Transmission of biosignals via LoRa using the Meshtastic net

This publication represents the first part of the project. The following stages and updates will be released in the coming weeks.

Introduction

The transmission of biosignals using LoRa (Long Range) technology plays a vital role in healthcare, biomedical research, and remote sensing. LoRa is distinguished by its low power consumption and long-range coverage, making it especially suitable for real-time monitoring in environments where Wi-Fi or Bluetooth are impractical. Its relevance is particularly evident in remote patient monitoring, offering reliable connectivity in rural or underserved regions with limited infrastructure.

With coverage of up to 15–20 kilometers in open environments, LoRa enables biomedical devices to connect with distant medical centers, supporting continuous monitoring of patients with chronic conditions, elderly individuals, or those with limited mobility. It also facilitates early detection of critical health issues such as arrhythmias or abnormal glucose levels through real-time biosignal transmission.

LoRa significantly enhances telemedicine by providing a cost-effective and robust method for transferring medical data. Portable devices equipped with biosensors can transmit information via LoRaWAN networks, enabling physicians to analyze signals and make timely decisions. In disaster or emergency scenarios, LoRa can quickly establish medical monitoring networks without relying on expensive infrastructure, thereby optimizing healthcare resources.

Energy efficiency is another major advantage. Biomedical wearables powered by small batteries—such as blood pressure cuffs, heart rate monitors, or neural/muscular patches—can operate for weeks or even months without recharging. Beyond healthcare, smartwatches and fitness trackers can leverage LoRa for transmitting real-time data on heart activity, temperature, or physical performance, aiding both clinical trials and sports science.

LoRa is also highly resilient in challenging environments. It provides reliable connectivity indoors, overcoming interference in hospitals or laboratories, and even under extreme conditions such as hyperbaric chambers, operating rooms, or harsh climates. This resilience makes it valuable for monitoring workers in high-risk industries like mining or offshore platforms, as well as patients in emergency vehicles.

While LoRa is not designed for transmitting large volumes of data, it excels at critical low-bandwidth signals, including medical alerts that must be delivered instantly. This makes it highly suitable for public health applications such as large-scale monitoring during pandemics or epidemics. In biomedical research, it enables the real-time collection of distributed data from multiple participants, supporting studies on population health patterns and advancing the medical Internet of Things (IoT).

In hospital settings, LoRa-based networks can monitor multiple patients across different wards, streaming vital signs to centralized dashboards or mobile apps for both patients and clinicians. Its scalability and cost-effectiveness allow institutions to deploy private LoRaWAN networks without relying on cellular carriers, with a single gateway capable of managing thousands of devices.

Practical applications already include ECG-based cardiac monitoring, athlete performance analysis, remote livestock health monitoring, and ambulance-to-hospital data transmission. Collectively, these use cases highlight LoRa’s potential as a cornerstone technology for biomedical connectivity.

For this project, we build on LoRa through the Meshtastic network, a mesh-based communication system that extends LoRa’s functionality. Meshtastic enables devices to exchange sensor data and text messages without cellular infrastructure, with each node acting as a relay to expand coverage. This makes it particularly valuable in outdoor activities, emergency response, and rural communities. Furthermore, Meshtastic can integrate with platforms like Node-RED, simplifying automation and real-time processing of biosignal data collected across the mesh network.

Project Objective

The primary goal of this project is to design and develop an intelligent system for analyzing, transmitting, and efficiently monitoring physiological parameters using LoRa technology. The system is intended to meet critical needs in areas such as emergency medical response, healthcare delivery in hard-to-reach regions, and remote patient monitoring in locations with limited infrastructure.

By ensuring reliable transmission of biomedical data—including heart rate, glucose levels, oxygen saturation, and other vital signals—the project aims to support faster and more effective clinical decision-making. A strong emphasis is placed on energy efficiency, allowing portable devices to operate for extended periods in environments where frequent battery recharging is not practical.

In addition, the system incorporates mesh connectivity through the Meshtastic network, providing scalability and resilience in demanding conditions. This approach enables long-distance data transmission and the ability to overcome obstacles such as thick walls or underground settings, making the solution highly adaptable for use in hospitals, industrial facilities, and rural communities.

Hardware Description

For this project, several devices are interconnected through the LoRa Meshtastic network, each contributing unique capabilities for biosignal transmission, data processing, and network scalability. The Wio Tracker 1110 Dev Kit provides long-range LoRa, integrated GPS, and low-power operation for real-time tracking and biomedical data transmission, while portable biomedical sensors measure heart rate, oxygen saturation, and glucose levels with energy-efficient microcontrollers to ensure prolonged monitoring. A LoRa Gateway functions as the central hub, receiving data packets from nodes and relaying them reliably to servers or the cloud, and Meshtastic-enabled devices equipped with LoRa radios extend network coverage by retransmitting data in rural or obstructed areas.

