This paper proposes two hybrid feature subset selection approaches based on the combination (union or intersection) of both supervised and unsupervised filter approaches before using a wrapper, aiming to obtain low-dimensional features with high accuracy and interpretability and low time consumption. Experiments with the proposed hybrid approaches have been conducted on seven high-dimensional feature datasets. The classifiers adopted are support vector machine (SVM), linear discriminant analysis (LDA), and K-nearest neighbour (KNN). Experimental results have demonstrated the advantages and usefulness of the proposed methods in feature subset selection in high-dimensional space in terms of the number of selected features and time spe

Total dissolved solids are at the top of the parameters list of water quality that requires investigations for planning and management, especially for irrigation and drinking purposes. If the quality of water is sufficiently predictable, then appropriate management is possible. In the current study, Multiple Linear Regression (MLR) and Artificial Neural Network (ANN) models were used as indicators of water quality and for the prediction of Total Dissolved Solids (TDS) along the Tigris River, in Baghdad city. To build these models five water parameters were selected from the intakes of four water treatment plants on the Tigris River, for the period between 2013 and 2017. The selected water parameters were Total Dissolved Solids (TDS

The alluvial fan of Mandali located between latitude 30˚45’00” N longitude 45˚30’00” E in east of Diyala Governorate, Iraq. Thirty-five wells were identified in the study area with average depth of 84 m and estimated area of 21550 ha. A three-dimensional conceptual model was prepared by using GMS program. From wells cross sections, four geological layers have been identified. The hydraulic conductivity of these layers was calculated for steady state condition, where the water levels for nine wells distributed over the study area were observed at same time. Afterward, PEST facility in the GMS was used to estimate the aquifer hydraulic characteristics. Other characteristics such as storage coefficient and specific yield have

Problem: Cancer is regarded as one of the world's deadliest diseases. Machine learning and its new branch (deep learning) algorithms can facilitate the way of dealing with cancer, especially in the field of cancer prevention and detection. Traditional ways of analyzing cancer data have their limits, and cancer data is growing quickly. This makes it possible for deep learning to move forward with its powerful abilities to analyze and process cancer data. Aims: In the current study, a deep-learning medical support system for the prediction of lung cancer is presented. Methods: The study uses three different deep learning models (EfficientNetB3, ResNet50 and ResNet101) with the transfer learning concept. The three models are trained using a

This paper compares between the direct and indirect georeferencing techniques in Photogrammetry bases on a simulation model. A flight plan is designed which consists of three strips with nine overlapped images for each strip by a (Canon 500D) digital camera with a resolution of 15 Mega Pixels.

The triangulation computations are carried out by using (ERDAS LPS) software, and the direct measurements are taken directly on the simulated model to substitute using GPS/INS in real case. Two computational tests have been implemented to evaluate the positional accuracy for the whole model and the Root Mean Square Error (RMSE) relating to (30) check points show that th

B Saleem, H Alwan, L Khalid, Journal of Engineering, 2011 - Cited by 2

Data generated from modern applications and the internet in healthcare is extensive and rapidly expanding. Therefore, one of the significant success factors for any application is understanding and extracting meaningful information using digital analytics tools. These tools will positively impact the application's performance and handle the challenges that can be faced to create highly consistent, logical, and information-rich summaries. This paper contains three main objectives: First, it provides several analytics methodologies that help to analyze datasets and extract useful information from them as preprocessing steps in any classification model to determine the dataset characteristics. Also, this paper provides a comparative st

The study aimed to prepare quick response codes to learn some of the technical skills of the second graders in the Faculty of Physical Education and Sports Sciences. The experimental method was used in the design of the experimental and control experimental and control groups. The research sample was represented by second-graders in the College of Physical Education and Sports Sciences / University of Baghdad, and by lot, the second division (a) was chosen to represent the experimental group that applied the inverse method using the QR code, and the second division (g) to represent the control group and applied the traditional method. (10) Students per group. After the tribal tests, his main experiment was carried out for 10 weeks with one