Abstract: Detection of player identity is challenging task in sport video content analysis. In case of soccer video player number recognition is effective and precise solution. Jersey numbers can be considered as scene text and difficulties in localization and recognition appear due to variations in orientation, size, illumination, motion etc. This paper proposed new method for player number localization and recognition. By observing hue, saturation and value for 50 different jersey examples we noticed that most often combination of low and high saturated pixels is used to separate number and jersey region. Image segmentation method based on this observation is introduced. Then, novel method for player number localization based on internal contours is proposed. False number candidates are filtered using area and aspect ratio. Before OCR processing extracted numbers are enhanced using image smoothing and rotation normalization.
Abstract: In this paper we propose a method for recognition of
adult video based on support vector machine (SVM). Different kernel
features are proposed to classify adult videos. SVM has an advantage
that it is insensitive to the relative number of training example in
positive (adult video) and negative (non adult video) classes. This
advantage is illustrated by comparing performance between different
SVM kernels for the identification of adult video.
Abstract: In this paper, we propose a new modular approach called neuroglial consisting of two neural networks slow and fast which emulates a biological reality recently discovered. The implementation is based on complex multi-time scale systems; validation is performed on the model of the asynchronous machine. We applied the geometric approach based on the Gerschgorin circles for the decoupling of fast and slow variables, and the method of singular perturbations for the development of reductions models.
This new architecture allows for smaller networks with less complexity and better performance in terms of mean square error and convergence than the single network model.
Abstract: Route bus system is the fundamental public transportation
system and has an important role in every province. To improve
the usability of it greatly, we develop an AR application for "Bus-
Net". The Bus-Net system is the shortest path planning system.
Bus-Net supports bus users to make a plan to change buses by
providing them with information about the direction. However, with
Bus-Net, these information are provided in text-base. It is difficult
to understand them for the person who does not know the place. We
developed the AR application for Bus-Net. It supports the action of
a bus user in an innovative way by putting information on a camera
picture and leading the way to a bus stop. The application also inform
the user the correct bus to get, the direction the bus takes and the
fare, which ease many anxieties and worries people tend to feel when
they take buses.
Abstract: One very interesting field of research in Pattern Recognition that has gained much attention in recent times is Gesture Recognition. In this paper, we consider a form of dynamic hand gestures that are characterized by total movement of the hand (arm) in space. For these types of gestures, the shape of the hand (palm) during gesturing does not bear any significance. In our work, we propose a model-based method for tracking hand motion in space, thereby estimating the hand motion trajectory. We employ the dynamic time warping (DTW) algorithm for time alignment and normalization of spatio-temporal variations that exist among samples belonging to the same gesture class. During training, one template trajectory and one prototype feature vector are generated for every gesture class. Features used in our work include some static and dynamic motion trajectory features. Recognition is accomplished in two stages. In the first stage, all unlikely gesture classes are eliminated by comparing the input gesture trajectory to all the template trajectories. In the next stage, feature vector extracted from the input gesture is compared to all the class prototype feature vectors using a distance classifier. Experimental results demonstrate that our proposed trajectory estimator and classifier is suitable for Human Computer Interaction (HCI) platform.
Abstract: An accident is an unexpected and unplanned situation
that happens and affects human in a negative outcome. The accident
can cause an injury to a human biological organism. Thus, the
provision of initial care for an illness or injury is very important
move to prepare the patients/victims before sending to the doctor. In
this paper, a First Aid Application is developed to give some
directions for preliminary taking care of patient/victim via Android
mobile device. Also, the navigation function using Google Maps API
is implemented in this paper for searching a suitable path to the
nearest hospital. Therefore, in the emergency case, this function can
be activated and navigate patients/victims to the hospital with the
shortest path.
Abstract: The design of chaos-based secure communication
via synchronized modified Chua-s systems is investigated in
this paper. A continuous control law is proposed to ensure
synchronization of the master and slave modified Chua-s
systems by using the variable structure control technique.
Particularly, the concept of extended systems is introduced
such that a continuous control input is obtained to avoid
chattering phenomenon. Then, it becomes possible to ensure
that the message signal embedded in the transmitter can be
recovered in the receiver.
