Wearable Biomedical Devices Research Articles

Flexible Organic Molecular Single Crystal-Based Triboelectric Device as a Self-Powered Tactile Sensor.

Triboelectric nanogenerators (TENGs) have proven to be effective at converting mechanical energy into electrical power, making them a viable technology for operating self-powered electronic devices used in medical diagnostics and environmental monitoring. In the present study, we demonstrate the utility of the flexible single crystals of an organic compound for the fabrication of a TENG as a self-powered tactile sensor. Triboelectrification was attained in single crystals as a result of surface functionalization with positively and negatively charged moieties, viz. Zn2+ and F-, respectively, which resulted in a variable surface potential and reversible adhesion through electrostatic interaction and induction phenomena. TENG incorporating the single crystals showed an output voltage of 2.4 V, a current density of ∼2.2 μA/m2, and a power density of ∼850 mW/m2 and was capable of charging commercial capacitors thereby ensuring its ability to be used as a self-powered touch sensor. Capitalizing on these features, a self-powered tactile sensor was fabricated to demonstrate limb movements. The excellent mechano-electric sensitivity (∼102 mV/kPa until 6 kPa range) and response time (∼38 ms) establish the viability of flexible organic single crystals for mechanical energy harvesting and biosensing applications that could pave the way for their utilization as biomedical wearable devices.

Solution-processed MoS2 nanostructures and thermal oxidization on carbon fabric with enhanced thermopower factor for wearable thermoelectric application

Miniaturization of electronic devices has become the new phase of modern technology. Wearable Thermoelectric Generators (WTEG), being flexible, lightweight, self-sustained, and safe are the only replacement for conventional batteries for mobile applications. Molybdenum Disulfide (MoS2), a graphene akin compound having diverse transport behaviour and low thermal conductivity is one of the most preferable candidates for thermoelectric application. However, limited reports are available on MoS2 for Wearable thermoelectric applications. In this study, we have accomplished successful growth of MoS2 nanostructures on conductive carbon fabric via one step hydrothermal method and the effect of thermal oxidation of MoS2 has been studied at various annealing temperature. The structural and elemental analysis confirms the transformation of MoS2 into MoO3. Annealing creates an MoS2/MoO3 interface thus enhancing the carrier mobility resulting in enhancement of power factor (481 nW.m−1K−2) of the sample annealed at 200 °C (M1) by 1.29 times than that of pristine MoS2. The sample possessing high performance has been employed to fabricate a WTEG and its real time output has been measured. The design and operating conditions of the device is studied and optimized to obtain the output open circuit voltage as high as 6.4 mV. This paves a promising route to fabricate self- powered wearable biomedical devices.

Skin‐Mount Textile‐Based Flexible Strain Sensors for Physiotherapy

Tremendous development in intelligent wearable gadgets creates opportunities for flexible strain sensors. Comfortable and safe flexible strain sensors have high demand in wearable applications and therefore the textile‐based strain sensors are desired. Achieving attributes like easy fabrication, cost‐effectiveness, high sensitivity, good stability, and portability is still a challenge to overcome. In this regard, textile‐based flexible strain sensors, one on jeans fabric and other on cotton fabric, are presented. A conventional interdigitated electrode structure is adopted and sensors are prepared by facile and economical fabrication process. Both sensors own high sensitivity factors, i.e., gauge factor >200 and stability of ≈10 000 cycles. The anticipated works show a linear response R2 = 0.99, low hysteresis <5%, and minimum resolution <7°. The intended sensors are implemented for real‐time application, i.e., the physiotherapy of the knee and neck. The jeans‐fabric‐based sensor is used for knee therapy and the cotton for neck. The daily therapy sessions are recorded and examined. The sensors respond well to the applied strain during therapy sessions, proving to be an outstanding choice for integration into biomedical wearable devices for therapeutic purposes. The proposed sensors can also be auspicious candidates for targeting many other wearable applications.

Wearable Ring-Shaped Biomedical Device for Physiological Monitoring through Finger-Based Acquisition of Electrocardiographic, Photoplethysmographic, and Galvanic Skin Response Signals: Design and Preliminary Measurements.

