An official website of the United States government
Classification of construction resource states, using sensor data analytics, has implications for improving informed decision-making for safety and productivity. However, training on sensor data analytics in construction education faces challenges owing to the complexity of analytical processes and the large stream of raw data involved. This research presents the development and user evaluation of ActionSens, a block-based end-user programming platform, for training students from construction-related disciplines to classify resources using sensor data analytics. ActionSens was designed for construction students to perform sensor data analytics such as activity recognition in construction. ActionSens was compared to traditional tools (i.e., combining Excel and MATLAB) used for performing sensor data analytics in terms of usability, workload, visual attention, and processing time using the System Usability Scale, NASA Task Load Index, eye-tracking, and qualitative feedback. Twenty students participated, performing data analytics tasks with both approaches. ActionSens exhibited a better user experience compared to conventional platforms, through higher usability scores and lower cognitive workload. This was evident through participants' interaction behavior, showcasing optimized attentional resource allocation across key tasks. The study contributes to knowledge by illustrating how the integration of construction domain information into block-based programming environments can equip students with the necessary skills for sensor data analytics. The development of ActionSens contributes to the Learning-for-Use framework by employing graphical and interactive programming objects to foster procedural knowledge for addressing challenges in sensor data analytics. The formative evaluation provides insights into how students engage with the programming environment and assesses the impact of the environment on their cognitive load.
more »
« less
Automated Gaze Recognition within a Block-based Sensor Data Analytics Platform for Construction Students
The construction industry is increasingly harnessing sensing technologies to overcome manual data collection limitations and address the need for advanced data analysis. This places an aggravated demand for associated skills to interpret sensor data. Yet, a substantial gap exists between the level of academic preparation and the actual needs of the industry, leading to an underprepared workforce. In this study, ActionSens, a Block-Based Programming Environment, is implemented as an educational tool that combines sensor data from Inertial Measurement Units with machine learning algorithms. This integration enables the classification of construction activities, offering construction students a platform to explore and learn about sensor data analytics. However, in a pedagogical setting, an enhanced learning experience can be achieved through the integration of automated classification models that intelligently detect learners’ focus with the potential to provide context-specific support. This study utilizes 19 construction students’ eye-tracking data to train and evaluate machine learning models to detect learners’ visual focus on specific Areas of Interest within ActionSens. Ensemble, Neural Network, and K-Nearest Neighbor performed the best for both raw and SMOTE-oversampled datasets. The Ensemble had an edge in recognizing Areas of Interest, achieving top precision, recall, F1-score, and AUC in the oversampled data.
more »
« less
- Award ID(s):
- 2111045
- PAR ID:
- 10534756
- Publisher / Repository:
- Associated Schools of Construction
- Date Published:
- Volume:
- 5
- Page Range / eLocation ID:
- 175 to 183
- Format(s):
- Medium: X
- Location:
- Auburn, AL
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
This study explores the use of Large Language Models (LLMs), specifically GPT, for different safety management applications in the construction industry. Many studies have explored the integration of GPT in construction safety for various applications; their primary focus has been on the feasibility of such integration, often using GPT models for specific applications rather than a thorough evaluation of GPT’s limitations and capabilities. In contrast, this study aims to provide a comprehensive assessment of GPT’s performance based on established key criteria. Using structured use cases, this study explores GPT’s strength and weaknesses in four construction safety areas: (1) delivering personalized safety training and educational content tailored to individual learner needs; (2) automatically analyzing post-accident reports to identify root causes and suggest preventive measures; (3) generating customized safety guidelines and checklists to support site compliance; and (4) providing real-time assistance for managing daily safety tasks and decision-making on construction sites. LLMs and NLP have already been employed in each of these four areas for improvement, making them suitable areas for further investigation. GPT demonstrated acceptable performance in delivering evidence-based, regulation-aligned responses, making it valuable for scaling personalized training, automating accident analyses, and developing safety protocols. Additionally, it provided real-time safety support through interactive dialogues. However, the model showed limitations in deeper critical analysis, extrapolating information, and adapting to dynamic environments. The study concludes that while GPT holds significant promise for enhancing construction safety, further refinement is necessary. This includes fine-tuning for more relevant safety-specific outcomes, integrating real-time data for contextual awareness, and developing a nuanced understanding of safety risks. These improvements, coupled with human oversight, could make GPT a robust tool for safety management.more » « less