Complementary hardware expands the system’s versatility: the SenseCAP Card Tracker T1000-E, a compact LoRaWAN tracker with GNSS, Wi-Fi, and Bluetooth, optimized for asset and biosignal tracking; the LILYGO® TTGO Lora GPIO V2.1-1.6, a development board useful for custom biosignal acquisition modules; the SenseCAP Indicator, a handheld display for patient vitals or system status; and the LilyGO T-Deck Plus, which integrates a LoRa transceiver, ESP32-S3 processor, touchscreen, microphone, and speaker for mobile biosignal visualization and on-device processing.

The Wio-SX1262 with XIAO ESP32S3 combines the SX1262 LoRa transceiver with hybrid Wi-Fi/BLE connectivity in a compact, low-power form factor ideal for wearable biomedical sensors.

Additionally, the SenseCAP Solar Node P1 Pro provides a solar-powered, maintenance-free solution for continuous outdoor operation, making it especially valuable in remote health monitoring or emergency scenarios where reliability and autonomy are critical.

Together, these components establish a robust, energy-efficient, and scalable system capable of transmitting biomedical signals over long distances, even in environments with limited infrastructure or connectivity.

Raspberry Pi 5 in the System

The Raspberry Pi 5 serves as the intelligent processing hub within the system architecture. Powered by its ARM Cortex-A76 CPU and VideoCore VII GPU, it enables the integration of multiple critical functions for biomedical data acquisition, analysis, and visualization.

In this project, the Raspberry Pi 5 is configured with a hybrid communication interface, combining Wi-Fi for local connectivity, LoRa for long-range transmission in remote areas, and HDMI graphical output for real-time data display on external monitors.

A key feature is the integration of the Hailo-8 AI accelerator, which provides high-performance machine learning inference capabilities, allowing efficient biosignal analysis and reducing latency in clinical decision-making.

Additionally, the Raspberry Pi 5 connects to a digital microscope, enabling complementary visual analysis for biomedical or laboratory studies. In parallel, it interfaces with a robot equipped with sensors and actuators designed to perform cardiac auscultation tasks, capturing heart sounds from different anatomical points and transmitting them to the system for AI-based processing.

With this modular setup, the Raspberry Pi 5 functions not only as a central communication node, but also as a biomedical integration hub, merging physiological signals, cardiac audio, and visual data into a unified analysis environment.Wio Tracker 1110 Dev Kit for Meshtastic

Wio Tracker 1110 Dev Board

The Wio Tracker 1110 Dev Board is built around the Wio-WM1110 wireless module, integrating the Semtech LR1110 LoRa® transceiver with a versatile radio front-end for geolocation. It also includes the Nordic nRF52840 microcontroller, providing Bluetooth Low Energy (BLE) connectivity. Complementary modules such as the Grove GPS (Air530) offer GNSS positioning (GPS and BeiDou), while the Grove 0.96" OLED Display enables real-time data visualization and device status monitoring.

The Wio Tracker 1110 offers key features that make it highly versatile for biomedical and IoT applications. It is fully compatible with the Meshtastic firmware, enabling the creation of decentralized LoRa® mesh networks for reliable communication in areas without existing infrastructure—an advantage in outdoor activities, emergency scenarios, and rural environments. Its integration with the Grove ecosystem, supporting over 300 modules, allows seamless expansion with additional sensors and actuators to meet diverse development needs. Furthermore, its low-power design makes it well-suited for energy-efficient applications such as wearables and remote monitoring devices with long battery life. Potential applications include remote patient monitoring for biosignal transmission where Wi-Fi or Bluetooth may be limited, emergency communication networks in disaster-affected or infrastructure-poor regions, and asset or personnel tracking in large or hard-to-reach areas.

XIAO ESP32S3 & Wio-SX1262 Kit for Meshtastic & LoRa

The XIAO ESP32S3 & Wio-SX1262 Kit combines the processing power of the XIAO ESP32S3 with the long-range communication capabilities of the SX1262 LoRa® transceiver, making it an ideal platform for lightweight IoT and biomedical applications. With built-in Wi-Fi and Bluetooth Low Energy (BLE), it enables hybrid connectivity, while LoRa ensures reliable data transmission over long distances in areas with poor infrastructure. Its compact size and low-power design make it suitable for wearables, portable biomedical sensors, and energy-efficient remote monitoring solutions. Moreover, the kit integrates seamlessly with the Meshtastic firmware, allowing the creation of decentralized mesh networks for communication in outdoor activities, emergency response, and rural communities. By supporting the Grove ecosystem, it can be easily expanded with a wide variety of sensors and actuators, enhancing adaptability for healthcare, research, and IoT development. Potential applications include remote patient monitoring, real-time biosignal transmission, emergency medical communication, and asset or personnel tracking in large or hard-to-reach environments.

Software Description

The system software is structured into two main levels, working together to ensure the efficient transmission, reception, and analysis of biomedical data and auxiliary signals.

At the first level, the communication infrastructure is based on the Meshtastic firmware, integrated into the various compatible IoT devices. This firmware enables the creation of a decentralized mesh network, where each device plays a specific role within the topology:

• Clients, responsible for sending biomedical data.
• Repeaters or routers, which extend network coverage and guarantee communication resilience.
• Repeaters or routers, which extend network coverage and guarantee communication resilience.
• Trackers, capable of transmitting information along with geolocation data.

