Personal Health Monitoring Research Articles

Blockchain for the Management of Internet of Things Devices in the Medical Industry

With the recent emergence of the smart healthcare era, and patients relying more on personalized health monitoring based on Internet of Medical Things (IoMT) devices; patients’ lives are becoming highly threatened in case they fall victim to counterfeit devices. Thus, verifying whether these body sensors utilized are authentic and reliable in an unimpeachable, credible, and auditable manner without any centralized management is of crucial importance. Furthermore, manipulating data and hijacking in an IoMT context are also of tremendous criticality. Motivated by the aforementioned challenges, in this article, a smart contract-based scalable authentication scheme dedicated for IoMT devices is proposed. The scheme mitigates the deficiencies of the traditional established systems that are extensively built on centralized approaches, vulnerable to distributed denial of service attacks, by leveraging blockchain’s decentralization and security properties. The scheme ensures confidentiality, anonymity, and privacy as it is built on a consortium blockchain and integrity by offering secure firmware updates and protects patients from counterfeit devices by leveraging the physical unclonable function. The authentication approach was implemented on Ethereum and evaluated with regard to its computation and communication costs to prove its feasibility and effectiveness as well as its security by presenting a formal analysis using ProVerif.

A portable aptasensor for facile personalized monitoring of serum uric acid

Uric acid (UA) is an important antioxidant to balance the oxidative stress of human body. Although UA exists mainly in human urine, serum UA is much more stable and is of higher clinical value. Since UA is associated with multiple diseases, methods capable of rapid and accurate detection of UA are of great importance for personalized health monitoring. Herein, a dual-FRET aptasensor with low signal background was developed for serum UA detection. It exhibited high selectivity against small molecules with similar redox potential or structures, as well as the main components in serum. For clinical serum samples analysis, the results by the proposed aptasensor were in good agreement with those by the hospital assay. To facilitate personalized health monitoring, a 3D-printed device was developed for the aptasensor, and an RGB-based cell phone App was designed for signal readout. The portable aptasensor could detect serum UA within 10 min, and the results for serum samples were also in consistent with the hospital assay. Moreover, with the portable aptasensor, it was confirmed that serum UA was more stable than urinary UA, and thus was more clinically relevant for personalized diagnosis.

Robust and flexible smart silk/PEDOT conductive fibers as wearable sensor for personal health management and information transmission

Flexible highly conductive fibers have attracted much attention due to their great potential in the field of wearable electronic devices. In this work, silk/PEDOT conductive fibers with a resistivity of 1.73 Ω·cm were obtained by oxidizing Ce3+ with H2O2 under alkaline conditions to produce CeO2 and further promote the in-situ polymerization of 3,4-ethylenedioxythiophene (EDOT) on the surface of silk fibers. The morphology and chemical composition of the silk/PEDOT conductive fibers were characterized and the results confirmed that a large amount of polythiophene was synthesized and deposited on the surface of silk fibers. The conductivity and electrochemical property stability of the silk/PEDOT conductive fibers were evaluated by soaping and organic solvent immersion, and the conductive silk fibers exhibited excellent environmental stability and durability. The silk/PEDOT conductive fibers show good pressure sensing and strain sensing performance, which exhibits high sensitivity, fast response and cyclability, and have excellent applications in personal health monitoring, human-machine information transmission, etc.

Thermoplastic Elastomers for Wireless, Skin‐Interfaced Electronic, and Microfluidic Devices

AbstractWireless, skin‐interfaced electronic and microfluidic devices have the potential to replace wired, bulky, and cumbersome technologies for personal and clinical health monitoring, allowing care to extend from hospital settings to the home. For use on skin, these devices commonly employ silicone‐based thermoset elastomers (TSEs) as layers that encapsulate the electronics or serve as molded microchannels for biofluid (e.g., sweat) capture, storage, and analysis. Barriers to commercial adoption of such devices include difficulties in use of these elastomers in conventional practices for mass manufacturing. Their relatively high cost and inability to allow for recycling represent additional disadvantages. By contrast, thermoplastic elastomers (TPEs) are fully compatible with industrial‐scale manufacturing processes, low in cost, and recyclable. Like TSEs, TPEs are soft, stretchable, flexible, and optically transparent, while possessing other properties well‐suited for applications in wireless, skin‐interfaced devices. Herein, the characteristics, processing, and application techniques for three commercially available TPEs, including two thermoplastic polyurethanes as encapsulation layers for a wireless skin hydration sensor and one thermoplastic styrenic block copolymer for a microfluidic sweat analysis platform, are reported. The results demonstrate that TPEs can be effectively integrated into these classes of devices, as a compelling alternative to TSEs, as a mass‐manufacturable, sustainable materials option.

