Search results for: conjugate gradient

Authors: A. Mirzaaghazadeh, H. Motameni, M. Karshenas, H. Nematzadeh

Abstract:

Learning the gradient of neuron's activity function like the weight of links causes a new specification which is flexibility. In flexible neural networks because of supervising and controlling the operation of neurons, all the burden of the learning is not dedicated to the weight of links, therefore in each period of learning of each neuron, in fact the gradient of their activity function, cooperate in order to achieve the goal of learning thus the number of learning will be decreased considerably. Furthermore, learning neurons parameters immunes them against changing in their inputs and factors which cause such changing. Likewise initial selecting of weights, type of activity function, selecting the initial gradient of activity function and selecting a fixed amount which is multiplied by gradient of error to calculate the weight changes and gradient of activity function, has a direct affect in convergence of network for learning.

Keywords: Back propagation, Flexible, Gradient, Learning, Neural network, Pattern recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1496

Authors: Meng Wu

Abstract:

Motion planning is a common task required to be fulfilled by robots. A strategy combining Ant Colony Optimization (ACO) and gravity gradient inversion algorithm is proposed for motion planning of mobile robots. In this paper, in order to realize optimal motion planning strategy, the cost function in ACO is designed based on gravity gradient inversion algorithm. The obstacles around mobile robot can cause gravity gradient anomalies; the gradiometer is installed on the mobile robot to detect the gravity gradient anomalies. After obtaining the anomalies, gravity gradient inversion algorithm is employed to calculate relative distance and orientation between mobile robot and obstacles. The relative distance and orientation deduced from gravity gradient inversion algorithm is employed as cost function in ACO algorithm to realize motion planning. The proposed strategy is validated by the simulation and experiment results.

Keywords: Motion planning, gravity gradient inversion algorithm, ant colony optimization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1154

Authors: Zhibin Yu, Artur J. Jaworski, Abdulrahman S. Abduljalil

Abstract:

A stack with a small critical temperature gradient is desirable for a standing wave thermoacoustic engine to obtain a low onset temperature difference (the minimum temperature difference to start engine-s self-oscillation). The viscous and heat relaxation loss in the stack determines the critical temperature gradient. In this work, a dimensionless critical temperature gradient factor is obtained based on the linear thermoacoustic theory. It is indicated that the impedance determines the proportion between the viscous loss, heat relaxation losses and the power production from the heat energy. It reveals the effects of the channel dimensions, geometrical configuration and the local acoustic impedance on the critical temperature gradient in stacks. The numerical analysis shows that there exists a possible optimum combination of these parameters which leads to the lowest critical temperature gradient. Furthermore, several different geometries have been tested and compared numerically.

Keywords: Critical temperature gradient, heat relaxation, stack, viscous effect.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1806

Authors: Xiaobai Li, Li Li, Yujin Hu, Weiming Deng, Zhe Ding

Abstract:

A size-dependent Euler–Bernoulli beam model, which accounts for nonlocal stress field, strain gradient field and higher order inertia force field, is derived based on the nonlocal strain gradient theory considering velocity gradient effect. The governing equations and boundary conditions are derived both in dimensional and dimensionless form by employed the Hamilton principle. The analytical solutions based on different continuum theories are compared. The effect of higher order inertia terms is extremely significant in high frequency range. It is found that there exists an asymptotic frequency for the proposed beam model, while for the nonlocal strain gradient theory the solutions diverge. The effect of strain gradient field in thickness direction is significant in low frequencies domain and it cannot be neglected when the material strain length scale parameter is considerable with beam thickness. The influence of each of three size effect parameters on the natural frequencies are investigated. The natural frequencies increase with the increasing material strain gradient length scale parameter or decreasing velocity gradient length scale parameter and nonlocal parameter.

