Modelling Temperature Variation of Mushroom Growing Hall Using Artificial Neural Networks DOI
Sina Ardabili,

Amir Mosavi,

Asghar Mahmoudi

и другие.

Lecture notes in networks and systems, Год журнала: 2020, Номер unknown, С. 33 - 45

Опубликована: Янв. 1, 2020

Язык: Английский

Artificial Neural Networks Based Optimization Techniques: A Review DOI Open Access
Maher G. M. Abdolrasol, S. M. Suhail Hussain, Taha Selim Ustun

и другие.

Electronics, Год журнала: 2021, Номер 10(21), С. 2689 - 2689

Опубликована: Ноя. 3, 2021

In the last few years, intensive research has been done to enhance artificial intelligence (AI) using optimization techniques. this paper, we present an extensive review of neural networks (ANNs) based algorithm techniques with some famous techniques, e.g., genetic (GA), particle swarm (PSO), bee colony (ABC), and backtracking search (BSA) modern developed lightning (LSA) whale (WOA), many more. The entire set such is classified as algorithms on a population where initial randomly created. Input parameters are initialized within specified range, they can provide optimal solutions. This paper emphasizes enhancing network via by manipulating its tuned or training obtain best structure pattern dissolve problems in way. includes results for improving ANN performance PSO, GA, ABC, BSA respectively, parameters, number neurons hidden layers learning rate. obtained net used solving energy management virtual power plant system.

Язык: Английский

Процитировано

437

COVID-19 Pandemic Prediction for Hungary; A Hybrid Machine Learning Approach DOI Creative Commons
Gergő Pintér, Imre Felde,

Amir Mosavi

и другие.

Mathematics, Год журнала: 2020, Номер 8(6), С. 890 - 890

Опубликована: Июнь 2, 2020

Several epidemiological models are being used around the world to project number of infected individuals and mortality rates COVID-19 outbreak. Advancing accurate prediction is utmost importance take proper actions. Due lack essential data uncertainty, have been challenged regarding delivery higher accuracy for long-term prediction. As an alternative susceptible-infected-resistant (SIR)-based models, this study proposes a hybrid machine learning approach predict COVID-19, we exemplify its potential using from Hungary. The methods adaptive network-based fuzzy inference system (ANFIS) multi-layered perceptron-imperialist competitive algorithm (MLP-ICA) proposed time series rate. that by late May, outbreak total morality will drop substantially. validation performed 9 days with promising results, which confirms model accuracy. It expected maintains as long no significant interruption occurs. This paper provides initial benchmarking demonstrate future research.

Язык: Английский

Процитировано

230

Deep learning convolutional neural network in rainfall–runoff modelling DOI Open Access

Song Pham Van,

Hoang Le,

Dat Vi Thanh

и другие.

Journal of Hydroinformatics, Год журнала: 2020, Номер 22(3), С. 541 - 561

Опубликована: Апрель 17, 2020

Abstract Rainfall–runoff modelling is complicated due to numerous complex interactions and feedback in the water cycle among precipitation evapotranspiration processes, also geophysical characteristics. Consequently, lack of characteristics such as soil properties leads difficulties developing physical analytical models when traditional statistical methods cannot simulate rainfall–runoff accurately. Machine learning techniques with data-driven methods, which can capture nonlinear relationship between prediction predictors, have been rapidly developed last decades many applications field resources. This study attempts develop a novel 1D convolutional neural network (CNN), deep technique, ReLU activation function for modelling. The paradigm includes applying two filters parallel separate time series, allows fast processing data exploitation correlation structure multivariate series. framework evaluated measured at Chau Doc Can Tho hydro-meteorological stations Vietnamese Mekong Delta. proposed model results are compared simulations long short-term memory (LSTM) models. Both CNN LSTM better performance than models, slightly results. We demonstrate that suitable regression-type problems effectively learn dependencies series without need historical time-efficient easy implement alternative recurrent-type networks tends outperform linear recurrent

Язык: Английский

Процитировано

206

Deep Learning for Detecting Building Defects Using Convolutional Neural Networks DOI Creative Commons
Husein Perez, J.H.M. Tah,

Amir Mosavi

и другие.