Wearable health devices (WHDs) are rapidly gaining ground in the biomedical field due to their ability to monitor the individual physiological state in everyday life scenarios, while providing a comfortable wear experience. This study introduces a novel wearable biomedical device capable of synchronously acquiring electrocardiographic (ECG), photoplethysmographic (PPG), galvanic skin response (GSR) and motion signals. The device has been specifically designed to be worn on a finger, enabling the acquisition of all biosignals directly on the fingertips, offering the significant advantage of being very comfortable and easy to be employed by the users. The simultaneous acquisition of different biosignals allows the extraction of important physiological indices, such as heart rate (HR) and its variability (HRV), pulse arrival time (PAT), GSR level, blood oxygenation level (SpO2), and respiratory rate, as well as motion detection, enabling the assessment of physiological states, together with the detection of potential physical and mental stress conditions. Preliminary measurements have been conducted on healthy subjects using a measurement protocol consisting of resting states (i.e., SUPINE and SIT) alternated with physiological stress conditions (i.e., STAND and WALK). Statistical analyses have been carried out among the distributions of the physiological indices extracted in time, frequency, and information domains, evaluated under different physiological conditions. The results of our analyses demonstrate the capability of the device to detect changes between rest and stress conditions, thereby encouraging its use for assessing individuals' physiological state. Furthermore, the possibility of performing synchronous acquisitions of PPG and ECG signals has allowed us to compare HRV and pulse rate variability (PRV) indices, so as to corroborate the reliability of PRV analysis under stationary physical conditions. Finally, the study confirms the already known limitations of wearable devices during physical activities, suggesting the use of algorithms for motion artifact correction.

Feasibility and acceptability of a novel biomedical device to prevent neonatal hypothermia and augment Kangaroo Mother Care in Kenya: Qualitative analysis of focus group discussions and key Informant Interviews.

Hypothermia is a leading newborn complication, especially among premature and/or low birth weight infants. Within low/middle-income countries where incubators and radiant warmers are often in short supply, leading to gaps in the thermal care chain, neonatal hypothermia underlies high rates of newborn morbidity and mortality. Kangaroo Mother Care/Skin-to-skin care is an effective method for prevention of hypothermia in premature and low birthweight babies but can be very burdensome for families and healthcare providers. Our international multidisciplinary team has developed a prototype for a wearable biomedical device ("NeoWarm") to provide continuous thermal care and augment kangaroo mother care practices in low-resource settings. The objective of this study was to assess the feasibility and acceptability of NeoWarm and to obtain user design feedback for an early prototype from among adult end-users in Western Kenya. We performed key informant interviews (n = 17) among healthcare providers and 5 focus group discussions (FGDs) among 3 groups of adult stakeholders of premature babies, including: (1) parents/family members of premature babies aged 6 weeks or less (3 FGDs); (2) healthcare providers of newborns (e.g., nurses; physicians; 1 FGD); (3) community opinion leaders and stakeholders (e.g., traditional birth attendants; pastors; village elders; 1 FGD). Content and thematic analyses of transcripts indicate that NeoWarm is acceptable and feasible in promoting facility-based kangaroo mother care in the Kenyan setting. Novel findings derived from respondents include (1) the ability of the device to potentially overcome several barriers to traditional kangaroo mother care methods and (2) user-driven encouragement to expand the use case of the device to potentially include community-based kangaroo mother care and neonatal transport. User design feedback obtained during the interviews informed several key design iterations for subsequent prototypes of the device.

Color-Tunable Organic Light-Emitting Diodes with Single Pt (O^N^C^N)-Dibenzofuran Emitter Exhibiting High External Quantum Efficiency of ≈30% and Superior Operational Lifetime.

Color-tunable organic light-emitting diodes (CT-OLEDs) have a large color-tuning range, high efficiency and operational stability at practical luminance, making them ideal for human-machine interactive terminals of wearable biomedical devices. However, the device operational lifetime of CT-OLEDs is currently far from reaching practical requirements. To address this problem, a tetradentate Pt(II) complex named tetra-Pt-dbf, which can emit efficiently in both monomer and aggregation states, is designed. This emitter has high Td of 508°C and large intermolecular bonding energy of -52.0kcalmol⁻1, which improve its thermal/chemical stability. This unique single-emitter CT-OLED essentially avoids the "color-aging issue" and achieves a large color-tuning span (red to yellowish green) and a high external quantum efficiency （EQE） of ≈30% at 1000cd m-2 as well as an EQE of above 25% at 10000cd m-2. A superior LT90 operational lifetime of 520,536 h at a functional luminance of 100cd m-2, which is over 20 times longer than the state-of-the-art CT-OLEDs, is estimated. To demonstrate the potential application of such OLEDs in wearable biomedical devices, a simple electromyography (EMG)-visualization system is fabricated using the CT-OLEDs.