Keywords: Euler-Bernoulli Beams, free vibration, higher order inertia, nonlocal strain gradient theory, velocity gradient.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1005

Authors: Habibis Saleh, Ishak Hashim

Abstract:

Conjugate natural convection in a differentially heated square enclosure containing a polygon shaped object is studied numerically in this article. The effect of various polygon types on the fluid flow and thermal performance of the enclosure is addressed for different thermal conductivities. The governing equations are modeled and solved numerically using the built-in finite element method of COMSOL software. It is found that the heat transfer rate remains stable by varying the polygon types.

Keywords: Natural convection, Polygon object, COMSOL

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1889

Authors: Yue-Tzu Yang, Shu-Ching Liao

Abstract:

This study presents the numerical simulation of three-dimensional incompressible steady and laminar fluid flow and conjugate heat transfer of a trapezoidal microchannel heat sink using water as a cooling fluid in a silicon substrate. Navier-Stokes equations with conjugate energy equation are discretized by finite-volume method. We perform numerical computations for a range of 50 ≦ Re ≦ 600, 0.05W ≦ P ≦ 0.8W, 20W/cm² ≦q"≦ 40W/cm². The present study demonstrates the numerical optimization of a trapezoidal microchannel heat sink design using the response surface methodology (RSM) and the genetic algorithm method (GA). The results show that the average Nusselt number increases with an increase in the Reynolds number or pumping power, and the thermal resistance decreases as the pumping power increases. The thermal resistance of a trapezoidal microchannel is minimized for a constant heat flux and constant pumping power.

Keywords: Microchannel heat sinks, Conjugate heat transfer, Optimization, Genetic algorithm method.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2159

Authors: Muzna Tariq, Ihtzaz Qamar

Abstract:

In most engineering cases, the working temperatures inside a combustion chamber are high enough that they lie beyond the operational range of thermocouples. Furthermore, design and manufacturing limitations restrict the use of internal thermocouples in many applications. Heat transfer inside a combustion chamber is caused due to interaction of the post-combustion hot fluid with the chamber wall. Heat transfer that involves an interaction between the fluid and solid is categorized as Conjugate Heat Transfer (CHT). Therefore, to satisfy the needs of CHT, CHT Analysis is performed by using ANSYS CFD tool to estimate theoretically precise thermocouple positions at the combustion chamber wall where excessive temperatures (beyond thermocouple range) can be avoided. In accordance with these Computational Fluid Dynamics (CFD) results, a combustion chamber is designed, and a prototype is manufactured with multiple thermocouple ports positioned at the specified distances so that the temperature of hot gases can be measured on the chamber wall where the temperatures do not exceed the thermocouple working range.

Keywords: Computational Fluid Dynamics, CFD, conduction, conjugate heat transfer, CHT, convection, fluid flow, thermocouples.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 691

Authors: Jatinderdeep Kaur

Abstract:

In this paper, the results of Kano from one dimensional cosine and sine series are extended to two dimensional cosine and sine series. To extend these results, some classes of coefficient sequences such as class of semi convexity and class R are extended from one dimension to two dimensions. Further, the function f(x, y) is two dimensional Fourier Cosine and Sine series or equivalently it represents an integrable function or not, has been studied. Moreover, some results are obtained which are generalization of Moricz’s results.

Keywords: Conjugate Dirichlet kernel, conjugate Fejer kernel, Fourier series, Semi-convexity.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2147

Authors: Wei-Jong Yang, Yu-Siang Su, Pau-Choo Chung, Jar-Ferr Yang

Abstract:

Moving object detection (MOD) is an important issue in advanced driver assistance systems (ADAS). There are two important moving objects, pedestrians and scooters in ADAS. In real-world systems, there exist two important challenges for MOD, including the computational complexity and the detection accuracy. The histogram of oriented gradient (HOG) features can easily detect the edge of object without invariance to changes in illumination and shadowing. However, to reduce the execution time for real-time systems, the image size should be down sampled which would lead the outlier influence to increase. For this reason, we propose the histogram of uniformly-oriented gradient (HUG) features to get better accurate description of the contour of human body. In the testing phase, the support vector machine (SVM) with linear kernel function is involved. Experimental results show the correctness and effectiveness of the proposed method. With SVM classifiers, the real testing results show the proposed HUG features achieve better than classification performance than the HOG ones.

