Search results for: multi-planar fast gradient echo

Authors: Jun Peng, Johnny Ching Ming Ho

Abstract:

In order to calculate the flexural strength of normal-strength concrete (NSC) beams, the nonlinear actual concrete stress distribution within the compression zone is normally replaced by an equivalent rectangular stress block, with two coefficients of α and β to regulate the intensity and depth of the equivalent stress respectively. For NSC beams design, α and β are usually assumed constant as 0.85 and 0.80 in reinforced concrete (RC) codes. From an earlier investigation of the authors, α is not a constant but significantly affected by flexural strain gradient, and increases with the increasing of strain gradient till a maximum value. It indicates that larger concrete stress can be developed in flexure than that stipulated by design codes. As an extension and application of the authors- previous study, the modified equivalent concrete stress block is used here to produce a series of design charts showing the maximum design limits of flexural strength and ductility of singly- and doubly- NSC beams, through which both strength and ductility design limits are improved by taking into account strain gradient effect.

Keywords: Concrete beam, Ductility, Equivalent concrete stress, Normal strength, Strain gradient, Strength

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1640

Authors: Romisaa Ali

Abstract:

The Policy Gradient approach is a subset of the Deep Reinforcement Learning (DRL) combines Deep Neural Networks (DNN) with Reinforcement Learning (RL). This approach finds the optimal policy of robot movement, based on the experience it gains from interaction with its environment. Unlike previous policy gradient algorithms, which were unable to handle the two types of error variance and bias introduced by the DNN model due to over- or underestimation, this algorithm is capable of handling both types of error variance and bias. This article will discuss the state-of-the-art SOTA policy gradient technique, trust region policy optimization (TRPO), by applying this method in various environments compared to another policy gradient method, the Proximal Policy Optimization (PPO), to explain their robust optimization, using this SOTA to gather experience data during various training phases after observing the impact of hyper-parameters on neural network performance.

Keywords: Deep neural networks, deep reinforcement learning, Proximal Policy Optimization, state-of-the-art, trust region policy optimization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 111

Authors: Fituri H Belgassem, Abdulbasit Nigrat, Seddeeq Ghrari

Abstract:

In this paper, the construction of fast algorithms for the computation of Periodic Walsh Piecewise-Linear PWL transform and the Periodic Haar Piecewise-Linear PHL transform will be presented. Algorithms for the computation of the inverse transforms are also proposed. The matrix equation of the PWL and PHL transforms are introduced. Comparison of the computational requirements for the periodic piecewise-linear transforms and other orthogonal transforms shows that the periodic piecewise-linear transforms require less number of operations than some orthogonal transforms such as the Fourier, Walsh and the Discrete Cosine transforms.

Keywords: Piece wise linear transforms, Fast transforms, Fast algorithms.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1619

Authors: Ching-Fen Jiang

Abstract:

Edge detection is usually the first step in medical image processing. However, the difficulty increases when a conventional kernel-based edge detector is applied to ultrasonic images with a textural pattern and speckle noise. We designed an adaptive diffusion filter to remove speckle noise while preserving the initial edges detected by using a Sobel edge detector. We also propose a genetic algorithm for edge selection to form complete boundaries of the detected entities. We designed two fitness functions to evaluate whether a criterion with a complex edge configuration can render a better result than a simple criterion such as the strength of gradient. The edges obtained by using a complex fitness function are thicker and more fragmented than those obtained by using a simple fitness function, suggesting that a complex edge selecting scheme is not necessary for good edge detection in medical ultrasonic images; instead, a proper noise-smoothing filter is the key.

Keywords: edge detection, ultrasonic images, speckle noise

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1440

Authors: Zhifeng Kong

Abstract:

Over-parameterized neural networks have attracted a great deal of attention in recent deep learning theory research, as they challenge the classic perspective of over-fitting when the model has excessive parameters and have gained empirical success in various settings. While a number of theoretical works have been presented to demystify properties of such models, the convergence properties of such models are still far from being thoroughly understood. In this work, we study the convergence properties of training two-hidden-layer partially over-parameterized fully connected networks with the Rectified Linear Unit activation via gradient descent. To our knowledge, this is the first theoretical work to understand convergence properties of deep over-parameterized networks without the equally-wide-hidden-layer assumption and other unrealistic assumptions. We provide a probabilistic lower bound of the widths of hidden layers and proved linear convergence rate of gradient descent. We also conducted experiments on synthetic and real-world datasets to validate our theory.

