Abstract: This paper proposes a new technique based on nonlinear Minmax Detector Based (MDB) filter for image restoration. The aim of image enhancement is to reconstruct the true image from the corrupted image. The process of image acquisition frequently leads to degradation and the quality of the digitized image becomes inferior to the original image. Image degradation can be due to the addition of different types of noise in the original image. Image noise can be modeled of many types and impulse noise is one of them. Impulse noise generates pixels with gray value not consistent with their local neighborhood. It appears as a sprinkle of both light and dark or only light spots in the image. Filtering is a technique for enhancing the image. Linear filter is the filtering in which the value of an output pixel is a linear combination of neighborhood values, which can produce blur in the image. Thus a variety of smoothing techniques have been developed that are non linear. Median filter is the one of the most popular non-linear filter. When considering a small neighborhood it is highly efficient but for large window and in case of high noise it gives rise to more blurring to image. The Centre Weighted Mean (CWM) filter has got a better average performance over the median filter. However the original pixel corrupted and noise reduction is substantial under high noise condition. Hence this technique has also blurring affect on the image. To illustrate the superiority of the proposed approach, the proposed new scheme has been simulated along with the standard ones and various restored performance measures have been compared.
Abstract: Automated discovery of Rule is, due to its applicability, one of the most fundamental and important method in KDD. It has been an active research area in the recent past. Hierarchical representation allows us to easily manage the complexity of knowledge, to view the knowledge at different levels of details, and to focus our attention on the interesting aspects only. One of such efficient and easy to understand systems is Hierarchical Production rule (HPRs) system. A HPR, a standard production rule augmented with generality and specificity information, is of the following form: Decision If < condition> Generality Specificity . HPRs systems are capable of handling taxonomical structures inherent in the knowledge about the real world. This paper focuses on the issue of mining Quantified rules with crisp hierarchical structure using Genetic Programming (GP) approach to knowledge discovery. The post-processing scheme presented in this work uses Quantified production rules as initial individuals of GP and discovers hierarchical structure. In proposed approach rules are quantified by using Dempster Shafer theory. Suitable genetic operators are proposed for the suggested encoding. Based on the Subsumption Matrix(SM), an appropriate fitness function is suggested. Finally, Quantified Hierarchical Production Rules (HPRs) are generated from the discovered hierarchy, using Dempster Shafer theory. Experimental results are presented to demonstrate the performance of the proposed algorithm.
Abstract: Most integrated inertial navigation systems (INS) and
global positioning systems (GPS) have been implemented using the
Kalman filtering technique with its drawbacks related to the need for
predefined INS error model and observability of at least four
satellites. Most recently, a method using a hybrid-adaptive network
based fuzzy inference system (ANFIS) has been proposed which is
trained during the availability of GPS signal to map the error
between the GPS and the INS. Then it will be used to predict the
error of the INS position components during GPS signal blockage.
This paper introduces a genetic optimization algorithm that is used to
update the ANFIS parameters with respect to the INS/GPS error
function used as the objective function to be minimized. The results
demonstrate the advantages of the genetically optimized ANFIS for
INS/GPS integration in comparison with conventional ANFIS
specially in the cases of satellites- outages. Coping with this problem
plays an important role in assessment of the fusion approach in land
navigation.
Abstract: We constructed a method of noise reduction for
JPEG-compressed image based on Bayesian inference using the
maximizer of the posterior marginal (MPM) estimate. In this method,
we tried the MPM estimate using two kinds of likelihood, both of
which enhance grayscale images converted into the JPEG-compressed
image through the lossy JPEG image compression. One is the
deterministic model of the likelihood and the other is the probabilistic
one expressed by the Gaussian distribution. Then, using the Monte
Carlo simulation for grayscale images, such as the 256-grayscale
standard image “Lena" with 256 × 256 pixels, we examined the
performance of the MPM estimate based on the performance measure
using the mean square error. We clarified that the MPM estimate via
the Gaussian probabilistic model of the likelihood is effective for
reducing noises, such as the blocking artifacts and the mosquito noise,
if we set parameters appropriately. On the other hand, we found that
the MPM estimate via the deterministic model of the likelihood is not
effective for noise reduction due to the low acceptance ratio of the
Metropolis algorithm.
