Search results for: split activation function.

Authors: Erhan Ata, Yusuf Yaylı

Abstract:

Let M be an almost split quaternionic manifold on which its almost split quaternionic structure is defined by a three dimensional subbundle V of ( T M) T (M) * Ôèù and {F,G,H} be a local basis for V . Suppose that the (global) (1, 2) tensor field defined[V ,V ]is defined by [V,V ] = [F,F]+[G,G] + [H,H], where [,] denotes the Nijenhuis bracket. In ref. [7], for the almost split-hypercomplex structureH = J α,α =1,2,3, and the Obata connection ÔêçH vanishes if and only if H is split-hypercomplex. In this study, we give a prof, in particular, prove that if either M is a split quaternionic Kaehler manifold, or if M is a splitcomplex manifold with almost split-complex structure F , then the vanishing [V ,V ] is equivalent to that of all the Nijenhuis brackets of {F,G,H}. It follows that the bundle V is trivial if and only if [V ,V ] = 0 .

Keywords: Almost split - hypercomplex structure, Almost split quaternionic structure, Almost split quaternion Kaehler manifold, Obata connection.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1513

Authors: Anita S. Gangal, P. K. Kalra, D. S. Chauhan

Abstract:

The backpropagation algorithm in general employs quadratic error function. In fact, most of the problems that involve minimization employ the Quadratic error function. With alternative error functions the performance of the optimization scheme can be improved. The new error functions help in suppressing the ill-effects of the outliers and have shown good performance to noise. In this paper we have tried to evaluate and compare the relative performance of complex valued neural network using different error functions. During first simulation for complex XOR gate it is observed that some error functions like Absolute error, Cauchy error function can replace Quadratic error function. In the second simulation it is observed that for some error functions the performance of the complex valued neural network depends on the architecture of the network whereas with few other error functions convergence speed of the network is independent of architecture of the neural network.

Keywords: Complex backpropagation algorithm, complex errorfunctions, complex valued neural network, split activation function.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2425

Authors: Erhan Ata, H. Hilmi Hacisalihoğlu, Yusuf Yayli

Abstract:

In this work some characterizations of semi Riemannian curvature tensor on almost split quaternion Kaehler manifolds and some characterizations of Ricci tensor on almost split quaternion Kaehler manifolds are given.

Keywords: Almost split quaternion Kaehler manifold, Riemann curvature, Ricci curvature.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1760

Authors: M. Satya Sai Ram, P. Siddaiah, M. Madhavi Latha

Abstract:

Vector quantization is a powerful tool for speech coding applications. This paper deals with LPC Coding of speech signals which uses a new technique called Multi Switched Split Vector Quantization, This is a hybrid of two product code vector quantization techniques namely the Multi stage vector quantization technique, and Switched split vector quantization technique,. Multi Switched Split Vector Quantization technique quantizes the linear predictive coefficients in terms of line spectral frequencies. From results it is proved that Multi Switched Split Vector Quantization provides better trade off between bitrate and spectral distortion performance, computational complexity and memory requirements when compared to Switched Split Vector Quantization, Multi stage vector quantization, and Split Vector Quantization techniques. By employing the switching technique at each stage of the vector quantizer the spectral distortion, computational complexity and memory requirements were greatly reduced. Spectral distortion was measured in dB, Computational complexity was measured in floating point operations (flops), and memory requirements was measured in (floats).

Keywords: Unconstrained vector quantization, Linear predictiveCoding, Split vector quantization, Multi stage vector quantization, Switched Split vector quantization, Line Spectral Frequencies.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1742

Authors: P. B. Sob, A. A. Alugongo, T. B. Tengen

Abstract:

The activation volume of 6082T6 aluminum is investigated at different temperatures for grain size variants. The deformation activation volume was computed on the basis of the relationship between the Boltzmann’s constant k, the testing temperatures, the material strain rate sensitivity and the material yield stress grain size variants. The material strain rate sensitivity is computed as a function of yield stress and strain rate grain size variants. The effect of the material strain rate sensitivity and the deformation activation volume of 6082T6 aluminum at different temperatures of 3-D grain are discussed. It is shown that the strain rate sensitivities and activation volume are negative for the grain size variants during the deformation of nanostructured materials. It is also observed that the activation volume vary in different ways with the equivalent radius, semi minor axis radius, semi major axis radius and major axis radius. From the obtained results it is shown that the variation of activation volume increase and decrease with the testing temperature. It was revealed that, increase in strain rate sensitivity led to decrease in activation volume whereas increase in activation volume led to decrease in strain rate sensitivity.

