Abstract: Designing a simulated system and training it to optimize its tasks in simulated environment helps the designers to avoid problems that may appear when designing the system directly in real world. These problems are: time consuming, high cost, high errors percentage and low efficiency and accuracy of the system. The proposed system will investigate and improve the efficiency and accuracy of a simulated robot to choose correct behavior to perform its task. In this paper, machine learning, which uses genetic algorithm, is adopted. This type of machine learning is called genetic-based machine learning in which a distributed classifier system is used to improve the efficiency and accuracy of the robot. Consequently, it helps the robot to achieve optimal action.
Abstract: In China, with the rapid urbanization and
industrialization, and highly accelerated economic development have
resulted in degradation of water resource. The water quality
deterioration usual result from eutrophication in most cases, so how to
dispose this type pollution water higher efficiently is an urgent task.
Hower, different with traditional technology, constructed wetlands are
effective treatment systems that can be very useful because they are
simple technology and low operational cost. A pilot-scale treatment
including constructed wetlands was constructed at XingYun Lake,
Yuxi, China, and operated as primary treatment measure before
eutrophic-lake water draining to riverine landscape. Water quality
indices were determined during the experiment, the results indicated
that treatment removal efficiencies were high for Nitrate nitrogen,
Chlorophyll–a and Algae, the final removal efficiency reached to
95.20%, 93.33% and 99.87% respectively, but the removal efficiency
of Total phosphorous and Total nitrogen only reach to 68.83% and
50.00% respectively.
Abstract: Developing a stable early warning system (EWS)
model that is capable to give an accurate prediction is a challenging
task. This paper introduces k-nearest neighbour (k-NN) method
which never been applied in predicting currency crisis before with the
aim of increasing the prediction accuracy. The proposed k-NN
performance depends on the choice of a distance that is used where in
our analysis; we take the Euclidean distance and the Manhattan as a
consideration. For the comparison, we employ three other methods
which are logistic regression analysis (logit), back-propagation neural
network (NN) and sequential minimal optimization (SMO). The
analysis using datasets from 8 countries and 13 macro-economic
indicators for each country shows that the proposed k-NN method
with k = 4 and Manhattan distance performs better than the other
methods.
Abstract: Content-based music retrieval generally involves analyzing, searching and retrieving music based on low or high level features of a song which normally used to represent artists, songs or music genre. Identifying them would normally involve feature extraction and classification tasks. Theoretically the greater features analyzed, the better the classification accuracy can be achieved but with longer execution time. Technique to select significant features is important as it will reduce dimensions of feature used in classification and contributes to the accuracy. Artificial Immune System (AIS) approach will be investigated and applied in the classification task. Bio-inspired audio content-based retrieval framework (B-ACRF) is proposed at the end of this paper where it embraces issues that need further consideration in music retrieval performances.
Abstract: In this paper, we have presented the effect of varying
time-delays on performance and stability in the single-channel multirate
sampled-data system in hard real-time (RT-Linux) environment.
The sampling task require response time that might exceed the
capacity of RT-Linux. So a straight implementation with RT-Linux is
not feasible, because of the latency of the systems and hence,
sampling period should be less to handle this task. The best sampling
rate is chosen for the sampled-data system, which is the slowest rate
meets all performance requirements. RT-Linux is consistent with its
specifications and the resolution of the real-time is considered 0.01
seconds to achieve an efficient result. The test results of our
laboratory experiment shows that the multi-rate control technique in
hard real-time operating system (RTOS) can improve the stability
problem caused by the random access delays and asynchronization.
Abstract: Automatic Extraction of Event information from
social text stream (emails, social network sites, blogs etc) is a vital
requirement for many applications like Event Planning and
Management systems and security applications. The key information
components needed from Event related text are Event title, location,
participants, date and time. Emails have very unique distinctions over
other social text streams from the perspective of layout and format
and conversation style and are the most commonly used
communication channel for broadcasting and planning events.
Therefore we have chosen emails as our dataset. In our work, we
have employed two statistical NLP methods, named as Finite State
Machines (FSM) and Hidden Markov Model (HMM) for the
extraction of event related contextual information. An application
has been developed providing a comparison among the two methods
over the event extraction task. It comprises of two modules, one for
each method, and works for both bulk as well as direct user input.
