Abstract: ECG analysis method was developed using ROC
analysis of PVC detecting algorithm. ECG signal of MIT-BIH
arrhythmia database was analyzed by MATLAB. First of all, the
baseline was removed by median filter to preprocess the ECG signal.
R peaks were detected for ECG analysis method, and normal VCG
was extracted for VCG analysis method. Four PVC detecting
algorithm was analyzed by ROC curve, which parameters are
maximum amplitude of QRS complex, width of QRS complex, r-r
interval and geometric mean of VCG. To set cut-off value of
parameters, ROC curve was estimated by true-positive rate
(sensitivity) and false-positive rate. sensitivity and false negative rate
(specificity) of ROC curve calculated, and ECG was analyzed using
cut-off value which was estimated from ROC curve. As a result, PVC
detecting algorithm of VCG geometric mean have high availability,
and PVC could be detected more accurately with amplitude and width
of QRS complex.
Abstract: The paper presents a complete discrete statistical framework, based on a novel vector quantization (VQ) front-end process. This new VQ approach performs an optimal distribution of VQ codebook components on HMM states. This technique that we named the distributed vector quantization (DVQ) of hidden Markov models, succeeds in unifying acoustic micro-structure and phonetic macro-structure, when the estimation of HMM parameters is performed. The DVQ technique is implemented through two variants. The first variant uses the K-means algorithm (K-means- DVQ) to optimize the VQ, while the second variant exploits the benefits of the classification behavior of neural networks (NN-DVQ) for the same purpose. The proposed variants are compared with the HMM-based baseline system by experiments of specific Arabic consonants recognition. The results show that the distributed vector quantization technique increase the performance of the discrete HMM system.
Abstract: This paper presents an exact analytical model for
optimizing stability of thin-walled, composite, functionally graded
pipes conveying fluid. The critical flow velocity at which divergence
occurs is maximized for a specified total structural mass in order to
ensure the economic feasibility of the attained optimum designs. The
composition of the material of construction is optimized by defining
the spatial distribution of volume fractions of the material
constituents using piecewise variations along the pipe length. The
major aim is to tailor the material distribution in the axial direction so
as to avoid the occurrence of divergence instability without the
penalty of increasing structural mass. Three types of boundary
conditions have been examined; namely, Hinged-Hinged, Clamped-
Hinged and Clamped-Clamped pipelines. The resulting optimization
problem has been formulated as a nonlinear mathematical
programming problem solved by invoking the MatLab optimization
toolbox routines, which implement constrained function
minimization routine named “fmincon" interacting with the
associated eigenvalue problem routines. In fact, the proposed
mathematical models have succeeded in maximizing the critical flow
velocity without mass penalty and producing efficient and economic
designs having enhanced stability characteristics as compared with
the baseline designs.
Abstract: Estimation time and cost of work completion in a
project and follow up them during execution are contributors to
success or fail of a project, and is very important for project
management team. Delivering on time and within budgeted cost
needs to well managing and controlling the projects. To dealing with
complex task of controlling and modifying the baseline project
schedule during execution, earned value management systems have
been set up and widely used to measure and communicate the real
physical progress of a project. But it often fails to predict the total
duration of the project. In this paper data mining techniques is used
predicting the total project duration in term of Time Estimate At
Completion-EAC (t). For this purpose, we have used a project with
90 activities, it has updated day by day. Then, it is used regular
indexes in literature and applied Earned Duration Method to
calculate time estimate at completion and set these as input data for
prediction and specifying the major parameters among them using
Clem software. By using data mining, the effective parameters on
EAC and the relationship between them could be extracted and it is
very useful to manage a project with minimum delay risks. As we
state, this could be a simple, safe and applicable method in prediction
the completion time of a project during execution.