Keywords: Moving object detection, histogram of oriented gradient histogram of oriented gradient, histogram of uniformly-oriented gradient, linear support vector machine.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1234

Authors: Safwan Kanan, Jonathan Dewsbury, Gregory Lane-Serff

Abstract:

A salinity gradient solar pond is a free energy source system for collecting, convertingand storing solar energy as heat. In thispaper, the principles of solar pond are explained. A mathematical model is developed to describe and simulate heat and mass transferbehaviour of salinity gradient solar pond. MATLAB codes are programmed to solve the one dimensional finite difference method for heat and mass transfer equations. Temperature profiles and concentration distributions are calculated. The numerical results are validated with experimental data and the results arefound to be in good agreement.

Keywords: Finite Difference method, Salt-gradient solar-pond, Solar energy, Transient heat and mass transfer.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4980

Authors: Chandrakant R Kini, Satish Shenoy B, Yagnesh Sharma N.

Abstract:

In a bid to improve turbine entry temperature for maximizing the thermal efficiency of the HP stage gas turbine blade, an attempt is made in this paper to compare the performance of helicoidal ducted blade cooling with turbulator of different geometric proportion. It is found from analysis that there is significant improvement in cooling characteristics for turbine blade with turbulator geometry having larger e/D ratio. Also it is found from analysis, performance is vastly improved for greater thickness of turbulator geometry.

Keywords: Conjugate heat transfer, turbine blade cooling, helicoidal cooling duct, turbulator.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2728

Authors: Essam Al Daoud

Abstract:

Gradient boosting methods have been proven to be a very important strategy. Many successful machine learning solutions were developed using the XGBoost and its derivatives. The aim of this study is to investigate and compare the efficiency of three gradient methods. Home credit dataset is used in this work which contains 219 features and 356251 records. However, new features are generated and several techniques are used to rank and select the best features. The implementation indicates that the LightGBM is faster and more accurate than CatBoost and XGBoost using variant number of features and records.

Keywords: Gradient boosting, XGBoost, LightGBM, CatBoost, home credit.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 9470

Authors: S. Ansari Sadrabadi, G. H. Rahimi

Abstract:

In this paper, thick walled Cylindrical tanks or tubes made of functionally graded material under internal pressure and temperature gradient are studied. Material parameters have been considered as power functions. They play important role in the elastoplastic behavior of these materials. To clarify their role, different materials with different parameters have been used under temperature gradient. Finally, their effect and loading effect have been determined in first yield point. Also, the important role of temperature gradient was also shown. At the end the study has been results obtained from changes in the elastic modulus and yield stress. Also special attention is also given to the effects of this internal pressure and temperature gradient in the creation of tensile and compressive stresses.

Keywords: FGM, Cylindrical pressure tubes, Small deformation theory, Yield onset, Thermal loading.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1945

Authors: Young-Seok Choi

Abstract:

We propose two affine projection algorithms (APA) with variable regularization parameter. The proposed algorithms dynamically update the regularization parameter that is fixed in the conventional regularized APA (R-APA) using a gradient descent based approach. By introducing the normalized gradient, the proposed algorithms give birth to an efficient and a robust update scheme for the regularization parameter. Through experiments we demonstrate that the proposed algorithms outperform conventional R-APA in terms of the convergence rate and the misadjustment error.

