Seifeldeen Eteifa

Dr. Seifeldeen Eteifa


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2018 in Journal of Management in Engineering
Verified
Journal Article
Closed access
SESeifeldeen Eteifa
Seifeldeen Eteifa
Islam H. El-adawayIslam H. El-adaway
Islam H. El-adaway
Fatal accident rates in the U.S. construction industry trail behind other developed countries. Previous research investigated accident causation, but no studies focused on the relationship among root causes for construction fatalities. This research aims to analyze the interaction between fatal accident root causes and their relationship to commonly quoted direct causes using social network analysis (SNA). SNA is an analytical technique evolving from graph theory used in multiple fields including social sciences, natural sciences, construction management, and safety. To achieve this goal, a three-step methodology is devised. First, data about accident causation was extracted from 100 case files. Second, an SNA model was developed and performed at an aggregate level analyzing the fatalities causation network as a whole, as well as at a disaggregate level to pinpoint root causes of the fatal four accident direct causes. Third, the results of the model are interpreted and validated to draw conclusions about accident causation and underlying factors leading to fatalities. The model successfully identified the key root causes of construction fatalities and the interrelationships among them. For example, it indicated that lack of job-specific training is the most central cause of “struck by,” and “caught in between” accidents. It also indicated that the absence of fall arrest systems, lack of jobsite training, and lack of personal protective equipment are the most interrelated root causes. This research should reshape the current approach to fatal accident causation by creating a more holistic understanding of root causes for construction fatalities and how they interact together.

1 August 2017 in Journal of Legal Affairs and Dispute Resolution in Engineering and Construction
Verified
Journal Article
Closed access
Islam H. El-adawayIslam H. El-adaway
Islam H. El-adaway
IAIbrahim Abotaleb
Ibrahim Abotaleb
SESeifeldeen Eteifa
Seifeldeen Eteifa
A framework for multi-party relational contracting is proposed whereby the owner, contractor, suppliers, and manufacturers collaboratively work together under similar terms and conditions. The proposed framework improves and fills the voids in the already available Integrated Project Delivery (IPD) agreements. To this end, a four-step research methodology was utilized. First, a comparative analysis between available traditional and relational contract agreements was provided. Second, the available standard integrated project delivery contracts in the United States and the standard partnering contracts in the United Kingdom were reviewed. Third, practical case studies in the US market were reviewed and analyzed for lessons learned. Fourth, the proposed framework was developed to address ten critical interrelated aspects including: project environment, project management, partnering advisor, design process, partnering and project schedules, suppliers and manufacturers, prices and profits, incentives, changes, and conflicts and disputes. This study paves the ground for a more efficient and effective contracting environment that can hopefully recover communication, encourage cooperation, share risk, improve quality, decrease cost, minimize waste, maximize efficiency, and mitigate conflicts. The proposed framework should be formally drafted by legal professionals to allow piloting and testing on actual case study projects. While this research is applied within the framework of the U.S. market, its results and associated discussions and analyses are transferrable and implementable in other contracting environments.

7 March 2025 in Sensors
Verified
Journal Article
Open access
PDF file
SESeifeldeen Eteifa
Seifeldeen Eteifa
ASAmr Shafik
Amr Shafik
HEHoda Eldardiry
Hoda Eldardiry
Hesham RakhaHesham Rakha
Hesham Rakha
Predicting Signal Phase and Timing (SPaT) information and confidence levels is needed to enhance Green Light Optimal Speed Advisory (GLOSA) and/or Eco-Cooperative Adaptive Cruise Control (Eco-CACC) systems. This study proposes an architecture based on transformer encoders to improve prediction performance. This architecture is combined with different deep learning methods, including Multilayer Perceptrons (MLP), Long-Short-Term Memory neural networks (LSTM), and Convolutional Long-Short-Term Memory neural networks (CNNLSTM) to form an ensemble of predictors. The ensemble is used to make data-driven predictions of SPaT information obtained from traffic signal controllers for six different intersections along the Gallows Road corridor in Virginia. The study outlines three primary tasks. Task one is predicting whether a phase would change within 20 s. Task two is predicting the exact change time within 20 s. Task three is assigning a confidence level to that prediction. The experiments show that the proposed transformer-based architecture outperforms all the previously used deep learning methods for the first two prediction tasks. Specifically, for the first task, the transformer encoder model provides an average accuracy of 96%. For task two, the transformer encoder models provided an average mean absolute error (MAE) of 1.49 s, compared to 1.63 s for other models. Consensus between models is shown to be a good leading indicator of confidence in ensemble predictions. The ensemble predictions with the highest level of consensus are within one second of the true value for 90.2% of the time as opposed to those with the lowest confidence level, which are within one second for only 68.4% of the time.

