Fig 4 - uploaded by S.C. Mukhopadhyay
Content may be subject to copyright.
Source publication
In this article, a smart wireless sensing non-invasive system for estimating the amount of fluid loss, a person experiences while physical activity is presented. The system measures three external body parameters, Heart Rate, Galvanic Skin Response (GSR, or skin conductance), and Skin Temperature. These three parameters are entered into an empirica...
Contexts in source publication
Context 1
... the participant s height and weight so their BMI could be calculated. Have the participants place their hand on the device shown in Fig. 4 and take initial readings for heart rate, GSR, and skin ...
Context 2
... is a company who are in the process of de- veloping a polymer that will expand and contract when in the presence of certain substances in bodily fluids. This expanding polymer will actuate a micro strain gauge that will produce a changing resistance that can be measured and equated to a hydration level. The device is not publicly available now as it is still in its prototyping phase [13]. There is a current patent for a device that judges whether a person is dehydrated according to changes in their bioelectric impedance, as well as the body temperature [12]. The device appears complicated to set up and use as well as being bulky. A smart wireless sensing dehydration measuring system has been designed and developed. The Fig. 4 shows the developed ...
Citations
... They then extract multiple features from the acquired PPG data using the variable frequency complex demodulation algorithm, feed them to a support vector machine classifier, and report an accuracy of 67.91%. [16] collects the EDA data, skin temperature, heart rate and body mass index from 16 participants while they undergo a workout/physical activity known as circuit training. It then feeds this data to an empirically derived formula in order to quantify fluid loss (dehydration) caused by physical activity. ...
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.
... Suryadevara et al. [8] presented a smart, wireless, and noninvasive sensing system to estimate the amount of fluid loss that a person experiences while performing a physical activity. The system measures three external body parameters-heart rate, Galvanic Skin Response (GSR), and skin conductance-and the skin temperature. ...
Wearable smart devices are widely used to determine various physico-mechanical parameters at chosen intervals. The proliferation of such devices has been driven by the acceptance of enhanced technology in society. Despite the exponential growth of wearable sensors, there are limitations in terms of the broader aspects of their commercialized uses, which need improvement to further enhance the field of wearable electronics. The Internet of Things (IoT) is responsible for connecting smart objects around the world and has led to the proliferation of these smart objects over the last two decades. This Special Issue aims to present the issues and challenges faced by the currently proposed IoT-based systems in addition to state-of-the-art research on the com-mercialization of the current systems. This editorial summarizes the published papers in this Special Issue on Wearable Sensors and Systems on the Internet of Things theme of applications. The global market for Internet of things (IoT) technology reached USD 100 billion for the first time in 2017, with a forecast to further grow to around USD 1.6 trillion by 2025, according to [1]. The global internet of things in the healthcare market was valued at USD 113.75 billion in 2019 and is expected to reach USD 332.67 billion by 2027, registering a compound annual growth-rate of 13.20% from 2020 to 2027 according to [2]. Human-activity monitoring is a vibrant area of research with the potential for commercial development, which is discussed by Mukhopadhyay [3]. It is expected that many more lightweight, robust, and efficient wearable devices will be available for monitoring a wide range of activities. The development of lightweight physiological sensors will lead to the formation of comfortable wearable systems to monitor different ranges of inhabitant-related activities. Formal and informal surveys predict an increase in the interest in, and consequently usage of, wearable devices in the near future, where the cost of such devices is expected to fall with an increased use. Wearable devices have been a state-of-the-art technology and associated with IoT for quite some time. The full range of new capabilities of these IoT-based wearable sensors has been realized every day for their pervasive connectivity. Traditional remote healthcare information systems involve data transfer, signal processing mechanisms , and naive machine learning models deployed on remote servers to process the medical data of patients. Some of the shortcomings of this technique include an un-suitability for resource-constrained wearable IoT devices. Resources such as processing , memory, energy, and networking capability are limited in wearable IoT (WIoT) devices. Citation: Mukhopadhyay, S.C.; Suryadevara, N.K.; Nag, A. Wearable Sensors and Systems in the IoT. Sensors 2021, 21, 7880.
... The value of Cv is2.68. Cv value is 2.97 and pH buffer tuning is 0.17 The voltage in the sensor was displayed as the human body a large resistor [76]. The output system from microcontroller is influenced on the voltage. ...
... Moreover, urine resistance can be used as a particular parameter for pH measurement. According to [76,78] sensor detection in human urine depends on the voltage output divider equation which every human urine has a different resistor. Several previous study from [59,60] have reported that the diagnosis smart sensing to detect creatinine level using a sensor is depended on voltage output on creatinine. ...
