Abstract: This paper deals with the application of a well-known neural network technique, multilayer back-propagation (BP) neural network, in financial data mining. A modified neural network forecasting model is presented, and an intelligent mining system is developed. The system can forecast the buying and selling signs according to the prediction of future trends to stock market, and provide decision-making for stock investors. The simulation result of seven years to Shanghai Composite Index shows that the return achieved by this mining system is about three times as large as that achieved by the buy and hold strategy, so it is advantageous to apply neural networks to forecast financial time series, the different investors could benefit from it.
Abstract: Nowadays, Gene Ontology has been used widely by many researchers for biological data mining and information retrieval, integration of biological databases, finding genes, and incorporating knowledge in the Gene Ontology for gene clustering. However, the increase in size of the Gene Ontology has caused problems in maintaining and processing them. One way to obtain their accessibility is by clustering them into fragmented groups. Clustering the Gene Ontology is a difficult combinatorial problem and can be modeled as a graph partitioning problem. Additionally, deciding the number k of clusters to use is not easily perceived and is a hard algorithmic problem. Therefore, an approach for solving the automatic clustering of the Gene Ontology is proposed by incorporating cohesion-and-coupling metric into a hybrid algorithm consisting of a genetic algorithm and a split-and-merge algorithm. Experimental results and an example of modularized Gene Ontology in RDF/XML format are given to illustrate the effectiveness of the algorithm.
Abstract: In this paper, we present a new algorithm for clustering data in large datasets using image processing approaches. First the dataset is mapped into a binary image plane. The synthesized image is then processed utilizing efficient image processing techniques to cluster the data in the dataset. Henceforth, the algorithm avoids exhaustive search to identify clusters. The algorithm considers only a small set of the data that contains critical boundary information sufficient to identify contained clusters. Compared to available data clustering techniques, the proposed algorithm produces similar quality results and outperforms them in execution time and storage requirements.
Abstract: The one-class support vector machine “support vector
data description” (SVDD) is an ideal approach for anomaly or outlier
detection. However, for the applicability of SVDD in real-world
applications, the ease of use is crucial. The results of SVDD are
massively determined by the choice of the regularisation parameter C
and the kernel parameter of the widely used RBF kernel. While for
two-class SVMs the parameters can be tuned using cross-validation
based on the confusion matrix, for a one-class SVM this is not
possible, because only true positives and false negatives can occur
during training. This paper proposes an approach to find the optimal
set of parameters for SVDD solely based on a training set from
one class and without any user parameterisation. Results on artificial
and real data sets are presented, underpinning the usefulness of the
approach.
Abstract: Much research into handwritten Thai character
recognition have been proposed, such as comparing heads of
characters, Fuzzy logic and structure trees, etc. This paper presents a
system of handwritten Thai character recognition, which is based on
the Ant-minor algorithm (data mining based on Ant colony
optimization). Zoning is initially used to determine each character.
Then three distinct features (also called attributes) of each character
in each zone are extracted. The attributes are Head zone, End point,
and Feature code. All attributes are used for construct the
classification rules by an Ant-miner algorithm in order to classify
112 Thai characters. For this experiment, the Ant-miner algorithm is
adapted, with a small change to increase the recognition rate. The
result of this experiment is a 97% recognition rate of the training set
(11200 characters) and 82.7% recognition rate of unseen data test
(22400 characters).
Abstract: Every day human life experiences new equipments
more automatic and with more abilities. So the need for faster
processors doesn-t seem to finish. Despite new architectures and
higher frequencies, a single processor is not adequate for many
applications. Parallel processing and networks are previous solutions
for this problem. The new solution to put a network of resources on a
chip is called NOC (network on a chip). The more usual topology for
NOC is mesh topology. There are several routing algorithms suitable
for this topology such as XY, fully adaptive, etc. In this paper we
have suggested a new algorithm named Intermittent X, Y (IX/Y). We
have developed the new algorithm in simulation environment to
compare delay and power consumption with elders' algorithms.
Abstract: An end-member selection method for spectral unmixing that is based on Particle Swarm Optimization (PSO) is developed in this paper. The algorithm uses the K-means clustering algorithm and a method of dynamic selection of end-members subsets to find the appropriate set of end-members for a given set of multispectral images. The proposed algorithm has been successfully applied to test image sets from various platforms such as LANDSAT 5 MSS and NOAA's AVHRR. The experimental results of the proposed algorithm are encouraging. The influence of different values of the algorithm control parameters on performance is studied. Furthermore, the performance of different versions of PSO is also investigated.
Abstract: In the automotive industry test drives are being conducted
during the development of new vehicle models or as a part of
quality assurance of series-production vehicles. The communication
on the in-vehicle network, data from external sensors, or internal
data from the electronic control units is recorded by automotive
data loggers during the test drives. The recordings are used for fault
analysis. Since the resulting data volume is tremendous, manually
analysing each recording in great detail is not feasible.