Leveraging Machine Learning for Personalized Wearable Biomedical Devices: A Review.

This review investigates the convergence of artificial intelligence (AI) and personalized health monitoring through wearable devices, classifying them into three distinct categories: bio-electrical, bio-impedance and electro-chemical, and electro-mechanical. Wearable devices have emerged as promising tools for personalized health monitoring, utilizing machine learning to distill meaningful insights from the expansive datasets they capture. Within the bio-electrical category, these devices employ biosignal data, such as electrocardiograms (ECGs), electromyograms (EMGs), electroencephalograms (EEGs), etc., to monitor and assess health. The bio-impedance and electro-chemical category focuses on devices measuring physiological signals, including glucose levels and electrolytes, offering a holistic understanding of the wearer's physiological state. Lastly, the electro-mechanical category encompasses devices designed to capture motion and physical activity data, providing valuable insights into an individual's physical activity and behavior. This review critically evaluates the integration of machine learning algorithms within these wearable devices, illuminating their potential to revolutionize healthcare. Emphasizing early detection, timely intervention, and the provision of personalized lifestyle recommendations, the paper outlines how the amalgamation of advanced machine learning techniques with wearable devices can pave the way for more effective and individualized healthcare solutions. The exploration of this intersection promises a paradigm shift, heralding a new era in healthcare innovation and personalized well-being.

Antibacterial highly sensitive eco-friendly wearable piezoresistive sensor for monitoring multiple physiological parameters

Recent progress in wearable biomedical devices has made real-time monitoring possible through non-invasive wearable strain sensors, which can transform physical or biological signals into electrical responses. This work has fabricated multifunctional wearable strain sensors by coating composites (SiE-µG) of electrochemically exfoliated micro-sized multi-layer graphene flakes (µG) and Silicone elastomer (SiE) onto stretchable textile-based orthopedic bandage having ZnO adhesive (SiE-µG@Bandage). The composite coated textile sensors exhibited a remarkable sensitivity of 18330, large stretchability of 35%, superior mechanical durability of 50000 cycles, minute detection limit of 0.04% strain, and fast response time of 400 and recovery time 900 ms. The SiE-µG@Bandage also showed antibacterial properties against Escherichia coli (E. coli) bacteria. Additionally, zinc oxide-based skin-friendly and non-toxic adhesive on the backside of the bandage allowed stable and conformal attachment with the skin. Owing to the above merits, the sensors have shown applicability in real-time monitoring of various physical activities, physiological signals, joint movements, yoga postures, and meditation. Furthermore, the relevance of the sensors in the man-machine interaction has been demonstrated via real-time monitoring of traffic signals by finger movements. Moreover, the exceptional performance and specific features of the SiE-µG@Bandage sensors have enabled their application as electronics skins in health care and preventive care.

Synthesis of Power Line Notch Filter in Wearable Biomedical Devices for Wireless Body Area Network

Synthesis of Power Line Notch Filter in Wearable Biomedical Devices for Wireless Body Area Network

The NeoRoo mobile app: Initial design and prototyping of an Android-based digital health tool to support Kangaroo Mother Care in low/middle-income countries (LMICs).

Premature birth and neonatal mortality are significant global health challenges, with 15 million premature births annually and an estimated 2.5 million neonatal deaths. Approximately 90% of preterm births occur in low/middle income countries, particularly within the global regions of sub-Saharan Africa and South Asia. Neonatal hypothermia is a common and significant cause of morbidity and mortality among premature and low birth weight infants, particularly in low/middle-income countries where rates of premature delivery are high, and access to health workers, medical commodities, and other resources is limited. Kangaroo Mother Care/Skin-to-Skin care has been shown to significantly reduce the incidence of neonatal hypothermia and improve survival rates among premature infants, but there are significant barriers to its implementation, especially in low/middle-income countries (LMICs). The paper proposes the use of a multidisciplinary approach to develop an integrated mHealth solution to overcome the barriers and challenges to the implementation of Kangaroo Mother Care/Skin-to-skin care (KMC/STS) in LMICs. The innovation is an integrated mHealth platform that features a wearable biomedical device (NeoWarm) and an Android-based mobile application (NeoRoo) with customized user interfaces that are targeted specifically to parents/family stakeholders and healthcare providers, respectively. This publication describes the iterative, human-centered design and participatory development of a high-fidelity prototype of the NeoRoo mobile application. The aim of this study was to design and develop an initial ("A") version of the Android-based NeoRoo mobile app specifically to support the use case of KMC/STS in health facilities in Kenya. Key functions and features are highlighted. The proposed solution leverages the promise of digital health to overcome identified barriers and challenges to the implementation of KMC/STS in LMICs and aims to equip parents and healthcare providers of prematurely born infants with the tools and resources needed to improve the care provided to premature and low birthweight babies. It is hoped that, when implemented and scaled as part of a thoughtful, strategic, cross-disciplinary approach to reduction of global rates of neonatal mortality, NeoRoo will prove to be a useful tool within the toolkit of parents, health workers, and program implementors.

