Search results for: diagonal sparse matrices

Authors: Han Xiao, Xiaoyan Zhu

Abstract:

Margin-Based Principle has been proposed for a long time, it has been proved that this principle could reduce the structural risk and improve the performance in both theoretical and practical aspects. Meanwhile, feed-forward neural network is a traditional classifier, which is very hot at present with a deeper architecture. However, the training algorithm of feed-forward neural network is developed and generated from Widrow-Hoff Principle that means to minimize the squared error. In this paper, we propose a new training algorithm for feed-forward neural networks based on Margin-Based Principle, which could effectively promote the accuracy and generalization ability of neural network classifiers with less labelled samples and flexible network. We have conducted experiments on four UCI open datasets and achieved good results as expected. In conclusion, our model could handle more sparse labelled and more high-dimension dataset in a high accuracy while modification from old ANN method to our method is easy and almost free of work.

Keywords: Max-Margin Principle, Feed-Forward Neural Network, Classifier.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1695

Authors: Kjersti Engan, Karl Skretting, Jostein Herredsvela, Thor Ole Gulsrud

Abstract:

Texture classification is an important image processing task with a broad application range. Many different techniques for texture classification have been explored. Using sparse approximation as a feature extraction method for texture classification is a relatively new approach, and Skretting et al. recently presented the Frame Texture Classification Method (FTCM), showing very good results on classical texture images. As an extension of that work the FTCM is here tested on a real world application as detection of abnormalities in mammograms. Some extensions to the original FTCM that are useful in some applications are implemented; two different smoothing techniques and a vector augmentation technique. Both detection of microcalcifications (as a primary detection technique and as a last stage of a detection scheme), and soft tissue lesions in mammograms are explored. All the results are interesting, and especially the results using FTCM on regions of interest as the last stage in a detection scheme for microcalcifications are promising.

Keywords: detection, mammogram, texture classification, dictionary learning, FTCM

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1347

Authors: Mahmoud Miri, Abdolreza Zare, Hossein Abbas zadeh

Abstract:

The knee bracing steel frame (KBF) is a new kind of energy dissipating frame, which combines excellent ductility and lateral stiffness. In this framing system, a special form of diagonal brace connected to a knee element instead of beam-column joint, is investigated. Recently, a similar system was proposed and named as chevron knee bracing system (CKB) which in comparison with the former system has a better energy absorption characteristic and at the same time retains the elastic nature of the structures. Knee bracing can provide a stiffer bracing system but reduces the ductility of the steel frame. Chevron knee bracing can be employed to provide the desired ductility level for a design. In this article, relation between seismic performance and structural parameters of the two above mentioned systems are investigated and compared. Frames with similar dimensions but various heights in both systems are designed according to Iranian code of practice for seismic resistant design of building, and then based on a non-linear push over static analysis; the seismic parameters such as behavior factor and performance levels are compared.

Keywords: Seismic behaviour, ordinary knee bracing frame, Chevron knee brace, behaviour factor, performance level.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4211

Authors: Leehter Yao, Kuei-Song Weng, Cherng-Dir Huang

Abstract:

A fuzzy classifier using multiple ellipsoids approximating decision regions for classification is to be designed in this paper. An algorithm called Gustafson-Kessel algorithm (GKA) with an adaptive distance norm based on covariance matrices of prototype data points is adopted to learn the ellipsoids. GKA is able toadapt the distance norm to the underlying distribution of the prototypedata points except that the sizes of ellipsoids need to be determined a priori. To overcome GKA's inability to determine appropriate size ofellipsoid, the genetic algorithm (GA) is applied to learn the size ofellipsoid. With GA combined with GKA, it will be shown in this paper that the proposed method outperforms the benchmark algorithms as well as algorithms in the field.

