Eman Salih Al-Shamery
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Eman Salih Al-Shamery has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Hussein Abdul Ameer Abbas Al-Khamees
University of Babylon
3 shared publications - Lee Richard Machado
Centre for Physical Activity and Life Sciences, University of Northampton, Northampton, UK
3 shared publications - Michael Opoku Agyeman
University of Northampton
3 shared publications - Mu Mu
University of Northampton
3 shared publications - Nabeel Al-A'ARaji
University of Babylon
3 shared publications - Suraj Ajit
University of Northampton
3 shared publications
Latest Publications
- Open Access
- 30 April 2025
- Published by University of Kerbala - KIJOMS in Karbala International Journal of Modern Science
- Vol. 11 (2) , 6
Predicting Healthcare Service Quality Based on a Kalman-Optimized Bi-LSTM-Inspired Deep Learning Model
Health is one of the most important aspects of human well-being, and access to high-quality healthcare is essential for a good quality of life. Providing top-level health services at all times is crucial. However, the research in healthcare poses significant challenges due to the diversity and variations of medical practices across different hospitals. This paper aims to tackle the challenge of data missing and scattering during data collection. Then, the quality of services (QoS) offered by healthcare facilities will be analyzed and predicted from the patient's perspective. The model begins preprocessing data by data cleaning, handling missing values, and scattering data using clustering, similarity techniques, and collaborative filtering methods. Then, it focuses on predicting QoS using a structured structure for bidirectional long short-term memory (Bi-LSTM) networks. Finally, the model employs a Kalman filter method to optimize prediction by reducing the squared error between the model prediction and the actual prediction. In this study, two types of databases were used. The first data was from Iraqi hospitals in various geographical areas: Al-Hillah General Teaching Hospital in Babylon (H1), Al-Kafeel Hospital in Karbala (H2), Al-Yarmouk Hospital in Baghdad (H3), and Diwaniyah Women's and Children's Hospital in Diwaniyah (H4). The data was collected through questionnaires in both manual and electronic form. The second data was obtained from United States hospitals; it was collected by the Centers for Medicare and Medicaid Services (CMS). The model achieved an accuracy of 98.4%, precision of 98 %, recall of 97.7 %, and F1-measure of 97.6 % with the U.S. hospital databases, outperforming many models such as deep learning techniques (LSTM and Bi-LSTM), regression, and random forest.
- 30 April 2025
- Published by University of Kerbala - KIJOMS in Karbala International Journal of Modern Science
- Vol. 11 (2) , 6
Open AccessPredicting Healthcare Service Quality Based on a Kalman-Optimized Bi-LSTM-Inspired Deep Learning Model
Health is one of the most important aspects of human well-being, and access to high-quality healthcare is essential for a good quality of life. Providing top-level health services at all times is crucial. However, the research in healthcare poses significant challenges due to the diversity and variations of medical practices across different hospitals. This paper aims to tackle the challenge of data missing and scattering during data collection. Then, the quality of services (QoS) offered by healthcare facilities will be analyzed and predicted from the patient's perspective. The model begins preprocessing data by data cleaning, handling missing values, and scattering data using clustering, similarity techniques, and collaborative filtering methods. Then, it focuses on predicting QoS using a structured structure for bidirectional long short-term memory (Bi-LSTM) networks. Finally, the model employs a Kalman filter method to optimize prediction by reducing the squared error between the model prediction and the actual prediction. In this study, two types of databases were used. The first data was from Iraqi hospitals in various geographical areas: Al-Hillah General Teaching Hospital in Babylon (H1), Al-Kafeel Hospital in Karbala (H2), Al-Yarmouk Hospital in Baghdad (H3), and Diwaniyah Women's and Children's Hospital in Diwaniyah (H4). The data was collected through questionnaires in both manual and electronic form. The second data was obtained from United States hospitals; it was collected by the Centers for Medicare and Medicaid Services (CMS). The model achieved an accuracy of 98.4%, precision of 98 %, recall of 97.7 %, and F1-measure of 97.6 % with the U.S. hospital databases, outperforming many models such as deep learning techniques (LSTM and Bi-LSTM), regression, and random forest.
