Advances in flexible and printable sensor technologies have made it possible to use posture classification for providing timely services in digital healthcare, especially for bedsores or decubitus ulcers. However, managing a large amount of sensor data and ensuring accurate predictions can be challenging. While lossy compressors can reduce data volume, it is still unclear whether this would lead to losing important information and affect downstream application performance. In this paper, we propose LCDNN (Lossy Compression using Deep Neural Network) to reduce the size of sensor data and evaluate the performance of posture classification models. Our sensors, placed under hospital beds, have a thickness of just 0.4mm and collect pressure data from 28 sensors (7 by 4) at an 8 Hz cycle, categorizing postures into 4 types from 5 patients. Our evaluation, which includes reduced datasets by LCDNN, demonstrates that the results are promising.
more »
« less
Effective Posture Classification using Statistically Significant Data from Flexible Pressure Sensors
Advancements in flexible and printable sensor technologies to overcome the limitations of conventional rigid counterparts offer an excellent opportunity to design various healthcare applications for humans, and their potential flexibility can be used in real-time health monitoring and personalized physical conditions with minimal or no inconvenience. However, managing a large volume of obtained sensor datasets and ensuring accurate predictions can take time and effort. While statistical analysis and the Pearson correlation coefficient can reduce data volume, whether this would lead to losing important information and affect downstream application performance is still being determined. In this paper, we use posture classification as an exemplar of timely services in digital healthcare, especially for bedsores or decubitus ulcers. Our sensors, placed under hospital beds, have a thickness of just 0.4mm and collect pressure data from 28 sensors (7 by 4) at an 8 Hz cycle, categorizing postures into 4 types from 5 patients. We then collected sensor data to explore the possibility of using a small number of pressure sensors for patient posture classification. Next, we apply a statistical analysis to the datasets obtained to select the featured sensor data cells and evaluate the performance of posture classification models on various groups of sensors. Our evaluation involves the analysis of reduced datasets through statistical methods and the Pearson correlation coefficient. The classification performance using datasets comprising 5 featured and 28 sensors are 0.93 and 0.99, respectively. These results suggest comparable performance and the viability of useful classifiers for both cases. Consequently, comparable posture classification performance can be achieved using only 17.9% of the entire dataset.
more »
« less
- Award ID(s):
- 1751143
- PAR ID:
- 10510883
- Publisher / Repository:
- IEEE
- Date Published:
- Journal Name:
- IEEE Journal on Flexible Electronics
- ISSN:
- 2768-167X
- Page Range / eLocation ID:
- 1 to 1
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The purpose of this study was to evaluate the use of compressible soft robotic sensors (C-SRS) in determining plantar pressure to infer vertical and shear forces in wearable technology: A ground reaction pressure sock (GRPS). To assess pressure relationships between C-SRS, pressure cells on a BodiTrakTM Vector Plate, and KistlerTM Force Plates, thirteen volunteers performed three repetitions of three different movements: squats, shifting center-of-pressure right to left foot, and shifting toes to heels with C-SRS in both anterior–posterior (A/P) and medial–lateral (M/L) sensor orientations. Pearson correlation coefficient of C-SRS to BodiTrakTM Vector Plate resulted in an average R-value greater than 0.70 in 618/780 (79%) of sensor to cell comparisons. An average R-value greater than 0.90 was seen in C-SRS comparison to KistlerTM Force Plates during shifting right to left. An autoregressive integrated moving average (ARIMA) was conducted to identify and estimate future C-SRS data. No significant differences were seen in sensor orientation. Sensors in the A/P orientation reported a mean R2 value of 0.952 and 0.945 in the M/L sensor orientation, reducing the effectiveness to infer shear forces. Given the high R values, the use of C-SRSs to infer normal pressures appears to make the development of the GRPS feasible.more » « less
-
