Informacja

Drogi użytkowniku, aplikacja do prawidłowego działania wymaga obsługi JavaScript. Proszę włącz obsługę JavaScript w Twojej przeglądarce.

English (EN)·Polski (PL)·Yкраїнський (UK)
Przejdź do strony domowej biblioteki Centralna Biblioteka Wojskowa Link otwiera się w nowym oknie Logo biblioteki Prolib Integro - strona głównaCentralna Biblioteka Wojskowa

Wyszukujesz frazę "machine learning algorithm" wg kryterium: Wszystkie pola

  Lista filtrów

Dostawca treści

Wyrównaj
    Wyświetlanie 1-41 z 41
    Tytuł:
    Prediction of PM2.5 hourly concentrations in Beijing based on machine learning algorithm and ground-based LiDAR
    Autorzy:
    Fang, Zhiyuan
    Yang, Hao
    Li, Cheng
    Cheng, Liangliang
    Zhao, Ming
    Xie, Chenbo
    Powiązania:
    https://bibliotekanauki.pl/articles/2073773.pdf
    Data publikacji:
    2021
    Wydawca:
    Polska Akademia Nauk. Czytelnia Czasopism PAN
    Tematy:
    PM2.5
    LiDAR
    machine learning
    air pollution monitoring
    Opis:
    The prediction of PM2.5 is important for environmental forecasting and air pollution control. In this study, four machine learning methods, ground-based LiDAR data and meteorological data were used to predict the ground-level PM2.5 concentrations in Beijing. Among the four methods, the random forest (RF) method was the most effective in predicting ground-level PM2.5 concentrations. Compared with BP neural network, support vector machine (SVM), and various linear fitting methods, the accuracy of the RF method was superior by 10%. The method can describe the spatial and temporal variation in PM2.5 concentrations under different meteorological conditions, with low root mean square error (RMSE) and mean square deviation (MD), and the consistency index (IA) reached 99.69%. Under different weather conditions, the hourly variation in PM2.5 concentrations has a good descriptive ability. In this paper, we analyzed the weights of input variables in the RF method, constructed a pollution case to correspond to the relationship between input variables and PM2.5, and analyzed the sources of pollutants via HYSPLIT backward trajectory. This method can study the interaction between PM2.5 and air pollution variables, and provide new ideas for preventing and forecasting air pollution.
    Źródło:
    Archives of Environmental Protection; 2021, 47, 3; 98--107
    2083-4772
    2083-4810
    Pojawia się w:
    Archives of Environmental Protection
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Use of machine learning algorithm for the better prediction of SR peculiarities of WEDM of Nimonic-90 superalloy
    Autorzy:
    Singh Nain, S.
    Sai, R.
    Sihag, P.
    Vambol, S.
    Vambol, V.
    Powiązania:
    https://bibliotekanauki.pl/articles/378951.pdf
    Data publikacji:
    2019
    Wydawca:
    Stowarzyszenie Komputerowej Nauki o Materiałach i Inżynierii Powierzchni w Gliwicach
    Tematy:
    support vector machine
    Gaussian process
    artificial neural network
    WEDM
    maszyna wektorów nośnych
    proces gaussowski
    sztuczna sieć neuronowa
    Opis:
    Purpose: With the end goal to fulfil stringent structural shape of the component in aeronautics industry, machining of Nimonic-90 super alloy turns out to be exceptionally troublesome and costly by customary procedures, for example, milling, grinding, turning, etc. For that reason, the manufacture and design engineer worked on contactless machining process like EDM and WEDM. Based on previous studies, it has been observed that rare research work has been published pertaining to the use of machine learning in manufacturing. Therefore the current research work proposed the use of SVM, GP and ANN methods to evaluate the WEDM of Nimonic-90. Design/methodology/approach: The experiments have been performed on the WEDM considering five process variables. The Taguchi L 18 mixed type array is used to formulate the experimental plan. The surface roughness is checked by using surface contact profilometre. The evolutionary algorithms like SVM, GP and ANN approaches have been used to evaluate the SR of WEDM of Nimonic-90 super alloy. Findings: The entire models present the significant results for the better prediction of SR peculiarities of WEDM of Nimonic-90 superalloy. The GP PUK kernel model is dominating the entire model. Research limitations/implications: The investigation was carried for the Nimonic-90 super alloy is selected as a work material. Practical implications: The results of this study provide an opportunity to conduct contactless processing superalloy Nimonic-90. At the same time, this contactless process is much cheaper, faster and more accurate. Originality/value: An experimental work has been reported on the WEDM of Udimet-L605 and use of advance machine learning algorithm and optimization approaches like SVM, and GRA is recommended. A study on WEDM of Inconel 625 has been explored and optimized the process using Taguchi coupled with grey relational approach. The applicability of some evolutionary algorithm like random forest, M5P, and SVM also tested to evaluate the WEDM of Udimet-L605.The fuzzy- inference and BP-ANN approached is used to evaluate the WEDM process. The multi-objective optimization using ratio analysis approach has been utilized to evaluate the WEDM of high carbon & chromium steel. But this current research work proposed the use of SVM, GP and ANN methods to evaluate the WEDM of Nimonic-90.
