Abstract: This paper presents a novel method for remaining
useful life prediction using the Elliptical Basis Function (EBF)
network and a Markov chain. The EBF structure is trained by a
modified Expectation-Maximization (EM) algorithm in order to take
into account the missing covariate set. No explicit extrapolation is
needed for internal covariates while a Markov chain is constructed to
represent the evolution of external covariates in the study. The
estimated external and the unknown internal covariates constitute an
incomplete covariate set which are then used and analyzed by the EBF
network to provide survival information of the asset. It is shown in the
case study that the method slightly underestimates the remaining
useful life of an asset which is a desirable result for early maintenance
decision and resource planning.
Abstract: This paper presents the methodology from machine
learning approaches for short-term rain forecasting system. Decision
Tree, Artificial Neural Network (ANN), and Support Vector Machine
(SVM) were applied to develop classification and prediction models
for rainfall forecasts. The goals of this presentation are to
demonstrate (1) how feature selection can be used to identify the
relationships between rainfall occurrences and other weather
conditions and (2) what models can be developed and deployed for
predicting the accurate rainfall estimates to support the decisions to
launch the cloud seeding operations in the northeastern part of
Thailand. Datasets collected during 2004-2006 from the
Chalermprakiat Royal Rain Making Research Center at Hua Hin,
Prachuap Khiri khan, the Chalermprakiat Royal Rain Making
Research Center at Pimai, Nakhon Ratchasima and Thai
Meteorological Department (TMD). A total of 179 records with 57
features was merged and matched by unique date. There are three
main parts in this work. Firstly, a decision tree induction algorithm
(C4.5) was used to classify the rain status into either rain or no-rain.
The overall accuracy of classification tree achieves 94.41% with the
five-fold cross validation. The C4.5 algorithm was also used to
classify the rain amount into three classes as no-rain (0-0.1 mm.),
few-rain (0.1- 10 mm.), and moderate-rain (>10 mm.) and the overall
accuracy of classification tree achieves 62.57%. Secondly, an ANN
was applied to predict the rainfall amount and the root mean square
error (RMSE) were used to measure the training and testing errors of
the ANN. It is found that the ANN yields a lower RMSE at 0.171 for
daily rainfall estimates, when compared to next-day and next-2-day
estimation. Thirdly, the ANN and SVM techniques were also used to
classify the rain amount into three classes as no-rain, few-rain, and
moderate-rain as above. The results achieved in 68.15% and 69.10%
of overall accuracy of same-day prediction for the ANN and SVM
models, respectively. The obtained results illustrated the comparison
of the predictive power of different methods for rainfall estimation.
Abstract: Although lots of research work has been done for
human pose recognition, the view-point of cameras is still critical
problem of overall recognition system. In this paper, view-point
insensitive human pose recognition is proposed. The aims of the
proposed system are view-point insensitivity and real-time processing.
Recognition system consists of feature extraction module, neural
network and real-time feed forward calculation. First, histogram-based
method is used to extract feature from silhouette image and it is
suitable for represent the shape of human pose. To reduce the
dimension of feature vector, Principle Component Analysis(PCA) is
used. Second, real-time processing is implemented by using Compute
Unified Device Architecture(CUDA) and this architecture improves
the speed of feed-forward calculation of neural network. We
demonstrate the effectiveness of our approach with experiments on
real environment.
Abstract: Tool wear and surface roughness prediction plays a
significant role in machining industry for proper planning and control
of machining parameters and optimization of cutting conditions. This
paper deals with developing an artificial neural network (ANN)
model as a function of cutting parameters in turning steel under
minimum quantity lubrication (MQL). A feed-forward
backpropagation network with twenty five hidden neurons has been
selected as the optimum network. The co-efficient of determination
(R2) between model predictions and experimental values are 0.9915,
0.9906, 0.9761 and 0.9627 in terms of VB, VM, VS and Ra
respectively. The results imply that the model can be used easily to
forecast tool wear and surface roughness in response to cutting
parameters.
