Search results for: loss function decomposition.

Authors: P. C. Ihenacho, M. Burby, G. G. Nasr, G. C. Enyi

Abstract:

Formulation of a low oil-water ratio drilling mud with vegetable oil continuous phase without adversely affecting the mud rheology and stability has been a major challenge. A low oil-water ratio is beneficial in producing low fluid loss which is essential for wellbore stability. This study examined the possibility of 50/50 oil-water ratio invert emulsion drilling mud using a vegetable oil continuous phase. Jatropha oil was used as continuous phase. 12 ml of egg yolk which was separated from the albumen was added as the primary emulsifier additive. The rheological, stability and filtration properties were examined. The plastic viscosity and yield point were found to be 36cp and 17 Ib/100 ft² respectively. The electrical stability at 48.9ºC was 353v and the 30 minutes fluid loss was 6ml. The results compared favourably with a similar formulation using 70/30 oil - water ratio giving plastic viscosity of 31cp, yield point of 17 Ib/100 ft², electrical stability value of 480v and 12ml for the 30 minutes fluid loss. This study indicates that with a good mud composition using guided empiricism, 50/50 oil-water ratio invert emulsion drilling mud is feasible with a vegetable oil continuous phase. The choice of egg yolk as emulsifier additive is for compatibility with the vegetable oil and environmental concern. The high water content with no fluid loss additive will also minimise the cost of mud formulation.

Keywords: Environmental compatibility, low cost of mud formulation, low fluid loss, wellbore stability.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2903

Authors: Ali Dorostkar

Abstract:

In this paper, a basic schematic of fractional dimensional optimization problem is presented. As will be shown, a method is performed based on a relation between roots and tangent lines of function in fractional dimensions for an arbitrary initial point. It is shown that for each polynomial function with order N at least N tangent lines must be existed in fractional dimensions of 0 < α < N+1 which pass exactly through the all roots of the proposed function. Geometrical analysis of tangent lines in fractional dimensions is also presented to clarify more intuitively the proposed method. Results show that with an appropriate selection of fractional dimensions, we can directly find the roots. Method is presented for giving a different direction of optimization problems by the use of fractional dimensions.

Keywords: Tangent line, fractional dimension, root, optimization problem.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 515

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 91

Authors: N. Tuncbag, T. Haliloglu, O. Keskin

Abstract:

Understanding the cell's large-scale organization is an interesting task in computational biology. Thus, protein-protein interactions can reveal important organization and function of the cell. Here, we investigated the correspondence between protein interactions and function for the yeast. We obtained the correlations among the set of proteins. Then these correlations are clustered using both the hierarchical and biclustering methods. The detailed analyses of proteins in each cluster were carried out by making use of their functional annotations. As a result, we found that some functional classes appear together in almost all biclusters. On the other hand, in hierarchical clustering, the dominancy of one functional class is observed. In brief, from interaction data to function, some correlated results are noticed about the relationship between interaction and function which might give clues about the organization of the proteins.

Keywords: Pair-wise protein interactions, DIP database, functional correlations, biclustering.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1656

Authors: Subariah Ibrahim, Mohd Aizaini Maarof

Abstract:

A generalization of the concepts of Feistel Networks (FN), known as Extended Feistel Network (EFN) is examined. EFN splits the input blocks into n > 2 sub-blocks. Like conventional FN, EFN consists of a series of rounds whereby at least one sub-block is subjected to an F function. The function plays a key role in the diffusion process due to its completeness property. It is also important to note that in EFN the F-function is the most computationally expensive operation in a round. The aim of this paper is to determine a suitable type of EFN for a scalable cipher. This is done by analyzing the threshold number of rounds for different types of EFN to achieve the completeness property as well as the number of F-function required in the network. The work focuses on EFN-Type I, Type II and Type III only. In the analysis it is found that EFN-Type II and Type III diffuses at the same rate and both are faster than Type-I EFN. Since EFN-Type-II uses less F functions as compared to EFN-Type III, therefore Type II is the most suitable EFN for use in a scalable cipher.

