Abstract: On-line handwritten scripts are usually dealt with pen tip traces from pen-down to pen-up positions. Time evaluation of the pen coordinates is also considered along with trajectory information. However, the data obtained needs a lot of preprocessing including filtering, smoothing, slant removing and size normalization before recognition process. Instead of doing such lengthy preprocessing, this paper presents a simple approach to extract the useful character information. This work evaluates the use of the counter- propagation neural network (CPN) and presents feature extraction mechanism in full detail to work with on-line handwriting recognition. The obtained recognition rates were 60% to 94% using the CPN for different sets of character samples. This paper also describes a performance study in which a recognition mechanism with multiple thresholds is evaluated for counter-propagation architecture. The results indicate that the application of multiple thresholds has significant effect on recognition mechanism. The method is applicable for off-line character recognition as well. The technique is tested for upper-case English alphabets for a number of different styles from different peoples.
Abstract: Application of pesticides in the paddy fields has
deleterious effects on non-target organisms including cyanobacteria
which are photosynthesizing and nitrogen fixing micro-organisms
contributing significantly towards soil fertility and crop yield.
Pesticide contamination in the paddy fields has manifested into a
serious global environmental concern. To study the effect of one such
pesticide, three cyanobacterial strains; Anabaena fertilissima,
Aulosira fertilissima and Westiellopsis prolifica were selected for
their stress responses to an Organochlorine insecticide - 6, 7, 8, 9, 10,
10-hexachloro-1, 5, 5a, 6, 9, 9a-hexahydro-6, 9-methano-2, 4, 3-
benzodioxathiepine-3-oxide, with reference to their photosynthesic
pigments-chlorophyll-a and carotenoids as well as accessory
pigments-phycobiliproteins (phycocyanin, allophycocyanin and
phycoerythrin), stress induced biochemical metabolites like
carbohydrates, proteins, amino acids, phenols and enzymes-nitrate
reductase, glutamine synthetase and succinate dehydrogenase. All
the three cyanobacterial strains were adversely affected by the
insecticide doses and inhibition was dose dependent. Reduction in
photosynthetic and accessory pigments, metabolites, nitrogen fixing
and respiratory enzymes of the test organisms were accompanied
with an initial increase in their total protein at lower Organochlorine
doses. On the other hand, increased amount of phenols in all the
insecticide treated concentrations was indicative of stressed activities
of the organisms.
Abstract: Realistic 3D face model is more precise in representing
pose, illumination, and expression of face than 2D face model so that it
can be utilized usefully in various applications such as face recognition,
games, avatars, animations, and etc.
In this paper, we propose a 3D face modeling method based on 3D
dense morphable shape model. The proposed 3D modeling method
first constructs a 3D dense morphable shape model from 3D face scan
data obtained using a 3D scanner. Next, the proposed method extracts
and matches facial landmarks from 2D image sequence containing a
face to be modeled, and then reconstructs 3D vertices coordinates of
the landmarks using a factorization-based SfM technique. Then, the
proposed method obtains a 3D dense shape model of the face to be
modeled by fitting the constructed 3D dense morphable shape model
into the reconstructed 3D vertices. Also, the proposed method makes a
cylindrical texture map using 2D face image sequence. Finally, the
proposed method generates a 3D face model by rendering the 3D dense
face shape model using the cylindrical texture map. Through building
processes of 3D face model by the proposed method, it is shown that
the proposed method is relatively easy, fast and precise.
Abstract: Electronic commerce is growing rapidly with on-line
sales already heading for hundreds of billion dollars per year. Due to
the huge amount of money transferred everyday, an increased
security level is required. In this work we present the architecture of
an intelligent speaker verification system, which is able to accurately
verify the registered users of an e-commerce service using only their
voices as an input. According to the proposed architecture, a
transaction-based e-commerce application should be complemented
by a biometric server where customer-s unique set of speech models
(voiceprint) is stored. The verification procedure requests from the
user to pronounce a personalized sequence of digits and after
capturing speech and extracting voice features at the client side are
sent back to the biometric server. The biometric server uses pattern
recognition to decide whether the received features match the stored
voiceprint of the customer who claims to be, and accordingly grants
verification. The proposed architecture can provide e-commerce
applications with a higher degree of certainty regarding the identity
of a customer, and prevent impostors to execute fraudulent
transactions.
Abstract: In this article two algorithms, one based on variation iteration method and the other on Adomian's decomposition method, are developed to find the numerical solution of an initial value problem involving the non linear integro differantial equation where R is a nonlinear operator that contains partial derivatives with respect to x. Special cases of the integro-differential equation are solved using the algorithms. The numerical solutions are compared with analytical solutions. The results show that these two methods are efficient and accurate with only two or three iterations
Abstract: The paper presents a multimodal approach for biometric authentication, based on multiple classifiers. The proposed solution uses a post-classification biometric fusion method in which the biometric data classifiers outputs are combined in order to improve the overall biometric system performance by decreasing the classification error rates. The paper shows also the biometric recognition task improvement by means of a carefully feature selection, as much as not all of the feature vectors components support the accuracy improvement.
