Abstract: This research study aims to present a retrospective
study about speech recognition systems and artificial intelligence.
Speech recognition has become one of the widely used technologies,
as it offers great opportunity to interact and communicate with
automated machines. Precisely, it can be affirmed that speech
recognition facilitates its users and helps them to perform their daily
routine tasks, in a more convenient and effective manner. This
research intends to present the illustration of recent technological
advancements, which are associated with artificial intelligence.
Recent researches have revealed the fact that speech recognition is
found to be the utmost issue, which affects the decoding of speech. In
order to overcome these issues, different statistical models were
developed by the researchers. Some of the most prominent statistical
models include acoustic model (AM), language model (LM), lexicon
model, and hidden Markov models (HMM). The research will help in
understanding all of these statistical models of speech recognition.
Researchers have also formulated different decoding methods, which
are being utilized for realistic decoding tasks and constrained
artificial languages. These decoding methods include pattern
recognition, acoustic phonetic, and artificial intelligence. It has been
recognized that artificial intelligence is the most efficient and reliable
methods, which are being used in speech recognition.
Abstract: This paper analyzes the conceptual framework of three
statistical methods, multiple regression, path analysis, and structural
equation models. When establishing research model of the statistical
modeling of complex social phenomenon, it is important to know the
strengths and limitations of three statistical models. This study
explored the character, strength, and limitation of each modeling and
suggested some strategies for accurate explaining or predicting the
causal relationships among variables. Especially, on the studying of
depression or mental health, the common mistakes of research
modeling were discussed.
Abstract: We proposed a Hyperbolic Gompertz Growth Model
(HGGM), which was developed by introducing a shape parameter
(allometric). This was achieved by convoluting hyperbolic sine
function on the intrinsic rate of growth in the classical gompertz
growth equation. The resulting integral solution obtained
deterministically was reprogrammed into a statistical model and used
in modeling the height and diameter of Pines (Pinus caribaea). Its
ability in model prediction was compared with the classical gompertz
growth model, an approach which mimicked the natural variability of
height/diameter increment with respect to age and therefore provides
a more realistic height/diameter predictions using goodness of fit
tests and model selection criteria. The Kolmogorov Smirnov test and
Shapiro-Wilk test was also used to test the compliance of the error
term to normality assumptions while the independence of the error
term was confirmed using the runs test. The mean function of top
height/Dbh over age using the two models under study predicted
closely the observed values of top height/Dbh in the hyperbolic
gompertz growth models better than the source model (classical
gompertz growth model) while the results of R2, Adj. R2, MSE and
AIC confirmed the predictive power of the Hyperbolic Gompertz
growth models over its source model.
Abstract: The hydrolysis of lactose using β-galactosidase is one of the most promising biotechnological applications, which has wide range of potential applications in food processing industries. However, due to intracellular location of the yeast enzyme, and expensive extraction methods, the industrial applications of enzymatic hydrolysis processes are being hampered. The use of permeabilization technique can help to overcome the problems associated with enzyme extraction and purification of yeast cells and to develop the economically viable process for the utilization of whole cell biocatalysts in food industries. In the present investigation, standardization of permeabilization process of novel yeast isolate was carried out using a statistical model approach known as Response Surface Methodology (RSM) to achieve maximal b-galactosidase activity. The optimum operating conditions for permeabilization process for optimal β-galactosidase activity obtained by RSM were 1:1 ratio of toluene (25%, v/v) and ethanol (50%, v/v), 25.0 oC temperature and treatment time of 12 min, which displayed enzyme activity of 1.71 IU /mg DW.
