Deep learning technology has been widely adopted in the research of automatic arrhythmia detection. However, there are several limitations in existing diagnostic models, e.g., difficulties in extracting temporal information from long-term ECG signals, a plethora of parameters, and sluggish operation speed. Additionally, the diagnosis performance of arrhythmia is prone to mistakes from signal noise. This paper proposes a smartphone-based m-health system for arrhythmia diagnosis. First, we design a cycle-GAN-based ECG denoising model which takes real-world noise signals as input and aims to produce clean ECG signals. In order to train its two generators and two discriminators simultaneously, we explore an unsupervised pre-training strategy to initialize the generator and accelerate the convergence speed during training. Second, we propose an arrhythmia diagnosis model based on the time convolution network (TCN). This model can identify 34 common arrhythmia events using eight-lead ECG signals, and we deploy such a model on the Android platform to develop an at-home ECG monitoring system. Experimental results have demonstrated that our approach outperforms the existing noise reduction methods and arrhythmia diagnosis models in terms of denoising effect, recognition accuracy, model size, and operation speed, making it more suitable for deployment on mobile devices for m-health monitoring services.
Arrhythmias, Cardiac , Electrocardiography , Smartphone , Arrhythmias, Cardiac/diagnosis , Humans , Monitoring, Physiologic , Signal Processing, Computer-Assisted , Telemedicine , Algorithms
High temperature lubricating composites have been widely used in aerospace and other high-tech industries. In the actual application process, high temperature oxidation resistance is a very importance parameter. In this paper, BaO/TiO2-enhanced NiAl-based composites were prepared by vacuum hot-press sintering. The oxidation resistance performance of the composites at 800 °C was investigated. The composites exhibited very good sintered compactness and only a few pores were present. Meanwhile, the composite had excellent oxidation resistance properties due to the formation of a dense Al2O3 layer which could prevent further oxidation of the internal substrate; its oxidation mechanism was mainly decided by the outward diffusion of Al and the inward diffusion of O. The addition of BaO/TiO2 introduced more boundaries and made the Kp value increase from 1.2 × 10-14 g2/cm4 s to 3.3 × 10-14 g2/cm4 s, leading to a slight reduction in the oxidation resistance performance of the composites-although it was still excellent.
Wheel rail rolling contact fatigue is a very common form of damage, which can lead to uneven rail treads, railhead nuclear damage, etc. Therefore, ANSYS software was used to establish a three-dimensional wheel-rail contact model and analyze the effects of several main characteristics, such as the rail crack length and crack propagation angle, on the fatigue crack intensity factor during crack propagation. The main findings were as follows: (1) With the rail crack length increasing, the position where the crack propagated by mode I moved from the inner edge of the wheel-rail contact spot to the outer edge. When the crack propagated to 0.3-0.5 mm, it propagated to the rail surface, causing the rail material to peel or fall off and other damage. (2) When the crack propagation angle was less than 30°, the cracks were mainly mode II cracks. When the angle was between 30 and 70°, the cracks were mode I-II cracks. When the angle was more than 70°, the cracks were mainly mode I cracks. When the crack propagation angle was 60°, the equivalent stress intensity factor reached the maximum, and the rail cracks propagated the fastest.
While WiFi-based indoor localization is attractive, there are many indoor places without WiFi coverage with a strong demand for localization capability. This paper describes a system and associated algorithms to address the indoor vehicle localization problem without the installation of additional infrastructure. In this paper, we propose VeLoc, which utilizes the sensor data of smartphones in the vehicle together with the floor map of the parking structure to track the vehicle in real time. VeLoc simultaneously harnesses constraints imposed by the map and environment sensing. All these cues are codified into a novel augmented particle filtering framework to estimate the position of the vehicle. Experimental results show that VeLoc performs well when even the initial position and the initial heading direction of the vehicle are completely unknown.
