Non-invasive diabetes level monitoring system using artificial intelligence and UWB

Minarul Islam; Sabira Khatun; Nusrat Jahan Shoumy; Md Shawkat Ali; Mohamad Shaiful Abdul Karim; Bifta Sama Bari

doi:10.1007/978-3-030-52856-0_30

Non-invasive diabetes level monitoring system using artificial intelligence and UWB

Minarul Islam, Sabira Khatun, Nusrat Jahan Shoumy, Md Shawkat Ali, Mohamad Shaiful Abdul Karim, Bifta Sama Bari

Computing, Mathematics and Engineering

Research output: Book chapter/Published conference paper › Conference paper › peer-review

2 Citations (Scopus)

Abstract

Diabetes is a silent-killer disease throughout the world. It is not curable, therefore, regular blood glucose concentration levels (BGCL) monitoring is necessary to be healthy in a long run. The traditional way of BGCL measurement is invasive by pricking and collecting blood sample from human arm (or finger-tip), then measuring the level either using a glucometer or sending to laboratory. This blood collecting process produces significant discomfort to the patients, especially to the children with type-A diabetes, resulting increased undetected-cases and health-complications. To overcome this drawbacks, a non-invasive ultra-wideband (UWB) BGCL measurement system is proposed here with enhanced software module. The hardware can be controlled through the graphical user interface (GUI) of software and can execute signal processing, feature extraction, and feature classification using artificial intelligence (AI). As AI, cascade forward neural network (CFNN) and naïve bayes (NB) algorithms are investigated, then CFNN with four independent features (skewness, kurtosis, variance, mean-absolute-deviation) are found to be best-suited for BGCL estimation. A transmit (Tx) antenna was placed at one side of left-earlobe to Tx UWB signals, and a receive (Rx) antenna at opposite side to Rx transmitted signals with BGCL marker. These signals are saved and used for AI training, validation and testing. The system with CFNN shows approximately 86.62% accuracy for BGCL measurement, which is 5.62% improved compared to other methods by showing its superiority. This enhanced system is affordable, effective and easy-to-use for all users (home and hospital), to reduce undetected diabetes cases and related mortality rate in near future.

Original language	English
Title of host publication	Cyber Security and Computer Science
Subtitle of host publication	Second EAI International Conference, ICONCS 2020, Proceedings
Editors	Touhid Bhuiyan, Md. Mostafijur Rahman, Md. Asraf Ali
Place of Publication	Cham, Switzerland
Publisher	Springer
Pages	376-387
Number of pages	12
Volume	325
ISBN (Electronic)	9783030528560
ISBN (Print)	9783030528553
DOIs	https://doi.org/10.1007/978-3-030-52856-0_30
Publication status	Published - 2020
Event	2nd International Conference on Computer Science and Cyber Security, ICONCS 2020 - Daffodil International University, Dhaka, Bangladesh Duration: 15 Feb 2020 → 16 Feb 2020 http://iconcs.daffodilvarsity.edu.bd/ (conference website) https://link.springer.com/book/10.1007/978-3-030-52856-0 (conference proceedings) http://iconcs.daffodilvarsity.edu.bd/program.php (conference program)

Publication series

Name	Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
Volume	325 LNICST
ISSN (Print)	1867-8211

Conference

Conference	2nd International Conference on Computer Science and Cyber Security, ICONCS 2020
Country/Territory	Bangladesh
City	Dhaka
Period	15/02/20 → 16/02/20
Internet address	http://iconcs.daffodilvarsity.edu.bd/ (conference website) https://link.springer.com/book/10.1007/978-3-030-52856-0 (conference proceedings) http://iconcs.daffodilvarsity.edu.bd/program.php (conference program)

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-030-52856-0_30

Cite this

Islam, M., Khatun, S., Shoumy, N. J., Ali, M. S., Karim, M. S. A., & Bari, B. S. (2020). Non-invasive diabetes level monitoring system using artificial intelligence and UWB. In T. Bhuiyan, M. M. Rahman, & M. A. Ali (Eds.), Cyber Security and Computer Science : Second EAI International Conference, ICONCS 2020, Proceedings (Vol. 325, pp. 376-387). (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST; Vol. 325 LNICST). Springer. https://doi.org/10.1007/978-3-030-52856-0_30

Islam, Minarul ; Khatun, Sabira ; Shoumy, Nusrat Jahan et al. / Non-invasive diabetes level monitoring system using artificial intelligence and UWB. Cyber Security and Computer Science : Second EAI International Conference, ICONCS 2020, Proceedings. editor / Touhid Bhuiyan ; Md. Mostafijur Rahman ; Md. Asraf Ali. Vol. 325 Cham, Switzerland : Springer, 2020. pp. 376-387 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST).

