Search Results (2)

Stamping processes remain crucial in manufacturing processes; therefore, diagnosing the condition of stamping tools is critical. One of the challenges in diagnosing stamping tool conditions is that traditionally, the tools need to be visually checked, and the production processes thus need to be halted. With the development of Industry 4.0, intelligent monitoring systems have been developed by using accelerometers and algorithms to diagnose the wear classification of stamping tools. Although several deep learning models such as the convolutional neural network (CNN), auto encoder (AE), and recurrent neural network (RNN) models have demonstrated promising results for classifying complex signals including accelerometer signals, the practicality of those methods are restricted due to the flexibility of adding new classes and low accuracy when faced to low numbers of samples per class. In this study, we applied deep metric learning (DML) methods to overcome these problems. DML involves extracting meaningful features using feature extraction modules to map inputs into embedding features. We compared the probability method, the contrastive method, and a triplet network to determine which method was most suitable for our case. The experimental results revealed that, compared with other models, a triplet network can be more effectively trained with limited training data. The triplet network demonstrated the best test results of the compared methods in the noised test data. Finally, when tested using unseen class, the triplet network and the probability method demonstrated similar results. Full article

Deep and meaningful learning (DML) in distant education should be an essential outcome of quality education. In this literature review, we focus on e-learning effectiveness along with the factors and conditions leading to DML when using social virtual reality environments (SVREs) in distance mode higher education (HE). Hence, a systematic literature review was conducted summarizing the findings from thirty-three empirical studies in HE between 2004 (appearance of VR) and 2019 (before coronavirus appearance). We searched for the cognitive, social, and affective aspects of DML in a research framework and studied their weight in SVREs. The findings suggest that the use of SVREs can provide authentic, simulated, cognitively challenging experiences in engaging, motivating environments for open-ended social and collaborative interactions and intentional, personalized learning. Furthermore, the findings indicate that educators and SVRE designers need to place more emphasis on the socio-cultural semiotics and emotional aspects of e-learning and ethical issues such as privacy and security. The mediating factors for DML in SVREs were accumulated and classified in the resultant Blended Model for Deep and Meaningful e-learning in SVREs. Improvement recommendations include meaningful contexts, purposeful activation, learner agency, intrinsic emotional engagement, holistic social integration, and meticulous user obstacle removal. Full article