Keywords: Cryptography, Extended Feistel Network, Diffusion Analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1667

Authors: Chaiyakrit Raoupatham, Ram Hari Dhakal, Chalermchai Wanichlamlert

Abstract:

This paper aimed to introduce the solution of concrete slump recovery using chemical admixture type-F (superplasticizer, naphthalene base) to the practice in order to solve unusable concrete problem due to concrete loss its slump, especially for those tropical countries that have faster slump loss rate. In the other hand, randomly adding superplasticizer into concrete can cause concrete to segregate. Therefore, this paper also develops the estimation model used to calculate amount of second dose of superplasticizer need for concrete slump recovery. Fresh properties of ordinary Portland cement concrete with volumetric ratio of paste to void between aggregate (paste content) of 1.1-1.3 with water-cement ratio zone of 0.30 to 0.67 and initial superplasticizer (naphthalene base) of 0.25%-1.6% were tested for initial slump and slump loss for every 30 minutes for one and half hour by slump cone test. Those concretes with slump loss range from 10% to 90% were re-dosed and successfully recovered back to its initial slump. Slump after re-dosed was tested by slump cone test. From the result, it has been concluded that, slump loss was slower for those mix with high initial dose of superplasticizer due to addition of superplasticizer will disturb cement hydration. The required second dose of superplasticizer was affected by two major parameters, which were water-cement ratio and paste content, where lower water-cement ratio and paste content cause an increase in require second dose of superplasticizer. The amount of second dose of superplasticizer is higher as the solid content within the system is increase, solid can be either from cement particles or aggregate. The data was analyzed to form an equation use to estimate the amount of second dosage requirement of superplasticizer to recovery slump to its original.

Keywords: Estimation model, second superplasticizer dosage, slump loss, slump recovery.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1865

Authors: Y. Long, L. Liu, K. V. Branin

Abstract:

One challenge faced by procurement decision-maker during the acquisition process is how to compare similar products from different suppliers and allocate orders among different products or services. This work focuses on allocating orders among multiple suppliers considering rebate. The objective function is to minimize the total acquisition cost including purchasing cost and rebate benefit. Rebate benefit is complex and difficult to estimate at the ordering step. Rebate rules vary for different suppliers and usually change over time. In this work, we developed a system to collect the rebate policies, standardized the rebate policies and developed two-stage optimization models for ordering allocation. Rebate policy with multi-tiers is considered in modeling. The discontinuous cost function of rebate benefit is formulated for different scenarios. A piecewise linear function is used to approximate the discontinuous cost function of rebate benefit. And a Mixed Integer Programing (MIP) model is built for order allocation problem with multi-tier rebate. A case study is presented and it shows that our optimization model can reduce the total acquisition cost by considering rebate rules.

Keywords: Discontinuous cost function, mixed integer programming, optimization, procurement, rebate.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 613

Authors: Rassoul Abdelaziz

Abstract:

We develop a new estimator of the renewal function for heavy-tailed claims amounts. Our approach is based on the peak over threshold method for estimating the tail of the distribution with a generalized Pareto distribution. The asymptotic normality of an appropriately centered and normalized estimator is established, and its performance illustrated in a simulation study.

Keywords: Renewal function, peak-over-threshold, POT method, extremes value, generalized pareto distribution, heavy-tailed distribution.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1435

Authors: Mohamad Mahdavi, Mojtaba Mahdavi

Abstract:

This paper tries to represent a new method for computing the reliability of a system which is arranged in series or parallel model. In this method we estimate life distribution function of whole structure using the asymptotic Extreme Value (EV) distribution of Type I, or Gumbel theory. We use EV distribution in minimal mode, for estimate the life distribution function of series structure and maximal mode for parallel system. All parameters also are estimated by Moments method. Reliability function and failure (hazard) rate and p-th percentile point of each function are determined. Other important indexes such as Mean Time to Failure (MTTF), Mean Time to repair (MTTR), for non-repairable and renewal systems in both of series and parallel structure will be computed.

