A Model to Predict Heartbeat Rate Using Deep Learning Algorithms DOI Open Access
Ahmed A. Alsheikhy, Yahia Said, Tawfeeq Shawly

et al.

Healthcare, Journal Year: 2023, Volume and Issue: 11(3), P. 330 - 330

Published: Jan. 22, 2023

ECG provides critical information in a waveform about the heart's condition. This is crucial to physicians as it first thing be performed by cardiologists. When COVID-19 spread globally and became pandemic, government of Saudi Arabia placed various restrictions guidelines protect save citizens residents. One these was preventing individuals from touching any surface public private places. In addition, authorities mandatory rule all facilities sector evaluate temperature before entering. Thus, idea this study stems need have touchless technique determine heartbeat rate. article proposes viable dependable method estimate an average rate based on reflected light skin. model uses deep learning tools, including AlexNet, Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTMs), ResNet50V2. Three scenarios been conducted validate presented model. proposed approach takes its inputs video streams converts into frames images. Numerous trials volunteers assess outputs terms accuracy, mean absolute error (MAE), squared (MSE). The achieves 99.78% MAE 0.142 when combing LSTMs ResNet50V2, while MSE 1.82. Moreover, comparative measurement between algorithm some studies literature utilized methods, MAE, are performed. achieved outcomes reveal that developed surpasses other methods. findings show can applied healthcare aid physicians.

Language: Английский

Multistage SVR-RBF-Based Model for Heart Rate Prediction of Individuals DOI
Ivan Izonin, Roman Tkachenko,

Rostyslav Holoven

et al.

Lecture notes on data engineering and communications technologies, Journal Year: 2023, Volume and Issue: unknown, P. 211 - 220

Published: Jan. 1, 2023

Language: Английский

Citations

6
Potential of Machine Learning for Predicting Sleep Disorders: A Comprehensive Analysis of Regression and Classification Models DOI Creative Commons
Raed Alazaidah, Ghassan Samara, Mohammad Aljaidi

et al.

Diagnostics, Journal Year: 2023, Volume and Issue: 14(1), P. 27 - 27

Published: Dec. 22, 2023

Sleep disorder is a disease that can be categorized as both an emotional and physical problem. It imposes several difficulties problems, such distress during the day, sleep-wake disorders, anxiety, other problems. Hence, main objective of this research was to utilize strong capabilities machine learning in prediction sleep disorders. In specific, aimed meet three objectives. These objectives were identify best regression model, classification strategy highly suited datasets. Considering two related datasets evaluation metrics tasks classification, results revealed superiority MultilayerPerceptron, SMOreg, KStar models compared with twenty models. Furthermore, IBK, RandomForest, RandomizableFilteredClassifier showed superior performance belonged strategies. Finally, Function predictive among six considered strategies respect most metrics.

Language: Английский

Citations

6
Characterizing Help-Seeking Searches for Substance Use Treatment From Google Trends and Assessing Their Use for Infoveillance: Longitudinal Descriptive and Validation Statistical Analysis DOI Creative Commons
Thomas Patton, Daniela Abramovitz, Derek C. Johnson

et al.

Journal of Medical Internet Research, Journal Year: 2022, Volume and Issue: 24(12), P. e41527 - e41527

Published: Nov. 4, 2022

Background There is no recognized gold standard method for estimating the number of individuals with substance use disorders (SUDs) seeking help within a given geographical area. This presents challenge to policy makers in effective deployment resources treatment SUDs. Internet search queries related SUDs using Google Trends may represent low-cost, real-time, and data-driven infoveillance tool address this shortfall information. Objective paper assesses feasibility query data as an indicator unmet needs, demand treatment, predictor health harms needs. We explore continuum hypotheses account different outcomes that might be expected occur depending on relative system capacity timing relation trajectories behavior change. Methods used negative binomial regression models examine temporal trends annual SUD help-seeking internet from by US state cocaine, methamphetamine, opioids, cannabis, alcohol 2010 2020. To validate value these surveillance purposes, we then investigate relationship between searches state-level across care (including lack care). started looking at associations self-reported need National Survey Drug Use Health, national survey general population. Next, explored admission rates Treatment Episode Data Set, facilities. Finally, studied people experiencing dying opioid overdose, Agency Healthcare Research Quality CDC WONDER database. Results Statistically significant differences were observed over time 2020 (based P<.05 corresponding Wald tests). able identify outlier states each drug (eg, West Virginia both opioids methamphetamine), indicating significantly higher behaviors compared trends. our validation analyses showed positive, statistically relating use, admissions methamphetamine emergency department visits overdose mortality coefficients having P≤.05). Conclusions study demonstrates clear potential predict spatially temporally, especially disorders.

Language: Английский

Citations

9
A non-linear SVR-based cascade model for improving prediction accuracy of biomedical data analysis DOI Creative Commons
Ivan Izonin, Roman Tkachenko, Oleksandr Gurbych

et al.

Mathematical Biosciences & Engineering, Journal Year: 2023, Volume and Issue: 20(7), P. 13398 - 13414

Published: Jan. 1, 2023

<abstract> <p>Biomedical data analysis is essential in current diagnosis, treatment, and patient condition monitoring. The large volumes of that characterize this area require simple but accurate fast methods intellectual to improve the level medical services. Existing machine learning (ML) many resources (time, memory, energy) when processing datasets. Or they demonstrate a accuracy insufficient for solving specific application task. In paper, we developed new ensemble model increased approximation problems biomedical sets. based on cascading ML response surface linearization principles. addition, used Ito decomposition as means nonlinearly expanding inputs at each model. As weak learners, Support Vector Regression (SVR) with linear kernel was due significant advantages demonstrated by method among existing ones. training procedures SVR-based cascade are described, flow chart its implementation presented. modeling carried out real-world tabular set volume. task predicting heart rate individuals solved, which provides possibility determining human stress, an indicator various applied fields. optimal parameters operating were selected experimentally. authors shown more than 20 times higher (according Mean Squared Error (MSE)), well reduction duration procedure compared method, provided highest work those considered.</p> </abstract>

Language: Английский

Citations

5
A Model to Predict Heartbeat Rate Using Deep Learning Algorithms DOI Open Access
Ahmed A. Alsheikhy, Yahia Said, Tawfeeq Shawly

et al.

Healthcare, Journal Year: 2023, Volume and Issue: 11(3), P. 330 - 330

Published: Jan. 22, 2023

ECG provides critical information in a waveform about the heart's condition. This is crucial to physicians as it first thing be performed by cardiologists. When COVID-19 spread globally and became pandemic, government of Saudi Arabia placed various restrictions guidelines protect save citizens residents. One these was preventing individuals from touching any surface public private places. In addition, authorities mandatory rule all facilities sector evaluate temperature before entering. Thus, idea this study stems need have touchless technique determine heartbeat rate. article proposes viable dependable method estimate an average rate based on reflected light skin. model uses deep learning tools, including AlexNet, Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTMs), ResNet50V2. Three scenarios been conducted validate presented model. proposed approach takes its inputs video streams converts into frames images. Numerous trials volunteers assess outputs terms accuracy, mean absolute error (MAE), squared (MSE). The achieves 99.78% MAE 0.142 when combing LSTMs ResNet50V2, while MSE 1.82. Moreover, comparative measurement between algorithm some studies literature utilized methods, MAE, are performed. achieved outcomes reveal that developed surpasses other methods. findings show can applied healthcare aid physicians.

Language: Английский

Citations

4