Amir H. Behzadan

Amir H. Behzadan

Auto-generated profile, based on publicly available information

Amir H. Behzadan

Department of Construction Science, Texas A&M University, College Station, TX, USA

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

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

Representative Publications

View All Publications
14 August 2020 in Frontiers in Built Environment
Verified
Journal Article
Open access
PDF file
NNNipun D. Nath
Nipun D. Nath
ABAmir H. Behzadan
Amir H. Behzadan
Sensing and reality capture devices are widely used in construction sites. Among different technologies, vision-based sensors are by far the most common and ubiquitous. A large volume of images and videos is collected from construction projects every day to track work progress, measure productivity, litigate claims, and monitor safety compliance. Manual interpretation of such colossal amounts of data, however, is non-trivial, error-prone, and resource-intensive. This has motivated new research on soft computing methods that utilize high-power data processing, computer vision, and deep learning (DL) in the form of convolutional neural networks (CNNs). A fundamental step toward machine-driven interpretation of construction site scenery is to accurately identify objects of interest for a particular problem. The accuracy requirement, however, may offset the computational speed of the candidate method. While lightweight DL algorithms (e.g., Mask R-CNN) can perform visual recognition with relatively high accuracy, they suffer from low processing efficacy, which hinders their use in real-time decision-making. One of the most promising DL algorithms that balance speed and accuracy is YOLO (you-only-look-once). This paper investigates YOLO-based CNN models in fast detection of construction objects. First, a large-scale image dataset, named Pictor-v2, is created, which contains about 3,500 images and approximately 11,500 instances of common construction site objects (e.g., building, equipment, worker). To assess the agility of object detection, transfer learning is used to train two variations of this model, namely, YOLO-v2 and YOLO-v3, and test them on different data combinations (crowdsourced, web-mined, or both). Results indicate that performance is higher if the model is trained on both crowdsourced and web-mined images. Additionally, YOLO-v3 outperforms YOLO-v2 by focusing on smaller, harder-to-detect objects. The best-performing YOLO-v3 model has a 78.2% mAP when tested on crowdsourced data. Sensitivity analysis of the output shows that the model's strong suit is in detecting larger objects in less crowded and well-lit spaces. The proposed methodology can also be extended to predict the relative distance of the detected objects with reliable accuracy. Findings of this work lay the foundation for further research on technology-assistive systems to augment human capacities in quickly and reliably interpreting visual data in complex environments.

1 November 2013 in Journal of Construction Engineering and Management
Verified
Journal Article
Closed access
Reza AkhavianReza Akhavian
Reza Akhavian
ABAmir H. Behzadan
Amir H. Behzadan
In order to develop a realistic simulation model, it is critical to provide the model with factual input data based on the interactions and events that take place between real entities. However, the existing trend in simulation of construction fleet activities is based on estimating input parameters such as activity durations using expert judgments and assumptions. Not only may such estimations not be precise, but project dynamics can influence model parameters beyond expectation. Therefore, the simulation model may not be a proper and reliable representation of the real engineering system. In order to alleviate these issues and improve the current practice of construction simulation, a thorough approach is needed that enables the integration of field data into simulation modeling and systematic refinement of the resulting models. This paper describes the latest efforts by authors to design and test a novel methodology for multimodal-process data capturing, fusion, and mining that provides a solid...

30 December 2020 in IEEE Transactions on Affective Computing
Verified
Journal Article
Closed access
MYMegha Yadav
Megha Yadav
NSNazmus Sakib
Nazmus Sakib
ENEhsanul Haque Nirjhar
Ehsanul Haque Nirjhar
KFKexin Feng
Kexin Feng
ABAmir H. Behzadan
Amir H. Behzadan
TCTheodora Chaspari
Theodora Chaspari
Public speaking is a vital skill for making good impressions, effectively exchanging ideas, and influencing others. Yet, public speaking anxiety (PSA) ranks as a top social phobia. Recent advancements in wearable devices and ubiquitous virtual reality (VR) interfaces can help measure and mitigate PSA. This research quantifies PSA through bio-behavioral markers related to individuals' physiological and acoustic characteristics. The effect of virtual reality (VR) training on alleviating PSA is measured through self-reported and bio-behavioral indices. Psychological (e.g., general trait anxiety, personality) and demographic (e.g., age, gender, highest education, native language) traits are examined as moderating factors between bio-behavioral indices and PSA, as well as moderating factors for measuring the VR effectiveness in mitigating PSA. These measures are also used as clustering criteria for stratifying participants in group-based models of PSA. Results indicate the significance of such traits to modeling PSA with the proposed group-based models yielding Spearman's correlation of 0:55 ( $p \lt 0:05$ ) between the actual and predicted outcome. Results further demonstrate that systematic exposure to public speaking in VR can alleviate PSA in terms of both self-reported ( $p \lt 0:05$ ) and physiological ( $p \lt 0:05$ ) indices. Findings from this study will enable researchers to better understand antecedents and causes of PSA and lay the foundation for personalized adaptive feedback for PSA interventions.

1 November 2021 in Environmental Pollution
Verified
Journal Article
Closed access
ZGZahra Ghorbani
Zahra Ghorbani
ABAmir H. Behzadan
Amir H. Behzadan

9 October 2018 in International Journal of Construction Education and Research
Verified
Journal Article
Closed access
SVShahin Vassigh
Shahin Vassigh
DDDebra Davis
Debra Davis
ABAmir H. Behzadan
Amir H. Behzadan
AMAli Mostafavi
Ali Mostafavi
KRKhandakar Rashid
Khandakar Rashid
GGGiovanna Gallardo
Giovanna Gallardo
Immersive technologies are transforming all aspects of daily life. In educational context, augmented reality (AR) and virtual reality (VR) offer the promise of experiential learning, where the real world is enhanced with information and graphics or is completely simulated. The project described in this paper, builds on advances of these technologies to develop, implement, and test “Skope,” a prototype immersive learning environment. Skope is designed to facilitate interdisciplinary education of architecture, engineering, and construction (AEC) students for design and construction of environmentally sustainable buildings. The Skope learning environment is comprised of an AR and a VR visualization tool as well as learning modules that contain interdisciplinary content. Skope is implemented and tested in three interdisciplinary AEC classes. Quantitative and qualitative analyses of student performance in these classes suggest that Skope has a positive impact and increased students’ motivation and understanding of building science principles, ultimately leading to an improvement of learning across domains. In addition, findings of this research indicate that using Skope improves students’ attitude toward collaborative learning.

1 November 2009 in Journal of Computing in Civil Engineering
Verified
Journal Article
Closed access
ABAmir H. Behzadan
Amir H. Behzadan
VKVineet Kamat
Vineet Kamat
Three-dimensional (3D) visualization is an effective tool for communicating, verifying, and validating the results of a simulated operation. Traditional visualization tools used for this purpose are typically based on the paradigm of virtual reality. Augmented reality (AR) is a relatively newer visualization paradigm whose engineering applications have been explored by a limited number of researchers. In this paper, the problem of generating smooth and continuous AR animations from the results of running discrete event simulation models and a general purpose methodology to overcome this challenge are discussed. The structure of an AR animation authoring language developed by the writers to create a logical link between a running simulation model and its corresponding 3D visualization in AR is described. In order to validate the functionality and effectiveness of the designed methods and animation language, an AR-based visualization application was developed and the designed algorithms were successfully tested using different simulation scenarios of varying visual and operational complexity.