Keywords: Ellipsoids, genetic algorithm, classification, fuzzyc-means (FCM)

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1655

Authors: O. M. Bamigbola, A. A. Ibrahim

Abstract:

Analysis of real life problems often results in linear systems of equations for which solutions are sought. The method to employ depends, to some extent, on the properties of the coefficient matrix. It is not always feasible to solve linear systems of equations by direct methods, as such the need to use an iterative method becomes imperative. Before an iterative method can be employed to solve a linear system of equations there must be a guaranty that the process of solution will converge. This guaranty, which must be determined apriori, involve the use of some criterion expressible in terms of the entries of the coefficient matrix. It is, therefore, logical that the convergence criterion should depend implicitly on the algebraic structure of such a method. However, in deference to this view is the practice of conducting convergence analysis for Gauss- Seidel iteration on a criterion formulated based on the algebraic structure of Jacobi iteration. To remedy this anomaly, the Gauss- Seidel iteration was studied for its algebraic structure and contrary to the usual assumption, it was discovered that some property of the iteration matrix of Gauss-Seidel method is only diagonally dominant in its first row while the other rows do not satisfy diagonal dominance. With the aid of this structure we herein fashion out an improved version of Gauss-Seidel iteration with the prospect of enhancing convergence and robustness of the method. A numerical section is included to demonstrate the validity of the theoretical results obtained for the improved Gauss-Seidel method.

Keywords: Linear system of equations, Gauss-Seidel iteration, algebraic structure, convergence.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2883

Authors: Youssef Khmou, Said Safi, Miloud Frikel

Abstract:

This paper treats different aspects of entropy measure in classical information theory and statistical quantum mechanics, it presents the possibility of extending the definition of Von Neumann entropy to image and array processing. In the first part, we generalize the quantum entropy using singular values of arbitrary rectangular matrices to measure the randomness and the quality of denoising operation, this new definition of entropy can be implemented to compare the performance analysis of filtering methods. In the second part, we apply the concept of pure state in quantum formalism to generalize the maximum entropy method for narrowband and farfield source localization problem. Several computer simulation results are illustrated to demonstrate the effectiveness of the proposed techniques.

Keywords: Von Neumann entropy, Filtering, array, DoA, Maximum Entropy Method.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2459

Authors: Changchun Shen, Shouming Zhong

Abstract:

This paper investigates the problem of absolute stability and robust stability of a class of Lur-e systems with neutral type and time-varying delays. By using Lyapunov direct method and linear matrix inequality technique, new delay-dependent stability criteria are obtained and formulated in terms of linear matrix inequalities (LMIs) which are easy to check the stability of the considered systems. To obtain less conservative stability conditions, an operator is defined to construct the Lyapunov functional. Also, the free weighting matrices approach combining a matrix inequality technique is used to reduce the entailed conservativeness. Numerical examples are given to indicate significant improvements over some existing results.

Keywords: Lur'e system, linear matrix inequalities, Lyapunov, stability.

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

Authors: Dimitri Perrin, Heather J. Ruskin, Martin Crane

Abstract:

We report on the development of a model to understand why the range of experience with respect to HIV infection is so diverse, especially with respect to the latency period. To investigate this, an agent-based approach is used to extract highlevel behaviour which cannot be described analytically from the set of interaction rules at the cellular level. A network of independent matrices mimics the chain of lymph nodes. Dealing with massively multi-agent systems requires major computational effort. However, parallelisation methods are a natural consequence and advantage of the multi-agent approach and, using the MPI library, are here implemented, tested and optimized. Our current focus is on the various implementations of the data transfer across the network. Three communications strategies are proposed and tested, showing that the most efficient approach is communication based on the natural lymph-network connectivity.

Keywords: HIV, Immune modelling, MPI, Parallelisation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1515

Authors: Halil Snopce, Ilir Spahiu

Abstract:

In this paper is investigated a possible optimization of some linear algebra problems which can be solved by parallel processing using the special arrays called systolic arrays. In this paper are used some special types of transformations for the designing of these arrays. We show the characteristics of these arrays. The main focus is on discussing the advantages of these arrays in parallel computation of matrix product, with special approach to the designing of systolic array for matrix multiplication. Multiplication of large matrices requires a lot of computational time and its complexity is O(n3 ). There are developed many algorithms (both sequential and parallel) with the purpose of minimizing the time of calculations. Systolic arrays are good suited for this purpose. In this paper we show that using an appropriate transformation implicates in finding more optimal arrays for doing the calculations of this type.

