Location, Location, Location: Accelerometer Placement Affects Steps-Based Physical Activity Outcomes During Pregnancy and Postpartum

As pregnancy progresses, physical changes may affect physical activity (PA) measurement validity. n = 11 pregnant women (30.1 ± 3.8 years) wore ActiGraph GT3X+ accelerometers on the right hip, right ankle, and non-dominant wrist for 3–7 days during the second and third trimesters (21 and 32 weeks, respectively) and 12 weeks postpartum. Data were downloaded into 60-second epochs from which stepping cadence was calculated; repeated-measures analysis of variance was used to determine significant differences among placements. At all time points, the wrist accelerometer measured significantly more daily steps (9930–10 452 steps/d) and faster average stepping cadence (14.5–14.6 steps/min) than either the hip (4972–5944 steps/d, 7.1–8.6 steps/min) or ankle (7161–8205 steps/d, 10.3–11.9 steps/min) placement, while moderate- to vigorous-intensity activity at the wrist (1.2–1.7 min/d) was significantly less than either hip (3.0–5.9 min/d) or ankle (6.1–7.3 min/d). Steps, cadence, and counts were significantly lower for the hip than the ankle at all time points. Kappa calculated for agreement in intensity classification between the various pairwise comparisons ranged from .06 to .41, with Kappa for hip–ankle agreement (.34–.41) significantly higher than for wrist–ankle (.09–.11) or wrist–hip (.06–.16). These data indicate that wrist accelerometer placement during pregnancy likely results in over counting of PA parameters and should be used with caution.

Domain knowledge integration into deep learning for typhoon intensity classification

In this report, we propose a deep learning technique for high-accuracy estimation of the intensity class of a typhoon from a single satellite image, by incorporating meteorological domain knowledge. By using the Visual Geometric Group’s model, VGG-16, with images preprocessed with fisheye distortion, which enhances a typhoon’s eye, eyewall, and cloud distribution, we achieved much higher classification accuracy than that of a previous study, even with sequential-split validation. Through comparison of t-distributed stochastic neighbor embedding (t-SNE) plots for the feature maps of VGG with the original satellite images, we also verified that the fisheye preprocessing facilitated cluster formation, suggesting that our model could successfully extract image features related to the typhoon intensity class. Moreover, gradient-weighted class activation mapping (Grad-CAM) was applied to highlight the eye and the cloud distributions surrounding the eye, which are important regions for intensity classification; the results suggest that our model qualitatively gained a viewpoint similar to that of domain experts. A series of analyses revealed that the data-driven approach using only deep learning has limitations, and the integration of domain knowledge could bring new breakthroughs.

Is China’s Textile Industry Still a Labour-Intensive Industry?

Is China’s textile industry (CTI) still a laboor-intensive one? To answer this question, this study measures the capital-labour intensity and technology intensity of CTI and its sub-sectors during 2006-2018, then applies factor intensity classification and cluster analysis to identify their industrial attributes. The results show that CTI and its sub-sectors are still the labour- and non-technology-intensive. All the indexes of capital-labour intensity and technology intensity of CTI and its sub-sectors are below 100, lower than the average of industry sectors, indicating that they are not separate from the category of labour-intensive industry and still heavily dependent on labour. And cluster analysis verifies the industrial classification results. So CTI still needs to keep on increasing its capital intensity and technology intensity to achieve the goal of industrial transformation and upgrading in the future.

Development and Validation of Open-Source Activity Intensity Count and Activity Intensity Classification Algorithms from Raw Acceleration Signals of Wearable Sensors

Background: A popular outcome in rehabilitation studies is the activity intensity count, which is typically measured from commercially available accelerometers. However, the algorithms are not openly available, which impairs long-term follow-ups and restricts the potential to adapt the algorithms for pathological populations. The objectives of this research are to design and validate open-source algorithms for activity intensity quantification and classification. Methods: Two versions of a quantification algorithm are proposed (fixed [FB] and modifiable bandwidth [MB]) along with two versions of a classification algorithm (discrete [DM] vs. continuous methods [CM]). The results of these algorithms were compared to those of a commercial activity intensity count solution (ActiLife) with datasets from four activities (n = 24 participants). Results: The FB and MB algorithms gave similar results as ActiLife (r > 0.96). The DM algorithm is similar to a ActiLife (r ≥ 0.99). The CM algorithm differs (r ≥ 0.89) but is more precise. Conclusion: The combination of the FB algorithm with the DM results is a solution close to that of ActiLife. However, the MB version remains valid while being more adaptable, and the CM is more precise. This paper proposes an open-source alternative for rehabilitation that is compatible with several wearable devices and not dependent on manufacturer commercial decisions.