This flexibility in role assignment makes the network robust, scalable, and adaptable, particularly valuable in environments with limited or no connectivity.

At the second level, the Raspberry Pi 5 acts as the high-level processing hub. This platform not only connects to the Meshtastic network but can also send and receive data via dedicated LoRa links at 868 MHz, allowing the integration of devices not directly compatible with Meshtastic. In this way, the Raspberry Pi 5 serves as both a bridge and orchestrator, linking different nodes and communication protocols.

A key element is the integration of the Hailo-8 AI accelerator, which significantly enhances the Raspberry Pi 5’s computing capabilities. With this module, the system can execute real-time computer vision models applied to images captured by a digital microscope or the Raspberry Pi’s own camera. This opens the door to applications such as:

• Tissue and cell classification.
• Identification of biomedical patterns.
• Automated processing of laboratory samples.

Regarding biosignal transmission, this is carried out through LoRa devices, both those operating within the Meshtastic network and those functioning independently. The supported signals include ECG (electrocardiography), PPG (photoplethysmography), SpO₂ (oxygen saturation), and FCG (phonocardiography, heart sounds). Integrating these data sources enables comprehensive remote monitoring, with real-time analysis of patients’ cardiovascular and respiratory health.

Additionally, the system features a Python interface that facilitates interaction with the Meshtastic network. This interface:

• Manages the reception and analysis of collected data.
• Allows direct communication between nodes, both inside and outside the Meshtastic network.
• Extends interoperability with other independent LoRa devices, increasing the system’s reach and heterogeneity.

Taken together, this software and communication ecosystem forms a flexible, scalable, and multidisciplinary platform, suitable for telemedicine, biomedical research, and monitoring in critical environments.

Use Cases & Scenarios

The following section describes each of the possible scenarios in which the device can be used.

Remote patient monitoring

The device presented in this project enables remote patient monitoring through the integration of the Raspberry Pi 5 and the Hailo-8 AI accelerator. The combination of these two components allows both the capture and advanced analysis of data and images obtained from various biomedical sensors. Among the processed signals are ECG, PPG, SpO₂, spirometry, glucose, and blood pressure, providing a comprehensive view of the patient’s health status. This solution is particularly valuable in remote environments with limited medical coverage, in the care of individuals living alone, or in situations requiring an efficient and accessible telemedicine system.

This sensor makes it possible to capture an ECG signal, which is subsequently analyzed by an artificial intelligence model. This model can detect potential anomalies in the signal, thereby enabling an early assessment of the patient’s cardiac condition. The results of this classification are presented in the following figures, obtained from the training of the AI model.

Emergency communication

In the context of emergency communications, the system would enable the rapid deployment of an independent and resilient network, ensuring connectivity in environments where conventional infrastructure may be damaged, overloaded, or completely unavailable. This network would not only facilitate reliable message exchange among emergency personnel, improving coordination and decision-making, but also allow the real-time monitoring of potentially injured individuals or animals through integrated biomedical sensors.

By leveraging portable and solar-powered LoRa/Meshtastic nodes, the network can be quickly established in remote or disaster-stricken areas, maintaining coverage without the need for external power sources or pre-existing communication lines. In addition to transmitting critical biomedical parameters such as heart rate, oxygen saturation, or body temperature, the system can also provide geolocation data, supporting search-and-rescue operations and prioritizing assistance to those in greatest need.

This capability transforms the system into a dual-purpose tool: a communication backbone for emergency teams and a health-monitoring platform for vulnerable populations, contributing to faster response times, optimized resource allocation, and ultimately, improved survival rates during crisis scenarios.

Outdoor health missions

In field operations such as humanitarian aid, rural healthcare campaigns, or mobile vaccination programs, reliable communication and continuous monitoring are critical to ensure efficiency and safety. The proposed system provides a portable and autonomous solution that can be deployed in remote areas with limited or no infrastructure, enabling healthcare teams to establish a secure and scalable communication network.

Through the integration of LoRa/Meshtastic nodes, portable biomedical sensors, and solar-powered devices, medical personnel can monitor patients’ vital signs—including ECG, oxygen saturation, body temperature, and glucose levels—in real time, while simultaneously maintaining stable communication links among team members. This ensures that health data is transmitted over long distances with minimal energy consumption, supporting decision-making even in challenging environments such as mountainous regions, forests, or disaster-stricken zones.

The system’s adaptability also allows the incorporation of geolocation services, enabling patient tracking, mapping of affected areas, and coordination of medical supplies. In addition, the use of ruggedized and low-maintenance devices guarantees long-term functionality under adverse weather conditions, making it an effective tool for continuous outdoor health missions.

Ultimately, this approach transforms healthcare operations in the field by providing not only a robust communication backbone but also an intelligent biosignal monitoring infrastructure, ensuring timely interventions and improved quality of care in scenarios where traditional healthcare infrastructure is absent.

This publication represents the first part of the project. The following stages and updates will be released in the coming weeks.