Abstract: Currently, there are many local area industrial networks
that can give guaranteed bandwidth to synchronous traffic, particularly
providing CBR channels (Constant Bit Rate), which allow
improved bandwidth management. Some of such networks operate
over Ethernet, delivering channels with enough capacity, specially
with compressors, to integrate multimedia traffic in industrial monitoring
and image processing applications with many sources. In
these industrial environments where a low latency is an essential
requirement, JPEG is an adequate compressing technique but it
generates VBR traffic (Variable Bit Rate). Transmitting VBR traffic
in CBR channels is inefficient and current solutions to this problem
significantly increase the latency or further degrade the quality. In
this paper an R(q) model is used which allows on-line calculation of
the JPEG quantification factor. We obtained increased quality, a lower
requirement for the CBR channel with reduced number of discarded
frames along with better use of the channel bandwidth.
Abstract: Today, building automation is advancing from simple
monitoring and control tasks of lightning and heating towards more
and more complex applications that require a dynamic perception
and interpretation of different scenes occurring in a building. Current
approaches cannot handle these newly upcoming demands. In this
article, a bionically inspired approach for multimodal, dynamic scene
perception and interpretation is presented, which is based on neuroscientific
and neuro-psychological research findings about the perceptual
system of the human brain. This approach bases on data from diverse
sensory modalities being processed in a so-called neuro-symbolic
network. With its parallel structure and with its basic elements being
information processing and storing units at the same time, a very
efficient method for scene perception is provided overcoming the
problems and bottlenecks of classical dynamic scene interpretation
systems.
Abstract: Forecasting the values of the indicators, which
characterize the effectiveness of performance of organizations is of
great importance for their successful development. Such forecasting
is necessary in order to assess the current state and to foresee future
developments, so that measures to improve the organization-s
activity could be undertaken in time. The article presents an
overview of the applied mathematical and statistical methods for
developing forecasts. Special attention is paid to artificial neural
networks as a forecasting tool. Their strengths and weaknesses are
analyzed and a synopsis is made of the application of artificial neural
networks in the field of forecasting of the values of different
education efficiency indicators. A method of evaluation of the
activity of universities using the Balanced Scorecard is proposed and
Key Performance Indicators for assessment of e-learning are
selected. Resulting indicators for the evaluation of efficiency of the
activity are proposed. An artificial neural network is constructed and
applied in the forecasting of the values of indicators for e-learning
efficiency on the basis of the KPI values.
Abstract: Due to the coexistence of different Radio Access
Technologies (RATs), Next Generation Wireless Networks (NGWN)
are predicted to be heterogeneous in nature. The coexistence of
different RATs requires a need for Common Radio Resource
Management (CRRM) to support the provision of Quality of Service
(QoS) and the efficient utilization of radio resources. RAT selection
algorithms are part of the CRRM algorithms. Simply, their role is to
verify if an incoming call will be suitable to fit into a heterogeneous
wireless network, and to decide which of the available RATs is most
suitable to fit the need of the incoming call and admit it.
Guaranteeing the requirements of QoS for all accepted calls and at
the same time being able to provide the most efficient utilization of
the available radio resources is the goal of RAT selection algorithm.
The normal call admission control algorithms are designed for
homogeneous wireless networks and they do not provide a solution
to fit a heterogeneous wireless network which represents the NGWN.
Therefore, there is a need to develop RAT selection algorithm for
heterogeneous wireless network. In this paper, we propose an
approach for RAT selection which includes receiving different
criteria, assessing and making decisions, then selecting the most
suitable RAT for incoming calls. A comprehensive survey of
different RAT selection algorithms for a heterogeneous wireless
network is studied.