@inproceedings{accd3587267c457b99d87bf413e935c2,

title = "Non-invasive diabetes level monitoring system using artificial intelligence and UWB",

abstract = "Diabetes is a silent-killer disease throughout the world. It is not curable, therefore, regular blood glucose concentration levels (BGCL) monitoring is necessary to be healthy in a long run. The traditional way of BGCL measurement is invasive by pricking and collecting blood sample from human arm (or finger-tip), then measuring the level either using a glucometer or sending to laboratory. This blood collecting process produces significant discomfort to the patients, especially to the children with type-A diabetes, resulting increased undetected-cases and health-complications. To overcome this drawbacks, a non-invasive ultra-wideband (UWB) BGCL measurement system is proposed here with enhanced software module. The hardware can be controlled through the graphical user interface (GUI) of software and can execute signal processing, feature extraction, and feature classification using artificial intelligence (AI). As AI, cascade forward neural network (CFNN) and na{\"i}ve bayes (NB) algorithms are investigated, then CFNN with four independent features (skewness, kurtosis, variance, mean-absolute-deviation) are found to be best-suited for BGCL estimation. A transmit (Tx) antenna was placed at one side of left-earlobe to Tx UWB signals, and a receive (Rx) antenna at opposite side to Rx transmitted signals with BGCL marker. These signals are saved and used for AI training, validation and testing. The system with CFNN shows approximately 86.62% accuracy for BGCL measurement, which is 5.62% improved compared to other methods by showing its superiority. This enhanced system is affordable, effective and easy-to-use for all users (home and hospital), to reduce undetected diabetes cases and related mortality rate in near future.",

keywords = "Blood glucose concentration level, Cascade forward neural network, Non-invasive measurement, UWB",

author = "Minarul Islam and Sabira Khatun and Shoumy, {Nusrat Jahan} and Ali, {Md Shawkat} and Karim, {Mohamad Shaiful Abdul} and Bari, {Bifta Sama}",

year = "2020",

doi = "10.1007/978-3-030-52856-0_30",

language = "English",

isbn = "9783030528553",

volume = "325",

series = "Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST",

publisher = "Springer",

pages = "376--387",

editor = "Touhid Bhuiyan and Rahman, {Md. Mostafijur} and Ali, {Md. Asraf}",

booktitle = "Cyber Security and Computer Science",

address = "United States",

note = "2nd International Conference on Computer Science and Cyber Security, ICONCS 2020 ; Conference date: 15-02-2020 Through 16-02-2020",

url = "http://iconcs.daffodilvarsity.edu.bd/, https://link.springer.com/book/10.1007/978-3-030-52856-0, http://iconcs.daffodilvarsity.edu.bd/program.php",

}

Islam, M, Khatun, S, Shoumy, NJ, Ali, MS, Karim, MSA & Bari, BS 2020, Non-invasive diabetes level monitoring system using artificial intelligence and UWB. in T Bhuiyan, MM Rahman & MA Ali (eds), Cyber Security and Computer Science : Second EAI International Conference, ICONCS 2020, Proceedings. vol. 325, Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST, vol. 325 LNICST, Springer, Cham, Switzerland, pp. 376-387, 2nd International Conference on Computer Science and Cyber Security, ICONCS 2020, Dhaka, Bangladesh, 15/02/20. https://doi.org/10.1007/978-3-030-52856-0_30

Non-invasive diabetes level monitoring system using artificial intelligence and UWB. / Islam, Minarul; Khatun, Sabira; Shoumy, Nusrat Jahan et al.
Cyber Security and Computer Science : Second EAI International Conference, ICONCS 2020, Proceedings. ed. / Touhid Bhuiyan; Md. Mostafijur Rahman; Md. Asraf Ali. Vol. 325 Cham, Switzerland: Springer, 2020. p. 376-387 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST; Vol. 325 LNICST).

