Abstract: Generative Adversarial Net (GAN) has proved to be a powerful machine learning tool in image data analysis and generation. In this paper, we propose to use Conditional Generative Adversarial Net (CGAN) to learn and simulate time series data. The conditions include both categorical and continuous variables with different auxiliary information. Our simulation studies show that CGAN has the capability to learn different types of normal and heavy-tailed distributions, as well as dependent structures of different time series. It also has the capability to generate conditional predictive distributions consistent with training data distributions. We also provide an in-depth discussion on the rationale behind GAN and the neural networks as hierarchical splines to establish a clear connection with existing statistical methods of distribution generation. In practice, CGAN has a wide range of applications in market risk and counterparty risk analysis: it can be applied to learn historical data and generate scenarios for the calculation of Value-at-Risk (VaR) and Expected Shortfall (ES), and it can also predict the movement of the market risk factors. We present a real data analysis including a backtesting to demonstrate that CGAN can outperform Historical Simulation (HS), a popular method in market risk analysis to calculate VaR. CGAN can also be applied in economic time series modeling and forecasting. In this regard, we have included an example of hypothetical shock analysis for economic models and the generation of potential CCAR scenarios by CGAN at the end of the paper.
Abstract: High lamination in microchannel is one of the main challenges in on-chip components like micro total analyzer systems and lab-on-a-chips. Electro-osmotic force is highly effective in chip-scale. This research proposes a microfluidic-based micropump for low ionic strength solutions. Narrow microchannels are designed to generate an efficient electroosmotic flow near the walls. Microelectrodes are embedded in the lateral sides and actuated by low electric potential to generate pumping effect inside the channel. Based on the simulation study, the fluid velocity increases by increasing the electric potential amplitude. We achieve a net flow velocity of 100 µm/s, by applying +/- 2 V to the electrode structures. Our proposed low voltage design is of interest in conventional lab-on-a-chip applications.
Abstract: Banda Sea Collision Zone (BSCZ) is the result of the
interaction and convergence of Indo-Australian plate, Eurasian plate
and Pacific plate. This location is located in eastern Indonesia. This
zone has a very high seismic activity. In this research, we will
calculate the rate (λ) and Mean Square Error (MSE). By this result,
we will classification earthquakes distribution in the BSCZ with the
point process approach. Chi-square is used to determine the type of
earthquakes distribution in the sub region of BSCZ. The data used in
this research is data of earthquakes with a magnitude ≥ 6 SR for the
period 1964-2013 and sourced from BMKG Jakarta. This research is
expected to contribute to the Moluccas Province and surrounding
local governments in performing spatial plan document related to
disaster management.
Abstract: In this talk, we introduce a newly developed quantile
function model that can be used for estimating conditional
distributions of financial returns and for obtaining multi-step ahead
out-of-sample predictive distributions of financial returns. Since we
forecast the whole conditional distributions, any predictive quantity
of interest about the future financial returns can be obtained simply
as a by-product of the method. We also show an application of the
model to the daily closing prices of Dow Jones Industrial Average
(DJIA) series over the period from 2 January 2004 - 8 October 2010.
We obtained the predictive distributions up to 15 days ahead for
the DJIA returns, which were further compared with the actually
observed returns and those predicted from an AR-GARCH model.
The results show that the new model can capture the main features
of financial returns and provide a better fitted model together with
improved mean forecasts compared with conventional methods. We
hope this talk will help audience to see that this new model has the
potential to be very useful in practice.
Abstract: In this paper we make a temperature investigations in
two type of superposed crimped connections using experimental
determinations. All the samples use 8 copper wire 7.1 x 3 mm2
crimped by two methods: the first method uses one crimp indents and
the second is a proposed method with two crimp indents. The ferrule
is a parallel one. We study the influence of number and position of
crimp indents. The samples are heated in A.C. current at different
current values until steady state heating regime. After obtaining of
temperature values, we compare them and present the conclusion.
Abstract: This paper presents a regression model with
autocorrelated errors in which the inputs are social moods obtained by
analyzing the adjectives in Twitter posts using a document topic
model, where document topics are extracted using LDA. The
regression model predicts Dow Jones Industrial Average (DJIA) more
precisely than autoregressive moving-average models.
Abstract: In this paper the core objective is to apply discrete wavelet transform and maximal overlap discrete wavelet transform functions namely Haar, Daubechies2, Symmlet4, Coiflet2 and discrete approximation of the Meyer wavelets in non stationary financial time series data from Dow Jones index (DJIA30) of US stock market. The data consists of 2048 daily data of closing index from December 17, 2004 to October 23, 2012. Unit root test affirms that the data is non stationary in the level. A comparison between the results to transform non stationary data to stationary data using aforesaid transforms is given which clearly shows that the decomposition stock market index by discrete wavelet transform is better than maximal overlap discrete wavelet transform for original data.
Abstract: The national economy development affects the vehicle
ownership which ultimately increases fuel consumption. The rise of
the vehicle ownership is dominated by the increasing number of
motorcycles. This research aims to analyze and identify the
characteristics of fuel consumption, the city transportation system,
and to analyze the relationship and the effect of the city
transportation system on the fuel consumption. A multivariable
analysis is used in this study. The data analysis techniques include: a
Multivariate Multivariable Analysis by using the R software. More
than 84% of fuel on Java is consumed in metropolitan and large
cities. The city transportation system variables that strongly effect the
fuel consumption are population, public vehicles, private vehicles and
private bus. This method can be developed to control the fuel
consumption by considering the urban transport system and city
tipology. The effect can reducing subsidy on the fuel consumption,
increasing state economic.
Abstract: This paper presents a microstrip meandered open
circuited stub with bandstop characteristic. The proposed structure is
designed on a high frequency laminate with dielectric constant of 4.0
and board thickness of 0.508 millimeters. The scattering parameters
and electromagnetic field distributions at various frequencies are
investigated by modeling the structure with three dimensional
electromagnetic simulation tool. In order to describe the resonant
and bandstop characteristic of the meandered open circuited stub, a
Smith chart as well as electric field at various frequencies and phases
is illustrated accordingly. The structure can be an alternative method
in suppressing the harmonic response of a bandpass filter.
Abstract: This study presents a mathematical modeling approach to the planning of HIV therapies on an individual basis. The model replicates clinical data from typical-progressors to AIDS for all stages of the disease with good agreement. Clinical data from rapid-progressors and long-term non-progressors is also matched by estimation of immune system parameters only. The ability of the model to reproduce these phenomena validates the formulation, a fact which is exploited in the investigation of effective therapies. The therapy investigation suggests that, unlike continuous therapy, structured treatment interruptions (STIs) are able to control the increase in both the drug-sensitive and drug-resistant virus population and, hence, prevent the ultimate progression from HIV to AIDS. The optimization results further suggest that even patients characterised by the same progression type can respond very differently to the same treatment and that the latter should be designed on a case-by-case basis. Such a methodology is presented here.