Ultrafast fabrication of deep eutectic solvent flexible ionic gel with high-transmittance, freeze-resistant and conductivity by frontal polymerization

As a common flexible sensing device, gels are widely used in electronic skin, personalized health monitoring, and smart manufacturing. However, gel suffers from temperature sensitivity, long polymerization times or thickness limitations. Deep eutectic solvents (DESs) have abundant hydrogen bond networks and low saturated vapor pressure, which can accelerate the frontal polymerization of ionic gels, and overcome the temperature sensitivity problem. Here, we showed how choline chloride (ChCl)-glycerol (Gly) DES can be used to create ionic gels with different properties and functions by combining them with different monomers (acrylamide (AM), acrylic acid (AA) and itaconic acid (IA)). Subsequently, we revealed the rapid gelation mechanism of PAM-ChCl-Gly ionic gel from multiple perspectives by density functional theory and molecular dynamics simulation, which was then applied to flexible sensing. The experimental results showed that the PAM-ChCl-Gly ionic gel had excellent tensile properties, high transparency, self-adhesion and stability. In addition, its gelation time was only 90 s without heating. ChCl-Gly DES offered a plentiful and stable hydrogen bonding network. PAM-ChCl-Gly ionic gels can detect tiny pressure and strain changes, making them suitable for flexible sensing. This greatly enriched the theoretical research foundation of DES-based ionic gels and broadened their application areas.

Caffeic acid induced in-situ growth of AgNWs on cotton fabric for temperature and pressure sensing and electrical interference shielding

In recent years, smart wearable devices with thermal management, sensing response, and electromagnetic interference (EMI) shielding have gained great attention in multiple fields. In this work, high aspect ratios AgNWs with a diameter of 40 ∼ 60 nm and a length of 40 ∼ 60 μm generated in situ on the surface of cotton fabrics at room temperature using caffeic acid as reducing agent and anchoring agent, and polyvinypyrrolidone (PVP) as template agent. The preparation method is green, low cost and easy to scale up. The resulting flexible silver nanowire/cotton fabric (AgNW/cotton fabric) with a sheet resistance of 0.23 Ω/sq possesses good physical properties, excellent and durable stability of electrical conductivity. The prepared flexible AgNW/cotton fabric show good temperature and pressure sensing performance. Temperature sensing performance of AgNW/cotton fabric allows it to be used as a temperature alarm in agricultural greenhouses and textile fire. Pressure sensing of AgNW/cotton fabric exhibits high sensitivity (∼-53 % kPa−1), fast response (100 ms), low detection limit (73.1 mg) and recyclability, which reveals its potential practical value for personal health monitoring, human–computer interaction and entertainment. AgNW/cotton fabric can quickly reach 54.8 °C and 86.2 °C through electrical-thermal and photo-thermal conversions, respectively, which is hopefully used as a wearable heater for self-heating garments and smart heat therapy. Additionally, AgNW/cotton fabric exhibits an EMI shielding efficiency of 38.2 dB in X-band. AgNW/cotton fabrics have great potential in manufacturing flexible, breathable and multi-functional flexible wearable textile devices.

Passive sweat wearable: A new paradigm in the wearable landscape toward enabling "detect to treat" opportunities.

Growing interest over recent years in personalized health monitoring coupled with the skyrocketing popularity of wearable smart devices has led to the increased relevance of wearable sweat-based sensors for biomarker detection. From optimizing workouts to risk management of cardiovascular diseases and monitoring prediabetes, the ability of sweat sensors to continuously and noninvasively measure biomarkers in real-time has a wide range of applications. Conventional sweat sensors utilize external stimulation of sweat glands to obtain samples, however; this stimulation influences the expression profile of the biomarkers and reduces the accuracy of the detection method. To address this limitation, our laboratory pioneered the development of the passive sweat sensor subfield, which allowed for our progress in developing a sweat chemistry panel. Passive sweat sensors utilize nanoporous structures to confine and detect biomarkers in ultra-low sweat volumes. The ability of passive sweat sensors to use smaller samples than conventional sensors enable users with sedentary lifestyles who perspire less to benefit from sweat sensor technology not previously afforded to them. Herein, the mechanisms and strategies of current sweat sensors are summarized with an emphasis on the emerging subfield of passive sweat-based diagnostics. Prospects for this technology include discovering new biomarkers expressed in sweat and expanding the list of relevant detectable biomarkers. Moreover, the accuracy of biomarker detection can be enhanced with machine learning using prediction algorithms trained on clinical data. Applying this machine learning in conjunction with multiplex biomarker detection will allow for a more holistic approach to trend predictions. This article is categorized under: Diagnostic Tools > Diagnostic Nanodevices Nanotechnology Approaches to Biology > Nanoscale Systems in Biology Diagnostic Tools > Biosensing.