- 16 January 2025
- Published by Springer Nature
- p. 133-147
Hybrid Model for Hospital Services Quality Prediction Based on Patient Viewpoint
- 16 January 2025
- Published by Springer Nature
- p. 133-147
Hybrid Model for Hospital Services Quality Prediction Based on Patient Viewpoint
- Open Access
- 17 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 115161-115178
A Novel Fuzzy Classifier Model for Cancer Classification Using Gene Expression Data
In the pursuit of better cancer classification, many studies have been conducted to identify the genes associated with cancer. However, the high dimensionality of gene expression data and the limited relevance of a few genes pose significant challenges to this endeavor. Existing gene selection methods yield divergent gene lists, further complicating the classification process. To overcome this issue, we developed a novel approach called Fuzzy Gene Selection (FGS), which combines the strengths of various gene selection methods in the field. FGS was developed using three feature selection techniques (Mutual Information, F-ClassIf, and Chi-squared) to rank genes based on their importance. These methods generated scores and rankings for each gene. Fuzzification and Defuzzification techniques were then applied to combine these scores into a single best score for each gene. This approach aids in identifying genes of significance in cancer classification, especially in multi-class scenarios. Classifiers often produce convergent decisions in such cases, where the predicted probabilities for different classes do not always correspond to the correct predicted class with the highest probability. To address this, we developed a novel Fuzzy classifier that leverages the contributions from each node’s traditional deep classifier. This novel approach combines the strengths of traditional deep classifiers at individual nodes, enabling the Fuzzy classifier to make more robust and informed predictions. The Fuzzy classifier (FC) has demonstrated improvements in accuracy and the generalization of the proposed algorithm to accurately classify different cancer types.
- 17 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 115161-115178
Open AccessA Novel Fuzzy Classifier Model for Cancer Classification Using Gene Expression Data
In the pursuit of better cancer classification, many studies have been conducted to identify the genes associated with cancer. However, the high dimensionality of gene expression data and the limited relevance of a few genes pose significant challenges to this endeavor. Existing gene selection methods yield divergent gene lists, further complicating the classification process. To overcome this issue, we developed a novel approach called Fuzzy Gene Selection (FGS), which combines the strengths of various gene selection methods in the field. FGS was developed using three feature selection techniques (Mutual Information, F-ClassIf, and Chi-squared) to rank genes based on their importance. These methods generated scores and rankings for each gene. Fuzzification and Defuzzification techniques were then applied to combine these scores into a single best score for each gene. This approach aids in identifying genes of significance in cancer classification, especially in multi-class scenarios. Classifiers often produce convergent decisions in such cases, where the predicted probabilities for different classes do not always correspond to the correct predicted class with the highest probability. To address this, we developed a novel Fuzzy classifier that leverages the contributions from each node’s traditional deep classifier. This novel approach combines the strengths of traditional deep classifiers at individual nodes, enabling the Fuzzy classifier to make more robust and informed predictions. The Fuzzy classifier (FC) has demonstrated improvements in accuracy and the generalization of the proposed algorithm to accurately classify different cancer types.
- Open Access
Fuzzy Gene Selection and Cancer Classification Based on Deep Learning Model
Machine learning (ML) approaches have been used to develop highly accurate and efficient applications in many fields including bio-medical science. However, even with advanced ML techniques, cancer classification using gene expression data is still complicated because of the high dimensionality of the datasets employed. We developed a new fuzzy gene selection technique (FGS) to identify informative genes to facilitate cancer classification and reduce the dimensionality of the available gene expression data. Three feature selection methods (Mutual Information, F-ClassIf, and Chi-squared) were evaluated and employed to obtain the score and rank for each gene. Then, using Fuzzification and Defuzzification methods to obtain the best single score for each gene, which aids in the identification of significant genes. Our study applied the fuzzy measures to six gene expression datasets including four Microarray and two RNA-seq datasets for evaluating the proposed algorithm. With our FGS-enhanced method, the cancer classification model achieved 96.5%,96.2%,96%, and 95.9% for accuracy, precision, recall, and f1-score respectively, which is significantly higher than 69.2% accuracy, 57.8% precision, 66% recall, and 58.2% f1-score when the standard MLP method was used. In examining the six datasets that were used, the proposed model demonstrates it's capacity to classify cancer effectively.
