Abstract: Automatic detection of syllable repetition is one of the
important parameter in assessing the stuttered speech objectively.
The existing method which uses artificial neural network (ANN)
requires high levels of agreement as prerequisite before attempting to
train and test ANNs to separate fluent and nonfluent. We propose
automatic detection method for syllable repetition in read speech for
objective assessment of stuttered disfluencies which uses a novel
approach and has four stages comprising of segmentation, feature
extraction, score matching and decision logic. Feature extraction is
implemented using well know Mel frequency Cepstra coefficient
(MFCC). Score matching is done using Dynamic Time Warping
(DTW) between the syllables. The Decision logic is implemented by
Perceptron based on the score given by score matching. Although
many methods are available for segmentation, in this paper it is done
manually. Here the assessment by human judges on the read speech
of 10 adults who stutter are described using corresponding method
and the result was 83%.
Abstract: Keystroke authentication is a new access control system
to identify legitimate users via their typing behavior. In this paper,
machine learning techniques are adapted for keystroke authentication.
Seven learning methods are used to build models to differentiate user
keystroke patterns. The selected classification methods are Decision
Tree, Naive Bayesian, Instance Based Learning, Decision Table, One
Rule, Random Tree and K-star. Among these methods, three of them
are studied in more details. The results show that machine learning
is a feasible alternative for keystroke authentication. Compared to
the conventional Nearest Neighbour method in the recent research,
learning methods especially Decision Tree can be more accurate. In
addition, the experiment results reveal that 3-Grams is more accurate
than 2-Grams and 4-Grams for feature extraction. Also, combination
of attributes tend to result higher accuracy.
Abstract: Waste lubricating oil re-refining adsorption process by
different adsorbent materials was investigated. Adsorbent materials
such as oil adsorbent, egg shale powder, date palm kernel powder,
and acid activated date palm kernel powder were used. The
adsorption process over fixed amount of adsorbent at ambient
conditions was investigated. The adsorption/extraction process was
able to deposit the asphaltenic and metallic contaminants from the
waste oil to lower values. It was found that the date palm kernel
powder with contact time of 4 h was able to give the best conditions
for treating the waste oil. The recovered solvent could be also reused.
It was also found that the activated bentonite gave the best
physical properties followed by the date palm kernel powder.
Abstract: Cardiovascular disease mostly in the form of atherosclerosis is responsible for 30% of all world deaths amounting to 17 million people per year. Atherosclerosis is due to the formation of plaque. The fatty plaque may be at risk of rupture, leading typically to stroke and heart attack. The plaque is usually associated with a high degree of lumen reduction, called a stenosis. The initiation and progression of the disease is strongly linked to the hemodynamic environment near the vessel wall. The aim of this study is to validate the flow of blood mimic through an arterial stenosis model with computational fluid dynamics (CFD) package. In experiment, an axisymmetric model constructed consists of contraction and expansion region that follow a mathematical form of cosine function. A 30% diameter reduction was used in this study. Particle image velocimetry (PIV) was used to characterize the flow. The fluid consists of rigid spherical particles suspended in waterglycerol- NaCl mixture. The particles with 20 μm diameter were selected to follow the flow of fluid. The flow at Re=155, 270 and 390 were investigated. The experimental result is compared with FLUENT simulated flow that account for viscous laminar flow model. The results suggest that laminar flow model was sufficient to predict flow velocity at the inlet but the velocity at stenosis throat at Re =390 was overestimated. Hence, a transition to turbulent regime might have been developed at throat region as the flow rate increases.
Abstract: A state of the art Speaker Identification (SI) system
requires a robust feature extraction unit followed by a speaker
modeling scheme for generalized representation of these features.
Over the years, Mel-Frequency Cepstral Coefficients (MFCC)
modeled on the human auditory system has been used as a standard
acoustic feature set for speech related applications. On a recent
contribution by authors, it has been shown that the Inverted Mel-
Frequency Cepstral Coefficients (IMFCC) is useful feature set for
SI, which contains complementary information present in high
frequency region. This paper introduces the Gaussian shaped filter
(GF) while calculating MFCC and IMFCC in place of typical
triangular shaped bins. The objective is to introduce a higher
amount of correlation between subband outputs. The performances
of both MFCC & IMFCC improve with GF over conventional
triangular filter (TF) based implementation, individually as well as
in combination. With GMM as speaker modeling paradigm, the
performances of proposed GF based MFCC and IMFCC in
individual and fused mode have been verified in two standard
databases YOHO, (Microphone Speech) and POLYCOST
(Telephone Speech) each of which has more than 130 speakers.
