A comprehensive study of mobile-health based assistive technology for the healthcare of dementia and Alzheimer’s disease (AD)

Yousaf, Kanwal; Mehmood, Zahid; Awan, Israr Ahmad; Saba, Tanzila; Alharbey, Riad; Qadah, Talal; Alrige, Mayda

doi:10.1007/s10729-019-09486-0

Cited by 90 publications

(58 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning techniques play a significant role in infection detection and prediction (Perveen et al, 2020;Yousaf et al, 2020). The trained-techniques can process big data at high speed to find infection cases and trends to warn the decision-makers (Sadad, Munir, Saba, & Hussain, 2018;Saba, Haseeb.…”

mentioning

confidence: 99%

Machine learning techniques to detect and forecast the daily total COVID‐19 infected and deaths cases under different lockdown types

Saba

Abunadi

Shahzad

et al. 2021

Microscopy Res & Technique

Self Cite

View full text Add to dashboard Cite

COVID‐19 has impacted the world in many ways, including loss of lives, economic downturn and social isolation. COVID‐19 was emerged due to the SARS‐CoV‐2 that is highly infectious pandemic. Every country tried to control the COVID‐19 spread by imposing different types of lockdowns. Therefore, there is an urgent need to forecast the daily confirmed infected cases and deaths in different types of lockdown to select the most appropriate lockdown strategies to control the intensity of this pandemic and reduce the burden in hospitals. Currently are imposed three types of lockdown (partial, herd, complete) in different countries. In this study, three countries from every type of lockdown were studied by applying time‐series and machine learning models, named as random forests, K‐nearest neighbors, SVM, decision trees (DTs), polynomial regression, Holt winter, ARIMA, and SARIMA to forecast daily confirm infected cases and deaths due to COVID‐19. The models' accuracy and effectiveness were evaluated by error based on three performance criteria. Actually, a single forecasting model could not capture all data sets' trends due to the varying nature of data sets and lockdown types. Three top‐ranked models were used to predict the confirmed infected cases and deaths, the outperformed models were also adopted for the out‐of‐sample prediction and obtained very close results to the actual values of cumulative infected cases and deaths due to COVID‐19. This study has proposed the auspicious models for forecasting and the best lockdown strategy to mitigate the causalities of COVID‐19.

show abstract

mentioning

confidence: 99%

Machine learning techniques to detect and forecast the daily total COVID‐19 infected and deaths cases under different lockdown types

Saba

Abunadi

Shahzad

et al. 2021

Microscopy Res & Technique

Self Cite

View full text Add to dashboard Cite

show abstract

“…Provider buy-in may also allay potential privacy and security concerns [ 63 ]. This will have to be addressed even as the market moves into the development of user-friendly mobile phone apps [ 64 ].…”

Section: Discussionmentioning

confidence: 99%

The Feasibility and Utility of a Personal Health Record for Persons With Dementia and Their Family Caregivers for Web-Based Care Coordination: Mixed Methods Study

Peterson¹,

Mikal²,

McCarron³

et al. 2020

JMIR Aging

View full text Add to dashboard Cite

Background Managing the complex and long-term care needs of persons living with Alzheimer disease and related dementias (ADRD) can adversely impact the health of informal caregivers and their care recipients. Web-based personal health records (PHRs) are one way to potentially alleviate a caregiver’s burden by simplifying ADRD health care management Objective This study aimed to evaluate Personal Health Record for Persons with Dementia and Their Family Caregivers (PHR-ADRD), a free web-based information exchange tool, using a multiphase mixed methods approach. Methods Dementia caregivers (N=34) were surveyed for their well-being and perceptions of PHR-ADRD feasibility and utility at 6 and 12 months using close- and open-ended questions as well as a semistructured interview (n=8). Exploratory analyses compared participants’ characteristics as well as PHR-ADRD use and experiences based on overall favorability status. Results Feasibility and utility scores decreased over time, but a subset of participants indicated that the system was helpful. Quantitative comparisons could not explain why some participants indicated favorable, neutral, or unfavorable views of the system overall or had not engaged with PHR-ADRD. Qualitative findings suggested that technology literacy and primary care provider buy-in were barriers. Both qualitative and qualitative findings indicated that time constraints to learn and use the system affected most participants. Conclusions Development and dissemination of PHRs for family caregivers of persons with ADRD should aim to make systems user-friendly for persons with limited time and technological literacy. Establishing health care provider buy-in may be essential to the future success of any PHR system.

show abstract

“…In machine learning, there are several supervisors and unsupervised learning techniques that provide accurate and robust recognition rates such as ANN (Tahir et al, 2019;), KNN(Ullah et al, 2019), CNN (Yousaf et al, 2019,b), SVM (Khan, Akram, et al, 2019; Khan, Javed, Sharif, Saba, & Rehman, 2019; Khan, Lali, et al, 2019; Khan, Nazir, et al, 2019; Khan, Sharif, et al, 2019; Sharif, Khan, Saba, Raza, & Rehman, 2019), Clustering (Fahad, Khan, Saba, Rehman, & Iqbal, 2018), regression (Saba et al, 2017). These learning algorithms have shown remarkable performance in pattern recognition for health care, security, stock market, renewable energy, weather forecasting etc.…”

Section: Proposed Methodologymentioning

confidence: 99%

Light microscopic iris classification using ensemble multi‐class support vector machine

Rehman

2021

Microscopy Res & Technique

View full text Add to dashboard Cite

Similar to other biometric systems such as fingerprint, face, DNA, iris classification could assist law enforcement agencies in identifying humans. Iris classification technology helps law‐enforcement agencies to recognize humans by matching their iris with iris data sets. However, iris classification is challenging in the real environment due to its invertible and complex texture variations in the human iris. Accordingly, this article presents an improved Oriented FAST and Rotated BRIEF with Bag‐of‐Words model to extract distinct and robust features from the iris image, followed by ensemble multi‐class‐SVM to classify iris. The proposed methodology consists of four main steps; first, iris image normalization and enhancement; second, localizing iris region; third, iris feature extraction; finally, iris classification using ensemble multi‐class support vector machine. For preprocessing of input images, histogram equalization, Gaussian mask and median filters are applied. The proposed technique is tested on two benchmark databases, that is, CASIA‐v1 and iris image database, and achieved higher accuracy than other existing techniques reported in state of the art.

show abstract

A comprehensive study of mobile-health based assistive technology for the healthcare of dementia and Alzheimer’s disease (AD)

Cited by 90 publications

References 78 publications

Machine learning techniques to detect and forecast the daily total COVID‐19 infected and deaths cases under different lockdown types

Machine learning techniques to detect and forecast the daily total COVID‐19 infected and deaths cases under different lockdown types

The Feasibility and Utility of a Personal Health Record for Persons With Dementia and Their Family Caregivers for Web-Based Care Coordination: Mixed Methods Study

Light microscopic iris classification using ensemble multi‐class support vector machine

Contact Info

Product

Resources

About