The large amount of features recorded from GPS and inertial sensors (external load) and well-being questionnaires (internal load) can be used together in a multi-dimensional non-linear machine learning based model for a better prediction of non-contact injuries. In this study we put forward the main hypothesis that the use of such models would be able to inform better about injury risks by considering the evolution of both internal and external loads over two horizons (one week and one month). Predictive models were trained with data collected by both GPS and subjective questionnaires and injury data from 40 elite male soccer players over one season. Various classification machine-learning algorithms that performed best on external and internal loads features were compared using standard performance metrics such as accuracy, precision, recall and the area under the receiver operator characteristic curve. In particular, tree-based algorithms based on non-linear models with an important interpretation aspect were privileged as they can help to understand internal and external load features impact on injury risk. For 1-week injury prediction, internal load features data were more accurate than external load features while for 1-month injury prediction, the best performances of classifiers were reached by combining internal and external load features.

Designing the way a complex system should evolve to better match customers' requirements provides an interesting class of applications for muticriteria techniques. The models required to support the improvement design of a complex system must include both preference models and system behavioral models. A MAUT model captures decisions related to design preferences, whereas a fuzzy representation is proposed to model relationships between system parameters and the fulfillment of system assessment criteria. The way in which these models are jointly used throughout our entire design procedure highlights that both models must be used in tandem to address managerial and implementation issues involved in an improvement project. The iterative improvement process is supported by a mathematical model, in addition to a software tool that allows our approach to be tested in an industrial case study. The search for adequate parameters regarding the improvement design is supported by a branch and bound algorithm to compute the most relevant actions to be performed. The findings confirm the efficiency of the algorithm.

Besides the ecological issues, recycling of plastics involves economical matters that encourage industrial firms to invest in the field. Part of them have focused on the waste sorting phase by designing optical device able to discriminate on line among plastics categories. For achieving ecological and economical objectives, sorting errors must be minimized to avoid serious recycling problems and significant quality degradation of the final recycled product. Even with the most recent acquisition technologies based on spectra imaging, plastic recognition remains a tough task due to the presence of imprecision and uncertainty, e.g., variability in the measurement due to atmospheric disturbances, ageing of plastics, dark or black coloured materials etc. The enhancement of the recent sorting techniques based on classification algorithms leads to rather good performance results, however for such applications, the remaining errors have serious consequences. In this article, we propose an imprecise classification algorithm to minimize sorting errors of standard classifiers when dealing with incomplete data by both integrating the processing of classification's doubt and hesitation in the decision process and improving the classification performances. To this aim, we propose a relabelling procedure that allows to better represent the imprecision of the learning data and we introduce the belief functions framework to represent the posterior probability provided by a classifier. Finally, the performances of our approach compared to existing imprecise classifiers is illustrated on the sorting problem of four plastics categories from mid-wavelength infra-red spectra acquired in an industrial context.

The design of mechatronic systems involves several technical and scientific disciplines. It is often difficult to anticipate, at the outset, the consequences of design decisions on the ultimate effectiveness of such complex systems, in which case the evaluation process is required to support the designers each time engineering choices must be made or justified. Since designers may belong to different technical and scientific cultures however, their understanding of both the design stakes and the evaluation process is too often biased. Moreover, design choices take place in an uncertain context and according to multiple criteria, some of which may be contradictory. In order to track the consequences of design decisions, we are proposing a conceptual data model to perform evaluations within the MBSE framework of Systems Engineering. We then proceed by relying on the relationships demonstrated by such a model to identify the potential impacts of design choices on future product performance. Since data available during the conceptual phase of the design are typically uncertain or imprecise, an original research protocol is extended to a qualitative impact analysis for the purpose of highlighting the most promising alternative system design solutions (ASDS). An example in the mechatronics field serves to illustrate our proposals.