Keywords: Nanostructured materials, grain size variants, temperature, yield stress, strain rate sensitivity, activation volume.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2602

Authors: Chang-Myeon Lee, Min-Hyung Lee, Jin-Young Hur, Ho-Nyun Lee, Hong-Kee Lee

Abstract:

An ultrasound-assisted activation method for electroless silver plating is presented in this study. When the ultrasound was applied during the activation step, the amount of the Pd species adsorbed on substrate surfaces was higher than that of sample pretreated with a conventional activation process without ultrasound irradiation. With this activation method, it was also shown that the adsorbed Pd species with a size of about 5 nm were uniformly distributed on the surfaces, thus a smooth and uniform coating on the surfaces was obtained by subsequent electroless silver plating. The samples after each step were characterized by AFM, XPS, FIB, and SEM.

Keywords: Cavitation, Electroless silver, Pd activation, Ultrasonic

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2385

Authors: Siddhartha Bhattacharyya, Paramartha Dutta, Ujjwal Maulik, Prashanta Kumar Nandi

Abstract:

The paper describes a self supervised parallel self organizing neural network (PSONN) architecture for true color image segmentation. The proposed architecture is a parallel extension of the standard single self organizing neural network architecture (SONN) and comprises an input (source) layer of image information, three single self organizing neural network architectures for segmentation of the different primary color components in a color image scene and one final output (sink) layer for fusion of the segmented color component images. Responses to the different shades of color components are induced in each of the three single network architectures (meant for component level processing) by applying a multilevel version of the characteristic activation function, which maps the input color information into different shades of color components, thereby yielding a processed component color image segmented on the basis of the different shades of component colors. The number of target classes in the segmented image corresponds to the number of levels in the multilevel activation function. Since the multilevel version of the activation function exhibits several subnormal responses to the input color image scene information, the system errors of the three component network architectures are computed from some subnormal linear index of fuzziness of the component color image scenes at the individual level. Several multilevel activation functions are employed for segmentation of the input color image scene using the proposed network architecture. Results of the application of the multilevel activation functions to the PSONN architecture are reported on three real life true color images. The results are substantiated empirically with the correlation coefficients between the segmented images and the original images.

Keywords: Colour image segmentation, fuzzy set theory, multi-level activation functions, parallel self-organizing neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2022

Authors: M. Satya Sai Ram, P. Siddaiah, M. Madhavi Latha

Abstract:

Vector quantization is a powerful tool for speech coding applications. This paper deals with LPC Coding of speech signals which uses a new technique called Multi Switched Split Vector Quantization (MSSVQ), which is a hybrid of Multi, switched, split vector quantization techniques. The spectral distortion performance, computational complexity, and memory requirements of MSSVQ are compared to split vector quantization (SVQ), multi stage vector quantization(MSVQ) and switched split vector quantization (SSVQ) techniques. It has been proved from results that MSSVQ has better spectral distortion performance, lower computational complexity and lower memory requirements when compared to all the above mentioned product code vector quantization techniques. Computational complexity is measured in floating point operations (flops), and memory requirements is measured in (floats).

Keywords: Linear predictive Coding, Multi stage vectorquantization, Switched Split vector quantization, Split vectorquantization, Line Spectral Frequencies (LSF).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1674

Authors: S. Meikandasivam, D. Vijayakumar, Rajesh Kumar Nema, Shailendra Kumar Jain

Abstract:

This paper investigates the performance of the single TCSC and proposed split TCSC on transmission system where India’s first TCSC project is installed in Kanpur - Ballabhgarh (KB) line to ensure the fine tuning of line reactance by proposed split TCSC in place of existing KB TCSC. A three phase KB transmission system is developed in MATLAB/Simulink (SimPowerSystems) for

1. without any compensation,
2. with fixed capacitor (FC),
3. with FC + existing KB TCSC and
4. with FC + proposed split TCSC

The KB system is analyzed for a step variation of load and performance of the system is investigated with a closed loop reactance control method.

