Abstract: A green design for assembly model is presented to
integrate design evaluation and assembly and disassembly sequence
planning by evaluating the three activities in one integrated model. For
an assembled product, an assembly sequence planning model is
required for assembling the product at the start of the product life cycle.
A disassembly sequence planning model is needed for disassembling
the product at the end. In a green product life cycle, it is important to
plan how a product can be disassembled, reused, or recycled, before
the product is actually assembled and produced. Given a product
requirement, there may be several design alternative cases to design
the same product. In the different design cases, the assembly and
disassembly sequences for producing the product can be different. In
this research, a new model is presented to concurrently evaluate the
design and plan the assembly and disassembly sequences. First, the
components are represented by using graph based models. Next, a
particle swarm optimization (PSO) method with a new encoding
scheme is developed. In the new PSO encoding scheme, a particle is
represented by a position matrix defining an assembly sequence and a
disassembly sequence. The assembly and disassembly sequences can
be simultaneously planned with an objective of minimizing the total of
assembly costs and disassembly costs. The test results show that the
presented method is feasible and efficient for solving the integrated
design evaluation and assembly and disassembly sequence planning
problem. An example product is implemented and illustrated in this
paper.
Abstract: This paper proposes, for the first time, how the
challenges facing the guard-band designs including the margin
assist-circuits scheme for the screening-test in the coming process
generations should be addressed. The increased screening error
impacts are discussed based on the proposed statistical analysis
models. It has been shown that the yield-loss caused by the
misjudgment on the screening test would become 5-orders of
magnitude larger than that for the conventional one when the
amplitude of random telegraph noise (RTN) caused variations
approaches to that of random dopant fluctuation. Three fitting methods
to approximate the RTN caused complex Gamma mixtures
distributions by the simple Gaussian mixtures model (GMM) are
proposed and compared. It has been verified that the proposed
methods can reduce the error of the fail-bit predictions by 4-orders of
magnitude.
Abstract: The authors present an optimization algorithm for order reduction and its application for the determination of the relative mapping errors of linear time invariant dynamic systems by the simplified models. These relative mapping errors are expressed by means of the relative integral square error criterion, which are determined for both unit step and impulse inputs. The reduction algorithm is based on minimization of the integral square error by particle swarm optimization technique pertaining to a unit step input. The algorithm is simple and computer oriented. It is shown that the algorithm has several advantages, e.g. the reduced order models retain the steady-state value and stability of the original system. Two numerical examples are solved to illustrate the superiority of the algorithm over some existing methods.
Abstract: The authors have been developing several models
based on artificial neural networks, linear regression models, Box-
Jenkins methodology and ARIMA models to predict the time series
of tourism. The time series consist in the “Monthly Number of Guest
Nights in the Hotels" of one region. Several comparisons between the
different type models have been experimented as well as the features
used at the entrance of the models. The Artificial Neural Network
(ANN) models have always had their performance at the top of the
best models. Usually the feed-forward architecture was used due to
their huge application and results. In this paper the author made a
comparison between different architectures of the ANNs using
simply the same input. Therefore, the traditional feed-forward
architecture, the cascade forwards, a recurrent Elman architecture and
a radial based architecture were discussed and compared based on the
task of predicting the mentioned time series.
Abstract: Developing techniques for mobile robot navigation constitutes one of the major trends in the current
research on mobile robotics. This paper develops a local
model network (LMN) for mobile robot navigation. The
LMN represents the mobile robot by a set of locally valid
submodels that are Multi-Layer Perceptrons (MLPs).
Training these submodels employs Back Propagation (BP) algorithm. The paper proposes the fuzzy C-means (FCM) in this scheme to divide the input space to sub regions, and then a submodel (MLP) is identified to represent a particular
region. The submodels then are combined in a unified
structure. In run time phase, Radial Basis Functions (RBFs) are employed as windows for the activated submodels. This
proposed structure overcomes the problem of changing operating regions of mobile robots. Read data are used in all experiments. Results for mobile robot navigation using the
proposed LMN reflect the soundness of the proposed
scheme.
Abstract: The objective of the paper is to develop the forecast
model for the HW flows. The methodology of the research included
6 modules: historical data, assumptions, choose of indicators, data
processing, and data analysis with STATGRAPHICS, and forecast
models. The proposed methodology was validated for the case study
for Latvia. Hypothesis on the changes in HW for time period of
2010-2020 have been developed and mathematically described with
confidence level of 95.0% and 50.0%. Sensitivity analysis for the
analyzed scenarios was done. The results show that the growth of
GDP affects the total amount of HW in the country. The total amount
of the HW is projected to be within the corridor of – 27.7% in the
optimistic scenario up to +87.8% in the pessimistic scenario with
confidence level of 50.0% for period of 2010-2020. The optimistic
scenario has shown to be the least flexible to the changes in the GDP
growth.
