Coronavirus (COVID-19) is a highly infectious disease that has captured the attention of the worldwide public. Modeling of such diseases can be extremely important in the prediction of their impact. While classic, statistical, modeling can provide satisfactory models, it can also fail to comprehend the intricacies contained within the data. In this paper, authors use a publicly available dataset, containing information on infected, recovered, and deceased patients in 406 locations over 51 days (22nd January 2020 to 12th March 2020). This dataset, intended to be a time-series dataset, is transformed into a regression dataset and used in training a multilayer perceptron (MLP) artificial neural network (ANN). The aim of training is to achieve a worldwide model of the maximal number of patients across all locations in each time unit. Hyperparameters of the MLP are varied using a grid search algorithm, with a total of 5376 hyperparameter combinations. Using those combinations, a total of 48384 ANNs are trained (16128 for each patient group—deceased, recovered, and infected), and each model is evaluated using the coefficient of determination (R2). Cross-validation is performed using K-fold algorithm with 5-folds. Best models achieved consists of 4 hidden layers with 4 neurons in each of those layers, and use a ReLU activation function, with R2 scores of 0.98599 for confirmed, 0.99429 for deceased, and 0.97941 for recovered patient models. When cross-validation is performed, these scores drop to 0.94 for confirmed, 0.781 for recovered, and 0.986 for deceased patient models, showing high robustness of the deceased patient model, good robustness for confirmed, and low robustness for recovered patient model.

No abstract

In this paper a genetic algorithm (GA) approach to design of multi-layer perceptron (MLP) for combined cycle power plant power output estimation is presented. Dataset used in this research is a part of publicly available UCI Machine Learning Repository and it consists of 9568 data points (power plant operating regimes) that is divided on training dataset that consists of 7500 data points and testing dataset containing 2068 data points. Presented research was performed with aim of increasing regression performances of MLP in comparison to ones available in the literature by utilizing heuristic algorithm. The GA described in this paper is performed by using mutation and crossover procedures. These procedures are utilized for design of 20 different chromosomes in 50 different generations. MLP configurations that are designed with GA implementation are validated by using Bland - Altman (B-A) analysis. By utilizing GA, MLP with five hidden layers of 80,25,65,75 and 80 nodes, respectively, is designed. For aforementioned MLP, k - fold cross-validation is performed in order to examine its generalization performances. The Root Mean Square Error ( R M S E ) value achieved with aforementioned MLP is 4.305 , that is significantly lower in comparison with MLP presented in available literature, but still higher than several complex algorithms such as KStar and tree based algorithms.

COVID-19 is one of the greatest challenges humanity has faced recently, forcing a change in the daily lives of billions of people worldwide. Therefore, many efforts have been made by researchers across the globe in the attempt of determining the models of COVID-19 spread. The objectives of this review are to analyze some of the open-access datasets mostly used in research in the field of COVID-19 regression modeling as well as present current literature based on Artificial Intelligence (AI) methods for regression tasks, like disease spread. Moreover, we discuss the applicability of Machine Learning (ML) and Evolutionary Computing (EC) methods that have focused on regressing epidemiology curves of COVID-19, and provide an overview of the usefulness of existing models in specific areas. An electronic literature search of the various databases was conducted to develop a comprehensive review of the latest AI-based approaches for modeling the spread of COVID-19. Finally, a conclusion is drawn from the observation of reviewed papers that AI-based algorithms have a clear application in COVID-19 epidemiological spread modeling and may be a crucial tool in the combat against coming pandemics.

Lowering joint torques of a robotic manipulator enables lowering the energy it uses as well as increase in the longevity of the robotic manipulator. This article proposes the use of evolutionary computation algorithms for optimizing the paths of the robotic manipulator with the goal of lowering the joint torques. The robotic manipulator used for optimization is modelled after a realistic six-degree-of-freedom robotic manipulator. Two cases are observed and these are a single robotic manipulator carrying a weight in a point-to-point trajectory and two robotic manipulators cooperating and moving the same weight along a calculated point-to-point trajectory. The article describes the process used for determining the kinematic properties using Denavit–Hartenberg method and the dynamic equations of the robotic manipulator using Lagrange–Euler and Newton–Euler algorithms. Then, the description of used artificial intelligence optimization algorithms is given – genetic algorithm using random and average recombination, simulated annealing using linear and geometric cooling strategy and differential evolution. The methods are compared and the results show that the genetic algorithm provides best results in regard to torque minimization, with differential evolution also providing comparatively good results and simulated annealing giving the comparatively weakest results while providing smoother torque curves.

