Abstract: Automatic reading of handwritten cheque is a computationally
complex process and it plays an important role in financial
risk management. Machine vision and learning provide a viable
solution to this problem. Research effort has mostly been focused
on recognizing diverse pitches of cheques and demand drafts with an
identical outline. However most of these methods employ templatematching
to localize the pitches and such schemes could potentially
fail when applied to different types of outline maintained by the
bank. In this paper, the so-called outline problem is resolved by
a cheque information tree (CIT), which generalizes the localizing
method to extract active-region-of-entities. In addition, the weight
based density plot (WBDP) is performed to isolate text entities and
read complete pitches. Recognition is based on texture features using
neural classifiers. Legal amount is subsequently recognized by both
texture and perceptual features. A post-processing phase is invoked
to detect the incorrect readings by Type-2 grammar using the Turing
machine. The performance of the proposed system was evaluated
using cheque and demand drafts of 22 different banks. The test data
consists of a collection of 1540 leafs obtained from 10 different
account holders from each bank. Results show that this approach
can easily be deployed without significant design amendments.
Abstract: Certain tRNA synthetases have developed highly accurate molecular machinery to discriminate their cognate amino acids. Those aaRSs achieve their goal via editing reaction in the Connective Polypeptide 1 (CP1). Recently mutagenesis studies have revealed the critical importance of residues in the CP1 domain for editing activity and X-ray structures have shown binding mode of noncognate amino acids in the editing domain. To pursue molecular mechanism for amino acid discrimination, molecular modeling studies were performed. Our results suggest that aaRS bind the noncognate amino acid more tightly than the cognate one. Finally, by comparing binding conformations of the amino acids in three systems, the amino acid binding mode was elucidated and a discrimination mechanism proposed. The results strongly reveal that the conserved threonines are responsible for amino acid discrimination. This is achieved through side chain interactions between T252 and T247/T248 as well as between those threonines and the incoming amino acids.
Abstract: SEMG (Surface Electromyogram) is one of the
bio-signals and is generated from the muscle. And there are many
research results that use forearm EMG to detect hand motions. In this
paper, we will talk about our developed the robot hand system that can
control grasping power by SEMG. In our system, we suppose that
muscle power is proportional to the amplitude of SEMG. The power is
estimated and the grip power of a robot hand is able to be controlled
using estimated muscle power in our system. In addition, to perform a
more precise control can be considered to build a closed loop feedback
system as an object to a subject to pressure from the edge of hand. Our
objectives of this study are the development of a method that makes
perfect detection of the hand grip force possible using SEMG patterns,
and applying this method to the man-machine interface.
Abstract: As the Internet continues to grow at a rapid pace as
the primary medium for communications and commerce and as
telecommunication networks and systems continue to expand their
global reach, digital information has become the most popular and
important information resource and our dependence upon the
underlying cyber infrastructure has been increasing significantly.
Unfortunately, as our dependency has grown, so has the threat to the
cyber infrastructure from spammers, attackers and criminal
enterprises. In this paper, we propose a new machine learning based
network intrusion detection framework for cyber security. The
detection process of the framework consists of two stages: model
construction and intrusion detection. In the model construction stage,
a semi-supervised machine learning algorithm is applied to a
collected set of network audit data to generate a profile of normal
network behavior and in the intrusion detection stage, input network
events are analyzed and compared with the patterns gathered in the
profile, and some of them are then flagged as anomalies should these
events are sufficiently far from the expected normal behavior. The
proposed framework is particularly applicable to the situations where
there is only a small amount of labeled network training data
available, which is very typical in real world network environments.
Abstract: The use of machine vision to inspect the outcome of
surgical tasks is investigated, with the aim of incorporating this
approach in robotic surgery systems. Machine vision is a non-contact
form of inspection i.e. no part of the vision system is in direct contact
with the patient, and is therefore well suited for surgery where
sterility is an important consideration,. As a proof-of-concept, three
primary surgical tasks for a common neurosurgical procedure were
inspected using machine vision. Experiments were performed on
cadaveric pig heads to simulate the two possible outcomes i.e.
satisfactory or unsatisfactory, for tasks involved in making a burr
hole, namely incision, retraction, and drilling. We identify low level
image features to distinguish the two outcomes, as well as report on
results that validate our proposed approach. The potential of using
machine vision in a surgical environment, and the challenges that
must be addressed, are identified and discussed.