Identification of Core Outcome Domains and Design of a Survey Questionnaire to Evaluate Impacts of Digital Health Solutions That Matter to People With Diabetes.

Digital health solutions (DHS) are increasingly used to support people with diabetes (PwD) to help manage their diabetes and to gather and manage health and treatment data. There is a need for scientifically reliable and valid methods to measure the value and impact of DHS on outcomes that matter to PwD. Here, we describe the development of a survey questionnaire designed to assess the perceptions of PwD toward DHS and their prioritized outcomes for DHS evaluation. We applied a structured process for engagement of a total of nine PwD and representatives of diabetes advocacy organizations. Questionnaire development consisted of a scoping literature review, individual interviews, workshops, asynchronous virtual collaboration, and cognitive debriefing interviews. We identified three overarching categories of DHS, which were meaningful to PwD and crucial for the identification of relevant outcomes: (1) online/digital tools for information, education, support, motivation; (2) personal health monitoring to support self-management; (3) digital and telehealth solutions for engaging with health professionals. Overall outcome domains identified to be important were diabetes-related quality of life, distress, treatment burden, and confidence in self-management. Additional positive and negative outcomes specific to DHS were identified and corresponding questions were incorporated into the survey questionnaire. We identified the need for self-reporting of quality of life, diabetes distress, treatment burden, and confidence in self-management, as well as specific positive and negative impacts of DHS. We designed a survey questionnaire to further assess the perceptions and perspectives of people with type 1 and 2 diabetes on outcomes relevant for DHS evaluations.

Mussel-inspired cellulose nanofiber/poly(vinyl alcohol) hydrogels with robustness, self-adhesion and antimicrobial activity for strain sensors

Flexible strain sensors have attracted substantial attention given their application in human-computer interaction and personal health monitoring. Due to the inherent disadvantages of conventional hydrogels, the manufacture of hydrogel strain sensors with high tensile strength, excellent adhesion, self-healing and antimicrobial properties in vitro, and conductive stability is still a challenge. Herein, a conductive hydrogel consisting of polydopamine-coated cellulose nanofibers (CNF@PDA), carbon nanotubes (CNT), and polyvinyl alcohol (PVA) was developed. The CNTs in PVA/CNF@PDA/CNT hydrogels were uniformly dispersed in the presence of CNF@PDA by hydrogen bonding, resulting in a nearly threefold increase in conductivity (0.4 S/m) over hydrogels without PDA. The hydrogel exhibited satisfactory tensile properties (tensile stress up to 0.79 MPa), good fatigue resistance, self-recovery and excellent antimicrobial activity in vitro. It showed excellent adhesion, especially the adhesion strength of pigskin was increased to 27 kPa. In addition, the hydrogel was used as a strain sensor, exhibiting excellent strain sensitivity (strain coefficient = 2.29), fast response (150 ms), and great durability (over 1000 cycles). The fabricated strain sensors can detect both large and subtle human movements (e.g., wrist bending and vocalization) with stable and repeatable electrical signals, indicating potential applications in personal health monitoring.

