Case study: Integrating IoT, streaming analytics and machine learning to improve intelligent diabetes management system

Ara, Affreen; Ara, Aftab

doi:10.1109/icecds.2017.8390043

Cited by 37 publications

(10 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The health domain may be the most pervasive applications because the IoT devices are attached to individuals. The applications predict sugar level for diabetes management [15], estimate thermal comfort level at a workplace [67], and detect when a person falls at home [108]. A study [38] employed deep learning to detect ambulation events such as abnormal walking pattern, sleeping habits, and washroom visits.…”

Section: A Review Of Intelligent Big Data Analytics For Iotmentioning

confidence: 99%

Machine learning and data analytics for the IoT

Adi

Anwar

Baig

et al. 2020

Neural Comput & Applic

193

View full text Add to dashboard Cite

The Internet of Things (IoT) applications has grown in exorbitant numbers, generating a large amount of data required for intelligent data processing. However, the varying IoT infrastructures (i.e. cloud, edge, fog) and the limitations of the IoT application layer protocols in transmitting/receiving messages become the barriers in creating intelligent IoT applications. These barriers prevent current intelligent IoT applications to adaptively learn from other IoT applications. In this paper, we critically review how IoT-generated data is processed for machine learning analysis, and highlight the current challenges in furthering intelligent solutions in the IoT environment. Furthermore, we propose a framework to enable IoT applications to adaptively learn from other IoT applications, and present a case study in how the framework can be applied to the real studies in the literature. Finally, we discuss the key factors that have an impact on future intelligent applications for the IoT.

show abstract

Section: A Review Of Intelligent Big Data Analytics For Iotmentioning

confidence: 99%

Machine learning and data analytics for the IoT

Adi

Anwar

Baig

et al. 2020

Neural Comput & Applic

193

View full text Add to dashboard Cite

show abstract

“…After completion of the FGM intervention, the glucose data were downloaded. The following glycemic variability indices obtained from the FGM were calculated using E-Followup software from Zion China [11]: mean amplitude of glycemic excursion (MAGE), mean of daily difference (MODD), standard deviation (SD), coefficient of variation (CV), interquartile range (IQR) and largest amplitude of glycemic excursions (LAGEs).…”

Section: Sensors and Readersmentioning

confidence: 99%

Continuous subcutaneous insulin infusion combined with liraglutide reduced glycemic variability and oxidative stress in type 2 diabetes mellitus: a study based on the flash glucose monitoring system

Yao

et al. 2019

Endocr J

View full text Add to dashboard Cite

We aimed to explore the use of the flash glucose monitoring (FGM) system in hospitalized newly diagnosed type 2 diabetes mellitus (T2DM) patients and to evaluate a new combination therapy of continuous subcutaneous insulin infusion (CSII) with or without liraglutide. This was an open-label, randomized study that was conducted in 60 newly diagnosed T2DM patients. The patients were randomized to receive either CSII (n = 30) or CSII + liraglutide (n = 30). The FGM system was used to assess the glycemic control and glycemic variability (GV) indices for 2 weeks. Mean blood glucose concentration (MBG), estimated hemoglobin A1c (HbA1c), and measures of GV, including the standard deviation of the mean glucose (SD), coefficient of variation (CV), interquartile range (IQR), mean amplitude of glycemic excursions (MAGE), largest amplitude of glycemic excursions (LAGE), and mean of daily difference (MODD) were compared between the two groups. Two oxidative stress biomarkers, 4-hydroxynonenal (4-HNE) and 8-hydroxydeoxyguanosine (8-OHdG), were measured before and after treatment. The estimated HbA1c and MBG decreased in both groups, especially the CSII + liraglutide group. SD, IQR, LAGE, and MODD were significantly lower in the CSII + liraglutide group than in the CSII group (all p < 0.05); there was no difference in CV or MAGE (p > 0.05). Similarly, the 4-HNE and 8-OHdG levels were significantly lower in the CSII + liraglutide group (p < 0.05). Our findings suggest that CSII with liraglutide was superior to CSII monotherapy in improving glycemic control and glycemic variability and in decreasing oxidative stress markers. Flash glucose monitoring can successfully provide ambulatory glucose profile data in the real world.

show abstract

“…Personalised diabetic management is an example of a PH service that uses the IoT and ML techniques. The system provides dietary advice to an individual based on analyzing their food habits and insulin response using a CloudIoT based application [ 10 ].…”

Section: Introductionmentioning

confidence: 99%

A Smart Biometric Identity Management Framework for Personalised IoT and Cloud Computing-Based Healthcare Services

Farid

Elkhodr

Sabrina

et al. 2021

Sensors

View full text Add to dashboard Cite

This paper proposes a novel identity management framework for Internet of Things (IoT) and cloud computing-based personalized healthcare systems. The proposed framework uses multimodal encrypted biometric traits to perform authentication. It employs a combination of centralized and federated identity access techniques along with biometric based continuous authentication. The framework uses a fusion of electrocardiogram (ECG) and photoplethysmogram (PPG) signals when performing authentication. In addition to relying on the unique identification characteristics of the users’ biometric traits, the security of the framework is empowered by the use of Homomorphic Encryption (HE). The use of HE allows patients’ data to stay encrypted when being processed or analyzed in the cloud. Thus, providing not only a fast and reliable authentication mechanism, but also closing the door to many traditional security attacks. The framework’s performance was evaluated and validated using a machine learning (ML) model that tested the framework using a dataset of 25 users in seating positions. Compared to using just ECG or PPG signals, the results of using the proposed fused-based biometric framework showed that it was successful in identifying and authenticating all 25 users with 100% accuracy. Hence, offering some significant improvements to the overall security and privacy of personalized healthcare systems.

show abstract

Case study: Integrating IoT, streaming analytics and machine learning to improve intelligent diabetes management system

Cited by 37 publications

References 0 publications

Machine learning and data analytics for the IoT

Machine learning and data analytics for the IoT

Continuous subcutaneous insulin infusion combined with liraglutide reduced glycemic variability and oxidative stress in type 2 diabetes mellitus: a study based on the flash glucose monitoring system

A Smart Biometric Identity Management Framework for Personalised IoT and Cloud Computing-Based Healthcare Services

Contact Info

Product

Resources

About