This paper proposes to use machine learning to support domainexperts
by preventing them from contemplating irrelevant data and
rather pointing them to the relevant parts in the recordings. The
underlying idea is to learn the normal behaviour from available
recordings, i.e. a training set, and then to autonomously detect
unexpected deviations and report them as anomalies.
The one-class support vector machine “support vector data description”
is utilised to calculate distances of feature vectors. SVDDSUBSEQ
is proposed as a novel approach, allowing to classify subsequences
in multivariate time series data. The approach allows to
detect unexpected faults without modelling effort as is shown with
experimental results on recordings from test drives.
Abstract: The trends of design and development of information systems have undergone a variety of ongoing phases and stages. These variations have been evolved due to brisk changes in user requirements and business needs. To meet these requirements and needs, a flexible and agile business solution was required to come up with the latest business trends and styles. Another obstacle in agility of information systems was typically different treatment of same diseases of two patients: business processes and information services. After the emergence of information technology, the business processes and information systems have become counterparts. But these two business halves have been treated under totally different standards. There is need to streamline the boundaries of these both pillars that are equally sharing information system's burdens and liabilities. In last decade, the object orientation has evolved into one of the major solutions for modern business needs and now, SOA is the solution to shift business on ranks of electronic platform. BPM is another modern business solution that assists to regularize optimization of business processes. This paper discusses how object orientation can be conformed to incorporate or embed SOA in BPM for improved information systems.
Abstract: Knowledge sharing in general and the contextual
access to knowledge in particular, still represent a key challenge in
the knowledge management framework. Researchers on semantic
web and human machine interface study techniques to enhance this
access. For instance, in semantic web, the information retrieval is
based on domain ontology. In human machine interface, keeping
track of user's activity provides some elements of the context that can
guide the access to information. We suggest an approach based on
these two key guidelines, whilst avoiding some of their weaknesses.
The approach permits a representation of both the context and the
design rationale of a project for an efficient access to knowledge. In
fact, the method consists of an information retrieval environment
that, in the one hand, can infer knowledge, modeled as a semantic
network, and on the other hand, is based on the context and the
objectives of a specific activity (the design). The environment we
defined can also be used to gather similar project elements in order to
build classifications of tasks, problems, arguments, etc. produced in a
company. These classifications can show the evolution of design
strategies in the company.
Abstract: This Classifying Bird Sounds (chip notes) project-s
purpose is to reduce the unwanted noise from recorded bird sound
chip notes, design a scheme to detect differences and similarities
between recorded chip notes, and classify bird sound chip notes. The
technologies of determining the similarities of sound waves have
been used in communication, sound engineering and wireless sound
applications for many years. Our research is focused on the similarity
of chip notes, which are the sounds from different birds. The program
we use is generated by Microsoft Cµ.
Abstract: Results of Chilean wine classification based on the
information provided by an electronic nose are reported in this paper.
The classification scheme consists of two parts; in the first stage,
Principal Component Analysis is used as feature extraction method to
reduce the dimensionality of the original information. Then, Radial
Basis Functions Neural Networks is used as pattern recognition
technique to perform the classification. The objective of this study is
to classify different Cabernet Sauvignon, Merlot and Carménère wine
samples from different years, valleys and vineyards of Chile.
Abstract: Previous the 3D model texture generation from multi-view images and mapping algorithms has issues in the texture chart generation which are the self-intersection and the concentration of the texture in texture space. Also we may suffer from some problems due to the occluded areas, such as inside parts of thighs. In this paper we propose a texture mapping technique for 3D models using multi-view images on the GPU. We do texture mapping directly on the GPU fragment shader per pixel without generation of the texture map. And we solve for the occluded area using the 3D model depth information. Our method needs more calculation on the GPU than previous works, but it has shown real-time performance and previously mentioned problems do not occur.
Abstract: A key to success of high quality software development
is to define valid and feasible requirements specification. We have
proposed a method of model-driven requirements analysis using
Unified Modeling Language (UML). The main feature of our method
is to automatically generate a Web user interface mock-up from UML
requirements analysis model so that we can confirm validity of
input/output data for each page and page transition on the system by
directly operating the mock-up. This paper proposes a support method
to check the validity of a data life cycle by using a model checking tool
“UPPAAL" focusing on CRUD (Create, Read, Update and Delete).
Exhaustive checking improves the quality of requirements analysis
model which are validated by the customers through automatically
generated mock-up. The effectiveness of our method is discussed by a
case study of requirements modeling of two small projects which are a
library management system and a supportive sales system for text
books in a university.
