Wyniki wyszukiwania - BazTech

1

Machine learning-driven mineral prospectivity mapping: A predictive performance analysis in Janja, Iran

Ebdali Mohammad, Hezarkhani Ardeshir, Shirazy Adel, Beiranvnd-Pour Amin

Nafta-Gaz

|

2025

|

R. 81, nr 5

295--317

EN

Geochemical analysis is an effective technique for detecting mineral deposits by examining element concentrations. Various statistical techniques have been developed to differentiate abnormal values from background values. A more accurate analysis can be obtained by employing multivariate statistical methods. The use of these methods enables the simultaneous analysis of changes in multiple variables. This research utilized correlation coefficients, cluster analysis, and factor analysis to demonstrate the genetic connections among various elements. The factor analysis method was additionally applied to generate multivariable maps and comprehensive multivariable results. Moreover, the stepwise factor analysis (SFA) method, an enhanced version of traditional factor analysis, was utilized to produce geochemical distribution maps. This technique entails initially recognizing and removing non-representative elements, followed by identifying the most important and impactful representative factors. This study demonstrates the efficacy of the SFA method when applied to geochemical data. This approach removes superfluous elements and increases the variance attributed to the predictive mineralization factor, thereby improving the geochemical halos. Additionally, this research evaluated multivariate analysis approaches alongside machine learning techniques. To achieve this, a multilayer perceptron neural network (MLP) was used to evaluate the levels of gold, silver, copper, lead, and zinc in the study area. The output variable represented the grade of a particular element individually, whereas the input variables encompassed the grades of the remaining four elements. To optimize the model, different quantities of hidden layers and a range of activation functions were applied. Ultimately, an ideal model was developed for each element. The model achieved accuracies of 95%, 88%, 73%, 80%, and 72% for the gold, silver, copper, lead, and zinc, respectively. The results show the significant computational efficiency of this method in assessing element grades. Finally, the element distribution maps generated by both methods indicate that the MLP approach identified the anomalous areas with higher accuracy.

PL

Analiza geochemiczna jest skuteczną techniką wykrywania złóż mineralnych poprzez badanie stężeń pierwiastków. Opracowano różne techniki statystyczne w celu odróżnienia nieprawidłowych wartości od wartości tła. Dokładniejszą analizę można uzyskać stosując wielowymiarowe metody statystyczne. Zastosowanie tych metod umożliwia jednoczesną analizę zmian wielu zmiennych. W niniejszym badaniu wykorzystano współczynniki korelacji, analizę skupień i analizę czynnikową w celu wykazania powiązań genetycznych między różnymi pierwiastkami. Metoda analizy czynnikowej została dodatkowo zastosowana do wygenerowania map wielu zmiennych i kompleksowych wyników wielu zmiennych. Co więcej, zastosowano metodę stopniowej analizy czynnikowej (SFA), ulepszoną wersję tradycyjnej analizy czynnikowej, w celu stworzenia map rozkładu geochemicznego. Technika ta polega na wstępnym rozpoznaniu i usunięciu pierwiastków niereprezentatywnych, a następnie zidentyfikowaniu najważniejszych i najbardziej wpływowych czynników reprezentatywnych. Przeprowadzone badania wykazały skuteczność metody SFA w analizie danych geochemicznych. Podejście to pozwala na eliminację zbędnych elementów oraz zwiększenie wariancji przypisanej predykcyjnemu czynnikowi mineralizacji, co prowadzi do lepszego zdefiniowania aureoli geochemicznych. Dodatkowo, w badaniu tym oceniono wielowymiarowe podejścia analityczne wraz z technikami uczenia maszynowego. Ponadto, w badaniu oceniono metody analizy wielowymiarowej w połączeniu z technikami uczenia maszynowego. W tym celu wykorzystano sieć neuronową – perceptron wielowarstwowy (MLP) do oceny zawartości złota, srebra, miedzi, ołowiu i cynku w badanym obszarze. Zmienną wyjściową była zawartość konkretnego pierwiastka, natomiast zmiennymi wejściowymi – zawartości pozostałych czterech pierwiastków. W celu optymalizacji modelu zastosowano różne liczby warstw ukrytych oraz szereg funkcji aktywacji. Ostatecznie opracowano model optymalny dla każdego pierwiastka. Modele osiągnęły dokładności wynoszące odpowiednio 95%, 88%, 73%, 80% i 72% dla złota, srebra, miedzi, ołowiu i cynku.