Abstract: Humic acids (HA) were produced by a Trichoderma
viride strain under submerged fermentation in a medium based on the
oil palm empty fruit bunch (EFB) and the main variables of the
process were optimized by using response surface methodology. A
temperature of 40°C and concentrations of 50g/L EFB, 5.7g/L potato
peptone and 0.11g/L (NH4)2SO4 were the optimum levels of the
variables that maximize the HA production, within the
physicochemical and biological limits of the process. The optimized
conditions led to an experimental HA concentration of 428.4±17.5
mg/L, which validated the prediction from the statistical model of
412.0mg/L. This optimization increased about 7–fold the HA
production previously reported in the literature. Additionally, the
time profiles of HA production and fungal growth confirmed our
previous findings that HA production preferably occurs during fungal
sporulation. The present study demonstrated that T. viride
successfully produced HA via the submerged fermentation of EFB
and the process parameters were successfully optimized using a
statistics-based response surface model. To the best of our
knowledge, the present work is the first report on the optimization of
HA production from EFB by a biotechnological process, whose
feasibility was only pointed out in previous works.
Abstract: Industries using conventional fossil fuels have an
interest in better understanding the mechanism of particulate
formation during combustion since such is responsible for emission
of undesired inorganic elements that directly impact the atmospheric
pollution level. Fine and ultrafine particulates have tendency to
escape the flue gas cleaning devices to the atmosphere. They also
preferentially collect on surfaces in power systems resulting in
ascending in corrosion inclination, descending in the heat transfer
thermal unit, and severe impact on human health. This adverseness
manifests particularly in the regions of world where coal is the
dominated source of energy for consumption.
This study highlights the behavior of calcium transformation as
mineral grains verses organically associated inorganic components
during pulverized coal combustion. The influence of existing type of
calcium on the coarse, fine and ultrafine mode formation mechanisms
is also presented. The impact of two sub-bituminous coals on particle
size and calcium composition evolution during combustion is to be
assessed. Three mixed blends named Blends 1, 2, and 3 are selected
according to the ration of coal A to coal B by weight. Calcium
percentage in original coal increases as going from Blend 1 to 3.
A mathematical model and a new approach of describing
constituent distribution are proposed. Analysis of experiments of
calcium distribution in ash is also modeled using Poisson distribution.
A novel parameter, called elemental index λ, is introduced as a
measuring factor of element distribution.
Results show that calcium in ash that originally in coal as mineral
grains has index of 17, whereas organically associated calcium
transformed to fly ash shown to be best described when elemental
index λ is 7.
As an alkaline-earth element, calcium is considered the
fundamental element responsible for boiler deficiency since it is the
major player in the mechanism of ash slagging process. The
mechanism of particle size distribution and mineral species of ash
particles are presented using CCSEM and size-segregated ash
characteristics. Conclusions are drawn from the analysis of
pulverized coal ash generated from a utility-scale boiler.
Abstract: This paper presents the experimental investigation of on-body channel fading at 2.45 GHz considering two effects of the user body movement; stationary and mobile. A pair of body-worn antennas was utilized in this measurement campaign. A statistical analysis was performed by comparing the measured on-body path loss to five well-known distributions; lognormal, normal, Nakagami, Weibull and Rayleigh. The results showed that the average path loss of moving arm varied higher than the path loss in sitting position for upper-arm-to-left-chest link, up to 3.5 dB. The analysis also concluded that the Nakagami distribution provided the best fit for most of on-body static link path loss in standing still and sitting position, while the arm movement can be best described by log-normal distribution.
Abstract: In this paper, a study of slope failures along the Alishan Highway is carried out. An innovative empirical model is developed based on 15-year records of rainfall-induced slope failures. The statistical models are intended for assessing the volume of landslide for slope failure along the Alishan Highway in the future. The rainfall data considered in the proposed models include the effective cumulative rainfall and the critical rainfall intensity. The effective cumulative rainfall is defined at the point when the curve of cumulative rainfall goes from steep to flat. Then, the rainfall thresholds of landslide are established for assessing the volume of landslide and issuing warning and/or closure for the Alishan Highway during a future extreme rainfall. Slope failures during Typhoon Saola in 2012 demonstrate that the new empirical model is effective and applicable to other cases with similar rainfall conditions.
Abstract: High Resolution NMR Spectroscopy offers unique screening capabilities for food quality and safety by combining non-targeted and targeted screening in one analysis.