Abstract Wearable electromechanical sensors are essential to improve health monitoring and off‐site point‐of‐care applications. However, their practicality is restricted by narrow ranges of detection, failure to simultaneously sense static and dynamic pressures, and low durability. Here, an all‐fabric pressure sensor with high sensitivity in a broad range of pressures, from subtle heart pulses to body posture, exceeding that of previously‐reported sensors is introduced. By taking advantage of chemical vapor deposition of p‐doped poly(3,4‐ethylenedioxythiophene) chloride (PEDOT‐Cl) on two natural textiles (cotton gauze and cotton balls), multiscale tunable pressure sensitivity with low power demand for data read‐out is obtained. To protect the sensor against humidity induced degradations, the sensor is encapsulated with a hydrophobic coating that leads to ultrastability of the sensor performance even after 1 week of exposure to 100% relative humidity and 20 laundry cycles. The sensor reveals excellent performance retention of >99% over 70 000 bending cycles under ambient conditions. The varied utility of this sensor for health monitoring is demonstrated by recording heartbeats, respiration, and joint movements. Furthermore, using this sensor, grip strength is successfully detected by 93.6% accuracy as compared to commercial dynamometer, speaking of its potential as the first fabric‐based sensor allowing for personalized real‐time grip strength analysis.more » « less
-
null (Ed.)Edge devices with attentive sensors enable various intelligent services by exploring streams of sensor data. However, anomalies, which are inevitable due to faults or failures in the sensor and network, can result in incorrect or unwanted operational decisions. While promptly ensuring the accuracy of IoT data is critical, lack of labels for live sensor data and limited storage resources necessitates efficient and reliable detection of anomalies at edge nodes. Motivated by the existence of unique sparsity profiles that express original signals as a combination of a few coefficients between normal and abnormal sensing periods, we propose a novel anomaly detection approach, called ADSP (Anomaly Detection with Sparsity Profile). The key idea is to apply a transformation on the raw data, identify top-K dominant components that represent normal data behaviors, and detect data anomalies based on the disparity from K values approximating the periods of normal data in an unsupervised manner. Our evaluation using a set of synthetic datasets demonstrates that ADSP can achieve 92%–100% of detection accuracy. To validate our anomaly detection approach on real-world cases, we label potential anomalies using a range of error boundary conditions using sensors exhibiting a straight line in Q-Q plot and strong Pearson correlation and conduct a controlled comparison of the detection accuracy. Our experimental evaluation using real-world datasets demonstrates that ADSP can detect 83%– 92% of anomalies using only 1.7% of the original data, which is comparable to the accuracy achieved by using the entire datasets.more » « less
-
Accurate balance assessment is important in healthcare for identifying and managing conditions affecting stability and coordination. It plays a key role in preventing falls, understanding movement disorders, and designing appropriate therapeutic interventions across various age groups and medical conditions. However, traditional balance assessment methods often suffer from subjectivity, lack of comprehensive balance assessments and remote assessment capabilities, and reliance on specialized equipment and expert analysis. In response to these challenges, our study introduces an innovative approach for estimating scores on the Modified Clinical Test of Sensory Interaction on Balance (m-CTSIB). Utilizing wearable sensors and advanced machine learning algorithms, we offer an objective, accessible, and efficient method for balance assessment. We collected comprehensive movement data from 34 participants under four different sensory conditions using an array of inertial measurement unit (IMU) sensors coupled with a specialized system to evaluate ground truth m-CTSIB balance scores for our analysis. This data was then preprocessed, and an extensive array of features was extracted for analysis. To estimate the m-CTSIB scores, we applied Multiple Linear Regression (MLR), Support Vector Regression (SVR), and XGBOOST algorithms. Our subject-wise Leave-One-Out and 5-Fold cross-validation analysis demonstrated high accuracy and a strong correlation with ground truth balance scores, validating the effectiveness and reliability of our approach. Key insights were gained regarding the significance of specific movements, feature selection, and sensor placement in balance estimation. Notably, the XGBOOST model, utilizing the lumbar sensor data, achieved outstanding results in both methods, with Leave-One-Out cross-validation showing a correlation of 0.96 and a Mean Absolute Error (MAE) of 0.23 and 5-fold cross-validation showing comparable results with a correlation of 0.92 and an MAE of 0.23, confirming the model’s consistent performance. This finding underlines the potential of our method to revolutionize balance assessment practices, particularly in settings where traditional methods are impractical or inaccessible.more » « less