Abstract: Surface roughness (Ra) is one of the most important requirements in machining process. In order to obtain better surface roughness, the proper setting of cutting parameters is crucial before the process take place. This research presents the development of mathematical model for surface roughness prediction before milling process in order to evaluate the fitness of machining parameters; spindle speed, feed rate and depth of cut. 84 samples were run in this study by using FANUC CNC Milling α-Τ14ιE. Those samples were randomly divided into two data sets- the training sets (m=60) and testing sets(m=24). ANOVA analysis showed that at least one of the population regression coefficients was not zero. Multiple Regression Method was used to determine the correlation between a criterion variable and a combination of predictor variables. It was established that the surface roughness is most influenced by the feed rate. By using Multiple Regression Method equation, the average percentage deviation of the testing set was 9.8% and 9.7% for training data set. This showed that the statistical model could predict the surface roughness with about 90.2% accuracy of the testing data set and 90.3% accuracy of the training data set.
Abstract: This paper presents a novel template-based method to
detect objects of interest from real images by shape matching. To
locate a target object that has a similar shape to a given template
boundary, the proposed method integrates three components: contour
grouping, partial shape matching, and boundary verification. In the
first component, low-level image features, including edges and
corners, are grouped into a set of perceptually salient closed contours
using an extended ratio-contour algorithm. In the second component,
we develop a partial shape matching algorithm to identify the
fractions of detected contours that partly match given template
boundaries. Specifically, we represent template boundaries and
detected contours using landmarks, and apply a greedy algorithm to
search the matched landmark subsequences. For each matched
fraction between a template and a detected contour, we estimate an
affine transform that transforms the whole template into a hypothetic
boundary. In the third component, we provide an efficient algorithm
based on oriented edge lists to determine the target boundary from
the hypothetic boundaries by checking each of them against image
edges. We evaluate the proposed method on recognizing and
localizing 12 template leaves in a data set of real images with clutter
back-grounds, illumination variations, occlusions, and image noises.
The experiments demonstrate the high performance of our proposed
method1.
Abstract: Study of soil properties like field capacity (F.C.) and permanent wilting point (P.W.P.) play important roles in study of soil moisture retention curve. Although these parameters can be measured directly, their measurement is difficult and expensive. Pedotransfer functions (PTFs) provide an alternative by estimating soil parameters from more readily available soil data. In this investigation, 70 soil samples were collected from different horizons of 15 soil profiles located in the Ziaran region, Qazvin province, Iran. The data set was divided into two subsets for calibration (80%) and testing (20%) of the models and their normality were tested by Kolmogorov-Smirnov method. Both multivariate regression and artificial neural network (ANN) techniques were employed to develop the appropriate PTFs for predicting soil parameters using easily measurable characteristics of clay, silt, O.C, S.P, B.D and CaCO3. The performance of the multivariate regression and ANN models was evaluated using an independent test data set. In order to evaluate the models, root mean square error (RMSE) and R2 were used. The comparison of RSME for two mentioned models showed that the ANN model gives better estimates of F.C and P.W.P than the multivariate regression model. The value of RMSE and R2 derived by ANN model for F.C and P.W.P were (2.35, 0.77) and (2.83, 0.72), respectively. The corresponding values for multivariate regression model were (4.46, 0.68) and (5.21, 0.64), respectively. Results showed that ANN with five neurons in hidden layer had better performance in predicting soil properties than multivariate regression.
Abstract: Phylogenetic tree is a graphical representation of the
evolutionary relationship among three or more genes or organisms.
These trees show relatedness of data sets, species or genes
divergence time and nature of their common ancestors. Quality of a
phylogenetic tree requires parsimony criterion. Various approaches
have been proposed for constructing most parsimonious trees. This
paper is concerned about calculating and optimizing the changes of
state that are needed called Small Parsimony Algorithms. This paper
has proposed enhanced small parsimony algorithm to give better
score based on number of evolutionary changes needed to produce
the observed sequence changes tree and also give the ancestor of the
given input.