Abstract: Ultra-wide band (UWB) communication is one of
the most promising technologies for high data rate wireless networks
for short range applications. This paper proposes a blind channel
estimation method namely IMM (Interactive Multiple Model) Based
Kalman algorithm for UWB OFDM systems. IMM based Kalman
filter is proposed to estimate frequency selective time varying
channel. In the proposed method, two Kalman filters are concurrently
estimate the channel parameters. The first Kalman filter namely
Static Model Filter (SMF) gives accurate result when the user is static
while the second Kalman filter namely the Dynamic Model Filter
(DMF) gives accurate result when the receiver is in moving state. The
static transition matrix in SMF is assumed as an Identity matrix
where as in DMF, it is computed using Yule-Walker equations. The
resultant filter estimate is computed as a weighted sum of individual
filter estimates. The proposed method is compared with other existing
channel estimation methods.
Abstract: In this paper, a class of impulsive BAM fuzzy cellular neural networks with distributed delays and reaction-diffusion terms is formulated and investigated. By employing the delay differential inequality and inequality technique developed by Xu et al., some sufficient conditions ensuring the existence, uniqueness and global exponential stability of equilibrium point for impulsive BAM fuzzy cellular neural networks with distributed delays and reaction-diffusion terms are obtained. In particular, the estimate of the exponential convergence rate is also provided, which depends on system parameters, diffusion effect and impulsive disturbed intention. It is believed that these results are significant and useful for the design and applications of BAM fuzzy cellular neural networks. An example is given to show the effectiveness of the results obtained here.
Abstract: This paper presents an exact pruning algorithm with
adaptive pruning interval for general dynamic neural networks
(GDNN). GDNNs are artificial neural networks with internal dynamics.
All layers have feedback connections with time delays to the
same and to all other layers. The structure of the plant is unknown, so
the identification process is started with a larger network architecture
than necessary. During parameter optimization with the Levenberg-
Marquardt (LM) algorithm irrelevant weights of the dynamic neural
network are deleted in order to find a model for the plant as
simple as possible. The weights to be pruned are found by direct
evaluation of the training data within a sliding time window. The
influence of pruning on the identification system depends on the
network architecture at pruning time and the selected weight to be
deleted. As the architecture of the model is changed drastically during
the identification and pruning process, it is suggested to adapt the
pruning interval online. Two system identification examples show
the architecture selection ability of the proposed pruning approach.
Abstract: Today, node-disjoint routing becomes inessential
technique in communication of packets among various nodes in
networks. Meanwhile AODV (Ad Hoc On-demand Multipath
Distance Vector) creates single-path route between a pair of source
and destination nodes. Some researches has done so far to make
multipath node-disjoint routing based on AODV protocol. But
however their overhead and end-to-end delay are relatively high,
while the detail of their code is not available too. This paper proposes
a new approach of multipath node-disjoint routing based on AODV
protocol. Then the algorithm of analytical model is presented. The
extensive results of this algorithm will be presented in the next paper.
Abstract: Saturated hydraulic conductivity is one of the soil
hydraulic properties which is widely used in environmental studies
especially subsurface ground water. Since, its direct measurement is
time consuming and therefore costly, indirect methods such as
pedotransfer functions have been developed based on multiple linear
regression equations and neural networks model in order to estimate
saturated hydraulic conductivity from readily available soil
properties e.g. sand, silt, and clay contents, bulk density, and organic
matter. The objective of this study was to develop neural networks
(NNs) model to estimate saturated hydraulic conductivity from
available parameters such as sand and clay contents, bulk density,
van Genuchten retention model parameters (i.e. r
θ , α , and n) as well
as effective porosity. We used two methods to calculate effective
porosity: : (1) eff s FC φ =θ -θ , and (2) inf φ =θ -θ eff s , in which s
θ is
saturated water content, FC θ is water content retained at -33 kPa
matric potential, and inf θ is water content at the inflection point.
Total of 311 soil samples from the UNSODA database was divided
into three groups as 187 for the training, 62 for the validation (to
avoid over training), and 62 for the test of NNs model. A commercial
neural network toolbox of MATLAB software with a multi-layer
perceptron model and back propagation algorithm were used for the
training procedure. The statistical parameters such as correlation
coefficient (R2), and mean square error (MSE) were also used to
evaluate the developed NNs model. The best number of neurons in
the middle layer of NNs model for methods (1) and (2) were
calculated 44 and 6, respectively. The R2 and MSE values of the test
phase were determined for method (1), 0.94 and 0.0016, and for
method (2), 0.98 and 0.00065, respectively, which shows that method
(2) estimates saturated hydraulic conductivity better than method (1).
