A starting point for addressing product innovativeness in the Fuzzy Front-End

Product innovativeness is a primary contingent factor to be addressed for the development of flexible management for the front-end. However, due to complexity of this early phase of the innovation process, the definition of which attributes to customise is critical to support a contingent approach. Therefore, this study investigates front-end attributes that need to be customised to permit effective management for different degrees of innovation. To accomplish this aim, a literature review and five case studies were performed. The findings highlighted the front-end strategic and operational levels as factors influencing the front-end attributes related to product innovativeness. In conclusion, this study suggests that two front-end attributes should be customised: development activities and decision-making approach. Copyright © 2011 Inderscience Enterprises Ltd.

An Online Expectation-Maximization Algorithm for Changepoint Models

Changepoint models are widely used to model the heterogeneity of sequential data. We present a novel sequential Monte Carlo (SMC) online Expectation-Maximization (EM) algorithm for estimating the static parameters of such models. The SMC online EM algorithm has a cost per time which is linear in the number of particles and could be particularly important when the data is representable as a long sequence of observations, since it drastically reduces the computational requirements for implementation. We present an asymptotic analysis for the stability of the SMC estimates used in the online EM algorithm and demonstrate the performance of this scheme using both simulated and real data originating from DNA analysis.

An Online Expectation-Maximization Algorithm for Changepoint Models

Changepoint models are widely used to model the heterogeneity of sequential data. We present a novel sequential Monte Carlo (SMC) online Expectation-Maximization (EM) algorithm for estimating the static parameters of such models. The SMC online EM algorithm has a cost per time which is linear in the number of particles and could be particularly important when the data is representable as a long sequence of observations, since it drastically reduces the computational requirements for implementation. We present an asymptotic analysis for the stability of the SMC estimates used in the online EM algorithm and demonstrate the performance of this scheme using both simulated and real data originating from DNA analysis.