Abstract: In ad hoc networks, the main issue about designing of protocols is quality of service, so that in wireless sensor networks the main constraint in designing protocols is limited energy of sensors. In fact, protocols which minimize the power consumption in sensors are more considered in wireless sensor networks. One approach of reducing energy consumption in wireless sensor networks is to reduce the number of packages that are transmitted in network. The technique of collecting data that combines related data and prevent transmission of additional packages in network can be effective in the reducing of transmitted packages- number. According to this fact that information processing consumes less power than information transmitting, Data Aggregation has great importance and because of this fact this technique is used in many protocols [5]. One of the Data Aggregation techniques is to use Data Aggregation tree. But finding one optimum Data Aggregation tree to collect data in networks with one sink is a NP-hard problem. In the Data Aggregation technique, related information packages are combined in intermediate nodes and form one package. So the number of packages which are transmitted in network reduces and therefore, less energy will be consumed that at last results in improvement of longevity of network. Heuristic methods are used in order to solve the NP-hard problem that one of these optimization methods is to solve Simulated Annealing problems. In this article, we will propose new method in order to build data collection tree in wireless sensor networks by using Simulated Annealing algorithm and we will evaluate its efficiency whit Genetic Algorithm.
Abstract: Researchers have been applying tional intelligence (AI/CI) methods to computer games. In this research field, further researchesare required to compare AI/CI
methods with respect to each game application. In th
our experimental result on the comparison of three evolutionary algorithms – evolution strategy, genetic algorithm, and their hybrid
applied to evolving controller agents for the CIG 2007 Simulated Car Racing competition. Our experimental result shows that, premature
convergence of solutions was observed in the case of ES, and GA outperformed ES in the last half of generations. Besides, a hybrid
which uses GA first and ES next evolved the best solution among the whole solutions being generated. This result shows the ability of GA in
globally searching promising areas in the early stage and the ability of ES in locally searching the focused area (fine-tuning solutions).
Abstract: Image Compression using Artificial Neural Networks
is a topic where research is being carried out in various directions
towards achieving a generalized and economical network.
Feedforward Networks using Back propagation Algorithm adopting
the method of steepest descent for error minimization is popular and
widely adopted and is directly applied to image compression.
Various research works are directed towards achieving quick
convergence of the network without loss of quality of the restored
image. In general the images used for compression are of different
types like dark image, high intensity image etc. When these images
are compressed using Back-propagation Network, it takes longer
time to converge. The reason for this is, the given image may
contain a number of distinct gray levels with narrow difference with
their neighborhood pixels. If the gray levels of the pixels in an image
and their neighbors are mapped in such a way that the difference in
the gray levels of the neighbors with the pixel is minimum, then
compression ratio as well as the convergence of the network can be
improved. To achieve this, a Cumulative distribution function is
estimated for the image and it is used to map the image pixels. When
the mapped image pixels are used, the Back-propagation Neural
Network yields high compression ratio as well as it converges
quickly.
Abstract: Despite the recent surge of research in control of
worm propagation, currently, there is no effective defense system
against such cyber attacks. We first design a distributed detection
architecture called Detection via Distributed Blackholes (DDBH).
Our novel detection mechanism could be implemented via virtual
honeypots or honeynets. Simulation results show that a worm can be
detected with virtual honeypots on only 3% of the nodes. Moreover,
the worm is detected when less than 1.5% of the nodes are infected.
We then develop two control strategies: (1) optimal dynamic trafficblocking,
for which we determine the condition that guarantees
minimum number of removed nodes when the worm is contained and
(2) predictive dynamic traffic-blocking–a realistic deployment of
the optimal strategy on scale-free graphs. The predictive dynamic
traffic-blocking, coupled with the DDBH, ensures that more than
40% of the network is unaffected by the propagation at the time
when the worm is contained.
Abstract: To illustrate diversity of methods used to extract relevant (where the concept of relevance can be differently defined for different applications) visual data, the paper discusses three groups of such methods. They have been selected from a range of alternatives to highlight how hardware and software tools can be complementarily used in order to achieve various functionalities in case of different specifications of “relevant data". First, principles of gated imaging are presented (where relevance is determined by the range). The second methodology is intended for intelligent intrusion detection, while the last one is used for content-based image matching and retrieval. All methods have been developed within projects supervised by the author.
Abstract: Secure electronic payment system is presented in this
paper. This electronic payment system is to be secure for clients such
as customers and shop owners. The security architecture of the
system is designed by RC5 encryption / decryption algorithm. This
eliminates the fraud that occurs today with stolen credit card
numbers. The symmetric key cryptosystem RC5 can protect
conventional transaction data such as account numbers, amount and
other information. This process can be done electronically using RC5
encryption / decryption program written by Microsoft Visual Basic
6.0. There is no danger of any data sent within the system being
intercepted, and replaced. The alternative is to use the existing
network, and to encrypt all data transmissions. The system with
encryption is acceptably secure, but that the level of encryption has
to be stepped up, as computing power increases. Results In order to
be secure the system the communication between modules is
encrypted using symmetric key cryptosystem RC5. The system will
use simple user name, password, user ID, user type and cipher
authentication mechanism for identification, when the user first
enters the system. It is the most common method of authentication in
most computer system.