Keywords: Single TCSC, Split TCSC, TCSC Reactance characteristic curve, Power flow analysis, Sensitivity analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2600

Authors: Ning Xue, Srinivas Merugu, Ignacio Delgado Martinez, Tao Sun, John Tsang, Shih-Cheng Yen

Abstract:

We have developed a polyimide based neural interface electrode to record nerve signals from the sciatic nerve of a rat. The neural interface electrode has a split-ring shape, with four protruding gold electrodes for recording, and two reference gold electrodes around the split-ring. The split-ring electrode can be opened up to encircle the sciatic nerve. The four electrodes can be bent to sit on top of the nerve and hold the device in position, while the split-ring frame remains flat. In comparison, while traditional cuff electrodes can only fit certain sizes of the nerve, the developed device can fit a variety of rat sciatic nerve dimensions from 0.6 mm to 1.0 mm, and adapt to the chronic changes in the nerve as the electrode tips are bendable. The electrochemical impedance spectroscopy measurement was conducted. The gold electrode impedance is on the order of 10 kΩ, showing excellent charge injection capacity to record neural signals.

Keywords: Impedance, neural interface, split-ring electrode.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2598

Authors: Titin Andri Wihastuti, Djanggan Sargowo

Abstract:

NFκB is a transcription factor regulating many function of the vessel wall. In the normal condition , NFκB is revealed diffuse cytoplasmic expressionsuggesting that the system is inactive. The presence of activation NFκB provide a potential pathway for the rapid transcriptional of a variety of genes encoding cytokines, growth factors, adhesion molecules and procoagulatory factors. It is likely to play an important role in chronic inflamatory disease involved atherosclerosis. There are many stimuli with the potential to active NFκB, including hyperlipidemia. We used 24 mice which was divided in 6 groups. The HFD given by et libitum procedure during 2, 4, and 6 months. The parameters in this study were the amount of NFKB activation ,H2O2 as ROS and VCAM-1 as a product of NFKB activation. H2O2 colorimetryc assay performed directly using Anti Rat H2O2 ELISA Kit. The NFKB and VCAM-1 detection obtained from aorta mice, measured by ELISA kit and imunohistochemistry. There was a significant difference activation of H2O2, NFKB and VCAM-1 level at induce HFD after 2, 4 and 6 months. It suggest that HFD induce ROS formation and increase the activation of NFKB as one of atherosclerosis marker that caused by hyperlipidemia as classical atheroschlerosis risk factor.

Keywords: High Fat Diet, NFKB, H2O2, atherosclerosis

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2031

Authors: Ram N. Singh, Abraham K. George, Dawood N. Al-Namaani

Abstract:

The Euler-s equation of motion is extended to include the viscosity stress tensor leading to the formulation of Navier– Stokes type equation. The latter is linearized and applied to investigate the rotational motion or vorticity in a viscous fluid. Relations for the velocity of viscous waves and attenuation parameter are obtained in terms of viscosity (μ) and the density (¤ü) of the fluid. μ and ¤ü are measured experimentally as a function of temperature for two different samples of light and heavy crude oil. These data facilitated to determine the activation energy, velocity of viscous wave and the attenuation parameter. Shear wave velocity in heavy oil is found to be much larger than the light oil, whereas the attenuation parameter in heavy oil is quite low in comparison to light one. The activation energy of heavy oil is three times larger than light oil.

Keywords: Activation Energy, Attenuation, Crude Oil, Navier- Stokes Equation, Viscosity.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1987

Authors: Wee Leong Son, Hasmayadi Abdul Majid, Rohana Musa

Abstract:

This paper study the segmented split capacitor Digital-to-Analog Converter (DAC) implemented in a differentialtype 12-bit Successive Approximation Analog-to-Digital Converter (SA-ADC). The series capacitance split array method employed as it reduced the total area of the capacitors required for high resolution DACs. A 12-bit regular binary array structure requires 2049 unit capacitors (Cs) while the split array needs 127 unit Cs. These results in the reduction of the total capacitance and power consumption of the series split array architectures as to regular binary-weighted structures. The paper will show the 12-bit DAC series split capacitor with 4-bit thermometer coded DAC architectures as well as the simulation and measured results.

