Neamat El-Tazi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Neamat El-Tazi has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
Ayman El-Kilany
Department of Information Systems, Faculty of Computers and Artificial Intelligence, Cairo University, Giza, Egypt
2 shared publicationsH. V. Jagadish
Ann Arbor, MI
2 shared publicationsAbla Lotfy
Information Systems Department, Faculty of Computers and Information Cairo University, Giza, Egypt
1 shared publicationAhmad Hany Hossny
1 shared publicationAhmad Hossny
University of Adelaide Adelaide, Australia
1 shared publication- Amal Elgammal
Cairo University
1 shared publication
Latest Publications
- Open Access
- 11 February 2026
- Published by MDPI AG in Informatics
- Vol. 13 (2) , 32
A Model-Driven Engineering Approach to AI-Powered Healthcare Platforms
Artificial intelligence (AI) has the potential to transform healthcare by supporting more accurate diagnoses and personalized treatments. However, its adoption in practice remains constrained by fragmented data sources, strict privacy rules, and the technical complexity of building reliable clinical systems. To address these challenges, we introduce a model-driven engineering (MDE) framework designed specifically for healthcare AI. The framework relies on formal metamodels, domain-specific languages (DSLs), and automated transformations to move from high-level specifications to running software. At its core is the Medical Interoperability Language (MILA), a graphical DSL that enables clinicians and data scientists to define queries and machine learning pipelines using shared ontologies. When combined with a federated learning architecture, MILA allows institutions to collaborate without exchanging raw patient data, ensuring semantic consistency across sites while preserving privacy. We evaluate this approach in a multi-center cancer immunotherapy study. The generated pipelines delivered strong predictive performance, with best-performing models achieving up to 98.5% accuracy on selected prediction tasks, while substantially reducing manual coding effort. These findings suggest that MDE principles—metamodeling, semantic integration, and automated code generation—can provide a practical path toward interoperable, reproducible, and reliable digital health platforms.
- 11 February 2026
- Published by MDPI AG in Informatics
- Vol. 13 (2) , 32
Open AccessA Model-Driven Engineering Approach to AI-Powered Healthcare Platforms
Artificial intelligence (AI) has the potential to transform healthcare by supporting more accurate diagnoses and personalized treatments. However, its adoption in practice remains constrained by fragmented data sources, strict privacy rules, and the technical complexity of building reliable clinical systems. To address these challenges, we introduce a model-driven engineering (MDE) framework designed specifically for healthcare AI. The framework relies on formal metamodels, domain-specific languages (DSLs), and automated transformations to move from high-level specifications to running software. At its core is the Medical Interoperability Language (MILA), a graphical DSL that enables clinicians and data scientists to define queries and machine learning pipelines using shared ontologies. When combined with a federated learning architecture, MILA allows institutions to collaborate without exchanging raw patient data, ensuring semantic consistency across sites while preserving privacy. We evaluate this approach in a multi-center cancer immunotherapy study. The generated pipelines delivered strong predictive performance, with best-performing models achieving up to 98.5% accuracy on selected prediction tasks, while substantially reducing manual coding effort. These findings suggest that MDE principles—metamodeling, semantic integration, and automated code generation—can provide a practical path toward interoperable, reproducible, and reliable digital health platforms.
- Open Access
- 22 December 2025
- Published by Springer Nature in International Journal of Data Science and Analytics
- Vol. 21 (1) , 80
Discovering weighted and attributed communities from social graphs
Community search is currently attracting a lot of attention. The problem of a community search in a node-attributed graph is to locate a meaningful community that satisfies certain query parameters. It has piqued the interest of both industry and academia. Most research on finding communities in graphs focuses on either the link weight or the node attributes. This can be inefficient when you need to find communities that are both weighted and share similar characteristics. To address this, this paper proposes two approaches: Bottom-Up and Top-Down . Both approaches use link weight and node attributes to identify the top-r-weighted and attributed k-core communities, where r denotes the number of top-ranked communities. The Bottom-Up approach utilizes the global search paradigm to find communities, while Top-Down method utilizes a local search to efficiently find the top-weighted and attributed communities. To achieve this efficient local search, the Top-Down method leverages two special indexes: a simple index and a matrix-based index . The study compared all methods with several real-world data sets and found that Top-Down method that leverages matrix-based index was the most effective and efficient.