Abstract: In this paper, a neural network tuned fuzzy controller
is proposed for controlling Multi-Input Multi-Output (MIMO)
systems. For the convenience of analysis, the structure of MIMO
fuzzy controller is divided into single input single-output (SISO)
controllers for controlling each degree of freedom. Secondly,
according to the characteristics of the system-s dynamics coupling, an
appropriate coupling fuzzy controller is incorporated to improve the
performance. The simulation analysis on a two-level mass–spring
MIMO vibration system is carried out and results show the
effectiveness of the proposed fuzzy controller. The performance
though improved, the computational time and memory used is
comparatively higher, because it has four fuzzy reasoning blocks and
number may increase in case of other MIMO system. Then a fuzzy
neural network is designed from a set of input-output training data to
reduce the computing burden during implementation. This control
strategy can not only simplify the implementation problem of fuzzy
control, but also reduce computational time and consume less
memory.
Abstract: Scheduling algorithms are used in operating systems
to optimize the usage of processors. One of the most efficient
algorithms for scheduling is Multi-Layer Feedback Queue (MLFQ)
algorithm which uses several queues with different quanta. The most
important weakness of this method is the inability to define the
optimized the number of the queues and quantum of each queue. This
weakness has been improved in IMLFQ scheduling algorithm.
Number of the queues and quantum of each queue affect the response
time directly. In this paper, we review the IMLFQ algorithm for
solving these problems and minimizing the response time. In this
algorithm Recurrent Neural Network has been utilized to find both
the number of queues and the optimized quantum of each queue.
Also in order to prevent any probable faults in processes' response
time computation, a new fault tolerant approach has been presented.
In this approach we use combinational software redundancy to
prevent the any probable faults. The experimental results show that
using the IMLFQ algorithm results in better response time in
comparison with other scheduling algorithms also by using fault
tolerant mechanism we improve IMLFQ performance.
Abstract: This paper presents a method to estimate load profile
in a multiple power flow solutions for every minutes in 24 hours per
day. A method to calculate multiple solutions of non linear profile is
introduced. The Power System Simulation/Engineering (PSS®E) and
python has been used to solve the load power flow. The result of this
power flow solutions has been used to estimate the load profiles for
each load at buses using Independent Component Analysis (ICA)
without any knowledge of parameter and network topology of the
systems. The proposed algorithm is tested with IEEE 69 test bus
system represents for distribution part and the method of ICA has
been programmed in MATLAB R2012b version. Simulation results
and errors of estimations are discussed in this paper.
Abstract: Stochastic models of biological networks are well established in systems biology, where the computational treatment of such models is often focused on the solution of the so-called chemical master equation via stochastic simulation algorithms. In contrast to this, the development of storage-efficient model representations that are directly suitable for computer implementation has received significantly less attention. Instead, a model is usually described in terms of a stochastic process or a "higher-level paradigm" with graphical representation such as e.g. a stochastic Petri net. A serious problem then arises due to the exponential growth of the model-s state space which is in fact a main reason for the popularity of stochastic simulation since simulation suffers less from the state space explosion than non-simulative numerical solution techniques. In this paper we present transition class models for the representation of biological network models, a compact mathematical formalism that circumvents state space explosion. Transition class models can also serve as an interface between different higher level modeling paradigms, stochastic processes and the implementation coded in a programming language. Besides, the compact model representation provides the opportunity to apply non-simulative solution techniques thereby preserving the possible use of stochastic simulation. Illustrative examples of transition class representations are given for an enzyme-catalyzed substrate conversion and a part of the bacteriophage λ lysis/lysogeny pathway.
Abstract: A method has been developed for preparing load
models for power flow and stability. The load modeling
(LOADMOD) computer software transforms data on load class mix,
composition, and characteristics into the from required for
commonly–used power flow and transient stability simulation
programs. Typical default data have been developed for load
composition and characteristics. This paper defines LOADMOD
software and describes the dynamic and static load modeling
techniques used in this software and results of initial testing for
BAKHTAR power system.
Abstract: In many sensor network applications, sensor nodes are deployed in open environments, and hence are vulnerable to physical attacks, potentially compromising the node's cryptographic keys. False sensing report can be injected through compromised nodes, which can lead to not only false alarms but also the depletion of limited energy resource in battery powered networks. Ye et al. proposed a statistical en-route filtering scheme (SEF) to detect such false reports during the forwarding process. In this scheme, the choice of a security threshold value is important since it trades off detection power and overhead. In this paper, we propose a fuzzy logic for determining a security threshold value in the SEF based sensor networks. The fuzzy logic determines a security threshold by considering the number of partitions in a global key pool, the number of compromised partitions, and the energy level of nodes. The fuzzy based threshold value can conserve energy, while it provides sufficient detection power.
