Volume 16, Issue 2, Summer and Autumn 2019


Estimation of Bayes Robustness for the Reliability Function for the Distribution Weibull Truncated with Application to Gastric Ulcer b Patients

Ban Alani; Dhwyiai salman; Raya Al-Rassam

IRAQI JOURNAL OF STATISTICAL SCIENCES, 2019, Volume 16, Issue 2, Pages 1-10
DOI: 10.33899/iqjoss.2019.164188

In this paper,the reliability function was estimation by the robust bayes approach using the initial distribution of the parameter 𝜃 with class (ML-II-𝜀-contaminated) when the shape parameter β is known and under the quadratic loss function for the duration of gastric ulcer patients since diagnosis and treatment until recovery and hospital discharge or death. The time of patient's admission to diagnosis and treatment was truncated. It was found that the data follow the two-parameter Weibul distribution (𝜃,β) where the prior 
distribution of the scale parameter was two-parameter Fréchet distribution (α0=1,𝜎0) according to prior information from previous years about the length of hospital stay and the opinions doctors and specialists.

Comparison Between The Method of Principal Component Analysis And Principal Component Analysis Kernel For Imaging Dimensionality Reduction

Assel Muslim Essa; Asmaa Ghalib Alrawi

IRAQI JOURNAL OF STATISTICAL SCIENCES, 2019, Volume 16, Issue 2, Pages 11-24
DOI: 10.33899/iqjoss.2019.164189

This paper tackles with two methods to dimensionality reduction, namely principal component analysis (PCA )    in the case of linear combinations and kernel principal component  analysis method  in the case of nonlinear combinations to digital image processing and analysis for useful information .And then compare the two methods and know which methods are appropriate to imaging dimensionality reduction 
The methods were applied to a group of satellite images of an area in the province of Basra, which represents the mouth of the Tigris and
          Euphrates in the Shatt al-Arab, as well as the water channels permeating Basra Governorate and the water bodies scattered around these channels.In this research, it is shown that the fourth image band is best when using the PCA method the value of it is eigen value was the biggest ,while the KPCA method showed that the third image band was the best, giving the highest latent value. Comparing the two methods using the mean error error (MSE) method, the results showed that the main KPCA method was the best.

Using the Hybrid MLR-GA Approach for Air Pollution Forecasting

Fanar Abdul Razaq Mohammed; Osama Basheer Hannon

IRAQI JOURNAL OF STATISTICAL SCIENCES, 2019, Volume 16, Issue 2, Pages 25-36
DOI: 10.33899/iqjoss.2019.164190

Air Quality Modeling gained great importance in atmospheric pollution because of its negative effects on the environment and human health. In our study, the relationship between (Particulate Matter PM10) and other nine variables over three years is studied to applied the multiple linear regression models. The seasonal influences for seasonally periods lead to difficult analyzing and forecasting. Therefore, Time-stratified (TS) approach is used into seasonally. The multiple linear regression 
(MLR) model is the most common for studying like this number of variables. Genetic algorithm (GA) as well as their hybrid method such as MLR–GA, is proposed to reduce the number of studied variables. Reducing the number of variables may also lead to more accurate results. The genetic algorithm has improved the performance of MLR method separately. GA also improved MLR performance by using hybrid method MLR-GA.

Using the Hybrid MLR-RNN Approach for Air Pollution Forecasting

Osama Basheer Hannon; Mariam Moneeb

IRAQI JOURNAL OF STATISTICAL SCIENCES, 2019, Volume 16, Issue 2, Pages 37-46
DOI: 10.33899/iqjoss.2019.164191

Air Quality Modeling gained great importance in atmospheric pollution because of its negative effects on the environment and human health. In our study, the relationship between (Particulate Matter PM10) and other nine variables over three years is studied to applied the multiple linear regression models (MLR). The MLR model is the most common for studying like this multivariate case. The main problem for this type of data is the non linear style that has been referred by many researchers before. The recurrent neural network (RNN) is nonlinear method  which can be used to solve the nonlinearity problem and resul better forecasting. The hybrid method MLR–RNN can be used also for the best results and lead to more accurate forecasting. The hybrid method MLR–RNN has improved the performance of MLR method separately