Abstract: There has been a growing interest in utilizing surfactants in remediation processes to separate the hydrophobic volatile organic compounds (HVOCs) from aqueous solution. One attractive process is cloud point extraction (CPE), which utilizes nonionic surfactants as a separating agent. Since the surfactant cost is a key determination of the economic viability of the process, it is important that the surfactants are recycled and reused. This work aims to study the performance of the co-current vacuum stripping using a packed column for HVOCs removal from contaminated surfactant solution. Six types HVOCs are selected as contaminants. The studied surfactant is the branched secondary alcohol ethoxylates (AEs), Tergitol TMN-6 (C14H30O2). The volatility and the solubility of HVOCs in surfactant system are determined in terms of an apparent Henry’s law constant and a solubilization constant, respectively. Moreover, the HVOCs removal efficiency of vacuum stripping column is assessed in terms of percentage of HVOCs removal and the overall liquid phase volumetric mass transfer coefficient. The apparent Henry’s law constant of benzenz , toluene, and ethyl benzene were 7.00×10-5, 5.38×10-5, 3.35× 10-5 respectively. The solubilization constant of benzene, toluene, and ethyl benzene were 1.71, 2.68, 7.54 respectively. The HVOCs removal for all solute were around 90 percent.
Abstract: In this paper, we propose a supervised method for
color image classification based on a multilevel sigmoidal neural
network (MSNN) model. In this method, images are classified into
five categories, i.e., “Car", “Building", “Mountain", “Farm" and
“Coast". This classification is performed without any segmentation
processes. To verify the learning capabilities of the proposed method,
we compare our MSNN model with the traditional Sigmoidal Neural
Network (SNN) model. Results of comparison have shown that the
MSNN model performs better than the traditional SNN model in the
context of training run time and classification rate. Both color
moments and multi-level wavelets decomposition technique are used
to extract features from images. The proposed method has been
tested on a variety of real and synthetic images.
Abstract: A manufacturing feature can be defined simply as a
geometric shape and its manufacturing information to create the shape.
In a feature-based process planning system, feature library that
consists of pre-defined manufacturing features and the manufacturing
information to create the shape of the features, plays an important role
in the extraction of manufacturing features with their proper
manufacturing information. However, to manage the manufacturing
information flexibly, it is important to build a feature library that can
be easily modified. In this paper, the implementation of Semantic Wiki
for the development of the feature library is proposed.
Abstract: Environment both endowed and built are essential for
tourism. However tourism and environment maintains a complex
relationship, where in most cases environment is at the receiving end.
Many tourism development activities have adverse environmental
effects, mainly emanating from construction of general infrastructure
and tourism facilities. These negative impacts of tourism can lead to
the destruction of precious natural resources on which it depends.
These effects vary between locations; and its effect on a hill
destination is highly critical. This study aims at developing a
Sustainable Tourism Planning Model for an environmentally
sensitive tourism destination in Kerala, India. Being part of the
Nilgiri mountain ranges, Munnar falls in the Western Ghats, one of
the biological hotspots in the world. Endowed with a unique high
altitude environment Munnar inherits highly significant ecological
wealth. Giving prime importance to the protection of this ecological
heritage, the study proposes a tourism planning model with resource
conservation and sustainability as the paramount focus. Conceiving a
novel approach towards sustainable tourism planning, the study
proposes to assess tourism attractions using Ecological Sensitivity
Index (ESI) and Tourism Attractiveness Index (TAI). Integration of
these two indices will form the Ecology – Tourism Matrix (ETM),
outlining the base for tourism planning in an environmentally
sensitive destination. The ETM Matrix leads to a classification of
tourism nodes according to its Conservation Significance and
Tourism Significance. The spatial integration of such nodes based on
the Hub & Spoke Principle constitutes sub – regions within the STZ.
Ensuing analyses lead to specific guidelines for the STZ as a whole,
specific tourism nodes, hubs and sub-regions. The study results in a
multi – dimensional output, viz., (1) Classification system for tourism
nodes in an environmentally sensitive region/ destination (2)
Conservation / Tourism Development Strategies and Guidelines for
the micro and macro regions and (3) A Sustainable Tourism Planning
Tool particularly for Ecologically Sensitive Destinations, which can
be adapted for other destinations as well.
