TinyML-Based Classification in an ECG Monitoring Embedded System

Recently, the development of the Internet of Things (IoT) hasenabled continuous and personal electrocardiogram (ECG) monitoring. In theECG monitoring system, classification plays an important role because it canselect useful data (i.e., reduce the size of the dataset) and identify abnormaldata that can be used to detect the clinical diagnosis and guide furthertreatment. Since the classification requires computing capability, the ECGdata are usually delivered to the gateway or the server where the classificationis performed based on its computing resource. However, real-time ECG datatransmission continuously consumes battery and network resources, whichare expensive and limited. To mitigate this problem, this paper proposes atiny machine learning (TinyML)-based classification (i.e., TinyCES), wherethe ECG monitoring device performs the classification by itself based onthe machine-learning model, which can reduce the memory and the networkresource usages for the classification. To demonstrate the feasibility, afterwe configure the convolutional neural networks (CNN)-based model usingECG data from the Massachusetts Institute of Technology (MIT)-Beth IsraelHospital (BIH) arrhythmia and the Physikalisch Technische Bundesanstalt(PTB) diagnostic ECG databases, TinyCES is validated using the TinyMLsupportedArduino prototype. The performance results show that TinyCEScan have an approximately 97% detection ratio, which means that it has greatpotential to be a lightweight and resource-efficient ECG monitoring system.

Analgesic efficacy of median nerve stimulation in mice with chemotherapy-induced peripheral neuropathy via modulation of brain-derived neurotrophic factor expression

OBJECTIVE:Chemotherapeutic agents such as docetaxel(DTX)can trigger chemotherapy-induced peripheral neuropathy(CIPN),which is characterized by unbearable pain.This study was designed to investigate the analgesic effect and related neuronal mechanism of low-frequency median nerve stimulation(LFMNS)on DTX-induced tactile hypersensitivity in mice.METHODS:To produce CIPN,DTX was administered intraperitoneally 4 times,once every 2 d,to male ICR mice.LFMNS was performed on the wrist area,and the pain response was measured using von Frey filaments on both hind paws.Western blot and immunofluorescence staining were performed using dorsal root ganglion and spinal cord samples to measure the expression of brainderived neurotrophic factor(BDNF).RESULTS:Repeated LFMNS significantly attenuated the DTX-induced abnormal sensory response and suppressed the enhanced expression of BDNF in the DRG neurons and spinal dorsal area.CONCLUSIONS:LFMNS might be an effective nonpharmaceutical option for treating patients suffering from CIPN via regulating the expression of peripheral and central BDNF.