Browsing by Subject "Piezoelectric sensor"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Anomaly Detection and Inter-Sensor Transfer Learning on Smart Manufacturing Datasets
    (MDPI, 2023-01-02) Abdallah, Mustafa; Joung, Byung-Gun; Lee, Wo Jae; Mousoulis, Charilaos; Raghunathan, Nithin; Shakouri, Ali; Sutherland, John W.; Bagchi, Saurabh; Computer and Information Science, School of Science
    Smart manufacturing systems are considered the next generation of manufacturing applications. One important goal of the smart manufacturing system is to rapidly detect and anticipate failures to reduce maintenance cost and minimize machine downtime. This often boils down to detecting anomalies within the sensor data acquired from the system which has different characteristics with respect to the operating point of the environment or machines, such as, the RPM of the motor. In this paper, we analyze four datasets from sensors deployed in manufacturing testbeds. We detect the level of defect for each sensor data leveraging deep learning techniques. We also evaluate the performance of several traditional and ML-based forecasting models for predicting the time series of sensor data. We show that careful selection of training data by aggregating multiple predictive RPM values is beneficial. Then, considering the sparse data from one kind of sensor, we perform transfer learning from a high data rate sensor to perform defect type classification. We release our manufacturing database corpus (4 datasets) and codes for anomaly detection and defect type classification for the community to build on it. Taken together, we show that predictive failure classification can be achieved, paving the way for predictive maintenance.
  • Thumbnail Image
    Item
    Wearable Piezoelectric-Based System for Continuous Beat-to-Beat Blood Pressure Measurement
    (MDPI, 2020-02) Wang, Ting-Wei; Lin, Shien-Fong; Krannert Institute of Cardiology, School of Medicine
    Non-invasive continuous blood pressure measurement is an emerging issue that potentially can be applied to cardiovascular disease monitoring and prediction. Recently, many groups have proposed the pulse transition time (PTT) method to estimate blood pressure for long-term monitoring. However, the PTT-based methods for blood pressure estimation are limited by non-specific estimation models and require multiple calibrations. This study aims to develop a low-cost wearable piezoelectric-based system for continuous beat-to-beat blood pressure measurement. The pressure change in the radial artery was extracted by systolic and diastolic feature points in pressure pulse wave (PPW) and the pressure sensitivity of the sensor. The proposed system showed a reliable accuracy of systolic blood pressure (SBP) (mean absolute error (MAE) ± standard deviation (SD) 1.52 ± 0.30 mmHg) and diastolic blood pressure (DBP, MAE ± SD 1.83 ± 0.50), and its performance agreed with standard criteria of MAE within 5 mmHg and SD within ±8 mmHg. In conclusion, this study successfully developed a low-cost, high-accuracy piezoelectric-based system for continuous beat-to-beat SBP and DBP measurement without multiple calibrations and complex regression analysis. The system is potentially suitable for continuous, long-term blood pressure-monitoring applications.