Abstract: In many countries, digital city or ubiquitous city
(u-City) projects have been initiated to provide digitalized economic
environments to cities. Recently in Korea, Kangwon Province has
started the u-Kangwon project to boost local economy with digitalized
tourism services. We analyze the limitations of the ubiquitous IT
approach through the u-Kangwon case. We have found that travelers
are more interested in quality over speed in access of information. For
improved service quality, we are looking to develop an
IT-convergence service design framework (ISDF). The ISDF is based
on the service engineering technique and composed of three parts:
Service Design, Service Simulation, and the Service Platform.
Abstract: Trust management is one of the drawbacks in Peer-to-Peer (P2P) system. Lack of centralized control makes it difficult to control the behavior of the peers. Reputation system is one approach to provide trust assessment in P2P system. In this paper, we use fuzzy logic to model trust in a P2P environment. Our trust model combines first-hand (direct experience) and second-hand (reputation)information to allow peers to represent and reason with uncertainty regarding other peers' trustworthiness. Fuzzy logic can help in handling the imprecise nature and uncertainty of trust. Linguistic labels are used to enable peers assign a trust level intuitively. Our fuzzy trust model is flexible such that inference rules are used to weight first-hand and second-hand accordingly.
Abstract: In this paper a new cost function for blind equalization
is proposed. The proposed cost function, referred to as the modified
maximum normalized cumulant criterion (MMNC), is an extension
of the previously proposed maximum normalized cumulant criterion
(MNC). While the MNC requires a separate phase recovery system
after blind equalization, the MMNC performs joint blind equalization
and phase recovery. To achieve this, the proposed algorithm
maximizes a cost function that considers both amplitude and phase of
the equalizer output. The simulation results show that the proposed
algorithm has an improved channel equalization effect than the MNC
algorithm and simultaneously can correct the phase error that the
MNC algorithm is unable to do. The simulation results also show that
the MMNC algorithm has lower complexity than the MNC algorithm.
Moreover, the MMNC algorithm outperforms the MNC algorithm
particularly when the symbols block size is small.
Abstract: In this study, a high accuracy protein-protein interaction
prediction method is developed. The importance of the proposed
method is that it only uses sequence information of proteins while
predicting interaction. The method extracts phylogenetic profiles of
proteins by using their sequence information. Combining the phylogenetic
profiles of two proteins by checking existence of homologs
in different species and fitting this combined profile into a statistical
model, it is possible to make predictions about the interaction status
of two proteins.
For this purpose, we apply a collection of pattern recognition
techniques on the dataset of combined phylogenetic profiles of protein
pairs. Support Vector Machines, Feature Extraction using ReliefF,
Naive Bayes Classification, K-Nearest Neighborhood Classification,
Decision Trees, and Random Forest Classification are the methods
we applied for finding the classification method that best predicts
the interaction status of protein pairs. Random Forest Classification
outperformed all other methods with a prediction accuracy of 76.93%
Abstract: In data mining, the association rules are used to find
for the associations between the different items of the transactions
database. As the data collected and stored, rules of value can be found
through association rules, which can be applied to help managers
execute marketing strategies and establish sound market frameworks.
This paper aims to use Fuzzy Frequent Pattern growth (FFP-growth)
to derive from fuzzy association rules. At first, we apply fuzzy
partition methods and decide a membership function of quantitative
value for each transaction item. Next, we implement FFP-growth
to deal with the process of data mining. In addition, in order to
understand the impact of Apriori algorithm and FFP-growth algorithm
on the execution time and the number of generated association
rules, the experiment will be performed by using different sizes of
databases and thresholds. Lastly, the experiment results show FFPgrowth
algorithm is more efficient than other existing methods.
Abstract: The overall objective of this paper is to retrieve soil
surfaces parameters namely, roughness and soil moisture related to
the dielectric constant by inverting the radar backscattered signal
from natural soil surfaces.
Because the classical description of roughness using statistical
parameters like the correlation length doesn't lead to satisfactory
results to predict radar backscattering, we used a multi-scale
roughness description using the wavelet transform and the Mallat
algorithm. In this description, the surface is considered as a
superposition of a finite number of one-dimensional Gaussian
processes each having a spatial scale. A second step in this study
consisted in adapting a direct model simulating radar backscattering
namely the small perturbation model to this multi-scale surface
description. We investigated the impact of this description on radar
backscattering through a sensitivity analysis of backscattering
coefficient to the multi-scale roughness parameters.
