Portable Dynamometer-Based Measurement of Pelvic Floor Muscle Force.

OBJECTIVE: In attempts to improve the quality of life of women, continuous projects are sought between rehabilitation intervention and engineering. Using the knowledge of the pelvic floor muscle (PFM) physiology, assessment and training methods are developed to reduce lower urinary tract symptoms such as urinary incontinence. Therefore, this paper covers the design and implementation of a portable vaginal dynamometer. METHODS: A PFM probe is designed, 3D printed, assembled, and tested in ten women to assess its acceptability and usability. The feedback from the usability study is used to optimize the PFM probe design. A vaginal dynamometer is developed based on the designed PFM probe, then tested for linearity, repeatability, hysteresis, noise and heat effect, and power consumption. The variability between the different produced PFM probe prototypes is evaluated. RESULTS: Force measurements are made using a load cell. Wireless communication is performed through a Bluetooth low energy transceiver v5.0, with a corresponding interface on both computer and smartphone. The device operates at a 3.3V supply and achieves a power consumption of 49.5 mW in operating mode. Two PFM probe sizes are designed to accommodate different vaginal hiatus sizes, based on usability study feedback. The proposed system allows the physiotherapist to wirelessly monitor variation in pelvic floor muscle force during assessment and/or training. DISCUSSION/CONCLUSION: The testing results showed that the newly designed system has the potential to measure the PFM function in functional conditions such as the standing position.

Tiny CNN for Seizure Prediction in Wearable Biomedical Devices.

Epilepsy is a life-threatening disease affecting millions of people all over the world. Artificial intelligence epileptic predictors offer excellent potential to improve epilepsy therapy. Particularly, deep learning models such as convolutional neural networks (CNN) can be used to accurately detect ictogenesis through deep structured learning representations. In this work, a tiny one-dimensional stacked convolutional neural network (1DSCNN) is proposed based on short-time Fourier transform (STFT) to predict epileptic seizure. The results demonstrate that the proposed method obtains better performance compared to recent state-of-the-art methods, achieving an average sensitivity of 94.44%, average false prediction rate (FPR) of 0.011/h and average area under the curve (AUC) of 0.979 on the test set of the American Epilepsy Society Seizure Prediction Challenge dataset, while featuring a model size of only 21.32kB. Furthermore, after adapting the model to 4-bit quantization, its size is significantly decreased by 7.08x with only 0.51% AUC score precision loss, which shows excellent potential for hardware-friendly wearable implementation.

Optimizing the Energy Efficiency of Unreliable Memories for Quantized Kalman Filtering.

This paper presents a quantized Kalman filter implemented using unreliable memories. We consider that both the quantization and the unreliable memories introduce errors in the computations, and we develop an error propagation model that takes into account these two sources of errors. In addition to providing updated Kalman filter equations, the proposed error model accurately predicts the covariance of the estimation error and gives a relation between the performance of the filter and its energy consumption, depending on the noise level in the memories. Then, since memories are responsible for a large part of the energy consumption of embedded systems, optimization methods are introduced to minimize the memory energy consumption under the desired estimation performance of the filter. The first method computes the optimal energy levels allocated to each memory bank individually, and the second one optimizes the energy allocation per groups of memory banks. Simulations show a close match between the theoretical analysis and experimental results. Furthermore, they demonstrate an important reduction in energy consumption of more than 50%.