The reliability of complex or safety critical systems is of increasing importance in several application fields. In many cases, decisions evaluating situations or conditions are made. To ensure the high accuracy of these decisions, the assignments from different classifiers can be fused to one final decision to improve the decision performance in terms of given measures like accuracy or false alarm rate. Recent research results show that fusion methods not always outperform individual classifiers trained and optimized for a specific situation. Nevertheless fusion helps to ensure reliability and redundancy by combining the advantages of individual classifiers, even if some classifiers are not performing well for specific situations. Especially in unexpected (untrained) situations, fusion of more than one classifier allows to get a suitable decision, because of different behavior of classifiers in this case. Nevertheless, there are several examples, where fusion not always improves the overall accuracy of a decision. In this contribution fusion options are discussed to overcome the problem to overcome the aforementioned problem and to define influencing factors on overall fusion accuracy. As a results requirements for good or guaranteed or possibly increased fusion performance and also suggestions denoting those options not leading to any kind of improvement are given. For illustrating the effects a practical example based on three characteristics of fusion methods (type of classifier output, use of these outputs and necessity of training) and four data properties (number of classes, number of samples, entropy of classes and entropy of attributes) are considered and analyzed with 15 different benchmark data sets, which are classified with eight classification methods. The classification results are fused using seven fusion methods. From the discussion of the results it can be concluded, which fusion method performs best/worst for all data sets as well as which fusion method characteristic or data property has more or less positive/negative influence on the fusion performance in comparison to the best base classifier.Using this information, suitable fusion methods can be selected or data sets can be adapted to improve the reliability of decisions made in complex or safety critical systems.

Research in understanding human behavior is a growing field within the development of Advanced Driving Assistance Systems (ADASs). In this contribution, a state machine approach is proposed to develop a driving behavior recognition model. The state machine approach is a behavior model based on the current state and a given set of inputs. Transitions to different states occur or we remain in the same state producing outputs. The transition between states depends on a set of environmental and driving variables. Based on a heuristic understanding of driving situations modeled as states, as well as one of the related actions modeling the state, using an assumed relation between them as the state machine topology, in this paper, a crisp approach is applied to adapt the model to real behaviors. An important aspect of the contribution is to introduce a trainable state machine-based model to describe drivers’ lane changing behavior. Three driving maneuvers are defined as states. The training of the model is related to the definition/tuning of transition variables (and state definitions). Here, driving data are used as the input for training. The non-dominated sorting genetic algorithm II is used to generate the optimized transition threshold. Comparing the data of actual human driving behaviors collected using driving simulator experiments and the calculated driving behaviors, this approach is able to develop a personalized behavior recognition model. The newly established algorithm presents an easy to apply, reliable, and interpretable AI approach.

Reliability and availability of technically complex and safety-critical systems are of increasing importance. Besides the degree of wear, the quality of mechanical systems is significant for the system reliability. The focus of this contribution is the development and application of readily applicable and easily interpretable algorithms for industrial data obtained from technical systems during operation. The methods are within the focus of the production-oriented automation programs (Industrial Internet, Automation 4.0, China 2025). In this contribution as example a hydraulically driven machine in which parts slide over each other is chosen as sliding wear example. Monitoring is applied to distinguish normal and abnormal operation as well as to define end of useful lifetime. In this contribution four different methods will be introduced and experimentally compared without the availability of objective information about the wear state. The approaches differ with respect to the used measurements and data preparation. As measurements Acoustic Emission and the hydraulic pressure of the driving machine are used. For processing the accumulation of damage related values, a machine learning algorithm, and a sensitivity matrix are used. For comparison the experimental validation is based on identical data sets. Different operational states of the system denoted as actual system state are defined and classified. The comparison shows that the four introduced methods provide similar classification results although the underlying measurements are based on different physical principles. The newly introduced approaches allow online evaluation of the actual system state and can serve within improved maintenance strategies.