Modelling groundwater level fluctuations by ELM merged advanced metaheuristic algorithms using hydroclimatic data

Geocarto International, Journal Year: 2022, Volume and Issue: 38(1)

Published: Dec. 14, 2022

The accurate assessment of groundwater levels is critical to water resource management. With global warming and climate change, its significance has become increasingly evident, particularly in arid semi-arid areas. This study compares new extreme learning machines (ELM) methods tuned with metaheuristic algorithms such as particle swarm optimization, grey wolf the whale optimization algorithm (WOA), Harris Hawks optimizer (HHO), jellyfish search (JFO) level estimation. Daily precipitation temperature datasets acquired from two stations northern Bangladesh were used inputs models, which evaluated based on different quantitative statistics assessed RMSE, MAE, R2, some graphical inspection methods. outcomes applications revealed that efficiency ELM models was considerably improved by using algorithms. ELM-JSO RMSE standalone model 13% for optimal precipitation, temperature, testing stage. Among implemented methods, ELM-JFO performed best estimating daily level, ELM-WOA ELM-HHO, respectively, followed it. Viability a machine method Jellyfish investigated estimation.The compared hybrid ELM-PSO, ELM-HHO data Bangladesh.The improves root mean square error inputs.

Language: Английский

---

BO-ALLCNN: Bayesian-Based Optimized CNN for Acute Lymphoblastic Leukemia Detection in Microscopic Blood Smear Images

Sensors, Journal Year: 2022, Volume and Issue: 22(15), P. 5520 - 5520

Published: July 24, 2022

Acute lymphoblastic leukemia (ALL) is a deadly cancer characterized by aberrant accumulation of immature lymphocytes in the blood or bone marrow. Effective treatment ALL strongly associated with early diagnosis disease. Current practice for initial performed through manual evaluation stained smear microscopy images, which time-consuming and error-prone process. Deep learning-based human-centric biomedical has recently emerged as powerful tool assisting physicians making medical decisions. Therefore, numerous computer-aided diagnostic systems have been developed to autonomously identify images. In this study, new Bayesian-based optimized convolutional neural network (CNN) introduced detection microscopic To promote classification performance, architecture proposed CNN its hyperparameters are customized input data Bayesian optimization approach. The technique adopts an informed iterative procedure search hyperparameter space optimal set that minimizes objective error function. trained validated using hybrid dataset formed integrating two public datasets. Data augmentation adopted further supplement image boost performance. search-derived model recorded improved performance image-based on test set. findings study reveal superiority Bayesian-optimized over other deep learning models.

Language: Английский

---

Feature Selection and Training Multilayer Perceptron Neural Networks Using Grasshopper Optimization Algorithm for Design Optimal Classifier of Big Data Sonar

Journal of Sensors, Journal Year: 2022, Volume and Issue: 2022, P. 1 - 14

Published: Nov. 14, 2022

The complexity and high dimensions of big data sonar, as well the unavoidable presence unwanted signals such noise, clutter, reverberation in environment sonar propagation, have made classification one most interesting applicable topics for active researchers this field. This paper proposes use Grasshopper Optimization Algorithm (GOA) to train Multilayer Perceptron Artificial Neural Network (MLP-NN) also select optimal features (called GMLP-GOA). GMLP-GOA hybrid classifier first extracts experimental using MFCC. Then, are selected GOA. In last step, MLP-NN trained with GOA is used classify sonar. To evaluate performance GMLP-GOA, compared MLP-GOA, MLP-GWO, MLP-PSO, MLP-ACO, MLP-GSA classifiers terms rate, convergence local optimization avoidance power, processing time. results indicated that achieved a rate 98.12% time 3.14 s.