Open AccessFuzzy Gene Selection and Cancer Classification Based on Deep Learning Model
Machine learning (ML) approaches have been used to develop highly accurate and efficient applications in many fields including bio-medical science. However, even with advanced ML techniques, cancer classification using gene expression data is still complicated because of the high dimensionality of the datasets employed. We developed a new fuzzy gene selection technique (FGS) to identify informative genes to facilitate cancer classification and reduce the dimensionality of the available gene expression data. Three feature selection methods (Mutual Information, F-ClassIf, and Chi-squared) were evaluated and employed to obtain the score and rank for each gene. Then, using Fuzzification and Defuzzification methods to obtain the best single score for each gene, which aids in the identification of significant genes. Our study applied the fuzzy measures to six gene expression datasets including four Microarray and two RNA-seq datasets for evaluating the proposed algorithm. With our FGS-enhanced method, the cancer classification model achieved 96.5%,96.2%,96%, and 95.9% for accuracy, precision, recall, and f1-score respectively, which is significantly higher than 69.2% accuracy, 57.8% precision, 66% recall, and 58.2% f1-score when the standard MLP method was used. In examining the six datasets that were used, the proposed model demonstrates it's capacity to classify cancer effectively.
- Open Access
- 1 April 2023
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 13 (2) , 2123-2130
Enhancing the stability of the deep neural network using a non-constant learning rate for data stream
The data stream is considered the backbone of many real-world applications. These applications are most effective when using modern techniques of machine learning like deep neural networks (DNNs). DNNs are very sensitive to set parameters, the most prominent one is the learning rate. Choosing an appropriate learning rate value is critical because it is able to control the overall network performance. This paper presents a new developing DNN model using a multi-layer perceptron (MLP) structure that includes network training based on the optimal learning rate. Thereupon, this model consists of three hidden layers and does not adopt the stability of the learning rate but has a non-constant value (varying over time) to obtain the optimal learning rate which is able to reduce the error in each iteration and increase the model accuracy. This is done by deriving a new parameter that is added to and subtracted from the learning rate. The proposed model is evaluated by three streaming datasets: electricity, network security layer-knowledge discovery in database (NSL-KDD), and human gait database (HuGaDB) datasets. The results proved that the proposed model achieves better results than the constant model and outperforms previous models in terms of accuracy, where it achieved 88.16%, 98.67%, and 97.63% respectively.
- 1 April 2023
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 13 (2) , 2123-2130
Open AccessEnhancing the stability of the deep neural network using a non-constant learning rate for data stream
The data stream is considered the backbone of many real-world applications. These applications are most effective when using modern techniques of machine learning like deep neural networks (DNNs). DNNs are very sensitive to set parameters, the most prominent one is the learning rate. Choosing an appropriate learning rate value is critical because it is able to control the overall network performance. This paper presents a new developing DNN model using a multi-layer perceptron (MLP) structure that includes network training based on the optimal learning rate. Thereupon, this model consists of three hidden layers and does not adopt the stability of the learning rate but has a non-constant value (varying over time) to obtain the optimal learning rate which is able to reduce the error in each iteration and increase the model accuracy. This is done by deriving a new parameter that is added to and subtracted from the learning rate. The proposed model is evaluated by three streaming datasets: electricity, network security layer-knowledge discovery in database (NSL-KDD), and human gait database (HuGaDB) datasets. The results proved that the proposed model achieves better results than the constant model and outperforms previous models in terms of accuracy, where it achieved 88.16%, 98.67%, and 97.63% respectively.