Abstract: Raisin Concentrate (RC) are the most important
products obtained in the raisin processing industries. These RC
products are now used to make the syrups, drinks and confectionery
productions and introduced as natural substitute for sugar in food
applications. Iran is a one of the biggest raisin exporter in the world
but unfortunately despite a good raw material, no serious effort to
extract the RC has been taken in Iran. Therefore, in this paper, we
determined and analyzed affected parameters on extracting RC
process and then optimizing these parameters for design the
extracting RC process in two types of raisin (round and long)
produced in Khorasan region. Two levels of solvent (1:1 and 2:1),
three levels of extraction temperature (60°C, 70°C and 80°C), and
three levels of concentration temperature (50°C, 60°C and 70°C)
were the treatments. Finally physicochemical characteristics of the
obtained concentrate such as color, viscosity, percentage of reduction
sugar, acidity and the microbial tests (mould and yeast) were
counted. The analysis was performed on the basis of factorial in the
form of completely randomized design (CRD) and Duncan's multiple
range test (DMRT) was used for the comparison of the means.
Statistical analysis of results showed that optimal conditions for
production of concentrate is round raisins when the solvent ratio was
2:1 with extraction temperature of 60°C and then concentration
temperature of 50°C. Round raisin is cheaper than the long one, and
it is more economical to concentrate production. Furthermore, round
raisin has more aromas and the less color degree with increasing the
temperature of concentration and extraction. Finally, according to
mentioned factors the concentrate of round raisin is recommended.
Abstract: Ultrasound is useful in demonstrating bone mineral
density of regenerating osseous tissue as well as structural alterations.
A proposed ultrasound method, which included ultrasonography and
acoustic parameters measurement, was employed to evaluate its
efficacy in monitoring the bone callus changes in a rabbit tibial
distraction osteogenesis (DO) model.
The findings demonstrated that ultrasonographic images depicted
characteristic changes of the bone callus, typical of histology findings,
during the distraction phase. Follow-up acoustic parameters
measurement of the bone callus, including speed of sound, reflection
and attenuation, showed significant linear changes over time during
the distraction phase. The acoustic parameters obtained during the
distraction phase also showed moderate to strong correlation with
consolidated bone callus density and micro-architecture measured by
micro-computed tomography at the end of the consolidation phase.
The results support the preferred use of ultrasound imaging in the
early monitoring of bone callus changes during DO treatment.
Abstract: A biophysically based multilayer continuum model of the facial soft tissue composite has been developed for simulating wrinkle formation. The deformed state of the soft tissue block was determined by solving large deformation mechanics equations using the Galerkin finite element method. The proposed soft tissue model is composed of four layers with distinct mechanical properties. These include stratum corneum, epidermal-dermal layer (living epidermis and dermis), subcutaneous tissue and the underlying muscle. All the layers were treated as non-linear, isotropic Mooney Rivlin materials. Contraction of muscle fibres was approximated using a steady-state relationship between the fibre extension ratio, intracellular calcium concentration and active stress in the fibre direction. Several variations of the model parameters (stiffness and thickness of epidermal-dermal layer, thickness of subcutaneous tissue layer) have been considered.
Abstract: An important problem in speech research is the automatic extraction of information about the shape and dimensions of the vocal tract during real-time speech production. We have previously developed Southampton dynamic magnetic resonance imaging (SDMRI) as an approach to the solution of this problem.However, the SDMRI images are very noisy so that shape extraction is a major challenge. In this paper, we address the problem of tongue shape extraction, which poses difficulties because this is a highly deforming non-parametric shape. We show that combining active shape models with the dynamic Hough transform allows the tongue shape to be reliably tracked in the image sequence.
Abstract: In this paper a novel approach for generalized image
retrieval based on semantic contents is presented. A combination of
three feature extraction methods namely color, texture, and edge
histogram descriptor. There is a provision to add new features in
future for better retrieval efficiency. Any combination of these
methods, which is more appropriate for the application, can be used
for retrieval. This is provided through User Interface (UI) in the
form of relevance feedback. The image properties analyzed in this
work are by using computer vision and image processing algorithms.
For color the histogram of images are computed, for texture cooccurrence
matrix based entropy, energy, etc, are calculated and for
edge density it is Edge Histogram Descriptor (EHD) that is found.
For retrieval of images, a novel idea is developed based on greedy
strategy to reduce the computational complexity. The entire system
was developed using AForge.Imaging (an open source product),
MATLAB .NET Builder, C#, and Oracle 10g. The system was tested
with Coral Image database containing 1000 natural images and
achieved better results.
Abstract: When the results of the total element concentrations using USEPA method 3051A are compared to the sequential extraction analyses (i.e. the sum of fractions BCR1, BCR2 and BRC3), it can be calculated that the recovery values of elements varied between 56.8-% and 69.4-% in the bottom ash, and between 11.3-% and 70.9-% in the fly ash. This indicates that most of the elements in the ashes do not occur as readily soluble forms.