A Validation Study to Confirm the Accuracy of Wearable Devices Based on Health Data Analysis

This research article presents an analysis of health data collected from wearable devices, aiming to uncover the practical applications and implications of such analyses in personalized healthcare. The study explores insights derived from heart rate, sleep patterns, and specific workouts. The findings demonstrate potential applications in personalized health monitoring, fitness optimization, and sleep quality assessment. The analysis focused on the heart rate, sleep patterns, and specific workouts of the respondents. Results indicated that heart rate values during functional strength training fell within the target zone, with variations observed between different types of workouts. Sleep patterns were found to be individualized, with variations in sleep interruptions among respondents. The study also highlighted the impact of individual factors, such as demographics and manually defined information, on workout outcomes. The study acknowledges the challenges posed by the emerging nature of wearable devices and technological constraints. However, it emphasizes the significance of the research, highlighting variations in workout intensities based on heart rate data and the individualized nature of sleep patterns and disruptions. Perhaps the future cognitive healthcare platform may harness these insights to empower individuals in monitoring their health and receiving personalized recommendations for improved well-being. This research opens up new horizons in personalized healthcare, transforming how we approach health monitoring and management.

Textile and metasurface integrated wide-band wearable antenna for wireless body area network applications

Wireless Body Area Network (WBAN) enhances the quality of life through personal health and remote healthcare monitoring. In this work, we present a numerical model, which is based on CST Microwave Studio simulations, and a fabrication process to achieve a wideband, low-profile, and flexible wearable antenna by integrating textiles with a metasurface (MTS). The performance of the developed antenna was investigated in free space and on a human body (chest, arm, and leg) both numerically and experimentally. The results showed that by incorporating a metasurface structure on the antenna, the simulated gain was improved from 6.1 dBi to 9.08 dBi, while the measured gain was increased from 6.63 dBi to 8.49 dBi. The increased gain in a specific direction is related to more power concentration in that direction. The antenna operates in a bandwidth ranging from 6 to 12 GHz, which is preferred for WBAN applications. The antenna with an MTS structure displayed a more uniform radiation pattern with greater directivity and a Front-to-Back Ratio (FBR) of approximately 15 dB from both numerical and measured results, which is essential for WBAN to avoid back radiation from the body while worn and to increase the wireless signal distance. Additionally, numerical analysis of the bending evaluation for different diameters revealed that its reflection coefficient is not much altered. We believe that the developed structure could assist in the fabrication of unique WBANs and healthcare monitoring devices.

Online continual learning for human activity recognition

Sensor-based human activity recognition (HAR), with the ability to recognise human activities from wearable or embedded sensors, has been playing an important role in many applications including personal health monitoring, smart home, and manufacturing. The real-world, long-term deployment of these HAR systems drives a critical research question: how to evolve the HAR model automatically over time to accommodate changes in an environment or activity patterns. This paper presents an online continual learning (OCL) scenario for HAR, where sensor data arrives in a streaming manner which contains unlabelled samples from already learnt activities or new activities. We propose a technique, OCL-HAR, making a real-time prediction on the streaming sensor data while at the same time discovering and learning new activities. We have empirically evaluated OCL-HAR on four third-party, publicly available HAR datasets. Our results have shown that this OCL scenario is challenging to state-of-the-art continual learning techniques that have significantly underperformed. Our technique OCL-HAR has consistently outperformed them in all experiment setups, leading up to 0.17 and 0.23 improvements in micro and macro F1 scores.

Fabrication of multifunctional cotton textile with battery waste- derived graphene oxide for enhanced joule heating and electromagnetic interference shielding

Nowadays, the research on wearable electronics have received tremendous attraction because of their potential applications in personalized health monitoring and treatment, energy conversion and storage, and human-machine interface system. Herein, we report a facile route for the fabrication of electrically conductive cotton fabric with excellent joule heating and high electromagnetic shielding performances using graphene oxide (GO) and silver nitrate (AgNO3). The GO used in this study is exclusively synthesized from spent batteries in order to minimize the environmental pollution. The surface morphology, elemental analysis, electrical conductivity, thermo-heating behavior and electromagnetic shielding performance have been studied systematically. Due to the high electrical conductivity, the GO-Ag coated cotton with 5 wt% of GO reached high surface temperature of 117.8°C within 35 s, and also it exhibits high electromagnetic interference shielding efficiency value of 79.08 dB. The high flexibility, excellent conductivity, electromagnetic shielding efficiency and joule heating performance of GO-Ag coated cotton fabric suggesting that the GO synthesized from spent batteries will be a potential and valuable resource for the new generation of wearable electronics.

Mixed Method Evaluation of My Vital Cycles®: A Holistic School-Based Ovulatory Menstrual Health Literacy Program.