Keywords: Over-parameterization, Rectified Linear Units (ReLU), convergence, gradient descent, neural networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 811

Authors: Farhad Asadi, S. Hossein Sadati

Abstract:

This paper presents a prediction performance of feedforward Multilayer Perceptron (MLP) and Echo State Networks (ESN) trained with extended Kalman filter. Feedforward neural networks and ESN are powerful neural networks which can track and predict nonlinear signals. However, their tracking performance depends on the specific signals or data sets, having the risk of instability accompanied by large error. In this study we explore this process by applying different network size and leaking rate for prediction of nonlinear or chaotic signals in MLP neural networks. Major problems of ESN training such as the problem of initialization of the network and improvement in the prediction performance are tackled. The influence of coefficient of activation function in the hidden layer and other key parameters are investigated by simulation results. Extended Kalman filter is employed in order to improve the sequential and regulation learning rate of the feedforward neural networks. This training approach has vital features in the training of the network when signals have chaotic or non-stationary sequential pattern. Minimization of the variance in each step of the computation and hence smoothing of tracking were obtained by examining the results, indicating satisfactory tracking characteristics for certain conditions. In addition, simulation results confirmed satisfactory performance of both of the two neural networks with modified parameterization in tracking of the nonlinear signals.

Keywords: Feedforward neural networks, nonlinear signal prediction, echo state neural networks approach, leaking rates, capacity of neural networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 704

Authors: Israa Al-Neami, Ali J. Al-Askery, Martin Johnston, Charalampos Tsimenidis

Abstract:

In this paper, we focus on the design of a multi-line copper wire (MLCW) communication system. First, we construct our proposed MLCW channel and verify its characteristics based on the Kolmogorov-Smirnov test. In addition, we apply Middleton class A impulsive noise (IN) to the copper channel for further investigation. Second, the MIMO G.fast system is adopted utilizing the proposed MLCW channel model and is compared to a single line G-fast system. Second, the performance of the coded system is obtained utilizing concatenated interleaved Reed-Solomon (RS) code with four-dimensional trellis-coded modulation (4D TCM), and compared to the single line G-fast system. Simulations are obtained for high quadrature amplitude modulation (QAM) constellations that are commonly used with G-fast communications, the results demonstrate that the bit error rate (BER) performance of the coded MLCW system shows an improvement compared to the single line G-fast systems.

Keywords: G.fast, Middleton Class A impulsive noise, mitigation techniques, copper channel Model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 638

Authors: Mehdi Ghayoumi

Abstract:

We have applied new accelerated algorithm for linear discriminate analysis (LDA) in face recognition with support vector machine. The new algorithm has the advantage of optimal selection of the step size. The gradient descent method and new algorithm has been implemented in software and evaluated on the Yale face database B. The eigenfaces of these approaches have been used to training a KNN. Recognition rate with new algorithm is compared with gradient.

Keywords: lda, adaptive, svm, face recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1376

Authors: Vincent King Soon Wong, Hong Seng Ng, Florinna Sim

Abstract:

Negative Bias Temperature Instability (NBTI) is one of the critical degradation mechanisms in semiconductor device reliability that causes shift in the threshold voltage (Vth). However, thorough understanding of this reliability failure mechanism is still unachievable due to a recovery characteristic known as NBTI recovery. This paper will demonstrate the severity of NBTI recovery as well as one of the effective methods used to mitigate, which is the minimization of measurement system delays. Comparison was done in between two measurement systems that have significant differences in measurement delays to show how NBTI recovery causes result deviations and how fast measurement systems can mitigate NBTI recovery. Another method to minimize NBTI recovery without the influence of measurement system known as Fast Wafer Level Reliability (FWLR) NBTI was also done to be used as reference.

Keywords: Fast vs slow BTI, Fast wafer level reliability, Negative bias temperature instability, NBTI measurement system, metal-oxide-semiconductor field-effect transistor, MOSFET, NBTI recovery, reliability.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1581

Authors: Danni Cong, Meiping Wu, Xiaofeng He, Junxiang Lian, Juliang Cao, Shaokuncai, Hao Qin

Abstract:

Gravity gradient instrument (GGI) is the core of the gravity gradiometer, so the structural error of the sensor has a great impact on the measurement results. In order not to affect the aimed measurement accuracy, limit error is required in the installation of the accelerometer. In this paper, based on the established measuring principle model, the radial installation limit error is calibrated, which is taken as an example to provide a method to calculate the other limit error of the installation under the premise of ensuring the accuracy of the measurement result. This method provides the idea for deriving the limit error of the geometry structure of the sensor, laying the foundation for the mechanical precision design and physical design.

