Abstract: Leo Breimans Random Forests (RF) is a recent
development in tree based classifiers and quickly proven to be one of
the most important algorithms in the machine learning literature. It
has shown robust and improved results of classifications on standard
data sets. Ensemble learning algorithms such as AdaBoost and
Bagging have been in active research and shown improvements in
classification results for several benchmarking data sets with mainly
decision trees as their base classifiers. In this paper we experiment to
apply these Meta learning techniques to the random forests. We
experiment the working of the ensembles of random forests on the
standard data sets available in UCI data sets. We compare the
original random forest algorithm with their ensemble counterparts
and discuss the results.
Abstract: A novel design of two-wheeled robotic vehicle with moving payload is presented in this paper. A mathematical model describing the vehicle dynamics is derived and simulated in Matlab Simulink environment. Two control strategies were developed to stabilise the vehicle in the upright position. A robust Proportional- Integral-Derivative (PID) control strategy has been implemented and initially tested to measure the system performance, while the second control strategy is to use a hybrid fuzzy logic controller (FLC). The results are given on a comparative basis for the system performance in terms of disturbance rejection, control algorithms robustness as well as the control effort in terms of input torque.
Abstract: The aim of this paper is to present a comparative
study on two different methods for the evaluation of the equilibrium
point of a ship, core issue for designing an On Board Stability System
(OBSS) module that, starting from geometry information of a ship
hull, described by a discrete model in a standard format, and the
distribution of all weights onboard calculates the ship floating
conditions (in draught, heel and trim).
Abstract: Adaptive Genetic Algorithms extend the Standard Gas
to use dynamic procedures to apply evolutionary operators such as
crossover, mutation and selection. In this paper, we try to propose a
new adaptive genetic algorithm, which is based on the statistical
information of the population as a guideline to tune its crossover,
selection and mutation operators. This algorithms is called Statistical
Genetic Algorithm and is compared with traditional GA in some
benchmark problems.
Abstract: Data mining (DM) is the process of finding and extracting frequent patterns that can describe the data, or predict unknown or future values. These goals are achieved by using various learning algorithms. Each algorithm may produce a mining result completely different from the others. Some algorithms may find millions of patterns. It is thus the difficult job for data analysts to select appropriate models and interpret the discovered knowledge. In this paper, we describe a framework of an intelligent and complete data mining system called SUT-Miner. Our system is comprised of a full complement of major DM algorithms, pre-DM and post-DM functionalities. It is the post-DM packages that ease the DM deployment for business intelligence applications.
Abstract: An enhanced particle swarm optimization algorithm
(PSO) is presented in this work to solve the non-convex OPF
problem that has both discrete and continuous optimization variables.
The objective functions considered are the conventional quadratic
function and the augmented quadratic function. The latter model
presents non-differentiable and non-convex regions that challenge
most gradient-based optimization algorithms. The optimization
variables to be optimized are the generator real power outputs and
voltage magnitudes, discrete transformer tap settings, and discrete
reactive power injections due to capacitor banks. The set of equality
constraints taken into account are the power flow equations while the
inequality ones are the limits of the real and reactive power of the
generators, voltage magnitude at each bus, transformer tap settings,
and capacitor banks reactive power injections. The proposed
algorithm combines PSO with Newton-Raphson algorithm to
minimize the fuel cost function. The IEEE 30-bus system with six
generating units is used to test the proposed algorithm. Several cases
were investigated to test and validate the consistency of detecting
optimal or near optimal solution for each objective. Results are
compared to solutions obtained using sequential quadratic
programming and Genetic Algorithms.
Abstract: Current systems for face recognition techniques often
use either SVM or Adaboost techniques for face detection part and use
PCA for face recognition part. In this paper, we offer a novel method
for not only a powerful face detection system based on
Six-segment-filters (SSR) and Adaboost learning algorithms but also
for a face recognition system. A new exclusive face detection
algorithm has been developed and connected with the recognition
algorithm. As a result of it, we obtained an overall high-system
performance compared with current systems. The proposed algorithm
was tested on CMU, FERET, UNIBE, MIT face databases and
significant performance has obtained.
Abstract: Since the actuator capacity is limited, in the real
application of active control systems under sever earthquakes it is
conceivable that the actuators saturate, hence the actuator saturation
should be considered as a constraint in design of optimal controllers.