Keywords: Reliability, extreme value, parallel, series, lifedistribution

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2047

Authors: C. Worakitjaroenphon, A. Oonsivilai

Abstract:

The study of piezoelectric material in the past was in T-Domain form; however, no one has studied piezoelectric material in the S-Domain form. This paper will present the piezoelectric material in the transfer function or S-Domain model. S-Domain is a well known mathematical model, used for analyzing the stability of the material and determining the stability limits. By using S-Domain in testing stability of piezoelectric material, it will provide a new tool for the scientific world to study this material in various forms.

Keywords: Piezoelectric, Stability, S-Domain, Transfer function

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3820

Authors: H. Ozbasaran

Abstract:

Lateral torsional buckling is a global buckling mode which should be considered in design of slender structural members under flexure about their strong axis. It is possible to compute the load which causes lateral torsional buckling of a beam by finite element analysis, however, closed form equations are needed in engineering practice for calculation ease which can be obtained by using energy method. In lateral torsional buckling applications of energy method, a proper function for the critical lateral torsional buckling mode should be chosen which can be thought as the variation of twisting angle along the buckled beam. Accuracy of the results depends on how close is the chosen function to the exact mode. Since critical lateral torsional buckling mode of the cantilever I-beams varies due to material properties, section properties and loading case, the hardest step is to determine a proper mode function in application of energy method. This paper presents an approximate function for critical lateral torsional buckling mode of doubly symmetric cantilever I-beams. Coefficient matrices are calculated for concentrated load at free end, uniformly distributed load and constant moment along the beam cases. Critical lateral torsional buckling modes obtained by presented function and exact solutions are compared. It is found that the modes obtained by presented function coincide with differential equation solutions for considered loading cases.

Keywords: Buckling mode, cantilever, lateral-torsional buckling, I-beam.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2512

Authors: Hnin Hnin Kyi, Khaing Khaing Aye

Abstract:

Acoustic function plays an important role in aerodynamic mechanical engineering. It can classify the kind of air-vehicle such as subsonic or supersonic. Acoustic velocity relates with velocity and Mach number. Mach number relates again acoustic stability or instability condition. Mach number plays an important role in growth or decay in energy system. Acoustic is a function of temperature and temperature is directly proportional to pressure. If we control the pressure, we can control acoustic function. To get pressure stability condition, we apply Navier-Stokes equations.

Keywords: Acoustic velocity, Irrotational, Mach number, Rotational.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1757

Authors: Tsunwai Gary Yip

Abstract:

Phase locked loops for data links operating at 10 Gb/s or faster are low phase noise devices designed to operate with a low jitter reference clock. Characterization of their jitter transfer function is difficult because the intrinsic noise of the device is comparable to the random noise level in the reference clock signal. A linear model is proposed to account for the intrinsic noise of a PLL. The intrinsic noise data of a PLL for 10 Gb/s links is presented. The jitter transfer function of a PLL in a test chip for 12.8 Gb/s data links was determined in experiments using the 400 MHz reference clock as the source of simultaneous excitations over a wide range of frequency. The result shows that the PLL jitter transfer function can be approximated by a second order linear model.

Keywords: Intrinsic phase noise, jitter in data link, PLL jitter transfer function, high speed clocking in electronic circuit

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1892

Authors: H. P. Singh, S. Singh

Abstract:

The voice signal in Voice over Internet protocol (VoIP) system is processed through the best effort policy based IP network, which leads to the network degradations including delay, packet loss jitter. The work in this paper presents the implementation of finite impulse response (FIR) filter for voice quality improvement in the VoIP system through distributed arithmetic (DA) algorithm. The VoIP simulations are conducted with AMR-NB 6.70 kbps and G.729a speech coders at different packet loss rates and the performance of the enhanced VoIP signal is evaluated using the perceptual evaluation of speech quality (PESQ) measurement for narrowband signal. The results show reduction in the computational complexity in the system and significant improvement in the quality of the VoIP voice signal.