Keywords: Gravity gradient sensor, radial installation limit error, accelerometer, uniaxial rotational modulation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 879

Authors: Iau-Teh Wang, Chin-Yu Lee

Abstract:

The impact force of a rockfall is mainly determined by its moving behavior and velocity, which are contingent on the rock shape, slope gradient, height, and surface roughness of the moving path. It is essential to precisely calculate the moving path of the rockfall in order to effectively minimize and prevent damages caused by the rockfall. By applying the Colorado Rockfall Simulation Program (CRSP) program as the analysis tool, this research studies the influence of three shapes of rock (spherical, cylindrical and discoidal) and surface roughness on the moving path of a single rockfall. As revealed in the analysis, in addition to the slope gradient, the geometry of the falling rock and joint roughness coefficient ( JRC ) of the slope are the main factors affecting the moving behavior of a rockfall. On a single flat slope, both the rock-s bounce height and moving velocity increase as the surface gradient increases, with a critical gradient value of 1:m = 1 . Bouncing behavior and faster moving velocity occur more easily when the rock geometry is more oval. A flat piece tends to cause sliding behavior and is easily influenced by the change of surface undulation. When JRC <1.4 the moving velocity decreases and the bounce height increases as JRC increases. If the gradient is fixed, when JRC is greater, the bounce height will be higher, while the moving velocity will experience a downward trend. Therefore, the best protecting point and facilities can be chosen if the moving paths of rockfalls are precisely estimated.

Keywords: rock shape, surface roughness, moving path.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1906

Authors: Nur Syarafina Binti Othman, Tsubasa Jindo, Makato Yamada, Miho Tsuyama, Hitoshi Nakano

Abstract:

A novel method to produce a fast high voltage solid states switch using Insulated Gate Bipolar Transistors (IGBTs) is presented for discharge-pumped gas lasers. The IGBTs are connected in series to achieve a high voltage rating. An avalanche transistor is used as the gate driver. The fast pulse generated by the avalanche transistor quickly charges the large input capacitance of the IGBT, resulting in a switch out of a fast high-voltage pulse. The switching characteristic of fast-high voltage solid state switch has been estimated in the multi-stage series-connected IGBT with the applied voltage of several tens of kV. Electrical circuit diagram and the mythology of fast-high voltage solid state switch as well as experimental results obtained are presented.

Keywords: High voltage, IGBT, Solid states switch.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 5860

Authors: Bib Paruhum Silalahi, Djihad Wungguli, Sugi Guritman

Abstract:

Steepest descent method is a simple gradient method for optimization. This method has a slow convergence in heading to the optimal solution, which occurs because of the zigzag form of the steps. Barzilai and Borwein modified this algorithm so that it performs well for problems with large dimensions. Barzilai and Borwein method results have sparked a lot of research on the method of steepest descent, including alternate minimization gradient method and Yuan method. Inspired by previous works, we modified the step size of the steepest descent method. We then compare the modification results against the Barzilai and Borwein method, alternate minimization gradient method and Yuan method for quadratic function cases in terms of the iterations number and the running time. The average results indicate that the steepest descent method with the new step sizes provide good results for small dimensions and able to compete with the results of Barzilai and Borwein method and the alternate minimization gradient method for large dimensions. The new step sizes have faster convergence compared to the other methods, especially for cases with large dimensions.

Keywords: Convergence, iteration, line search, running time, steepest descent, unconstrained optimization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3110

Authors: Syed Muhammad Aqil Burney, Tahseen Ahmed Jilani, C. Ardil

Abstract:

Minimization methods for training feed-forward networks with Backpropagation are compared. Feedforward network training is a special case of functional minimization, where no explicit model of the data is assumed. Therefore due to the high dimensionality of the data, linearization of the training problem through use of orthogonal basis functions is not desirable. The focus is functional minimization on any basis. A number of methods based on local gradient and Hessian matrices are discussed. Modifications of many methods of first and second order training methods are considered. Using share rates data, experimentally it is proved that Conjugate gradient and Quasi Newton?s methods outperformed the Gradient Descent methods. In case of the Levenberg-Marquardt algorithm is of special interest in financial forecasting.