In this paper optimal design of active controllers for nonlinear
structures by considering actuator saturation, has been studied. The
proposed method for designing optimal controllers is based on
defining an optimization problem which the objective has been to
minimize the maximum displacement of structure when a limited
capacity for actuator has been used. To this end a single degree of
freedom (SDF) structure with a bilinear hysteretic behavior has been
simulated under a white noise ground acceleration of different
amplitudes. Active tendon control mechanism, comprised of prestressed
tendons and an actuator, and extended nonlinear Newmark
method based instantaneous optimal control algorithm have been
used. To achieve the best results, the weights corresponding to
displacement, velocity, acceleration and control force in the
performance index have been optimized by the Distributed Genetic
Algorithm (DGA). Results show the effectiveness of the proposed
method in considering actuator saturation. Also based on the
numerical simulations it can be concluded that the actuator capacity
and the average value of required control force are two important
factors in designing nonlinear controllers which consider the actuator
saturation.
Abstract: Access control is a critical security service in Wire- less
Sensor Networks (WSNs). To prevent malicious nodes from joining
the sensor network, access control is required. On one hand, WSN
must be able to authorize and grant users the right to access to the
network. On the other hand, WSN must organize data collected by
sensors in such a way that an unauthorized entity (the adversary)
cannot make arbitrary queries. This restricts the network access only
to eligible users and sensor nodes, while queries from outsiders will
not be answered or forwarded by nodes. In this paper we presentee
different access control schemes so as to ?nd out their objectives,
provision, communication complexity, limits, etc. Using the node
density parameter, we also provide a comparison of these proposed
access control algorithms based on the network topology which can
be flat or hierarchical.
Abstract: Industrial radiography is a famous technique for the identification and evaluation of discontinuities, or defects, such as cracks, porosity and foreign inclusions found in welded joints. Although this technique has been well developed, improving both the inspection process and operating time, it does suffer from several drawbacks. The poor quality of radiographic images is due to the physical nature of radiography as well as small size of the defects and their poor orientation relatively to the size and thickness of the evaluated parts. Digital image processing techniques allow the interpretation of the image to be automated, avoiding the presence of human operators making the inspection system more reliable, reproducible and faster. This paper describes our attempt to develop and implement digital image processing algorithms for the purpose of automatic defect detection in radiographic images. Because of the complex nature of the considered images, and in order that the detected defect region represents the most accurately possible the real defect, the choice of global and local preprocessing and segmentation methods must be appropriated.
Abstract: In this paper is investigated a possible
optimization of some linear algebra problems which can be
solved by parallel processing using the special arrays called
systolic arrays. In this paper are used some special types of
transformations for the designing of these arrays. We show
the characteristics of these arrays. The main focus is on
discussing the advantages of these arrays in parallel
computation of matrix product, with special approach to the
designing of systolic array for matrix multiplication.
Multiplication of large matrices requires a lot of
computational time and its complexity is O(n3 ). There are
developed many algorithms (both sequential and parallel) with
the purpose of minimizing the time of calculations. Systolic
arrays are good suited for this purpose. In this paper we show
that using an appropriate transformation implicates in finding
more optimal arrays for doing the calculations of this type.
Abstract: In this paper, we propose a face recognition algorithm
using AAM and Gabor features. Gabor feature vectors which are well
known to be robust with respect to small variations of shape, scaling,
rotation, distortion, illumination and poses in images are popularly
employed for feature vectors for many object detection and
recognition algorithms. EBGM, which is prominent among face
recognition algorithms employing Gabor feature vectors, requires
localization of facial feature points where Gabor feature vectors are
extracted. However, localization method employed in EBGM is based
on Gabor jet similarity and is sensitive to initial values. Wrong
localization of facial feature points affects face recognition rate. AAM
is known to be successfully applied to localization of facial feature
points. In this paper, we devise a facial feature point localization
method which first roughly estimate facial feature points using AAM
and refine facial feature points using Gabor jet similarity-based facial
feature localization method with initial points set by the rough facial
feature points obtained from AAM, and propose a face recognition
algorithm using the devised localization method for facial feature
localization and Gabor feature vectors. It is observed through
experiments that such a cascaded localization method based on both
AAM and Gabor jet similarity is more robust than the localization
method based on only Gabor jet similarity. Also, it is shown that the
proposed face recognition algorithm using this devised localization
method and Gabor feature vectors performs better than the
conventional face recognition algorithm using Gabor jet
similarity-based localization method and Gabor feature vectors like
EBGM.