Keywords: VoIP, Signal Quality, Distributed Arithmetic, Packet Loss, Speech Coder.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1781

Authors: C. Pislaru, A. Shebani

Abstract:

This paper uses the radial basis function neural network (RBFNN) for system identification of nonlinear systems. Five nonlinear systems are used to examine the activity of RBFNN in system modeling of nonlinear systems; the five nonlinear systems are dual tank system, single tank system, DC motor system, and two academic models. The feed forward method is considered in this work for modelling the non-linear dynamic models, where the KMeans clustering algorithm used in this paper to select the centers of radial basis function network, because it is reliable, offers fast convergence and can handle large data sets. The least mean square method is used to adjust the weights to the output layer, and Euclidean distance method used to measure the width of the Gaussian function.

Keywords: System identification, Nonlinear system, Neural networks, RBF neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2813

Authors: Martin Cermak, Stanislav Sysala

Abstract:

In this paper we present the efficient parallel implementation of elastoplastic problems based on the TFETI (Total Finite Element Tearing and Interconnecting) domain decomposition method. This approach allow us to use parallel solution and compute this nonlinear problem on the supercomputers and decrease the solution time and compute problems with millions of DOFs. In our approach we consider an associated elastoplastic model with the von Mises plastic criterion and the combination of linear isotropic-kinematic hardening law. This model is discretized by the implicit Euler method in time and by the finite element method in space. We consider the system of nonlinear equations with a strongly semismooth and strongly monotone operator. The semismooth Newton method is applied to solve this nonlinear system. Corresponding linearized problems arising in the Newton iterations are solved in parallel by the above mentioned TFETI. The implementation of this problem is realized in our in-house MatSol packages developed in MatLab.

Keywords: Isotropic-kinematic hardening, TFETI, domain decomposition, parallel solution.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1712

Authors: Tomohiro Ando, Satoshi Yamashita

Abstract:

The objective of this study is to propose a statistical modeling method which enables simultaneous term structure estimation of the risk-free interest rate, hazard and loss given default, incorporating the characteristics of the bond issuing company such as credit rating and financial information. A reduced form model is used for this purpose. Statistical techniques such as spline estimation and Bayesian information criterion are employed for parameter estimation and model selection. An empirical analysis is conducted using the information on the Japanese bond market data. Results of the empirical analysis confirm the usefulness of the proposed method.

Keywords: Empirical Bayes, Hazard term structure, Loss given default.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1623

Authors: Panpan Xu, Shulin Sui

Abstract:

The crossover probability and mutation probability are the two important factors in genetic algorithm. The adaptive genetic algorithm can improve the convergence performance of genetic algorithm, in which the crossover probability and mutation probability are adaptively designed with the changes of fitness value. We apply adaptive genetic algorithm into a function optimization problem. The numerical experiment represents that adaptive genetic algorithm improves the convergence speed and avoids local convergence.

Keywords: Genetic algorithm, Adaptive genetic algorithm, Function optimization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1658

Authors: Tsunwai Gary Yip

Abstract:

Phase locked loops in 10 Gb/s and faster data links are low phase noise devices. Characterization of their phase jitter transfer functions is difficult because the intrinsic noise of the PLLs is comparable to the phase noise of the reference clock signal. The problem is solved by using a linear model to account for the intrinsic noise. This study also introduces a novel technique for measuring the transfer function. It involves the use of the reference clock as a source of wideband excitation, in contrast to the commonly used sinusoidal excitations at discrete frequencies. The data reported here include the intrinsic noise of a PLL for 10 Gb/s links and the jitter transfer function of a PLL for 12.8 Gb/s links. The measured transfer function suggests that the PLL responded like a second order linear system to a low noise reference clock.

Keywords: Intrinsic phase noise, jitter in data link, PLL jitter transfer function, high speed clocking in electronic circuit

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1557

Authors: Ahmet Z. Ozcelik, Serkan Narli

Abstract:

In this study, two new classes of generalized homeomorphisms are introduced and shown that one of these classes has a group structure. Moreover, some properties of these two homeomorphisms are obtained.