Keywords: Backpropagation algorithm, conjugacy condition, line search, matrix perturbation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3596

Authors: Helle Hein, Ülo Lepik

Abstract:

A gradient learning method to regulate the trajectories of some nonlinear chaotic systems is proposed. The method is motivated by the gradient descent learning algorithms for neural networks. It is based on two systems: dynamic optimization system and system for finding sensitivities. Numerical results of several examples are presented, which convincingly illustrate the efficiency of the method.

Keywords: Chaos, Dynamical Systems, Learning, Neural Networks

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1328

Authors: Shruti Taksali

Abstract:

This paper focuses on the analysis of Nanoptenna for extreme fast communication. The Nanoptenna is basically a nano antenna designed for communication at optical range of frequencies. Since, this range of frequencies includes the visible spectrum of the light, so there is a high possibility of the data transfer at high rates and extreme fast communication (XFC). The shape chosen for the analysis is a bow tie structure due to its various characteristics of electric field enhancement.

Keywords: Nanoptenna, communication, optical range, XFC.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1292

Authors: Hazem M. El-Bakry, Qiangfu Zhao

Abstract:

Recently, neural networks have shown good results for detection of a certain pattern in a given image. In our previous papers [1-5], a fast algorithm for pattern detection using neural networks was presented. Such algorithm was designed based on cross correlation in the frequency domain between the input image and the weights of neural networks. Image conversion into symmetric shape was established so that fast neural networks can give the same results as conventional neural networks. Another configuration of symmetry was suggested in [3,4] to improve the speed up ratio. In this paper, our previous algorithm for fast neural networks is developed. The frequency domain cross correlation is modified in order to compensate for the symmetric condition which is required by the input image. Two new ideas are introduced to modify the cross correlation algorithm. Both methods accelerate the speed of the fast neural networks as there is no need for converting the input image into symmetric one as previous. Theoretical and practical results show that both approaches provide faster speed up ratio than the previous algorithm.

Keywords: Fast Pattern Detection, Neural Networks, Modified Cross Correlation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1690

Authors: Hazem M. El-Bakry

Abstract:

Principal Component Analysis (PCA) has many different important applications especially in pattern detection such as face detection / recognition. Therefore, for real time applications, the response time is required to be as small as possible. In this paper, new implementation of PCA for fast face detection is presented. Such new implementation is designed based on cross correlation in the frequency domain between the input image and eigenvectors (weights). Simulation results show that the proposed implementation of PCA is faster than conventional one.

Keywords: Fast Face Detection, PCA, Cross Correlation, Frequency Domain

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1740

Authors: Boontee Kruatrachue, Narongchai Moongfangklang, Kritawan Siriboon

Abstract:

This paper describes fast and efficient method for page segmentation of document containing nonrectangular block. The segmentation is based on edge following algorithm using small window of 16 by 32 pixels. This segmentation is very fast since only border pixels of paragraph are used without scanning the whole page. Still, the segmentation may contain error if the space between them is smaller than the window used in edge following. Consequently, this paper reduce this error by first identify the missed segmentation point using direction information in edge following then, using X-Y cut at the missed segmentation point to separate the connected columns. The advantage of the proposed method is the fast identification of missed segmentation point. This methodology is faster with fewer overheads than other algorithms that need to access much more pixel of a document.

Keywords: Contour Direction Technique, Missed SegmentationPoints, Page Segmentation, Recursive X-Y Cut Technique

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2726

Authors: L. Dahmani, M.Kouane

Abstract:

In this paper are illustrated the principal aspects connected with the numerical evaluation of thermal stress induced by high gradient temperature in the concrete beam. The reinforced concrete beam has many advantages over steel beam, such as high resistance to high temperature, high resistance to thermal shock, Better resistance to fatigue and buckling, strong resistance against, fire, explosion, etc. The main drawback of the reinforced concrete beam is its poor resistance to tensile stresses. In order to investigate the thermal induced tensile stresses, a numerical model of a transient thermal analysis is presented for the evaluation of thermo-mechanical response of concrete beam to the high temperature, taking into account the temperature dependence of the thermo physical properties of the concrete like thermal conductivity and specific heat.