Keywords: Data dependences, matrix multiplication, systolicarray, transformation matrix.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1476

Authors: Adil AL-Rammahi

Abstract:

When we prefer to make the data secure from various attacks and fore integrity of data, we must encrypt the data before it is transmitted or stored. This paper introduces a new effective and lossless image encryption algorithm using a natural logarithmic function. The new algorithm encrypts an image through a three stage process. In the first stage, a reference natural logarithmic function is generated as the foundation for the encryption image. The image numeral matrix is then analyzed to five integer numbers, and then the numbers’ positions are transformed to matrices. The advantages of this method is useful for efficiently encrypting a variety of digital images, such as binary images, gray images, and RGB images without any quality loss. The principles of the presented scheme could be applied to provide complexity and then security for a variety of data systems such as image and others.

Keywords: Linear Systems, Image Encryption, Calculus.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2355

Authors: Naser Ahmadi Sani, Karim Solaimani, Lida Razaghnia, Jalal Zandi

Abstract:

In recent decades, rapid and incorrect changes in land-use have been associated with consequences such as natural resources degradation and environmental pollution. Detecting changes in land-use is one of the tools for natural resource management and assessment of changes in ecosystems. The target of this research is studying the land-use changes in Haraz basin with an area of 677000 hectares in a 15 years period (1996 to 2011) using LANDSAT data. Therefore, the quality of the images was first evaluated. Various enhancement methods for creating synthetic bonds were used in the analysis. Separate training sites were selected for each image. Then the images of each period were classified in 9 classes using supervised classification method and the maximum likelihood algorithm. Finally, the changes were extracted in GIS environment. The results showed that these changes are an alarm for the HARAZ basin status in future. The reason is that 27% of the area has been changed, which is related to changing the range lands to bare land and dry farming and also changing the dense forest to sparse forest, horticulture, farming land and residential area.

Keywords: HARAZ Basin, Change Detection, Land-use, Satellite Data.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2271

Authors: Meng Hu, Lili Wang

Abstract:

In this paper, based on linear matrix inequality (LMI), by using Lyapunov functional theory, the exponential stability criterion is obtained for a class of uncertain Takagi-Sugeno fuzzy Hopfield neural networks (TSFHNNs) with time delays. Here we choose a generalized Lyapunov functional and introduce a parameterized model transformation with free weighting matrices to it, these techniques lead to generalized and less conservative stability condition that guarantee the wide stability region. Finally, an example is given to illustrate our results by using MATLAB LMI toolbox.

Keywords: Hopfield neural network, linear matrix inequality, exponential stability, time delay, T-S fuzzy model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1467

Authors: Ma Myint Myint Aye

Abstract:

Any rotation of a 3-dimensional object can be performed by three consecutive rotations over Euler angles. Intrinsic rotations produce the same result as extrinsic rotations in transformation. Euler rotations are the movement obtained by changing one of the Euler angles while leaving the other two constant. These Euler rotations are applied in a simple two-axis gimbals set mounted on an automotives. The values of Euler angles are [π/4, π/4, π/4] radians inside the angles ranges for a given coordinate system and these actual orientations can be directly measured from these gimbals set of moving automotives but it can occur the gimbals lock in application at [π/2.24, 0, 0] radians. In order to avoid gimbals lock, the values of quaternion must be [π/4.8, π/8.2, 0, π/4.8] radians. The four-gimbals set can eliminate gimbals lock.

Keywords: Intrinsic rotations, extrinsic rotations, Euler rotations, rotation matrices, quaternion.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3403

Authors: Abdul H, Jamil A, Imran U

Abstract:

Conflicts identification among non-functional requirements is often identified intuitively which impairs conflict analysis practices. This paper proposes a new model to identify conflicts among non-functional requirements. The proposed model uses the matrix mechanism to identify the quality based conflicts among non-functional requirements. The potential conflicts are identified through the mapping of low level conflicting quality attributes to low level functionalities using the matrices. The proposed model achieves the identification of conflicts among product and process requirements, identifies false conflicts, decreases the documentation overhead, and maintains transparency of identified conflicts. The attributes are not concomitantly taken into account by current models in practice.