Abstract: This work presents the results of a study carried out to
determine the sliding wear behavior and its effect on the process
parameters of components manufactured by direct metal laser
sintering (DMLS). A standard procedure and specimen had been used
in the present study to find the wear behavior. Using Taguchi-s
experimental technique, an orthogonal array of modified L8 had been
developed. Sliding wear testing using pin-on-disk machine was
carried out and analysis of variance (ANOVA) technique was used to
investigate the effect of process parameters and to identify the main
process parameter that influences the properties of wear behavior on
the DMLS components. It has been found that part orientation, one
of the selected process parameter had more influence on wear as
compared to other selected process parameters.
Abstract: In this paper presented initial design of Low Speed
Axial Flux Permanent Magnet (AFPM) Machine with Non-Slotted
TORUS topology type by use of certain algorithm (Appendix).
Validation of design algorithm studied by means of selected data of
an initial prototype machine. Analytically design calculation carried
out by means of design algorithm and obtained results compared with
results of Finite Element Method (FEM).
Abstract: This paper discusses coordinated reactive power -
voltage (Q-V) control in a multi machine steam power plant. The
drawbacks of manual Q-V control are briefly listed, and the design
requirements for coordinated Q-V controller are specified.
Theoretical background and mathematical model of the new
controller are presented next followed by validation of developed
Matlab/Simulink model through comparison with recorded
responses in real steam power plant and description of practical
realisation of the controller. Finally, the performance of
commissioned controller is illustrated on several examples of
coordinated Q-V control in real steam power plant and compared
with manual control.
Abstract: This paper presents a systematic procedure for modelling and simulation of a power system installed with a power system stabilizer (PSS) and a flexible ac transmission system (FACTS)-based controller. For the design purpose, the model of example power system which is a single-machine infinite-bus power system installed with the proposed controllers is developed in MATLAB/SIMULINK. In the developed model synchronous generator is represented by model 1.1. which includes both the generator main field winding and the damper winding in q-axis so as to evaluate the impact of PSS and FACTS-based controller on power system stability. The model can be can be used for teaching the power system stability phenomena, and also for research works especially to develop generator controllers using advanced technologies. Further, to avoid adverse interactions, PSS and FACTS-based controller are simultaneously designed employing genetic algorithm (GA). The non-linear simulation results are presented for the example power system under various disturbance conditions to validate the effectiveness of the proposed modelling and simultaneous design approach.
Abstract: The amount of the information being churned out by the field of biology has jumped manifold and now requires the extensive use of computer techniques for the management of this information. The predominance of biological information such as protein sequence similarity in the biological information sea is key information for detecting protein evolutionary relationship. Protein sequence similarity typically implies homology, which in turn may imply structural and functional similarities. In this work, we propose, a learning method for detecting remote protein homology. The proposed method uses a transformation that converts protein sequence into fixed-dimensional representative feature vectors. Each feature vector records the sensitivity of a protein sequence to a set of amino acids substrings generated from the protein sequences of interest. These features are then used in conjunction with support vector machines for the detection of the protein remote homology. The proposed method is tested and evaluated on two different benchmark protein datasets and it-s able to deliver improvements over most of the existing homology detection methods.
Abstract: This paper presents a recognition system for isolated
words like robot commands. It’s carried out by Time Delay Neural
Networks; TDNN. To teleoperate a robot for specific tasks as turn,
close, etc… In industrial environment and taking into account the
noise coming from the machine. The choice of TDNN is based on its
generalization in terms of accuracy, in more it acts as a filter that
allows the passage of certain desirable frequency characteristics of
speech; the goal is to determine the parameters of this filter for
making an adaptable system to the variability of speech signal and to
noise especially, for this the back propagation technique was used in
learning phase. The approach was applied on commands pronounced
in two languages separately: The French and Arabic. The results for
two test bases of 300 spoken words for each one are 87%, 97.6% in
neutral environment and 77.67%, 92.67% when the white Gaussian
noisy was added with a SNR of 35 dB.
