Abstract: Image Edge Detection is one of the most important
parts of image processing. In this paper, by fuzzy technique, a new
method is used to improve digital image edge detection. In this
method, a 3x3 mask is employed to process each pixel by means of
vicinity. Each pixel is considered a fuzzy input and by examining
fuzzy rules in its vicinity, the edge pixel is specified and by utilizing
calculation algorithms in image processing, edges are displayed more
clearly. This method shows significant improvement compared to
different edge detection methods (e.g. Sobel, Canny).
Abstract: This work presents the Risk Threshold RED (RTRED)
congestion control strategy for TCP networks. In addition to the
maximum and minimum thresholds in existing RED-based strategies,
we add a third dropping level. This new dropping level is the risk
threshold which works with the actual and average queue sizes to
detect the immediate congestion in gateways. Congestion reaction
by RTRED is on time. The reaction to congestion is neither too
early, to avoid unfair packet losses, nor too late to avoid packet
dropping from time-outs. We compared our novel strategy with RED
and ARED strategies for TCP congestion handling using a NS-2
simulation script. We found that the RTRED strategy outperformed
RED and ARED.
Abstract: This paper proposes an efficient learning method for the layered neural networks based on the selection of training data and input characteristics of an output layer unit. Comparing to recent neural networks; pulse neural networks, quantum neuro computation, etc, the multilayer network is widely used due to its simple structure. When learning objects are complicated, the problems, such as unsuccessful learning or a significant time required in learning, remain unsolved. Focusing on the input data during the learning stage, we undertook an experiment to identify the data that makes large errors and interferes with the learning process. Our method devides the learning process into several stages. In general, input characteristics to an output layer unit show oscillation during learning process for complicated problems. The multi-stage learning method proposes by the authors for the function approximation problems of classifying learning data in a phased manner, focusing on their learnabilities prior to learning in the multi layered neural network, and demonstrates validity of the multi-stage learning method. Specifically, this paper verifies by computer experiments that both of learning accuracy and learning time are improved of the BP method as a learning rule of the multi-stage learning method. In learning, oscillatory phenomena of a learning curve serve an important role in learning performance. The authors also discuss the occurrence mechanisms of oscillatory phenomena in learning. Furthermore, the authors discuss the reasons that errors of some data remain large value even after learning, observing behaviors during learning.
Abstract: Designing and implementing intelligent systems has become a crucial factor for the innovation and development of better products of space technologies. A neural network is a parallel system, capable of resolving paradigms that linear computing cannot. Field programmable gate array (FPGA) is a digital device that owns reprogrammable properties and robust flexibility. For the neural network based instrument prototype in real time application, conventional specific VLSI neural chip design suffers the limitation in time and cost. With low precision artificial neural network design, FPGAs have higher speed and smaller size for real time application than the VLSI and DSP chips. So, many researchers have made great efforts on the realization of neural network (NN) using FPGA technique. In this paper, an introduction of ANN and FPGA technique are briefly shown. Also, Hardware Description Language (VHDL) code has been proposed to implement ANNs as well as to present simulation results with floating point arithmetic. Synthesis results for ANN controller are developed using Precision RTL. Proposed VHDL implementation creates a flexible, fast method and high degree of parallelism for implementing ANN. The implementation of multi-layer NN using lookup table LUT reduces the resource utilization for implementation and time for execution.
Abstract: In this paper, an ultrasonic technique is proposed to
predict oil content in a fresh palm fruit. This is accomplished by
measuring the attenuation based on ultrasonic transmission mode.
Several palm fruit samples with known oil content by Soxhlet
extraction (ISO9001:2008) were tested with our ultrasonic
measurement. Amplitude attenuation data results for all palm samples
were collected. The Feedforward Neural Networks (FNNs) are
applied to predict the oil content for the samples. The Root Mean
Square Error (RMSE) and Mean Absolute Error (MAE) of the FNN
model for predicting oil content percentage are 7.6186 and 5.2287
with the correlation coefficient (R) of 0.9193.
Abstract: This paper discusses the development of wireless
structure control of an induction motor scalar drives. This was
realised up on the wireless WiFi networks. This strategy of control is
ensured by the use of Wireless ad hoc networks and a virtual network
interface based on VNC which is used to make possible to take the
remote control of a PC connected on a wireless Ethernet network.