The objective is to demonstrate, that due to its extreme reproducibility NMR can detect smallest changes in concentrations of many components in a mixture, which is best monitored by statistical evaluation however also delivers reliable quantification results.
The methodology typically uses a 400 MHz high resolution instrument under full automation after minimized sample preparation.
For example one fruit juice analysis in a push button operation takes at maximum 15 minutes and delivers a multitude of results, which are automatically summarized in a PDF report.
The method has been proven on fruit juices, where so far unknown frauds could be detected. In addition conventional targeted parameters are obtained in the same analysis. This technology has the advantage that NMR is completely quantitative and concentration calibration only has to be done once for all compounds. Since NMR is so reproducible, it is also transferable between different instruments (with same field strength) and laboratories. Based on strict SOP`s, statistical models developed once can be used on multiple instruments and strategies for compound identification and quantification are applicable as well across labs.
Abstract: This paper examines the available experiment data for a copper bromide vapor laser (CuBr laser), emitting at two wavelengths - 510.6 and 578.2nm. Laser output power is estimated based on 10 independent input physical parameters. A classification and regression tree (CART) model is obtained which describes 97% of data. The resulting binary CART tree specifies which input parameters influence considerably each of the classification groups. This allows for a technical assessment that indicates which of these are the most significant for the manufacture and operation of the type of laser under consideration. The predicted values of the laser output power are also obtained depending on classification. This aids the design and development processes considerably.
Abstract: We compare three categorical data clustering
algorithms with respect to the problem of classifying cultural data
related to the aesthetic judgment of comics artists. Such a
classification is very important in Comics Art theory since the
determination of any classes of similarities in such kind of data will
provide to art-historians very fruitful information of Comics Art-s
evolution. To establish this, we use a categorical data set and we
study it by employing three categorical data clustering algorithms.
The performances of these algorithms are compared each other,
while interpretations of the clustering results are also given.
Abstract: One of the essential sectors of Myanmar economy is
agriculture which is sensitive to climate variation. The most
important climatic element which impacts on agriculture sector is
rainfall. Thus rainfall prediction becomes an important issue in
agriculture country. Multi variables polynomial regression (MPR)
provides an effective way to describe complex nonlinear input output
relationships so that an outcome variable can be predicted from the
other or others. In this paper, the modeling of monthly rainfall
prediction over Myanmar is described in detail by applying the
polynomial regression equation. The proposed model results are
compared to the results produced by multiple linear regression model
(MLR). Experiments indicate that the prediction model based on
MPR has higher accuracy than using MLR.
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.
Abstract: Using a set of confidence intervals, we develop a
common approach, to construct a fuzzy set as an estimator for
unknown parameters in statistical models. We investigate a method
to derive the explicit and unique membership function of such fuzzy
estimators. The proposed method has been used to derive the fuzzy
estimators of the parameters of a Normal distribution and some
functions of parameters of two Normal distributions, as well as the
parameters of the Exponential and Poisson distributions.
Abstract: In this research, a systematic investigation was carried out to determine the optimum conditions of HDS reactor. Moreover, a suitable model was developed for a rigorous RTO (real time optimization) loop of HDS (Hydro desulfurization) process. A systematic experimental series was designed based on CCD (Central Composite design) and carried out in the related pilot plant to tune the develop model. The designed variables in the experiments were Temperature, LHSV and pressure. However, the hydrogen over fresh feed ratio was remained constant. The ranges of these variables were respectively equal to 320-380ºC, 1- 21/hr and 50-55 bar. a power law kinetic model was also developed for our further research in the future .The rate order and activation energy , power of reactant concentration and frequency factor of this model was respectively equal to 1.4, 92.66 kJ/mol and k0=2.7*109 .
