Smart and adaptive cutting-edge IoT based implementation for remote environments

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2026 | Volume : 13 | 01 | Page :
    By

    Israr Shaikh,

  • Arun Sharma,

  • Dr.Shiksha Dubey,

  1. Research Scholar, Thakur Institute of Management Stu0dies, Career Development & Research (TIMSCDR) Mumba, Maharashtra, India
  2. Research Scholar, Thakur Institute of Management Stu0dies, Career Development & Research (TIMSCDR) Mumba, Maharashtra, India
  3. Assistant Professor, Thakur Institute of Management Stu0dies, Career Development & Research (TIMSCDR) Mumba, Maharashtra, India

Abstract

In remote, mountainous, or snow-covered regions, mobile networks and GPS signals usually become unreliable, which creates major challenges for search and rescue (SAR) operations. To overcome the issue, this paper presents a compact, low-power, voice-activated wearable device that integrates LoRa communication with a TinyML-based keyword detection system. The proposed device enables individuals to send signals in areas where GPS coverage is unavailable. Using the Received Signal Strength Indicator (RSSI), the system applies trilateration techniques to get an approximate location of the user without having to rely on GPS. When someone says words like “Help” or “Bachao”, etc., the device quickly sends an emergency message using LoRa technology. This message includes the person’s location, either from GPS or by estimating it using the signal strength (RSSI) if GPS isn’t working. The rescue team, who have special LoRa receivers, can study the signal strength to guess how far and in which direction the person is. This makes it easier and faster for them to find the person, especially in mountainous or hard-to-reach areas, and increases the chances of saving lives.

Keywords: LoRa, TinyML, RSSI Trilateration, Keyword Spotting, Emergency Signaling, GPS-Denied Environments, Search and Rescue

How to cite this article:
Israr Shaikh, Arun Sharma, Dr.Shiksha Dubey. Smart and adaptive cutting-edge IoT based implementation for remote environments. Journal of Microcontroller Engineering and Applications. 2026; 13(01):-.
How to cite this URL:
Israr Shaikh, Arun Sharma, Dr.Shiksha Dubey. Smart and adaptive cutting-edge IoT based implementation for remote environments. Journal of Microcontroller Engineering and Applications. 2026; 13(01):-. Available from: https://journals.stmjournals.com/jomea/article=2026/view=241099


References

  1. Manuel MP, Faied M, Krishnan M. A novel LoRa LPWAN-based communication architecture for search & rescue missions. IEEE Access. 2022;10:57596–57607.
  2. Paredes WD, Kaushal H, Vakilinia I, Prodanoff Z. LoRa technology in flying ad hoc networks: a survey of challenges and open issues. Sensors. 2023;23(5):2403.
  3. TinyML and on-device inference: applications, challenges, and future directions. Electronics. 2025;14(2):1–22.
  4. Sandhya G, Ajay Kumar N, Gowtham S, Faheem Aslam M. LoRa-based smart system for unsafe event detection in mining industry using IoT and TinyML. Migr Lett. 2024;21(S5):1664–1672.
  5. Malche T. Voice-activated home automation for IoT edge devices using TinyML. IoT Edge AI. 2025;7(1):1–20.
  6. Sharma AK, Gupta PK. A survey of TinyML models and architectures for acoustic sensor applications. IEEE Access. 2024;12:1–20.
  7. Garai S, Samui S. Exploring TinyML frameworks for small-footprint keyword spotting: a concise overview. ResearchGate. 2023;5(2):1–10.
  8. Ahmed MZ, Ali H, Singh TK. TinyML for acoustic anomaly detection on resource-constrained edge devices. Sensors. 2023;23(12):1–20.
  9. Chen HE, Wu XT, Zhang YL. Energy-efficient keyword spotting with binary neural networks on MCUs. In: Proc TinyML Summit. 2023;3(1):1–10.
  10. Chen Y, Lin F, Fan H. Keyword spotting system and evaluation of pruning and quantization methods on low-power edge microcontrollers. ResearchGate. 2022;2(4):1–10.
  11. Saini RS, Patel SM. Real-time voice wake-up detection in noisy environments using a TinyML framework. In: Proc ICESS. 2022;4(2):1–10.
Ahead of Print Subscription Review Article
Volume 13
01
Received 08/04/2026
Accepted 23/04/2026
Published 27/04/2026
Publication Time 19 Days
1

Login


My IP

PlumX Metrics