2

Application of neural networks for drought forecasting based on the standardised precipitation index

Fathiyana Rana Z., Haryadi Deny, Ananda Naufal, Hidayat Dinda J., Wicaksana Haryas Subyantara, Azahra Rahma Wafii, Saputra Hakim Giraldi

Journal of Water and Land Development

|

2025

|

no. 65

113--121

EN

Based on data from the National Disaster Management Agency, South Sumatra is one of the provinces with a reasonably large drought-affected area, totalling 8,853,691.009 ha. Drought is a hydrometeorological disaster, characterised by anomalous rainfall below normal levels. Reduced rainfall can lead to decreased soil moisture, reduced river flows, and a general scarcity of water, which limits availability of water both on the surface and in the soil. To anticipate and mitigate the impacts of drought, an accurate forecasting system is essential for effective disaster management and mitigation. This research focuses on forecasting drought using the standardised precipitation index (SPI) based on Long Short-Term Memory (LSTM) and Multilayer Perceptron (MLP) algorithms. It compares LSTM and MLP algorithms by integrating rainfall data from the FY-4A satellite and observational rain gauges, which are processed to generate SPI values. These data are employed to train and test MLP and LSTM models in predicting future drought conditions. The results indicate that drought can be effectively predicted using both MLP and LSTM. However, the MLP outperforms the LSTM, as reflected by a higher Nash-Sutcliffe efficiency (NSE) value, a lower error rate, and a predicted date trend that more closely aligns with actual observations.

3

Deep Learning at Two Timescales: Dual Neural Networks for Predicting Fast Urban and Slow Karst Floods

Adounkpe Julien Yise Peniel, Wendling Valentin, Dezetter Alain, Arfib Bruno, Traoré Kalil, Artigue Guillaume, Dobricean Octavian, Pistre Séverin, Johannet Anne

Inżynieria Mineralna

|

2025

|

Vol. 3, no. 2

art. no. 27

EN

Flash floods in urban and karst environments present major modeling challenges due to their complex hydrodynamics, characterized by a rapid urban runoff response and a delayed slower karst groundwater response. This study explores the use of artificial neural networks ANN (multilayer perceptron in particular) to predict flash floods at the downstream of the Las River in Toulon (France). The Las River is fed in a larger proportion by the nearby karst springs and in a smaller proportion by the urban drainage network. In this study, we propose an ensemble modeling strategy to address the system’s double hydrological regime. The initial step was to identify rainfall events in the six-year hydrometeorological database and classify them according to their karst contributions. Two specialized models: urban runoff model (UM) and karst model (KM) were trained solely on each event type (urban runoff and karst events). These models were combined by two methods in an attempt model all events, disregarding of their event type: the first approach was to combine the outputs of the specialized models in an ANN called output combination model (OM), the second approach was to combine the structures of the specialized models and retraining the model parameters called structure combination model (SM). A third more “basic” approach, called bulk model (BM), was to optimize the ANN by selecting the inputs with the best performance improvements. As expected, the specialized models (UM and KM) performed the best on the cross-validation sets and on the test sets on their respective event types but failed to generalize across regimes. The OM was the most robust ensemble strategy across all event types with consistent accuracy on predicting both urban runoff and karst flood events. The BM was better on the karst events while having worst performance on karst events and the SM was the least accurate model. These findings confirm the added value of combining specialized ANNs to model complex hydrological systems. In addition, selecting the right inputs to the models has a bigger impact on the model’s performance than choosing its structure by changing its hyperparameters.

