An intelligent health monitoring and diagnosis system based on the internet of things and fuzzy logic for cardiac arrhythmia COVID-19 patients

Computers in Biology and Medicine, Journal Year: 2023, Volume and Issue: 154, P. 106583 - 106583

Published: Jan. 25, 2023

Language: Английский

---

Overview of Explainable Artificial Intelligence for Prognostic and Health Management of Industrial Assets Based on Preferred Reporting Items for Systematic Reviews and Meta-Analyses

Sensors, Journal Year: 2021, Volume and Issue: 21(23), P. 8020 - 8020

Published: Dec. 1, 2021

Surveys on explainable artificial intelligence (XAI) are related to biology, clinical trials, fintech management, medicine, neurorobotics, and psychology, among others. Prognostics health management (PHM) is the discipline that links studies of failure mechanisms system lifecycle management. There a need, which still absent, produce an analytical compilation PHM-XAI works. In this paper, we use preferred reporting items for systematic reviews meta-analyses (PRISMA) present state art XAI applied PHM industrial assets. This work provides overview trend in answers question accuracy versus explainability, considering extent human involvement, explanation assessment, uncertainty quantification topic. Research articles associated with subject, since 2015 2021, were selected from five databases following PRISMA methodology, several them sensors. The data extracted examined obtaining diverse findings synthesized as follows. First, while young, analysis indicates growing acceptance PHM. Second, offers dual advantages, where it assimilated tool execute tasks explain diagnostic anomaly detection activities, implying real need Third, review shows papers provide interesting results, suggesting performance unaffected by XAI. Fourth, role, evaluation metrics, areas requiring further attention community. Adequate assessment metrics cater needs requested. Finally, most case featured considered based data, some sensors, showing available blends solve real-world challenges, increasing confidence models’ adoption industry.

Language: Английский

---

Machine learning and automatic ARIMA/Prophet models-based forecasting of COVID-19: methodology, evaluation, and case study in SAARC countries

Stochastic Environmental Research and Risk Assessment, Journal Year: 2022, Volume and Issue: 37(1), P. 345 - 359

Published: Oct. 5, 2022

Language: Английский

---

Abnormality Detection and Failure Prediction Using Explainable Bayesian Deep Learning: Methodology and Case Study with Industrial Data

Mathematics, Journal Year: 2022, Volume and Issue: 10(4), P. 554 - 554

Published: Feb. 11, 2022

Mistrust, amplified by numerous artificial intelligence (AI) related incidents, is an issue that has caused the energy and industrial sectors to be amongst slowest adopter of AI methods. Central this black-box problem AI, which impedes investments fast becoming a legal hazard for users. Explainable (XAI) recent paradigm tackle such issue. Being backbone industry, prognostic health management (PHM) domain recently been introduced into XAI. However, many deficiencies, particularly lack explanation assessment methods uncertainty quantification, plague young domain. In present paper, we elaborate framework on explainable anomaly detection failure employing Bayesian deep learning model Shapley additive explanations (SHAP) generate local global from PHM tasks. An measure utilized as marker anomalies expands scope include model’s confidence. addition, used improve performance, aspect neglected handful studies PHM-XAI. The quality examined accuracy consistency properties. elaborated tested real-world gas turbine synthetic turbofan prediction data. Seven out eight were successfully identified. Additionally, outcome showed 19% improvement in statistical terms achieved highest score best published results topic.

Language: Английский

---

Classifying COVID-19 based on amino acids encoding with machine learning algorithms

Chemometrics and Intelligent Laboratory Systems, Journal Year: 2022, Volume and Issue: 224, P. 104535 - 104535

Published: March 15, 2022

Language: Английский

---

Multi-source data driven cryptocurrency price movement prediction and portfolio optimization

Expert Systems with Applications, Journal Year: 2023, Volume and Issue: 219, P. 119600 - 119600

Published: Jan. 25, 2023

Language: Английский

---

On a Novel Dynamics of SEIR Epidemic Models with a Potential Application to COVID-19

Symmetry, Journal Year: 2022, Volume and Issue: 14(7), P. 1436 - 1436

Published: July 13, 2022

In this paper, we study a type of disease that unknowingly spreads for long time, but by default, only to minimal population. This is not usually fatal and often goes unnoticed. We propose derive novel epidemic mathematical model describe such disease, utilizing fractional differential system under the Atangana–Baleanu–Caputo derivative. deals with transmission between susceptible, exposed, infected, recovered classes. After formulating model, equilibrium points as well stability feasibility analyses are stated. Then, present results concerning existence positivity in solutions sensitivity analysis. Consequently, computational experiments conducted discussed via proper criteria. From our experimental results, find loss regain immunity result gain infections. Epidemic models can be linked symmetry asymmetry from distinct view. By using approach, much research may expected epidemiology other areas, particularly COVID-19, state how develops after being infected virus.