The results are evaluated using Precision, Recall and F-Score.
Experiments show that both methods produce high performance and
accuracy, however HMM was good enough over Title extraction and
FSM proved to be better for Venue, Date, and time.
Abstract: In this paper the development of a heat exchanger as a
pilot plant for educational purpose is discussed and the use of neural
network for controlling the process is being presented. The aim of the
study is to highlight the need of a specific Pseudo Random Binary
Sequence (PRBS) to excite a process under control. As the neural
network is a data driven technique, the method for data generation
plays an important role. In light of this a careful experimentation
procedure for data generation was crucial task. Heat exchange is a
complex process, which has a capacity and a time lag as process
elements. The proposed system is a typical pipe-in- pipe type heat
exchanger. The complexity of the system demands careful selection,
proper installation and commissioning. The temperature, flow, and
pressure sensors play a vital role in the control performance. The
final control element used is a pneumatically operated control valve.
While carrying out the experimentation on heat exchanger a welldrafted
procedure is followed giving utmost attention towards safety
of the system. The results obtained are encouraging and revealing
the fact that if the process details are known completely as far as
process parameters are concerned and utilities are well stabilized then
feedback systems are suitable, whereas neural network control
paradigm is useful for the processes with nonlinearity and less
knowledge about process. The implementation of NN control
reinforces the concepts of process control and NN control paradigm.
The result also underlined the importance of excitation signal
typically for that process. Data acquisition, processing, and
presentation in a typical format are the most important parameters
while validating the results.
Abstract: There are very complex communication systems, as
the multifunction radar, MFAR (Multi-Function Array Radar), where
functions are integrated all together, and simultaneously are
performed the classic functions of tracking and surveillance, as all
the functions related to the communication, countermeasures, and
calibration. All these functions are divided into the tasks to execute.
The task scheduler is a key element of the radar, since it does the
planning and distribution of energy and time resources to be shared
and used by all tasks. This paper presents schedulers based on the use
of multiple queue. Several schedulers have been designed and
studied, and it has been made a comparative analysis of different
performed schedulers. The tests and experiments have been done by
means of system software simulation. Finally a suitable set of radar
characteristics has been selected to evaluate the behavior of the task
scheduler working.
Abstract: The study of human hand morphology reveals that developing an artificial hand with the capabilities of human hand is an extremely challenging task. This paper presents the development of a robotic prosthetic hand focusing on the improvement of a tendon driven mechanism towards a biomimetic prosthetic hand. The design of this prosthesis hand is geared towards achieving high level of dexterity and anthropomorphism by means of a new hybrid mechanism that integrates a miniature motor driven actuation mechanism, a Shape Memory Alloy actuated mechanism and a passive mechanical linkage. The synergy of these actuators enables the flexion-extension movement at each of the finger joints within a limited size, shape and weight constraints. Tactile sensors are integrated on the finger tips and the finger phalanges area. This prosthesis hand is developed with an exact size ratio that mimics a biological hand. Its behavior resembles the human counterpart in terms of working envelope, speed and torque, and thus resembles both the key physical features and the grasping functionality of an adult hand.
Abstract: Mining Sequential Patterns in large databases has become
an important data mining task with broad applications. It is
an important task in data mining field, which describes potential
sequenced relationships among items in a database. There are many
different algorithms introduced for this task. Conventional algorithms
can find the exact optimal Sequential Pattern rule but it takes a
long time, particularly when they are applied on large databases.
Nowadays, some evolutionary algorithms, such as Particle Swarm
Optimization and Genetic Algorithm, were proposed and have been
applied to solve this problem. This paper will introduce a new kind
of hybrid evolutionary algorithm that combines Genetic Algorithm
(GA) with Particle Swarm Optimization (PSO) to mine Sequential
Pattern, in order to improve the speed of evolutionary algorithms
convergence. This algorithm is referred to as SP-GAPSO.