4

Comparison of particle swarm optimization algorithms in hyperparameter optimization problem of multi layered perceptron

Shiomi Kenta, Sato Tetsuya, Kita Eisuke

Computer Assisted Methods in Engineering and Science

|

2025

|

Vol. 32, no. 1

3--24

EN

This paper describes the application of particle swarm optimization (PSO) for the hy- perparameter optimization problem of multi-layered perceptron (MLP) model. Several PSO algorithms are presented by many researchers; basic PSO, PSO with inertia weight (PSO-w), PSO with constriction factor (PSO-cf), local PSO-w, local PSO-cf, union of local and global PSOs (UPSO), PSO with second global best particle (SG-PSO), and PSO with second local best particle (SP-PSO). The wine dataset is taken as a numerical example and hyperparameters of MLP the model are determined by the above-mentioned PSO algorithms. The sets of hyperparameters determined by these PSO algorithms are compared with the results of the traditional algorithms for hyperparameter optimization such as random search, tree-structured Parzen estimator (TPE), and covariance matrix adaptation evolution strategy (CMA-ES). Numerical results indicate that PSO-cf is the best-performing and local PSO-w is the second best among the PSO algorithms. The sets of hyperparameters determined by the PSO algorithms were relatively similar. An important finding from the numerical results is that PSO algorithms could find better hyperparameters than random search, TPE, and CMA-ES. This demonstrates that PSO is suitable for the hyperparameter optimization problem in MLP models.

5

Modeling and forecasting relative humidity using multilayer perceptron, radial basis function, and linear regression approaches

Kadiri Imad, Yahia Abdellah Ben, Abdallaoui Abdelaziz, El Hmaidi Abdellah

Advances in Science and Technology. Research Journal

|

2025

|

Vol. 19, no. 6

414--425

EN

Forecasting relative humidity is a critical for addressing the challenges of climate change. It facilitates comprehension of climatic mechanisms and the anticipation of extreme weather events, while also contributing to strengthening societal resilience and protection. Indeed, elevated levels of humidity have been demonstrated to exacerbate heat waves, leading to a marked increase in both the perceived temperature and the associated health risks. Conversely, low humidity promotes conditions conducive to droughts and wildfires. Moreover, relative humidity plays a key role in the water cycle, influencing precipitation, evaporation, and cloud formation. Understanding these mechanisms is essential for anticipating floods, droughts, and water shortages. In this study, mathematical models were developed to predict relative humidity in the Fez, Morocco, using multilayer perceptron (MLP) neural networks, radial basis function (RBF) neural networks, and multiple linear regression (MLR). The dataset used in this study includes daily values of eight meteorological parameters, including temperature at 2m, shortwave Radiation, diffuse shortwave radiation, precipitation total, evapotranspiration, vapor pressure deficit and wind speed and relative humidity as the output. The data spans 38 years, from January 1985 to December 2022, and includes 13879 observation days.. To evaluate the predictive performance of these models, we analyzed their architectures, learning algorithms, correlation coefficients, and mean squared errors. The results indicate that the MLP model attains the highest predictive accuracy, with a correlation coefficient of 0.9809 and a mean squared error MSE of 0.0099, outperforming the RBF model (correlation of 0.9603) and the MLR model (correlation of 0.9023), the best performing model used a Tansig activation function in the hidden layer, a Purelin function in the output layer and the Levenberg-Marquardt learning algorithm with a MLP configuration [7-15-1]. The findings of this study offer a valuable contribution to the field of water resource management in the region. They demonstrate the efficacy of artificial neural network models in enhancing moisture forecasting, thereby providing a solid foundation for future research in climate modelling.

6

The utilization of machine learning for network intrusion detection systems

Sanmorino Ahmad, Setiawan Herri, Coyanda John Roni

Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska

|

2024

|

T. 14, nr 4

86--89

EN

This study investigates the integration of MultilayerPerceptron (MLP) architecture in Network Intrusion Detection Systems (NIDS) to strengthen cyber defencesagainst evolving threats. The goal is to explore the potential of MLP in learning complex patterns and adapting to dynamic attack vectors, thereby improving detection accuracy. Key results from 5-fold cross-validation demonstrate model consistency, achieving an average accuracy of 0.97 with minimal standard deviation. Further evaluation across multiple nodes per layer and train-test splits demonstrate model robustness, displaying high metrics such as AUC-ROC and F1-Score. Challenges, such as the scarcity of large labelleddatasets and complex model interpretability,are acknowledged. This study provides a comprehensive foundation for future investigations, suggesting potential directions such as integrating advanced neural network architectures and assessing model transferability. In conclusion, this study contributes to the evolving intersection of machine learningand cyber security, offering insights into the strengths, limitations, and future directions of MLP-based NIDS. As cyber threats evolve, continued refinement of MLP methods is critical to effective network defencesagainst sophisticated adversaries.