- 22 December 2025
- Published by Springer Nature in International Journal of Data Science and Analytics
- Vol. 21 (1) , 80
Open AccessDiscovering weighted and attributed communities from social graphs
Community search is currently attracting a lot of attention. The problem of a community search in a node-attributed graph is to locate a meaningful community that satisfies certain query parameters. It has piqued the interest of both industry and academia. Most research on finding communities in graphs focuses on either the link weight or the node attributes. This can be inefficient when you need to find communities that are both weighted and share similar characteristics. To address this, this paper proposes two approaches: Bottom-Up and Top-Down . Both approaches use link weight and node attributes to identify the top-r-weighted and attributed k-core communities, where r denotes the number of top-ranked communities. The Bottom-Up approach utilizes the global search paradigm to find communities, while Top-Down method utilizes a local search to efficiently find the top-weighted and attributed communities. To achieve this efficient local search, the Top-Down method leverages two special indexes: a simple index and a matrix-based index . The study compared all methods with several real-world data sets and found that Top-Down method that leverages matrix-based index was the most effective and efficient.
- Open Access
- 11 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 141694-141716
TSB-Forecast: A Short-Term Load Forecasting Model in Smart Cities for Integrating Time Series Embeddings and Large Language Models
In smart cities, energy management systems are essential for efficient resource utilization, enhanced operational efficiency, and sustainability promotion. This work presents a novel load forecasting model, TSB-Forecast (Time Series BERT), a hybrid machine learning model aiming to improve short-term electrical demand forecasting by integrating structured and unstructured data. The model uses Sentence Bidirectional Encoder Representations from Transformers (SBERT) to extract semantic characteristics from textual news and Time to Vector (Time2Vec) to capture temporal patterns, acquiring cyclical behavior and context-sensitive impacts. TSB-Forecast shows significant improvements reducing MAE by 38.7%, RMSE by 18.2%, and SMAPE by 50.6% compared to several baselines, including the official ENTSO-E forecast, Extra Trees Regressor (ETR), a hybrid model with basic text processing (M6), and a deep learning model combining GRU and CNN (CNN-GRU). TSB-Forecast demonstrates a stronger ability to combine time-related and contextual information, which helps reduce errors. Our contributions in this paper are fourfold and can be summarized as follows: The model initially integrates multi-source inputs, encompassing load demand, BBC News, meteorological data, and holiday information. Secondly, it utilizes Time2Vec and SBERT for improved temporal and semantic feature encoding. Subsequently, Extreme Gradient Boosting (XGBoost) and Extra Trees Regressor (ETR) collectively enhance the robustness of a stacked ensemble. Finally, a thorough empirical analysis showing consistent outperformance of the proposed model over all the forecasting measures against baseline models.
- 11 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 141694-141716
Open AccessTSB-Forecast: A Short-Term Load Forecasting Model in Smart Cities for Integrating Time Series Embeddings and Large Language Models
In smart cities, energy management systems are essential for efficient resource utilization, enhanced operational efficiency, and sustainability promotion. This work presents a novel load forecasting model, TSB-Forecast (Time Series BERT), a hybrid machine learning model aiming to improve short-term electrical demand forecasting by integrating structured and unstructured data. The model uses Sentence Bidirectional Encoder Representations from Transformers (SBERT) to extract semantic characteristics from textual news and Time to Vector (Time2Vec) to capture temporal patterns, acquiring cyclical behavior and context-sensitive impacts. TSB-Forecast shows significant improvements reducing MAE by 38.7%, RMSE by 18.2%, and SMAPE by 50.6% compared to several baselines, including the official ENTSO-E forecast, Extra Trees Regressor (ETR), a hybrid model with basic text processing (M6), and a deep learning model combining GRU and CNN (CNN-GRU). TSB-Forecast demonstrates a stronger ability to combine time-related and contextual information, which helps reduce errors. Our contributions in this paper are fourfold and can be summarized as follows: The model initially integrates multi-source inputs, encompassing load demand, BBC News, meteorological data, and holiday information. Secondly, it utilizes Time2Vec and SBERT for improved temporal and semantic feature encoding. Subsequently, Extreme Gradient Boosting (XGBoost) and Extra Trees Regressor (ETR) collectively enhance the robustness of a stacked ensemble. Finally, a thorough empirical analysis showing consistent outperformance of the proposed model over all the forecasting measures against baseline models.
