No abstract

The frequency of occurrence of an accident scenario is one of the key aspects to take into consideration in the field of risk assessment. This frequency is commonly assessed by a generic failure frequency approach. Although every data source takes into account different variables, aspects such as the human factor are not explicitly detailed, mainly because this factor is laborious to quantify. In the present work, the generic failure frequencies are modified using fuzzy logic. This theory allows the inclusion of qualitative variables that are not considered by traditional methods and to deal with the uncertainty involved. This methodology seems to be a suitable tool to integrate the human factor in risk assessment since it is specially oriented to rationalize the uncertainty related to imprecision or vagueness. A fuzzy modifier has been developed in order to introduce the human factor in the failure frequency estimation.\ud \ud In order to design the proposed model, it is necessary to consider the opinion of the experts. Therefore, a questionnaire on the variables was designed and replied by forty international experts. To test the model, it was applied to two real case studies of chemical plants. New frequency values were obtained and together with the consequence assessment, new iso-risk curves were plotted allowing to compare them to the ones resulting from a quantitative risk analysis (QRA). Since the human factor is now reflected in the failure frequency estimation, the results are more realistic and accurate, and consequently they improve the final risk assessmentPeer ReviewedPostprint (author's final draft

No abstract

No abstract

A time series representation, piecewise trend approximation (PTA), is proposed to improve efficiency of time series data mining in high dimensional large databases. PTA represents time series in concise form while retaining main trends in original time series; the dimensionality of original data is therefore reduced, and the key features are maintained. Different from the representations that based on original data space, PTA transforms original data space into the feature space of ratio between any two consecutive data points in original time series, of which sign and magnitude indicate changing direction and degree of local trend, respectively. Based on the ratio-based feature space, segmentation is performed such that each two conjoint segments have different trends, and then the piecewise segments are approximated by the ratios between the first and last points within the segments. To validate the proposed PTA, it is compared with classical time series representations PAA and APCA on two classical datasets by applying the commonly used K-NN classification algorithm. For ControlChart dataset, PTA outperforms them by 3.55% and 2.33% higher classification accuracy and 8.94% and 7.07% higher for Mixed-BagShapes dataset, respectively. It is indicated that the proposed PTA is effective for high dimensional time series data mining.