IRAQI JOURNAL OF STATISTICAL SCIENCES

This study deals with the famous trackers named Kalman and extended Kalman filters. This is introduced by describing the state space representation approach to model the target system. A modification to the state prediction equation of Kalman and extended Kalman filters is given in order to offer an ability of multi-step ahead prediction of the target future position. The problem of missed measurements, with different percentages of missing, is studied and a method to estimate these missed measurements is then suggested. Some simulation experiments are performed and indicated that Kalman filtering techniques are promising when they deal with target tracking problem.

We present in this paper Bays method by using Jeffery prior information and new Bayesian using extension of Jeffery prior information for estimating the parameter of exponential distribution and survival function . It has been shown from the computational results that the method which gives the best estimates is an extension of Jeffery prior information .

The importance of Transfer Function Model comes from its use in prediction . The model has been constructed with multi-inputs because of the importance of multi-input in contructing models. Such multi-inputs give better results because the more effective inputs are used , the more precise are the results.In order to get the best prediction , the study studies the construction of transfer function model by black box models.


This method consists of constructing many models for the basic models of the black box Model,namely (ARX, ARMAX, BJ, OE ). The model which gave the best result was the model "BJ" depending , for comparison , on a group of statistical and geometrical standards .

ABSTRACT
A comparative study between linear transfer models of low order and ARX model of high order depends on spatial series.
The research includes a comparison between efficiency of the different linear transfer function f stationary time – spatial series with low order models ( ARX11k , ARMAX2221 ,O.E221 , B.J22221 , pss1 ) and high order ARX model according to the percentage rate of coincidence of the model to the data . The comparison is made on a spatial – time series which shows the effect resulted on the biological factors of the soil as a consequence of changes in the chemical factors on one hand and physical factors on the other, and the two factors all are together as an input–output model ( multiple–uni ) in one time and (multiple–multiple) on another time . It appears that ARX models of high order has a high percentage fit compared with the transfer models of low order .

In This paper, we suggest two approaches for the parallel tangent (PARTAN) method. First is to combine PARTAN method with Perry algorithm and second is to combine PARTAN method with Al-Bayati-Ahmed, 1996 algorithm. The new suggested methods are tested to solve unconstrained optimization problems by using statistical tests and the results of the new suggested methods are better than the original PARTAN method with respect to time and the accuracy.

The study of time series is one of first important subjects especially with study of analysis behavior of different phenomenon’s and discussed it throw the historical in different period to forecasting.
The initial aims of statistical sciences to know the behavior of feature search, we found each day throw the media the care of different economic and wether forecasting. The aim of this search to compare Adaptive Filtering and Artificial Neural Networks to forecasting of time series models.

In this paper, we shall try to determine outliers and pinpoint its source of existence by using Box-Whisker plots technique which is an effective approach to detect and treat outliers. Thus the researchers prove that the Box-Whisker-Plot is the most effective method among other methods used in this research which is the hypothesis of the paper.

This study deals with hidden Markov models . These models consist of sets of finite states , each one of them is associated with a probability distribution . The transition among the states is governed by a set of probabilities namely “ Transition probabilities ” . In general , the final observation produced according to the associated probability , where there is only probability production instead of a clear visible states . Therefore , these states are described as hidden
The basic problems for hidden Markov models (HMMs) are :

- The probability account for the observation sequence (O) when the model is given = (A , B , ) , i.e. P(O|) Where :
A = The state transition probabilities .
B = The observation probability matrix .
The initial state distribution .
- Choosing the optimal state of the sequence for hidden Markov process.
- Finding the model  = (A , B , ) which has the greatest probability , i.e. re-estimating the model to maximiz P(O|) .
in addition to its results .

The idea of this project is based on programming the functions of DirectX, which will connect the last one with the windows, this work is needed because DirectX deals with the hardware and the buffers of the memory while the windows does not directly deal with it.
The work focuses on programming the DirectPlay function, which is considered as an interface programming to guarantee the arrival of the applications to the communication services.
DirectPlay supports the facilities of connecting the game with the internet directly by the Modem Link or indirectly by the Ethernet. Actually the game becomes more flexible and enjoying if it is played against a real player (or another user of the computer) instead of playing with the computer itself. Also DirectPlay supports a group of users connected with each other in an active way at the same time (for example, the Internet chatting or Ethernet chatting).
In this work, an Ethernet chatting is done by using a Client/Server applications to see the working of DirectPlay, then, we try to use an active and strong language to make this is possible, and therefor we use the Visual C++ language.

This paper studies a time series for the number of infection of Tuberculosis of the lungs as a Markov – chain. We have made hypotheses concerning the number of infections in order to set the problem according to Markov-chain. Then I’ll try to find the characteristic of this chain that proved to be non-ergodic. I found the absorbing probability for the transient state and the expected absorbing time.

In this paper, a simulation has been done for the radial basis model of sunspot time series . Chaotic analysis of the simulated data from model, and the study of the chaotic behavior for such a model indicates that the model is chaotic and the sunspot time series is chaos .

The secret Electronic Mail messages encounter many problems that causes hacking or modifies it, therefore is necessary to find active ways, to keep it out of hackers and intruders, hiding technique was applied to satisfying that.
The Traditional ways depend on hiding secret message data in between words or statements of carrier message, after dividing its characters values in to sequence of bits, was leaving one or two spaces depending on hided bit value (0 or 1).
In this research, a new concept was applied to create only one space in this two cases, this method carried out higher performance than traditional methods, there is no perceptual hiding for hackers and intruders, and satisfied full matching in figure and size of carrier message before and after hiding.

In this research, we compared restricted least squares with restricted Liu estimator . by using (MSE) criterion in the existence of multicollinearity. We found that restricted Liu estimator is the best in comparison.