Language: Английский

---

An IoT-fuzzy intelligent approach for holistic management of COVID-19 patients

Heliyon, Journal Year: 2023, Volume and Issue: 10(1), P. e22454 - e22454

Published: Nov. 20, 2023

In this study, an internet of things (IoT)-enabled fuzzy intelligent system is introduced for the remote monitoring, diagnosis, and prescription treatment patients with COVID-19. The main objective present study to develop integrated tool that combines IoT logic provide timely healthcare diagnosis within a smart framework. This tracks patients' health by utilizing Arduino microcontroller, small affordable computer reads data from various sensors, gather data. Once collected, are processed, analyzed, transmitted web page access via IoT-compatible Wi-Fi module. cases emergencies, such as abnormal blood pressure, cardiac issues, glucose levels, or temperature, immediate action can be taken monitor critical COVID-19 in isolation. employs recommend medical treatments patients. Sudden changes these conditions remotely reported through providers, relatives, friends. assists professionals making informed decisions based on patient's condition.

Language: Английский

---

A Trend Forecasting Method for the Vibration Signals of Aircraft Engines Combining Enhanced Slice-Level Adaptive Normalization Using Long Short-Term Memory Under Multi-Operating Conditions

Sensors, Journal Year: 2025, Volume and Issue: 25(7), P. 2066 - 2066

Published: March 26, 2025

Trend forecasting and early anomaly warnings are important for avoiding aircraft engine failures or accidents. This study proposes a trend method based on enhanced Slice-level Adaptive Normalization (SAN) using Long Short-Term Memory (LSTM) neural network under multi-operating conditions. Firstly, condition recognition technology is constructed to automatically identify the operating conditions predetermined judgment conditions, vibration signal features adaptively divided into three typical namely, idling condition, starting utmost condition. The of original signals extracted reduce impacts fluctuations noise preliminarily. Secondly, SAN used normalize denormalize alleviate non-stationary factors. To improve prediction accuracy, an L1 filter adopted extract term features, which can effectively overfitting local information. Moreover, slice length quantitatively estimated by fixed points in filtering, tail amendment added expand applicable range SAN. Finally, LSTM-based model forecast normalized data from SAN, serving as input during denormalization. final results different output validity proposed verified test engine. show that achieve higher accuracy compared other methods.

Language: Английский

---

A Novel Hybrid Approach Using an Attention-Based Transformer + GRU Model for Predicting Cryptocurrency Prices

Mathematics, Journal Year: 2025, Volume and Issue: 13(9), P. 1484 - 1484

Published: April 30, 2025

In this article, we introduce a novel deep learning hybrid model that integrates attention Transformer and gated recurrent unit (GRU) architectures to improve the accuracy of cryptocurrency price predictions. By combining Transformer’s strength in capturing long-range patterns with GRU’s ability short-term sequential trends, provides well-rounded approach time series forecasting. We apply predict daily closing prices Bitcoin Ethereum based on historical data include past prices, trading volumes, Fear Greed Index. evaluate performance our proposed by comparing it four other machine models, two are non-sequential feedforward models: radial basis function network (RBFN) general regression neural (GRNN), bidirectional memory-based long memory (BiLSTM) (BiGRU). The model’s is assessed using several metrics, including mean squared error (MSE), root (RMSE), absolute (MAE), percentage (MAPE), along statistical validation through non-parametric Friedman test followed post hoc Wilcoxon signed-rank test. Results demonstrate consistently achieves superior accuracy, highlighting its effectiveness for financial prediction tasks. These findings provide valuable insights enhancing real-time decision making markets support growing use models analytics.

Language: Английский

---