- Open Access
- 19 February 2025
- Published by MDPI AG in Informatics
- Vol. 12 (1) , 22
Predictive Machine Learning Approaches for Supply and Manufacturing Processes Planning in Mass-Customization Products
Planning in mass-customization supply and manufacturing processes is a complex process that requires continuous planning and optimization to minimize time and cost across a wide variety of choices in large production volumes. While soft computing techniques are widely used for optimizing mass-customization products, they face scalability issues when handling large datasets and rely heavily on manually defined rules, which are prone to errors. In contrast, machine learning techniques offer an opportunity to overcome these challenges by automating rule generation and improving scalability. However, their full potential has yet to be explored. This article proposes a machine learning-based approach to address this challenge, aiming to optimize both the supply and manufacturing planning phases as a practical solution for industry planning or optimization problems. The proposed approach examines supervised machine learning and deep learning techniques for manufacturing time and cost planning in various scenarios of a large-scale real-life pilot study in the bicycle manufacturing domain. This experimentation included K-Nearest Neighbors with regression and Random Forest from the machine learning family, as well as Neural Networks and Ensembles as deep learning approaches. Additionally, Reinforcement Learning was used in scenarios where real-world data or historical experiences were unavailable. The training performance of the pilot study was evaluated using cross-validation along with two statistical analysis methods: the t-test and the Wilcoxon test. These performance evaluation efforts revealed that machine learning techniques outperform deep learning methods and the reinforcement learning approach, with K-NN combined with regression yielding the best results. The proposed approach was validated by industry experts in bicycle manufacturing. It demonstrated up to a 37% reduction in both time and cost for orders compared to traditional expert estimates.
- 19 February 2025
- Published by MDPI AG in Informatics
- Vol. 12 (1) , 22
Open AccessPredictive Machine Learning Approaches for Supply and Manufacturing Processes Planning in Mass-Customization Products
Planning in mass-customization supply and manufacturing processes is a complex process that requires continuous planning and optimization to minimize time and cost across a wide variety of choices in large production volumes. While soft computing techniques are widely used for optimizing mass-customization products, they face scalability issues when handling large datasets and rely heavily on manually defined rules, which are prone to errors. In contrast, machine learning techniques offer an opportunity to overcome these challenges by automating rule generation and improving scalability. However, their full potential has yet to be explored. This article proposes a machine learning-based approach to address this challenge, aiming to optimize both the supply and manufacturing planning phases as a practical solution for industry planning or optimization problems. The proposed approach examines supervised machine learning and deep learning techniques for manufacturing time and cost planning in various scenarios of a large-scale real-life pilot study in the bicycle manufacturing domain. This experimentation included K-Nearest Neighbors with regression and Random Forest from the machine learning family, as well as Neural Networks and Ensembles as deep learning approaches. Additionally, Reinforcement Learning was used in scenarios where real-world data or historical experiences were unavailable. The training performance of the pilot study was evaluated using cross-validation along with two statistical analysis methods: the t-test and the Wilcoxon test. These performance evaluation efforts revealed that machine learning techniques outperform deep learning methods and the reinforcement learning approach, with K-NN combined with regression yielding the best results. The proposed approach was validated by industry experts in bicycle manufacturing. It demonstrated up to a 37% reduction in both time and cost for orders compared to traditional expert estimates.
