No abstract

Mass collaboration efforts can increase innovation and design possibilities. Incorporation of open innovation into the product development process allows for a vast array of unique perspectives and ideas. However, with the broad expansion of design possibilities, coordination of these development processes is paramount. To best make use of open innovation in product development, increased organizational efforts must be considered. The mass collaboration of individuals must account for individual intellectual abilities (competencies), working experience and even personality traits or idiosyncrasies. Approaches to this problem require the fusion of social network analysis with quantifiable design impacts. This work proposes a simulation framework that evaluates the design potential of a project team based on individual attributes and the team network structure. The overall contribution of this work comes from the exploration of team structure, focusing on network composition metrics such as centrality and network density, while attempting to understand the role of individual ability and positioning on the success of the design process. This work aims to garner a more thorough understanding of how the network structure of design teams correlates with their potential performance through a generalized simulation framework, applicable to future crowd and design initiatives.

No abstract

Product development is a key component of engineering education taught at a number of universities through their capstone design course. This course provides students with an opportunity to apply their newly obtained knowledge in engineering to design, build, and test working prototypes. This educational approach also encourages students to place additional attention on time and group management. As students walk through the design process, their focus fluctuates between group organization, product development, and course deliverables. This paper observes this variation in focus to extract key insights related to who is focusing on what and when. Data was collected in the form of individual project journals for each student and these provide a detailed look into the design activities throughout the semester allowing for a focus mapping from week to week. The focus of each student is quantified by a topic distribution of each student’s weekly journal entries, automatically extracted using Latent Dirichlet Allocation. Our results place emphasis on the topic identification accuracy and interpretation, before identifying trends found that separate high performing students and groups from those with poor performances. It was found that efficient time management focusing on the required course deliverables, and group cohesion led to the most impactful performance variations. Using this knowledge, we identify future directions supporting the pedagogy for capstone projects.

Increasingly complex engineering design challenges requires the diversification of knowledge required on design teams. In the context of open innovation, positioning key members within these teams or groups based on their estimated abilities leads to more impactful results since mass collaboration is fundamentally a sociotechnical system. Determining how each individual influences the overall design process requires an understanding of the predicted mapping between their technical competency and performance. This work explores this relationship through the use of predictive models composed of various regression algorithms. With support of a dataset composed of documents related to the design performance of students working on their capstone design project in combination with textual descriptors representing individual technical aptitudes, correlations are explored as a method to predict overall project development performance. Each technical competency and project is represented as a distribution of topic knowledge to produce the performance metrics, that are referred to as topic competencies, since topic representations increase the ability to decompose and identify human-centric performance measures. Three methods of topic identification and five prediction models are compared based on their prediction accuracy. From this analysis it is found that representing input variables as topics distributions and the resulting performance as a single indicator while using support vector regression provided the most accurate mapping between ability and performance. With these findings, complex open innovation projects will benefit from increased knowledge of individual ability and how that correlates to their predicted performances.