Abstract: Needs of an efficient information retrieval in recent
years in increased more then ever because of the frequent use of
digital information in our life. We see a lot of work in the area of
textual information but in multimedia information, we cannot find
much progress. In text based information, new technology of data
mining and data marts are now in working that were started from the
basic concept of database some where in 1960.
In image search and especially in image identification,
computerized system at very initial stages. Even in the area of image
search we cannot see much progress as in the case of text based
search techniques. One main reason for this is the wide spread roots
of image search where many area like artificial intelligence,
statistics, image processing, pattern recognition play their role. Even
human psychology and perception and cultural diversity also have
their share for the design of a good and efficient image recognition
and retrieval system.
A new object based search technique is presented in this paper
where object in the image are identified on the basis of their
geometrical shapes and other features like color and texture where
object-co-relation augments this search process.
To be more focused on objects identification, simple images are
selected for the work to reduce the role of segmentation in overall
process however same technique can also be applied for other
images.
Abstract: An exploratory computational investigation using
RANS & URANS was carried out to understand the aerodynamics
around an isolatedsingle rotating wheel with decreasing ground
proximity. The wheel was initially modeled in free air conditions,
then with decreasing ground proximity and increased yaw angle with
rotational speeds. Three speeds of rotation were applied to the wheel
so that the effect of different angular velocities can be investigated. In
addition to rotation, three different yaw angles were applied to the
rotating wheel in order to understand how these two variables
combined affect the aerodynamic flow field around the wheel.
Abstract: For cognitive radio networks, there is a major
spectrum sensing problem, i.e. dynamic spectrum management. It is
an important issue to sense and identify the spectrum holes in
cognitive radio networks. The first-order derivative scheme is usually
used to detect the edge of the spectrum. In this paper, a novel
spectrum sensing technique for cognitive radio is presented. The
proposed algorithm offers efficient edge detection. Then, simulation
results show the performance of the first-order derivative scheme and
the proposed scheme and depict that the proposed scheme obtains
better performance than does the first-order derivative scheme.
Abstract: Thrombosis can be life threatening, necessitating therefore its instant treatment. Hydergine, a nootropic agent is used as a cognition enhancer in stroke patients but relatively little is known about its anti-thrombolytic effect. To investigate this aspect, in vivo and ex vivo experiments were designed and conducted. Three groups of rats were injected 1.5mg, 3.0mg and 4.5mg hydergine intraperitonealy with and without prior exposure to fresh plasma. Positive and negative controls were run in parallel. Animals were sacrificed after 1.5hrs and BT, CT, PT, INR, APTT, plasma calcium levels were estimated. For ex vivo analyses, each 1ml blood aspirated was exposed to 0.1mg, 0.2mg, 0.3mg dose of hydergine with parallel controls. Parameters analyzed were as above. Statistical analysis was through one-way ANOVA. Dunken-s and Tukey-s tests provided intra-group variance. BT, CT, PT, INR and APTT increased while calcium levels dropped significantly (P
Abstract: Active research is underway on virtual touch screens
that complement the physical limitations of conventional touch
screens. This paper discusses a virtual touch screen that uses a
multi-layer perceptron to recognize and control three-dimensional
(3D) depth information from a time of flight (TOF) camera. This
system extracts an object-s area from the image input and compares it
with the trajectory of the object, which is learned in advance, to
recognize gestures. The system enables the maneuvering of content in
virtual space by utilizing human actions.
Abstract: This study proposes novel hybrid social network analysis and collaborative filtering approach to enhance the performance of recommender systems. The proposed model selects subgroups of users in Internet community through social network analysis (SNA), and then performs clustering analysis using the information about subgroups. Finally, it makes recommendations using cluster-indexing CF based on the clustering results. This study tries to use the cores in subgroups as an initial seed for a conventional clustering algorithm. This model chooses five cores which have the highest value of degree centrality from SNA, and then performs clustering analysis by using the cores as initial centroids (cluster centers). Then, the model amplifies the impact of friends in social network in the process of cluster-indexing CF.
Abstract: This study aimed to develop and initially validate an instrument that measures social competency among tertiary level faculty members. A review of extant literature on social competence was done. The review of extant literature led to the writing of the items in the initial instrument which was evaluated by 11 Subject Matter Experts (SMEs). The SMEs were either educators or psychologists. The results of the evaluations done by the SMEs served as bases for the creation of the pre-try-out instrument used in the first trial-run. Insights from the first trial-run participants led to the development of the main try-out instrument used in the final test administration. One Hundred Forty-one participants from five private Higher Education Institutions (HEIs) in the National Capital Region (NCR) and five private HEIs in Central Luzon in the Philippines participated in the final test administration. The reliability of the instrument was evaluated using Cronbach-s Coefficient Alpha formula and had a Cronbach-s Alpha of 0.92. On the other hand, Factor Analysis was used to evaluate the validity of the instrument and six factors were identified. The development of the final instrument was based on the results of the evaluation of the instrument-s reliability and validity. For purposes of recognition, the instrument was named “Social Competency Inventory for Tertiary Level Faculty Members (SCI-TLFM)."