To perform the inversion of the small perturbation multi-scale
scattering model (MLS SPM) we used a multi-layer neural network
architecture trained by backpropagation learning rule. The inversion
leads to satisfactory results with a relative uncertainty of 8%.
Abstract: This paper investigates how the use of machine learning techniques can significantly predict the three major dimensions of learner-s emotions (pleasure, arousal and dominance) from brainwaves. This study has adopted an experimentation in which participants were exposed to a set of pictures from the International Affective Picture System (IAPS) while their electrical brain activity was recorded with an electroencephalogram (EEG). The pictures were already rated in a previous study via the affective rating system Self-Assessment Manikin (SAM) to assess the three dimensions of pleasure, arousal, and dominance. For each picture, we took the mean of these values for all subjects used in this previous study and associated them to the recorded brainwaves of the participants in our study. Correlation and regression analyses confirmed the hypothesis that brainwave measures could significantly predict emotional dimensions. This can be very useful in the case of impassive, taciturn or disabled learners. Standard classification techniques were used to assess the reliability of the automatic detection of learners- three major dimensions from the brainwaves. We discuss the results and the pertinence of such a method to assess learner-s emotions and integrate it into a brainwavesensing Intelligent Tutoring System.
Abstract: In Data mining, Fuzzy clustering algorithms have
demonstrated advantage over crisp clustering algorithms in dealing
with the challenges posed by large collections of vague and uncertain
natural data. This paper reviews concept of fuzzy logic and fuzzy
clustering. The classical fuzzy c-means algorithm is presented and its
limitations are highlighted. Based on the study of the fuzzy c-means
algorithm and its extensions, we propose a modification to the cmeans
algorithm to overcome the limitations of it in calculating the
new cluster centers and in finding the membership values with
natural data. The efficiency of the new modified method is
demonstrated on real data collected for Bhutan-s Gross National
Happiness (GNH) program.
Abstract: Intelligent systems are required in order to quickly and accurately analyze enormous quantities of data in the Internet environment. In intelligent systems, information extracting processes can be divided into supervised learning and unsupervised learning. This paper investigates intelligent clustering by unsupervised learning. Intelligent clustering is the clustering system which determines the clustering model for data analysis and evaluates results by itself. This system can make a clustering model more rapidly, objectively and accurately than an analyzer. The methodology for the automatic clustering intelligent system is a multi-agent system that comprises a clustering agent and a cluster performance evaluation agent. An agent exchanges information about clusters with another agent and the system determines the optimal cluster number through this information. Experiments using data sets in the UCI Machine Repository are performed in order to prove the validity of the system.
Abstract: In this paper, we propose the variational approach to solve single image defogging problem. In the inference process of the atmospheric veil, we defined new functional for atmospheric veil that satisfy edge-preserving regularization property. By using the fundamental lemma of calculus of variations, we derive the Euler-Lagrange equation foratmospheric veil that can find the maxima of a given functional. This equation can be solved by using a gradient decent method and time parameter. Then, we can have obtained the estimated atmospheric veil, and then have conducted the image restoration by using inferred atmospheric veil. Finally we have improved the contrast of restoration image by various histogram equalization methods. The experimental results show that the proposed method achieves rather good defogging results.
Abstract: The evaluation of conversational agents or chatterbots question answering systems is a major research area that needs much attention. Before the rise of domain-oriented conversational agents based on natural language understanding and reasoning, evaluation is never a problem as information retrieval-based metrics are readily available for use. However, when chatterbots began to become more domain specific, evaluation becomes a real issue. This is especially true when understanding and reasoning is required to cater for a wider variety of questions and at the same time to achieve high quality responses. This paper discusses the inappropriateness of the existing measures for response quality evaluation and the call for new standard measures and related considerations are brought forward. As a short-term solution for evaluating response quality of conversational agents, and to demonstrate the challenges in evaluating systems of different nature, this research proposes a blackbox approach using observation, classification scheme and a scoring mechanism to assess and rank three example systems, AnswerBus, START and AINI.