Design a knowledge base system (KBOSR) for enhancing software reusability

Ali Zein Alabedeen; Safwan Omar

IRAQI JOURNAL OF STATISTICAL SCIENCES, 2019, Volume 16, Issue 2, Pages 47-60
DOI: 10.33899/iqjoss.2019.164192

As a result of the development of software engineering , especially with regard to improving the software systems within a short time to enhance the development process and reduce cost as much as possible . Software reusability is one of the most important software engineering metrics which aim to reduce the effort and time in the development process . It is the process of using pre-existing software components for implementing and updating new software systems , thereby reducing effort , time and cost in addition to increasing the quality and productivity of software systems . Many factors affect the reusability of a software , of these factors , coupling and cohesion are used in this search for the aforementioned purpose .
Reusability of classes is determined based on coupling and cohesion results . Cohesion measures the intra-dependability of functions and variables inside the class , while coupling measures the inter-dependability among classes in the same package . The proposed expert system also used for computing coupling , cohesion and reusability status , and produce suggestions to enhance the reusability status of unreusable classes by offering intelligence advices which depending on the weakness of the tested codes .
Proposed knowledge Base System (KBOSR) contains (61) rules to provide and demonstrate why the items are not reusable by displaying code weaknesses , and to provide advice, guidance and modifications to the code for making the product reusable and displaying these guidelines  and instructions on user interfaces in a clear and easy-to-understand way, KBOSR is the first knowledge base system to determine the status of reuse and improve it .
          The knowledge base  was tested using 13 classes were distributed in two packages , first package contains 5 classes , second package contains 8 classes , coupling and cohesion values of classes are computed . Coupling , cohesion and reusability status of these classes are determined , then , by proposed expert system . Finally , suggestions of improvement of unresable classes are displayed . The results of testing process have proved the strength and validity of the proposed knowledge base in determining reusability status of the software components , and the accuracy of the advices that were suggested , these advices are practically applied on the codes of interest and the modified codes proved to be highly reusable .

Employ spiral model analysis and design tool to optimize software written in Java

Rahma Salem Alsawaf; Asmaa Yasin Hamoo

IRAQI JOURNAL OF STATISTICAL SCIENCES, 2019, Volume 16, Issue 2, Pages 61-72
DOI: 10.33899/iqjoss.2019.164193

The spiral model is one of the models used in software development. This model was used in the analysis, design and construction of the tool (JCOT), where the tool replaces some of the sentences written in JAVA in other sentences that match the work but at the time of implementation less. The tool also displays the shortness of the time in a longitudinal and chromatic strip for ease of user recognition. The spiral model proved its effectiveness. Each case of optimization was treated as a link and then the other state was transferred to the end of the tool. This enabled the researcher to easily add new cases of the tool (JCOT).

A Review of Object-Oriented Programming Software Metrics

Mariam Hussian; Mohammed Aldabbag

IRAQI JOURNAL OF STATISTICAL SCIENCES, 2019, Volume 16, Issue 2, Pages 73-90
DOI: 10.33899/iqjoss.2019.164194

It is no secret that the software industry in the present and future time is the leading industry and the main element in any new technology and is involved in most modern industries, from the smallest ones such as mobile phones and smart watches to the largest ones such as airplanes, space stations and nuclear reactors, and the relation of this software to preserving human life or saving in sometimes It was important to make sure that it was quality and error-free. For this reason was must be to develop metrics to measure this software. This research will provide a comprehensive review of most of the standards used in software quality measurement and emphasis on software
design and implementation because it is now the leader in the software industry. This study serves as a reference for software engineering students interested in software standards.

A Review of Block Cipher’s S-Boxes Tests Criteria

Auday H. Saeed AL-Wattar

IRAQI JOURNAL OF STATISTICAL SCIENCES, 2019, Volume 16, Issue 2, Pages 91-104
DOI: 10.33899/iqjoss.2019.164195

The Symmetric Block cipher is a considerable encryption algorithm because of its straightforwardness, rapidity and strength and this cryptographic algorithm is employed in carrying out the encryption and decryption for most current security applications. The confusion properties are attained using the substitution-Box (S-Box). Substitution and permutation functions are normally used in block ciphers to make them much firmer and more effectual ciphers. The Security of S-Box is checked using S-Box test criteria and the randomness test. The objective of this paper is to give the researchers a specific knowledge (standards) for testing the ciphers’ S-Boxes.  This paper includes survey or guide for the S-box test criteria.