Abstract: The present energy situation and the concerns
about global warming has stimulated active research interest
in non-petroleum, carbon free compounds and non-polluting
fuels, particularly for transportation, power generation, and
agricultural sectors. Environmental concerns and limited
amount of petroleum fuels have caused interests in the
development of alternative fuels for internal combustion (IC)
engines. The petroleum crude reserves however, are declining
and consumption of transport fuels particularly in the
developing countries is increasing at high rates. Severe
shortage of liquid fuels derived from petroleum may be faced
in the second half of this century. Recently more and more
stringent environmental regulations being enacted in the USA
and Europe have led to the research and development
activities on clean alternative fuels. Among the gaseous fuels
hydrogen is considered to be one of the clean alternative fuel.
Hydrogen is an interesting candidate for future internal
combustion engine based power trains. In this experimental
investigation, the performance and combustion analysis were
carried out on a direct injection (DI) diesel engine using
hydrogen with diesel following the TMI(Time Manifold
Injection) technique at different injection timings of 10
degree,45 degree and 80 degree ATDC using an electronic
control unit (ECU) and injection durations were controlled.
Further, the tests have been carried out at a constant speed of
1500rpm at different load conditions and it can be observed
that brake thermal efficiency increases with increase in load
conditions with a maximum gain of 15% at full load
conditions during all injection strategies of hydrogen. It was
also observed that with the increase in hydrogen energy share
BSEC started reducing and it reduced to a maximum of 9% as
compared to baseline diesel at 10deg ATDC injection during
maximum injection proving the exceptional combustion
properties of hydrogen.
Abstract: One major source of performance decline in speaker
recognition system is channel mismatch between training and testing.
This paper focuses on improving channel robustness of speaker
recognition system in two aspects of channel compensation technique
and channel robust features. The system is text-independent speaker
identification system based on two-stage recognition. In the aspect of
channel compensation technique, this paper applies MAP (Maximum
A Posterior Probability) channel compensation technique, which was
used in speech recognition, to speaker recognition system. In the
aspect of channel robust features, this paper introduces
pitch-dependent features and pitch-dependent speaker model for the
second stage recognition. Based on the first stage recognition to
testing speech using GMM (Gaussian Mixture Model), the system
uses GMM scores to decide if it needs to be recognized again. If it
needs to, the system selects a few speakers from all of the speakers
who participate in the first stage recognition for the second stage
recognition. For each selected speaker, the system obtains 3
pitch-dependent results from his pitch-dependent speaker model, and
then uses ANN (Artificial Neural Network) to unite the 3
pitch-dependent results and 1 GMM score for getting a fused result.
The system makes the second stage recognition based on these fused
results. The experiments show that the correct rate of two-stage
recognition system based on MAP channel compensation technique
and pitch-dependent features is 41.7% better than the baseline system
for closed-set test.
Abstract: Many recent electrophysiological studies have
revealed the importance of investigating meditation state in order to
achieve an increased understanding of autonomous control of
cardiovascular functions. In this paper, we characterize heart rate
variability (HRV) time series acquired during meditation using
nonlinear dynamical parameters. We have computed minimum
embedding dimension (MED), correlation dimension (CD), largest
Lyapunov exponent (LLE), and nonlinearity scores (NLS) from HRV
time series of eight Chi and four Kundalini meditation practitioners.
The pre-meditation state has been used as a baseline (control) state to
compare the estimated parameters. The chaotic nature of HRV during
both pre-meditation and meditation is confirmed by MED. The
meditation state showed a significant decrease in the value of CD and
increase in the value of LLE of HRV, in comparison with premeditation
state, indicating a less complex and less predictable nature
of HRV. In addition, it was shown that the HRV of meditation state
is having highest NLS than pre-meditation state. The study indicated
highly nonlinear dynamic nature of cardiac states as revealed by
HRV during meditation state, rather considering it as a quiescent
state.
Abstract: A study was conducted to formally characterize
notebook computer performance under various environmental and
usage conditions. Software was developed to collect data from the
operating system of the computer. An experiment was conducted to
evaluate the performance parameters- variations, trends, and
correlations, as well as the extreme value they can attain in various
usage and environmental conditions. An automated software script
was written to simulate user activity. The variability of each
performance parameter was addressed by establishing the empirical
relationship between performance parameters. These equations were
presented as baseline estimates for performance parameters, which
can be used to detect system deviations from normal operation and
for prognostic assessment. The effect of environmental factors,
including different power sources, ambient temperatures, humidity,
and usage, on performance parameters of notebooks was studied.