Abstract: In the self-stabilizing algorithmic paradigm, each node has a local view of the system, in a finite amount of time the system converges to a global state with desired property. In a graph G =
(V, E), a subset S C V is a 2-packing if Vi c V: IN[i] n SI
Abstract: Whit the increasing of traffic, noise emanated from
motor vehicles increases as well, which subsequently causes adding
to the stress of modern city. Thus, it is needed to look for most
critical areas in terms of environmental and social impact of noise.
There are several critical situations for noise emanated from motor
vehicles such as stop and go situation which usually occurs near
junctions or at-grade intersections. This study was conducted in two
locations, most common types of intersections, crossroads and Tjunctions.
The highest average noise levels are recorded during Go
phase for T-junction, 64.4 dB, and Drive phase for crossroad, 64 dB.
It implies that the existence of intersection caused the noise level to
increase. The vehicles starting to move produce more sound than
when they travel at a constant speed along the intersection. It is
suggested that special considerations and priority of allocating funds
should be given to these critical spots.
Abstract: This paper investigates the problem of exponential stability for a class of uncertain discrete-time stochastic neural network with time-varying delays. By constructing a suitable Lyapunov-Krasovskii functional, combining the stochastic stability theory, the free-weighting matrix method, a delay-dependent exponential stability criteria is obtained in term of LMIs. Compared with some previous results, the new conditions obtain in this paper are less conservative. Finally, two numerical examples are exploited to show the usefulness of the results derived.
Abstract: The Kansei engineering is a technology which
converts human feelings into quantitative terms and helps designers
develop new products that meet customers- expectation. Standard
Kansei engineering procedure involves finding relationships between
human feelings and design elements of which many researchers have
found forward and backward relationship through various soft
computing techniques. In this paper, we proposed the framework of
Kansei engineering linking relationship not only between human
feelings and design elements, but also the whole part of product, by
constructing association rules. In this experiment, we obtain input
from emotion score that subjects rate when they see the whole part of
the product by applying semantic differentials. Then, association
rules are constructed to discover the combination of design element
which affects the human feeling. The results of our experiment
suggest the pattern of relationship of design elements according to
human feelings which can be derived from the whole part of product.
Abstract: Diagnostic goal of transformers in service is to detect the winding or the core in fault. Transformers are valuable equipment which makes a major contribution to the supply security of a power system. Consequently, it is of great importance to minimize the frequency and duration of unwanted outages of power transformers. So, Frequency Response Analysis (FRA) is found to be a useful tool for reliable detection of incipient mechanical fault in a transformer, by finding winding or core defects. The authors propose as first part of this article, the coupled circuits method, because, it gives most possible exhaustive modelling of transformers. And as second part of this work, the application of FRA in low frequency in order to improve and simplify the response reading. This study can be useful as a base data for the other transformers of the same categories intended for distribution grid.
Abstract: This work investigated the steady state and dynamic
simulation of a fixed bed industrial naphtha reforming reactors. The
performance of the reactor was investigated using a heterogeneous
model. For process simulation, the differential equations are solved
using the 4th order Runge-Kutta method .The models were validated
against measured process data of an existing naphtha reforming plant.
The results of simulation in terms of components yields and
temperature of the outlet were in good agreement with empirical data.
The simple model displays a useful tool for dynamic simulation,
optimization and control of naphtha reforming.
Abstract: Phase transformation temperature is one of the most important parameters for the shape memory alloys (SMAs). The most popular method to determine these phase transformation temperatures is the Differential Scanning Calorimeter (DSC), but due to the limitation of the DSC testing itself, it made it difficult for the finished product which is not in the powder form. A novel method which uses the Universal Testing Machine has been conducted to determine the phase transformation temperatures. The Flexinol wire was applied with force and maintained throughout the experiment and at the same time it was heated up slowly until a temperature of approximately 1000C with direct current. The direct current was then slowly decreased to cool down the temperature of the Flexinol wire. All the phase transformation temperatures for Flexinol wire were obtained. The austenite start at 52.540C and austenite finish at 60.900C, while martensite start at 44.780C and martensite finish at 32.840C.