    Źródło:
    Archives of Materials Science and Engineering; 2019, 95, 1; 12-19
    1897-2764
    Pojawia się w:
    Archives of Materials Science and Engineering
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Improving Crop Yield Predictions in Morocco Using Machine Learning Algorithms
    Autorzy:
    Ed-Daoudi, Rachid
    Alaoui, Altaf
    Ettaki, Badia
    Zerouaoui, Jamal
    Powiązania:
    https://bibliotekanauki.pl/articles/24202898.pdf
    Data publikacji:
    2023
    Wydawca:
    Polskie Towarzystwo Inżynierii Ekologicznej
    Tematy:
    crop yield prediction
    machine learning algorithm
    statistical model
    model evaluation
    Opis:
    In Morocco, agriculture is an important sector that contributes to the country’s economy and food security. Accurately predicting crop yields is crucial for farmers, policy makers, and other stakeholders to make informed decisions regarding resource allocation and food security. This paper investigates the potential of Machine Learning algorithms for improving the accuracy of crop yield predictions in Morocco. The study examines various factors that affect crop yields, including weather patterns, soil moisture levels, and rainfall, and how these factors can be incorporated into Machine Learning models. The performance of different algorithms, including Decision Trees, Random Forests, and Neural Networks, is evaluated and compared to traditional statistical models used for crop prediction. The study demonstrated that the Machine Learning algorithms outperformed the Statistical models in predicting crop yields. Specifically, the Machine Learning algorithms achieved mean squared error values between 0.10 and 0.23 and coefficient of determination values ranging from 0.78 to 0.90, while the Statistical models had mean squared error values ranging from 0.16 to 0.24 and coefficient of determination values ranging from 0.76 to 0.84. The Feed Forward Artificial Neural Network algorithm had the lowest mean squared error value (0.10) and the highest R² value (0.90), indicating that it performed the best among the three Machine Learning algorithms. These results suggest that Machine Learning algorithms can significantly improve the accuracy of crop yield predictions in Morocco, potentially leading to improved food security and optimized resource allocation for farmers.