Abstract: The recent development of Information and Communication Technology (ICT) enables new ways of "democratic" decision-making such as a page-ranking system, which estimates the importance of a web page based on indirect trust on that page shared by diverse group of unorganized individuals. These kinds of "democracy" have not been acclaimed yet in the world of real politics. On the other hand, a large amount of data about personal relations including trust, norms of reciprocity, and networks of civic engagement has been accumulated in a computer-readable form by computer systems (e.g., social networking systems). We can use these relations as a new type of social capital to construct a new democratic decision-making system based on a delegation network. In this paper, we propose an effective decision-making support system, which is based on empowering someone's vote whom you trust. For this purpose, we propose two new techniques: the first is for estimating entire vote distribution from a small number of votes, and the second is for estimating active voter choice to promote voting using a delegation network. We show that these techniques could increase the voting ratio and credibility of the whole decision by agent-based simulations.
Abstract: Electrophysiological signals were recorded from primary cultures of dissociated rat cortical neurons coupled to Micro-Electrode Arrays (MEAs). The neuronal discharge patterns may change under varying physiological and pathological conditions. For this reason, we developed a new burst detection method able to identify bursts with peculiar features in different experimental conditions (i.e. spontaneous activity and under the effect of specific drugs). The main feature of our algorithm (i.e. Burst On Hurst), based on the auto-similarity or fractal property of the recorded signal, is the independence from the chosen spike detection method since it works directly on the raw data.
Abstract: One of the most importance of intelligence in-car and
roadside systems is the cooperative vehicle-infrastructure system. In
Thailand, ITS technologies are rapidly growing and real-time vehicle
information is considerably needed for ITS applications; for example,
vehicle fleet tracking and control and road traffic monitoring
systems. This paper defines the communication protocols and
software design for middleware components of B-VIS (Burapha
Vehicle-Infrastructure System). The proposed B-VIS middleware architecture serves the needs of a distributed RFID sensor network and simplifies some intricate details of several communication standards.
Abstract: The Chiu-s method which generates a Takagi-Sugeno Fuzzy Inference System (FIS) is a method of fuzzy rules extraction. The rules output is a linear function of inputs. In addition, these rules are not explicit for the expert. In this paper, we develop a method which generates Mamdani FIS, where the rules output is fuzzy. The method proceeds in two steps: first, it uses the subtractive clustering principle to estimate both the number of clusters and the initial locations of a cluster centers. Each obtained cluster corresponds to a Mamdani fuzzy rule. Then, it optimizes the fuzzy model parameters by applying a genetic algorithm. This method is illustrated on a traffic network management application. We suggest also a Mamdani fuzzy rules generation method, where the expert wants to classify the output variables in some fuzzy predefined classes.
Abstract: The special constraints of sensor networks impose a
number of technical challenges for employing them. In this review,
we study the issues and existing protocols in three areas: coverage
and routing. We present two types of coverage problems: to
determine the minimum number of sensor nodes that need to perform
active sensing in order to monitor a certain area; and to decide the
quality of service that can be provided by a given sensor network.
While most routing protocols in sensor networks are data-centric,
there are other types of routing protocols as well, such as
hierarchical, location-based, and QoS-aware. We describe and
compare several protocols in each group. We present several multipath
routing protocols and single-path with local repair routing
protocols, which are proposed for recovering from sensor node
crashes. We also discuss some transport layer schemes for reliable
data transmission in lossy wireless channels.
Abstract: This paper presents parametric probability density
models for call holding times (CHTs) into emergency call center
based on the actual data collected for over a week in the public
Emergency Information Network (EIN) in Mongolia. When the set of
chosen candidates of Gamma distribution family is fitted to the call
holding time data, it is observed that the whole area in the CHT
empirical histogram is underestimated due to spikes of higher
probability and long tails of lower probability in the histogram.