Keywords: Successive Approximation Register Analog-to- Digital Converter, SAR ADC, Low voltage ADC.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 9562

Authors: Jia-Shiun Chen, Hsiu-Ying Hwang

Abstract:

Hybrid electric vehicles can reduce pollution and improve fuel economy. Power-split hybrid electric vehicles (HEVs) provide two power paths between the internal combustion engine (ICE) and energy storage system (ESS) through the gears of an electrically variable transmission (EVT). EVT allows ICE to operate independently from vehicle speed all the time. Therefore, the ICE can operate in the efficient region of its characteristic brake specific fuel consumption (BSFC) map. The two-mode powertrain can operate in input-split or compound-split EVT modes and in four different fixed gear configurations. Power-split architecture is advantageous because it combines conventional series and parallel power paths. This research focuses on input-split and compound-split modes in the two-mode power-split powertrain. Fuzzy Logic Control (FLC) for an internal combustion engine (ICE) and PI control for electric machines (EMs) are derived for the urban driving cycle simulation. These control algorithms reduce vehicle fuel consumption and improve ICE efficiency while maintaining the state of charge (SOC) of the energy storage system in an efficient range.

Keywords: Hybrid electric vehicle, fuel economy, two-mode hybrid, fuzzy control.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2609

Authors: Apoorva Vinod, Archana Mathur, Snehanshu Saha

Abstract:

Though there exists a plethora of Activation Functions (AFs) used in single and multiple hidden layer Neural Networks (NN), their behavior always raised curiosity, whether used in combination or singly. The popular AFs – Sigmoid, ReLU, and Tanh – have performed prominently well for shallow and deep architectures. Most of the time, AFs are used singly in multi-layered NN, and, to the best of our knowledge, their performance is never studied and analyzed deeply when used in combination. In this manuscript, we experiment on multi-layered NN architecture (both on shallow and deep architectures; Convolutional NN and VGG16) and investigate how well the network responds to using two different AFs (Sigmoid-Tanh, Tanh-ReLU, ReLU-Sigmoid) used alternately against a traditional, single (Sigmoid-Sigmoid, Tanh-Tanh, ReLU-ReLU) combination. Our results show that on using two different AFs, the network achieves better accuracy, substantially lower loss, and faster convergence on 4 computer vision (CV) and 15 Non-CV (NCV) datasets. When using different AFs, not only was the accuracy greater by 6-7%, but we also accomplished convergence twice as fast. We present a case study to investigate the probability of networks suffering vanishing and exploding gradients when using two different AFs. Additionally, we theoretically showed that a composition of two or more AFs satisfies Universal Approximation Theorem (UAT).

Keywords: Activation Function, Universal Approximation function, Neural Networks, convergence.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 154

Authors: Siddhartha Bhattacharyya, Paramartha Dutta, Ujjwal Maulik, Prashanta Kumar Nandi

Abstract:

A multilayer self organizing neural neural network (MLSONN) architecture for binary object extraction, guided by a beta activation function and characterized by backpropagation of errors estimated from the linear indices of fuzziness of the network output states, is discussed. Since the MLSONN architecture is designed to operate in a single point fixed/uniform thresholding scenario, it does not take into cognizance the heterogeneity of image information in the extraction process. The performance of the MLSONN architecture with representative values of the threshold parameters of the beta activation function employed is also studied. A three layer bidirectional self organizing neural network (BDSONN) architecture comprising fully connected neurons, for the extraction of objects from a noisy background and capable of incorporating the underlying image context heterogeneity through variable and adaptive thresholding, is proposed in this article. The input layer of the network architecture represents the fuzzy membership information of the image scene to be extracted. The second layer (the intermediate layer) and the final layer (the output layer) of the network architecture deal with the self supervised object extraction task by bi-directional propagation of the network states. Each layer except the output layer is connected to the next layer following a neighborhood based topology. The output layer neurons are in turn, connected to the intermediate layer following similar topology, thus forming a counter-propagating architecture with the intermediate layer. The novelty of the proposed architecture is that the assignment/updating of the inter-layer connection weights are done using the relative fuzzy membership values at the constituent neurons in the different network layers. Another interesting feature of the network lies in the fact that the processing capabilities of the intermediate and the output layer neurons are guided by a beta activation function, which uses image context sensitive adaptive thresholding arising out of the fuzzy cardinality estimates of the different network neighborhood fuzzy subsets, rather than resorting to fixed and single point thresholding. An application of the proposed architecture for object extraction is demonstrated using a synthetic and a real life image. The extraction efficiency of the proposed network architecture is evaluated by a proposed system transfer index characteristic of the network.

Keywords: Beta activation function, fuzzy cardinality, multilayer self organizing neural network, object extraction,

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1566

Authors: Ioannis Neokosmidis, Nikos Gkekas, Thomas Kamalakis, Thomas Sphicopoulos

Abstract:

In high powered dense wavelength division multiplexed (WDM) systems with low chromatic dispersion, four-wave mixing (FWM) can prove to be a major source of noise. The MultiCanonical Monte Carlo Method (MCMC) and the Split Step Fourier Method (SSFM) are combined to accurately evaluate the probability density function of the decision variable of a receiver, limited by FWM. The combination of the two methods leads to more accurate results, and offers the possibility of adding other optical noises such as the Amplified Spontaneous Emission (ASE) noise.

Keywords: Monte Carlo, Nonlinear optics, optical crosstalk, Wavelength-division Multiplexing (WDM).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1692

Authors: N. M. Nawi, R. S. Ransing, M. R. Ransing

Abstract:

The conjugate gradient optimization algorithm is combined with the modified back propagation algorithm to yield a computationally efficient algorithm for training multilayer perceptron (MLP) networks (CGFR/AG). The computational efficiency is enhanced by adaptively modifying initial search direction as described in the following steps: (1) Modification on standard back propagation algorithm by introducing a gain variation term in the activation function, (2) Calculation of the gradient descent of error with respect to the weights and gains values and (3) the determination of a new search direction by using information calculated in step (2). The performance of the proposed method is demonstrated by comparing accuracy and computation time with the conjugate gradient algorithm used in MATLAB neural network toolbox. The results show that the computational efficiency of the proposed method was better than the standard conjugate gradient algorithm.

Keywords: Adaptive gain variation, back-propagation, activation function, conjugate gradient, search direction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1521

Authors: Luen Chow Chan

Abstract:

With the advocacy of green transportation and green traveling, cycling has become increasingly popular nowadays. Physiology and bike design are key factors for the influence of cycling efficiency. Therefore, this study aimed to investigate the significance of bike-frame geometric factors on cycling efficiency and muscle activation for different body sizes of non-professional Asian male cyclists. Participants who represented various body sizes, as measured by leg and back lengths, carried out cycling tests using a tailor-assembled road bike with different ergonomic design configurations including seat-height adjustments (i.e., 96%, 100%, and 104% of trochanteric height) and bike frame sizes (i.e., small and medium frames) for an assessable distance of 1 km. A specific power meter and self-developed adaptable surface electromyography (sEMG) were used to measure average pedaling power and cadence generated and muscle activation, respectively. The results showed that changing the seat height was far more significant than the body and bike frame sizes. The sEMG data evidently provided a better understanding of muscle activation as a function of different seat heights. Therefore, the interpretation of this study is that the major bike ergonomic design factor dominating the cycling efficiency of Asian participants with different body sizes was the seat height.

