Abstract: The purpose of this paper is to present two different
approaches of financial distress pre-warning models appropriate for
risk supervisors, investors and policy makers. We examine a sample
of the financial institutions and electronic companies of Taiwan
Security Exchange (TSE) market from 2002 through 2008. We
present a binary logistic regression with paned data analysis. With
the pooled binary logistic regression we build a model including
more variables in the regression than with random effects, while the
in-sample and out-sample forecasting performance is higher in
random effects estimation than in pooled regression. On the other
hand we estimate an Adaptive Neuro-Fuzzy Inference System
(ANFIS) with Gaussian and Generalized Bell (Gbell) functions and
we find that ANFIS outperforms significant Logit regressions in both
in-sample and out-of-sample periods, indicating that ANFIS is a
more appropriate tool for financial risk managers and for the
economic policy makers in central banks and national statistical
services.
Abstract: In this paper variation of spot price and total profits of
the generating companies- through wholesale electricity trading are
discussed with and without Central Generating Stations (CGS) share
and seasonal variations are also considered. It demonstrates how
proper analysis of generators- efficiencies and capabilities, types of
generators owned, fuel costs, transmission losses and settling price
variation using the solutions of Optimal Power Flow (OPF), can
allow companies to maximize overall revenue. It illustrates how
solutions of OPF can be used to maximize companies- revenue under
different scenarios. And is also extended to computation of Available
Transfer Capability (ATC) is very important to the transmission
system security and market forecasting. From these results it is
observed that how crucial it is for companies to plan their daily
operations and is certainly useful in an online environment of
deregulated power system. In this paper above tasks are demonstrated
on 124 bus real-life Indian utility power system of Andhra Pradesh
State Grid and results have been presented and analyzed.
Abstract: This paper explores the effectiveness of machine
learning techniques in detecting firms that issue fraudulent financial
statements (FFS) and deals with the identification of factors
associated to FFS. To this end, a number of experiments have been
conducted using representative learning algorithms, which were
trained using a data set of 164 fraud and non-fraud Greek firms in the
recent period 2001-2002. The decision of which particular method to
choose is a complicated problem. A good alternative to choosing
only one method is to create a hybrid forecasting system
incorporating a number of possible solution methods as components
(an ensemble of classifiers). For this purpose, we have implemented
a hybrid decision support system that combines the representative
algorithms using a stacking variant methodology and achieves better
performance than any examined simple and ensemble method. To
sum up, this study indicates that the investigation of financial
information can be used in the identification of FFS and underline the
importance of financial ratios.
Abstract: Photovoltaic power generation forecasting is an
important task in renewable energy power system planning and
operating. This paper explores the application of neural networks
(NN) to study the design of photovoltaic power generation
forecasting systems for one week ahead using weather databases
include the global irradiance, and temperature of Ghardaia city
(south of Algeria) using a data acquisition system. Simulations were
run and the results are discussed showing that neural networks
Technique is capable to decrease the photovoltaic power generation
forecasting error.
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: The coverage probability and range of IEEE 802.16
systems depend on different wireless scenarios. Evaluating the
performance of IEEE 802.16 systems over Stanford University
Interim (SUI) channels is suggested by IEEE 802.16 specifications.
In order to derive an effective method for forecasting the coverage
probability and range, this study uses the SUI channel model to
analyze the coverage probability with Rayleigh fading for an IEEE
802.16 system. The BER of the IEEE 802.16 system is shown in the
simulation results. Then, the maximum allowed path loss can be
calculated and substituted into the coverage analysis. Therefore,
simulation results show the coverage range with and without
Rayleigh fading.
Abstract: Model Predictive Control has been previously applied
to supply chain problems with promising results; however hitherto
proposed systems possessed no information on future demand. A
forecasting methodology will surely promote the efficiency of
control actions by providing insight on the future. A complete supply
chain management framework that is based on Model Predictive
Control (MPC) and Time Series Forecasting will be presented in this
paper. The proposed framework will be tested on industrial data in
order to assess the efficiency of the method and the impact of
forecast accuracy on overall control performance of the supply chain.
To this end, forecasting methodologies with different characteristics
will be implemented on test data to generate forecasts that will serve
as input to the Model Predictive Control module.
Abstract: The statistical process control (SPC) is one of the most powerful tools developed to assist ineffective control of quality, involves collecting, organizing and interpreting data during production. This article aims to show how the use of CEP industries can control and continuously improve product quality through monitoring of production that can detect deviations of parameters representing the process by reducing the amount of off-specification products and thus the costs of production. This study aimed to conduct a technological forecasting in order to characterize the research being done related to the CEP. The survey was conducted in the databases Spacenet, WIPO and the National Institute of Industrial Property (INPI). Among the largest are the United States depositors and deposits via PCT, the classification section that was presented in greater abundance to F.
