Cyber-Empathic Design: A Data-Driven Framework for Product Design

Abstract

A critical task in product design is mapping information from consumer to design space. Currently, this process largely depends on designers identifying and mapping psychological and consumer level factors to engineered attributes. In this way, current methodologies lack provision to test a designer's cognitive reasoning and could introduce bias when mapping from consumer to design space. In addition, current dominant frameworks do not include user–product interaction data in design decision making, nor do they assist designers in understanding why a consumer has a particular perception about a product. This paper proposes a framework—cyber-empathic (CE) design—where user–product interaction data are acquired using embedded sensors. To gain insight into consumer perceptions relative to product features, a network of psychological constructs is utilized. Structural equation modeling (SEM) is used as the parameter estimation and hypothesis testing technique, making the framework falsifiable in nature. To demonstrate effectiveness of the framework, a case study of sensor-integrated shoes is presented, where two models are compared—one survey-only and one using the cyber-empathic framework model. Covariance-based SEM (CB-SEM) is used to estimate the parameters and the fit indices. It is shown that the cyber-empathic framework results in improved fit over a survey-only SEM. This work demonstrates how low-level user–product interaction data can be used to understand and model user perceptions in a way that can support falsifiable design inference.

Application of autoencoders in cyber-empathic design

“…An important observation can be made for the R 2 value for the Perceived Comfort (Formative) psychological construct, which is 0.5269 for the survey-based model, 0.6607 for the manually extracted features based Cyber-Empathic model, and 0.7278 for the Autoencoder-based Cyber-Empathic model. First, this validates the results from (Ghosh et al 2017a) that the Cyber-Empathic model performs better than the pure survey-based model in understanding consumer perceptions. Second, since the R 2 value for the Perceived Comfort Formative construct for the Autoencoder-driven model is larger than the value for manually extracted features, it demonstrates the superiority of using Autoencoders for this case study.…”

“…This section presents a brief review of the unsupervised deep learning method integrating Autoencoders and PLS-SEM. An in-depth review of the existing work in design analytics, motivations and the mechanics of CED are presented in (Ghosh et al 2017a). A limitation of the CED framework is that information representing user-product interaction is extracted manually from raw sensor data (i.e., features from raw sensor data as in Figure 1).…”

“…The analysis procedure to estimate the parameters of the CED framework is shown in Figure 6. The manually designed and extracted features from (Ghosh et al 2017a) are reused in this work. As a novel contribution, this work replaces the manual feature extraction by Autoencoder extracted features as shown in Figure 6.…”

Smart design engineering: a literature review of the impact of the 4th industrial revolution on product design and development

“…The argue that the latter alternative is more natural and is easier for users control, thus reducing the need for embedding smartness into several devices, facilitating the designer to deal with questions of privacy, reducing the device's interaction complexity, and serving as a gateway to control and report the status of smart home products. Ghosh et al (2017) propose a cyber-emphatic design framework that considers data feedback from productembedded sensors, which is processed through a network of psychological constructs. As a result, they identify the potential to manipulate product features and then measure the changes in perception using sensors and psychological construct models.…”

Empathic accuracy in design: Exploring design outcomes through empathic performance and physiology

“…Extensive literature reviews (Kouprie & Sleeswijk Visser 2009;Strobel et al 2013;Walther, Miller & Sochacka 2017), borrowing definitions from psychology (Wong et al 2016;Surma-aho, Björklund & Hölttä-Otto 2018) and based on interviews with designers (Strobel et al 2013;Hess, Strobel & Pan 2016) and observing designers (Hess & Fila 2016) suggest that empathy is commonly equated with some type of comprehensive user understanding. For instance, empathy in design has been associated with user-understanding methods like immersing oneself in the dreams of a future user (Battarbee et al 2002), imposing extreme user-like features on designers (Vaughan, Seepersad & Crawford 2014;Pang & Seepersad 2016) or on non-extreme users (Lin & Seepersad 2007), understanding users through a combination of survey and sensor data (Ghosh et al 2017), and projecting into a user's life through using one's imagination (Koskinen & Battarbee 2003). Some studies define designer empathy as an outcome of user interaction -an increased ability to understand users and solve their issues (Raviselvam et al 2017;Raviselvam et al 2018).…”