International Journal For Multidisciplinary Research

E-ISSN: 2582-2160   •   Impact Factor: 9.24

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Call for Paper Volume 6 Issue 4 July-August 2024 Submit your research before last 3 days of August to publish your research paper in the issue of July-August.
Submit Research Paper Join as a Reviewer

Plagiarism is checked by the leading plagiarism checker TurnItIn

Call for Paper

Volume 6 Issue 4
July-August 2024

Submit your research paper

Indexing Partners
Academia Advanced Sciences Index Bielefeld Academic Search Engine CiteSeer DRJI Google Scholar Independent Search Engine & Directory Network ISI (International Scientific Indexing) Issuu Mendeley Research Networks
RefSeek ResearcherId - Thomson Reuters ResearchGate Scirus Scribd Semantic Scholar UTeM - Universiti Teknikal Malaysia Melaka Wiki for Call for Papers WorldCat Zenodo

Design and Evaluation of a High-Efficiency Smart IoT Device Incorporating Embedded Tiny Machine Learning for Monitoring Asset Activity

Author(s) M.K.Kishore, K.Saritha, M.V.N.Chandrika, B.Bhanu sai, Y.Pavan raghava
Country India
Abstract This article suggests a proof-of-concept gadget with an energy-efficient architectural design that can track the use of handheld power tools and identify construction-related activities (like various drilling jobs) as well as possible misuses (like drops). The device's design relies on RFID and WIFI module (ESP8266) communication. Wifi module is used for data exchange with a gateway, whereas RFID is used to identifyy the user. An accelerometer is included for tracking tool use, while sensors for temperature and humidity are used to keep an eye on storage conditions. Information processing at the edge is accomplished by using the Arudino uno that is included within the wifi module. In order to analyze the data directly on board and achieve low latency and great energy efficiency, a Tiny Machine Learning (TinyML) method is developed. The suggested gadget contains an incorporated TinyML algorithm that has been created to identify three distinct use classes: wood drilling, metal drilling, and no-load. The device was coupled to a construction rotary hammer drill to capture a dataset that included over 280 minutes of three-axis accelerations during various operations. This dataset was utilized to train and verify the algorithm.
Using a model size of around 30 kB, a neural architecture search was conducted to maximize the trade- off between accuracy and complexity, and an accuracy of 90.6% was obtained. Based on the testing findings, TinyML ran on the edge with an ultralow power usage of 550 nA in sleep mode and an 8 mA peak power consumption. With a basic 250-mAh coin battery, this leads to a balanced mix of low power consumption and edge processing capabilities, allowing the creation of a smart Internet of Things (IoT) device in the field with a long lifespan of up to four years in operation and 17 years in shelf mode. This study closes the gap between edge processing and fine-granularity data assessment by enabling extended battery lifetime operation of device degradation and utility analysis
Keywords Asset management, condition monitoring, construction 4.0, energy efficiency, low-power design, smart sensors, tool usage monitoring, wireless sensor networks
Field Engineering
Published In Volume 6, Issue 2, March-April 2024
Published On 2024-04-18
Cite This Design and Evaluation of a High-Efficiency Smart IoT Device Incorporating Embedded Tiny Machine Learning for Monitoring Asset Activity - M.K.Kishore, K.Saritha, M.V.N.Chandrika, B.Bhanu sai, Y.Pavan raghava - IJFMR Volume 6, Issue 2, March-April 2024. DOI 10.36948/ijfmr.2024.v06i02.17525
DOI https://doi.org/10.36948/ijfmr.2024.v06i02.17525
Short DOI https://doi.org/gtrfmg
View / Download PDF File

Share this


E-ISSN 2582-2160
CrossRef

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads
Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 6 Isu 4 Cover Page Vol 6 Isu 3 Cover Page Vol 6 Isu 2

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA Open Access

About IJFMR
Fees & Payment
Current Issue
Publication Archive 		Submit Research Paper
Track Submission Status
Publication Guidelines
Publication Ethics
Peer Review & Plagiarism 		Join as a Reviewer
Editors & Reviewers
Reviewer Referral Program
Get Reviewer Membership Certi. 		Website/Journal Policies
Usage Policy
Content Policies
Privacy Policy
Contact Us +91-9898-5948-55 editor@ijfmr.com