29 March 2018
Verified
Conference Paper
Closed access
Islam H. El-adawayIslam H. El-adaway
Islam H. El-adaway
IAIbrahim Abotaleb
Ibrahim Abotaleb
SESeifeldeen Eteifa
Seifeldeen Eteifa
Previous studies have shown the potential of integrated project delivery (IPD). They demonstrated its superiority to other delivery methods in terms of exhibiting enhanced productivity, cost, schedule, quality, and risk performances. It achieves so through cooperative collaboration, open information sharing, risk and reward sharing, and early involvement. Yet, voids have been identified in current IPD agreements that hinder them from attaining their full potential. This research proposes a contractual framework that fills these voids by utilizing the lessons learned from prior IPD projects and building on the strengths of relevant partnering contracts from the United Kingdom (U.K). In other words, this research presents a relational contract framework that integrates the strengths of the U.S. IPD with the U.K. partnering agreements. A three-step methodology was utilized. First, the authors reviewed the available standard forms of IPD and partnering contracts in the U.S. and the U.K. markets. Second, the authors investigated past IPD projects to analyze their faced contract-based problems and lessons learned. Third, the authors developed a contractual framework that addresses the critical contractual aspects. The developed framework should be useful to contract drafters as it promotes a more efficient and effective contracting environment throughout improved cooperation, risk sharing, incentives, and conflict mitigation. The authors encourage legal professionals to utilize the proposed framework in the process of updating and further enhancing the IPD standard forms of contract.

16 January 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
SESeifeldeen Eteifa
Seifeldeen Eteifa
ASAmr Shafik
Amr Shafik
HEHoda Eldardiry
Hoda Eldardiry
Hesham RakhaHesham Rakha
Hesham Rakha
Predicting Signal Phase and Timing (SPaT) information and confidence levels is needed to enhance green light optimal speed advisory (GLOSA) and/or Eco-Cooperative Adaptive Cruise Control (Eco-CACC) systems. This study proposes an architecture based on transformer encoders to improve prediction performance. This architecture is combined with different deep learning methods, including Multilayer Perceptrons (MLP), Long-Short-Term Memory neural networks (LSTM), and Convolutional Long-Short Term Memory neural networks (CNNLSTM) to form an ensemble of predictors. The ensemble is used to make data-driven predictions of SPaT information for six different intersections along the Gallows Road corridor in Virginia. The study outlines three primary tasks. Task one is predicting whether a phase would change within 20 seconds. Task two is predicting the exact change time within 20 seconds. Task three is assigning a confidence level to that prediction. The experiments show that the proposed transformer-based architecture outperforms all the previously used deep learning methods for the first two prediction tasks. For the first task, the transformer encoder model provides an average accuracy of 96%. For task two, the transformer encoder models provided an average mean absolute error (MAE) of 1.49 seconds, compared to 1.63 seconds for other models. Consensus between models is shown to be a good leading indicator of confidence in ensemble predictions. The ensemble predictions with the highest level of consensus are within one second of the true value for 90.2% of the time as opposed to those with the lowest confidence level, which are within one second for only 68.4% of the time.

10 August 2020 in arXiv
Verified
Preprint
Open access
PDF file
SESeifeldeen Eteifa
Seifeldeen Eteifa
Hesham RakhaHesham Rakha
Hesham Rakha
HEHoda Eldardiry
Hoda Eldardiry
Vehicle acceleration and deceleration maneuvers at traffic signals results in significant fuel and energy consumption levels. Green light optimal speed advisory systems require reliable estimates of signal switching times to improve vehicle fuel efficiency. Obtaining these estimates is difficult for actuated signals where the length of each green indication changes to accommodate varying traffic conditions. This study details a four-step Long Short-Term Memory deep learning-based methodology that can be used to provide reasonable switching time estimates from green to red and vice versa while being robust to missing data. The four steps are data gathering, data preparation, machine learning model tuning, and model testing and evaluation. The input to the models included controller logic, signal timing parameters, time of day, traffic state from detectors, vehicle actuation data, and pedestrian actuation data. The methodology is applied and evaluated on data from an intersection in Northern Virginia. A comparative analysis is conducted between different loss functions including the mean squared error, mean absolute error, and mean relative error used in LSTM and a new loss function is proposed. The results show that while the proposed loss function outperforms conventional loss functions in terms of overall absolute error values, the choice of the loss function is dependent on the prediction horizon. In particular, the proposed loss function is outperformed by the mean relative error for very short prediction horizons and mean squared error for very long prediction horizons.