Abstract: ANNARIMA that combines both autoregressive integrated moving average (ARIMA) model and artificial neural network (ANN) model is a valuable tool for modeling and forecasting nonlinear time series, yet the over-fitting problem is more likely to occur in neural network models. This paper provides a hybrid methodology that combines both radial basis function (RBF) neural network and auto regression (AR) model based on binomial smoothing (BS) technique which is efficient in data processing, which is called BSRBFAR. This method is examined by using the data of Canadian Lynx data. Empirical results indicate that the over-fitting problem can be eased using RBF neural network based on binomial smoothing which is called BS-RBF, and the hybrid model–BS-RBFAR can be an effective way to improve forecasting accuracy achieved by BSRBF used separately.
Abstract: Missing data is a persistent problem in almost all
areas of empirical research. The missing data must be treated very
carefully, as data plays a fundamental role in every analysis.
Improper treatment can distort the analysis or generate biased results.
In this paper, we compare and contrast various imputation techniques
on missing data sets and make an empirical evaluation of these
methods so as to construct quality software models. Our empirical
study is based on NASA-s two public dataset. KC4 and KC1. The
actual data sets of 125 cases and 2107 cases respectively, without
any missing values were considered. The data set is used to create
Missing at Random (MAR) data Listwise Deletion(LD), Mean
Substitution(MS), Interpolation, Regression with an error term and
Expectation-Maximization (EM) approaches were used to compare
the effects of the various techniques.
Abstract: Water quality is a subject of ongoing concern.
Deterioration of water quality has initiated serious management
efforts in many countries. This study endeavors to automatically
classify water quality. The water quality classes are evaluated using 6
factor indices. These factors are pH value (pH), Dissolved Oxygen
(DO), Biochemical Oxygen Demand (BOD), Nitrate Nitrogen
(NO3N), Ammonia Nitrogen (NH3N) and Total Coliform (TColiform).
The methodology involves applying data mining
techniques using multilayer perceptron (MLP) neural network
models. The data consisted of 11 sites of canals in Dusit district in
Bangkok, Thailand. The data is obtained from the Department of
Drainage and Sewerage Bangkok Metropolitan Administration
during 2007-2011. The results of multilayer perceptron neural
network exhibit a high accuracy multilayer perception rate at 96.52%
in classifying the water quality of Dusit district canal in Bangkok
Subsequently, this encouraging result could be applied with plan and
management source of water quality.
Abstract: Improving the performance of the QCL through block diagram as well as mathematical models is the main scope of this paper. In order to enhance the performance of the underlined device, the mathematical model parameters are used in a reliable manner in such a way that the optimum behavior was achieved. These parameters play the central role in specifying the optical characteristics of the considered laser source. Moreover, it is important to have a large amount of radiated power, where increasing the amount of radiated power represents the main hopping process that can be predicted from the behavior of quantum laser devices. It was found that there is a good agreement between the calculated values from our mathematical model and those obtained with VisSim and experimental results. These demonstrate the strength of mplementation of both mathematical and block diagram models.
Abstract: In recent methodological articles related to structural equation modeling (SEM), the question of how to measure endogenous formative variables has been raised as an urgent, unresolved issue. This research presents an empirical application from the CRM system development context to test a recently developed technique, which makes it possible to measure endogenous formative constructs in structural models. PLS path modeling is used to demonstrate the feasibility of measuring antecedent relationships at the formative indicator level, not the formative construct level. Empirical results show that this technique is a promising approach to measure antecedent relationships of formative constructs in SEM.
Abstract: Software organizations are constantly looking for
better solutions when designing and using well-defined software
processes for the development of their products and services.
However, while the technical aspects are virtually easier to arrange,
many software development processes lack more support on project
management issues. When adopting such processes, an organization
needs to apply good project management skills along with technical
views provided by those models. This research proposes the
definition of a new model that integrates the concepts of PMBOK
and those available on the OPEN metamodel, helping not only
process integration but also building the steps towards a more
comprehensive and automatable model.
Abstract: Using Dynamic Bayesian Networks (DBN) to model genetic regulatory networks from gene expression data is one of the major paradigms for inferring the interactions among genes. Averaging a collection of models for predicting network is desired, rather than relying on a single high scoring model. In this paper, two kinds of model searching approaches are compared, which are Greedy hill-climbing Search with Restarts (GSR) and Markov Chain Monte Carlo (MCMC) methods. The GSR is preferred in many papers, but there is no such comparison study about which one is better for DBN models. Different types of experiments have been carried out to try to give a benchmark test to these approaches. Our experimental results demonstrated that on average the MCMC methods outperform the GSR in accuracy of predicted network, and having the comparable performance in time efficiency. By proposing the different variations of MCMC and employing simulated annealing strategy, the MCMC methods become more efficient and stable. Apart from comparisons between these approaches, another objective of this study is to investigate the feasibility of using DBN modeling approaches for inferring gene networks from few snapshots of high dimensional gene profiles. Through synthetic data experiments as well as systematic data experiments, the experimental results revealed how the performances of these approaches can be influenced as the target gene network varies in the network size, data size, as well as system complexity.