Keywords: Generalized closed set, homeomorphism, gsghomeomorphism, sgs-homeomorphism.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1854

Authors: Chiou-Yng Lee, Wen-Yo Lee, Chieh-Tsai Wu, Cheng-Chen Yang

Abstract:

Shifted polynomial basis (SPB) is a variation of polynomial basis representation. SPB has potential for efficient bit level and digi -level implementations of multiplication over binary extension fields with subquadratic space complexity. For efficient implementation of pairing computation with large finite fields, this paper presents a new SPB multiplication algorithm based on Karatsuba schemes, and used that to derive a novel scalable multiplier architecture. Analytical results show that the proposed multiplier provides a trade-off between space and time complexities. Our proposed multiplier is modular, regular, and suitable for very large scale integration (VLSI) implementations. It involves less area complexity compared to the multipliers based on traditional decomposition methods. It is therefore, more suitable for efficient hardware implementation of pairing based cryptography and elliptic curve cryptography (ECC) in constraint driven applications.

Keywords: Digit-serial systolic multiplier, elliptic curve cryptography (ECC), Karatsuba algorithm (KA), shifted polynomial basis (SPB), pairing computation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2026

Authors: Sakshi Kausha, R.K Sharma

Abstract:

High speed networks provide realtime variable bit rate service with diversified traffic flow characteristics and quality requirements. The variable bit rate traffic has stringent delay and packet loss requirements. The burstiness of the correlated traffic makes dynamic buffer management highly desirable to satisfy the Quality of Service (QoS) requirements. This paper presents an algorithm for optimization of adaptive buffer allocation scheme for traffic based on loss of consecutive packets in data-stream and buffer occupancy level. Buffer is designed to allow the input traffic to be partitioned into different priority classes and based on the input traffic behavior it controls the threshold dynamically. This algorithm allows input packets to enter into buffer if its occupancy level is less than the threshold value for priority of that packet. The threshold is dynamically varied in runtime based on packet loss behavior. The simulation is run for two priority classes of the input traffic – realtime and non-realtime classes. The simulation results show that Adaptive Partial Buffer Sharing (ADPBS) has better performance than Static Partial Buffer Sharing (SPBS) and First In First Out (FIFO) queue under the same traffic conditions.

Keywords: Buffer Management, Consecutive packet loss, Quality-of-Service, Priority based packet discarding, partial buffersharing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1597

Authors: Bing Yu , Xingshi He

Abstract:

In this paper, Differential Evolution (DE) algorithm, a new promising evolutionary algorithm, is proposed to train Radial Basis Function (RBF) network related to automatic configuration of network architecture. Classification tasks on data sets: Iris, Wine, New-thyroid, and Glass are conducted to measure the performance of neural networks. Compared with a standard RBF training algorithm in Matlab neural network toolbox, DE achieves more rational architecture for RBF networks. The resulting networks hence obtain strong generalization abilities.

Keywords: differential evolution, neural network, Rbf function

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2003

Authors: Yoichi Hikino, Mutsuto Kawahara

Abstract:

The purpose of this study is to derive optimal shapes of a body located in viscous flows by the finite element method using the acoustic velocity and the four-step explicit scheme. The formulation is based on an optimal control theory in which a performance function of the fluid force is introduced. The performance function should be minimized satisfying the state equation. This problem can be transformed into the minimization problem without constraint conditions by using the adjoint equation with adjoint variables corresponding to the state equation. The performance function is defined by the drag and lift forces acting on the body. The weighted gradient method is applied as a minimization technique, the Galerkin finite element method is used as a spatial discretization and the four-step explicit scheme is used as a temporal discretization to solve the state equation and the adjoint equation. As the interpolation, the orthogonal basis bubble function for velocity and the linear function for pressure are employed. In case that the orthogonal basis bubble function is used, the mass matrix can be diagonalized without any artificial centralization. The shape optimization is performed by the presented method.

Keywords: Shape Optimization, Optimal Control Theory, Finite Element Method, Weighted Gradient Method, Fluid Force, Orthogonal Basis Bubble Function, Four-step Explicit Scheme, Acoustic Velocity.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1423

Authors: U.K. Saha, L.K. Arora

Abstract:

The multiindex Mittag-Leffler (M-L) function and the multiindex Dzrbashjan-Gelfond-Leontiev (D-G-L) differentiation and integration play a very pivotal role in the theory and applications of generalized fractional calculus. The object of this paper is to investigate the relations that exist between the Riemann-Liouville fractional calculus and multiindex Dzrbashjan-Gelfond-Leontiev differentiation and integration with multiindex Mittag-Leffler function.

