This research aims to analyze and simulate biochemical real test data for uncovering the relationships among the tests, and how each of them impacts others. The data were acquired from Iraqi private biochemical laboratory. However, these data have many dimensions with a high rate of null values, and big patient numbers. Then, several experiments have been applied on these data beginning with unsupervised techniques such as hierarchical clustering, and k-means, but the results were not clear. Then the preprocessing step performed, to make the dataset analyzable by supervised techniques such as Linear Discriminant Analysis (LDA), Classification And Regression Tree (CART), Logistic Regression (LR), K-Nearest Neighbor (K-NN), Naïve Bays (NB

The using of the parametric models and the subsequent estimation methods require the presence of many of the primary conditions to be met by those models to represent the population under study adequately, these prompting researchers to search for more flexible parametric models and these models were nonparametric, many researchers, are interested in the study of the function of permanence and its estimation methods, one of these non-parametric methods.

For work of purpose statistical inference parameters around the statistical distribution for life times which censored data , on the experimental section of this thesis has been the comparison of non-parametric methods of permanence function, the existence

This research presents a model for surveying networks configuration which is designed and called a Computerized Integrated System for Triangulation Network Modeling (CISTNM). It focuses on the strength of figure as a concept then on estimating the relative error (RE) for the computed side (base line) triangulation element. The CISTNM can compute the maximum elevations of the highest
obstacles of the line of sight, the observational signal tower height, the contribution of each triangulation station with their intervisibility test and analysis. The model is characterized by the flexibility to select either a single figure or a combined figures network option. Each option includes three other implicit options such as: triangles, quadri

In this research the performance of 5G mobile system is evaluated through the Ergodic capacity metric. Today, in an­­y wireless communication system, many parameters have a significant role on system performance. Three main parameters are of concern here; the source power, number of antennas, and transmitter-receiver distance. User equipment’s (UEs) with equal and non-equal powers are used to evaluate the system performance in addition to using different antenna techniques to demonstrate the differences between SISO, MIMO, and massive MIMO. Using two mobile stations (MS) with different distances from the base station (BS), resulted in showing how using massive MIMO system will improve the performance than the standar

This paper reports an evaluation of the properties of medium-quality concrete incorporating recycled coarse aggregate (RCA). Concrete specimens were prepared with various percentages of the RCA (25%, 50%, 75%, and 100%). The workability, mechanical properties, and durability in terms of abrasion of cured concrete were examined at different ages. The results reveal insignificant differences between the recycled concrete (RC) and reference concrete in terms of the mechanical and durability-related measurements. Meanwhile, the workability of the RC reduced vastly since the replacement of the RCA reached 75% and 100%. The ultrasound pulse velocity (UPV) results greatly depend on the porosity of concrete and the RC exhibited higher poros

Building a system to identify individuals through their speech recording can find its application in diverse areas, such as telephone shopping, voice mail and security control. However, building such systems is a tricky task because of the vast range of differences in the human voice. Thus, selecting strong features becomes very crucial for the recognition system. Therefore, a speaker recognition system based on new spin-image descriptors (SISR) is proposed in this paper. In the proposed system, circular windows (spins) are extracted from the frequency domain of the spectrogram image of the sound, and then a run length matrix is built for each spin, to work as a base for feature extraction tasks. Five different descriptors are generated fro

A niger, a fungus which doesn't have high ability to production lipid, this fungus has been select to investigate the non oleaginicity. In this search, there are explorations about: i) growth profile ii) enzymes profile iii) isoforms. Growth profile shows that this fungus doesn't have ability to accumulate lipid more than 6% while bio mass are around 10g/l in spite of the presence of glucose in the media till the end of cultivation time and excision of nitrogen within 24 hrs. In enzyme study, we investigate all lipogenic enzymes Malic enzyme (ME), Fatty acid synthase (FAS), ATP: Citrate lays (ACL), NAD+ isocitrate dehydrogenase (NAD+ICDH), Glucose-6-phosphate (G6PD), and 6-phosphogluconate dehydrogenase (6PGD), all these enzymes show, ac

Monaural source separation is a challenging issue due to the fact that there is only a single channel available; however, there is an unlimited range of possible solutions. In this paper, a monaural source separation model based hybrid deep learning model, which consists of convolution neural network (CNN), dense neural network (DNN) and recurrent neural network (RNN), will be presented. A trial and error method will be used to optimize the number of layers in the proposed model. Moreover, the effects of the learning rate, optimization algorithms, and the number of epochs on the separation performance will be explored. Our model was evaluated using the MIR-1K dataset for singing voice separation. Moreover, the proposed approach achi

Visual analytics becomes an important approach for discovering patterns in big data. As visualization struggles from high dimensionality of data, issues like concept hierarchy on each dimension add more difficulty and make visualization a prohibitive task. Data cube offers multi-perspective aggregated views of large data sets and has important applications in business and many other areas. It has high dimensionality, concept hierarchy, vast number of cells, and comes with special exploration operations such as roll-up, drill-down, slicing and dicing. All these issues make data cubes very difficult to visually explore. Most existing approaches visualize a data cube in 2D space and require preprocessing steps. In this paper, we propose a visu