Search for: All records

The construction industry's shift to data-driven project management has led to the increasing adoption of various sensing technologies. The transition triggers a demand for a workforce skilled in both the technical and analytical aspects of these tools. While sensing technologies and data analytics can support construction processes, the inherent complexity of sensor data processing often exceeds the skill sets of the graduating workforce. Further, integrating sensor-based applications into construction curricula lacks evidence to support effectiveness in training future professionals. Computational thinking-supported data practices can allow construction students to perform sensor data analytics, spanning from data generation to visualization. This pilot study utilizes InerSens, a block programming interface, as a pedagogical tool to develop construction students’ computational thinking through sensor-based ergonomic risk assessment. Twenty-six undergraduate students were engaged in instructional units using wearable sensors, data, and InerSens. The effectiveness of the approach was evaluated by examining students' perceived self-efficacy in sensor data analytics skills, task performance and reflections, and technology acceptance. Results show gains in self-efficacy, positive technology acceptance, and satisfactory performance on course assignments. The study contributes to the Learning-for-Use, constructivism, and constructionism frameworks by integrating computational thinking into graphical and interactive programming objects to develop procedural knowledge and by summatively assessing how construction students learn to address challenges with sensor data analytics. 

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. 

With rising interest in innovative construction methodologies, global construction companies are actively exploring emerging sensing technologies and employing data analytics techniques to draw insights and improve their operations. While numerous educational disciplines employ Block-based Programming Interfaces to enhance domain-specific data-related inquiry and visualization skills, the construction sector has yet to fully explore this practical approach. Introducing block interfaces in construction education may overwhelm newcomers with excessive cognitive load. Past research has primarily relied on subjective measures, overlooking objective indicators for assessing cognitive responses to block interfaces’ interaction elements. This study evaluates the cognitive load induced using InerSens, a Block Programming Interface designed to address authentic construction challenges in ergonomic risk assessment. Electroencephalography is utilized to measure cognitive load, and the results are compared to those of a traditional tool, Excel. Theta Power Spectral Density in the frontal brain region, an indicator of cognitive load, demonstrates that in four out of six tasks, InerSens incurs lower cognitive load than Excel. The findings of this study underscore the potential of InerSens as a viable tool in managing cognitive load efficiency, paving the way for more effective and streamlined sensor data analytics learning experiences for future construction professionals. 

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.