Abstract: In this study, the use of silicon NAM (Non-Audible
Murmur) microphone in automatic speech recognition is presented.
NAM microphones are special acoustic sensors, which are attached
behind the talker-s ear and can capture not only normal (audible)
speech, but also very quietly uttered speech (non-audible murmur).
As a result, NAM microphones can be applied in automatic speech
recognition systems when privacy is desired in human-machine communication.
Moreover, NAM microphones show robustness against
noise and they might be used in special systems (speech recognition,
speech conversion etc.) for sound-impaired people. Using a small
amount of training data and adaptation approaches, 93.9% word
accuracy was achieved for a 20k Japanese vocabulary dictation
task. Non-audible murmur recognition in noisy environments is also
investigated. In this study, further analysis of the NAM speech has
been made using distance measures between hidden Markov model
(HMM) pairs. It has been shown the reduced spectral space of NAM
speech using a metric distance, however the location of the different
phonemes of NAM are similar to the location of the phonemes
of normal speech, and the NAM sounds are well discriminated.
Promising results in using nonlinear features are also introduced,
especially under noisy conditions.
Abstract: Knowledge is indispensable but voluminous knowledge becomes a bottleneck for efficient processing. A great challenge for data mining activity is the generation of large number of potential rules as a result of mining process. In fact sometimes result size is comparable to the original data. Traditional data mining pruning activities such as support do not sufficiently reduce the huge rule space. Moreover, many practical applications are characterized by continual change of data and knowledge, thereby making knowledge voluminous with each change. The most predominant representation of the discovered knowledge is the standard Production Rules (PRs) in the form If P Then D. Michalski & Winston proposed Censored Production Rules (CPRs), as an extension of production rules, that exhibit variable precision and supports an efficient mechanism for handling exceptions. A CPR is an augmented production rule of the form: If P Then D Unless C, where C (Censor) is an exception to the rule. Such rules are employed in situations in which the conditional statement 'If P Then D' holds frequently and the assertion C holds rarely. By using a rule of this type we are free to ignore the exception conditions, when the resources needed to establish its presence, are tight or there is simply no information available as to whether it holds or not. Thus the 'If P Then D' part of the CPR expresses important information while the Unless C part acts only as a switch changes the polarity of D to ~D. In this paper a scheme based on Dempster-Shafer Theory (DST) interpretation of a CPR is suggested for discovering CPRs from the discovered flat PRs. The discovery of CPRs from flat rules would result in considerable reduction of the already discovered rules. The proposed scheme incrementally incorporates new knowledge and also reduces the size of knowledge base considerably with each episode. Examples are given to demonstrate the behaviour of the proposed scheme. The suggested cumulative learning scheme would be useful in mining data streams.
Abstract: Automated material handling is given prime
importance in the semi automated and automated facilities since it
provides solution to the gigantic problems related to inventory and
also support the latest philosophies like just in time production JIT
and lean production. Automated storage and retrieval system is an
antidote (if designed properly) to the facility sufferings like getting
the right material , materials getting perished, long cycle times or
many other similar kind of problems. A working model of automated
storage and retrieval system (AS/RS) is designed and developed
under the design parameters specified by Material Handling Industry
of America (MHIA). Later on analysis was carried out to calculate
the throughput and size of the machine. The possible implementation
of this technology in local scenario is also discussed in this paper.
Abstract: A lot of research made during these last 15 years
showed that the quantification of the springback has a significant role
in the industry of sheet metal forming. These studies were made with
the objective of finding techniques and methods to minimize or
completely avoid this permanent physical variation. Moreover, the
use of steel and aluminum alloys in the car industry and aviation
poses every day the problem of the springback. The determination in
advance of the quantity of the springback allows consequently the
design and manufacture of the tool. The aim of this paper is to study
experimentally the influence of the blank holder force BHF and the
radius of curvature of the die on the springback and their influence on
the strain in various zone of specimen.
The original of our purpose consist on tests which are ensured by
adapting a U-type stretching-bending device on a tensile testing
machine, where we studied and quantified the variation of the
springback according to displacement.