Nanozyme-Cosmetic Contact Lenses for Ocular Surface Disease Prevention.

Efficiently balancing excess reactive oxygen species (ROS) caused by various factors on the ocular surface is a promising strategy for preventing the development of ocular surface diseases (OSDs). Nevertheless, the conventional topical administration of antioxidants is limited in efficacy due to poor absorption, rapid metabolism, and irreversible depletion, which impede their performance. To address this issue, contact lenses embedded with antioxidant nanozymes that can continuously scavenge ROS, thereby providing an excellent preventive effect against OSDs are developed. Specifically, Prussian blue family nanozymes are chosen based on their multiple antioxidant enzyme-like activities and excellent biocompatibility. The diverse range of colors made them promising candidates for the development of cosmetic contact lenses (CCLs) as a substitute for conventional pigments. The efficacy of nanozyme-CCLs is demonstrated in rabbits and rats exposed to a high risk of developing OSDs. These OSDs' prevention nanozyme-CCLs can pave the way for CCLs toward powerful wearable biomedical devices and provide novel strategies for the rational utilization of nanomaterials in clinical practice.

Revolutionizing Healthcare through Health Monitoring Applications with Wearable Biomedical Devices

The Internet of Things (IoT) has revolutionized the connectivity and communication of tangible objects, and it serves as a versatile and cost-effective solution in the healthcare sector, particularly in regions with limited healthcare infrastructure. This research explores the application of sensors such as LM35, AD8232, and MAX30100 for the detection of vital health indicators, including body temperature, pulse rate, electrocardiogram (ECG), and oxygen saturation levels, with data transmission through IoT cloud, offering real-time parameter access via an Android application for non-invasive remote patient monitoring. The study aims to expand healthcare services to various settings, such as hospitals, commercial areas, educational institutions, workplaces, and residential neighborhoods. After the COVID-19 pandemic, IoT-enabled continuous monitoring of critical health metrics such as temperature and pulse rate has become increasingly crucial for early illness detection and efficient communication with healthcare providers. Our low-cost wearable device, which includes ECG monitoring, aims to bridge the accessibility gap for people with limited financial resources, with the primary goal of providing efficient healthcare solutions to underserved rural areas while also contributing valuable data to future medical research. Our proposed system is a low-cost, high-efficiency solution that outperforms existing systems in healthcare data collection and patient monitoring. It improves access to vital health data and shows economic benefits, indicating a significant advancement in healthcare technology.

Preparation and analysis of dielectric behaviour of BCZT based flexible PVDF polymer composite membrane

In this paper, Barium Calcium Zirconium Titanate (Ba0.86 Ca0.14 Zr0.05 Ti0.95 O3) ceramic powder samples were prepared by the solid-state reaction process. After that, it is mixed with polyvinylidene fluoride (PVDF) to form composite membrane, which is fabricated using the solution cast method. Two membranes were prepared with 15 wt% and 50 wt% filler concentrations of BCZT with PVDF matrix. Dielectric behaviours of prepared composite membrane are analyzed, and these various analyses of composite film are also compared with each other. In this, we see that the increasing addition of lead-free based inorganic filler with an organic PVDF matrix enhanced the dielectric constant five times for the frequency 1KHz and reduction in the losses and increases the conductivity of the composite as the filler weight percentage increased. These fabricated composite membrane can be used for wearable biomedical devices, soft robotics and flexible energy storage capacitors.

