decision making units (dmus) with non-negative inputs and outputs are evaluated in a special period of time. however, in the real world there are situations wherein performance of firms must be evaluated in multip...

data envelopment analysis (dea) measures the relative efficiency of decision making units (dmus) with multiple inputs and multiple outputs. dea-based malmquist productivity index measures the productivity change over time. we propose a dynamic dea model involving network structure in each period within the framework a dea. we have previously published the network dea (ndea) and the dynamic dea ...

We propose an approach to efficiently generate and multiplex optical orbital angular momentum (OAM) modes in a fiber with a ring refractive index profile by using multiple coherent inputs from a Gaussian mode. By controlling the phase relationship of the multiple inputs, one can selectively generate OAM modes of different states l. By controlling both the amplitude and phase of the multiple inp...

This paper presents the capacity performance of multiple antennas for wireless communication systems. Multiple antennas structures can be classified into single-input multiple-outputs (SIMO), multiple-inputs single output (MISO), and multiple-inputs multiple-outputs (MIMO) systems. Assuming that the channel is unknown at receiver, capacity expressions are provided for each structure. Our result...

In this paper, a design of a full-order observer for linear time-invariant (LTI) multivariable systems with multiple time-delays and unknown inputs (UI) is proposed. The main idea is to reduce the problem of the unknown input observer (UIO) for systems with multiple time-delays to that of a standard one. To that purpose, the orthogonal collocation method is used to transform the infinite dimens...

In this paper we present neuro-evolution of neural network controllers for mobile agents in a simulated environment. The controller is obtained through evolution of hypercube encoded weights of recurrent neural networks (HyperNEAT). The simulated agent’s goal is to find a target in a shortest time interval. The generated neural network processes three different inputs – surface quality, obstacl...