    Źródło:
    Journal of Ecological Engineering; 2023, 24, 6; 392--400
    2299-8993
    Pojawia się w:
    Journal of Ecological Engineering
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    The Effect of Dual Hyperparameter Optimization on Software Vulnerability Prediction Models
    Autorzy:
    Bassi, Deepali
    Singh, Hardeep
    Powiązania:
    https://bibliotekanauki.pl/articles/2203949.pdf
    Data publikacji:
    2023
    Wydawca:
    Politechnika Wrocławska. Oficyna Wydawnicza Politechniki Wrocławskiej
    Tematy:
    software vulnerability
    hyperparameter optimization
    machine learning algorithm
    data balancing techniques
    data complexity measures
    Opis:
    Background: Prediction of software vulnerabilities is a major concern in the field of software security. Many researchers have worked to construct various software vulnerability prediction (SVP) models. The emerging machine learning domain aids in building effective SVP models. The employment of data balancing/resampling techniques and optimal hyperparameters can upgrade their performance. Previous research studies have shown the impact of hyperparameter optimization (HPO) on machine learning algorithms and data balancing techniques. Aim: The current study aims to analyze the impact of dual hyperparameter optimization on metrics-based SVP models. Method: This paper has proposed the methodology using the python framework Optuna that optimizes the hyperparameters for both machine learners and data balancing techniques. For the experimentation purpose, we have compared six combinations of five machine learners and five resampling techniques considering default parameters and optimized hyperparameters. Results: Additionally, the Wilcoxon signed-rank test with the Bonferroni correction method was implied, and observed that dual HPO performs better than HPO on learners and HPO on data balancers. Furthermore, the paper has assessed the impact of data complexity measures and concludes that HPO does not improve the performance of those datasets that exhibit high overlap. Conclusion: The experimental analysis unveils that dual HPO is 64% effective in enhancing the productivity of SVP models.
    Źródło:
    e-Informatica Software Engineering Journal; 2023, 17, 1; art. no. 230102
    1897-7979
    Pojawia się w:
    e-Informatica Software Engineering Journal
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Weighted accuracy algorithmic approach in counteracting fake news and disinformation
    Algorytmiczne podejście do dokładności ważonej w przeciwdziałaniu fałszywym informacjom i dezinformacji
    Autorzy:
    Bonsu, K.O.
    Powiązania:
    https://bibliotekanauki.pl/articles/2048986.pdf
    Data publikacji:
    2021
    Wydawca:
    Akademia Bialska Nauk Stosowanych im. Jana Pawła II w Białej Podlaskiej
    Tematy:
    artificial intelligence
    natural language processing
    machine learning algorithm
    disinformation
    digital revolution
    fake news
    Opis:
    Subject and purpose of work: Fake news and disinformation are polluting information environment. Hence, this paper proposes a methodology for fake news detection through the combined weighted accuracies of seven machine learning algorithms. Materials and methods: This paper uses natural language processing to analyze the text content of a list of news samples and then predicts whether they are FAKE or REAL. Results: Weighted accuracy algorithmic approach has been shown to reduce overfitting. It was revealed that the individual performance of the different algorithms improved after the data was extracted from the news outlet websites and 'quality' data was filtered by the constraint mechanism developed in the experiment. Conclusions: This model is different from the existing mechanisms in the sense that it automates the algorithm selection process and at the same time takes into account the performance of all the algorithms used, including the less performing ones, thereby increasing the mean accuracy of all the algorithm accuracies.
    Źródło:
    Economic and Regional Studies; 2021, 14, 1; 99-107
    2083-3725
    2451-182X
    Pojawia się w:
    Economic and Regional Studies
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Machine learning methods applied to sea level predictions in the upper part of a tidal estuary
    Autorzy:
    Guillou, N.
    Chapalain, G.
    Powiązania:
    https://bibliotekanauki.pl/articles/2078822.pdf
    Data publikacji:
    2021
    Wydawca:
    Polska Akademia Nauk. Instytut Oceanologii PAN
    Tematy:
    multiple regression model
    artificial neural network
    multilayer perceptron
    regression function
    machine learning algorithm
    sea level
    Opis:
    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.