Keywords: Multiindex Mittag-Leffler function, Multiindex Dzrbashjan-Gelfond-Leontiev differentiation and integration, Riemann-Liouville fractional integrals and derivatives.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1484

Authors: Byung-Joo Oh

Abstract:

This paper describes a method to improve the robustness of a face recognition system based on the combination of two compensating classifiers. The face images are preprocessed by the appearance-based statistical approaches such as Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA). LDA features of the face image are taken as the input of the Radial Basis Function Network (RBFN). The proposed approach has been tested on the ORL database. The experimental results show that the LDA+RBFN algorithm has achieved a recognition rate of 93.5%

Keywords: Face recognition, linear discriminant analysis, radial basis function network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2070

Authors: M. Govindarajan, R. M.Chandrasekaran

Abstract:

Text data mining is a process of exploratory data analysis. Classification maps data into predefined groups or classes. It is often referred to as supervised learning because the classes are determined before examining the data. This paper describes proposed radial basis function Classifier that performs comparative crossvalidation for existing radial basis function Classifier. The feasibility and the benefits of the proposed approach are demonstrated by means of data mining problem: direct Marketing. Direct marketing has become an important application field of data mining. Comparative Cross-validation involves estimation of accuracy by either stratified k-fold cross-validation or equivalent repeated random subsampling. While the proposed method may have high bias; its performance (accuracy estimation in our case) may be poor due to high variance. Thus the accuracy with proposed radial basis function Classifier was less than with the existing radial basis function Classifier. However there is smaller the improvement in runtime and larger improvement in precision and recall. In the proposed method Classification accuracy and prediction accuracy are determined where the prediction accuracy is comparatively high.

Keywords: Text Data Mining, Comparative Cross-validation, Radial Basis Function, runtime, accuracy.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1510

Authors: Ali Zaker, Zhi Chen

Abstract:

Due to the concerns about the depletion of fossil fuel sources and the deteriorating environment, the attempt to investigate the production of renewable energy will play a crucial role as a potential to alleviate the dependency on mineral fuels. One particular area of interest is generation of bio-oil through sewage sludge (SS) pyrolysis. SS can be a potential candidate in contrast to other types of biomasses due to its availability and low cost. However, the presence of high molecular weight hydrocarbons and oxygenated compounds in the SS bio-oil hinders some of its fuel applications. In this context, catalytic pyrolysis is another attainable route to upgrade bio-oil quality. Among different catalysts (i.e., zeolites) studied for SS pyrolysis, activated chars (AC) are eco-friendly alternatives. The beneficial features of AC derived from SS comprise the comparatively large surface area, porosity, enriched surface functional groups and presence of a high amount of metal species that can improve the catalytic activity. Hence, a sludge-based AC catalyst was fabricated in a single-step pyrolysis reaction with NaOH as the activation agent and was compared with HZSM5 zeolite in this study. The thermal decomposition and kinetics were invested via thermogravimetric analysis (TGA) for guidance and control of pyrolysis and catalytic pyrolysis and the design of the pyrolysis setup. The results indicated that the pyrolysis and catalytic pyrolysis contain four obvious stages and the main decomposition reaction occurred in the range of 200-600 °C. Coats-Redfern method was applied in the 2nd and 3rd devolatilization stages to estimate the reaction order and activation energy (E) from the mass loss data. The average activation energy (Em) values for the reaction orders n = 1, 2 and 3 were in the range of 6.67-20.37 kJ/mol for SS; 1.51-6.87 kJ/mol for HZSM5; and 2.29-9.17 kJ/mol for AC, respectively. According to the results, AC and HZSM5 both were able to improve the reaction rate of SS pyrolysis by abridging the Em value. Moreover, to generate and examine the effect of the catalysts on the quality of bio-oil, a fixed-bed pyrolysis system was designed and implemented. The composition analysis of the produced bio-oil was carried out via gas chromatography/mass spectrometry (GC/MS). The selected SS to catalyst ratios were 1:1, 2:1 and 4:1. The optimum ratio in terms of cracking the long-chain hydrocarbons and removing oxygen-containing compounds was 1:1 for both catalysts. The upgraded bio-oils with HZSM5 and AC were in the total range of C4-C17 with around 72% in the range of C4-C9. The bio-oil from pyrolysis of SS contained 49.27% oxygenated compounds while the presence of HZSM5 and AC dropped to 7.3% and 13.02%, respectively. Meanwhile, generation of value-added chemicals such as light aromatic compounds were significantly improved in the catalytic process. Furthermore, the fabricated AC catalyst was characterized by BET, SEM-EDX, FT-IR and TGA techniques. Overall, this research demonstrated that AC is an efficient catalyst in the pyrolysis of SS and can be used as a cost-competitive catalyst in contrast to HZSM5.