- Open Access
- 8 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 85154-85169
Future Activities Prediction Framework in Smart Homes Environment
Smart homes have been recently important sources for providing Activity of Daily Living (ADL) data about their residents. ADL data can be a great asset while analyzing residents’ behavior to provide residents with better and optimized services. A popular example is to analyze residents’ behavior to predict their future activities and optimize smart homes performance accordingly. This paper proposes a forecasting framework that utilizes ADL data to predict residents’ next activities in a smart home environment. Forecasting is performed via the conjunction of embedding algorithm to encode the data and Bidirectional Long Short-Term Memory (BiLSTM) deep neural networks to process the data. The proposed framework is evaluated over five real ADL datasets where the experiments show the outperformance of the proposed framework with accuracy scores ranging from 98.7% to 93.8%.
- 8 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 85154-85169
Open AccessFuture Activities Prediction Framework in Smart Homes Environment
Smart homes have been recently important sources for providing Activity of Daily Living (ADL) data about their residents. ADL data can be a great asset while analyzing residents’ behavior to provide residents with better and optimized services. A popular example is to analyze residents’ behavior to predict their future activities and optimize smart homes performance accordingly. This paper proposes a forecasting framework that utilizes ADL data to predict residents’ next activities in a smart home environment. Forecasting is performed via the conjunction of embedding algorithm to encode the data and Bidirectional Long Short-Term Memory (BiLSTM) deep neural networks to process the data. The proposed framework is evaluated over five real ADL datasets where the experiments show the outperformance of the proposed framework with accuracy scores ranging from 98.7% to 93.8%.
- Open Access
- 14 July 2018
- Published by Academy and Industry Research Collaboration Center (AIRCC)
- p. 49-57
Skyline Query Processing in Graph Databases
- 14 July 2018
- Published by Academy and Industry Research Collaboration Center (AIRCC)
- p. 49-57
Open AccessSkyline Query Processing in Graph Databases
- Open Access
- 3 April 2017
- Published by Association for Computing Machinery (ACM)
- p. 1674-1678
Text-based question routing for question answering communities via deep learning
Online Communities for Question Answering (CQA) such as Quora and Stack Overflow face the challenge of providing sufficient answers for the questions asked by users. The exponential growing rate of the unanswered questions compromises the effectiveness of the CQA frameworks as knowledge sharing platforms. The main reason for this issue is the inefficient routing of the questions to the potential answerers, who are the field experts and interested users. This paper proposes the deep-learning-based technique QR-DSSM to increase the accuracy of the question routing process. This technique uses deep semantic similarity model (DSSM) to extract semantic similarity features using deep neural networks and use the features to rank users' profiles. QR-DSSM maps the asked questions and the profiles of the users into a latent semantic space where the ability to answer is measured using the cosine similarity between the questions and the profiles of the users. QR-DSSM experiments outperformed the baseline models such as LDA, SVM, and Rank-SVM techniques and achieved an MRR score of 0.1737.
- 3 April 2017
- Published by Association for Computing Machinery (ACM)
- p. 1674-1678
Open AccessText-based question routing for question answering communities via deep learning
Online Communities for Question Answering (CQA) such as Quora and Stack Overflow face the challenge of providing sufficient answers for the questions asked by users. The exponential growing rate of the unanswered questions compromises the effectiveness of the CQA frameworks as knowledge sharing platforms. The main reason for this issue is the inefficient routing of the questions to the potential answerers, who are the field experts and interested users. This paper proposes the deep-learning-based technique QR-DSSM to increase the accuracy of the question routing process. This technique uses deep semantic similarity model (DSSM) to extract semantic similarity features using deep neural networks and use the features to rank users' profiles. QR-DSSM maps the asked questions and the profiles of the users into a latent semantic space where the ability to answer is measured using the cosine similarity between the questions and the profiles of the users. QR-DSSM experiments outperformed the baseline models such as LDA, SVM, and Rank-SVM techniques and achieved an MRR score of 0.1737.