Abstract: Due to the increasing and varying risks that economic units face with, derivative instruments gain substantial importance, and trading volumes of derivatives have reached very significant level. Parallel with these high trading volumes, researchers have developed many different models. Some are parametric, some are nonparametric. In this study, the aim is to analyse the success of artificial neural network in pricing of options with S&P 100 index options data. Generally, the previous studies cover the data of European type call options. This study includes not only European call option but also American call and put options and European put options. Three data sets are used to perform three different ANN models. One only includes data that are directly observed from the economic environment, i.e. strike price, spot price, interest rate, maturity, type of the contract. The others include an extra input that is not an observable data but a parameter, i.e. volatility. With these detail data, the performance of ANN in put/call dimension, American/European dimension, moneyness dimension is analyzed and whether the contribution of the volatility in neural network analysis make improvement in prediction performance or not is examined. The most striking results revealed by the study is that ANN shows better performance when pricing call options compared to put options; and the use of volatility parameter as an input does not improve the performance.
Abstract: This paper is concerned with motion recognition based fuzzy WP(Wavelet Packet) feature extraction approach from Vicon physical data sets. For this purpose, we use an efficient fuzzy mutual-information-based WP transform for feature extraction. This method estimates the required mutual information using a novel approach based on fuzzy membership function. The physical action data set includes 10 normal and 10 aggressive physical actions that measure the human activity. The data have been collected from 10 subjects using the Vicon 3D tracker. The experiments consist of running, seating, and walking as physical activity motion among various activities. The experimental results revealed that the presented feature extraction approach showed good recognition performance.
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.
Abstract: Self-organizing map (SOM) is a well known data
reduction technique used in data mining. It can reveal structure in
data sets through data visualization that is otherwise hard to detect
from raw data alone. However, interpretation through visual
inspection is prone to errors and can be very tedious. There are
several techniques for the automatic detection of clusters of code
vectors found by SOM, but they generally do not take into account
the distribution of code vectors; this may lead to unsatisfactory
clustering and poor definition of cluster boundaries, particularly
where the density of data points is low. In this paper, we propose the
use of an adaptive heuristic particle swarm optimization (PSO)
algorithm for finding cluster boundaries directly from the code
vectors obtained from SOM. The application of our method to
several standard data sets demonstrates its feasibility. PSO algorithm
utilizes a so-called U-matrix of SOM to determine cluster boundaries;
the results of this novel automatic method compare very favorably to
boundary detection through traditional algorithms namely k-means
and hierarchical based approach which are normally used to interpret
the output of SOM.
Abstract: Text Mining is around applying knowledge discovery techniques to unstructured text is termed knowledge discovery in text (KDT), or Text data mining or Text Mining. In Neural Network that address classification problems, training set, testing set, learning rate are considered as key tasks. That is collection of input/output patterns that are used to train the network and used to assess the network performance, set the rate of adjustments. This paper describes a proposed back propagation neural net classifier that performs cross validation for original Neural Network. In order to reduce the optimization of classification accuracy, training time. The feasibility the benefits of the proposed approach are demonstrated by means of five data sets like contact-lenses, cpu, weather symbolic, Weather, labor-nega-data. It is shown that , compared to exiting neural network, the training time is reduced by more than 10 times faster when the dataset is larger than CPU or the network has many hidden units while accuracy ('percent correct') was the same for all datasets but contact-lences, which is the only one with missing attributes. For contact-lences the accuracy with Proposed Neural Network was in average around 0.3 % less than with the original Neural Network. This algorithm is independent of specify data sets so that many ideas and solutions can be transferred to other classifier paradigms.
Abstract: Multiple sequence alignment is a fundamental part in
many bioinformatics applications such as phylogenetic analysis.
Many alignment methods have been proposed. Each method gives a
different result for the same data set, and consequently generates a
different phylogenetic tree. Hence, the chosen alignment method
affects the resulting tree. However in the literature, there is no
evaluation of multiple alignment methods based on the comparison of
their phylogenetic trees. This work evaluates the following eight
aligners: ClustalX, T-Coffee, SAGA, MUSCLE, MAFFT, DIALIGN,
ProbCons and Align-m, based on their phylogenetic trees (test trees)
produced on a given data set. The Neighbor-Joining method is used
to estimate trees. Three criteria, namely, the dNNI, the dRF and the
Id_Tree are established to test the ability of different alignment
methods to produce closer test tree compared to the reference one
(true tree). Results show that the method which produces the most
accurate alignment gives the nearest test tree to the reference tree.