Keywords: Conflict Identification, Matrix Maps, Non-functional Requirements, Requirements Analysis, Software Engineering

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2513

Authors: Francesco Maiorana

Abstract:

In this paper a one-dimension Self Organizing Map algorithm (SOM) to perform feature selection is presented. The algorithm is based on a first classification of the input dataset on a similarity space. From this classification for each class a set of positive and negative features is computed. This set of features is selected as result of the procedure. The procedure is evaluated on an in-house dataset from a Knowledge Discovery from Text (KDT) application and on a set of publicly available datasets used in international feature selection competitions. These datasets come from KDT applications, drug discovery as well as other applications. The knowledge of the correct classification available for the training and validation datasets is used to optimize the parameters for positive and negative feature extractions. The process becomes feasible for large and sparse datasets, as the ones obtained in KDT applications, by using both compression techniques to store the similarity matrix and speed up techniques of the Kohonen algorithm that take advantage of the sparsity of the input matrix. These improvements make it feasible, by using the grid, the application of the methodology to massive datasets.

Keywords: Clustering algorithm, Data mining, Feature selection, Grid, Kohonen Self Organizing Map.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3006

Authors: Hsian Ming Goo

Abstract:

The paper concerns a special approximate algorithm of the square root of the specific positive integer, which is built by the use of the property of positive integer solution of the Pell’s equation, together with using some elementary theorems of matrices, and then takes it to compare with general used the Newton’s method and give a practical numerical example and error analysis; it is unexpected to find its special property: the significant figure of the approximation value of the square root of positive integer will increase one digit by one. It is well useful in some occasions.

Keywords: Special approximate algorithm, square root, Pell’s equation, Newton’s method, error analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2756

Authors: Ahmed Elrewainy

Abstract:

Mixing in the hyperspectral imaging occurs due to the low spatial resolutions of the used cameras. The existing pure materials “endmembers” in the scene share the spectra pixels with different amounts called “abundances”. Unmixing of the data cube is an important task to know the present endmembers in the cube for the analysis of these images. Unsupervised unmixing is done with no information about the given data cube. Sparsity is one of the recent approaches used in the source recovery or unmixing techniques. The l₁-norm optimization problem “basis pursuit” could be used as a sparsity-based approach to solve this unmixing problem where the endmembers is assumed to be sparse in an appropriate domain known as dictionary. This optimization problem is solved using proximal method “iterative thresholding”. The l₁-norm basis pursuit optimization problem as a sparsity-based unmixing technique was used to unmix real and synthetic hyperspectral data cubes.

Keywords: Basis pursuit, blind source separation, hyperspectral imaging, spectral unmixing, wavelets.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 799

Authors: Ling Zhang, Feng Liu

Abstract:

A matrix is called a ray pattern matrix if its entries are either 0 or a ray in complex plane which originates from 0. A ray pattern A of order n is called spectrally arbitrary if the complex matrices in the ray pattern class of A give rise to all possible nth degree complex polynomial. Otherwise, it is said to be spectrally non-arbitrary ray pattern. We call that a spectrally arbitrary ray pattern A of order n is minimally spectrally arbitrary if any nonzero entry of A is replaced, then A is not spectrally arbitrary. In this paper, we find that is not spectrally arbitrary when n equals to 4 for any θ which is greater than or equal to 0 and less than or equal to n. In this article, we give several ray patterns A(θ) of order n that are not spectrally arbitrary for some θ which is greater than or equal to 0 and less than or equal to n. by using the nilpotent-Jacobi method. One example is given in our paper.

Keywords: Spectrally arbitrary, Nilpotent matrix, Ray patterns, sign patterns.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 565

Authors: F. Javier Benitez, Carolina Garcia, Juan Luis Acero, Francisco J. Real

Abstract:

Four phenylurea herbicides (isoproturon, chlortoluron, diuron and linuron) were dissolved in different water matrices in order to study their chemical degradation by using UV radiation, ozone and some advanced oxidation processes (UV/H2O2, O3/H2O2, Fenton reagent and the photo- Fenton system). The waters used were: ultra-pure water, a commercial mineral water, a groundwater and a surface water taken from a reservoir. Elimination levels were established for each herbicide and for several global quality parameters, and a kinetic study was performed in order to determine basic kinetic parameters of each reaction between the target phenylureas and these oxidizing systems.