    Źródło:
    Oceanologia; 2021, 63, 4; 531-544
    0078-3234
    Pojawia się w:
    Oceanologia
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    CellProfiler and WEKA Tools: Image Analysis for Fish Erythrocytes Shape and Machine Learning Model Algorithm Accuracy Prediction of Dataset
    Autorzy:
    Talapatra, Soumendra Nath
    Chaudhuri, Rupa
    Ghosh, Subhasis
    Powiązania:
    https://bibliotekanauki.pl/articles/1193348.pdf
    Data publikacji:
    2021
    Wydawca:
    Przedsiębiorstwo Wydawnictw Naukowych Darwin / Scientific Publishing House DARWIN
    Tematy:
    Automatic image analysis
    CellProfiler tool
    Fish erythrocytes quantification
    Machine learning algorithm
    Model classifier accuracy
    Shapes measurement
    WEKA tool
    Opis:
    The first part of the study was detected the number of cells and measurement of shape of cells, cytoplasm, and nuclei in an image of Giemsa-stained of fish peripheral erythrocytes by using CellProfiler (CP, version 2.1.0) tool, an image analysis tool. In the second part, it was evaluated machine learning (ML) algorithm models viz. BayesNet (BN), NaiveBayes (NB), logistic regression (LR), Lazy.KStar (K*), decision tree (DT) J48, Random forest (RF) and Random tree (RT) in the WEKA tool (version 3.8.5) for the prediction of the accuracy of the dataset generated from an image. The CP predicts the numbers and individual cellular area shape (arbitrary unit) of cells, cytoplasm, and nuclei as primary, secondary, and tertiary object data in an image. The performance of model accuracy of studied ML algorithm classifications as per correctly and incorrectly classified instances, the highest values were observed in RF and RT followed by K*, LR, BN and DTJ48 and lowest in NB as per training and testing set of correctly classified instances. In case of performance accuracy of class for K value, the highest values were observed in RF and RT followed by K*, LR, BN and DTJ48 and lowest in NB while lowest values were obtained for mean absolute error (MAE) and root mean squared error (RMSE) in case of RT followed by RF, K*, LR, BN and DTJ48 and comparatively highest value in case of NB as per training and testing set. In conclusion, both tools performed well as an image to the dataset and obtained dataset to rich information through ML modelling and future study in WEKA tool can easily be analysed many biological big data to predict classifier accuracy.
    Źródło:
    World Scientific News; 2021, 154; 101-116
    2392-2192
    Pojawia się w:
    World Scientific News
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Building computer vision systems using machine learning algorithms
    Autorzy:
    Boyko, N.
    Sokil, N.
    Powiązania:
    https://bibliotekanauki.pl/articles/410768.pdf
    Data publikacji:
    2017
    Wydawca:
    Polska Akademia Nauk. Oddział w Lublinie PAN
    Tematy:
    algorithm
    information system
    neural network
    machine learning
    client-server architecture
    script
    artificial system
    machine learning algorithms
    algorytm
    systemy informacyjne
    sieci neuronowe
    systemy uczące
    architektura klient-serwer
    skrypt
    Opis:
    In this paper theoretic aspects of machine learning system in the field of computer vision is considered. There are presented methods of behavior analysis. There are offered tasks and problems associated with building systems using machine learning algorithm. The paper provides signs of problems that can be solved by using machine learning algorithms There is demonstrated step by step construction of computer vision system. The paper provides the algorithm of solving the problem of binary (two classes) classification for demonstration the machine learning algorithm possibilities in image recognition field, which can recognize the gender of the person on the photo. Aspects related to the search of data processing are also considered. There is analyzed the search of optimal parameters for algorithms. An interpretation of results in machine learning algorithm is provided. Binarization methods in machine learning algorithm are offered. There is analyzed the technology for improving the accuracy of machine learning algorithm. There are proposed ways to improve computer vision system in neural systems. Also there are analyzed large software modules that work using machine learning systems. The article provides prospects of powerful information technologies, which are necessary for the proper data selection in learning and configuration of feature extraction algorithm to create a computer vision system.
    Źródło:
    ECONTECHMOD : An International Quarterly Journal on Economics of Technology and Modelling Processes; 2017, 6, 2; 15-20
    2084-5715
    Pojawia się w:
    ECONTECHMOD : An International Quarterly Journal on Economics of Technology and Modelling Processes
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    A survey on prediction of diabetes using classification algorithms
    Autorzy:
    Khanwalkar, A.
    Soni, R.
