An intelligent driven deep residual learning framework for brain tumor classification using MRI images

Expert Systems with Applications, Journal Year: 2022, Volume and Issue: 213, P. 119087 - 119087

Published: Oct. 23, 2022

Language: Английский

---

Dynamic Candidate Solution Boosted Beluga Whale Optimization Algorithm for Biomedical Classification

Mathematics, Journal Year: 2023, Volume and Issue: 11(3), P. 707 - 707

Published: Jan. 30, 2023

In many fields, complicated issues can now be solved with the help of Artificial Intelligence (AI) and Machine Learning (ML). One more modern Metaheuristic (MH) algorithms used to tackle numerous in various fields is Beluga Whale Optimization (BWO) method. However, BWO has a lack diversity, which could lead being trapped local optimaand premature convergence. This study presents two stages for enhancing fundamental algorithm. The initial stage BWO’s Opposition-Based (OBL), also known as OBWO, helps expedite search process enhance learning methodology choose better generation candidate solutions BWO. second step, referred OBWOD, combines Dynamic Candidate Solution (DCS) OBWO based on k-Nearest Neighbor (kNN) classifier boost variety improve consistency selected solution by giving potential candidates chance solve given problem high fitness value. A comparison present optimization single-objective bound-constraint problems was conducted evaluate performance OBWOD algorithm from 2022 IEEE Congress Evolutionary Computation (CEC’22) benchmark test suite range dimension sizes. results statistical significance confirmed that proposed competitive algorithms. addition, surpassed seven other an overall classification accuracy 85.17% classifying 10 medical datasets different sizes according evaluation matrix.

Language: Английский

---

A lightweight CNN-based network on COVID-19 detection using X-ray and CT images

Computers in Biology and Medicine, Journal Year: 2022, Volume and Issue: 146, P. 105604 - 105604

Published: May 11, 2022

Language: Английский

---

Community Detection Algorithms in Healthcare Applications: A Systematic Review

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 30247 - 30272

Published: Jan. 1, 2023

Over the past few years, number and volume of data sources in healthcare databases has grown exponentially. Analyzing these voluminous medical is both opportunity challenge for knowledge discovery health informatics. In last decade, social network analysis techniques community detection algorithms are being used more scientific fields, including medicine. While have been widely analysis, a comprehensive review its applications way to benefit practitioners informatics still overwhelmingly missing. This paper contributes fill this gap provide up-to-date literature research. Especially, categorizations existing presented discussed. Moreover, most reviewed categorized. Finally, publicly available datasets, key challenges, gaps field studied reviewed.

Language: Английский

---

A deep learning based trust- and tag-aware recommender system

Neurocomputing, Journal Year: 2021, Volume and Issue: 488, P. 557 - 571

Published: Nov. 27, 2021

Language: Английский

---

Novel leakage detection by ensemble 1DCNN-VAPSO-SVM in oil and gas pipeline systems

Applied Soft Computing, Journal Year: 2021, Volume and Issue: 115, P. 108212 - 108212

Published: Dec. 8, 2021

Language: Английский

---

An advanced short-term wind power forecasting framework based on the optimized deep neural network models

International Journal of Electrical Power & Energy Systems, Journal Year: 2022, Volume and Issue: 141, P. 108143 - 108143

Published: April 6, 2022

Language: Английский

---

A novel explainable COVID-19 diagnosis method by integration of feature selection with random forest

Informatics in Medicine Unlocked, Journal Year: 2022, Volume and Issue: 30, P. 100941 - 100941

Published: Jan. 1, 2022

Several Artificial Intelligence-based models have been developed for COVID-19 disease diagnosis. In spite of the promise artificial intelligence, there are very few which bridge gap between traditional human-centered diagnosis and potential future machine-centered Under concept human-computer interaction design, this study proposes a new explainable intelligence method that exploits graph analysis feature visualization optimization purpose from blood test samples. model, an decision forest classifier is employed to classification based on routinely available patient data. The approach enables clinician use tree guide explainability interpretability prediction model. By utilizing novel selection phase, proposed model will not only improve accuracy but decrease execution time as well.

Language: Английский

---

Artificial Intelligence and Internet of Things (AI-IoT) Technologies in Response to COVID-19 Pandemic: A Systematic Review

IEEE Access, Journal Year: 2022, Volume and Issue: 10, P. 62613 - 62660

Published: Jan. 1, 2022

The origin of the COVID-19 pandemic has given overture to redirection, as well innovation many digital technologies. Even after progression vaccination efforts across globe, total eradication this is still a distant future due evolution new variants. To proactively deal with pandemic, health care service providers and caretaker organizations require technologies, alongside improvements in existing related Internet Things (IoT), Artificial Intelligence (AI), Machine Learning terms infrastructure, efficiency, privacy, security. This paper provides an overview current theoretical application prospects IoT, AI, cloud computing, edge deep learning techniques, blockchain social networks, robots, machines, security techniques. In consideration these intersection we reviewed technologies within broad umbrella AI-IoT most concise classification scheme. review, illustrated that technological applications innovations have impacted field healthcare. essential found for healthcare were fog computing learning, blockchain. Furthermore, highlighted several aspects their impact novel methodology using techniques from image processing, machine differential system modeling.

Language: Английский

---

Probabilistic Wind Power Forecasting Using Optimized Deep Auto-Regressive Recurrent Neural Networks

IEEE Transactions on Industrial Informatics, Journal Year: 2022, Volume and Issue: 19(3), P. 2814 - 2825

Published: March 22, 2022

Wind power forecasting is very crucial for system planning and scheduling. Deep neural networks (DNNs) are widely used in applications due to their exceptional performance. However, the DNNs’ architectural configuration has a significant impact on performance, selection of proper hyper-parameters determines success or failure these models. Therefore, one challenging issues DNNs how assess hyper-parameter values effectively. Most previous researches literature have tuned manually, which weak time-consuming task. Using optimization/evolutionary algorithms an effective way obtain optimal automatically. In this article, we propose novel evolutionary algorithm that based grasshopper optimization (GOA) improved by adding two operators, opposition-based learning chaos theory, process. Overall, probabilistic wind model named GOA deep auto-regressive (NGOA-DeepAr) proposed recurrent network optimized its hyper-parameters. The performance NGOA-DeepAr tested different datasets: One publicly available GEFCom-2014 dataset other Australian Energy Market Operator dataset. prediction interval coverage probability pinball loss datasets $[0.902, 0.320]$ notation="LaTeX">$[0.933, 1.4885]$ , respectively. According experimental findings, our much faster outperforms benchmark neuroevolutionary

Language: Английский

---