Keywords: Phenylurea herbicides, UV radiation; Ozone, Fenton reagent, Hydroxyl radicals, Rate constants, Quantum yields

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1891

Authors: Properties, Approximation Distribution Reductions in Multigranulation Rough Set Model

Abstract:

Some properties of approximation sets are studied in multi-granulation optimist model in rough set theory using maximal compatible classes. The relationships between or among lower and upper approximations in single and multiple granulation are compared and discussed. Through designing Boolean functions and discernibility matrices in incomplete information systems, the lower and upper approximation sets and reduction in multi-granulation environments can be found. By using examples, the correctness of computation approach is consolidated. The related conclusions obtained are suitable for further investigating in multiple granulation RSM.

Keywords: Incomplete information system, maximal compatible class, multi-granulation rough set model, reduction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 815

Authors: Fatima Setti, Ezziane Karim, Setti Bakhti, Negadi Kheira

Abstract:

The objective of this study is to present and to analyze the feasibility of using steel fibers as reinforcement in the cementations matrix to minimize the effect of free shrinkage which is a major cause of cracks that have can observe on concrete structures, also to improve the mechanical resistances of this concrete reinforced. The experimental study was performed on specimens with geometric characteristics adapted to the testing. The tests of shrinkage apply on prismatic specimens, equipped with rods fixed to the ends with different dosages of fibers, it should be noted that the fibers used are hooked end of 50mm length and 67 slenderness. The results show that the compressive strength and flexural strength increases as the degree of incorporation of fibbers increases. And the shrinkage deformations are generally less important for fibers-reinforced concrete to those appearing in the concrete without fibers.

Keywords: Concrete, Steel fibers, Compression, Flexural, Deformation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1642

Authors: Samsiah Abdul Razak, Daud Mohamad

Abstract:

Molodstov-s soft sets theory was originally proposed as general mathematical tool for dealing with uncertainty problems. The matrix form has been introduced in soft set and some of its properties have been discussed. However, the formulation of soft matrix in group decision making problem only with equal importance weights of criteria, which does not show the true opinion of decision maker on each criteria. The aim of this paper is to propose a method for solving group decision making problem incorporating the importance of criteria by using soft matrices in a more objective manner. The weight of each criterion is calculated by using the Analytic Hierarchy Process (AHP) method. An example of house selection process is given to illustrate the effectiveness of the proposed method.

Keywords: Soft set, Soft Matrix, Soft max-min decision making (SMmDM), Analytic hierarchy process (AHP)

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1858

Authors: Yun Jong Choi, Nam Woong, PooGyeon Park

Abstract:

Variable Structure Control (VSC) is one of the most useful tools handling the practical system with uncertainties and disturbances. Up to now, unfortunately, not enough studies on the input-saturated system with linear-growth-bound disturbances via VSC have been presented. Therefore, this paper proposes an asymp¬totic stability condition for the system via VSC. The designed VSC controller consists of two control parts. The linear control part plays a role in stabilizing the system, and simultaneously, the nonlinear control part in rejecting the linear-growth-bound disturbances perfectly. All conditions derived in this paper are expressed with Linear Matrices Inequalities (LMIs), which can be easily solved with an LMI toolbox in MATLAB.

Keywords: Input saturation, linear-growth bounded disturbances, linear matrix inequality (LMI), variable structure control

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1593

Authors: Alireza Gholami, Amir H. D. Markazi

Abstract:

In this paper, an observer-based direct adaptive fuzzy sliding mode (OAFSM) algorithm is proposed. In the proposed algorithm, the zero-input dynamics of the plant could be unknown. The input connection matrix is used to combine the sliding surfaces of individual subsystems, and an adaptive fuzzy algorithm is used to estimate an equivalent sliding mode control input directly. The fuzzy membership functions, which were determined by time consuming try and error processes in previous works, are adjusted by adaptive algorithms. The other advantage of the proposed controller is that the input gain matrix is not limited to be diagonal, i.e. the plant could be over/under actuated provided that controllability and observability are preserved. An observer is constructed to directly estimate the state tracking error, and the nonlinear part of the observer is constructed by an adaptive fuzzy algorithm. The main advantage of the proposed observer is that, the measured outputs is not limited to the first entry of a canonical-form state vector. The closed-loop stability of the proposed method is proved using a Lyapunov-based approach. The proposed method is applied numerically on a multi-link robot manipulator, which verifies the performance of the closed-loop control. Moreover, the performance of the proposed algorithm is compared with some conventional control algorithms.

