In data mining, classification is a form of data analysis that can be used to extract models describing important data classes. Two of the well known algorithms used in data mining classification are Backpropagation Neural Network (BNN) and Naïve Bayesian (NB). This paper investigates the performance of these two classification methods using the Car Evaluation dataset. Two models were built for both algorithms and the results were compared. Our experimental results indicated that the BNN classifier yield higher accuracy as compared to the NB classifier but it is less efficient because it is time-consuming and difficult to analyze due to its black-box implementation.
This research had been achieved to identify the image of the subsurface structure representing the Tertiary period in the Galabat Field northeast of Iraq using 2D seismic survey measurements. Synthetic seismograms of the Galabat-3 well were generated in order to identify and pick the reflectors in seismic sections. Structural Images were drawn in the time domain and then converted to the depth domain by using average velocities. Structurally, seismic sections illustrate these reflectors are affected by two reverse faults affected on the Jeribe Formation and the layers below with the increase in the density of the reverse faults in the northern division. The structural maps show Galabat field, which consists of longitudinal Asymmetrical narr
... Show MoreThis paper focus on study the variations of monthly tropospheric NO2 concentrations over three Iraqi cities Baghdad (33.3° N, 44.4° E), Basrah (30.56° N, 47.8° E) and Erbil (36.3° N, 44.06° E). Monthly NO2 retrievals from the Ozone Monitoring Instrument (OMI) onboard Aura satellite during the period from October 2004 to March 2013 have been used. The results show a high monthly and annual NO2 concentrations at Baghdad than Basra and Erbil may be attribute to high densely populations and a high economic activity. During the whole period, Baghdad, Basrah and Erbil were exhibited an average of NO2 (8.1±2.5), (3.7±1.3) and (3.3±1.7) in unit 1015 molecules
... Show MorePurpose: The research aims to estimate models representing phenomena that follow the logic of circular (angular) data, accounting for the 24-hour periodicity in measurement. Theoretical framework: The regression model is developed to account for the periodic nature of the circular scale, considering the periodicity in the dependent variable y, the explanatory variables x, or both. Design/methodology/approach: Two estimation methods were applied: a parametric model, represented by the Simple Circular Regression (SCR) model, and a nonparametric model, represented by the Nadaraya-Watson Circular Regression (NW) model. The analysis used real data from 50 patients at Al-Kindi Teaching Hospital in Baghdad. Findings: The Mean Circular Erro
... Show MoreWireless Body Area Sensor Network (WBASN) is gaining significant attention due to its applications in smart health offering cost-effective, efficient, ubiquitous, and unobtrusive telemedicine. WBASNs face challenges including interference, Quality of Service, transmit power, and resource constraints. Recognizing these challenges, this paper presents an energy and Quality of Service-aware routing algorithm. The proposed algorithm is based on each node's Collaboratively Evaluated Value (CEV) to select the most suitable cluster head (CH). The Collaborative Value (CV) is derived from three factors, the node's residual energy, the distance vector between nodes and personal device, and the sensor's density in each CH. The CEV algorithm operates i
... Show MoreDeep learning has recently received a lot of attention as a feasible solution to a variety of artificial intelligence difficulties. Convolutional neural networks (CNNs) outperform other deep learning architectures in the application of object identification and recognition when compared to other machine learning methods. Speech recognition, pattern analysis, and image identification, all benefit from deep neural networks. When performing image operations on noisy images, such as fog removal or low light enhancement, image processing methods such as filtering or image enhancement are required. The study shows the effect of using Multi-scale deep learning Context Aggregation Network CAN on Bilateral Filtering Approximation (BFA) for d
... Show MoreA total of 70 pregnant women with toxoplasmosis were studied to evaluate of some immunological aspects. The women were distributed into three groups: 37 women were IgG positive, 18 women were IgM positive and 15 women were IgG and IgM positive as well as 25 healthy women were considered as control group. Serum samples were collected and ELISA method was employed to assess levels of interleukins 4, 6, 10, Interferon gamma-induced protein 10 (IP-10), Granulocyte-macrophage colony-stimulating factor (GM-CSF) and Vascular endothelial growth factor (VEGF). As compared with control the levels of cytokines were significantly increased in serum of three pregnant women groups with toxoplasmosis and the highest increase was observed in the IgM positi
... Show MoreAbstract Background: Crown lengthening is a surgical procedure that apically positions the gingival edge and/or removes supporting bone in order to increase the amount of supra gingival tooth structure for restorative or cosmetic purposes.
The objective of the study: The purpose of this study was to evaluate the efficacy of the 940nm diode laser in esthetic crown lengthening surgery through clinical observations, patient questionnaires, clinical photographs, and gingival healing following gingival operations. Material and methods: In this randomized clinical trial, 16 patients (11 females and 5 males) had their crowns surgically lengthened using a diode laser (940 nm) in continuou
... Show More