Abstract: Distance protection of transmission lines including advanced flexible AC transmission system (FACTS) devices has been a very challenging task. FACTS devices of interest in this paper are static synchronous series compensators (SSSC) and unified power flow controller (UPFC). In this paper, a new algorithm is proposed to detect and classify the fault and identify the fault position in a transmission line with respect to a FACTS device placed in the midpoint of the transmission line. Discrete wavelet transformation and wavelet entropy calculations are used to analyze during fault current and voltage signals of the compensated transmission line. The proposed algorithm is very simple and accurate in fault detection and classification. A variety of fault cases and simulation results are introduced to show the effectiveness of such algorithm.
Abstract: Load forecasting has become in recent years one of the major areas of research in electrical engineering. Most traditional forecasting models and artificial intelligence neural network techniques have been tried out in this task. Artificial neural networks (ANN) have lately received much attention, and a great number of papers have reported successful experiments and practical tests. This article presents the development of an ANN-based short-term load forecasting model with improved generalization technique for the Regional Power Control Center of Saudi Electricity Company, Western Operation Area (SEC-WOA). The proposed ANN is trained with weather-related data and historical electric load-related data using the data from the calendar years 2001, 2002, 2003, and 2004 for training. The model tested for one week at five different seasons, typically, winter, spring, summer, Ramadan and fall seasons, and the mean absolute average error for one hour-ahead load forecasting found 1.12%.
Abstract: Designing modern machine tools is a complex task. A
simulation tool to aid the design work, a virtual machine, has
therefore been developed in earlier work. The virtual machine
considers the interaction between the mechanics of the machine
(including structural flexibility) and the control system. This paper
exemplifies the usefulness of the virtual machine as a tool for product
development. An optimisation study is conducted aiming at
improving the existing design of a machine tool regarding weight and
manufacturing accuracy at maintained manufacturing speed. The
problem can be categorised as constrained multidisciplinary multiobjective
multivariable optimisation. Parameters of the control and
geometric quantities of the machine are used as design variables. This
results in a mix of continuous and discrete variables and an
optimisation approach using a genetic algorithm is therefore
deployed. The accuracy objective is evaluated according to
international standards. The complete systems model shows nondeterministic
behaviour. A strategy to handle this based on statistical
analysis is suggested. The weight of the main moving parts is reduced
by more than 30 per cent and the manufacturing accuracy is
improvement by more than 60 per cent compared to the original
design, with no reduction in manufacturing speed. It is also shown
that interaction effects exist between the mechanics and the control,
i.e. this improvement would most likely not been possible with a
conventional sequential design approach within the same time, cost
and general resource frame. This indicates the potential of the virtual
machine concept for contributing to improved efficiency of both
complex products and the development process for such products.
Companies incorporating such advanced simulation tools in their
product development could thus improve its own competitiveness as
well as contribute to improved resource efficiency of society at large.
Abstract: In this paper, a framework for the simplification and
standardization of metaheuristic related parameter-tuning by applying
a four phase methodology, utilizing Design of Experiments and
Artificial Neural Networks, is presented. Metaheuristics are multipurpose
problem solvers that are utilized on computational optimization
problems for which no efficient problem specific algorithm
exist. Their successful application to concrete problems requires the
finding of a good initial parameter setting, which is a tedious and
time consuming task. Recent research reveals the lack of approach
when it comes to this so called parameter-tuning process. In the
majority of publications, researchers do have a weak motivation for
their respective choices, if any. Because initial parameter settings
have a significant impact on the solutions quality, this course of
action could lead to suboptimal experimental results, and thereby
a fraudulent basis for the drawing of conclusions.
Abstract: In the past years a lot of effort has been made in the
field of face detection. The human face contains important features
that can be used by vision-based automated systems in order to
identify and recognize individuals. Face location, the primary step of
the vision-based automated systems, finds the face area in the input
image. An accurate location of the face is still a challenging task.
Viola-Jones framework has been widely used by researchers in order
to detect the location of faces and objects in a given image. Face
detection classifiers are shared by public communities, such as
OpenCV. An evaluation of these classifiers will help researchers to
choose the best classifier for their particular need. This work focuses
of the evaluation of face detection classifiers minding facial
landmarks.