Abstract: Covering-based rough sets is an extension of rough
sets and it is based on a covering instead of a partition of the
universe. Therefore it is more powerful in describing some practical
problems than rough sets. However, by extending the rough sets,
covering-based rough sets can increase the roughness of each model
in recognizing objects. How to obtain better approximations from
the models of a covering-based rough sets is an important issue.
In this paper, two concepts, determinate elements and indeterminate
elements in a universe, are proposed and given precise definitions
respectively. This research makes a reasonable refinement of the
covering-element from a new viewpoint. And the refinement may
generate better approximations of covering-based rough sets models.
To prove the theory above, it is applied to eight major coveringbased
rough sets models which are adapted from other literature.
The result is, in all these models, the lower approximation increases
effectively. Correspondingly, in all models, the upper approximation
decreases with exceptions of two models in some special situations.
Therefore, the roughness of recognizing objects is reduced. This
research provides a new approach to the study and application of
covering-based rough sets.
Abstract: Nowadays, the increase of human population every
year results in increasing of water usage and demand. Saen Saep
canal is important canal in Bangkok. The main objective of this study
is using Artificial Neural Network (ANN) model to estimate the
Chemical Oxygen Demand (COD) on data from 11 sampling sites.
The data is obtained from the Department of Drainage and Sewerage,
Bangkok Metropolitan Administration, during 2007-2011. The
twelve parameters of water quality are used as the input of the
models. These water quality indices affect the COD. The
experimental results indicate that the ANN model provides a high
correlation coefficient (R=0.89).
Abstract: Not all types of mobile phone are successful in entering the market because some types of the mobile phone have a negative perception of user. Therefore, it is important to understand the influence of mobile phone's characteristics in the local user perception. This research investigates the influence of QWERTY mobile phone's forms in the perception of Indonesian user. First, some alternatives of mobile phone-s form are developed based on a certain number of mobile phone's models. At the second stage, some word pairs as design attributes of the mobile phone are chosen to represent the user perception of mobile phone. At the final stage, a survey is conducted to investigate the influence of the developed form alternatives to the user perception. Based on the research, users perceive mobile phone's form with curved top and straight bottom shapes and mobile phone's form with slider and antenna as the most negative form. Meanwhile, mobile phone's form with curved top and bottom shapes and mobile phone-s form without slider and antenna are perceived by the user as the most positive form.
Abstract: In this paper we present discretization and decomposition methods for a multi-component transport model of a chemical vapor deposition (CVD) process. CVD processes are used to manufacture deposition layers or bulk materials. In our transport model we simulate the deposition of thin layers. The microscopic model is based on the heavy particles, which are derived by approximately solving a linearized multicomponent Boltzmann equation. For the drift-process of the particles we propose diffusionreaction equations as well as for the effects of heat conduction. We concentrate on solving the diffusion-reaction equation with analytical and numerical methods. For the chemical processes, modelled with reaction equations, we propose decomposition methods and decouple the multi-component models to simpler systems of differential equations. In the numerical experiments we present the computational results of our proposed models.
Abstract: A sequential decision problem, based on the task ofidentifying the species of trees given acoustic echo data collectedfrom them, is considered with well-known stochastic classifiers,including single and mixture Gaussian models. Echoes are processedwith a preprocessing stage based on a model of mammalian cochlearfiltering, using a new discrete low-pass filter characteristic. Stoppingtime performance of the sequential decision process is evaluated andcompared. It is observed that the new low pass filter processingresults in faster sequential decisions.
Abstract: Energy dissipation in drops has been investigated by
physical models. After determination of effective parameters on the
phenomenon, three drops with different heights have been
constructed from Plexiglas. They have been installed in two existing
flumes in the hydraulic laboratory. Several runs of physical models
have been undertaken to measured required parameters for
determination of the energy dissipation. Results showed that the
energy dissipation in drops depend on the drop height and discharge.
Predicted relative energy dissipations varied from 10.0% to 94.3%.
This work has also indicated that the energy loss at drop is mainly
due to the mixing of the jet with the pool behind the jet that causes
air bubble entrainment in the flow. Statistical model has been
developed to predict the energy dissipation in vertical drops denotes
nonlinear correlation between effective parameters. Further an
artificial neural networks (ANNs) approach was used in this paper to
develop an explicit procedure for calculating energy loss at drops
using NeuroSolutions. Trained network was able to predict the
response with R2 and RMSE 0.977 and 0.0085 respectively. The
performance of ANN was found effective when compared to
regression equations in predicting the energy loss.
Abstract: Motion control of flexible arms is more difficult than
that of rigid arms, however utilizing its dynamics enables improved
performance such as a fast motion in short operation time. This paper
investigates a ball throwing robot with one rigid link and one flexible
link. This robot throws a ball at a set speed with a proper control torque.
A mathematical model of this ball throwing robot is derived through
Hamilton’s principle. Several patterns of torque input are designed and
tested through the proposed simulation models. The parameters of
each torque input pattern is optimized and determined by chaos
embedded vector evaluated particle swarm optimization (CEVEPSO).
Then, the residual vibration of the manipulator after throwing is
suppressed with input shaping technique. Finally, a real experiment is
set up for the model checking.