PL

W niniejszym artykule zbadano integrację architektury wielowarstwowego perceptronu (MLP) w systemach wykrywania włamań do sieci (NIDS) w celu wzmocnienia cyberobrony przed ewoluującymi zagrożeniami. Celem jest zbadanie potencjału MLP w uczeniu się złożonych wzorcówi dostosowywaniu się do dynamicznych wektorów ataków, a tym samym poprawienie dokładności wykrywania. Kluczowe wyniki 5-krotnej walidacji krzyżowej wykazują spójność modelu, osiągając średnią dokładność 0,97 przy minimalnym odchyleniu standardowym. Dalsza ocena w wielu węzłachna warstwę i podziały trening-test wykazują solidność modelu, wykazując wysokie metryki, takie jak AUC-ROC i F1-Score. Wyzwania, takie jak niedobór dużych zestawów danych z etykietami i złożona interpretowalność modelu, są uznawane. Niniejsze badanie zapewnia kompleksową podstawę do przyszłych badań, sugerując potencjalne kierunki, takie jak integracja zaawansowanych architektur sieci neuronowych i ocena przenoszalności modelu. Podsumowując, niniejsze badanie przyczynia się do ewoluującego skrzyżowania uczenia maszynowego i cyberbezpieczeństwa, oferując wgląd w mocne strony, ograniczenia i przyszłe kierunki NIDS opartych na MLP. W miarę rozwoju cyberzagrożeń ciągłe udoskonalanie metodMLP staje się kluczowedla skutecznej obrony sieci przed wyrafinowanymi przeciwnikami.

7

Intelligent Design of an Ultra-Thin Near-Ideal Multilayer Solar Selective Absorber Using Grey Wolf Optimization Linked to Deep Learning

Gliti Oussama, El Idrissi Mohamed Chafik, Igouzal Mohammed

Ecological Engineering & Environmental Technology

|

2024

|

Vol. 25, iss. 2

70--87

EN

This study explored the development of an optimal effective solar absorber by leveraging recent advancements in artificial intelligence and nanotechnology. A predictive computational approach for designing a multilayer metal-dielectric thin film solar selective absorber, specifically the SiO2/Cr/SiO2/Cr/SiO2/Cu structure was proposed. The adopted approach integrates the transfer matrix method (TMM) as a predictive electromagnetic tool and combines it with the swarm-based heuristic algorithm grey wolf optimization (GWO) linked to machine learning algorithms, specifically the artificial neural network (ANN). Through dynamic modeling and rigorous testing against multiple static versions, the adopted approach demonstrates exceptional predictive performance with an value of 0.999. The results obtained using this novel GWO-ANN approach reveal near-perfect broadband absorption of 0.996534 and low emission of 0.194170594 for the designed thin film structure. These outcomes represent a significant advancement in photo-to-thermal conversion efficiency, particularly for a working temperature of 500 °C and a solar concentration of 100 suns, showcasing its potential for practical applications across various fields. Additionally, the designed structure meets the stringent thermal stability requirements necessary for current Concentrated solar power (CSP) projects. This emphasizes its suitability for integration into existing CSP systems and highlights its potential to contribute to advancements in solar energy technology.

8

Relative performance of Neural Networks and Binary Logistic Regression in a Variable Selection framework

Hounmenou Castro Gbêmêmali, Agbangba Émile C., Amagbégnon Génevieve, Marone Reine Marie Ndéla

Annals of Computer Science and Information Systems

|

2024

|

Vol. 40

25--32

EN

In this study, the predictive abilities of a binary response variable on a set of descriptors using Multilayer Perceptron neural networks and binary logistic regression in a variable selection context were evaluated. The data used was related to the identification of prenatal factors linked to premature birth in women already in labor. The stepwise selection method on binary logistic regression and the Olden selection method based on the neural network approach were used to select the most relevant variables to predict the probability of premature birth by women. Then, the two selection methods were combined with binary logistic regression and multilayer perceptron neural network models. Using the performance criteria such as sensitivity, precision, rate of good classification, F-score and Area Under the Curve (AUC), the selection methods were compared in order to choose the best model. It appears from the analysis that the best procedure for selecting variables in a binary variable prediction is the use of the Stepwise procedure followed by multilayer perceptron neural networks.