Verification of the proposed strategy of control is provided by
experimental realistic tests on scalar controlled induction motor
drives. The experimental results of the implementations with their
analysis are detailed.
Abstract: Recently, malware attacks have become more serious
over the Internet by e-mail, denial of service (DoS) or distributed
denial of service (DDoS). The Botnets have become a significant part
of the Internet malware attacks. The traditional botnets include three
parts – botmaster, command and control (C&C) servers and bots. The
C&C servers receive commands from botmaster and control the
distributions of computers remotely. Bots use DNS to find the
positions of C&C server. In this paper, we propose an advanced hybrid
peer-to-peer (P2P) botnet 2.0 (AHP2P botnet 2.0) using web 2.0
technology to hide the instructions from botmaster into social sites,
which are regarded as C&C servers. Servent bots are regarded as
sub-C&C servers to get the instructions from social sites. The AHP2P
botnet 2.0 can evaluate the performance of servent bots, reduce DNS
traffics from bots to C&C servers, and achieve harder detection bots
actions than IRC-based botnets over the Internet.
Abstract: Game theory could be used to analyze the conflicted
issues in the field of information hiding. In this paper, 2-phase game
can be used to build the embedder-attacker system to analyze the
limits of hiding capacity of embedding algorithms: the embedder
minimizes the expected damage and the attacker maximizes it. In the
system, the embedder first consumes its resource to build embedded
units (EU) and insert the secret information into EU. Then the attacker
distributes its resource evenly to the attacked EU. The expected
equilibrium damage, which is maximum damage in value from the
point of view of the attacker and minimum from the embedder against
the attacker, is evaluated by the case when the attacker attacks a
subset from all the EU. Furthermore, the optimal equilibrium capacity
of hiding information is calculated through the optimal number of EU
with the embedded secret information. Finally, illustrative examples
of the optimal equilibrium capacity are presented.
Abstract: Digital news with a variety topics is abundant on the
internet. The problem is to classify news based on its appropriate
category to facilitate user to find relevant news rapidly. Classifier
engine is used to split any news automatically into the respective
category. This research employs Support Vector Machine (SVM) to
classify Indonesian news. SVM is a robust method to classify
binary classes. The core processing of SVM is in the formation of an
optimum separating plane to separate the different classes. For
multiclass problem, a mechanism called one against one is used to
combine the binary classification result. Documents were taken
from the Indonesian digital news site, www.kompas.com. The
experiment showed a promising result with the accuracy rate of 85%.
This system is feasible to be implemented on Indonesian news
classification.
Abstract: Sequential pattern mining is a challenging task in data mining area with large applications. One among those applications is mining patterns from weblog. Recent times, weblog is highly dynamic and some of them may become absolute over time. In addition, users may frequently change the threshold value during the data mining process until acquiring required output or mining interesting rules. Some of the recently proposed algorithms for mining weblog, build the tree with two scans and always consume large time and space. In this paper, we build Revised PLWAP with Non-frequent Items (RePLNI-tree) with single scan for all items. While mining sequential patterns, the links related to the nonfrequent items are not considered. Hence, it is not required to delete or maintain the information of nodes while revising the tree for mining updated transactions. The algorithm supports both incremental and interactive mining. It is not required to re-compute the patterns each time, while weblog is updated or minimum support changed. The performance of the proposed tree is better, even the size of incremental database is more than 50% of existing one. For evaluation purpose, we have used the benchmark weblog dataset and found that the performance of proposed tree is encouraging compared to some of the recently proposed approaches.
Abstract: In this paper we present a photo mosaic smartphone
application in client-server based large-scale image databases. Photo
mosaic is not a new concept, but there are very few smartphone
applications especially for a huge number of images in the
client-server environment. To support large-scale image databases,
we first propose an overall framework working as a client-server
model. We then present a concept of image-PAA features to efficiently
handle a huge number of images and discuss its lower bounding
property. We also present a best-match algorithm that exploits the
lower bounding property of image-PAA. We finally implement an
efficient Android-based application and demonstrate its feasibility.