Abstract: This paper proposes a novel approach that combines statistical models and support vector machines. A hybrid scheme which appropriately incorporates the advantages of both the generative and discriminant model paradigms is described and evaluated. Support vector machines (SVMs) are trained to divide the whole speakers' space into small subsets of speakers within a hierarchical tree structure. During testing a speech token is assigned to its corresponding group and evaluation using gaussian mixture models (GMMs) is then processed. Experimental results show that the proposed method can significantly improve the performance of text independent speaker identification task. We report improvements of up to 50% reduction in identification error rate compared to the baseline statistical model.
Abstract: The problem of generation expansion planning (GEP)
has been extensively studied for many years. This paper presents
three topics in GEP as follow: statistical model, models for
generation expansion, and expansion problem. In the topic of
statistical model, the main stages of the statistical modeling are
briefly explained. Some works on models for GEP are reviewed in
the topic of models for generation expansion. Finally for the topic of
expansion problem, the major issues in the development of a longterm
expansion plan are summarized.
Abstract: The fault detection and diagnosis of complicated
production processes is one of essential tasks needed to run the process
safely with good final product quality. Unexpected events occurred in
the process may have a serious impact on the process. In this work,
triangular representation of process measurement data obtained in an
on-line basis is evaluated using simulation process. The effect of using
linear and nonlinear reduced spaces is also tested. Their diagnosis
performance was demonstrated using multivariate fault data. It has
shown that the nonlinear technique based diagnosis method produced
more reliable results and outperforms linear method. The use of
appropriate reduced space yielded better diagnosis performance. The
presented diagnosis framework is different from existing ones in that it
attempts to extract the fault pattern in the reduced space, not in the
original process variable space. The use of reduced model space helps
to mitigate the sensitivity of the fault pattern to noise.
Abstract: Rutting is one of the major load-related distresses in airport flexible pavements. Rutting in paving materials develop gradually with an increasing number of load applications, usually appearing as longitudinal depressions in the wheel paths and it may be accompanied by small upheavals to the sides. Significant research has been conducted to determine the factors which affect rutting and how they can be controlled. Using the experimental design concepts, a series of tests can be conducted while varying levels of different parameters, which could be the cause for rutting in airport flexible pavements. If proper experimental design is done, the results obtained from these tests can give a better insight into the causes of rutting and the presence of interactions and synergisms among the system variables which have influence on rutting. Although traditionally, laboratory experiments are conducted in a controlled fashion to understand the statistical interaction of variables in such situations, this study is an attempt to identify the critical system variables influencing airport flexible pavement rut depth from a statistical DoE perspective using real field data from a full-scale test facility. The test results do strongly indicate that the response (rut depth) has too much noise in it and it would not allow determination of a good model. From a statistical DoE perspective, two major changes proposed for this experiment are: (1) actual replication of the tests is definitely required, (2) nuisance variables need to be identified and blocked properly. Further investigation is necessary to determine possible sources of noise in the experiment.
Abstract: Simultaneous Saccharification and Fermentation (SSF) of sugarcane bagasse by cellulase and Pachysolen tannophilus MTCC *1077 were investigated in the present study. Important process variables for ethanol production form pretreated bagasse were optimized using Response Surface Methodology (RSM) based on central composite design (CCD) experiments. A 23 five level CCD experiments with central and axial points was used to develop a statistical model for the optimization of process variables such as incubation temperature (25–45°) X1, pH (5.0–7.0) X2 and fermentation time (24–120 h) X3. Data obtained from RSM on ethanol production were subjected to the analysis of variance (ANOVA) and analyzed using a second order polynomial equation and contour plots were used to study the interactions among three relevant variables of the fermentation process. The fermentation experiments were carried out using an online monitored modular fermenter 2L capacity. The processing parameters setup for reaching a maximum response for ethanol production was obtained when applying the optimum values for temperature (32°C), pH (5.6) and fermentation time (110 h). Maximum ethanol concentration (3.36 g/l) was obtained from 50 g/l pretreated sugarcane bagasse at the optimized process conditions in aerobic batch fermentation. Kinetic models such as Monod, Modified Logistic model, Modified Logistic incorporated Leudeking – Piret model and Modified Logistic incorporated Modified Leudeking – Piret model have been evaluated and the constants were predicted.