    Powiązania:
    https://bibliotekanauki.pl/articles/1818807.pdf
    Data publikacji:
    2021
    Wydawca:
    Stowarzyszenie Komputerowej Nauki o Materiałach i Inżynierii Powierzchni w Gliwicach
    Tematy:
    diabetes
    diabetes prediction
    algorithm
    data mining
    machine learning
    cukrzyca
    algorytm
    eksploracja danych
    uczenie maszynowe
    Opis:
    Purpose: Diabetes is a chronic disease that pays for a large proportion of the nation's healthcare expenses when people with diabetes want medical care continuously. Several complications will occur if the polymer disorder is not treated and unrecognizable. The prescribed condition leads to a diagnostic center and a doctor's intention. One of the real-world subjects essential is to find the first phase of the polytechnic. In this work, basically a survey that has been analyzed in several parameters within the poly-infected disorder diagnosis. It resembles the classification algorithms of data collection that plays an important role in the data collection method. Automation of polygenic disorder analysis, as well as another machine learning algorithm. Design/methodology/approach: This paper provides extensive surveys of different analogies which have been used for the analysis of medical data, For the purpose of early detection of polygenic disorder. This paper takes into consideration methods such as J48, CART, SVMs and KNN square, this paper also conducts a formal surveying of all the studies, and provides a conclusion at the end. Findings: This surveying has been analyzed on several parameters within the poly-infected disorder diagnosis. It resembles that the classification algorithms of data collection plays an important role in the data collection method in Automation of polygenic disorder analysis, as well as another machine learning algorithm. Practical implications: This paper will help future researchers in the field of Healthcare, specifically in the domain of diabetes, to understand differences between classification algorithms. Originality/value: This paper will help in comparing machine learning algorithms by going through results and selecting the appropriate approach based on requirements.
    Źródło:
    Journal of Achievements in Materials and Manufacturing Engineering; 2021, 104, 2; 77--84
    1734-8412
    Pojawia się w:
    Journal of Achievements in Materials and Manufacturing Engineering
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Innovative stress analysis and machine learning forecasting for semi-trailer truck body durability
    Autorzy:
    Lyashuk, Oleh
    Levkovych, Mykhailo
    Stashkiv, Mykola
    Pastukh, Oleh
    Martyniuk, Volodymyr
    Mironov, Dmytro
    Rabe, Marcin
    Vovk, Yuriy
    Powiązania:
    https://bibliotekanauki.pl/articles/27324297.pdf
    Data publikacji:
    2023
    Wydawca:
    Fundacja Centrum Badań Socjologicznych
    Tematy:
    transport
    energy resources
    semi-trailer truck body
    static stress
    static displacement
    CAD model
    algorithm
    machine learning
    Opis:
    This article presents an in-depth analysis of the stress-deformation state (SDS) in the bottom structure of a semi-trailer truck body. Engineering analysis was conducted utilizing the SolidWorks software, focusing on a comprehensive CAD model of the semi-trailer truck body. The study explored variations in SDS parameters resulting from alterations in the geometric parameters of the body bottom elements. The research investigated alterations in static stress and displacement relative to changes in the proportions of the cross-section of the channel while maintaining fixed geometric dimensions of the workpiece, thickness of the workpiece, and the material of the body bottom. Graphical representations were generated to illustrate the variations in static stress, displacement, and safety margin concerning the thickness of the shelf and channel. Additionally, dependencies were derived that correlate static stresses in the channel with the thickness of the channel wall and the thickness of the body bottom sheet. The study results were compiled and summarized, offering valuable insights into the stress-deformation state of the semi-trailer truck body's bottom. Furthermore, machine learning techniques, specifically the RandomForest algorithm, were implemented in a Python environment to predict changes in static stress based on various factors. The model's predictions were validated by comparing predicted static stress values with actual values on a test sample. These findings facilitate efficient selection of appropriately sized elements by predicting static stress values, employing the RandomForest machine learning algorithm.
    Źródło:
    Journal of Sustainable Development of Transport and Logistics; 2023, 8, 2; 43--57
    2520-2979
    Pojawia się w:
    Journal of Sustainable Development of Transport and Logistics
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Reasoning algorithm for a creative decision support system integrating inference and machine learning
    Autorzy:
    Wilk-Kolodziejczyk, D.