Keywords: Adaptive algorithm, fuzzy systems, membership functions, observer.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 729

Authors: Ayman Abd-Elhamed, Sayed Mahmoud

Abstract:

The present research work investigates the seismic response of reinforced concrete (RC) frame building considering the effect of modeling masonry infill (MI) walls. The seismic behavior of a residential 6-storey RC frame building, considering and ignoring the effect of masonry, is numerically investigated using response spectrum (RS) analysis. The considered herein building is designed as a moment resisting frame (MRF) system following the Egyptian code (EC) requirements. Two developed models in terms of bare frame and infill walls frame are used in the study. Equivalent diagonal strut methodology is used to represent the behavior of infill walls, whilst the well-known software package ETABS is used for implementing all frame models and performing the analysis. The results of the numerical simulations such as base shear, displacements, and internal forces for the bare frame as well as the infill wall frame are presented in a comparative way. The results of the study indicate that the interaction between infill walls and frames significantly change the responses of buildings during earthquakes compared to the results of bare frame building model. Specifically, the seismic analysis of RC bare frame structure leads to underestimation of base shear and consequently damage or even collapse of buildings may occur under strong shakings. On the other hand, considering infill walls significantly decrease the peak floor displacements and drifts in both X and Y-directions.

Keywords: Masonry infill, bare frame, response spectrum, seismic response.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3473

Authors: J. Ruiz-Pinales, J. J. Acosta-Reyes, A. Salazar-Garibay, R. Jaime-Rivas

Abstract:

In this paper, we present a new method for incorporating global shift invariance in support vector machines. Unlike other approaches which incorporate a feature extraction stage, we first scale the image and then classify it by using the modified support vector machines classifier. Shift invariance is achieved by replacing dot products between patterns used by the SVM classifier with the maximum cross-correlation value between them. Unlike the normal approach, in which the patterns are treated as vectors, in our approach the patterns are treated as matrices (or images). Crosscorrelation is computed by using computationally efficient techniques such as the fast Fourier transform. The method has been tested on the ORL face database. The tests indicate that this method can improve the recognition rate of an SVM classifier.

Keywords: Face recognition, support vector machines, shiftinvariance, image registration.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1700

Authors: Liping Jing, Michael K. Ng, Xinhua Yang, Joshua Zhexue Huang

Abstract:

This paper presents a text clustering system developed based on a k-means type subspace clustering algorithm to cluster large, high dimensional and sparse text data. In this algorithm, a new step is added in the k-means clustering process to automatically calculate the weights of keywords in each cluster so that the important words of a cluster can be identified by the weight values. For understanding and interpretation of clustering results, a few keywords that can best represent the semantic topic are extracted from each cluster. Two methods are used to extract the representative words. The candidate words are first selected according to their weights calculated by our new algorithm. Then, the candidates are fed to the WordNet to identify the set of noun words and consolidate the synonymy and hyponymy words. Experimental results have shown that the clustering algorithm is superior to the other subspace clustering algorithms, such as PROCLUS and HARP and kmeans type algorithm, e.g., Bisecting-KMeans. Furthermore, the word extraction method is effective in selection of the words to represent the topics of the clusters.

