Diabetes is one of the increasing chronic diseases, affecting millions of people around the earth. Diabetes diagnosis, its prediction, proper cure, and management are compulsory. Machine learning-based prediction techniques for diabetes data analysis can help in the early detection and prediction of the disease and its consequences such as hypo/hyperglycemia. In this paper, we explored the diabetes dataset collected from the medical records of one thousand Iraqi patients. We applied three classifiers, the multilayer perceptron, the KNN and the Random Forest. We involved two experiments: the first experiment used all 12 features of the dataset. The Random Forest outperforms others with 98.8% accuracy. The second experiment used only five attributes of the training process. The results of the second experiment showed improvement in the performance of the KNN and the Multilayer Perceptron. The results of the second experiment showed a slight decrease in the performance of the Random Forest with 97.5 % accuracy.
Different frequency distributions models were fitted to the monthly data of raw water Turbidity at water treatment plants (WTPs) along Tigris River in Baghdad. Eight water treatment plants in Baghdad were selected, with raw water turbidity data for the period (2008-2014). The frequency distribution models used in this study are the Normal, Log-normal, Weibull, Exponential and two parameters Gamma type. The Kolmogorov-Smirnov test was used to evaluate the goodness of fit. The data for years (2008-2011) were used for building the models. The best fitted distributions were Log-Normal (LN) for Al-Karkh, Al-Wathbah, Al-Qadisiya, Al- Dawrah and, Al-Rashid WTPs. Gamma distribution fitted well for East Tigris and Al-Karamah WTPs. As for Al-
... Show MoreDifferent frequency distributions models were fitted to the monthly data of raw water Turbidity at water treatment plants (WTPs) along Tigris River in Baghdad. Eight water treatment plants in Baghdad were selected, with raw water turbidity data for the period (2008-2014). The frequency distribution models used in this study are the Normal, Log-normal, Weibull, Exponential and two parameters Gamma type. The Kolmogorov-Smirnov test was used to evaluate the goodness of fit. The data for years (2008-2011) were used for building the models. The best fitted distributions were Log-Normal (LN) for Al-Karkh, Al-Wathbah, Al-Qadisiya, Al-Dawrah and, Al-Rashid WTPs. Gamma distribution fitted well for East Tigris and Al-Karamah
... Show MoreAbstract
The current research aims to identify the effect of using a model of generative learning in the achievement of first-middle students of chemical concepts in science. The researcher adopted the null hypothesis, which is there is no statistically significant difference at the level (0.05) between the mean scores of the experimental group who study using the generative learning model and the average scores of the control group who study using the traditional method in the chemical concepts achievement test. The research consisted of (200) students of the first intermediate at Al-Farqadin Intermediate School for Boys affiliated with the Directorate of General Education in Baghdad Governorate / Al-Karkh 3 wit
... Show MoreWireless channels are typically much more noisy than wired links and subjected to fading due to multipath propagation which result in ISI and hence high error rate. Adaptive modulation is a powerful technique to improve the tradeoff between spectral efficiency and Bit Error Rate (BER). In order to adjust the transmission rate, channel state information (CSI) is required at the transmitter side.
In this paper the performance enhancement of using linear prediction along with channel estimation to track the channel variations and adaptive modulation were examined. The simulation results shows that the channel estimation is sufficient for low Doppler frequency shifts (<30 Hz), while channel prediction is much more suited at
... Show MoreExperimental activity coefficients at infinite dilution are particularly useful for calculating the parameters needed in an expression for the excess Gibbs energy. If reliable values of γ∞1 and γ∞2 are available, either from direct experiment or from a correlation, it is possible to predict the composition of the azeotrope and vapor-liquid equilibrium over the entire range of composition. These can be used to evaluate two adjustable constants in any desired expression for G E. In this study MOSCED model and SPACE model are two different methods were used to calculate γ∞1 and γ∞2
Crop yield prediction is a critical measurement, especially in the time when parts of the world are suffering from farming issues. Yield forecasting gives an alert regarding economic trading, food production monitoring, and global food security. This research was conducted to investigate whether active optical sensors could be utilized for potato (Solanum tuberosum L.) yield prediction at the mid.le of the growing season. Three potato cultivars (Russet Burbank, Superior, and Shepody) were planted and six rates of N (0, 56, 112, 168, 224, and 280 kg ha−1), ammonium sulfate, which was replaced by ammonium nitrate in the 2nd year, were applied on 11 sites in a randomized complete block design, with four replications. Normalized difference ve
... Show MorePredicting vertical stress was indeed useful for controlling geomechanical issues since it allowed for the computation of pore pressure for the formation and the classification of fault regimes. This study provides an in-depth observation of vertical stress prediction utilizing numerous approaches using the Techlog 2015 software. Gardner's method results in incorrect vertical stress values with a problem that this method doesn't start from the surface and instead relies only on sound log data. Whereas the Amoco, Wendt non-acoustic, Traugott, average technique simply needed density log as input and used a straight line as the observed density, this was incorrect for vertical computing stress. The results of these methods
... Show More