A biodegradable wearable flexible sensor based on natural wheat flour polymer for human motion and sweat monitoring

Fabrication of economical and eco-friendly flexible sensors is highly demanded in developing wearable biomedical devices. In this study, an eco-friendly strain and sweat sensor has been successfully assembled based on innovative composites consisting of carbon black (CB) and natural flour polymer, which are entirely green and biodegradable. A film-based sensing device has been developed to measure electrical resistance and strain simultaneously and continuously, owing to the highly sensitive resistance responsibility of the as-developed hybrid of CB and wheat flour (CB-dough). Furthermore, the influence of simulated sweat on the electric response of such sensor was also investigated. Repeatable relationships in resistance versus strain were revealed and obtained for varying samples with different content of simulated sweat, in which the amplitude of resistance was directly proportional to the concentration of NaCl. Accordingly, the as-developed CB-dough sensor was efficaciously used for durable surveillance of human activity and real-time feedback of sweat secretion during body motion. This work offers a simple and cost-effective way to manufacture flexible strain sensors, with a broad application prospect in wearable electronics, artificial intelligence systems, and other bio-sensors.

A power-aware task scheduler for energy harvesting-based wearable biomedical systems using snake optimizer

There is an increasing interest in energy harvesting for wearable biomedical devices. This requires power conservation and management to ensure long-term and steady operation. Hence, task scheduling algorithms will be used throughout this work to provide a reliable solution to minimize energy consumption while considering the system operation constraints. This study proposes a novel power-aware task scheduler to manage system operations. For example, we used the scheduler to handle system operations, including heart rate and temperature sensors. Two optimization techniques have been used to illustrate the impact of task scheduling on energy consumption. The first is based on Snake Optimizer (SO), and the second is a greedy approach to compute the Hamming-based Tikhonov regularization. The FPA approach showed 50% improvement in the convergence time for the scheduler.

A novel UWB flexible antenna with dual notch bands for wearable biomedical devices.

This study presents a novel UWB flexible antenna with dual band-notched design for wearable biomedical devices. The proposed antenna is designed on Kapton Polyimide-based flexible substrate. This includes a CPW fed circular and triangle structure. The dual notched bands are realized by using two triangular-shaped spiral slots defected ground structures. The first notched band (2.4-3.7GHz) is generated for rejecting WLAN and WiMAX, the second notch (5.15-5.725GHz) is generated for rejecting HyperLAN/2. The designed UWB antenna has approximately a bandwith of 159% (2.05-14GHz) in simulation. Thus, the designed UWB antenna meets FCC standards. The antenna has an omnidirectional radiation pattern with a maximum gain of 12.7dB in 8.4GHz. The proposed antenna is fabricated with the low-cost airbrush printed technique. In this technique, a higher gain value is obtained by controlling the thickness of the conductive layer. Effect of flexibility on the antenna performance is tested for different configurations in the simulation and anechoic chamber environments. According to the results obtained, the overall performance is not affected except for the shift in frequency. Since the antenna has a UWB structure, the frequency shift that occurs in bending is at a tolerable level. The proposed UWB antenna is suitable for wearable biomedical devices, with a high UWB performance.

A hybrid piezoelectric and electrostatic energy harvester for scavenging arterial pulsations

Implantable and wearable biomedical devices suffer from a limited lifespan of on-board batteries which require change causing physical discomfort. In order to overcome this, various energy harvesters have been developed as the human body possesses several types of energy available for scavenging through appropriately designed energy harvesting devices, while the cardiovascular system in particular represents a constant reliable source of mechanical energy from vibration. Most conventional energy harvesters exploit only a single phenomenon, such piezo- or triboelectricity, thus producing reduced power density. As an improvement, hybridisation of energy harvesters intends to negate this drawback by simultaneously scavenging energy by multiple harvesters. In the present work, the reverse electrowetting on dielectric (REWOD) phenomenon is combined with the piezoelectric effect in a proof-of-concept hybrid harvester for scavenging biomechanical energy from arterial or other type pulsations. A mathematical model of the harvester was developed; and, an investigation using computational fluid dynamics simulations was carried out using the COMSOL Multiphysics software. The effect of the materials of piezoelectric film and geometrical features of the harvester on parameters such as the displacement, the frequency of pulsations and the energy produced were studied. An experimental setup that could model the time-varying pressures and displacements caused from arterial pulsations was designed and the characteristics of the produced piezoelectrical energy were analysed. A comparison between experimental and computational data was carried out demonstrating a good agreement. The dependencies between geometrical parameters and electrical output were determined and recommendations on piezoelectric materials and design solutions were provided.