9

Predicting sea surface salinity in a tidal estuary with machine learning

Guillou Nicolas, Chapalain Georges, Petton Sébastien

Oceanologia

|

2023

|

No. 65 (2)

318--332

EN

As an indicator of exchanges between watersheds, rivers and coastal seas, salinity may provide valuable information about the exposure, ecological health and robustness of marine ecosystems, including especially estuaries. The temporal variations of salinity are traditionally approached with numerical models based on a physical description of hydrodynamic and hydrological processes. However, as these models require large computational resources, such an approach is, in practice, rarely considered for rapid turnaround predictions as requested by engineering and operational applications dealing with the ecological monitoring of estuaries. As an alternative efficient and rapid solution, we investigated here the potential of machine learning algorithms to mimic the non-linear complex relationships between salinity and a series of input parameters (such as tide-induced free-surface elevation, river discharges and wind velocity). Beyond regression methods, the attention was dedicated to popular machine learning approaches including MultiLayer Perceptron, Support Vector Regression and Random Forest. These algorithms were applied to six-year observations of sea surface salinity at the mouth of the Elorn estuary (bay of Brest, western Brittany, France) and compared to predictions from an advanced ecological numerical model. In spite of simple input data, machine learning algorithms reproduced the seasonal and semi-diurnal variations of sea surface salinity characterised by noticeable tide-induced modulations and low-salinity events during the winter period. Support Vector Regression provided the best estimations of surface salinity, improving especially predictions from the advanced numerical model during low-salinity events. This promotes the exploitation of machine learning algorithms as a complementary tool to process-based physical models.

10

Estimation of Suspended Sediment Load Using Artificial Neural Network in Khour Al Zubair Port, Iraq

Hassan Ayman A., Ibrahim Husham T., Al-Aboodi Ali H.

Journal of Ecological Engineering

|

2023

|

Vol. 24, nr 6

54--64

EN

The port of Khour Al-Zubair is located 60.0 km south of the city centre of Basrah; it is also located 105.0 kilometres from the northern tip of the Arabian Gulf. The main goal of this paper is to estimate the concentration of suspended deposit (SSC) in “Khour Al-Zubair” port using a Multilayer Perceptron Neural Network (MLP) based on hydraulic and local boundary parameters while also studying the effect of these parameters on estimating the SSC. Five input parameters (channel width, water depth, discharge, cross-section area, and flow velocity) are used for estimating SSC. Different input hydraulic and local boundary parameter combinations in the three sections (port center, port south, and port north) were used for creating nine models. The use of both hydraulic and local boundary parameters for SSC estimation is very important in the port area for estimating sediment loads without the need for field measurements, which require effort and time.

11

Urban traffic crash analysis using deep learning techniques

Sobhana Mummaneni, Vemulapalli Nihitha, Mendu Gnana Siva Sai Venkatesh, Ginjupalli Naga Deepika, Dodda Pragathi, Subramanyam Rayanoothala Bala Venkata

Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska

|

2023

|

T. 13, nr 3

56--63

EN

Road accidents are concerningly increasing in Andhra Pradesh. In 2021, Andhra Pradesh experienced a 20 percent upsurge in road accidents. The state's unfortunate position of being ranked eighth in terms of fatalities, with 8,946 lives lost in 22,311 traffic accidents, underscores the urgent nature of the problem. The significant financial impact on the victims and their families stresses the necessity for effective actions to reduce road accidents.This study proposes a framework that collects accident data from regions, namely Patamata, Penamaluru, Mylavaram, Krishnalanka, Ibrahimpatnam,and Gandhinagar in Vijayawada(India)from 2019 to 2021. The dataset comprises over 12,000 records of accident data. Deep learning techniquesare applied to classify the severity of road accidents into Fatal, Grievous, and Severe Injuries. The classification procedure leverages advanced neural network models, including the Multilayer Perceptron, Long-Short Term Memory, Recurrent Neural Network, and Gated Recurrent Unit. These modelsare trained on the collected data to accurately predict the severity of road accidents. The project study to make important contributions for suggesting proactive measures and policies to reduce the severity and frequency of road accidents in Andhra Pradesh.