Abstract: Recent developments in Soft computing techniques,
power electronic switches and low-cost computational hardware have
made it possible to design and implement sophisticated control
strategies for sensorless speed control of AC motor drives. Such an
attempt has been made in this work, for Sensorless Speed Control of
Induction Motor (IM) by means of Direct Torque Fuzzy Control
(DTFC), PI-type fuzzy speed regulator and MRAS speed estimator
strategy, which is absolutely nonlinear in its nature. Direct torque
control is known to produce quick and robust response in AC drive
system. However, during steady state, torque, flux and current ripple
occurs. So, the performance of conventional DTC with PI speed
regulator can be improved by implementing fuzzy logic techniques.
Certain important issues in design including the space vector
modulated (SVM) 3-Ф voltage source inverter, DTFC design,
generation of reference torque using PI-type fuzzy speed regulator
and sensor less speed estimator have been resolved. The proposed
scheme is validated through extensive numerical simulations on
MATLAB. The simulated results indicate the sensor less speed
control of IM with DTFC and PI-type fuzzy speed regulator provides
satisfactory high dynamic and static performance compare to
conventional DTC with PI speed regulator.
Abstract: The quick training algorithms and accurate solution
procedure for incremental learning aim at improving the efficiency of
training of SVR, whereas there are some disadvantages for them, i.e.
the nonconvergence of the formers for changeable training set and
the inefficiency of the latter for a massive dataset. In order to handle
the problems, a new training algorithm for a changeable training
set, named Approximation Incremental Training Algorithm (AITA),
was proposed. This paper explored the reason of nonconvergence
theoretically and discussed the realization of AITA, and finally
demonstrated the benefits of AITA both on precision and efficiency.
Abstract: When designing information systems that deal with
large amount of domain knowledge, system designers need to consider
ambiguities of labeling termsin domain vocabulary for navigating
users in the information space. The goal of this study is to develop a
methodology for system designers to label navigation items, taking
account of ambiguities stems from synonyms or polysemes of labeling
terms. In this paper, we propose a method for concept labeling based
on mappings between domain ontology andthesaurus, and report
results of an empirical evaluation.
Abstract: This paper explores university course timetabling
problem. There are several characteristics that make scheduling and
timetabling problems particularly difficult to solve: they have huge
search spaces, they are often highly constrained, they require
sophisticated solution representation schemes, and they usually
require very time-consuming fitness evaluation routines. Thus
standard evolutionary algorithms lack of efficiency to deal with
them. In this paper we have proposed a memetic algorithm that
incorporates the problem specific knowledge such that most of
chromosomes generated are decoded into feasible solutions.
Generating vast amount of feasible chromosomes makes the progress
of search process possible in a time efficient manner. Experimental
results exhibit the advantages of the developed Hybrid Genetic
Algorithm than the standard Genetic Algorithm.
Abstract: Web 2.0 (social networking, blogging and online
forums) can serve as a data source for social science research because
it contains vast amount of information from many different users.
The volume of that information has been growing at a very high rate
and becoming a network of heterogeneous data; this makes things
difficult to find and is therefore not almost useful. We have proposed
a novel theoretical model for gathering and processing data from
Web 2.0, which would reflect semantic content of web pages in
better way. This article deals with the analysis part of the model and
its usage for content analysis of blogs. The introductory part of the
article describes methodology for the gathering and processing data
from blogs. The next part of the article is focused on the evaluation
and content analysis of blogs, which write about specific trend.
Abstract: Documents clustering become an essential technology
with the popularity of the Internet. That also means that fast and
high-quality document clustering technique play core topics. Text
clustering or shortly clustering is about discovering semantically
related groups in an unstructured collection of documents. Clustering
has been very popular for a long time because it provides unique
ways of digesting and generalizing large amounts of information.
One of the issues of clustering is to extract proper feature (concept)
of a problem domain. The existing clustering technology mainly
focuses on term weight calculation. To achieve more accurate
document clustering, more informative features including concept
weight are important. Feature Selection is important for clustering
process because some of the irrelevant or redundant feature may
misguide the clustering results. To counteract this issue, the proposed
system presents the concept weight for text clustering system
developed based on a k-means algorithm in accordance with the
principles of ontology so that the important of words of a cluster can
be identified by the weight values. To a certain extent, it has resolved
the semantic problem in specific areas.