One of the challenges of maritime aff airs is automatic object recognition from aerial imagery. This can be achieved by utilizing a Convolutional Neural Network (CNN) based algorithm. For purposes of these research a dataset of 5608 marine object images is collected by using Google satellite imagery and Google Image Search. The dataset is divided in two main classes ("Vessels" and "Other objects") and each class is divided into four sub-classes ("Vessels" sub-classes are "Cargo ships", "Cruise ships", "War ships" and "Boats", while "Other objects" sub-classes are "Waves", "Marine animals", "Garbage patches" and "Oil spills"). For recognition of marine objects, an algorithm constructed with three CNNs is proposed. The fi rst CNN for classifi cation on the main classes achieves accuracy of 92.37 %. The CNN used for vessels recognition achieves accuracies of 94.12 % for cargo ships recognition, 98.82 % for cruise ships recognition, 97.64 % for war ships recognition and 95.29 % for boats recognition. The CNN used for recognition of other objects achieves accuracies of 88.56 % for waves and marine animals recognition, 96.92 % for garbage patches recognition and 89.21 % for oil spills recognition. This research has shown that CNN is appropriate artifi cial intelligence (AI) method for marine object recognition from aerial imagery. Sažetak Jedan je od izazova u pomorstvu automatsko prepoznavanje objekata na zračnim snimkama. Ono se može postići uporabom algoritma na temelju konvolucijskih neuronskih mreža (CNN). U ovome istraživanju prikupljeni su podaci na temelju 5608 slika morskih objekata dobivenih s pomoću Googleovih satelitskih snimaka i pretraživanja slika. Prikupljeni podaci podijeljeni su na dvije kategorije ("Brodovi" i "Ostali objekti"), a svaka kategorija podijeljena je na četiri potkategorije (potkategorije "Brodova" jesu "Teretni brodovi", "Brodovi za kružna putovanja", "Ratni brodovi" i "Brodice", dok su potkategorije "Ostalih objekata" "Valovi", "Morska bića", "Otoci smeća" i "Izljevi nafte"). Da bi se prepoznali morski objekti, predložen je algoritam koji se sastoji od triju konvolucijskih neuronskih mreža (CNN). Preciznost prvog CNN-a kojim se klasifi ciraju osnovne kategorije iznosi otprilike 98,82%. Preciznost CNN-a kojim se prepoznaju brodovi iznosi 94,12% za teretne brodove, 98,22% za kruzere, 97,64% za ratne brodove i 95,29% za brodice. Preciznost CNN mreža koje se koriste za prepoznavanje drugih objekata iznosi otprilike 88,56% za valove i morska bića, 96,92% za prepoznavanje otoka smeća te 89,21% za prepoznavanje izljeva nafte. Rezultati istraživanja pokazali su da su CNN mreže odgovarajuća metoda umjetne inteligencije (AI) za prepoznavanje morskih objekata na zračnim snimkama. KEY WORDS artifi cial intelligence Convolutional Neural Network marine object recognition vessels pollution KLJUČNE RIJEČI umjetna inteligencija konvolucijske neuronske mreže prepoznavanje morskih objekata brodovi zagađenje

The paper presents an exergy analysis of marine steam turbine labyrinth (gland) seals - an inevitable component of any marine steam turbine cylinder, in three different operating regimes. Throughout labyrinth seals, steam specific enthalpy can be considered as a constant because the results obtained by this assumption do not deviate significantly from the results of complex numerical models. Changes in labyrinth seals exergy efficiency and specific exergy destruction are reverse proportional. The analyzed labyrinth seals have high exergy efficiencies in each observed operating regime at the ambient temperature of 298 K (above 92%), what indicates seals proper operation. An increase in the ambient temperature resulted with a decrease in labyrinth seals exergy efficiency, but even at the highest observed ambient temperature of 318 K, seals exergy efficiency did not fall below 90.5% in each observed operating regime.

In this paper, a comparison of two different methods for a steam turbine energy analysis is presented. A high-pressure steam turbine from a supercritical thermal power plant (HPT) was analysed at three different turbine loads using the energy flow stream (EFS) method and isentropic (IS) method. The EFS method is based on steam turbine input and output energy flow streams and on the real steam turbine produced power. The method is highly dependable on the steam mass flow rate lost through the turbine gland seals. The IS method is based on a comparison of turbine steam expansion processes. Observed energy analysis methods cannot be directly compared because they are based on different sources of steam turbine energy losses, so, an overall steam turbine energy analysis is presented. Unlike most steam turbines from the literature, the analysed HPT did not have the highest overall energy efficiency at a full load due to exceeding the water/steam critical pressure at the turbine inlet during such operation.