Keywords: Cracking, Gradient Temperature, Reinforced Concrete beam, Thermo-mechanical analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3641

Authors: Yeon-Jea Cho, Sang-Uk Park, Won-Chul Choi, Dong-Jo Park

Abstract:

This paper proposes a smart design strategy for a sequential detector to reliably detect the primary user-s signal, especially in fast fading environments. We study the computation of the log-likelihood ratio for coping with a fast changing received signal and noise sample variances, which are considered random variables. First, we analyze the detectability of the conventional generalized log-likelihood ratio (GLLR) scheme when considering fast changing statistics of unknown parameters caused by fast fading effects. Secondly, we propose an efficient sensing algorithm for performing the sequential probability ratio test in a robust and efficient manner when the channel statistics are unknown. Finally, the proposed scheme is compared to the conventional method with simulation results with respect to the average number of samples required to reach a detection decision.

Keywords: Cognitive radio, fast fading, sequential detection, spectrum sensing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1707

Authors: Dali Zhang, Baoqun Yin, Hongsheng Xi

Abstract:

In this paper, we propose a single sample path based algorithm with state aggregation to optimize the average rewards of singularly perturbed Markov reward processes (SPMRPs) with a large scale state spaces. It is assumed that such a reward process depend on a set of parameters. Differing from the other kinds of Markov chain, SPMRPs have their own hierarchical structure. Based on this special structure, our algorithm can alleviate the load in the optimization for performance. Moreover, our method can be applied on line because of its evolution with the sample path simulated. Compared with the original algorithm applied on these problems of general MRPs, a new gradient formula for average reward performance metric in SPMRPs is brought in, which will be proved in Appendix, and then based on these gradients, the schedule of the iteration algorithm is presented, which is based on a single sample path, and eventually a special case in which parameters only dominate the disturbance matrices will be analyzed, and a precise comparison with be displayed between our algorithm with the old ones which is aim to solve these problems in general Markov reward processes. When applied in SPMRPs, our method will approach a fast pace in these cases. Furthermore, to illustrate the practical value of SPMRPs, a simple example in multiple programming in computer systems will be listed and simulated. Corresponding to some practical model, physical meanings of SPMRPs in networks of queues will be clarified.

Keywords: Singularly perturbed Markov processes, Gradient of average reward, Differential reward, State aggregation, Perturbed close network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1590

Authors: Sergey Kopysov, Nikita Nedozhogin, Leonid Tonkov

Abstract:

The article presents a parallel iterative solver for large sparse linear systems which can be used on a heterogeneous platform. Traditionally, the problem of solving linear systems do not scale well on cluster containing multiple Central Processing Units (multi-CPUs cluster) or cluster containing multiple Graphics Processing Units (multi-GPUs cluster). For example, most of the attempts to implement the classical conjugate gradient method were at best counted in the same amount of time as the problem was enlarged. The paper proposes the pipelined variant of the conjugate gradient method (PCG), a formulation that is potentially better suited for hybrid CPU/GPU computing since it requires only one synchronization point per one iteration, instead of two for standard CG (Conjugate Gradient). The standard and pipelined CG methods need the vector entries generated by current GPU and other GPUs for matrix-vector product. So the communication between GPUs becomes a major performance bottleneck on miltiGPU cluster. The article presents an approach to minimize the communications between parallel parts of algorithms. Additionally, computation and communication can be overlapped to reduce the impact of data exchange. Using pipelined version of the CG method with one synchronization point, the possibility of asynchronous calculations and communications, load balancing between the CPU and GPU for solving the large linear systems allows for scalability. The algorithm is implemented with the combined use of technologies: MPI, OpenMP and CUDA. We show that almost optimum speed up on 8-CPU/2GPU may be reached (relatively to a one GPU execution). The parallelized solver achieves a speedup of up to 5.49 times on 16 NVIDIA Tesla GPUs, as compared to one GPU.

Keywords: Conjugate Gradient, GPU, parallel programming, pipelined algorithm.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 320

Authors: Hazem M. El-Bakry, Qiangfu Zhao

Abstract:

Here, a new idea to speed up the operation of complex valued time delay neural networks is presented. The whole data are collected together in a long vector and then tested as a one input pattern. The proposed fast complex valued time delay neural networks uses cross correlation in the frequency domain between the tested data and the input weights of neural networks. It is proved mathematically that the number of computation steps required for the presented fast complex valued time delay neural networks is less than that needed by classical time delay neural networks. Simulation results using MATLAB confirm the theoretical computations.