Abstract: This paper analyses the torsional efforts in gas turbine-generator shafts caused by high speed automatic reclosing of transmission lines. This issue is especially important for cases of three phase short circuit and unsuccessful reclosure of lines in the vicinity of the thermal plant. The analysis was carried out for the thermal plant TERMOPERNAMBUCO located on Northeast region of Brazil. It is shown that stress level caused by lines unsuccessful reclosing can be several times higher than terminal three-phase short circuit. Simulations were carried out with detailed shaft torsional model provided by machine manufacturer and with the “Alternative Transient Program – ATP" program [1]. Unsuccessful three phase reclosing for selected lines in the area closed to the plant indicated most critical cases. Also, reclosing first the terminal next to the gas turbine gererator will lead also to the most critical condition. Considering that the values of transient torques are very sensible to the instant of reclosing, simulation of unsuccessful reclosing with statistics ATP switch were carried out for determination of most critical transient torques for each section of the generator turbine shaft.
Abstract: The aim of this study was to determine noise level of
six different types of machines in printing companies in Novi Sad.
The A-weighted levels on Leq, Lmax and Lmin Sound Pressure Level
(SPL) in dBA were measured. It was found that the folders, offset
printing presses and binding machines are the predominant noise
sources. The noise levels produced by 12 of 38 machines exceed the
limiting threshold level of 85 dBA, tolerated by law. Since it was
determined that the average noise level for folders (87.7 dB) exceeds
the permitted value the octave analysis of noise was performed.
Abstract: The operating control parameters of injection
flushing type of electrical discharge machining process on stainless
steel 304 workpiece using copper tools are being optimized
according to its individual machining characteristic i.e. Electrode
Wear Ratio (EWR). Higher EWR would give bad dimensional
precision for the EDM machined workpiece because of high
electrode wear. Hence, the quality characteristic for EWR is set to
lower-the-better to achieve the optimum dimensional precision for
the machined workpiece. Taguchi method has been used for the
construction, layout and analysis of the experiment for EWR
machining characteristic. The use of Taguchi method in the
experiment saves a lot of time and cost of preparing and machining
the experiment samples. Therefore, an L18 Orthogonal array
which was the fundamental component in the statistical design of
experiments has been used to plan the experiments and Analysis of
Variance (ANOVA) is used to determine the optimum machining
parameters for this machining characteristic. The control
parameters selected for this optimization experiments are polarity,
pulse on duration, discharge current, discharge voltage, machining
depth, machining diameter and dielectric liquid pressure. The
result had shown that negative polarity machining parameter
setting will decreases EWR.
Abstract: Optimal selection of electrical insulations in electrical
machinery insures reliability during operation. From the insulation
studies of view for electrical machines, stator is the most important
part. This fact reveals the requirement for inspection of the electrical
machine insulation along with the electro-thermal stresses. In the
first step of the study, a part of the whole structure of machine in
which covers the general characteristics of the machine is chosen,
then based on the electromagnetic analysis (finite element method),
the machine operation is simulated. In the simulation results, the
temperature distribution of the total structure is presented
simultaneously by using electro-thermal analysis. The results of
electro-thermal analysis can be used for designing an optimal cooling
system. In order to design, review and comparing the cooling
systems, four wiring structures in the slots of Stator are presented.
The structures are compared to each other in terms of electrical,
thermal distribution and remaining life of insulation by using Finite
Element analysis. According to the steps of the study, an optimization
algorithm has been presented for selection of appropriate structure.
Abstract: In this paper, a novel algorithm based on Ridgelet
Transform and support vector machine is proposed for human action
recognition. The Ridgelet transform is a directional multi-resolution
transform and it is more suitable for describing the human action by
performing its directional information to form spatial features
vectors. The dynamic transition between the spatial features is carried
out using both the Principal Component Analysis and clustering
algorithm K-means. First, the Principal Component Analysis is used
to reduce the dimensionality of the obtained vectors. Then, the kmeans
algorithm is then used to perform the obtained vectors to form
the spatio-temporal pattern, called set-of-labels, according to given
periodicity of human action. Finally, a Support Machine classifier is
used to discriminate between the different human actions. Different
tests are conducted on popular Datasets, such as Weizmann and
KTH. The obtained results show that the proposed method provides
more significant accuracy rate and it drives more robustness in very
challenging situations such as lighting changes, scaling and dynamic
environment