Accident-data-aided design: visualizing typical and potential risks of consumer products by data mining an accident database

Designing a safe product requires predicting how consumers will use the product and what sort of risks exist in their daily environment. However, assistive technology for risk assessment of consumer products used in the daily environment has not yet been established. One of the most promising approaches is to utilize data on actual accidents that have occurred in the past. This paper proposes a new method that uses recently developed data mining technology to predict the typical and potential risks of consumer products. The proposed method is as follows: 1) create a database by structurizing a situation graph of accident data; 2) use this database to determine the typical risk; and 3) use two methods to determine the potential risk: a probabilistic latent semantic indexing (pLSI) method and a method based on the features of the product. The feature method uses 48 predefined latent classes of product features, such as, for example, things that rotate, things that can be held, and things that have high temperatures. To demonstrate the effectiveness of the proposed system, we applied our system to a dataset of 681 cases of accidental burning or scalding injuries.