Keywords: Bike frame sizes, cadence rate, pedaling power, seat height.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 924

Authors: Ebru Kavak Akpinar, Seda Toraman

Abstract:

In the present work, the effective moisture diffusivity and activation energy were calculated using an infinite series solution of Fick-s diffusion equation. The results showed that increasing drying temperature accelerated the drying process. All drying experiments had only falling rate period. The average effective moisture diffusivity values varied from 2.807x10-10 to 6.977x10-10m2 s_1 over the temperature and velocity range. The temperature dependence of the effective moisture diffusivity for the thin layer drying of the ginger slices was satisfactorily described by an Arrhenius-type relationship with activation energy values of 19.313- 22.722 kJ.mol-1 within 40–70 °C and 0.8-3 ms-1 temperature range.

Keywords: Ginger, Drying, Activation energy, Moisture diffusivity.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2711

Authors: Guozhen Li, Philip Hall, Nick Miles, Tao Wu, Jie Dong

Abstract:

This paper presents a Euler-Lagrange model of the water-particles multiphase flows in a Vorsyl separator where particles with different densities are separated. A series of particles with their densities ranging from 760 kg/m³ to 1380 kg/m³ were fed into the Vorsyl separator with water by means of tangential inlet. The simulation showed that the feed materials acquired centrifugal force which allows most portion of the particles with a density less than water to move to the center of the separator, enter the vortex finder and leave the separator through the bottom outlet. While the particles heavier than water move to the wall, reach the throat area and leave the separator through the side outlet. The particles were thus separated and particles collected at the bottom outlet are pure and clean. The influence of particle density on separation efficiency was investigated which demonstrated a positive correlation of the separation efficiency with increasing density difference between medium liquid and the particle. In addition, the influence of the split ratio on the performance was studied which showed that the separation efficiency of the Vorsyl separator can be improved by the increase of split ratio. The simulation also suggested that the Vorsyl separator may not function when the feeding velocity is smaller than a certain critical feeding in velocity. In addition, an increasing feeding velocity gives rise to increased pressure drop, however does not necessarily increase the separation efficiency.

Keywords: Vorsyl separator, separation efficiency, CFD, split ratio.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1198

Authors: Mohammad Reza Ghasemi, Amin Ghorbani

Abstract:

The main goal of the present work is to decrease the computational burden for optimum design of steel frames with frequency constraints using a new type of neural networks called Wavelet Neural Network. It is contested to train a suitable neural network for frequency approximation work as the analysis program. The combination of wavelet theory and Neural Networks (NN) has lead to the development of wavelet neural networks. Wavelet neural networks are feed-forward networks using wavelet as activation function. Wavelets are mathematical functions within suitable inner parameters, which help them to approximate arbitrary functions. WNN was used to predict the frequency of the structures. In WNN a RAtional function with Second order Poles (RASP) wavelet was used as a transfer function. It is shown that the convergence speed was faster than other neural networks. Also comparisons of WNN with the embedded Artificial Neural Network (ANN) and with approximate techniques and also with analytical solutions are available in the literature.

Keywords: Weight Minimization, Frequency Constraints, Steel Frames, ANN, WNN, RASP Function.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1741

Authors: N. M. Nawi, M. R. Ransing, R. S. Ransing

Abstract:

The conjugate gradient optimization algorithm usually used for nonlinear least squares is presented and is combined with the modified back propagation algorithm yielding a new fast training multilayer perceptron (MLP) algorithm (CGFR/AG). The approaches presented in the paper consist of three steps: (1) Modification on standard back propagation algorithm by introducing gain variation term of the activation function, (2) Calculating the gradient descent on error with respect to the weights and gains values and (3) the determination of the new search direction by exploiting the information calculated by gradient descent in step (2) as well as the previous search direction. The proposed method improved the training efficiency of back propagation algorithm by adaptively modifying the initial search direction. Performance of the proposed method is demonstrated by comparing to the conjugate gradient algorithm from neural network toolbox for the chosen benchmark. The results show that the number of iterations required by the proposed method to converge is less than 20% of what is required by the standard conjugate gradient and neural network toolbox algorithm.