PL

Liczba wypadków drogowych w Andhra Pradesh niepokojąco rośnie. W 2021 r. stan Andhra Pradesh odnotował 20% wzrost liczby wypadków drogowych. Niefortunna pozycja stanu, który zajmuje ósme miejsce pod względem liczby ofiar śmiertelnych, z 8946 ofiarami śmiertelnymiw 22311 wypadkach drogowych, podkreśla pilny charakter problemu. Znaczący wymiar finansowy dla ofiari ich rodziny podkreśla konieczność podjęcia skutecznych działań w celu ograniczenia liczby wypadków drogowych. W niniejszym badaniu zaproponowano system gromadzenia danych o wypadkachz regionów Patamata, Penamaluru, Mylavaram, Krishnalanka, Ibrahimpatnam i Gandhinagar w Vijayawada (India) w latach 2019–2021. Zbiór danych obejmuje ponad 12 000 rekordów danych o wypadkach. Techniki głębokiego uczenia są stosowane do klasyfikowania wagi wypadków drogowychna śmiertelne, poważne i ciężkie obrażenia. Procedura klasyfikacji wykorzystuje zaawansowane modele sieci neuronowych, w tymwielowarstwowy perceptron, pamięć długoterminową i krótkoterminową, rekurencyjną sieć neuronową i Gated Recurrent Unit. Modele te są trenowane na zebranych danych w celu dokładnego przewidywania wagi wypadków drogowych. Projekt ma wnieść istotny wkład w sugerowanie proaktywnych środków i polityk mających na celu zmniejszenie dotkliwości i częstotliwości wypadków drogowych w Andhra Pradesh.

12

Automated detection of cybersecurity attacks in healthcare systems with recursive feature elimination and multilayer perceptron optimization

Firat Kilincer Ilhan, Ertam Fatih, Sengur Abdulkadir, Tan Ru-San, Rajendra Acharya U.

Biocybernetics and Biomedical Engineering

|

2023

|

Vol. 43, no. 1

30--41

EN

Widespread proliferation of interconnected healthcare equipment, accompanying software, operating systems, and networks in the Internet of Medical Things (IoMT) raises the risk of security compromise as the bulk of IoMT devices are not built to withstand internet attacks. In this work, we have developed a cyber-attack and anomaly detection model based on recursive feature elimination (RFE) and multilayer perceptron (MLP). The RFE approach selected optimal features using logistic regression (LR) and extreme gradient boosting regression (XGBRegressor) kernel functions. MLP parameters were adjusted by using a hyperparameter optimization and 10-fold cross-validation approach was performed for performance evaluations. The developed model was performed on various IoMT cybersecurity datasets, and attained the best accuracy rates of 99.99%, 99.94%, 98.12%, and 96.2%, using Edith Cowan University- Internet of Health Things (ECU-IoHT), Intensive Care Unit (ICU Dataset), Telemetry data, Operating systems’ data, and Network data from the testbed IoT/IIoT network (TON-IoT), and Washington University in St. Louis enhanced healthcare monitoring system (WUSTL-EHMS) datasets, respectively. The proposed method has the ability to counter cyber attacks in healthcare applications.

13

A dual-stage transformer and MLP-based network for breast ultrasound image segmentation