- Open Access
- 30 September 2022
- Published by Korean Institute of Intelligent Systems in International Journal of Fuzzy Logic and Intelligent Systems
- Vol. 22 (3) , 267-275
An Evolving Fuzzy Model to Determine an Optimal Number of Data Stream Clusters
Hussein A. A. Al-Khamees, Nabeel Al-A’araji, and Eman S. Al-Shamery. International Journal of Fuzzy Logic and Intelligent Systems 2022;22:267-75. https://doi.org/10.5391/IJFIS.2022.22.3.267
- 30 September 2022
- Published by Korean Institute of Intelligent Systems in International Journal of Fuzzy Logic and Intelligent Systems
- Vol. 22 (3) , 267-275
Open AccessAn Evolving Fuzzy Model to Determine an Optimal Number of Data Stream Clusters
Hussein A. A. Al-Khamees, Nabeel Al-A’araji, and Eman S. Al-Shamery. International Journal of Fuzzy Logic and Intelligent Systems 2022;22:267-75. https://doi.org/10.5391/IJFIS.2022.22.3.267
- 17 June 2022
- Published by Springer Nature
- p. 107-118
Classifying the Human Activities of Sensor Data Using Deep Neural Network
- 17 June 2022
- Published by Springer Nature
- p. 107-118
Classifying the Human Activities of Sensor Data Using Deep Neural Network
- Open Access
- 25 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 27522-27534
A Survey of Machine Learning Approaches Applied to Gene Expression Analysis for Cancer Prediction
Machine learning approaches are powerful techniques commonly employed for developing cancer prediction models using associated gene expression and mutation data. Our survey provides a comprehensive review of recent cancer studies that have employed gene expression data from several cancer types (breast, lung, kidney, ovarian, liver, central nervous system and gallbladder) for survival prediction,tumor identification and stratification. We also provide an overview of biomarker studies that are associated with these cancer types. The survey captures multiple aspects of machine learning associated cancer studies,including cancer classification, cancer prediction, identification of biomarker genes, microarray, and RNA-Seq data.We discuss the technical issues with current cancer prediction models and the corresponding measurement tools for determining the activity levels of gene expression between cancerous tissues and noncancerous tissues. Additionally, we investigate how identifying putative biomarker gene expression patterns can aid in predicting future risk of cancer and inform the provision of personalized treatment.
- 25 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 27522-27534
Open AccessA Survey of Machine Learning Approaches Applied to Gene Expression Analysis for Cancer Prediction
Machine learning approaches are powerful techniques commonly employed for developing cancer prediction models using associated gene expression and mutation data. Our survey provides a comprehensive review of recent cancer studies that have employed gene expression data from several cancer types (breast, lung, kidney, ovarian, liver, central nervous system and gallbladder) for survival prediction,tumor identification and stratification. We also provide an overview of biomarker studies that are associated with these cancer types. The survey captures multiple aspects of machine learning associated cancer studies,including cancer classification, cancer prediction, identification of biomarker genes, microarray, and RNA-Seq data.We discuss the technical issues with current cancer prediction models and the corresponding measurement tools for determining the activity levels of gene expression between cancerous tissues and noncancerous tissues. Additionally, we investigate how identifying putative biomarker gene expression patterns can aid in predicting future risk of cancer and inform the provision of personalized treatment.
- Open Access
- 1 February 2021
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1804 (1) , 012050
A Review on Distributed Blockchain Technology for E-voting Systems
Election is an important event in all countries. Conventional voting suffers many issues, such as cost of time and efforts needed for tallying and counting results, cost in papers, arrangements and all that it takes for a voting process to be achieved. Many countries such as Australia, Belgium, Brazil, Canada, Estonia, France, Germany, India, Italy, Namibia, the Netherlands, Norway, Peru, Switzerland, the UK, Venezuela and the Philippines considered online e-voting systems, but the traditional e-voting systems suffer a lack of trust, it is not known if a vote is counted correctly, tampered or not. The voter has no guarantee that his/her vote is considered as they voted in elections, it’s a lack of transparency. A solution is e-voting systems based on blockchain (sometimes referred as Distributed Ledger Technology (DLT)) has now turned to be promising for what properties it offer, such as, privacy, security, transparency, accuracy, decentralization in which no central control exist, and most of all, creates an immutable system, where citizens are allowed to vote from their location by using digital devices (smart phones, computers, electronic voting machines). Also, due to the COVID-19 pandemic, many technology applications are heading towards systems with all these properties, at the same time, maintaining social distancing. This review introduced many different ideas for implementing e-voting systems based on Blockchain and how the users (voters and candidates) interact with the system showing the voting process from the first step of registration to authentication till showing the final results. At the end of this review we will illustrate a table that contain all mechanisms used in the papers involved that covers the most important requirements needed for every e-voting system based on blockchain or Distributed Ledger Technology (DLT).
