Digital, Volume 1, Issue 2 (June 2021) – 3 articles

Digital twins are meant to bridge the gap between real-world physical systems and virtual representations. Both stand-alone and descriptive digital twins incorporate 3D geometric models, which are the physical representations of objects in the digital replica. Digital twin applications are required to rapidly update internal parameters with the evolution of their physical counterpart. Due to an essential need for having high-quality geometric models for accurate physical representations, the storage and bandwidth requirements for storing 3D model information can quickly exceed the available storage and bandwidth capacity. In this work, we demonstrate a novel approach to geometric change detection in a digital twin context. We address the issue through a combined solution of dynamic mode decomposition (DMD) for motion detection, YOLOv5 for object detection, and 3D machine learning for pose estimation. DMD is applied for background subtraction, enabling detection of moving foreground objects in real-time. The video frames containing detected motion are extracted and used as input to the change detection network. The object detection algorithm YOLOv5 is applied to extract the bounding boxes of detected objects in the video frames. Furthermore, we estimate the rotational pose of each object in a 3D pose estimation network. A series of convolutional neural networks (CNNs) conducts feature extraction from images and 3D model shapes. Then, the network outputs the camera orientation’s estimated Euler angles concerning the object in the input image. By only storing data associated with a detected change in pose, we minimize necessary storage and bandwidth requirements while still recreating the 3D scene on demand. Our assessment of the new geometric detection framework shows that the proposed methodology could represent a viable tool in emerging digital twin applications. Full article

Physical inactivity in children is a major public health challenge, for which valid physical activity assessment tools are needed. Wearable devices provide a means for objective assessment of children’s physical activity, but they are often not adopted because of issues such as cost, comfort, and privacy. In this context, self-reporting tools could be employed, but their validity in relation to a child’s age is understudied. We present the agreement of one of the most popular self-reporting tools, the Physical Activity Questionnaire for Children (PAQ-C) with accelerometer-measured physical activity in 9-year-old versus 12-year-old children, wearing an accelerometer-based wearable device for seven consecutive days. We study the relationship between the PAQ-C and accelerometer scores using Spearman’s rank correlation coefficients and Bland–Altman plots in a sample of 131 children included for analysis. Overall, there was correlation between PAQ-C score and physical activity measures for the 12-year-old children (rho = 0.47 for total physical activity, rho = 0.43 for moderate-to-vigorous physical activity, rho = 0.41 for steps, p < 0.01), but not for the 9-year-old children (rho = 0.08 for total physical activity, rho = 0.21 for moderate-to-vigorous physical activity, rho = 0.19 for steps, p > 0.05). All PAQ-C items other than item 3 (activity at recess) did not reach significance in correlation with accelerometry for the 9-year-old children (p > 0.05). Therefore, the use of wearable devices for more objective assessment of physical activity in younger children should be preferred. Full article

Phrase-based statistical machine translation (PB-SMT) has been the dominant paradigm in machine translation (MT) research for more than two decades. Deep neural MT models have been producing state-of-the-art performance across many translation tasks for four to five years. To put it another way, neural MT (NMT) took the place of PB-SMT a few years back and currently represents the state-of-the-art in MT research. Translation to or from under-resourced languages has been historically seen as a challenging task. Despite producing state-of-the-art results in many translation tasks, NMT still poses many problems such as performing poorly for many low-resource language pairs mainly because of its learning task’s data-demanding nature. MT researchers have been trying to address this problem via various techniques, e.g., exploiting source- and/or target-side monolingual data for training, augmenting bilingual training data, and transfer learning. Despite some success, none of the present-day benchmarks have entirely overcome the problem of translation in low-resource scenarios for many languages. In this work, we investigate the performance of PB-SMT and NMT on two rarely tested under-resourced language pairs, English-To-Tamil and Hindi-To-Tamil, taking a specialised data domain into consideration. This paper demonstrates our findings and presents results showing the rankings of our MT systems produced via a social media-based human evaluation scheme. Full article