Keywords: Affine projection, regularization, gradient descent, system identification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1613

Authors: N. W. K. Jayatissa, R. Attalage, Prabath Hewageegana, P. A. A. Perera, M. A. Punyasena

Abstract:

Per capita energy usage in any country is exponentially increasing with their development. As a result, the country’s dependence on the fossil fuels for energy generation is also increasing tremendously creating economic and environmental concerns. Tropical countries receive considerable amount of solar radiation throughout the year, use of solar energy with different energy storage and conversion methodologies is a viable solution to minimize the ever increasing demand for the depleting fossil fuels. Salinity gradient solar pond is one such solar energy application. This paper reports the characteristics and performance of a thermally insulated, experimental salinity-gradient solar pond, built at the premises of the University of Kelaniya, Sri Lanka. Particular stress is given to the behavior of the evolution of the three layer structure exist at the stable state of a salinity gradient solar pond over a long period of time, under different environmental conditions. The operational procedures required to maintain the long term thermal stability are also reported in this article.

Keywords: Salt-gradient, solar pond, solar radiation, renewable energy.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1606

Authors: Yanwen Li, Shuguo Xie

Abstract:

In electromagnetic imaging, because of the diffraction limited system, the pixel values could change slowly near the edge of the image targets and they also change with the location in the same target. Using traditional digital image segmentation methods to segment electromagnetic gradient images could result in lots of errors because of this change in pixel values. To address this issue, this paper proposes a novel image segmentation and extraction algorithm based on Mean-Shift and dictionary learning. Firstly, the preliminary segmentation results from adaptive bandwidth Mean-Shift algorithm are expanded, merged and extracted. Then the overlap rate of the extracted image block is detected before determining a segmentation region with a single complete target. Last, the gradient edge of the extracted targets is recovered and reconstructed by using a dictionary-learning algorithm, while the final segmentation results are obtained which are very close to the gradient target in the original image. Both the experimental results and the simulated results show that the segmentation results are very accurate. The Dice coefficients are improved by 70% to 80% compared with the Mean-Shift only method.

Keywords: Gradient image, segmentation and extract, mean-shift algorithm, dictionary learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 970

Authors: Y. Li, Q. S. Zhang, H. Z. Huang, B. Y. Wu

Abstract:

The mechanism behind the electromigration and thermomigration failure in flip-chip solder joints with Cu-pillar bumps was investigated in this paper through using finite element method. Hot spot and the current crowding occurrs in the upper corner of copper column instead of solders of the common solder ball. The simulation results show that the change in thermal gradient is noticeable, which might greatly affect the reliability of solder joints with Cu-pillar bumps under current stressing. When the average applied current density is increased from 1×104 A/cm2 to 3×104 A/cm2 in solders, the thermal gradient would increase from 74 K/cm to 901 K/cm at an ambient temperature of 25°C. The force from thermal gradient of 901 K/cm can nearly induce thermomigration by itself. With the increase in applied current, the thermal gradient is growing. It is proposed that thermomigration likely causes a serious reliability issue for Cu column based interconnects.

Keywords: Simulation, Cu-pillar bumps, Electromigration, Thermomigration.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1867

Authors: Morteza Mirhosseini, Amir B. Khoshnevis

Abstract:

The boundary layer separation and new active flow control of a NACA 0025 airfoil were studied experimentally. This new flow control is sometimes known as a co-flow jet (cfj) airfoil. This paper presents the fluctuating velocity in a wall jet over the co-flow jet airfoil subjected to an adverse pressure gradient and a curved surface. In these results, the fluctuating velocity at the inner part increasing by increased the angle of attack up to 12^o and this has due to the jet energized, while the angle of attack 20^o has different. The airfoil cord based Reynolds number has 10⁵.