Abstract: In this paper, the structural genetic algorithm is used to optimize the neural network to control the joint movements of robotic arm. The robotic arm has also been modeled in 3D and simulated in real-time in MATLAB. It is found that Neural Networks provide a simple and effective way to control the robot tasks. Computer simulation examples are given to illustrate the significance of this method. By combining Genetic Algorithm optimization method and Neural Networks for the given robotic arm with 5 D.O.F. the obtained the results shown that the base joint movements overshooting time without controller was about 0.5 seconds, while with Neural Network controller (optimized with Genetic Algorithm) was about 0.2 seconds, and the population size of 150 gave best results.
Abstract: Many multimedia communication applications require a
source to transmit messages to multiple destinations subject to quality
of service (QoS) delay constraint. To support delay constrained
multicast communications, computer networks need to guarantee an
upper bound end-to-end delay from the source node to each of
the destination nodes. This is known as multicast delay problem.
On the other hand, if the same message fails to arrive at each
destination node at the same time, there may arise inconsistency and
unfairness problem among users. This is related to multicast delayvariation
problem. The problem to find a minimum cost multicast
tree with delay and delay-variation constraints has been proven to
be NP-Complete. In this paper, we propose an efficient heuristic
algorithm, namely, Economic Delay and Delay-Variation Bounded
Multicast (EDVBM) algorithm, based on a novel heuristic function,
to construct an economic delay and delay-variation bounded multicast
tree. A noteworthy feature of this algorithm is that it has very high
probability of finding the optimal solution in polynomial time with
low computational complexity.
Abstract: The main goal of this seminal paper is to introduce the
application of Wireless Sensor Networks (WSN) in long distance
infrastructure monitoring (in particular in pipeline infrastructure
monitoring) – one of the on-going research projects by the Wireless
Communication Research Group at the department of Electronic and
Computer Engineering, Nnamdi Azikiwe University, Awka. The
current sensor network architectures for monitoring long distance
pipeline infrastructures are previewed. These are wired sensor
networks, RF wireless sensor networks, integrated wired and wireless
sensor networks. The reliability of these architectures is discussed.
Three reliability factors are used to compare the architectures in
terms of network connectivity, continuity of power supply for the
network, and the maintainability of the network. The constraints and
challenges of wireless sensor networks for monitoring and protecting
long distance pipeline infrastructure are discussed.
Abstract: In the past few years, the use of wireless sensor networks (WSNs) potentially increased in applications such as intrusion detection, forest fire detection, disaster management and battle field. Sensor nodes are generally battery operated low cost devices. The key challenge in the design and operation of WSNs is to prolong the network life time by reducing the energy consumption among sensor nodes. Node clustering is one of the most promising techniques for energy conservation. This paper presents a novel clustering algorithm which maximizes the network lifetime by reducing the number of communication among sensor nodes. This approach also includes new distributed cluster formation technique that enables self-organization of large number of nodes, algorithm for maintaining constant number of clusters by prior selection of cluster head and rotating the role of cluster head to evenly distribute the energy load among all sensor nodes.
Abstract: Multirate multimedia delivery applications in multihop Wireless Mesh Network (WMN) are data redundant and delay-sensitive, which brings a lot of challenges for designing efficient transmission systems. In this paper, we propose a new cross layer resource allocation scheme to minimize the receiver side distortion within the delay bound requirements, by exploring application layer Position and Value (P-V) diversity as well as the multihop Effective Capacity (EC). We specifically consider image transmission optimization here. First of all, the maximum supportable source traffic rate is identified by exploring the multihop Effective Capacity (EC) model. Furthermore, the optimal source coding rate is selected according to the P-V diversity of multirate media streaming, which significantly increases the decoded media quality. Simulation results show the proposed approach improved media quality significantly compared with traditional approaches under the same QoS requirements.