Language: Английский

---

BIFM: Big-Data Driven Intelligent Forecasting Model for COVID-19

IEEE Access, Journal Year: 2021, Volume and Issue: 9, P. 97505 - 97517

Published: Jan. 1, 2021

Ever since the pandemic of Coronavirus disease (COVID-19) emerged in Wuhan, China, it has been recognized as a global threat and several studies have carried out nationally globally to predict outbreak with varying levels dependability accuracy. Also, mobility restrictions had widespread impact on people's behavior such fear using public transportation (traveling unknown passengers closed area). Securing an appropriate level safety during situation is highly problematic issue that resulted from sector which hit hard by COVID-19. This paper focuses developing intelligent computing model for forecasting The autoregressive integrated moving average (ARIMA) machine learning used develop best twenty-one worst-affected states India six worst-hit countries world including India. ARIMA models are predicting daily-confirmed cases 90 days future values high incidence goodness-of-fit measures achieved 85% MAPE all above computational analysis will be able throw some light planning management healthcare systems infrastructure.

Language: Английский

---

A Hybrid Sparrow Search Algorithm of the Hyperparameter Optimization in Deep Learning

Mathematics, Journal Year: 2022, Volume and Issue: 10(16), P. 3019 - 3019

Published: Aug. 22, 2022

Deep learning has been widely used in different fields such as computer vision and speech processing. The performance of deep algorithms is greatly affected by their hyperparameters. For complex machine models neural networks, it difficult to determine In addition, existing hyperparameter optimization easily converge a local optimal solution. This paper proposes method for that combines the Sparrow Search Algorithm Particle Swarm Optimization, called Hybrid Algorithm. takes advantages avoiding solution search efficiency Optimization achieve global optimization. Experiments verified proposed algorithm simple networks. results show strong capability avoid solutions satisfactory both low high-dimensional spaces. provides new problems models.

Language: Английский

---

COVID-19 diagnosis using chest CT scans and deep convolutional neural networks evolved by IP-based sine-cosine algorithm

Medical & Biological Engineering & Computing, Journal Year: 2022, Volume and Issue: 60(10), P. 2931 - 2949

Published: Aug. 12, 2022

Language: Английский

---

Optimal power flow using a hybridization algorithm of arithmetic optimization and aquila optimizer

Expert Systems with Applications, Journal Year: 2023, Volume and Issue: 235, P. 121212 - 121212

Published: Aug. 18, 2023

Language: Английский

---

Pulmonary Diffuse Airspace Opacities Diagnosis from Chest X-Ray Images Using Deep Convolutional Neural Networks Fine-Tuned by Whale Optimizer

Wireless Personal Communications, Journal Year: 2021, Volume and Issue: 124(2), P. 1355 - 1374

Published: Dec. 1, 2021

Language: Английский

---

Deep Transfer Learning for the Multilabel Classification of Chest X-ray Images

Diagnostics, Journal Year: 2022, Volume and Issue: 12(6), P. 1457 - 1457

Published: June 13, 2022

Chest X-ray (CXR) is widely used to diagnose conditions affecting the chest, its contents, and nearby structures. In this study, we a private data set containing 1630 CXR images with disease labels; most of were disease-free, but others contained multiple sites abnormalities. Here, deep convolutional neural network (CNN) models extract feature representations identify possible diseases in these images. We also transfer learning combined large open-source image sets resolve problems insufficient training optimize classification model. The effects different approaches reusing pretrained weights (model finetuning layer transfer), source sizes similarity levels target (ImageNet, ChestX-ray, CheXpert), methods integrating into (initiating, concatenating, co-training), backbone CNN (ResNet50 DenseNet121) on assessed. results demonstrated that applied model approach typically afforded better prediction models. When only one was adopted, ChestX-ray performed than CheXpert; however, after ImageNet initials attached, CheXpert better. ResNet50 initiating learning, whereas DenseNet121 concatenating co-training learning. Transfer preferable set. Overall, can further enhance capabilities reduce computing costs for

Language: Английский

---

Variable-length CNNs evolved by digitized chimp optimization algorithm for deep learning applications

Multimedia Tools and Applications, Journal Year: 2023, Volume and Issue: 83(1), P. 2589 - 2607

Published: May 16, 2023

Language: Английский

---