Keywords: Adverse pressure gradient, fluctuating velocity, wall jet, co-flow jet airfoil.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1469

Authors: H. J. Kim, G. C. Park, K. C. Kim, J. H. Shin

Abstract:

Cavities are frequently found beneath conduits on pile foundations in old embankments. Cavity reduces seepage length significantly and consequently causes piping failure of embankments. Case studies of embankment failures indicate that the relative settlement between ground and pile supported-concrete conduit was the main reason of the cavity. In this paper, an attempt to simulate the cavity-induced piping failure mechanism was made using finite element numerical method. Piping potential is examined by carrying out parametric study for influencing factors such as cavity length, water level, and flow conditions. The concentration of hydraulic gradient adjacent to cavity was found. It is found that the hydraulic gradient close to the cavity exceeds considerably the critical hydraulic gradient causing piping. Piping failure potential due to the existence of cavity is evaluated and contour map for the potential risk of an embankment for piping failure is proposed.

Keywords: Cavity, Embankment, Hydraulic gradient, Piping.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1490

Authors: Saman Ghaffarian, Ilgın Gökasar

Abstract:

This paper presents a new automatic vehicle detection method from very high resolution aerial images to measure traffic density. The proposed method starts by extracting road regions from image using road vector data. Then, the road image is divided into equal sections considering resolution of the images. Gradient vectors of the road image are computed from edge map of the corresponding image. Gradient vectors on the each boundary of the sections are divided where the gradient vectors significantly change their directions. Finally, number of vehicles in each section is carried out by calculating the standard deviation of the gradient vectors in each group and accepting the group as vehicle that has standard deviation above predefined threshold value. The proposed method was tested in four very high resolution aerial images acquired from Istanbul, Turkey which illustrate roads and vehicles with diverse characteristics. The results show the reliability of the proposed method in detecting vehicles by producing 86% overall F1 accuracy value.

Keywords: Aerial images, intelligent transportation systems, traffic density measurement, vehicle detection.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2936

Authors: Se-Jin Ko, Deok-Min Kim, Seok-Yoon Kim

Abstract:

The trend of growing density on chips has increases not only the temperature in chips but also the gradient of the temperature depending on locations. In this paper, we propose the balanced skew tree generation technique for minimizing the clock skew that is affected by the temperature gradients on chips. We calculate the interconnect delay using Elmore delay equation, and find out the optimal balanced clock tree by modifying the clock trees generated through the Deferred Merge Embedding(DME) algorithm. The experimental results show that the distance variance of clock insertion points with and without considering the temperature gradient can be lowered below 54% and we confirm that the skew is remarkably decreased after applying the proposed technique.

Keywords: clock, clock-skew, temperature, thermal.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1713

Authors: Adam Rabcewicz

Abstract:

Variational methods for optical flow estimation are known for their excellent performance. The method proposed by Brox et al. [5] exemplifies the strength of that framework. It combines several concepts into single energy functional that is then minimized according to clear numerical procedure. In this paper we propose a modification of that algorithm starting from the spatiotemporal gradient constancy assumption. The numerical scheme allows to establish the connection between our model and the CLG(H) method introduced in [18]. Experimental evaluation carried out on synthetic sequences shows the significant superiority of the spatial variant of the proposed method. The comparison between methods for the realworld sequence is also enclosed.

Keywords: optical flow, variational methods, gradient constancy assumption.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2183

Authors: H. R. Kazemi Nia, A. Yeganeh Fallah

Abstract:

Without uncertainty by applying external loads on beams, bending is created. The created bending in I-beams, puts one of the flanges in tension and the other one in compression. With increasing of bending, compression flange buckled and beam in out of its plane direction twisted, this twisting well-known as Lateral Torsional Buckling. Providing bending moment varieties along the beam, the critical moment is greater than the case its under pure bending. In other words, the value of bending gradient coefficient is always greater than unite. In this article by the use of " ANSYS 10.0" software near 80 3-D finite element models developed for the propose of analyzing beams` lateral torsional buckling and surveying influence of slenderness on beams' bending gradient coefficient. Results show that, presented Cb coefficient via AISC is not correct for some of beams and value of this coefficient is smaller than what proposed by AISC. Therefore instead of using a constant Cb for each case of loading , a function with two criterion for calculation of Cb coefficient for some cases is proposed.