There is a high prevalence of ovulatory menstrual (OM) dysfunctions among adolescents, and their menstrual health literacy is poor. The OM cycle can be used as a personal health monitor provided that the skills to understand it are correctly taught. My Vital Cycles®, a holistic school-based OM health literacy program, was trialed with a Grade 9 cohort in one single-sex school in Western Australia using the Health Promoting School framework. A validated OM health literacy questionnaire was administered pre- and post-program with 94 participants. Functional OM health literacy improved overall, with 15 out of 20 items showing improvement post-program (p < 0.05). In addition, 19 out of 53 items for interactive OM health literacy, and 18 out of 25 items for critical OM health literacy improved (p < 0.05). The improvement in mood concerns (p = 0.002) was unexpected. Thematic analysis of three focus groups of 18 girls revealed four themes of increasing comfort levels; finding the program informative; inclusion of non-teaching support such as healthcare professionals; and suggestions for future refinements. Overall, this Western Australian PhD project which developed and trialed My Vital Cycles® improved OM health literacy and was positively received. Future research possibilities include understanding the program's impact on mental health and further trials in co-educational settings; amongst different populations; and with extended post-program testing.

Development of a Smart and Ultrafast Flexible Humidity Sensor Using the 0D/2D Au/GeS Heterostructure for Human Respiration Rate Monitoring

We have developed a smart, Internet of Things (IoT)-enabled, intelligent, and flexible humidity sensor for human respiration rate monitoring by using a heterostructure of two-dimensional (2D) germanium(II) sulfide (GeS) and zero-dimensional (0D) gold nanoparticles (Au NPs). The 2D GeS was synthesized by a facile liquid-phase exfoliation process, followed by the post-functionalization of Au NPs. Furthermore, the chemical and structural integrities of the heterostructure were corroborated by microscopic and spectroscopic techniques. The as-prepared heterostructure (termed Au-GeS) exhibited a maximum sensor response of 7102% at 90% of relative humidity (RH) level compared to the pristine GeS sensor response of 2700% at the same RH level. Finally, we demonstrate the use of the Au-GeS flexible humidity sensor for human respiration rate monitoring. The sensor showed an ultrafast response and recovery times of 0.69 and 0.73 s, respectively, during exhalation and inhalation. The sensor was further integrated into a portable electronic system to facilitate IoT-enabled real-time wireless sensing at the smartphone application interface. In our study, the excellent sensor performance with a simple fabrication process offers utilization of the flexible sensor in personal health monitoring.

High-strength, high-toughness regenerated cellulose/graphene oxide nanofluidic membrane with highly oriented and charged nanochannels for wearable sweat-monitoring systems

Nanofluids with directional, selective, and efficient ion-transport properties are widely used in energy-conversion research. However, designing wearable nanofluidic systems for personal health monitoring is challenging owing to the large size of the test equipment, complex preparation process, and stringent biosafety requirements. Herein, we present a bottom-up strategy, integrating structural orientation, densification, and charge, to prepare a robust regenerated cellulose/graphene oxide nanofluidic membrane (TACM) comprising well-aligned nanochannels (3–4 nm) and negatively charged surfaces. The TACM exhibited high strength (76.27 MPa) and toughness (24.56 MJ m−3) as well as excellent ionic conductivity (0.65 S m−1) at low salt concentrations (<0.001 mM), attributed to the selective transport properties of the ordered charged nanochannels for oppositely charged ions, as demonstrated by experiments and finite-element simulations. In addition, we fabricated a sweat-sensing system incorporating the TACM as a core, which successfully monitored sweat changes during various aerobic and anaerobic exercises and provided health alerts. This study contributes toward the application of biomass-based nanofluids in health monitoring and alerting systems.

Flexible planar capacitive devices for hydration and sweat sensing

Skin is one of the most complex structures in the body, with many physiological functions. Skin acts as the barrier or an interface between the external environment and internal organs. Hydration within the skin is varied, known as the skin’s water-loading. Perspiration occurs when watery fluid is secreted through the eccrine and apocrine glands. Flexible epidermal sensors are fabricated, which can be used to measure skin hydration and perspiration (sweat) as these sensors need to be skin-conformable. Polyimide and polydimethylsiloxane are used as they are flexible and skin compliant, and the sensing layer is formed on them. The sensitivity of hydration sensors was in the range of 0.002–0.0046/%, while for sweat sensors, it was in the range of 0.092–0.116 μl−1. Stability tests indicated that external factors such as environment or physical deformation and skin curvature do not affect the performance of the as-prepared sensors. The sensitivity and stability results of the planar capacitor are highly suitable for flexible hydration and sweat-sensing applications. The proposed sensors offer an outstandingly good option for incorporation into wearable systems for physical personal health monitoring. In the future, we plan to integrate these sensors on a single substrate to create a multimodal device.