Lin Guidi, Chen Mingzhi, Tan Minsheng, Chen Lingna, Chen Junxi

Biocybernetics and Biomedical Engineering

|

2023

|

Vol. 43, no. 4

656--671

EN

Automatic segmentation of breast lesions from ultrasound images plays an important role in computer-aided breast cancer diagnosis. Many deep learning methods based on convolutional neural networks (CNNs) have been proposed for breast ultrasound image segmentation. However, breast ultrasound image segmentation is still challenging due to ambiguous lesion boundaries. We propose a novel dual-stage framework based on Transformer and Multi-layer perceptron (MLP) for the segmentation of breast lesions. We combine the Swin Transformer block with an efficient pyramid squeezed attention block in a parallel design and introduce bi-directional interactions across branches, which can efficiently extract multi-scale long-range dependencies to improve the segmentation performance and robustness of the model. Furthermore, we introduce tokenized MLP block in the MLP stage to extract global contextual information while retaining fine-grained information to segment more complex breast lesions. We have conducted extensive experiments with state-of-the-art methods on three breast ultrasound datasets, including BUSI, BUL, and MT_BUS datasets. The dice coefficient reached 0.8127 ± 0.2178, and the intersection over union reached 0.7269 ± 0.2370 on benign lesions when the Hausdorff distance was maintained at 3.75 ± 1.83. The dice coefficient of malignant lesions is improved by 3.09% for BUSI dataset. The segmentation results on the BUL and MT_BUS datasets also show that our proposed model achieves better segmentation results than other methods. Moreover, the external experiments indicate that the proposed model provides better generalization capability for breast lesion segmentation. The dual-stage scheme and the proposed Transformer module achieve the fine-grained local information and long-range dependencies to relieve the burden of radiologists.

14

Neural Network Model for Control of Operating Modes of Crushing and Grinding Complex

Kalinchyk Vasyl, Meita Olexandr, Pobigaylo Vitalii, Borychenko Olena, Kalinchyk Vitalii

Rocznik Ochrona Środowiska

|

2022

|

Tom 24

26--40

EN

This article investigates the application of neural network models to create automated control systems for industrial processes. We reviewed and analysed works on dispatch control and evaluation of equipment operating modes and the use of artificial neural networks to solve problems of this type. It is shown that the main requirements for identification models are the accuracy of estimation and ease of algorithm implementation. It is shown that artificial neural networks meet the requirements for accuracy of classification problems, ease of execution and speed. We considered the structures of neural networks that can be used to recognise the modes of operation of technological equipment. Application of the model and structure of networks with radial basis functions and multilayer perceptrons for identifying the mode of operation of equipment under given conditions is substantiated. The input conditions for constructing neural network models of two types with a given three-layer structure are offered. The results of training neural models on the model of a multilayer perceptron and a network with radial basis functions are presented. The estimation and comparative analysis of models depending on model parameters are made. It is shown that networks with radial basis functions offer greater accuracy in solving identification problems. The structural scheme of the automated process control system with mode identification based on artificial neural networks is offered.

15

Comparison of MLP and RBF Neural Networks in the Task of Classifying the Diameters of Water Pipes

Gvishiani Zurab, Dawidowicz Jacek

Rocznik Ochrona Środowiska

|

2022

|

Tom 24

505--519

EN

Hydraulic calculations of water distribution systems are currently performed using computer programs. In addition to the basic calculation procedure, modules responsible for evaluating the obtained calculation results are introduced more and more often into the programs. This article presents the results of research on artificial neural networks with a radial base function (RBF) and a multilayer perceptron (MLP), aimed at determining whether they can be used to model the relationship between the variables describing the computational section of the water distribution system and the diameter of the water pipe. The classification capabilities of the RBF and MLP networks were analyzed according to the number of neurons in the hidden layer of the network. A comparative analysis of RBF networks with multilayer perceptron (MLP) networks was performed. The results showed that the MLP networks have much better classification properties and are better suited for the task of assessing the selected diameters of the water pipes.

16

Cat swarm optimization algorithm tuned multilayer perceptron for stock price prediction

Chandar S. Kumar, Punjabi Hitesh

Computer Assisted Methods in Engineering and Science

|

2022

|

Vol. 29, no. 1-2 spec.