... The workings of this sensors are to use a heater contained in the sensor section when exposed to ammonia gas (NH 3 ), the value of the resistance of the sensor will change. The urine testing was applied in the morning to know urine quality like as explained in Section 1. Ammonia concentration in urine was used for the first detection of diseases like kidney, urinary tract disorders, and gastrointestinal bleeding [76]. The use of ammonia sensors may decrease cost, more flexible and disposable sensing platform that can be validated easier [78]. ...
Urine can be used to diagnose diabetes in a non-invasively manner. This study aims to create a quality urine detection based on urine pH, turbidity, and ammonia concentration by using multi-sensor: pH4502C to measure pH level, turbidity sensor to measure urine turbidity, and MQ-137 to measure ammonia concentration. Urine samples of 15 subjects were collected early in the morning before doing any activities. For the experiment, all sensors can be read analog signals which are received by an Arduino Nano as a micro-controller and converted into digital values in the form of pH scale, Nephelometric Turbidity Units (NTU), and parts per million (ppm). These values are displayed on the LCD display. Our experiments showed that the measured sensor using the system was compared with the calculated sensor from a manual calculation using an equation. These comparisons were used to know the error percentage. The experiment results found that the average of error percentage from pH sensor, turbidity sensor, and ammonia sensor was 0.0061% (very small), 5.098% (very small), and 1.679% (very small), respectively. The urine measurement from 15 subjects was obtained pH urine of 5.6293, Turbidity urine of 0.59 NTU, and ammonia urine of 0.66 ppm. The accuracy of pH sensor, ammonia sensor, and turbidity sensor are 97.693%, 98.321%, and 97.095%. All sensors were proved capable to measure the quality of human urine. However, the measurement results are sensitive to the voltage of the sensor.
... The purpose of this study was to evaluate the feasibility of using autonomic responses to cognitive stress for the assessment of mild dehydration. A previous study attempted to assess dehydration that was produced by physical activity through the use of parameters that were obtained from heart rate, electrodermal activity (EDA), skin temperature, and body mass index by using an empirical formula [15]. The protocol only achieved a fluid loss of 0.53 in average, and the regression model fitted to predict fluid loss was not validated. ...
The feasibility of detecting mild dehydration by using autonomic responses to cognitive stress was studied. To induce cognitive stress, subjects (n = 17) performed the Stroop task, which comprised four minutes of rest and four minutes of test. Nine indices of autonomic control based on electrodermal activity (EDA) and pulse rate variability (PRV) were obtained during both the rest and test stages of the Stroop task. Measurements were taken on three consecutive days in which subjects were “wet” (not dehydrated) and “dry” (experiencing mild dehydration caused by fluid restriction). Nine approaches were tested for classification of “wet” and “dry” conditions: (1) linear (LDA) and (2) quadratic discriminant analysis (QDA), (3) logistic regression, (4) support vector machines (SVM) with cubic, (5) fine Gaussian kernel, (6) medium Gaussian kernel, (7) a k-nearest neighbor (KNN) classifier, (8) decision trees, and (9) subspace ensemble of KNN classifiers (SE-KNN). The classification models were tested for all possible combinations of the nine indices of autonomic nervous system control, and their performance was assessed by using leave-one-subject-out cross-validation. An overall accuracy of mild dehydration detection was 91.2% when using the cubic SE-KNN and indices obtained only at rest, and the accuracy was 91.2% when using the cubic SVM classifiers and indices obtained only at test. Accuracy was 86.8% when rest-to-test increments in the autonomic indices were used along with the KNN and QDA classifiers. In summary, measures of autonomic function based on EDA and PRV are suitable for detecting mild dehydration and could potentially be used for the noninvasive testing of dehydration.
... As mentioned earlier, the test can't be conducted when alcohol vapor is present in the breath. Lee et al [31] have studied the fabrication and characteristics of SnO 2 gas sensor array for many VOCs. ...
BREATH ACETONE-BASED NON-INVASIVE DETECTION OF BLOOD GLUCOSE LEVELS
... As mentioned earlier, the test can't be conducted when alcohol vapor is present in the breath. Lee et al [31] have studied the fabrication and characteristics of SnO 2 gas sensor array for many VOCs. ...
