Background: Markerless (ML) motion capture systems have recently become available for biomechanics applications. Evidence has indicated the potential feasibility of using an ML system to analyze lower extremity kinematics. However, no research has examined ML systems’ estimation of the lower extremity joint moments and powers. This study aimed to compare lower extremity joint moments and powers estimated by marker-based (MB) and ML motion capture systems. Methods: Sixteen volunteers ran on a treadmill for 120 s at 3.58 m/s. The kinematic data were simultaneously recorded by 8 infrared cameras and 8 high-resolution video cameras. The force data were recorded via an instrumented treadmill. Results: Greater peak magnitudes for hip extension and flexion moments, knee flexion moment, and ankle plantarflexion moment, along with their joint powers, were observed in the ML system compared to an MB system (p < 0.0001). For example, greater hip extension (MB: 1.42 ± 0.29 vs. ML: 2.27 ± 0.45) and knee flexion (MB: −0.74 vs. ML: −1.17 nm/kg) moments were observed in the late swing phase. Additionally, the ML system’s estimations resulted in significantly smaller peak magnitudes for knee extension moment, along with the knee production power (p < 0.0001). Conclusions: These observations indicate that inconsistent estimates of joint center position and segment center of mass between the two systems may cause differences in the lower extremity joint moments and powers. However, with the progression of pose estimation in the markerless system, future applications can be promising.

In terms of running mechanics, statistically significant differences were limited. However, cadence (steps‧min -1 ) was significantly lower in the Nike AF (174.6 ± 10.4) than the Asics HS (176.5 ± 10.3). CONCLUSION: Only the Nike AF and Asics MS matched the previously established Nike VF2 in running economy improvements. From these data, it appears the advantages conferred by new running shoe advancements are not fully shared across the competitive running shoe market.

An accurate medical image registration is crucial in a variety of neuroscience and clinical studies. In this paper, we proposed a new unsupervised learning network, DAVoxelMorph to improve the accuracy of 3D deformable medical image registration. Based on the VoxelMorph model, our network presented two modifications, one is adding a dual attention architecture, specifically, we model semantic correlation on spatial and coordinate dimensions respectively, and the location attention module selectively aggregates the features of each location by weighting the features of all locations. The coordinate attention module further puts the location information into the channel attention. The other is introducing the bending penalty as regularization in the loss function to penalize the bending in the deformation field. Experimental results show that DAVoxelMorph achieved better registration performance including average Dice scores (0.714) and percentage of locations with non-positive Jacobian (0.345) compare with VoxelMorph (0.703, 0.355), CycleMorph (0.705, 0.133), ANTs SyN (0.707, 0.137) and NiftyReg (0.694, 0.549). Our model increases both model sensitivity and registration accuracy.

With the rapid development of high-speed railway (HSR) transportation in China, its impact on regional spatial patterns and shaping has become increasingly significant. This study took seven urban agglomerations in the Yellow River Basin as the research object, using the 2 h HSR access time in the Yellow River Basin to comparatively analyze the differences in HSR access in the urban agglomeration in the Yellow River Basin, and using the 3 h HSR access to central cities as the background to conduct regional division and overlapping space identification through cross-regional economic links, before finally selecting the overlapping city of Changzhi for long-term space development strategic planning. The main conclusions were as follows: First, the low-value area of HSR travel time in the Yellow River Basin urban agglomerations was biased toward the center of the urban agglomerations, while the peripheral areas were relatively high-value travel traffic circles, and the HSR travel time showed a circular spatial pattern characteristic of continuous expansion from the center to the peripheral areas. Four urban agglomerations in the upper reaches of the city achieved a 2 h access pattern within the urban agglomeration, whereas three urban agglomerations in the middle and lower reaches of the city only reached the 2 h access level in the center. Second, the Yellow River Basin was divided into six community spaces using the SLPA model based on the economic linkage between the central city and other cities, which were filtered by the 3 h access time from the central city to each city for HSR travel. Three of the six communities produced overlapping spaces, i.e., Community 3 and Community 4 produced overlapping spaces containing Linfen, Community 3 and Community 5 produced overlapping spaces containing Changzhi, Handan, and Xingtai, and Community 4 and Community 5 produced overlapping spaces containing Yuncheng and Sanmenxia. Third, the overlapping space of Changzhi City was selected as a case study for a visionary strategic planning outlook. Combining the geographic location characteristics and future development opportunities of Changzhi, we can try to transform a pass-through node like Changzhi into a hub node in the future, strengthening the gateway status and expanding the hinterland. According to the results of the research and analysis, policymakers can try to implement the expansion and renovation of HSR trunk lines, break the transportation bottlenecks in less developed areas, improve the coverage of the HSR network, and establish a “cross-urban agglomeration” cooperation and coordination mechanism.