Abstract: Prior research has not effectively investigated how the
profitability of Chinese branches affect FDIs in China [1, 2], so this
study for the first time incorporates realistic earnings information
to systematically investigate effects of innovation, imitation, and
profit factors of FDI diffusions from Taiwan to China. Our nonlinear
least square (NLS) model, which incorporates earnings factors,
forms a nonlinear ordinary differential equation (ODE) in numerical
simulation programs. The model parameters are obtained through
a genetic algorithms (GA) technique and then optimized with the
collected data for the best accuracy. Particularly, Taiwanese regulatory
FDI restrictions are also considered in our modified model to meet
the realistic conditions. To validate the model-s effectiveness, this
investigation compares the prediction accuracy of modified model
with the conventional diffusion model, which does not take account
of the profitability factors.
The results clearly demonstrate the internal influence to be positive,
as early FDI adopters- consistent praises of FDI attract potential firms
to make the same move. The former erects a behavior model for the
latter to imitate their foreign investment decision. Particularly, the
results of modified diffusion models show that the earnings from
Chinese branches are positively related to the internal influence. In
general, the imitating tendency of potential consumers is substantially
hindered by the losses in the Chinese branches, and these firms would
invest less into China. The FDI inflow extension depends on earnings
of Chinese branches, and companies will adjust their FDI strategies
based on the returns. Since this research has proved that earning is
an influential factor on FDI dynamics, our revised model explicitly
performs superior in prediction ability than conventional diffusion
model.
Abstract: Time series forecasting is an important and widely
popular topic in the research of system modeling. This paper
describes how to use the hybrid PSO-RLSE neuro-fuzzy learning
approach to the problem of time series forecasting. The PSO
algorithm is used to update the premise parameters of the
proposed prediction system, and the RLSE is used to update the
consequence parameters. Thanks to the hybrid learning (HL)
approach for the neuro-fuzzy system, the prediction performance
is excellent and the speed of learning convergence is much faster
than other compared approaches. In the experiments, we use the
well-known Mackey-Glass chaos time series. According to the
experimental results, the prediction performance and accuracy in
time series forecasting by the proposed approach is much better
than other compared approaches, as shown in Table IV. Excellent
prediction performance by the proposed approach has been
observed.
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: Training neural networks to capture an intrinsic
property of a large volume of high dimensional data is a difficult
task, as the training process is computationally expensive. Input
attributes should be carefully selected to keep the dimensionality of
input vectors relatively small.
Technical indexes commonly used for stock market prediction
using neural networks are investigated to determine its effectiveness
as inputs. The feed forward neural network of Levenberg-Marquardt
algorithm is applied to perform one step ahead forecasting of
NASDAQ and Dow stock prices.
Abstract: The Bangalore City is facing the acute problem of
pollution in the atmosphere due to the heavy increase in the traffic
and developmental activities in recent years. The present study is an
attempt in the direction to assess trend of the ambient air quality
status of three stations, viz., AMCO Batteries Factory, Mysore Road,
GRAPHITE INDIA FACTORY, KHB Industrial Area, Whitefield
and Ananda Rao Circle, Gandhinagar with respect to some of the
major criteria pollutants such as Total Suspended particular matter
(SPM), Oxides of nitrogen (NOx), and Oxides of sulphur (SO2). The
sites are representative of various kinds of growths viz., commercial,
residential and industrial, prevailing in Bangalore, which are
contributing to air pollution. The concentration of Sulphur Dioxide
(SO2) at all locations showed a falling trend due to use of refined
petrol and diesel in the recent years. The concentration of Oxides of
nitrogen (NOx) showed an increasing trend but was within the
permissible limits. The concentration of the Suspended particular
matter (SPM) showed the mixed trend. The correlation between
model and observed values is found to vary from 0.4 to 0.7 for SO2,
0.45 to 0.65 for NOx and 0.4 to 0.6 for SPM. About 80% of data is
observed to fall within the error band of ±50%. Forecast test for the
best fit models showed the same trend as actual values in most of the
cases. However, the deviation observed in few cases could be
attributed to change in quality of petro products, increase in the
volume of traffic, introduction of LPG as fuel in many types of
automobiles, poor condition of roads, prevailing meteorological
conditions, etc.
Abstract: The aim of this paper is to present a methodology in
three steps to forecast supply chain demand. In first step, various data
mining techniques are applied in order to prepare data for entering
into forecasting models. In second step, the modeling step, an
artificial neural network and support vector machine is presented
after defining Mean Absolute Percentage Error index for measuring
error. The structure of artificial neural network is selected based on
previous researchers' results and in this article the accuracy of
network is increased by using sensitivity analysis. The best forecast
for classical forecasting methods (Moving Average, Exponential
Smoothing, and Exponential Smoothing with Trend) is resulted based
on prepared data and this forecast is compared with result of support
vector machine and proposed artificial neural network. The results
show that artificial neural network can forecast more precisely in
comparison with other methods. Finally, forecasting methods'
stability is analyzed by using raw data and even the effectiveness of
clustering analysis is measured.