Abstract: The aim of this study is to compare the innovativeness, risk taking, and focusing on opportunity of the nurse managers and nurses. The data are collected from nurse managers and nurses in Ondokuz Mayıs University, Faculty of Medicine Hospital and Karadeniz Technical University, Faculty of Medicine Hospital. The study sample consisted of 151 participants, 76 nurse managers (50.3%) and 75 nurses (49.7%). All participants have been assessed by Participant Information Form and Corporate Entrepreneurship Scale. In data analysis, independent t-test has applied. The results show that there are significant differences between nurse managers and nurses on innovativeness (t = 2.42, p < 0.05), risk taking (t = 3.62, p < 0.01), and focusing on opportunity (t = 2.16, p < 0.05). Consequently, it can be said that nurse managers have more innovativeness than nurses and tend to take more risks and focus more on opportunities.
Abstract: There is an urgent need to conserve the biological diversity of the Nigerian Environment for the future and present generation in the face of current energy resources development. This paper gives an in-depth analysis of the impact of oil and gas activities on the biological diversity of the Nigerian Niger Delta area and its consequences on the sustainable development of the host communities as it relates to their social, economic and environmental issues, particularly on the womenfolk who are the key managers of environmental resources. Also reviewed is the frustration of these communities that is reflected in unending conflicts.
Abstract: A large section of the society in Urban India is unable
to afford a basic dwelling unit. Housing shortage due to the rising unafforability makes it logical to consider alternative technologies more seriously for their application How far do these alternative
technologies match up with the conventional techniques? How do these integrate with the present-day need for urban amenities and
facilities? Are the owners of bamboo dwellings, for instance, a part of
the mainstream housing sector, having the same rights and privileges
as those enjoyed by other property owners? Will they have access to loans for building, improving, renovating or repairing their
dwellings? Why do we still hesitate to build a bamboo house for ourselves? Is our policy framework and political resolve in place, to
welcome such alternative technologies? It is time we found these answers, in order to explore the reasons for large-scale nonacceptance,
of a technology proven for its worthiness.
Abstract: The objective of the present research manuscript is to
perform parametric, nonparametric, and decision tree analysis to
evaluate two treatments that are being used for breast cancer patients.
Our study is based on utilizing real data which was initially used in
“Tamoxifen with or without breast irradiation in women of 50 years
of age or older with early breast cancer" [1], and the data is supplied
to us by N.A. Ibrahim “Decision tree for competing risks survival
probability in breast cancer study" [2]. We agree upon certain aspects
of our findings with the published results. However, in this
manuscript, we focus on relapse time of breast cancer patients instead
of survival time and parametric analysis instead of semi-parametric
decision tree analysis is applied to provide more precise
recommendations of effectiveness of the two treatments with respect
to reoccurrence of breast cancer.
Abstract: Most neural network (NN) models of human category learning use a gradient-based learning method, which assumes that locally-optimal changes are made to model parameters on each learning trial. This method tends to under predict variability in individual-level cognitive processes. In addition many recent models of human category learning have been criticized for not being able to replicate rapid changes in categorization accuracy and attention processes observed in empirical studies. In this paper we introduce stochastic learning algorithms for NN models of human category learning and show that use of the algorithms can result in (a) rapid changes in accuracy and attention allocation, and (b) different learning trajectories and more realistic variability at the individual-level.
Abstract: An experiment of vented gas explosions involving two
different cylinder vessel volumes (0.2 and 0.0065 m3) was reported,
with equivalence ratio (Φ) ranged from 0.3 to 1.6. Both vessels were
closed at the rear end and fitted at the other side with a circular
orifice plate that gives a constant vent coefficient (K =Av/V2/3) of
16.4. It was shown that end ignition gives higher overpressures than
central ignition, even though most of the published work on venting
uses central ignition. For propane and ethylene, it is found that rich
mixtures gave the highest overpressures and these mixtures are not
considered in current vent design guidance; which the guideline is
based on mixtures giving the maximum flame temperature. A strong
influence of the vessel volume at constant K was found for methane,
propane, ethylene and hydrogen-air explosions. It can be concluded
that self- acceleration of the flame, which is dependent on the
distance of a flame from the ignition and the ‘suction’ at the vent
opening are significant factors affecting the vent flow during
explosion development in vented gas explosion. This additional
volume influence on vented explosions is not taken into account in
the current vent design guidance.
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.