    Powiązania:
    https://bibliotekanauki.pl/articles/305355.pdf
    Data publikacji:
    2017
    Wydawca:
    Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
    Tematy:
    reasoning algorithm
    inferential theory of learning
    decision support
    rule induction
    logic of plausible reasoning
    Opis:
    In this paper a reasoning algorithm for a creative decision support system is proposed. It allows to integrate inference and machine learning algorithms. Execution of learning algorithm is automatic because it is formalized as aplying a complex inference rule, which generates intrinsically new knowledge using the facts stored already in the knowledge base as training data. This new knowledge may be used in the same inference chain to derive a decision. Such a solution makes the reasoning process more creative and allows to continue resoning in cases when the knowledge base does not have appropriate knowledge explicit encoded. In the paper appropriate knowledge representation and infeence model are proposed. Experimental verification is performed on a decision support system in a casting domain.
    Źródło:
    Computer Science; 2017, 18 (3); 317-338
    1508-2806
    2300-7036
    Pojawia się w:
    Computer Science
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Designing Smart Antennas Using Machine Learning Algorithms
    Autorzy:
    Samantaray, Barsa
    Das, Kunal Kumar
    Roy, Jibendu Sekhar
    Powiązania:
    https://bibliotekanauki.pl/articles/27312957.pdf
    Data publikacji:
    2023
    Wydawca:
    Instytut Łączności - Państwowy Instytut Badawczy
    Tematy:
    artificial neural network
    decision tree
    ensemble algorithm
    machine learning
    smart antenna
    support vector machine
    Opis:
    Smart antenna technologies improve spectral efficiency, security, energy efficiency, and overall service quality in cellular networks by utilizing signal processing algorithms that provide radiation beams to users while producing nulls for interferers. In this paper, the performance of such ML solutions as the support vector machine (SVM) algorithm, the artificial neural network (ANN), the ensemble algorithm (EA), and the decision tree (DT) algorithm used for forming the beam of smart antennas are compared. A smart antenna array made up of 10 half-wave dipoles is considered. The ANN method is better than the remaining approaches when it comes to achieving beam and null directions, whereas EA offers better performance in terms of reducing the side lobe level (SLL). The maximum SLL is achieved using EA for all the user directions. The performance of the ANN algorithm in terms of forming the beam of a smart antenna is also compared with that of the variable-step size adaptive algorithm.
    Źródło:
    Journal of Telecommunications and Information Technology; 2023, 4; 46--52
    1509-4553
    1899-8852
    Pojawia się w:
    Journal of Telecommunications and Information Technology
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Stationary supercapacitor energy storage operation algorithm based on neural network learning system
    Autorzy:
    Jefimowski, W.
    Nikitenko, A.
    Drążek, Z.
    Wieczorek, M.
    Powiązania:
    https://bibliotekanauki.pl/articles/200935.pdf
    Data publikacji:
    2020
    Wydawca:
    Polska Akademia Nauk. Czytelnia Czasopism PAN
    Tematy:
    stationary energy storage
    operation algorithms
    machine learning
    supervised learning
    prediction
    Opis:
    The paper proposes to apply an algorithm for predicting the minimum level of the state of charge (SoC) of stationary supercapacitor energy storage system operating in a DC traction substation, and for changing it over time. This is done to insure maximum energy recovery for trains while braking. The model of a supercapacitor energy storage system, its algorithms of operation and prediction of the minimum state of charge are described in detail; the main formulae, graphs and results of simulation are also provided. It is proposed to divide the SoC curve into equal periods of time during which the minimum states of charge remain constant. To predict the SoC level for the subsequent period, the learning algorithm based on the neural network could be used. Then, the minimum SoC could be based on two basic types of data: the first one is the time profile of the energy storage load during the previous period with the constant minimum SoC retained, while the second one relies on the trains’ locations and speed values in the previous period. It is proved that the use of variable minimum SoC ensures an increase of the energy volume recovered by approximately 10%. Optimum architecture and activation function of the neural network are also found.
