PurposeThis paper aims to explore the relationship between quality management practices and their impact on performance.Design/methodology/approachFirst, critical quality management practices are identified and classified in three main categories: management, infrastructure, and core practices. Then, a model linking these practices and performance is proposed and empirically tested. The empirical data were obtained from a survey of 133 Tunisian companies from the plastic transforming sector.FindingsThe results reveal a positive relationship between quality management practices and organizational performance. Moreover, the findings show a significant relationship between management and infrastructure practices. In addition, the results illustrate a direct effect of infrastructure practices on operational performance and of core practices on product quality.Research limitations/implicationsThe conceptual model proposed and tested in this study can be used by researchers for developing quality management theory. In addition, this model may offer a flow chart to practitioners for effective quality management implementation.Originality/valueThe proposed model is the first one to distinguish the direct effects of infrastructure practices on performance from the indirect effects of these practices through the core practices. Besides, the use of path analysis method to study the direct and indirect relationships between quality management practices and their effect on performance dimensions.

No abstract

No abstract

No abstract

The aim of the 2017 PhysioNet/CinC Challenge [1] is to classify short ECG signals (between 30 seconds and 60 seconds length), as Normal sinus rhythm (N), Atrial Fibrillation (AF), an alternative rhythm (O), or as too noisy to be classified. Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) as classifiers have recently shown improved performances compared to methods established in various sound recognition tasks [2] and interesting result in tasks such as the 2016 Physionet Challenge for the classification of heart sound [3]. Our approach is based on a convolutional recurrent neural network (CRNN), involving two independent CNNs, to extract relevant patterns, one from the ECG and the other from the heart rate, which are then merged into a RNN accounting for the sequence of the extracted patterns. The final decision is then evaluated through a Support Vector Machine (SVM).