145--160

EN

Due to the nonlinear and dynamic nature of stock data, prediction is one of the mostchallenging tasks in the financial market. Nowadays, soft and bio-inspired computing algorithms are used to forecast the stock price. This article assesses the efficiency of thehybrid stock prediction model using the multilayer perceptron (MLP) and cat swarm optimization (CSO) algorithm. The CSO algorithm is a bio-inspired algorithm inspired bythe behavior traits of cats. CSO is employed to find the appropriate value of MLP parameters. Technical indicators calculated from historical data are used as input variablesfor the proposed model. The model’s performance is validated using historical data notused for training. The model’s prediction efficiency is evaluated in terms of MSE, MAPE, RMSE and MAE. The model’s results are compared with other models optimized byvarious bio-inspired algorithms presented in the literature to prove its efficiency. The empirical findings confirm that the proposed CSO-MLP prediction model provides the bestperformance compared to other models taken for analysis.

17

Artificial Intelligence Based Flood Forecasting for River Hunza at Danyor Station in Pakistan

Yaseen Muhammad Waseem, Awais Muhammad, Riaz Khuram, Rasheed Muhammad Babar, Waqar Muhammad, Rasheed Sajid

Archives of Hydro-Engineering and Environmental Mechanics

|

2022

|

Vol. 69, nr 1

59--77

EN

Floods can cause significant problems for humans and can damage the economy. Implementing a reliable flood monitoring warning system in risk areas can help to reduce the negative impacts of these natural disasters. Artificial intelligence algorithms and statistical approaches are employed by researchers to enhance flood forecasting. In this study, a dataset was created using unique features measured by sensors along the Hunza River in Pakistan over the past 31 years. The dataset was used for classification and regression problems. Two types of machine learning algorithms were tested for classification: classical algorithms (Random Forest, RF and Support Vector Classifier, SVC) and deep learning algorithms (Multi-Layer Perceptron, MLP). For the regression problem, the result of MLP and Support Vector Regression (SVR) algorithms were compared based on their mean square, root mean square and mean absolute errors. The results obtained show that the accuracy of the RF classifier is 0.99, while the accuracies of the SVC and MLP methods are 0.98; moreover, in the case of flood prediction, the SVR algorithm outperforms the MLP approach.

18

Forecasting the Energy Consumption of an Industrial Enterprise Based on the Neural Network Model

Kalinchyk Vasyl, Meita Olexandr, Pobigaylo Vitalii, Kalinchyk Vitalii, Filyanin Danylo

Rocznik Ochrona Środowiska

|

2021

|

Tom 23

484--492

EN

This research paper investigates the application of neural network models for forecasting in energy. The results of forecasting the weekly energy consumption of the enterprise according to the model of a multilayer perceptron at different values of neurons and training algorithms are given. The estimation and comparative analysis of models depending on model parameters is made.

19

Machine learning methods applied to sea level predictions in the upper part of a tidal estuary

Guillou Nicolas, Chapalain Georges

Oceanologia

|

2021

|

No. 63 (4)

531--544

EN

Sea levels variations in the upper part of estuary are traditionally approached by relying on refined numerical simulations with high computational cost. As an alternative efficient and rapid solution, we assessed here the performances of two types of machine learning algorithms: (i) multiple regression methods based on linear and polynomial regression functions, and (ii) an artificial neural network, the multilayer perceptron. These algorithms were applied to three-year observations of sea levels maxima during high tides in the city of Landerneau, in the upper part of the Elorn estuary (western Brittany, France). Four input variables were considered in relation to tidal and coastal surge effects on sea level: the French tidal coefficient, the atmospheric pressure, the wind velocity and the river discharge. Whereas a part of these input variables derived from large-scale models with coarse spatial resolutions, the different algorithms showed good performances in this local environment, thus being able to capture sea level temporal variations at semi-diurnal and spring-neap time scales. Predictions improved furthermore the assessment of inundation events based so far on the exploitation of observations or numerical simulations in the downstream part of the estuary. Results obtained exhibited finally the weak influences of wind and river discharges on inundation events.

20

Neural network model for enterprise energy consumption forecasting

Kalinchyk Vasyl, Meita Olexandr, Pobigaylo Vitalii, Kalinchyk Vitalii, Filyanin Danylo

Journal of New Technologies in Environmental Science

|

2021

|

Vol. 5, nr 2

65--71

EN

This research paper investigates the application of neural network models for forecasting in energy. The results of forecasting the weekly energy consumption of the enterprise according to the model of a multilayer perceptron at different values of neurons and training algorithms are given. The estimation and comparative analysis of models depending on model parameters is made.