    Źródło:
    Bulletin of the Polish Academy of Sciences. Technical Sciences; 2020, 68, 4; 733-738
    0239-7528
    Pojawia się w:
    Bulletin of the Polish Academy of Sciences. Technical Sciences
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Automatic identification of malfunctions of large turbomachinery during transient states with genetic algorithm optimization
    Autorzy:
    Barszcz, Tomasz
    Zabaryłło, Mateusz
    Powiązania:
    https://bibliotekanauki.pl/articles/2052104.pdf
    Data publikacji:
    2022
    Wydawca:
    Polska Akademia Nauk. Czytelnia Czasopism PAN
    Tematy:
    machine learning
    fault detection
    transient
    turbine generator
    genetic algorithm
    Opis:
    Turbines and generators operating in the power generation industry are a major source of electrical energy worldwide. These are critical machines and their malfunctions should be detected in advance in order to avoid catastrophic failures and unplanned shutdowns. A maintenance strategy which enables to detect malfunctions at early stages of their existence plays a crucial role in facilities using such types of machinery. The best source of data applied for assessment of the technical condition are the transient data measured during start-ups and coast-downs. Most of the proposed methods using signal decomposition are applied to small machines with a rolling element bearing in steady-state operation with a shaft considered as a rigid body. The machines examined in the authors’ research operate above their first critical rotational speed interval and thus their shafts are considered to be flexible and are equipped with a hydrodynamic sliding bearing. Such an arrangement introduces significant complexity to the analysis of the machine behavior, and consequently, analyzing such data requires a highly skilled human expert. The main novelty proposed in the paper is the decomposition of transient vibration data into components responsible for particular failure modes. The method is automated and can be used for identification of turbogenerator malfunctions. Each parameter of a particular decomposed function has its physical representation and can help the maintenance staff to operate the machine properly. The parameters can also be used by the managing personnel to plan overhauls more precisely. The method has been validated on real-life data originating from a 200 MW class turbine. The real-life field data, along with the data generated by means of the commercial software utilized in GE’s engineering department for this particular class of machines, was used as the reference data set for an unbalanced response during the transients in question.
    Źródło:
    Metrology and Measurement Systems; 2022, 29, 1; 175-190
    0860-8229
    Pojawia się w:
    Metrology and Measurement Systems
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Man-algorithm Cooperation Intelligent Design of Clothing Products in Multi Links
    Autorzy:
    Han, Chen
    Lei, Shen
    Shaogeng, Zhang
    Mingming, Wang
    Ying, Tang
    Powiązania:
    https://bibliotekanauki.pl/articles/2056307.pdf
    Data publikacji:
    2022
    Wydawca:
    Sieć Badawcza Łukasiewicz - Instytut Biopolimerów i Włókien Chemicznych
    Tematy:
    intelligent algorithm
    cooperation
    clothing design
    machine learning
    efficiency
    Opis:
    The changes in technology have led to a synchronous change in the clothing design method, as well as media and artistic aesthetics in the same period. The intelligence algorithm is constantly increasing its participation in development and production in the clothing industry. In this study, a variety of intelligent algorithms, including the parameterised numer state algorithm, Generative Adversarial Networks, and style transfer were introduced into the multi-links of clothing product design and development, such as clothing shape, print pattern, texture craft, product vision, and so on. Then, an innovative clothing design method based on the cooperation of the intelligent algorithm and various human functional roles was constructed. The method improves the efficiency of the multiple links of clothing design, such as generating 10000 printing patterns every 72.12 seconds, and completing the migration of 92.7 frames of the garment process style every second. To a certain extent, this study realizes the scale economy of clothing design and reduces its marginal cost through the unlimited computing power brought about by Moore’s law of digital technology, which provides a reference for the exploration of clothing design in the era of industry 4.0.