Therefore, we provide the Gaussian parametric model of a mixture of
lognormal distributions with explicit analytical expressions for the
modeling of CHTs of PSNs. Finally, we show that the CHTs for
PSNs are fitted reasonably by a mixture of lognormal distributions
via the simulation of expectation maximization algorithm. This result
is significant as it expresses a useful mathematical tool in an explicit
manner of a mixture of lognormal distributions.
Abstract: Study of soil properties like field capacity (F.C.) and permanent wilting point (P.W.P.) play important roles in study of soil moisture retention curve. Although these parameters can be measured directly, their measurement is difficult and expensive. Pedotransfer functions (PTFs) provide an alternative by estimating soil parameters from more readily available soil data. In this investigation, 70 soil samples were collected from different horizons of 15 soil profiles located in the Ziaran region, Qazvin province, Iran. The data set was divided into two subsets for calibration (80%) and testing (20%) of the models and their normality were tested by Kolmogorov-Smirnov method. Both multivariate regression and artificial neural network (ANN) techniques were employed to develop the appropriate PTFs for predicting soil parameters using easily measurable characteristics of clay, silt, O.C, S.P, B.D and CaCO3. The performance of the multivariate regression and ANN models was evaluated using an independent test data set. In order to evaluate the models, root mean square error (RMSE) and R2 were used. The comparison of RSME for two mentioned models showed that the ANN model gives better estimates of F.C and P.W.P than the multivariate regression model. The value of RMSE and R2 derived by ANN model for F.C and P.W.P were (2.35, 0.77) and (2.83, 0.72), respectively. The corresponding values for multivariate regression model were (4.46, 0.68) and (5.21, 0.64), respectively. Results showed that ANN with five neurons in hidden layer had better performance in predicting soil properties than multivariate regression.
Abstract: The rapid advance of communication technology is
evolving the network environment into the broadband convergence
network. Likewise, the IT services operated in the individual network
are also being quickly converged in the broadband convergence
network environment. VoIP and IPTV are two examples of such new
services. Efforts are being made to develop the video phone service,
which is an advanced form of the voice-oriented VoIP service.
However, the new IT services will be subject to stability and reliability
vulnerabilities if the relevant security issues are not answered during
the convergence of the existing IT services currently being operated in
individual networks within the wider broadband network
environment. To resolve such problems, this paper attempts to analyze
the possible threats and identify the necessary security measures
before the deployment of the new IT services. Furthermore, it
measures the quality of the encryption algorithm application example
to describe the appropriate algorithm in order to present security
technology that will have no negative impact on the quality of the
video phone service.
Abstract: Many firms implemented various initiatives such as outsourced manufacturing which could make a supply chain (SC) more vulnerable to various types of disruptions. So managing risk has become a critical component of SC management. Different types of SC vulnerability management methodologies have been proposed for managing SC risk, most offer only point-based solutions that deal with a limited set of risks. This research aims to reinforce SC risk management by proposing an integrated approach. SC risks are identified and a risk index classification structure is created. Then we develop a SC risk assessment approach based on the analytic network process (ANP) and the VIKOR methods under the fuzzy environment where the vagueness and subjectivity are handled with linguistic terms parameterized by triangular fuzzy numbers. By using FANP, risks weights are calculated and then inserted to the FVIKOR to rank the SC members and find the most risky partner.
Abstract: Recommender systems are usually regarded as an
important marketing tool in the e-commerce. They use important
information about users to facilitate accurate recommendation. The
information includes user context such as location, time and interest
for personalization of mobile users. We can easily collect information
about location and time because mobile devices communicate with the
base station of the service provider. However, information about user
interest can-t be easily collected because user interest can not be
captured automatically without user-s approval process. User interest
usually represented as a need. In this study, we classify needs into two
types according to prior research. This study investigates the
usefulness of data mining techniques for classifying user need type for
recommendation systems. We employ several data mining techniques
including artificial neural networks, decision trees, case-based
reasoning, and multivariate discriminant analysis. Experimental
results show that CHAID algorithm outperforms other models for
classifying user need type. This study performs McNemar test to
examine the statistical significance of the differences of classification
results. The results of McNemar test also show that CHAID performs
better than the other models with statistical significance.