Abstract: Elementary particles are created in pairs of equal and opposite momentums at a reference frame at the speed of light. The speed of light reference frame is viewed as a point in space as observed by observer at rest. This point in space is the bang location of the big bang theory. The bang in the big bang theory is not more than sustained flow of pairs of positive and negative elementary particles. Electrons and negative charged elementary particles are ejected from this point in space at velocities faster than light, while protons and positively charged particles obtain velocities lower than light. Subsonic masses are found to have real and positive charge, while supersonic masses are found to be negative and imaginary indicating that the two masses are of different entities. The electron-s super-sonic speed, as viewed by rest observer was calculated and found to be less than the speed of light and is little higher than the electron speed in Bohr-s orbit. The newly formed hydrogen gas temperature was found to be in agreement with temperatures found on newly formed stars. Universe expansion was found to be in agreement. Partial mass and charge elementary particles and particles with momentum only were explained in the context of this theoretical approach.
Abstract: Iodine radionuclides in accident releases under severe
accident conditions at NPP with VVER are the most radiationimportant
with a view to population dose generation at the beginning
of the accident. To decrease radiation consequences of severe
accidents the technical solutions for severe accidents management
have been proposed in MIR.1200 project, with consideration of the
measures for suppression of volatile iodine forms generation in the
containment. Behavior dynamics of different iodine forms in the
containment under severe accident conditions has been analyzed for
the purpose of these technical solutions justification.
Abstract: When the crisscross baffles and logarithmic spiral
baffles are placed on the bottom of the stirred tank with elliptic
bottom, using CFD software FLUENT simulates the velocity field of
the stirred tank with elliptic bottom and bottom baffles. Compare the
velocity field of stirred tank with bottom crisscross baffle to the
velocity field of stirred tank without bottom baffle and analysis the
flow pattern on the same axis-section and different cross-sections. The
sizes of the axial and radial velocity are compared respectively when
the stirred tank with bottom crisscross baffles, bottom logarithmic
spiral baffles and without bottom baffle. At the same time, the
numerical calculations of mixing power are compared when the stirred
tank with bottom crisscross baffles and bottom logarithmic spiral
baffles. Research shows that bottom crisscross baffles and logarithmic
spiral baffles have a great impact on flow pattern within the reactor
and improve the mixing effect better than without baffle. It also has
shown that bottom logarithmic spiral baffles has lower power
consumption than bottom crisscross baffles.
Abstract: The aim of this studywas toinvestigate the effect
ofrunning classification (sprint, middle, and long distance)and two
distances on blood lactate (BLa), heart rate (HR), and rating of
perceived exertion (RPE) Borg scale ratings in collegiate athletes. On
different days, runners (n = 15) ran 400m and 1600m at a five min
mile pace, followed by a two min 6mph jog, and a two min 3mph
walk as part of the cool down. BLa, HR, and RPE were taken at
baseline, post-run, plus 2 and 4 min recovery times. The middle and
long distance runners exhibited lower BLa concentrations than sprint
runners after two min of recovery post 400 m runs, immediately after,
and two and four min recovery periods post 1600 m runs. When
compared to sprint runners, distance runners may have exhibited the
ability to clear BLa more quickly, particularly after running 1600 m.
Abstract: The existence of many biological systems,
especially human societies, is based on cooperative behavior
[1, 2]. If natural selection favors selfish individuals, then what
mechanism is at work that we see so many cooperative
behaviors? One answer is the effect of network structure. On a
graph, cooperators can evolve by forming network bunches
[2, 3, 4]. In a research, Ohtsuki et al used the idea of iterated
prisoners- dilemma on a graph to model an evolutionary
game. They showed that the average number of neighbors
plays an important role in determining whether cooperation is
the ESS of the system or not [3]. In this paper, we are going to
study the dynamics of evolution of cooperation in a social
network. We show that during evolution, the ratio of
cooperators among individuals with fewer neighbors to
cooperators among other individuals is greater than unity. The
extent to which the fitness function depends on the payoff of
the game determines this ratio.
Abstract: Classification is an interesting problem in functional
data analysis (FDA), because many science and application problems
end up with classification problems, such as recognition, prediction,
control, decision making, management, etc. As the high dimension
and high correlation in functional data (FD), it is a key problem to
extract features from FD whereas keeping its global characters, which
relates to the classification efficiency and precision to heavens. In this
paper, a novel automatic method which combined Genetic Algorithm
(GA) and classification algorithm to extract classification features is
proposed. In this method, the optimal features and classification model
are approached via evolutional study step by step. It is proved by
theory analysis and experiment test that this method has advantages in
improving classification efficiency, precision and robustness whereas
using less features and the dimension of extracted classification
features can be controlled.