Keywords: Back-propagation, activation function, conjugategradient, search direction, gain variation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2838

Authors: M. Münch, R. Brandt

Abstract:

Martensitic steels with an ultimate tensile strength beyond 2000 MPa are applied in the powertrain of vehicles due to their excellent fatigue strength and high creep resistance. However, the creep controlling mechanism in martensitic steels at ambient temperatures up to 423 K is not evident. The purpose of this study is to review the low temperature creep (LTC) behavior of martensitic steels at temperatures from 363 K to 523 K. Thus, the validity of a logarithmic creep law is reviewed and the stress and temperature dependence of the creep parameters α and β are revealed. Furthermore, creep tests are carried out, which include stepped changes in temperature or stress, respectively. On one hand, the change of the creep rate due to a temperature step provides information on the magnitude of the activation energy of the LTC controlling mechanism and on the other hand, the stress step approach provides information on the magnitude of the activation volume. The magnitude, the temperature dependency, and the stress dependency of both material specific activation parameters may deliver a significant contribution to the disclosure of the nature of the LTC rate controlling mechanism.

Keywords: Activation parameters, creep mechanisms, high strength steels, low temperature creep.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 714

Authors: H. R. Moghadamzadeh, M. Naimi, H. Rahimzadeh, M. Ardjmand, V. M. Nansa, A. M. Ghanadi

Abstract:

The Iranian bentonite was first characterized by Scanning Electron Microscopy (SEM), Inductively Coupled Plasma mass spectrometry (ICP-MS), X-ray fluorescence (XRF), X-ray Diffraction (XRD) and BET. The bentonite was then treated thermally between 150°C-250°C at 15min, 45min and 90min and also was activated chemically with different concentration of sulphuric acid (3N, 5N and 10N). Although the results of thermal activated-bentonite didn-t show any considerable changes in specific surface area and Cation Exchange Capacity (CEC), but the results of chemical treated bentonite demonstrated that such properties have been improved by acid activation process.

Keywords: Acid activation, Bentonite, CEC, Thermal activation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2845

Authors: V. Revathi, J. Thaarrini, M. Venkob Rao

Abstract:

This paper presents a study on use of alkali activated bottom ash (BA) and ground granulated blast furnace slag (GGBS) blend in paver blocks. A preliminary effort on alkali-activated bottom ash, blast furnace slag based geopolymer (BA-GGBS-GP) mortar with river sand was carried out to identify the suitable mix for paver block. Several mixes were proposed based on the combination of BA-GGBS. The percentage ratio of BA: GGBS was selected as 100:0, 75:25, 50:50, 25:75 and 0:100 for the source material. Sodium based alkaline activators were used for activation. The molarity of NaOH was considered as 8M. The molar ratio of SiO₂ to Na₂O was varied from 1 to 4. Two curing mode such as ambient and steam curing 60°C for 24 hours were selected. The properties of paver block such as compressive strength split tensile strength, flexural strength and water absorption were evaluated as per IS15658:2006. Based on the preliminary study on BA-GGBS-GP mortar, the combinations of 25% BA with 75% GGBS mix for M30 and 75% BA with 25% GGBS mix for M35 grade were identified for paver block. Test results shows that the combination of BA-GGBS geopolymer paver blocks attained remarkable compressive strength under steam curing as well as in ambient mode at 3 days. It is noteworthy to know BA-GGBS-GP has promising future in the construction industry.

Keywords: Bottom ash, GGBS, alkali activation, paver block.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4037

Authors: J. Tospornsampan, I. Kita, M. Ishii, Y. Kitamura

Abstract:

In this paper a combination approach of two heuristic-based algorithms: genetic algorithm and tabu search is proposed. It has been developed to obtain the least cost based on the split-pipe design of looped water distribution network. The proposed combination algorithm has been applied to solve the three well-known water distribution networks taken from the literature. The development of the combination of these two heuristic-based algorithms for optimization is aimed at enhancing their strengths and compensating their weaknesses. Tabu search is rather systematic and deterministic that uses adaptive memory in search process, while genetic algorithm is probabilistic and stochastic optimization technique in which the solution space is explored by generating candidate solutions. Split-pipe design may not be realistic in practice but in optimization purpose, optimal solutions are always achieved with split-pipe design. The solutions obtained in this study have proved that the least cost solutions obtained from the split-pipe design are always better than those obtained from the single pipe design. The results obtained from the combination approach show its ability and effectiveness to solve combinatorial optimization problems. The solutions obtained are very satisfactory and high quality in which the solutions of two networks are found to be the lowest-cost solutions yet presented in the literature. The concept of combination approach proposed in this study is expected to contribute some useful benefits in diverse problems.