Sensors, Год журнала: 2019, Номер 19(16), С. 3556 - 3556

Опубликована: Авг. 15, 2019

Clients are increasingly looking for fast and effective means to quickly frequently survey communicate the condition of their buildings so that essential repairs maintenance work can be done in a proactive timely manner before it becomes too dangerous expensive. Traditional methods this type commonly comprise engaging building surveyors undertake assessment which involves lengthy site inspection produce systematic recording physical elements, including cost estimates immediate projected long-term costs renewal, repair building. Current asset procedures extensively time consuming, laborious, expensive pose health safety threats surveyors, particularly at height roof levels difficult access. This paper aims evaluating application convolutional neural networks (CNN) towards an automated detection localisation key defects, e.g., mould, deterioration, stain, from images. The proposed model is based on pre-trained CNN classifier VGG-16 (later compaired with ResNet-50, Inception models), class activation mapping (CAM) object localisation. challenges limitations real-life applications have been identified. has proven robust able accurately detect localise defects. approach being developed potential scale-up further advance support defects deterioration real-time using mobile devices drones.

Язык: Английский

Процитировано

195

Advances in Machine Learning Modeling Reviewing Hybrid and Ensemble Methods DOI
Sina Ardabili,

Amir Mosavi,

Annamária R. Várkonyi-Kóczy

и другие.

Lecture notes in networks and systems, Год журнала: 2020, Номер unknown, С. 215 - 227

Опубликована: Янв. 1, 2020

Язык: Английский

Процитировано

171

EEG based Major Depressive disorder and Bipolar disorder detection using Neural Networks:A review DOI Creative Commons
Sana Yasin, Syed Asad Hussain, Sinem Aslan

и другие.

Computer Methods and Programs in Biomedicine, Год журнала: 2021, Номер 202, С. 106007 - 106007

Опубликована: Фев. 23, 2021

Язык: Английский

Процитировано

161

Deep learning versus gradient boosting machine for pan evaporation prediction DOI Creative Commons
Anurag Malik, Mandeep Kaur Saggi, Sufia Rehman

и другие.

Engineering Applications of Computational Fluid Mechanics, Год журнала: 2022, Номер 16(1), С. 570 - 587

Опубликована: Фев. 7, 2022

In the present study, two innovative techniques namely, Deep Learning (DL) and Gradient boosting Machine (GBM) models are developed based on a maximum air temperature 'univariate modeling scheme' for monthly pan evaporation (Epan) process. Monthly used to build predictive models. These evaluating prediction Kiashahr meteorological station located in north of Iran Ranichauri positioned Uttarakhand State India. Findings indicated that deep learning model was found best at testing datasets MAE (0.5691, mm/month), RMSE (0.7111, NSE (0.7496), IOA (0.9413). It can be concluded semi-arid climate both methods had good capability Epan. However, DL predicted Epan better than GBM. Moreover, highest accuracy also observed terms = 0.3693 mm/month, 0.4357 0.8344, & 0.9507 stage. Overall, results expose superior performance DL-based study stations utilized various other environmental modeling.

Язык: Английский

Процитировано

79

Deep Learning and Machine Learning in Hydrological Processes Climate Change and Earth Systems a Systematic Review DOI
Sina Ardabili,

Amir Mosavi,

Majid Dehghani

и другие.

Lecture notes in networks and systems, Год журнала: 2020, Номер unknown, С. 52 - 62

Опубликована: Янв. 1, 2020

Язык: Английский

Процитировано

132

Systematic Review of Deep Learning and Machine Learning Models in Biofuels Research DOI
Sina Ardabili,

Amir Mosavi,

Annamária R. Várkonyi-Kóczy

и другие.

Lecture notes in networks and systems, Год журнала: 2020, Номер unknown, С. 19 - 32

Опубликована: Янв. 1, 2020

Язык: Английский

Процитировано

93

Prediction of Combine Harvester Performance Using Hybrid Machine Learning Modeling and Response Surface Methodology DOI
Tarahom Mesri Gundoshmian, Sina Ardabili,

Amir Mosavi

и другие.

Lecture notes in networks and systems, Год журнала: 2020, Номер unknown, С. 345 - 360

Опубликована: Янв. 1, 2020

Язык: Английский

Процитировано

54