English العربية کوردی

I’m  Diman Siddiq Hassan

Assistant Professor

Specialties

Data Mining and Machine Learning

diman.hassan@uoz.edu.krd
009647501881841
Iraq , Zakho
0
Awards
5
Published Journal Articles
2
Thesis
4
Training Course

0
Book Chapter
1
Conference
0
Presentation
0
Workshop

Education

Doctor of Philosophy

University of Nottingham from University of Nottingham

2016

Master

University of Duhok from University of Duhok

2009

Bachelor

University of Mosul from University of Mosul

2004

Academic Title

Assistant Professor

2025-07-06

Lecturer

2016-10-15

Assistant Lecturer

2009-03-10

Published Journal Articles

Science Journal of University of Zakho (Issue : 1) (Volume : 14)
AN EXPLAINABLE DEEP LEARNING FRAMEWORK FOR BREAST CANCER CLASSIFICATION USING EFFICIENTNETV2B0 AND GRAD-CAM

Breast cancer remains one of the most serious health challenges worldwide, withearly and accurate diagnosis... See more

Breast cancer remains one of the most serious health challenges worldwide, withearly and accurate diagnosis can significantly improve patient outcomes. Traditional diagnostic methods often rely heavily on expert interpretation, which may lead to inconsistencies or delays in decision-making. To address this issue, this research provides a deep-learning framework that uses the EfficientNetV2B0 model in combination with Grad-CAM (Gradient-weighted Class Activation Mapping) to provide illustrated explanations to detect breast cancer using ultrasound and MRI datasets. Our method addresses serious challenges such as class imbalance and irrelevant image characteristics by employing SMOTE (Synthetic Minority Over-sampling Technique) oversampling and Region of Interest (ROI) extraction for BUSI (Breast Ultrasound Images) datasets. The Grad-CAM approach improves reliability and transparency by providing visual proof that support’s each decision, allowing healthcare professionals to better understand the AI's prediction. Trained and assessed on two different medical imaging datasets, the framework obtained extraordinarily high accuracy (98.97% on BUSI and 99.55% on MRI), along with low prediction error and high reliability. The model is both accurate and understandable, making it ideal for clinical usage. It is also faster and more dependable than current approaches, making it highly beneficial.

 2026-01
Zanco Journal of Pure and Applied Sciences (Issue : 5) (Volume : 37)
LINK PREDICTION BASED ON TOPOLOGICAL AND CONTENT ANALYSIS IN CO-AUTHORSHIP NETWORKS

In network analysis, the prediction of the connections or associations between entities or nodes within... See more

In network analysis, the prediction of the connections or associations between entities or nodes within the network becomes important. Link Prediction is the problem of predicting or identifying the existence of a link between two entities in a network. However, it still the main issue in the complex network data application field, particularly in the type of analysis related to co-authorship networks despite its wide usage. Topological methods and content-based methods are the two different approaches that have been proposed for the link prediction in collaboration networks. However, topological methods are based on the structural analysis of the network, and content-based approaches rely on textual information from academic papers in the network. In this paper, we introduce the Content and Graph-Based Link Prediction (CGLP) approach, which integrates topological and content-based features from networks in a hybrid manner for predicting links in co-authorship networks. The efficacy of the proposed approach was already tested using three academic datasets: Hep-th, Hep-lat, and AMC by applying various machine learning models. Results indicated that all models showed almost the same efficiency on all three datasets and outperformed the state-of-the-art approach with a maximum F1 score of 98.05% and ROC AUC of 98.74%.

 2025-10
Science Journal of University of Zakho (Issue : 2025) (Volume : 13)
THE EFFECT OF FEATURE SELECTION METHODS ON MACHINE LEARNING MODEL PERFORMANCE: A COMPARATIVE STUDY FOR BREAST CANCER PREDICTION

Developing countries often face a high incidence of breast cancer, making early detection vital for... See more

Developing countries often face a high incidence of breast cancer, making early detection vital for effective treatment. The risk of developing breast cancer can be evaluated using machine learning methods and regular diagnostic data. In cancer datasets, there is a wealth of patient information, but not all of it is valuable for predicting cancer. This highlights the significance of feature selection methods in uncovering the relevant data. In this field, many studies have attempted to predict the different types of breast tumours, since it is important to diagnose breast cancer medication accurately. This paper aims to perform a comparison such that to show the effect of different feature selection methods on the accuracy of various existing machine learning algorithms. The study focuses on seven machine learning algorithms: K-Nearest Neighbors (KNN), Naive Bayes (NB), Decision Trees (DT), Support Vector Machines (SVM), Logistic Regression (LR), Neural Network (NN), and Random Forest (RF). The feature selection techniques examined include F-test Feature Selection, Mutual Information (MI), and Spearman Correlation Coefficient. The dataset used for the experiments is the Wisconsin Diagnostic Breast Cancer (WDBC) dataset, which is publicly available from the UCI Repository. The findings reveal that when feature selection is implemented, the LR and NN algorithms demonstrate superior accuracy and perform exceptionally well across other metrics compared to the other models