Abstract: This method decrease usage power (expenditure) in networks on chips (NOC). This method data coding for data transferring in order to reduces expenditure. This method uses data compression reduces the size. Expenditure calculation in NOC occurs inside of NOC based on grown models and transitive activities in entry ports. The goal of simulating is to weigh expenditure for encoding, decoding and compressing in Baseline networks and reduction of switches in this type of networks. KeywordsNetworks on chip, Compression, Encoding, Baseline networks, Banyan networks.
Abstract: The current speech interfaces in many military
applications may be adequate for native speakers. However,
the recognition rate drops quite a lot for non-native speakers
(people with foreign accents). This is mainly because the nonnative
speakers have large temporal and intra-phoneme
variations when they pronounce the same words. This
problem is also complicated by the presence of large
environmental noise such as tank noise, helicopter noise, etc.
In this paper, we proposed a novel continuous acoustic feature
adaptation algorithm for on-line accent and environmental
adaptation. Implemented by incremental singular value
decomposition (SVD), the algorithm captures local acoustic
variation and runs in real-time. This feature-based adaptation
method is then integrated with conventional model-based
maximum likelihood linear regression (MLLR) algorithm.
Extensive experiments have been performed on the NATO
non-native speech corpus with baseline acoustic model trained
on native American English. The proposed feature-based
adaptation algorithm improved the average recognition
accuracy by 15%, while the MLLR model based adaptation
achieved 11% improvement. The corresponding word error
rate (WER) reduction was 25.8% and 2.73%, as compared to
that without adaptation. The combined adaptation achieved
overall recognition accuracy improvement of 29.5%, and
WER reduction of 31.8%, as compared to that without
adaptation.
Abstract: The Major Depressive Disorder has been a burden of
medical expense in Taiwan as well as the situation around the world.
Major Depressive Disorder can be defined into different categories by
previous human activities. According to machine learning, we can
classify emotion in correct textual language in advance. It can help
medical diagnosis to recognize the variance in Major Depressive
Disorder automatically. Association language incremental is the
characteristic and relationship that can discovery words in sentence.
There is an overlapping-category problem for classification. In this
paper, we would like to improve the performance in classification in
principle of no overlapping-category problems. We present an
approach that to discovery words in sentence and it can find in high
frequency in the same time and can-t overlap in each category, called
Association Language Features by its Category (ALFC).
Experimental results show that ALFC distinguish well in Major
Depressive Disorder and have better performance. We also compare
the approach with baseline and mutual information that use single
words alone or correlation measure.
Abstract: This paper presents a generalized formulation for the
problem of buckling optimization of anisotropic, radially graded,
thin-walled, long cylinders subject to external hydrostatic pressure.
The main structure to be analyzed is built of multi-angle fibrous
laminated composite lay-ups having different volume fractions of the
constituent materials within the individual plies. This yield to a
piecewise grading of the material in the radial direction; that is the
physical and mechanical properties of the composite material are
allowed to vary radially. The objective function is measured by
maximizing the critical buckling pressure while preserving the total
structural mass at a constant value equals to that of a baseline
reference design. In the selection of the significant optimization
variables, the fiber volume fractions adjoin the standard design
variables including fiber orientation angles and ply thicknesses. The
mathematical formulation employs the classical lamination theory,
where an analytical solution that accounts for the effective axial and
flexural stiffness separately as well as the inclusion of the coupling
stiffness terms is presented. The proposed model deals with
dimensionless quantities in order to be valid for thin shells having
arbitrary thickness-to-radius ratios. The critical buckling pressure
level curves augmented with the mass equality constraint are given
for several types of cylinders showing the functional dependence of
the constrained objective function on the selected design variables. It
was shown that material grading can have significant contribution to
the whole optimization process in achieving the required structural
designs with enhanced stability limits.