Abstract: In this paper the problem of face recognition under variable illumination conditions is considered. Most of the works in the literature exhibit good performance under strictly controlled acquisition conditions, but the performance drastically drop when changes in pose and illumination occur, so that recently number of approaches have been proposed to deal with such variability. The aim of this work is to introduce an efficient local appearance feature extraction method based steerable pyramid (SP) for face recognition. Local information is extracted from SP sub-bands using LBP(Local binary Pattern). The underlying statistics allow us to reduce the required amount of data to be stored. The experiments carried out on different face databases confirm the effectiveness of the proposed approach.
Abstract: The similarity comparison of RNA secondary
structures is important in studying the functions of RNAs. In recent
years, most existing tools represent the secondary structures by
tree-based presentation and calculate the similarity by tree alignment
distance. Different to previous approaches, we propose a new method
based on maximum clique detection algorithm to extract the maximum
common structural elements in compared RNA secondary structures.
A new graph-based similarity measurement and maximum common
subgraph detection procedures for comparing purely RNA secondary
structures is introduced. Given two RNA secondary structures, the
proposed algorithm consists of a process to determine the score of the
structural similarity, followed by comparing vertices labelling, the
labelled edges and the exact degree of each vertex. The proposed
algorithm also consists of a process to extract the common structural
elements between compared secondary structures based on a proposed
maximum clique detection of the problem. This graph-based model
also can work with NC-IUB code to perform the pattern-based
searching. Therefore, it can be used to identify functional RNA motifs
from database or to extract common substructures between complex
RNA secondary structures. We have proved the performance of this
proposed algorithm by experimental results. It provides a new idea of
comparing RNA secondary structures. This tool is helpful to those
who are interested in structural bioinformatics.
Abstract: Effectiveness of Artificial Neural Networks (ANN)
and Support Vector Machines (SVM) classifiers for fault diagnosis of
rolling element bearings are presented in this paper. The
characteristic features of vibration signals of rotating driveline that
was run in its normal condition and with faults introduced were used
as input to ANN and SVM classifiers. Simple statistical features such
as standard deviation, skewness, kurtosis etc. of the time-domain
vibration signal segments along with peaks of the signal and peak of
power spectral density (PSD) are used as features to input the ANN
and SVM classifier. The effect of preprocessing of the vibration
signal by Discreet Wavelet Transform (DWT) prior to feature
extraction is also studied. It is shown from the experimental results
that the performance of SVM classifier in identification of bearing
condition is better then ANN and pre-processing of vibration signal
by DWT enhances the effectiveness of both ANN and SVM classifier
Abstract: Prospective readers can quickly determine whether a document is relevant to their information need if the significant phrases (or keyphrases) in this document are provided. Although keyphrases are useful, not many documents have keyphrases assigned to them, and manually assigning keyphrases to existing documents is costly. Therefore, there is a need for automatic keyphrase extraction. This paper introduces a new domain independent keyphrase extraction algorithm. The algorithm approaches the problem of keyphrase extraction as a classification task, and uses a combination of statistical and computational linguistics techniques, a new set of attributes, and a new machine learning method to distinguish keyphrases from non-keyphrases. The experiments indicate that this algorithm performs better than other keyphrase extraction tools and that it significantly outperforms Microsoft Word 2000-s AutoSummarize feature. The domain independence of this algorithm has also been confirmed in our experiments.
Abstract: In this paper, we propose a practical digital music matching system that is robust to variation in sound qualities. The proposed system is subdivided into two parts: client and server. The client part consists of the input, preprocessing and feature extraction modules. The preprocessing module, including the music onset module, revises the value gap occurring on the time axis between identical songs of different formats. The proposed method uses delta-grouped Mel frequency cepstral coefficients (MFCCs) to extract music features that are robust to changes in sound quality. According to the number of sound quality formats (SQFs) used, a music server is constructed with a feature database (FD) that contains different sub feature databases (SFDs). When the proposed system receives a music file, the selection module selects an appropriate SFD from a feature database; the selected SFD is subsequently used by the matching module. In this study, we used 3,000 queries for matching experiments in three cases with different FDs. In each case, we used 1,000 queries constructed by mixing 8 SQFs and 125 songs. The success rate of music matching improved from 88.6% when using single a single SFD to 93.2% when using quadruple SFDs. By this experiment, we proved that the proposed method is robust to various sound qualities.