- 1 February 2021
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1804 (1) , 012050
Open AccessA Review on Distributed Blockchain Technology for E-voting Systems
Election is an important event in all countries. Conventional voting suffers many issues, such as cost of time and efforts needed for tallying and counting results, cost in papers, arrangements and all that it takes for a voting process to be achieved. Many countries such as Australia, Belgium, Brazil, Canada, Estonia, France, Germany, India, Italy, Namibia, the Netherlands, Norway, Peru, Switzerland, the UK, Venezuela and the Philippines considered online e-voting systems, but the traditional e-voting systems suffer a lack of trust, it is not known if a vote is counted correctly, tampered or not. The voter has no guarantee that his/her vote is considered as they voted in elections, it’s a lack of transparency. A solution is e-voting systems based on blockchain (sometimes referred as Distributed Ledger Technology (DLT)) has now turned to be promising for what properties it offer, such as, privacy, security, transparency, accuracy, decentralization in which no central control exist, and most of all, creates an immutable system, where citizens are allowed to vote from their location by using digital devices (smart phones, computers, electronic voting machines). Also, due to the COVID-19 pandemic, many technology applications are heading towards systems with all these properties, at the same time, maintaining social distancing. This review introduced many different ideas for implementing e-voting systems based on Blockchain and how the users (voters and candidates) interact with the system showing the voting process from the first step of registration to authentication till showing the final results. At the end of this review we will illustrate a table that contain all mechanisms used in the papers involved that covers the most important requirements needed for every e-voting system based on blockchain or Distributed Ledger Technology (DLT).
- Open Access
- 5 October 2020
- Published by University of Kerbala - KIJOMS in Karbala International Journal of Modern Science
- Vol. 6 (3) , 10
A Fuzzy Assessment Model for Hospitals Services Quality based on Patient Experience
The patient's experience is a lens for services assessment that provide from healthcare institutions because the patient is the first and the last recipient for the service. The patient's experience carries a lot of uncertainty and an ultimate decision cannot be taken from the patient about the services, but it carries the partial truth. Many artificial intelligence technologies deal with the concept of partial truth, such as genetic algorithms and neural networks, but the fuzzy logic remains pioneering to deal with uncertainty. This paper aims to develop an assessment model by using fuzzy inference that is able to assess the quality of services in a similar way to the human experts of healthcare. The fuzzy assessment model applied to measure the patient satisfaction rate for health services for more 4500 hospitals in the United States and two hospitals in Iraq. The services are assessed by the questionnaire and its design according to the questionnaire of the assessment of healthcare providers and systems (HCAHPS) for all hospitals in the United State. The population study in Iraq consisted of 1,000 patients divided between 500 patients from Al-Hillah general teaching hospital and 500 patients from Al-Kafil private hospital. Depending on the patients' answers, the degrees of membership are calculated among the fuzzy sets. The results show a clear difference between the services provided by private hospitals compared to public hospitals.
- 5 October 2020
- Published by University of Kerbala - KIJOMS in Karbala International Journal of Modern Science
- Vol. 6 (3) , 10
Open AccessA Fuzzy Assessment Model for Hospitals Services Quality based on Patient Experience
The patient's experience is a lens for services assessment that provide from healthcare institutions because the patient is the first and the last recipient for the service. The patient's experience carries a lot of uncertainty and an ultimate decision cannot be taken from the patient about the services, but it carries the partial truth. Many artificial intelligence technologies deal with the concept of partial truth, such as genetic algorithms and neural networks, but the fuzzy logic remains pioneering to deal with uncertainty. This paper aims to develop an assessment model by using fuzzy inference that is able to assess the quality of services in a similar way to the human experts of healthcare. The fuzzy assessment model applied to measure the patient satisfaction rate for health services for more 4500 hospitals in the United States and two hospitals in Iraq. The services are assessed by the questionnaire and its design according to the questionnaire of the assessment of healthcare providers and systems (HCAHPS) for all hospitals in the United State. The population study in Iraq consisted of 1,000 patients divided between 500 patients from Al-Hillah general teaching hospital and 500 patients from Al-Kafil private hospital. Depending on the patients' answers, the degrees of membership are calculated among the fuzzy sets. The results show a clear difference between the services provided by private hospitals compared to public hospitals.