GMGuhdar Ahmed Abdulaziz Mulla

Guhdar Ahmed Abdulaziz Mulla

*This is an algorithmically generated author record based on publicly available information.

Guhdar Ahmed Abdulaziz Mulla has a total of 3 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    An Analytical Study to Investigate the Effect of Speed Control Cameras in Reducing Traffic Accidents

    by Guhdar Ahmed Abdulaziz Mulla, Akram Salih, Yıldırım Demir

    In this study, the effect of speed control cameras on traffic accidents in Dohuk province of Iraqi Kurdistan Region is analyzed using data from 2011-2019. Three time periods: before, during and after the installation of cameras were used as criteria for the retrospective detection of traffic accidents. For control purposes, an area in the same region where the cameras were not installed was also included in the study. The importance of this research is that traffic accidents occur at high rates due to the increasing number of vehicles and speed violations in the province every year. It is of great importance to take measures to reduce vehicle speeds in order to reduce traffic accidents. By reducing vehicle speeds, traffic congestion on the roads and loss of life in accidents can be reduced. More speed control cameras are being used in the belief that they will reduce vehicle speeds. In Duhok province, the annual average number of vehicles increased by 7.62% and the number of speed-related traffic violations increased by 34.46%, while the number of traffic accidents increased by 4%, the number of injuries due to traffic accidents increased by 5.32% and the number of deaths increased by 1.86%. SPSS package program was used for the necessary analyses.

  • Open Access

    The Use of Clustering and Classification Methods in Machine Learning and Comparison of Some Algorithms of the Methods

    by Guhdar A. A. Mulla, Yıldırım Demir

    In this article, two machine learning methods such as classification and clustering are used for decision tree (DT), artificial neural network (ANN), and K-nearest neighbors algorithms. The datasets were used to evaluate the effectiveness of the clustering method and the data mining tool. Weather data were used to compare algorithms and methods in the study. This study showed that the best model was DT according to accuracy and precision measures but the best model according to F-measure and receiver operating characteristic curve area measures was ANN. Waikato Environment for Knowledge Analysis, a data mining tool, is utilized in this paper to carry out the clustering.


  • Combination of PCA with SMOTE Oversampling for Classification of High-Dimensional Imbalanced Data

    by Guhdar A. A. Mulla, Yıldırım Demi̇r, Masoud Hassan

    Imbalanced data classification is a common issue in data mining where the classifiers are skewed towards the larger data class. Classification of high-dimensional skewed (imbalanced) data is of great interest to decision-makers as it is more difficult to. The dimension reduction method, a process in which variables are reduced, allows high dimensional datasets to be interpreted more easily with a certain loss. This study, a method combining SMOTE oversampling with principal component analysis is proposed to solve the imbalance problem in high dimensional data. Three classification algorithms consisting of Logistic Regression, K-Nearest Neighbor, Decision Tree methods and two separate datasets were utilized to evaluate the suggested method's efficacy and determine the classifiers' performance. Respectively, raw datasets, converted datasets by PCA, SMOTE and SMOTE+PCA (SMOTE and PCA) methods, were analyzed with the given algorithms. Analyzes were made using WEKA. Analysis results suggest that almost all classification algorithms improve their classification performance using PCA, SOMTE, and SMOTE+PCA methods. However, the SMOTE method gave more efficient results than PCA and PCA+SMOTE methods for data rebalancing. Experimental results also suggest that K-Nearest Neighbor classifier provided higher classification performance compared to other algorithms.