-
Data analytics and computational thinking are essential for processing and analyzing data from sensors, and presenting the results in formats suitable for decision-making. However, most undergraduate construction engineering and management students struggle with understanding the required computational concepts and workflows because they lack the theoretical foundations. This has resulted in a shortage of skilled workforce equipped with the required competencies for developing sustainable solutions with sensor data. End-user programming environments present students with a means to execute complex analysis by employing visual programming mechanics. With end-user programming, students can easily formulate problems, logically organize, analyze sensor data, represent data through abstractions, and adapt the results to a wide variety of problems. This paper presents a conceptual system based on end-user programming and grounded in the Learning-for-Use theory which can equip construction engineering and management students with the competencies needed to implement sensor data analytics in the construction industry. The system allows students to specify algorithms by directly interacting with data and objects to analyze sensor data and generate information to support decision-making in construction projects. An envisioned scenario is presented to demonstrate the potential of the system in advancing students’ data analytics and computational thinking skills. The study contributes to existing knowledge in the application of computational thinking and data analytics paradigms in construction engineering education.more » « less
-
Grewe, Lynne L.; Blasch, Erik P.; Kadar, Ivan (Ed.)Sensor fusion combines data from a suite of sensors into an integrated solution that represents the target environment more accurately than that produced by individual sensors. New developments in Machine Learning (ML) algorithms are leading to increased accuracy, precision, and reliability in sensor fusion performance. However, these increases are accompanied by increases in system costs. Aircraft sensor systems have limited computing, storage, and bandwidth resources, which must balance monetary, computational, and throughput costs, sensor fusion performance, aircraft safety, data security, robustness, and modularity system objectives while meeting strict timing requirements. Performing trade studies of these system objectives should come before incorporating new ML models into the sensor fusion software. A scalable and automated solution is needed to quickly analyze the effects on the system’s objectives of providing additional resources to the new inference models. Given that model-based systems engineering (MBSE) is a focus of the majority of the aerospace industry for designing aircraft mission systems, it follows that leveraging these system models can provide scalability to the system analyses needed. This paper proposes adding empirically derived sensor fusion RNN performance and cost measurement data to machine-readable Model Cards. Furthermore, this paper proposes a scalable and automated sensor fusion system analysis process for ingesting SysML system model information and RNN Model Cards for system analyses. The value of this process is the integration of data analysis and system design that enables rapid enhancements of sensor system development.more » « less
-
This study uses a data-driven approach to address the complexities associated with research focused multi-sleeve Cone Penetration Test (CPT) devices, particularly focusing on the multi-friction attachment (MFA) and multi-piezo-friction attachment (MPFA) CPT devices. Hindered by time-consuming assembly and susceptibility to sensor stream losses due to extensive electronic components, these advanced devices demand optimization to transform from research devices to practice-suitable devices. This study aims at optimizing the design of the multi-sleeve CPT devices using machine learning, with soil type classification performance as the primary metric for device configuration effectiveness. The research scope centers not on using machine learning for soil classification but on refining the design of multi-sleeve CPT devices. A two-phase data-driven approach is adopted, testing various feature combinations across eight machine learning models. The first phase involves identifying the most suitable model for the dataset, followed by a refinement of features to balance sensor number minimization and soil classification accuracy. The result is a proposed configuration for a multi-sleeve CPT device, simplifying the original design while maintaining robustness, thereby enhancing cost-efficiency and operational effectiveness in geotechnical practice. This work sheds light on how the integration of machine learning can guide the design optimization of geotechnical instruments.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.29007/98tm