Keywords: Subspace Clustering, Text Mining, Feature Weighting, Cluster Interpretation, Ontology

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2414

Authors: G. Beulah Gnana Ananthi, A. Jaffer Sathick, M. Abirami

Abstract:

Fibre reinforced concrete (FRC) has been widely used in industrial pavements and non-structural elements such as pipes, culverts, tunnels, and precast elements. The strengthening effect of fibres in the concrete matrix is achieved primarily due to the bridging effect of fibres at the crack interfaces. The workability of the concrete was reduced on addition of high percentages of steel fibres. The optimum percentage of addition of steel fibres varies with its aspect ratio. For this study, 1% addition of steel has resulted to be the optimum percentage for both Hooked and Crimped Steel Fibres and was added to the beam specimens. The fibres restrain efficiently the cracks and take up residual stresses beyond the cracking. In this sense, diagonal cracks are effectively stitched up by fibres crossing it. The failure of beams within the shear failure range changed from shear to flexure in the presence of sufficient steel fibre quantity. The shear strength is increased with the addition of steel fibres and had exceeded the enhancement obtained with the transverse reinforcement. However, such increase is not directly in proportion with the quantity of fibres used. Considering all the clarification made in the present experimental investigation, it is concluded that 1% of crimped steel fibres with an aspect ratio of 50 is the best type of steel fibres for replacement of transverse stirrups in high strength concrete beams when compared to the steel fibres with hooked ends.

Keywords: Fibre reinforced concrete, steel fibre, shear strength, crack pattern.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 763

Authors: Nahid Ghasemi, Mohammad Goodarzi, Morteza Khosravi

Abstract:

Simultaneous determination of multicomponents of phenol, resorcinol and catechol with a chemometric technique a PCranking artificial neural network (PCranking-ANN) algorithm is reported in this study. Based on the data correlation coefficient method, 3 representative PCs are selected from the scores of original UV spectral data (35 PCs) as the original input patterns for ANN to build a neural network model. The results obtained by iterating 8000 .The RMSEP for phenol, resorcinol and catechol with PCranking- ANN were 0.6680, 0.0766 and 0.1033, respectively. Calibration matrices were 0.50-21.0, 0.50-15.1 and 0.50-20.0 μg ml-1 for phenol, resorcinol and catechol, respectively. The proposed method was successfully applied for the determination of phenol, resorcinol and catechol in synthetic and water samples.

Keywords: Phenol, Resorcinol, Catechol, Principal componentrankingArtificial Neural Network, Chemometrics.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1377

Authors: Wolfram Irsa, Lorenz Boruch

Abstract:

Innovative solutions in additive manufacturing applying material extrusion for functional parts necessitates innovative filaments with persistent quality. Uniform homogeneity and consistent dispersion of particles embedded in filaments generally require multiple cycles of extrusion or well-prepared primal matter by injection molding, kneader machines, or mixing equipment. These technologies commit to dedicated equipment that are rarely at disposal in production laboratories unfamiliar with research in polymer materials. This stands in contrast to laboratories which investigate on complex material topics and technology science to leverage on the potential of 3-D printing. Consequently, scientific studies in labs are often constrained to compositions and concentrations of fillers offered from the market. Therefore, we present a prototypal laboratory methodology scalable to tailored primal matter for extruding ceramic composite filaments with fused filament fabrication (FFF) technology. A desktop single-screw extruder serves as core device for the experiments. Custom-made filament encapsulates the ceramic fillers and serves with polylactide (PLA), which is a thermoplastic polyester, as primal matter and is processed in the melting area of the extruder preserving the defined concentration of the fillers. Validated results demonstrate that this approach enables continuously produced and uniform composite filaments with consistent homogeneity. It is 3-D printable with controllable dimensions, which is a prerequisite for any scalable application. Additionally, digital microscopy confirms steady dispersion of the ceramic particles in the composite filament. This permits a 2D reconstruction of the planar distribution of the embedded ceramic particles in the PLA matrices. The innovation of the introduced method lies in the smart simplicity of preparing the composite primal matter. It circumvents the inconvenience of numerous extrusion operations and expensive laboratory equipment. Nevertheless, it delivers consistent filaments of controlled, predictable, and reproducible filler concentration, which is the prerequisite for any industrial application. The introduced prototypal laboratory methodology seems capable for other polymer matrices and suitable to further utilitarian particle types, beyond and above of ceramic fillers. This inaugurates a roadmap for supplementary laboratory development of peculiar composite filaments, providing value for industries and societies. This low-threshold entry of sophisticated preparation of composite filaments - enabling businesses creating their own dedicated filaments - will support the mutual efforts for establishing 3D printing to new functional devices.

Keywords: Additive manufacturing, ceramic composites, complex filament, industrial application.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 315