Abstract: A Data Warehouses is a repository of information
integrated from source data. Information stored in data warehouse is
the form of materialized in order to provide the better performance
for answering the queries. Deciding which appropriated views to be
materialized is one of important problem. In order to achieve this
requirement, the constructing search space close to optimal is a
necessary task. It will provide effective result for selecting view to be
materialized. In this paper we have proposed an approach to reoptimize
Multiple View Processing Plan (MVPP) by using global
common subexpressions. The merged queries which have query
processing cost not close to optimal would be rewritten. The
experiment shows that our approach can help to improve the total
query processing cost of MVPP and sum of query processing cost
and materialized view maintenance cost is reduced as well after views
are selected to be materialized.
Abstract: The literature reports a large number of approaches for
measuring the similarity between protein sequences. Most of these
approaches estimate this similarity using alignment-based techniques
that do not necessarily yield biologically plausible results, for two
reasons.
First, for the case of non-alignable (i.e., not yet definitively aligned
and biologically approved) sequences such as multi-domain, circular
permutation and tandem repeat protein sequences, alignment-based
approaches do not succeed in producing biologically plausible results.
This is due to the nature of the alignment, which is based on the
matching of subsequences in equivalent positions, while non-alignable
proteins often have similar and conserved domains in non-equivalent
positions.
Second, the alignment-based approaches lead to similarity measures
that depend heavily on the parameters set by the user for the alignment
(e.g., gap penalties and substitution matrices). For easily alignable
protein sequences, it's possible to supply a suitable combination of
input parameters that allows such an approach to yield biologically
plausible results. However, for difficult-to-align protein sequences,
supplying different combinations of input parameters yields different
results. Such variable results create ambiguities and complicate the
similarity measurement task.
To overcome these drawbacks, this paper describes a novel and
effective approach for measuring the similarity between protein
sequences, called SAF for Substitution and Alignment Free. Without
resorting either to the alignment of protein sequences or to substitution
relations between amino acids, SAF is able to efficiently detect the
significant subsequences that best represent the intrinsic properties of
protein sequences, those underlying the chronological dependencies of
structural features and biochemical activities of protein sequences.
Moreover, by using a new efficient subsequence matching scheme,
SAF more efficiently handles protein sequences that contain similar
structural features with significant meaning in chronologically
non-equivalent positions. To show the effectiveness of SAF, extensive
experiments were performed on protein datasets from different
databases, and the results were compared with those obtained by
several mainstream algorithms.
Abstract: Data mining uses a variety of techniques each of which is useful for some particular task. It is important to have a deep understanding of each technique and be able to perform sophisticated analysis. In this article we describe a tool built to simulate a variation of the Kohonen network to perform unsupervised clustering and support the entire data mining process up to results visualization. A graphical representation helps the user to find out a strategy to optmize classification by adding, moving or delete a neuron in order to change the number of classes. The tool is also able to automatically suggest a strategy for number of classes optimization.The tool is used to classify macroeconomic data that report the most developed countries? import and export. It is possible to classify the countries based on their economic behaviour and use an ad hoc tool to characterize the commercial behaviour of a country in a selected class from the analysis of positive and negative features that contribute to classes formation.
Abstract: Quality evaluation of an image is an important task in image processing applications. In case of image compression, quality of decompressed image is also the criterion for evaluation of given coding scheme. In the process of compression -decompression various artifacts such as blocking artifacts, blur artifact, ringing or edge artifact are observed. However quantification of these artifacts is a difficult task. We propose here novel method to quantify blur and ringing artifact in an image.
Abstract: Many-core GPUs provide high computing ability and
substantial bandwidth; however, optimizing irregular applications
like SpMV on GPUs becomes a difficult but meaningful task. In this
paper, we propose a novel method to improve the performance of
SpMV on GPUs. A new storage format called HYB-R is proposed to
exploit GPU architecture more efficiently. The COO portion of the
matrix is partitioned recursively into a ELL portion and a COO
portion in the process of creating HYB-R format to ensure that there
are as many non-zeros as possible in ELL format. The method of
partitioning the matrix is an important problem for HYB-R kernel, so
we also try to tune the parameters to partition the matrix for higher
performance. Experimental results show that our method can get
better performance than the fastest kernel (HYB) in NVIDIA-s
SpMV library with as high as 17% speedup.