There has been a constant demand for the development of non-invasive, sensitive glucose sensor system that offers fast and real-time electronic readout of blood glucose levels. In this article, we propose a new system for detecting blood glucose levels by estimating the concentration of acetone in the exhaled breath. A TGS822 tin oxide (SnO 2) sensor has been used to detect the concentration of acetone in the exhaled air. Acetone in exhaled breath showed a correlation with the blood glucose levels. Effects of pressure, temperature and humidity have been considered. Artificial Neural Network (ANN) has been used to extract features from the output waveform of the sensors. The system has been trained and tested with patient data in the blood glucose ranges from 80 mg/dl to 180 mg/dl. Using the proposed system, the blood glucose concentration has been estimated within an error limit of ±7.5 mg/dl.
... Solar temperature sensors are connected outside the house to keep a note of the ambiance temperature. Extensive research work [100][101][102][103][104][105][106][107][108][109][110][111][112][113][114][115][116][117][118][119] has been carried regarding the designing and functioning of a smart home. Realtime data collection and analysis is done to decrease the complexity of the system and deal with the integral parameters like power management, cost effectiveness and to make the system more user friendly. ...
The technological advancement in the past three decades has impacted our lives and wellbeing significantly. Different aspects of monitoring our physiological parameters are considered. Wearable sensors are one of its most important areas that have an ongoing trend and have a huge tendency to rise in the future. The wearable sensors are the externally used devices attached to any individual to measure physiological parameters of interest. The range of wearable sensors varies from minuscule to large scaled devices physically fitted to the user operating on wired or wireless terms. Many common diseases affecting large number of people notably gait abnormalities, Parkinson's disease are analysed by the wearable sensors. The use of wearable sensors has got a better prospect with improved technical qualities and a better understanding of the currently used research methodologies. This chapter deals with the overview of the current and past means of wearable sensors with its associated protocols used for communication. It concludes with the ways the currently dealt wearable sensors can be improved in future.
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 reflected RF signals. 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 classify each subject as either hydrated or dehydrated. To train our ML classifiers, we have constructed our custom dataset by collecting data from 5 Muslim subjects who were fasting during the month of Ramadan. Specifically, we have implemented and tested the following ML classifiers: k-nearest neighbour, support vector machine, decision tree, ensemble classifier, and a neural network classifier. Among all the classifiers, the neural network classifier achieved the best classification accuracy, i.e., an accuracy of 93.8% (96.15%) for the proposed chest-based (hand-based) method. Compared to prior contact-based method where the reported accuracy is 97.83%, our proposed non-contact method provides slightly less accuracy than that of reported in the literature for contact-based method; nevertheless, the advantages of our non-contact dehydration method speak for themselves.
Wearable wrist type health monitoring devices use photoplethysmography (PPG) signal to estimate heart rate (HR). The HR estimation from these devices becomes difficult due to the existence of strong motion artifacts (MA) in PPG signal thereby leading to inaccurate HR estimation. The objective is to develop a novel de-noising algorithm that reduces the MA present in PPG signal, resulting in an accurate HR estimation. A novel de-noising technique using the hierarchical structure of cascade and parallel combinations of two different pairs of adaptive filters which reduces MA from the PPG signal and improves HR estimation is proposed. The first pair combines normalized least mean squares (NLMS) and recursive least squares (RLS) adaptive filters and the second pair combines recursive least squares (RLS) and least mean squares (LMS) adaptive filters. The de-noised signals obtained from the first and second pairs are combined to form a single de-noised PPG signal by means of convex combination. The HR of the de-noised PPG signal is estimated in the frequency domain using a Fast Fourier transform (FFT). Performance of the proposed technique is evaluated using a dataset of 12 individuals performing running activity in Treadmill. It resulted in an average absolute error of 0.92 beats per minute (BPM), standard deviation of the absolute error of 1.17 beats per minute (BPM), average relative error of 0.72 and Pearson correlation coefficient of 0.9973.
The exploitation of electrical equipment and the emergence of New Information and Communication Technologies (NICT), which led to a significant increase in electricity consumption. This article presents a decision-making tool for the choice of energy consumption, which makes it possible to ensure better energy efficiency. It examines how the semantic Web approach can be used to represent information about a resident, energy, behavior, and activities of residents. Ontology is the main element in this work because it represents information about concepts, properties, and relationships between concepts. This approach offers several advantages, such as sharing and reusing knowledge for good decision-making. We chose OWL (Ontology Web Language) for the formal representation of knowledge, SWRL rules (Semantic Web Rules) to present the intelligent reasoning of the solution, finally, the software Protégé2000 is used for the edition of knowledge. We applied our solution to a residence located in the city of Adrar in Algeria. This city is characterized by a climate and human activities specific to the region; these two characteristics have a great influence on the consumption of energy.
