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.
The proper operation, and control of wastewater treatment plants, is receiving an increasing attention, because of the rising concern about environmental issues. In this research a mathematical model was developed to predict biochemical oxygen demand in the waste water discharged from Abu-Ghraib diary factory in Baghdad using Artificial Neural Network (ANN).In this study the best selection of the input data were selected from the recorded parameters of the wastewater from the factory. The ANN model developed was built up with the following parameters: Chemical oxygen demand, Dissolved oxygen, pH, Total dissolved solids, Total suspended solids, Sulphate, Phosphate, Chloride and Influent flow rate. The results indicated that the constructed A
... Show MoreDocument source identification in printer forensics involves determining the origin of a printed document based on characteristics such as the printer model, serial number, defects, or unique printing artifacts. This process is crucial in forensic investigations, particularly in cases involving counterfeit documents or unauthorized printing. However, consistent pattern identification across various printer types remains challenging, especially when efforts are made to alter printer-generated artifacts. Machine learning models are often used in these tasks, but selecting discriminative features while minimizing noise is essential. Traditional KNN classifiers require a careful selection of distance metrics to capture relevant printing
... Show MoreIt boils down search is marked by (employing technology in the establishment of globalization in the Film Art), and walk parallel plan between the technical and artistic movements and the impact of globalization on the final performed in the film Film of innovations and technology and rapid capital that provided the filmmakers and Kartalatha which focused entirely in the embodiment of the idea and published in the service around the world. And distributes research on four chapters first chapter dealt with the methodological framework of the research, which included research problem marked by the following question: (What are the modalities to employ technology in the establishment of globalization in the Film Art?) And the importance of
... Show MoreThis paper proposes a new structure of the hybrid neural controller based on the identification model for nonlinear systems. The goal of this work is to employ the structure of the Modified Elman Neural Network (MENN) model into the NARMA-L2 structure instead of Multi-Layer Perceptron (MLP) model in order to construct a new hybrid neural structure that can be used as an identifier model and a nonlinear controller for the SISO linear or nonlinear systems. Weight parameters of the hybrid neural structure with its serial-parallel configuration are adapted by using the Back propagation learning algorithm. The ability of the proposed hybrid neural structure for nonlinear system has achieved a fast learning with minimum number
... Show More<span lang="EN-US">In the last years, the self-balancing platform has become one of the most common candidates to use in many applications such as flight, biomedical fields, and industry. In this paper, the physical prototype of a proposed self-balancing platform that described the self-balancing attitude in the (X-axis, Y-axis, or biaxial) under the influence of road disturbance has been introduced. In the physical prototype, the inertial measurement unit (IMU) sensor will sense the disturbance in (X-axis, Y-axis, and biaxial). With the determined error, the corresponding electronic circuit, DC servo motors, and the Arduino software, the platform overcame the tilt angle(disturbance). Optimization of the proportional-integral-
... Show MoreActivities associated with mining of uranium have generated significant quantities of waste materials containing uranium and other toxic metals. A qualitative and quantitative study was performed to assess the situation of nuclear pollution resulting from waste of drilling and exploration left on the surface layer of soil surrounding the abandoned uranium mine hole located in the southern of Najaf province in Iraq state. To measure the specific activity, twenty five surface soil samples were collected, prepared and analyzed by using gamma- ray spectrometer based on high counting efficiency NaI(Tl) scintillation detector. The results showed that the specific activities in Bq/kg are 37.31 to 1112.47 with mean of 268.16, 0.28 to 18.57 with
... Show MoreThis paper argues the accuracy of behavior based detection systems, in which the Application Programming Interfaces (API) calls are analyzed and monitored. The work identifies the problems that affecting the accuracy of such detection models. The work was extracted (4744) API call through analyzing. The new approach provides an accurate discriminator and can reveal malicious API in PE malware up to 83.2%. Results of this work evaluated with Discriminant Analysis
Different ANN architectures of MLP have been trained by BP and used to analyze Landsat TM images. Two different approaches have been applied for training: an ordinary approach (for one hidden layer M-H1-L & two hidden layers M-H1-H2-L) and one-against-all strategy (for one hidden layer (M-H1-1)xL, & two hidden layers (M-H1-H2-1)xL). Classification accuracy up to 90% has been achieved using one-against-all strategy with two hidden layers architecture. The performance of one-against-all approach is slightly better than the ordinary approach