Systematic map and review of predictive techniques in diabetes self-management

Idrissi, Touria El; Idri, Ali; Bakkoury, Zohra

doi:10.1016/j.ijinfomgt.2018.09.011

Cited by 52 publications

(28 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…El Idrissi et al [7] investigated by the mean of a systematic map and review the use of predictive techniques in data mining for the diabetes self-management. The study summarized and reviewed 38 studies published from 2000 to April 2017 with regards to: 1) publication's year and source, 2) diabetes' type, 3) investigated clinical tasks, 4) the used predictive techniques and 5) their performance.…”

Section: Related Workmentioning

confidence: 99%

“…However, none of the used DM predictive techniques is dominant over the others. Table I reports the findings of a set of selected studies from the review of El Idrissi et al [7], in addition to the two recent studies [8], [9]. From Table I, we note that:…”

Section: Related Workmentioning

confidence: 99%

“…If not well managed, this disease can lead to serious problems such as heart attacks, kidney damage, blindness, unconsciousness and even death [6]. The prediction of blood glucose level (BGL) is an important task in the diabetes management and self-management as it can help controlling the BGL by taking appropriate actions ahead of time [7]. To predict the BGL, the previous glucose measurements are required.…”

mentioning

confidence: 99%

“…To predict the BGL, the previous glucose measurements are required. The BGL can be measured: 1) Manually by selfmonitoring of blood glucose (SMBG) using sticks several times a day or 2) Automatically by continuous glucose monitoring (CGM) using sensors [6], [7].…”

mentioning

confidence: 99%

“…According to El Idrissi et al [7], considerable work was done for the BGL prediction and various Data Mining approaches including statistical methods and machine learning techniques were investigated for that purpose; the most used ones are Artificial Neural Networks (NNs) and Auto Regression (AR) [7]. Recently, deep learning modeling is gaining more interest, such as LSTM NN [8] and deep NN [9].…”

mentioning

confidence: 99%

See 4 more Smart Citations

Predicting blood glucose using an LSTM Neural Network

Idriss¹,

Idri

Abnane

et al. 2019

Annals of Computer Science and Information Systems

Self Cite

View full text Add to dashboard Cite

Diabetes self-management relies on the blood glucose prediction as it allows taking suitable actions to prevent low or high blood glucose level. In this paper, we propose a deep learning neural network (NN) model for blood glucose prediction. It is a sequential one using a Long-Short-Term Memory (LSTM) layer with two fully connected layers. Several experiments were carried out over data of 10 diabetic patients to decide on the model's parameters in order to identify the best variant of it. The performance of the proposed LSTM NN measured in terms of root mean square error (RMSE) was compared with the ones of an existing LSTM and an autoregressive (AR) models. The results show that our LSTM NN is significantly more accurate; in fact, it outperforms the existing LSTM model for all patients and outperforms the AR model in 9 over 10 patients, besides, the performance differences were assessed by the Wilcoxon statistical test. Furthermore, the mean of the RMSE of our model was 12.38 mg/dl while it was 28.84 mg/dl and 50.69 mg/dl for AR and the existing LSTM respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Predicting blood glucose using an LSTM Neural Network

Idriss¹,

Idri

Abnane

et al. 2019

Annals of Computer Science and Information Systems

Self Cite

View full text Add to dashboard Cite

show abstract

Role of sustainable business model, Industry 4.0, crowdfunding, and stakeholders' pressure toward firm's sustainability: A SEM‐ANN approach

Rahman,

Wen,

Amjad

2024

Bus Strat Env

View full text Add to dashboard Cite

With growing global attention on achieving sustainable development goals, businesses worldwide face mounting pressures to incorporate sustainability into their business models and operations. However, despite the recognized importance of sustainability in modern manufacturing operations, the path toward embedding sustainability remains unclear and challenging for many manufacturing firms. Within the theoretical framework of dynamic capability theory and the imperative of sustainable development goals, this study investigates the influence of sustainable business models, crowdfunding, Industry 4.0 technologies, and stakeholders' pressure on the sustainable performance of manufacturing firms in Pakistan. Based on survey data from 370 small and medium enterprise owners and managers, our study utilized a hybrid approach by combining partial least squares–Structural equation modeling (SEM) and artificial neural networking techniques. The results emphasize a significant and positive impact of a sustainable business model on firm sustainability. Moreover, the findings reveal that Industry 4.0 technology and crowdfunding partially mediate the relationship between sustainable business models and sustainable performance, highlighting the significant role of advanced technologies and alternative financing. Besides, stakeholders' pressure emerges as a crucial moderator, further strengthening the relationship between sustainable business models and firm sustainability. This study advances knowledge of sustainable business actions within the firms and constitutes a valuable input for businesses, policymakers, and other stakeholders dedicated to enhancing sustainable growth in the manufacturing sector.

show abstract

Why retail investors traded equity during the pandemic? An application of artificial neural networks to examine behavioral biases

Talwar¹,

Talwar

Tarjanne

et al. 2021

Psychology and Marketing

View full text Add to dashboard Cite

Behavioral biases are known to influence the investment decisions of retail investors.Indeed, extant research has revealed interesting findings in this regard. However, the literature on the impact of these biases on millennials' trading activity, particularly during a health crisis like the COVID-19 pandemic, as well as the equity recommendation intentions of such investors, is limited. The present study addressed these gaps by investigating the influence of eight behavioral biases: overconfidence and selfattribution, over-optimism, hindsight, representativeness, anchoring, loss aversion, mental accounting, and herding on the trading activity and recommendation intentions of millennials during the pandemic. An artificial neural network approach was used to analyze the data collected from 351 millennial men in Finland. The results revealed that herding, hindsight, overconfidence and self-attribution, representativeness, and anchoring influence both trading activity and recommendation intentions, albeit to varying extents. Notably, loss aversion and mental accounting influence only the recommendation intentions. Furthermore, the relationship of the two endogenous variables is nonlinear with herding, representativeness, and anchoring but is linear with other biases. In addition to the quantitative study, we also conducted a post hoc qualitative study with 19 millennials to evaluate the persistence of behavioral biases among them through the pandemic. K E Y W O R D S artificial neural network (ANN), behavioral biases, behavioral finance, heuristic simplification, retail investors 1 | INTRODUCTION Behavioral finance has emerged as a key field of study in the area of investment management. It examines the rationally inexplicable behavioral aspects of individuals and institutions transacting in financial markets. An increase in the investment activity of retail participants during the recent past has made understanding such behavioral aspects all the more critical (Seth et al., 2020). In this regard, scholars have observed that two distinct sets of factors drive retail investors' decision to invest: (a) rational factors related to traditional finance (Cuong & Jian, 2015) and (b) irrational factors that come under the domain of behavioral finance (Baltussen & Post, 2011). Traditional finance assumes that This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Systematic map and review of predictive techniques in diabetes self-management

Cited by 52 publications

References 38 publications

Predicting blood glucose using an LSTM Neural Network

Predicting blood glucose using an LSTM Neural Network

Role of sustainable business model, Industry 4.0, crowdfunding, and stakeholders' pressure toward firm's sustainability: A SEM‐ANN approach

Why retail investors traded equity during the pandemic? An application of artificial neural networks to examine behavioral biases

Contact Info

Product

Resources

About