Using Depth Cameras to Detect Patterns in Oral Presentations: A Case Study Comparing Two Generations of Computer Engineering Students

Abstract

Speaking and presenting in public are critical skills for academic and professional development. These skills are demanded across society, and their development and evaluation are a challenge faced by higher education institutions. There are some challenges to evaluate objectively, as well as to generate valuable information to professors and appropriate feedback to students. In this paper, in order to understand and detect patterns in oral student presentations, we collected data from 222 Computer Engineering (CE) fresh students at three different times, over two different years (2017 and 2018). For each presentation, using a developed system and Microsoft Kinect, we have detected 12 features related to corporal postures and oral speaking. These features were used as input for the clustering and statistical analysis that allowed for identifying three different clusters in the presentations of both years, with stronger patterns in the presentations of the year 2017. A Wilcoxon rank-sum test allowed us to evaluate the evolution of the presentations attributes over each year and pointed out a convergence in terms of the reduction of the number of features statistically different between presentations given at the same course time. The results can further help to give students automatic feedback in terms of their postures and speech throughout the presentations and may serve as baseline information for future comparisons with presentations from students coming from different undergraduate courses.

Sensor, Wearable, and Remote Patient Monitoring Competencies for Clinical Care and Training: Scoping Review

“…Learning analytics can be applied to cluster, depict, and process data to support a number of objectives (González-Crespo and Burgos 2019 ), since teachers need to reshape the course plan for different learners (e.g., styles, motivation, performance) and integrate that information with real-time analytical information to supervise, assess, adapt, and offer feedback. Sensors and wearables can be applied to a wide range of educational contexts, including but not limited to: learning management systems (LMS) or content management systems (CMS) that process user data collected studying relationships between type of device from which users access LMS and how it affects performance live or virtual reality (VR)-based sessions with teams or patients so oral and body language skills are shaped and improved game-based learning with virtual/augmented reality to improve procedures recommendations to users (e.g., explore impact of order given, behavioral response, impact of choices on engagement via algorithm) (Baldominos and Quintana 2019 ; Roque et al 2019 ) …”

Where are You? Exploring Micro-Location in Indoor Learning Environments

“…In accordance with the above, MMLA deals with data gathered from non-traditional sources through different sensors and systems, which can be collected from different and diverse learning settings (e.g. individual, collaborative, formal, informal, professional) and may consist of a myriad types and combinations, such as: facial expressions [24], gestures [25], movements [2], talking [9], vision [26] and heartbeats [27], among others [28]. Furthermore, professional competencies are the ultimate way of applying knowledge and skills at workplace environments, normally involving collaborative activities.…”

“…In education, integrating technologies to improve the quality of learning represents a growing challenge. In fact, different technological tools are being developed for this purpose [1], [2]. The use of devices in the classroom provides quantitative information to teachers about how the teaching-learning process is being developed [3].…”

Advanced Sensors Technology in Education

“…Speaking and presenting in public are critical skills for academic and professional development. In paper [11], Roque et al collect data from 222 Computer Engineering (CE) undergraduate students at three different times, over two different years. Regarding each presentation, using a developed system and Microsoft Kinect, they detect 12 features related to corporal postures and oral speaking.…”