MUSCLE outperforms all aligners with respect to the three criteria
and for all datasets, performing particularly better when sequence
identities are within 10-20%. It is followed by T-Coffee at lower
sequence identity (30%), trees scores of all methods
become similar.
Abstract: In the last decades, a number of robust fuzzy clustering algorithms have been proposed to partition data sets affected by noise and outliers. Robust fuzzy C-means (robust-FCM) is certainly one of the most known among these algorithms. In robust-FCM, noise is modeled as a separate cluster and is characterized by a prototype that has a constant distance δ from all data points. Distance δ determines the boundary of the noise cluster and therefore is a critical parameter of the algorithm. Though some approaches have been proposed to automatically determine the most suitable δ for the specific application, up to today an efficient and fully satisfactory solution does not exist. The aim of this paper is to propose a novel method to compute the optimal δ based on the analysis of the distribution of the percentage of objects assigned to the noise cluster in repeated executions of the robust-FCM with decreasing values of δ . The extremely encouraging results obtained on some data sets found in the literature are shown and discussed.
Abstract: Embedded systems need to respect stringent real
time constraints. Various hardware components included in such
systems such as cache memories exhibit variability and therefore
affect execution time. Indeed, a cache memory access from an
embedded microprocessor might result in a cache hit where the
data is available or a cache miss and the data need to be fetched
with an additional delay from an external memory. It is therefore
highly desirable to predict future memory accesses during
execution in order to appropriately prefetch data without incurring
delays. In this paper, we evaluate the potential of several artificial
neural networks for the prediction of instruction memory
addresses. Neural network have the potential to tackle the nonlinear
behavior observed in memory accesses during program
execution and their demonstrated numerous hardware
implementation emphasize this choice over traditional forecasting
techniques for their inclusion in embedded systems. However,
embedded applications execute millions of instructions and
therefore millions of addresses to be predicted. This very
challenging problem of neural network based prediction of large
time series is approached in this paper by evaluating various neural
network architectures based on the recurrent neural network
paradigm with pre-processing based on the Self Organizing Map
(SOM) classification technique.
Abstract: This paper reports work done to improve the modeling of complex processes when only small experimental data sets are available. Neural networks are used to capture the nonlinear underlying phenomena contained in the data set and to partly eliminate the burden of having to specify completely the structure of the model. Two different types of neural networks were used for the application of Pulping of Sugar Maple problem. A three layer feed forward neural networks, using the Preconditioned Conjugate Gradient (PCG) methods were used in this investigation. Preconditioning is a method to improve convergence by lowering the condition number and increasing the eigenvalues clustering. The idea is to solve the modified problem where M is a positive-definite preconditioner that is closely related to A. We mainly focused on Preconditioned Conjugate Gradient- based training methods which originated from optimization theory, namely Preconditioned Conjugate Gradient with Fletcher-Reeves Update (PCGF), Preconditioned Conjugate Gradient with Polak-Ribiere Update (PCGP) and Preconditioned Conjugate Gradient with Powell-Beale Restarts (PCGB). The behavior of the PCG methods in the simulations proved to be robust against phenomenon such as oscillations due to large step size.
Abstract: The network traffic data provided for the design of
intrusion detection always are large with ineffective information and
enclose limited and ambiguous information about users- activities.
We study the problems and propose a two phases approach in our
intrusion detection design. In the first phase, we develop a
correlation-based feature selection algorithm to remove the worthless
information from the original high dimensional database. Next, we
design an intrusion detection method to solve the problems of
uncertainty caused by limited and ambiguous information. In the
experiments, we choose six UCI databases and DARPA KDD99
intrusion detection data set as our evaluation tools. Empirical studies
indicate that our feature selection algorithm is capable of reducing the
size of data set. Our intrusion detection method achieves a better
performance than those of participating intrusion detectors.