Abstract: The microbiological and physicochemical
characteristics of wetland soils in Eket Local Government Area were
studied between May 2001 and June 2003. Total heterotrophic
bacterial counts (THBC), total fungal counts (TFC), and total
actinomycetes counts (TAC) were determined from soil samples
taken from four locations at two depths in the wet and dry seasons.
Microbial isolates were characterized and identified. Particle size and
chemical parameters were also determined using standard methods.
THBC ranged from 5.2 (+0.17) x106 to 1.7 (+0.18) x107 cfu/g and
from 2.4 (+0.02) x106 to 1.4 (+0.04) x107cfu/g in the wet and dry
seasons, respectively. TFC ranged from 1.8 (+0.03) x106 to 6.6 (+
0.18) x106 cfu/g and from 1.0 (+0.04) x106 to 4.2 (+ 0.01) x106 cfu/g
in the wet and dry seasons, respectively .TAC ranged from 1.2
(+0.53) x106 to 6.0 (+0.05) x106 cfu/g and from 0.6 (+0.01) x106 to
3.2 (+ 0.12) x106 cfu/g in the wet and dry season, respectively.
Acinetobacter, Alcaligenes, Arthrobacter, Bacillus, Beijerinckja,
Enterobacter, Micrococcus, Flavobacterium, Serratia, Enterococcus,
and Pseudomonas species were predominant bacteria while
Aspergillus, Fusarium, Mucor, Penicillium, and Rhizopus were the
dominant fungal genera isolated. Streptomyces and Norcadia were
the actinomycetes genera isolated. The particle size analysis showed
high sand fraction but low silt and clay. The pH and % organic
matter were generally acidic and low, respectively at all locations.
Calcium dominated the exchangeable bases with low electrical
conductivity and micronutrients. These results provide the baseline
data of Eket wetland soils for its management for sustainable
agriculture.
Abstract: Biodiesel as an alternative fuel for diesel engines has been developed for some three decades now. While it is gaining wide acceptance in Europe, USA and some parts of Asia, the same cannot be said of Africa. With more than 35 countries in the continent depending on imported crude oil, it is necessary to look for alternative fuels which can be produced from resources available locally within any country. Hence this study presents performance of single cylinder diesel engine using blends of shea butter biodiesel. Shea butter was transformed into biodiesel by transesterification process. Tests are conducted to compare the biodiesel with baseline diesel fuel in terms of engine performance and exhaust emission characteristics. The results obtained showed that the addition of biodiesel to diesel fuel decreases the brake thermal efficiency (BTE) and increases the brake specific fuel consumption (BSFC). These results are expected due to the lower energy content of biodiesel fuel. On the other hand while the NOx emissions increased with increase in biodiesel content in the fuel blends, the emissions of carbon monoxide (CO), un-burnt hydrocarbon (UHC) and smoke opacity decreased. The engine performance which indicates that the biodiesel has properties and characteristics similar to diesel fuel and the reductions in exhaust emissions make shea butter biodiesel a viable additive or substitute to diesel fuel.
Abstract: In this paper we present an efficient system for
independent speaker speech recognition based on neural network
approach. The proposed architecture comprises two phases: a
preprocessing phase which consists in segmental normalization and
features extraction and a classification phase which uses neural
networks based on nonparametric density estimation namely the
general regression neural network (GRNN). The relative
performances of the proposed model are compared to the similar
recognition systems based on the Multilayer Perceptron (MLP), the
Recurrent Neural Network (RNN) and the well known Discrete
Hidden Markov Model (HMM-VQ) that we have achieved also.
Experimental results obtained with Arabic digits have shown that the
use of nonparametric density estimation with an appropriate
smoothing factor (spread) improves the generalization power of the
neural network. The word error rate (WER) is reduced significantly
over the baseline HMM method. GRNN computation is a successful
alternative to the other neural network and DHMM.