Small defects on the rails develop fast under the continuous load of passing trains, and this may lead to train derailment and other disasters. In recent years, many types of wireless sensor systems have been developed for rail defect detection. However, there has been a lack of comprehensive reviews on the working principles, functions, and trade-offs of these wireless sensor systems. Therefore, we provide in this paper a systematic review of recent studies on wireless sensor-based rail defect detection systems from three different perspectives: sensing principles, wireless networks, and power supply. We analyzed and compared six sensing methods to discuss their detection accuracy, detectable types of defects, and their detection efficiency. For wireless networks, we analyzed and compared their application scenarios, the advantages and disadvantages of different network topologies, and the capabilities of different transmission media. From the perspective of power supply, we analyzed and compared different power supply modules in terms of installation and energy harvesting methods, and the amount of energy they can supply. Finally, we offered three suggestions that may inspire the future development of wireless sensor-based rail defect detection systems.

Modern scientific applications and supercomputing systems are generating large amounts of data in various fields, leading to critical challenges in data storage footprints and communication times. To address this issue, error-bounded GPU lossy compression has been widely adopted, since it can reduce the volume of data within a customized threshold on data distortion. In this work, we propose an ultra-fast error-bounded GPU lossy compressor cuSZp. Specifically, cuSZp computes the linear recurrences with hierarchical parallelism to fuse the massive computation into one kernel, drastically improving the end-to-end throughput. In addition, cuSZp adopts a block-wise design along with a lightweight fixed-length encoding and bit-shuffle inside each block such that it achieves high compression ratios and data quality. Our experiments on NVIDIA A100 GPU with 6 representative scientific datasets demonstrate that cuSZp can achieve an ultra-fast end-to-end throughput (95.53x compared with cuSZ) along with a high compression ratio and high reconstructed data quality.

The speed and the overall loading of a train are of great importance in determining whether the entire train is running in a safe and stable manner. We present here our work in developing a wireless rail monitoring system using IoT (Internet-of-Things) sensors and edge computing to provide accurate real-time running state parameters of trains continuously over time. By placing a wireless MEMS-based sensing system (overall size of 50×50×17 mm) on a rail to collect the vibration information of the rail under excitation by the wheels of passing trains, and by using edge computing technique to analyze these captured vibration data, we calculated the state parameters of the vehicle with the microprocessor integrated with the MEMS sensors. Then, the final analysis results were uploaded to a cloud server via Narrow Band Internet-of-Things (NB-IoT) networks. The entire system consists of a solar power module, a cloud server, and an IoT sensor. Compared with traditional train state detection systems (i.e., computer vision or IR detectors) this system has the advantages of low cost, self-powering, and no line occupation. We have demonstrated that 24-hour real-time wireless monitoring without occupation of track resources is feasible using this system, which greatly improves the efficiency and quality of railway track detection. We conducted field experiments on the Datong-Qinhuangdao Railway line using our system. Experimental results showed that the absolute error in speed is 0.2 Km/h and no error in carriages quantity detection. It is expected to play a key role in the real-time monitoring of railways and trains in the future.

Arrhythmia is a marked symptom of many cardiovascular diseases (CVDs). Fast and accurate measurement of heart rate (HR) can lead to prompt detection of arrhythmia, which could be potentially life-threatening. However, it remains a challenge to robustly and remotely measure HR due to the typically changing ambient conditions surrounding human subjects. In this study, we propose a method to accurately measure human HR by simply using a smartphone camera. We use three special approaches for HR estimation. Firstly, we fuse the raw data by subtracting G channel from R channel to enhance the heartbeat signal from video data. Secondly, instead of the entire palm, we select a region of interest (ROI) from the palm for heart rate detection based on signal-to-noise ratio (SNR) maps, which reduces the proportion of the weak signal area. Thirdly, after applying Fast Fourier Transform (FFT) analyses of the time-series data from the video, we set an interval threshold based on the heart rate range to accurately determine heart rate. With a reference HR value measured by electrocardiography (ECG), the detection rate of the proposed method is 95.84% (overall result from 30 test subjects) when used for measurement at an ambient light intensity of 150 lux within a distance of 4.5 meters. The method’s strong adaptability to changing ambient conditions and ease of implementation makes it applicable to many scenarios, such as homes of the elderly, classrooms, and other public spaces.