Abstract: The zero truncated model is usually used in modeling
count data without zero. It is the opposite of zero inflated model.
Zero truncated Poisson and zero truncated negative binomial models
are discussed and used by some researchers in analyzing the
abundance of rare species and hospital stay. Zero truncated models
are used as the base in developing hurdle models. In this study, we
developed a new model, the zero truncated strict arcsine model,
which can be used as an alternative model in modeling count data
without zero and with extra variation. Two simulated and one real
life data sets are used and fitted into this developed model. The
results show that the model provides a good fit to the data. Maximum
likelihood estimation method is used in estimating the parameters.
Abstract: Most scientific programs have large input and output
data sets that require out-of-core programming or use virtual memory
management (VMM). Out-of-core programming is very error-prone
and tedious; as a result, it is generally avoided. However, in many
instance, VMM is not an effective approach because it often results
in substantial performance reduction. In contrast, compiler driven I/O
management will allow a program-s data sets to be retrieved in parts,
called blocks or tiles. Comanche (COmpiler MANaged caCHE) is a
compiler combined with a user level runtime system that can be used
to replace standard VMM for out-of-core programs. We describe
Comanche and demonstrate on a number of representative problems
that it substantially out-performs VMM. Significantly our system
does not require any special services from the operating system and
does not require modification of the operating system kernel.
Abstract: Leo Breimans Random Forests (RF) is a recent
development in tree based classifiers and quickly proven to be one of
the most important algorithms in the machine learning literature. It
has shown robust and improved results of classifications on standard
data sets. Ensemble learning algorithms such as AdaBoost and
Bagging have been in active research and shown improvements in
classification results for several benchmarking data sets with mainly
decision trees as their base classifiers. In this paper we experiment to
apply these Meta learning techniques to the random forests. We
experiment the working of the ensembles of random forests on the
standard data sets available in UCI data sets. We compare the
original random forest algorithm with their ensemble counterparts
and discuss the results.
Abstract: A genetic algorithm (GA) based feature subset
selection algorithm is proposed in which the correlation structure of
the features is exploited. The subset of features is validated according
to the classification performance. Features derived from the
continuous wavelet transform are potentially strongly correlated.
GA-s that do not take the correlation structure of features into
account are inefficient. The proposed algorithm forms clusters of
correlated features and searches for a good candidate set of clusters.
Secondly a search within the clusters is performed. Different
simulations of the algorithm on a real-case data set with strong
correlations between features show the increased classification
performance. Comparison is performed with a standard GA without
use of the correlation structure.
Abstract: Research into the problem of classification of sonar signals has been taken up as a challenging task for the neural networks. This paper investigates the design of an optimal classifier using a Multi layer Perceptron Neural Network (MLP NN) and Support Vector Machines (SVM). Results obtained using sonar data sets suggest that SVM classifier perform well in comparison with well-known MLP NN classifier. An average classification accuracy of 91.974% is achieved with SVM classifier and 90.3609% with MLP NN classifier, on the test instances. The area under the Receiver Operating Characteristics (ROC) curve for the proposed SVM classifier on test data set is found as 0.981183, which is very close to unity and this clearly confirms the excellent quality of the proposed classifier. The SVM classifier employed in this paper is implemented using kernel Adatron algorithm is seen to be robust and relatively insensitive to the parameter initialization in comparison to MLP NN.
Abstract: This research work takes a different approach in
the discussion of urban form impacts on transport planning and
auto dependency. Concentrated density represented by effective
density explains auto dependency better than the conventional
density and it is proved to be a realistic density representative for
the urban transportation analysis. Model analysis reveals that
effective density is influenced by the shopping accessibility
index as well as job density factor. It is also combined with the
job access variable to classify four levels of Transport Activity
Centers (TACs) in Okinawa, Japan. Trip attraction capacity and
levels of the newly classified TACs was found agreeable with the
amount of daily trips attracted to each center. The trip attraction
data set was drawn from a 2007 Okinawa personal trip survey.
This research suggests a planning methodology which guides
logical transport supply routes and concentrated local
development schemes.