 2025-01
Science Journal of University of Zakho (Issue : 12) (Volume : 10)
LINK PREDICTION IN CO-AUTHORSHIP NETWORKS: A REVIEW

Besides social network analysis, the Link-Prediction (LP) problem has useful applications in information retrieval, bioinformatics,... See more

Besides social network analysis, the Link-Prediction (LP) problem has useful applications in information retrieval, bioinformatics, telecommunications, microbiology, and e-commerce as a forecast of future links in a given context to find what possible connections are based on a local and global statistical analysis of the given graph data. However, in Academic Social Networks (ASNs), the LP issue has recently attracted a lot of attention in academia and called for a variety of link prediction techniques to predict co-authorship among researchers and to examine the rich structural and associated data. As a result, this study investigates the problem of LPG in ASNs to forecast the upcoming co-authorships among researchers. In a systematic approach, this review presents, analyses, and compares the primary taxonomies of topological-based, content-based, and hybrid-based approaches, which are used for computing similar scores for each pair of unconnected nodes. Then, this study ends with findings on challenges and open problems for the community to work on for further development of the LP problem of scholarly social networks.

 2022-10
Biomedical Signal Processing and Control
Heart disease prediction based on pre-trained deep neural networks combined with principal component analysis

Heart Disease (HD) is often regarded as one of the deadliest human diseases. Therefore, early... See more

Heart Disease (HD) is often regarded as one of the deadliest human diseases. Therefore, early prediction of HD risks is crucial for prevention and treatment. Unfortunately, current clinical procedures for diagnosing HD are costly and often require an expert level of intervention. In response to this issue, researchers have recently developed various intelligent systems for the automated diagnosis of HD. Among the developed approaches, those based on artificial neural networks (ANNs) have gained more popularity due to their promising prediction results. However, to the authors’ knowledge, no research has attempted to exploit ANNs for feature extraction. Hence, research into bridging this gap is worthwhile for more excellent predictions. Motivated by this fact, this research proposes a new approach for HD prediction, utilizing a pre-trained Deep Neural Network (DNN) for feature extraction, Principal Component Analysis (PCA) for dimensionality reduction, and Logistic Regression (LR) for prediction. Cleveland, a publicly accessible HD dataset, was used to investigate the efficacy of the proposed approach (DNN + PCA + LR). Experimental results revealed that the proposed approach performs well on both the training and testing data, with accuracy rates of 91.79% and 93.33%, respectively. Furthermore, the proposed approach exhibited better performance when compared with the state-of-the-art approaches under most of the evaluation metrics used.

 2022-08

Thesis

2016-04-28
A Tree-Based Measure for Hierarchical Data in Mixed Databases

Ph.D. Thesis in Computer Science

 2016
2010-02-07
Modified Cryptosystems Based on Public-Key Algorithms

M.Sc. Thesis in Computer Science

 2010

Conference

Proceedings of the 2014 World Congress on Computational Intelligence (WCCI 2014)
 2014-07
Comparison of Distance Metrics for Hierarchical Data in Medical Databases

—Distance metrics are broadly used in different research areas and applications, such as bio-informatics, data mining and many other fields. However, there are some metrics, like pq-gram and Edit Distance used specifically for data with... See more

—Distance metrics are broadly used in different research areas and applications, such as bio-informatics, data mining and many other fields. However, there are some metrics, like pq-gram and Edit Distance used specifically for data with a hierarchical structure. Other metrics used for non-hierarchical data are the geometric and Hamming metrics. We have applied these metrics to The Health Improvement Network (THIN) database which has some hierarchical data. The THIN data has to be converted into a tree-like structure for the first group of metrics. For the second group of metrics, the data are converted into a frequency table or matrix, then for all metrics, all distances are found and normalised. Based on this particular data set, our research question: which of these metrics is useful for THIN data?. This paper compares the metrics, particularly the pqgram metric on finding the similarities of patients’ data. It also investigates the similar patients who have the same close distances as well as the metrics suitability for clustering the whole patient population. Our results show that the two groups of metrics perform differently as they represent different structures of the data. Nevertheless, all the metrics could represent some similar data of patients as well as discriminate sufficiently well in clustering the patient population using k-means clustering algorithm.

Training Course

2013-05-21,2013-05-22
Further LaTeX for researchers: developing your skills in LaTeX,

Further LaTeX for researchers: developing your skills in LaTeX. The University of Nottingham, Nottingham, United Kingdom.

 2013
2013-05-14,2013-05-15
Training course on English language

Training course on English language (Seven months) Castel College, Nottingham, United Kingdom, April 2011- November 2011.

 2013
2009-09-01,2009-12-01
Training course on Teaching Methods (3 months)

Training course on Teaching Methods (3 months) 2009, University of Duhok, Kurdistan-Iraq.

 2009
2005-08-06,2005-10-01
Training course on English language

Training course on English language (two months) University of Duhok

 2005