Abstract: In this paper we study the fuzzy c-mean clustering algorithm
combined with principal components method. Demonstratively
analysis indicate that the new clustering method is well rather than
some clustering algorithms. We also consider the validity of clustering
method.
Abstract: The Block Sorting problem is to sort a given
permutation moving blocks. A block is defined as a substring
of the given permutation, which is also a substring of the
identity permutation. Block Sorting has been proved to be
NP-Hard. Until now two different 2-Approximation algorithms
have been presented for block sorting. These are the best known
algorithms for Block Sorting till date. In this work we present
a different characterization of Block Sorting in terms of a
transposition cycle graph. Then we suggest a heuristic,
which we show to exhibit a 2-approximation performance
guarantee for most permutations.
Abstract: In the recent years multimedia traffic and in particular
VoIP services are growing dramatically. We present a new algorithm
to control the resource utilization and to optimize the voice codec
selection during SIP call setup on behalf of the traffic condition
estimated on the network path.
The most suitable methodologies and the tools that perform realtime
evaluation of the available bandwidth on a network path have
been integrated with our proposed algorithm: this selects the best
codec for a VoIP call in function of the instantaneous available
bandwidth on the path. The algorithm does not require any explicit
feedback from the network, and this makes it easily deployable over
the Internet. We have also performed intensive tests on real network
scenarios with a software prototype, verifying the algorithm
efficiency with different network topologies and traffic patterns
between two SIP PBXs.
The promising results obtained during the experimental validation
of the algorithm are now the basis for the extension towards a larger
set of multimedia services and the integration of our methodology
with existing PBX appliances.
Abstract: this paper presents a multi-context recurrent network for time series analysis. While simple recurrent network (SRN) are very popular among recurrent neural networks, they still have some shortcomings in terms of learning speed and accuracy that need to be addressed. To solve these problems, we proposed a multi-context recurrent network (MCRN) with three different learning algorithms. The performance of this network is evaluated on some real-world application such as handwriting recognition and energy load forecasting. We study the performance of this network and we compared it to a very well established SRN. The experimental results showed that MCRN is very efficient and very well suited to time series analysis and its applications.
Abstract: Knowledge Discovery of Databases (KDD) is the
process of extracting previously unknown but useful and significant
information from large massive volume of databases. Data Mining is
a stage in the entire process of KDD which applies an algorithm to
extract interesting patterns. Usually, such algorithms generate huge
volume of patterns. These patterns have to be evaluated by using
interestingness measures to reflect the user requirements.
Interestingness is defined in different ways, (i) Objective measures
(ii) Subjective measures. Objective measures such as support and
confidence extract meaningful patterns based on the structure of the
patterns, while subjective measures such as unexpectedness and
novelty reflect the user perspective. In this report, we try to brief the
more widely spread and successful subjective measures and propose
a new subjective measure of interestingness, i.e. shocking.
Abstract: This research paper evaluates and compares the
performance of equal cost adaptive multi-path routing algorithms
taking the transport protocols TCP (Transmission Control Protocol)
and UDP (User Datagram Protocol) using network simulator ns2 and
concludes which one is better.
Abstract: This paper presents a new approach using Combined Artificial Neural Network (CANN) module for daily peak load forecasting. Five different computational techniques –Constrained method, Unconstrained method, Evolutionary Programming (EP), Particle Swarm Optimization (PSO), and Genetic Algorithm (GA) – have been used to identify the CANN module for peak load forecasting. In this paper, a set of neural networks has been trained with different architecture and training parameters. The networks are trained and tested for the actual load data of Chennai city (India). A set of better trained conventional ANNs are selected to develop a CANN module using different algorithms instead of using one best conventional ANN. Obtained results using CANN module confirm its validity.
Abstract: Drying characteristics of rough rice (variety of lenjan) with an initial moisture content of 25% dry basis (db) was studied in a hot air dryer assisted by infrared heating. Three arrival air temperatures (30, 40 and 500C) and four infrared radiation intensities (0, 0.2 , 0.4 and 0.6 W/cm2) and three arrival air speeds (0.1, 0.15 and 0.2 m.s-1) were studied. Bending strength of brown rice kernel, percentage of cracked kernels and time of drying were measured and evaluated. The results showed that increasing the drying arrival air temperature and radiation intensity of infrared resulted decrease in drying time. High bending strength and low percentage of cracked kernel was obtained when paddy was dried by hot air assisted infrared dryer. Between this factors and their interactive effect were a significant difference (p