Keywords: Fast Complex Valued Time Delay Neural Networks, Cross Correlation, Frequency Domain

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1779

Authors: Minh Vuong Pham, Frédéric Plourde, Son Doan Kim

Abstract:

A strip domain decomposition parallel algorithm for fast direct Poisson solver is presented on a 3D Cartesian staggered grid. The parallel algorithm follows the principles of sequential algorithm for fast direct Poisson solver. Both Dirichlet and Neumann boundary conditions are addressed. Several test cases are likewise addressed in order to shed light on accuracy and efficiency in the strip domain parallelization algorithm. Actually the current implementation shows a very high efficiency when dealing with a large grid mesh up to 3.6 * 10⁹ under massive parallel approach, which explicitly demonstrates that the proposed algorithm is ready for massive parallel computing.

Keywords: Strip-decomposition, parallelization, fast directpoisson solver.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2007

Authors: Yiming Nie, Tao Wu, Xiangjing An, Hangen He

Abstract:

Fast depth estimation from binocular vision is often desired for autonomous vehicles, but, most algorithms could not easily be put into practice because of the much time cost. We present an image-processing technique that can fast estimate depth image from binocular vision images. By finding out the lines which present the best matched area in the disparity space image, the depth can be estimated. When detecting these lines, an edge-emphasizing filter is used. The final depth estimation will be presented after the smooth filter. Our method is a compromise between local methods and global optimization.

Keywords: Depth estimation, image filters, stereo match.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1211

Authors: Xin-Lei Feng, Ting-Zhu Huang

Abstract:

According to conjugate gradient algorithm, a new consensus protocol algorithm of discrete-time multi-agent systems is presented, which can achieve finite-time consensus. Finally, a numerical example is given to illustrate our theoretical result.

Keywords: Consensus protocols; Graph theory; Multi-agent systems;Conjugate gradient algorithm; Finite-time.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2081

Authors: Soon-Hyun Park, Takami Matsuo

Abstract:

This paper presents an adaptive differentiator of sequential data based on the adaptive control theory. The algorithm is applied to detect moving objects by estimating a temporal gradient of sequential data at a specified pixel. We adopt two nonlinear intensity functions to reduce the influence of noises. The derivatives of the nonlinear intensity functions are estimated by an adaptive observer with σ-modification update law.

Keywords: Adaptive estimation, parameter adjustmentlaw, motion detection, temporal gradient, differential filter.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1825

Authors: Mohamed Akrout, Douglas Tweed

Abstract:

The great success of deep learning relies on efficient optimizers, which are the algorithms that decide how to adjust network weights and biases based on gradient information. One of the most effective and widely used optimizers in recent years has been the method of adaptive moments, or Adam, but the mathematical reasons behind its effectiveness are still unclear. Attempts to analyse its behaviour have remained incomplete, in part because they hinge on a conjecture which has never been proven, regarding ratios of powers of the first and second moments of the gradient. Here we show that this conjecture is in fact false, but that a modified version of it is true, and can take its place in analyses of Adam.

Keywords: Adam optimizer, Bock’s conjecture, stochastic optimization, average regret.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 297

Authors: Sanjay Baburao Kulkarni

Abstract:

Exact solution of an unsteady flow of elastico-viscous fluid through a porous media in a tube of spherical cross section under the influence of constant pressure gradient has been obtained in this paper. Initially, the flow is generated by a constant pressure gradient. After attaining the steady state, the pressure gradient is suddenly withdrawn and the resulting fluid motion in a tube of spherical cross section by taking into account of the porosity factor of the bounding surface is investigated. The problem is solved in twostages the first stage is a steady motion in tube under the influence of a constant pressure gradient, the second stage concern with an unsteady motion. The problem is solved employing separation of variables technique. The results are expressed in terms of a nondimensional porosity parameter (K) and elastico-viscosity parameter (β), which depends on the Non-Newtonian coefficient. The flow parameters are found to be identical with that of Newtonian case as elastic-viscosity parameter tends to zero and porosity tends to infinity. It is seen that the effect of elastico-viscosity parameter, porosity parameter of the bounding surface has significant effect on the velocity parameter.

Keywords: Elastico-viscous fluid, Porous media, Second order fluids, Spherical cross-section.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2053