Research output: Book chapter/Published conference paper › Conference paper › peer-review

TY - GEN

T1 - Non-invasive diabetes level monitoring system using artificial intelligence and UWB

AU - Islam, Minarul

AU - Khatun, Sabira

AU - Shoumy, Nusrat Jahan

AU - Ali, Md Shawkat

AU - Karim, Mohamad Shaiful Abdul

AU - Bari, Bifta Sama

PY - 2020

Y1 - 2020

N2 - Diabetes is a silent-killer disease throughout the world. It is not curable, therefore, regular blood glucose concentration levels (BGCL) monitoring is necessary to be healthy in a long run. The traditional way of BGCL measurement is invasive by pricking and collecting blood sample from human arm (or finger-tip), then measuring the level either using a glucometer or sending to laboratory. This blood collecting process produces significant discomfort to the patients, especially to the children with type-A diabetes, resulting increased undetected-cases and health-complications. To overcome this drawbacks, a non-invasive ultra-wideband (UWB) BGCL measurement system is proposed here with enhanced software module. The hardware can be controlled through the graphical user interface (GUI) of software and can execute signal processing, feature extraction, and feature classification using artificial intelligence (AI). As AI, cascade forward neural network (CFNN) and naïve bayes (NB) algorithms are investigated, then CFNN with four independent features (skewness, kurtosis, variance, mean-absolute-deviation) are found to be best-suited for BGCL estimation. A transmit (Tx) antenna was placed at one side of left-earlobe to Tx UWB signals, and a receive (Rx) antenna at opposite side to Rx transmitted signals with BGCL marker. These signals are saved and used for AI training, validation and testing. The system with CFNN shows approximately 86.62% accuracy for BGCL measurement, which is 5.62% improved compared to other methods by showing its superiority. This enhanced system is affordable, effective and easy-to-use for all users (home and hospital), to reduce undetected diabetes cases and related mortality rate in near future.

AB - Diabetes is a silent-killer disease throughout the world. It is not curable, therefore, regular blood glucose concentration levels (BGCL) monitoring is necessary to be healthy in a long run. The traditional way of BGCL measurement is invasive by pricking and collecting blood sample from human arm (or finger-tip), then measuring the level either using a glucometer or sending to laboratory. This blood collecting process produces significant discomfort to the patients, especially to the children with type-A diabetes, resulting increased undetected-cases and health-complications. To overcome this drawbacks, a non-invasive ultra-wideband (UWB) BGCL measurement system is proposed here with enhanced software module. The hardware can be controlled through the graphical user interface (GUI) of software and can execute signal processing, feature extraction, and feature classification using artificial intelligence (AI). As AI, cascade forward neural network (CFNN) and naïve bayes (NB) algorithms are investigated, then CFNN with four independent features (skewness, kurtosis, variance, mean-absolute-deviation) are found to be best-suited for BGCL estimation. A transmit (Tx) antenna was placed at one side of left-earlobe to Tx UWB signals, and a receive (Rx) antenna at opposite side to Rx transmitted signals with BGCL marker. These signals are saved and used for AI training, validation and testing. The system with CFNN shows approximately 86.62% accuracy for BGCL measurement, which is 5.62% improved compared to other methods by showing its superiority. This enhanced system is affordable, effective and easy-to-use for all users (home and hospital), to reduce undetected diabetes cases and related mortality rate in near future.

KW - Blood glucose concentration level

KW - Cascade forward neural network

KW - Non-invasive measurement

KW - UWB

UR - http://www.scopus.com/inward/record.url?scp=85089608237&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85089608237&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-52856-0_30

DO - 10.1007/978-3-030-52856-0_30

M3 - Conference paper

AN - SCOPUS:85089608237

SN - 9783030528553

VL - 325

T3 - Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST

SP - 376

EP - 387

BT - Cyber Security and Computer Science

A2 - Bhuiyan, Touhid

A2 - Rahman, Md. Mostafijur

A2 - Ali, Md. Asraf

PB - Springer

CY - Cham, Switzerland

T2 - 2nd International Conference on Computer Science and Cyber Security, ICONCS 2020

Y2 - 15 February 2020 through 16 February 2020

ER -

Islam M, Khatun S, Shoumy NJ, Ali MS, Karim MSA, Bari BS. Non-invasive diabetes level monitoring system using artificial intelligence and UWB. In Bhuiyan T, Rahman MM, Ali MA, editors, Cyber Security and Computer Science : Second EAI International Conference, ICONCS 2020, Proceedings. Vol. 325. Cham, Switzerland: Springer. 2020. p. 376-387. (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST). Epub 2020 Jul 30. doi: 10.1007/978-3-030-52856-0_30

Non-invasive diabetes level monitoring system using artificial intelligence and UWB

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this