Keywords: Beams critical moment, Bending Gradient Coefficient, finite element, Lateral Torsional Buckling

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4531

Authors: Iman A. Saad, Loay E. George

Abstract:

Iris pattern is an important biological feature of human body; it becomes very hot topic in both research and practical applications. In this paper, an algorithm is proposed for iris recognition and a simple, efficient and fast method is introduced to extract a set of discriminatory features using first order gradient operator applied on grayscale images. The gradient based features are robust, up to certain extents, against the variations may occur in contrast or brightness of iris image samples; the variations are mostly occur due lightening differences and camera changes. At first, the iris region is located, after that it is remapped to a rectangular area of size 360x60 pixels. Also, a new method is proposed for detecting eyelash and eyelid points; it depends on making image statistical analysis, to mark the eyelash and eyelid as a noise points. In order to cover the features localization (variation), the rectangular iris image is partitioned into N overlapped sub-images (blocks); then from each block a set of different average directional gradient densities values is calculated to be used as texture features vector. The applied gradient operators are taken along the horizontal, vertical and diagonal directions. The low order norms of gradient components were used to establish the feature vector. Euclidean distance based classifier was used as a matching metric for determining the degree of similarity between the features vector extracted from the tested iris image and template features vectors stored in the database. Experimental tests were performed using 2639 iris images from CASIA V4-Interival database, the attained recognition accuracy has reached up to 99.92%.

Keywords: Iris recognition, contrast stretching, gradient features, texture features, Euclidean metric.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1965

Authors: D. Vainauska, S. Kozireva, A. Karpovs, M. Chistyakovs, M. Baryshev

Abstract:

Liposomal magnetofection is a simple, highly efficient technology for cell transfection, demonstrating better outcome than a number of other common gene delivery methods. However, aggregate complexes distribution over the cell surface is non-uniform due to the gradient of the permanent magnetic field. The aim of this study was to estimate the efficiency of liposomal magnetofection for prostate carcinoma PC3 cell line using newly designed device, “DynaFECTOR", ensuring magnetofection in a dynamic gradient magnetic field. Liposomal magnetofection in a dynamic gradient magnetic field demonstrated the highest transfection efficiency for PC3 cells – it increased for 21% in comparison with liposomal magnetofection and for 42% in comparison with lipofection alone. The optimal incubation time under dynamic magnetic field for PC3 cell line was 5 minutes and the optimal rotation frequency of magnets – 5 rpm. The new approach also revealed lower cytotoxic effect to cells than liposomal magnetofection.

Keywords: Dynamic gradient magnetic field, gene delivery, liposomal magnetofection, prostate cancer cell line

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1665

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 1688

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 186

Authors: A. Elyousfi, A. Tamtaoui, E. Bouyakhf

Abstract:

The H.264/AVC standard uses an intra prediction, 9 directional modes for 4x4 luma blocks and 8x8 luma blocks, 4 directional modes for 16x16 macroblock and 8x8 chroma blocks, respectively. It means that, for a macroblock, it has to perform 736 different RDO calculation before a best RDO modes is determined. With this Multiple intra-mode prediction, intra coding of H.264/AVC offers a considerably higher improvement in coding efficiency compared to other compression standards, but computational complexity is increased significantly. This paper presents a fast intra prediction algorithm for H.264/AVC intra prediction based a characteristic of homogeneity information. In this study, the gradient prediction method used to predict the homogeneous area and the quadratic prediction function used to predict the nonhomogeneous area. Based on the correlation between the homogeneity and block size, the smaller block is predicted by gradient prediction and quadratic prediction, so the bigger block is predicted by gradient prediction. Experimental results are presented to show that the proposed method reduce the complexity by up to 76.07% maintaining the similar PSNR quality with about 1.94%bit rate increase in average.

Keywords: Intra prediction, H.264/AVC, video coding, encodercomplexity.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1896

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 898

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 1423