Intelligent Multifunctional Sensing Systems based on Ordered Macro-Microporous Metal Organic Framework and Its Derivatives.

Compared with nanomaterials-based sensors with single function, the development of multifunctional sensors shows high potential in comprehensive monitoring of personal health and environment, intelligent human-machine interfaces, and realistic imitation of human skin in prosthetics. Ordered macro-microporous metal-organic frameworks (MOFs)-enabled flexible and stretchable electronics are promising candidates for integrated multifunctional sensing systems. Herein, a three-dimensional ordered macro-microporous zeolite imidazolate framework-8 (3DOM ZIF-8) for humidity sensing and the derived ZnO within a hierarchically ordered macroporous-mesoporous-microporous carbon matrix (ZnO@HOMC) for gas sensor is constructed. Benefit from hierarchically ordered macroporous-mesoporous-microporous structure, the active site is fully exposed, and the charge transfer is accelerated. As a result, the multifunctional sensing systems show ultrafast response and recovery speed (10 s and 34 s), high sensitivity (Rair /Rgas = 38.6@50ppm) to acetone, rapid humidity response speed (0.23 s) within changing humidity (RH 21%-99%), excellent stability and repeatability. Furthermore, in order to realize real-time monitoring of gas concentrations and humidity on mobile devices, an intelligent and portable sensor module is fabricated and wirelessly connected to a smartphone to effectively detect acetone concentration and humidity. This sensing technology shows fascinating applications in personal health, fitness tracking, electronic skins, artificial nervous systems, and human-machine interactions.

Controllable-Swelling Microneedle-Assisted Ultrasensitive Paper Sensing Platforms for Personal Health Monitoring.

Microneedle (MN) patches, which allow the extraction of skin interstitial fluid (ISF) without a pain sensation, are powerful tools for minimally invasive biofluid sampling. Herein, an MN-assisted paper-based sensing platform that enables rapid and painless biofluid analysis with ultrasensitive molecular recognition capacity is developed. First, a controllable-swelling MN patch is constructed through the engineering of a poly(ethylene glycol) diacrylate/methacrylated hyaluronic acid hydrogel; it combines rapid, sufficient extraction of ISF with excellent structural integrity. Notably, the analyte molecules in the needles can be recovered into a moist cellulose paper through spontaneous diffusion. More importantly, the paper can be functionalized with enzymatic colorimetric reagents or a plasmonic array, enabling a desired detection capacity-for example, the use of paper-based surface-enhanced Raman spectroscopy sensors leads to label-free, trace detection (sub-ppb level) of a diverse set of molecules (cefazolin, nicotine, paraquat, methylene blue). Finally, nicotine is selected as a model drug to evaluate the painless monitoring of three human volunteers. The changes in the nicotine levels could be tracked, with the levels varying significantly in response to metabolism of the drug in the different volunteers. This as-designed minimally invasive sensing system should open up new opportunities for precision medicine, especially for personal healthcare monitoring. This article is protected by copyright. All rights reserved.

Deep-learning-based gas identification by time-variant illumination of a single micro-LED-embedded gas sensor

Electronic nose (e-nose) technology for selectively identifying a target gas through chemoresistive sensors has gained much attention for various applications, such as smart factory and personal health monitoring. To overcome the cross-reactivity problem of chemoresistive sensors to various gas species, herein, we propose a novel sensing strategy based on a single micro-LED (μLED)-embedded photoactivated (μLP) gas sensor, utilizing the time-variant illumination for identifying the species and concentrations of various target gases. A fast-changing pseudorandom voltage input is applied to the μLED to generate forced transient sensor responses. A deep neural network is employed to analyze the obtained complex transient signals for gas detection and concentration estimation. The proposed sensor system achieves high classification (~96.99%) and quantification (mean absolute percentage error ~ 31.99%) accuracies for various toxic gases (methanol, ethanol, acetone, and nitrogen dioxide) with a single gas sensor consuming 0.53 mW. The proposed method may significantly improve the efficiency of e-nose technology in terms of cost, space, and power consumption.