Sherko H. Murad
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sherko H. Murad has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Brzu Tahir1 shared publication
- HazharHazhar M. Balaky
Biology Department, Faculty of Science, Soran University, Soran-Erbil, Kurdistan Region-Iraq
1 shared publication Lawson Arman
Department of facility Therapy named after professor. V.A. Valdman, St Peterburg state Pediatric Medical university, Saint Petersburg, Russia
1 shared publicationNoor Bahjat Tayfor
Institute of Informatic, Faculty of Science and Informatics, University of Szeged, Szeged, Hungary
1 shared publicationNozad H. Mahmood
Cihan University Sulaimaniya Research Center (CUSRC), Cihan University Sulaimaniya, Sulaymaniyah City, Kurdistan Region, Iraq
1 shared publication- Yosra Mohammed1 shared publication
Latest Publications
- Open Access
- 30 October 2025
- Published by EngiScience Publisher in Emerging Technologies and Engineering Journal
- Vol. 2 (2) , 1-17
A Systematic Mapping Study on Brain Tumor Segmentation Based on Machine Learning Algorithms
A brain tumor is a type of cancer that develops from abnormal cells in the brain or forms a mass within the brain. It is characterized by the growth of these abnormal cells in brain tissue, which can be challenging to treat and significantly affect a patient's cognitive abilities. Magnetic resonance imaging (MRI) is commonly used to evaluate brain tumors. This paper presents a survey of recent work on brain tumour segmentation, aiming to identify trends and requirements for future research endeavours. A systematic study determined the most significant research and categorized the findings. Approximately 100 papers were reviewed, all utilizing convolutional neural networks (CNNs) for 70% of their methodologies. This approach represents the majority of studies. Additionally, 15% of the papers employed fuzzy methods, 6% used discrete wavelet transforms, and 9% utilized the U-Net architecture for brain tumor segmentation. Although further research is required within MDWE's (Multi-Domain Workflow Engineering) scope, various composition mechanisms have been thoroughly recommended in the existing literature. Furthermore, there is a consistent suggestion for the need for solution proposals, validation studies, and philosophical papers based on prior analyses. The findings indicate that brain tumor segmentation is an active, emerging, and expansive field of research. However, particular areas still require further exploration. This is an improved area for publication.
- 30 October 2025
- Published by EngiScience Publisher in Emerging Technologies and Engineering Journal
- Vol. 2 (2) , 1-17
Open AccessA Systematic Mapping Study on Brain Tumor Segmentation Based on Machine Learning Algorithms
A brain tumor is a type of cancer that develops from abnormal cells in the brain or forms a mass within the brain. It is characterized by the growth of these abnormal cells in brain tissue, which can be challenging to treat and significantly affect a patient's cognitive abilities. Magnetic resonance imaging (MRI) is commonly used to evaluate brain tumors. This paper presents a survey of recent work on brain tumour segmentation, aiming to identify trends and requirements for future research endeavours. A systematic study determined the most significant research and categorized the findings. Approximately 100 papers were reviewed, all utilizing convolutional neural networks (CNNs) for 70% of their methodologies. This approach represents the majority of studies. Additionally, 15% of the papers employed fuzzy methods, 6% used discrete wavelet transforms, and 9% utilized the U-Net architecture for brain tumor segmentation. Although further research is required within MDWE's (Multi-Domain Workflow Engineering) scope, various composition mechanisms have been thoroughly recommended in the existing literature. Furthermore, there is a consistent suggestion for the need for solution proposals, validation studies, and philosophical papers based on prior analyses. The findings indicate that brain tumor segmentation is an active, emerging, and expansive field of research. However, particular areas still require further exploration. This is an improved area for publication.
- Open Access
Hybrid genetic algorithms-driven optimization of machine learning models for heart disease prediction
- 1 January 2019
- Published by University of Garmian
- Vol. 3 (2) , 1-9
Air Temperature Prediction Using Different Datamining Approaches In Sulaymaniyah City In Iraq
Climate change has a historical impact at universal and local levels over the past era. Climate change is one of the greatest challenge issues in the globe for meteorological research. Air temperature estimation, in particular, has been measured as a significant feature in weather impression studies on industrial sectors, environmental, ecological, and agricultural. Accurately predicting air temperature guides to measure lifestyle, perform a key character for the government, industries, and public in development activities. In this paper, we investigate the use of various data mining approaches such as Support Vector Machine (SVM), Decision tree (DT), and Naïve Bayes for air temperature prediction within Sulaymaniyah City in Kurdistan, IRAQ. The metrological data is collected from the local Weather Forecast Department in the city within the range 2013 to 2018 inclusive. A dataset for the metrological data was developed and used to train the data mining algorithms. The proposed data mining algorithms were tested on the dataset to predict the air temperature and the performance of these algorithms were compared using standard performance metrics. Support vector machine has accomplished promising performance among using algorithms
- 1 January 2019
- Published by University of Garmian
- Vol. 3 (2) , 1-9
Air Temperature Prediction Using Different Datamining Approaches In Sulaymaniyah City In Iraq
Climate change has a historical impact at universal and local levels over the past era. Climate change is one of the greatest challenge issues in the globe for meteorological research. Air temperature estimation, in particular, has been measured as a significant feature in weather impression studies on industrial sectors, environmental, ecological, and agricultural. Accurately predicting air temperature guides to measure lifestyle, perform a key character for the government, industries, and public in development activities. In this paper, we investigate the use of various data mining approaches such as Support Vector Machine (SVM), Decision tree (DT), and Naïve Bayes for air temperature prediction within Sulaymaniyah City in Kurdistan, IRAQ. The metrological data is collected from the local Weather Forecast Department in the city within the range 2013 to 2018 inclusive. A dataset for the metrological data was developed and used to train the data mining algorithms. The proposed data mining algorithms were tested on the dataset to predict the air temperature and the performance of these algorithms were compared using standard performance metrics. Support vector machine has accomplished promising performance among using algorithms