An electrical-mechanical cohesive zone model combining viscoelasticity and fatigue damage for soft adhesive layer in wearable sensor

The wearable biomedical devices are promising technologies in the field of human healthcare as the sensors are attached to human skin to monitor in real time physiological signal. The signal drift caused by the damage of adhesive layer between the sensor electrode and human skin is an important factor that affects the detection accuracy of the sensor. Considering the viscoelasticity and conductivity of the adhesive layer, a rate-dependent electrical–mechanical cohesive zone model (CZM) was developed to simulate the electrical signal degradation of wearable sensor electrode during cyclic loading condition. In the proposed CZM, the electrical response of the adhesive layer is related to its mechanical behavior and damage state, and the rate-dependent mechanical behavior of the adhesive layer is described by the Maxwell model. In addition, the fatigue damage evolution is also rate-dependent as the threshold of damage initiation and fracture are defined as the function of loading velocity. The proposed CZM was implemented in ABAQUS by the UEL subroutine and applied to simulate the damage and electrical signal degradation of a wearable electrocardiograph (ECG) sensor electrode in working condition. The results demonstrated that the proposed CZM is effective to characterize the rate-dependent fatigue damage behavior and electrical signal degradation behavior of the ECG electrode during cyclic loadings. It is a promising tool for predicting the electrical signal drift of wearable healthcare sensors and other similar components caused by the damage of adhesive layer, which is important for the accurate calibration of the sensors in long-term service.

Enzymatic Biofuel Cells Embedded Polymer-Based Soft Actuators

Enzymatic biofuel cells are presented as an untethered alternative energy source that could power small implantable or wearable medical devices. However, most of these catalytic processes do not provide with enough energy to power common small electronic-mechanical devices. On the other hand, conducting polymer-based actuators are of great interest for their biocompatibility, flexibility, processability, possibility to be miniaturized and low power consumption. So far, these artificial muscles have been driven by external power sources that prevent them for being completely autonomous. There is a need for a novel power source to elaborate actuators that could use physiological processes as a driving force. These soft actuators’ low power consumption matches the electrical power generated by the biocatalysis of some enzymes, such as glucose oxidase and laccase in presence of glucose and oxygen in aqueous media. Here, we present the latest results in the development of polypyrrole-based soft actuators powered by enzymatic biofuel cells. The actuator consists of a tri-layer conductive substrate on which the polypyrrole is electrodeposited in both sides. The polypyrrole layers act as the active part, expanding and contracting upon a redox reaction, resulting in a bending movement. Tetrathiofulvlene-7,7,8,8-tetracyanoquinodimethane (TTF-TCNQ) and 2,2′-azino-di-(3-ethylbenzthiazoline sulfonic acid) (ABTS) electron transfer mediators are cast on the surface of the polypyrrole to help the electron transmission. The glucose oxidase and laccase enzymes are immobilized in the modified-conducting polymer surface, integrating the electrode to the actuator. The bio-catalysis of enzymes in presence of glucose and oxygen in aqueous solution provides the actuator with the electrons needed for the redox reaction, converting the chemical energy into mechanical energy, i.e., movement. The glucose-self-powered soft actuator may contribute to the development of more complex implantable, ingestible, or wearable biomedical devices such as cardio-stimulators, insulin pumps, or muscle implants.

ATCN: Resource-efficient Processing of Time Series on Edge

This article presents a scalable deep learning model called Agile Temporal Convolutional Network (ATCN) for highly accurate fast classification and time series prediction in resource-constrained embedded systems. ATCN is a family of compact networks with formalized hyperparameters that enable application-specific adjustments to be made to the model architecture. It is primarily designed for embedded edge devices with very limited performance and memory, such as wearable biomedical devices and real-time reliability monitoring systems. ATCN makes fundamental improvements over the mainstream temporal convolutional neural networks, including residual connections to increase the network depth and accuracy and the incorporation of separable depth-wise convolution to reduce the computational complexity of the model. As part of the present work, two ATCN families, namely T0 and T1, are also presented and evaluated on different ranges of embedded processors: Cortex-M7 and Cortex-A57 processors. An evaluation of the ATCN models against the best-in-class InceptionTime and MiniRocket shows that ATCN almost maintains accuracy while improving the execution time on a broad range of embedded and cyber-physical applications with demand for real-time processing on the embedded edge. At the same time, in contrast to existing solutions, ATCN is the first time series classifier based on deep learning that can be run bare-metal on embedded microcontrollers (Cortex-M7) with limited computational performance and memory capacity while delivering state-of-the-art accuracy.