Keywords: GAs, Heuristics, Looped network, Least-cost design, Pipe network, Optimization, TS

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1788

Authors: Sinarwati Mohamad Suhaili, Naomie Salim, Mohamad Nazim Jambli

Abstract:

Sequence-to-sequence (seq2seq) models augmented with attention mechanisms are increasingly important in automated customer service. These models, adept at recognizing complex relationships between input and output sequences, are essential for optimizing chatbot responses. Central to these mechanisms are neural attention weights that determine the model’s focus during sequence generation. Despite their widespread use, there remains a gap in the comparative analysis of different attention weighting functions within seq2seq models, particularly in the context of chatbots utilizing the Customer Support Twitter (CST) dataset. This study addresses this gap by evaluating four distinct attention-scoring functions—dot, multiplicative/general, additive, and an extended multiplicative function with a tanh activation parameter — in neural generative seq2seq models. Using the CST dataset, these models were trained and evaluated over 10 epochs with the AdamW optimizer. Evaluation criteria included validation loss and BLEU scores implemented under both greedy and beam search strategies with a beam size of k = 3. Results indicate that the model with the tanh-augmented multiplicative function significantly outperforms its counterparts, achieving the lowest validation loss (1.136484) and the highest BLEU scores (0.438926 under greedy search, 0.443000 under beam search, k = 3). These findings emphasize the crucial influence of selecting an appropriate attention-scoring function to enhance the performance of seq2seq models for chatbots, particularly highlighting the model integrating tanh activation as a promising approach to improving chatbot quality in customer support contexts.

Keywords: Attention weight, chatbot, encoder-decoder, neural generative attention, score function, sequence-to-sequence.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 93

Authors: Mansi Dhuria, Aalok Misra

Abstract:

In the context of large volume Big Divisor (nearly) SLagy D3/D7 μ-Split SUSY [1], after an explicit identification of first generation of SM leptons and quarks with fermionic superpartners of four Wilson line moduli, we discuss the identification of gravitino as a potential dark matter candidate by explicitly calculating the decay life times of gravitino (LSP) to be greater than age of universe and lifetimes of decays of the co-NLSPs (the first generation squark/slepton and a neutralino) to the LSP (the gravitino) to be very small to respect BBN constraints. Interested in non-thermal production mechanism of gravitino, we evaluate the relic abundance of gravitino LSP in terms of that of the co-NLSP-s by evaluating their (co-)annihilation cross sections and hence show that the former satisfies the requirement for a potential Dark Matter candidate. We also show that it is possible to obtain a 125 GeV light Higgs in our setup.

Keywords: Split Supersymmetry, Large Volume Swiss-Cheese Calabi-Yau's, Dark Matter, (N)LSP decays, relic abundance.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1585

Authors: R. K. Saxena, Ravi Saxena

Abstract:

In view of their importance and usefulness in reliability theory and probability distributions, several generalizations of the inverse Gaussian distribution and the Krtzel function are investigated in recent years. This has motivated the authors to introduce and study a new generalization of the inverse Gaussian distribution and the Krtzel function associated with a product of a Bessel function of the third kind )(zKQ and a Z - Fox-Wright generalized hyper geometric function introduced in this paper. The introduced function turns out to be a unified gamma-type function. Its incomplete forms are also discussed. Several properties of this gamma-type function are obtained. By means of this generalized function, we introduce a generalization of inverse Gaussian distribution, which is useful in reliability analysis, diffusion processes, and radio techniques etc. The inverse Gaussian distribution thus introduced also provides a generalization of the Krtzel function. Some basic statistical functions associated with this probability density function, such as moments, the Mellin transform, the moment generating function, the hazard rate function, and the mean residue life function are also obtained.KeywordsFox-Wright function, Inverse Gaussian distribution, Krtzel function & Bessel function of the third kind.

Keywords: Fox-Wright function, Inverse Gaussian distribution, Krtzel function & Bessel function of the third kind.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1722