Abstract: In this paper, the potential security issues brought by the virtualization of a Software Defined Networks (SDN) would be analyzed. The virtualization of SDN is achieved by FlowVisor (FV). With FV, a physical network is divided into multiple isolated logical networks while the underlying resources are still shared by different slices (isolated logical networks). However, along with the benefits brought by network virtualization, it also presents some issues regarding security. By examining security issues existing in an OpenFlow network, which uses FlowVisor to slice it into multiple virtual networks, we hope we can get some significant results and also can get furtherdiscussions among the security of SDN virtualization.
Abstract: Cross layer optimization based on utility functions has
been recently studied extensively, meanwhile, numerous types of
utility functions have been examined in the corresponding literature.
However, a major drawback is that most utility functions take a fixed
mathematical form or are based on simple combining, which can
not fully exploit available information. In this paper, we formulate a
framework of cross layer optimization based on Adaptively Weighted
Utility Functions (AWUF) for fairness balancing in OFDMA networks.
Under this framework, a two-step allocation algorithm is
provided as a sub-optimal solution, whose control parameters can be
updated in real-time to accommodate instantaneous QoS constrains.
The simulation results show that the proposed algorithm achieves
high throughput while balancing the fairness among multiple users.
Abstract: In this paper we present a Feed-Foward Neural
Networks Autoregressive (FFNN-AR) model with genetic algorithms
training optimization in order to predict the gross domestic product
growth of six countries. Specifically we propose a kind of weighted
regression, which can be used for econometric purposes, where the
initial inputs are multiplied by the neural networks final optimum
weights from input-hidden layer of the training process. The
forecasts are compared with those of the ordinary autoregressive
model and we conclude that the proposed regression-s forecasting
results outperform significant those of autoregressive model.
Moreover this technique can be used in Autoregressive-Moving
Average models, with and without exogenous inputs, as also the
training process with genetics algorithms optimization can be
replaced by the error back-propagation algorithm.
Abstract: Gas flaring is one of the most GHG emitting sources in the oil and gas industries. It is also a major way for wasting such an energy that could be better utilized and even generates revenue. Minimize flaring is an effective approach for reducing GHG emissions and also conserving energy in flaring systems. Integrating waste and flared gases into the fuel gas networks (FGN) of refineries is an efficient tool. A fuel gas network collects fuel gases from various source streams and mixes them in an optimal manner, and supplies them to different fuel sinks such as furnaces, boilers, turbines, etc. In this article we use fuel gas network model proposed by Hasan et al. as a base model and modify some of its features and add constraints on emission pollution by gas flaring to reduce GHG emissions as possible. Results for a refinery case study showed that integration of flare gas stream with waste and natural gas streams to construct an optimal FGN can significantly reduce total annualized cost and flaring emissions.
Abstract: There are several approaches in trying to solve the
Quantitative 1Structure-Activity Relationship (QSAR) problem.
These approaches are based either on statistical methods or on
predictive data mining. Among the statistical methods, one should
consider regression analysis, pattern recognition (such as cluster
analysis, factor analysis and principal components analysis) or partial
least squares. Predictive data mining techniques use either neural
networks, or genetic programming, or neuro-fuzzy knowledge. These
approaches have a low explanatory capability or non at all. This
paper attempts to establish a new approach in solving QSAR
problems using descriptive data mining. This way, the relationship
between the chemical properties and the activity of a substance
would be comprehensibly modeled.
Abstract: The use of statistical data and of the neural networks, capable of elaborate a series of data and territorial info, have allowed the making of a model useful in the subdivision of urban places into homogeneous zone under the profile of a social, real estate, environmental and urbanist background of a city. The development of homogeneous zone has fiscal and urbanist advantages. The tools in the model proposed, able to be adapted to the dynamic changes of the city, allow the application of the zoning fast and dynamic.