The low-cost Inertial Measurement Unit (IMU) can provide orientation information and is widely used in our daily life. However, IMUs with bad calibration will provide inaccurate angular velocity and lead to rapid drift of integral orientation in a short time. In this paper, we present the Calib-Net which can achieve the accurate calibration of low-cost IMU via a simple deep convolutional neural network. Following a carefully designed mathematical calibration model, Calib-Net can output compensation components for gyroscope measurements dynamically. Dilation convolution is adopted in Calib-Net for spatio-temporal feature extraction of IMU measurements. We evaluate our proposed system on public datasets quantitively and qualitatively. The experimental results demonstrate that our Calib-Net achieves better calibration performance than other methods, what is more, and the estimated orientation with our Calib-Net is even comparable with the results from visual inertial odometry (VIO) systems.

Objectives: The aim of this study is to compare the prognostic effects of visceral fat area (VFA) with coronary artery calcification score (CACs) in patients on maintenance hemodialysis. Design and Methods: In the prospective study with no intervention, clinical characteristics and serum biochemical indexes at baseline for each patient were collected through the electronic medical records. Body composition assessment using bioelectrical impedance analysis, computed tomography examination with the Agatston scoring method, and echocardiographic measurements were performed at enrollment. Primary endpoints included cardiovascular events (CVEs), cardiovascular death (CVD), and all-cause death. Results: A total of 97 Chinese patients aged 48 (35-62) years were enrolled from our Hemodialysis Center, of which 61.9% were male and 20.6% had diabetes. The median of VFA and CACs at baseline was 64.5 (43.5-88.7) cm 2 and 0.9 (0-467.6), respectively. CVEs occurred in 20 (20.6%) patients during a median follow-up of 26.4 (13-27.7) months. The cardiovascular and all-cause mortality was 8.2% (8 patients) and 11.3% (11 patients), respectively. VFA was associated with CVEs (hazard ratio [HR] 5 9.21 for VFA $71.3 cm 2 vs. VFA ,71.3 cm 2 , P 5 .017), CVD (HR 5 1.11 for 1 cm 2 increase, P 5 .035), and all-cause mortality (HR 5 1.08 for 1 cm 2 increase, P 5 .011). Also, VFA was significantly correlated with cardiac structure parameters and the development of left ventricular hypertrophy (odds ratio 5 1.02 for 1 cm 2 increase, P 5 .03). Yet, CACs were not correlated with CVEs, CVD, or all-cause mortality. Conclusions: Increased VFA can be used as an independent predictor for CVEs, CVD, and all-cause mortality. The effect VFA exerts on cardiac reconstruction might be the underlying mechanism. Further studies are warranted for the management of VFA in the hemodialysis population.