Abstract: The most influential programming paradigm today
is object oriented (OO) programming and it is widely used in
education and industry. Recognizing the importance of equipping
students with OO knowledge and skills, it is not surprising that most
Computer Science degree programs offer OO-related courses. How
do we assess whether the students have acquired the right objectoriented
skills after they have completed their OO courses? What are
object oriented skills? Currently none of the current assessment
techniques would be able to provide this answer. Traditional forms of
OO programming assessment provide a ways for assigning numerical
scores to determine letter grades. But this rarely reveals information
about how students actually understand OO concept. It appears
reasonable that a better understanding of how to define and assess
OO skills is needed by developing a criterion referenced model. It is
even critical in the context of Malaysia where there is currently a
growing concern over the level of competency of Malaysian IT
graduates in object oriented programming. This paper discussed the
approach used to develop the criterion-referenced assessment model.
The model can serve as a guideline when conducting OO
programming assessment as mentioned. The proposed model is
derived by using Goal Questions Metrics methodology, which helps
formulate the metrics of interest. It concluded with a few suggestions
for further study.
Abstract: This paper presents a new technique for generating sets of synthetic classifiers to evaluate abstract-level combination methods. The sets differ in terms of both recognition rates of the individual classifiers and degree of similarity. For this purpose, each abstract-level classifier is considered as a random variable producing one class label as the output for an input pattern. From the initial set of classifiers, new slightly different sets are generated by applying specific operators, which are defined at the purpose. Finally, the sets of synthetic classifiers have been used to estimate the performance of combination methods for abstract-level classifiers. The experimental results demonstrate the effectiveness of the proposed approach.
Abstract: The understanding of the system level of biological behavior and phenomenon variously needs some elements such as gene sequence, protein structure, gene functions and metabolic pathways. Challenging problems are representing, learning and reasoning about these biochemical reactions, gene and protein structure, genotype and relation between the phenotype, and expression system on those interactions. The goal of our work is to understand the behaviors of the interactions networks and to model their evolution in time and in space. We propose in this study an ontological meta-model for the knowledge representation of the genetic regulatory networks. Ontology in artificial intelligence means the fundamental categories and relations that provide a framework for knowledge models. Domain ontology's are now commonly used to enable heterogeneous information resources, such as knowledge-based systems, to communicate with each other. The interest of our model is to represent the spatial, temporal and spatio-temporal knowledge. We validated our propositions in the genetic regulatory network of the Aarbidosis thaliana flower
Abstract: Graph rewriting-based visual model processing is a
widely used technique for model transformation. Visual model
transformations often need to follow an algorithm that requires a
strict control over the execution sequence of the transformation steps.
Therefore, in Visual Model Processors (VMPs) the execution order
of the transformation steps is crucial. This paper presents the visual
control flow support of Visual Modeling and Transformation System
(VMTS), which facilitates composing complex model
transformations of simple transformation steps and executing them.
The VMTS Visual Control Flow Language (VCFL) uses stereotyped
activity diagrams to specify control flow structures and OCL
constraints to choose between different control flow branches. This
paper introduces VCFL, discusses its termination properties and
provides an algorithm to support the termination analysis of VCFL
transformations.
Abstract: The use of human hand as a natural interface for humancomputer interaction (HCI) serves as the motivation for research in hand gesture recognition. Vision-based hand gesture recognition involves visual analysis of hand shape, position and/or movement. In this paper, we use the concept of object-based video abstraction for segmenting the frames into video object planes (VOPs), as used in MPEG-4, with each VOP corresponding to one semantically meaningful hand position. Next, the key VOPs are selected on the basis of the amount of change in hand shape – for a given key frame in the sequence the next key frame is the one in which the hand changes its shape significantly. Thus, an entire video clip is transformed into a small number of representative frames that are sufficient to represent a gesture sequence. Subsequently, we model a particular gesture as a sequence of key frames each bearing information about its duration. These constitute a finite state machine. For recognition, the states of the incoming gesture sequence are matched with the states of all different FSMs contained in the database of gesture vocabulary. The core idea of our proposed representation is that redundant frames of the gesture video sequence bear only the temporal information of a gesture and hence discarded for computational efficiency. Experimental results obtained demonstrate the effectiveness of our proposed scheme for key frame extraction, subsequent gesture summarization and finally gesture recognition.