Keywords: Activated char, bio-oil, catalytic pyrolysis, HZSM5, sewage sludge.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 623

Authors: Satyendra Nath Mandal, J. Pal Choudhury, Dilip De, S. R. Bhadra Chaudhuri

Abstract:

The selection for plantation of a particular type of mustard plant depending on its productivity (pod yield) at the stage of maturity. The growth of mustard plant dependent on some parameters of that plant, these are shoot length, number of leaves, number of roots and roots length etc. As the plant is growing, some leaves may be fall down and some new leaves may come, so it can not gives the idea to develop the relationship with the seeds weight at mature stage of that plant. It is not possible to find the number of roots and root length of mustard plant at growing stage that will be harmful of this plant as roots goes deeper to deeper inside the land. Only the value of shoot length which increases in course of time can be measured at different time instances. Weather parameters are maximum and minimum humidity, rain fall, maximum and minimum temperature may effect the growth of the plant. The parameters of pollution, water, soil, distance and crop management may be dominant factors of growth of plant and its productivity. Considering all parameters, the growth of the plant is very uncertain, fuzzy environment can be considered for the prediction of shoot length at maturity of the plant. Fuzzification plays a greater role for fuzzification of data, which is based on certain membership functions. Here an effort has been made to fuzzify the original data based on gaussian function, triangular function, s-function, Trapezoidal and L –function. After that all fuzzified data are defuzzified to get normal form. Finally the error analysis (calculation of forecasting error and average error) indicates the membership function appropriate for fuzzification of data and use to predict the shoot length at maturity. The result is also verified using residual (Absolute Residual, Maximum of Absolute Residual, Mean Absolute Residual, Mean of Mean Absolute Residual, Median of Absolute Residual and Standard Deviation) analysis.

Keywords: Fuzzification, defuzzification, gaussian function, triangular function, trapezoidal function, s-function, , membership function, residual analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2274

Authors: Okezie A. Ihugba

Abstract:

The bounds testing ARDL (2, 2, 2, 2, 0) technique to cointegration was used in this study to investigate the effect of energy consumption and energy loss on Nigeria's manufacturing sector from 1981 to 2020. The model was created to determine the relationship between these three variables while also accounting for interactions with control variables such as inflation and commercial bank loans to the manufacturing sector. When the dependent variables are energy consumption and energy loss, the bound tests show that the variables of interest are bound together in the long run. Because electricity consumption is a critical factor in determining manufacturing value-added in Nigeria, some intriguing observations were made. According to the findings, the relationship between log of electricity consumption (LELC) and log of manufacturing value added (LMVA) is statistically significant. According to the findings, electricity consumption reduces manufacturing value-added. The target variable (energy loss) is statistically significant and has a positive sign. In Nigeria, a 1% reduction in energy loss increases manufacturing value-added by 36% in the first lag and 35% in the second. According to the study, the government should speed up the ongoing renovation of existing power plants across the country, as well as the construction of new gas-fired power plants. This will address a number of issues, including overpricing of electricity as a result of grid failure.

Keywords: ARDL, cointegration, Nigeria's manufacturing, electricity.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 294