We report a novel non-contact method for dehydration monitoring. We utilize a transmit software defined radio (SDR) that impinges a wideband radio frequency (RF) signal (of frequency 5.23 GHz) onto either the chest or the hand of a subject who sits nearby. Further, another SDR in the closed vicinity collects the RF signals reflected off the chest (or passed through the hand) of the subject. Note that the two SDRs exchange orthogonal frequency division multiplexing (OFDM) signal, whose individual subcarriers get modulated once it reflects off (passes through) the chest (the hand) of the subject. This way, the signal collected by the receive SDR consists of channel frequency response (CFR) that captures the variation in the blood osmolality due to dehydration. The received raw CFR data is then passed through a handful of machine learning (ML) classifiers which once trained, output the classification result (i.e., whether a subject is hydrated or dehydrated). For the purpose of training our ML classifiers, we have constructed our custom HCDDM-RF-5 dataset by collecting data from 5 Muslim subjects (before and after sunset) who were fasting during the month of Ramadan. Specifically, we have implemented and tested the following ML classifiers (and their variants): K-nearest neighbour (KNN), support vector machine (SVM), decision tree (DT), ensemble classifier, and neural network classifier. Among all the classifiers, the neural network classifier acheived the best classification accuracy, i.e., an accuracy of 93.8% for the proposed CBDM method, and an accuracy of 96.15% for the proposed HBDM method. Compared to prior work where the reported accuracy is 97.83%, our proposed non-contact method is slightly inferior (as we report a maximum accuracy of 96.15%); nevertheless, the advantages of our non-contact dehydration method speak for themselves.

翻译：本文提出了一种新颖的非接触式脱水监测方法。我们利用发射型软件无线电（SDR）将宽带射频信号（频率为5.23 GHz）投射到就近就坐受试者的胸部或手部。同时，另一个近距离的SDR负责采集经受试者胸部反射（或穿透手部）的射频信号。需要指出，两个SDR之间传输的是正交频分复用（OFDM）信号，当信号经胸部反射（或穿透手部）时，其各个子载波会发生调制。通过这种方式，接收SDR采集到的信号包含信道频率响应（CFR），该响应能够反映脱水引起的血液渗透压变化。接收到的原始CFR数据随后被输入多个机器学习（ML）分类器，经过训练后即可输出分类结果（即判定受试者处于水合状态还是脱水状态）。为训练ML分类器，我们构建了专属HCDDM-RF-5数据集，采集了5名在斋月期间禁食的穆斯林受试者（日落前后）的数据。具体而言，我们实现并测试了以下ML分类器（及其变体）：K近邻（KNN）、支持向量机（SVM）、决策树（DT）、集成分类器和神经网络分类器。在所有分类器中，神经网络分类器取得了最佳分类准确率：所提出的CBDM方法准确率为93.8%，HBDM方法准确率为96.15%。相较于先前文献中报告的97.83%准确率，本文提出的非接触式方法（最高准确率96.15%）略逊一筹；然而，本非接触式脱水监测方法的优势不言而喻。