Abstract: This paper presents Faults Forecasting System (FFS)
that utilizes statistical forecasting techniques in analyzing process
variables data in order to forecast faults occurrences. FFS is
proposing new idea in detecting faults. Current techniques used in
faults detection are based on analyzing the current status of the
system variables in order to check if the current status is fault or not.
FFS is using forecasting techniques to predict future timing for faults
before it happens. Proposed model is applying subset modeling
strategy and Bayesian approach in order to decrease dimensionality
of the process variables and improve faults forecasting accuracy. A
practical experiment, designed and implemented in Okayama
University, Japan, is implemented, and the comparison shows that
our proposed model is showing high forecasting accuracy and
BEFORE-TIME.
Abstract: In this paper, the modelling and design of artificial neural network architecture for load forecasting purposes is investigated. The primary pre-requisite for power system planning is to arrive at realistic estimates of future demand of power, which is known as Load Forecasting. Short Term Load Forecasting (STLF) helps in determining the economic, reliable and secure operating strategies for power system. The dependence of load on several factors makes the load forecasting a very challenging job. An over estimation of the load may cause premature investment and unnecessary blocking of the capital where as under estimation of load may result in shortage of equipment and circuits. It is always better to plan the system for the load slightly higher than expected one so that no exigency may arise. In this paper, a load-forecasting model is proposed using a multilayer neural network with an appropriately modified back propagation learning algorithm. Once the neural network model is designed and trained, it can forecast the load of the power system 24 hours ahead on daily basis and can also forecast the cumulative load on daily basis. The real load data that is used for the Artificial Neural Network training was taken from LDC, Gujarat Electricity Board, Jambuva, Gujarat, India. The results show that the load forecasting of the ANN model follows the actual load pattern more accurately throughout the forecasted period.
Abstract: This research focus on developing a new segmentation method for improving forecasting model which is call trend based segmentation method (TBSM). Generally, the piece-wise linear representation (PLR) can finds some of pair of trading points is well for time series data, but in the complicated stock environment it is not well for stock forecasting because of the stock has more trends of trading. If we consider the trends of trading in stock price for the trading signal which it will improve the precision of forecasting model. Therefore, a TBSM with SVR model used to detect the trading points for various stocks of Taiwanese and America under different trend tendencies. The experimental results show our trading system is more profitable and can be implemented in real time of stock market
Abstract: Embedded systems need to respect stringent real
time constraints. Various hardware components included in such
systems such as cache memories exhibit variability and therefore
affect execution time. Indeed, a cache memory access from an
embedded microprocessor might result in a cache hit where the
data is available or a cache miss and the data need to be fetched
with an additional delay from an external memory. It is therefore
highly desirable to predict future memory accesses during
execution in order to appropriately prefetch data without incurring
delays. In this paper, we evaluate the potential of several artificial
neural networks for the prediction of instruction memory
addresses. Neural network have the potential to tackle the nonlinear
behavior observed in memory accesses during program
execution and their demonstrated numerous hardware
implementation emphasize this choice over traditional forecasting
techniques for their inclusion in embedded systems. However,
embedded applications execute millions of instructions and
therefore millions of addresses to be predicted. This very
challenging problem of neural network based prediction of large
time series is approached in this paper by evaluating various neural
network architectures based on the recurrent neural network
paradigm with pre-processing based on the Self Organizing Map
(SOM) classification technique.
Abstract: The mitigation of crop loss due to damaging freezes requires accurate air temperature prediction models. An improved model for temperature prediction in Georgia was developed by including information on seasonality and modifying parameters of an existing artificial neural network model. Alternative models were compared by instantiating and training multiple networks for each model. The inclusion of up to 24 hours of prior weather information and inputs reflecting the day of year were among improvements that reduced average four-hour prediction error by 0.18°C compared to the prior model. Results strongly suggest model developers should instantiate and train multiple networks with different initial weights to establish appropriate model parameters.
Abstract: Fast forecasting of stock market prices is very important for
strategic planning. In this paper, a new approach for fast forecasting of
stock market prices is presented. Such algorithm uses new high speed
time delay neural networks (HSTDNNs). The operation of these
networks relies on performing cross correlation in the frequency
domain between the input data and the input weights of neural
networks. It is proved mathematically and practically that the number
of computation steps required for the presented HSTDNNs is less
than that needed by traditional time delay neural networks
(TTDNNs). Simulation results using MATLAB confirm the
theoretical computations.