- 1 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Semi-supervised outlier detection via bipartite graph clustering
A considerable amount of attributes in real datasets are not numerical, but rather textual and categorical. We investigate the problem of identifying outliers in categorical and textual datasets. We propose a clustering-based semi-supervised outlier detection method which basically represents normal and unlabeled data points as a bipartite graph. We leverage the existing free of parameters clustering techniques to cluster the resulting graph. The bipartite graph is clustered with a specific end goal to distinguish unlabeled data points as either outliers or normal data points. The proposed method is evaluated using multiple categorical and textual datasets against one-class support vector machines classifier and FRaC approach for semi-supervised outlier detection where the proposed method has shown a comparable performance.
- 1 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Semi-supervised outlier detection via bipartite graph clustering
A considerable amount of attributes in real datasets are not numerical, but rather textual and categorical. We investigate the problem of identifying outliers in categorical and textual datasets. We propose a clustering-based semi-supervised outlier detection method which basically represents normal and unlabeled data points as a bipartite graph. We leverage the existing free of parameters clustering techniques to cluster the resulting graph. The bipartite graph is clustered with a specific end goal to distinguish unlabeled data points as either outliers or normal data points. The proposed method is evaluated using multiple categorical and textual datasets against one-class support vector machines classifier and FRaC approach for semi-supervised outlier detection where the proposed method has shown a comparable performance.
- Open Access
- 1 January 2016
- Published by Association for Computing Machinery (ACM)
- p. 328-333
SCI-F
Opinions are considered a powerful source of market research. Social networks are the most popular mean for people to state their opinions about products and services. Companies invest in analysing their customers' opinions from multiple existing social media platforms. The knowledge extracted from social media contains sentiment data that is not included in corporate database. This extracted data can be used to improve marketing campaigns to better retain customers and meet their needs. The integration between both social media data and corporate data can lead to better insights that would not have been possible to gain without such integration. This paper proposes a framework to integrate sentiment data, extracted from customers' opinions with corporate data of an organization. The process of integrating opinions streams into corporate database is proposed, then a multidimensional data warehouse is built over the integrated database to perform advanced analytical tasks and answer queries that would not have been possible without the integration. The new framework has been experimented with a case study of integrating opinions about digital devices and corporate data to illustrate the usage of the integrated model.
- 1 January 2016
- Published by Association for Computing Machinery (ACM)
- p. 328-333
Open AccessSCI-F
Opinions are considered a powerful source of market research. Social networks are the most popular mean for people to state their opinions about products and services. Companies invest in analysing their customers' opinions from multiple existing social media platforms. The knowledge extracted from social media contains sentiment data that is not included in corporate database. This extracted data can be used to improve marketing campaigns to better retain customers and meet their needs. The integration between both social media data and corporate data can lead to better insights that would not have been possible to gain without such integration. This paper proposes a framework to integrate sentiment data, extracted from customers' opinions with corporate data of an organization. The process of integrating opinions streams into corporate database is proposed, then a multidimensional data warehouse is built over the integrated database to perform advanced analytical tasks and answer queries that would not have been possible without the integration. The new framework has been experimented with a case study of integrating opinions about digital devices and corporate data to illustrate the usage of the integrated model.
- 1 October 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2174-2179
Sentiment Analysis over Social Networks: An Overview
The rapid increase in data on social media creates a need for mining such data to get valuable insights. The data type can be unstructured with large volumes. Sentiment analysis addresses such need by detecting opinions or emotions on the social media text. Sentiment analysis can be performed in various domains such as social, medical and industrial applications. This paper presents a survey about sentiment analysis addressing the different concepts in this area, problems and its solutions, available APIs, tools used and presenting a list of open challenges in this area.
- 1 October 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2174-2179
Sentiment Analysis over Social Networks: An Overview
The rapid increase in data on social media creates a need for mining such data to get valuable insights. The data type can be unstructured with large volumes. Sentiment analysis addresses such need by detecting opinions or emotions on the social media text. Sentiment analysis can be performed in various domains such as social, medical and industrial applications. This paper presents a survey about sentiment analysis addressing the different concepts in this area, problems and its solutions, available APIs, tools used and presenting a list of open challenges in this area.