    Źródło:
    Fibres & Textiles in Eastern Europe; 2022, 1 (151); 59--66
    1230-3666
    2300-7354
    Pojawia się w:
    Fibres & Textiles in Eastern Europe
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Forecasting short-term electric load using extreme learning machine with improved tree seed algorithm based on Lévy flight
    Autorzy:
    Chen, Xuan
    Przystupa, Krzysztof
    Ye, Zhiwei
    Chen, Feng
    Wang, Chunzhi
    Liu, Jinhang
    Gao, Rong
    Wei, Ming
    Kochan, Orest
    Powiązania:
    https://bibliotekanauki.pl/articles/2087016.pdf
    Data publikacji:
    2022
    Wydawca:
    Polska Akademia Nauk. Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne PAN
    Tematy:
    short-term electric load forecast
    extreme learning machine
    Lévy flight
    tree-seed algorithm
    Kernel principal component analysis
    Opis:
    In recent years, forecasting has received increasing attention since it provides an important basis for the effective operation of power systems. In this paper, a hybrid method, composed of kernel principal component analysis (KPCA), tree seed algorithm based on Lévy flight (LTSA) and extreme learning machine (ELM), is proposed for short-term load forecasting. Specifically, the randomly generated weights and biases of ELM have a significant impact on the stability of prediction results. Therefore, in order to solve this problem, LTSA is utilized to obtain the optimal parameters before the prediction process is executed by ELM, which is called LTSA-ELM. Meanwhile, the input data is extracted by KPCA considering the sparseness of the electric load data and used as the input of LTSA-ELM model. The proposed method is tested on the data from European network on intelligent technologies (EUNITE) and experimental results demonstrate the superiority of the proposed approaches compared to the other methods involved in the paper.
    Źródło:
    Eksploatacja i Niezawodność; 2022, 24, 2; 153--162
    1507-2711
    Pojawia się w:
    Eksploatacja i Niezawodność
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    A fast neural network learning algorithm with approximate singular value decomposition
    Autorzy:
    Jankowski, Norbert
    Linowiecki, Rafał
    Powiązania:
    https://bibliotekanauki.pl/articles/330870.pdf
    Data publikacji:
    2019
    Wydawca:
    Uniwersytet Zielonogórski. Oficyna Wydawnicza
    Tematy:
    Moore–Penrose pseudoinverse
    radial basis function network
    extreme learning machine
    kernel method
    machine learning
    singular value decomposition
    deep extreme learning
    principal component analysis
    pseudoodwrotność Moore–Penrose
    radialna funkcja bazowa
    maszyna uczenia ekstremalnego
    uczenie maszynowe
    analiza składników głównych
    Opis:
    The learning of neural networks is becoming more and more important. Researchers have constructed dozens of learning algorithms, but it is still necessary to develop faster, more flexible, or more accurate learning algorithms. With fast learning we can examine more learning scenarios for a given problem, especially in the case of meta-learning. In this article we focus on the construction of a much faster learning algorithm and its modifications, especially for nonlinear versions of neural networks. The main idea of this algorithm lies in the usage of fast approximation of the Moore–Penrose pseudo-inverse matrix. The complexity of the original singular value decomposition algorithm is O(mn2). We consider algorithms with a complexity of O(mnl), where l < n and l is often significantly smaller than n. Such learning algorithms can be applied to the learning of radial basis function networks, extreme learning machines or deep ELMs, principal component analysis or even missing data imputation.
    Źródło:
    International Journal of Applied Mathematics and Computer Science; 2019, 29, 3; 581-594
    1641-876X
    2083-8492
    Pojawia się w:
    International Journal of Applied Mathematics and Computer Science
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Data censoring with set-membership affine projection algorithm
    Autorzy:
    Karamali, Gholamreza
    Zardadi, Akram
    Moradi, Hamid Reza
    Powiązania:
    https://bibliotekanauki.pl/articles/305734.pdf
    Data publikacji:
    2020
    Wydawca:
    Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
    Tematy:
    adaptive filtering
    machine learning
    data censoring
    big data
    Opis:
    In this work, we use the single-threshold and double-threshold set-membership affine projection algorithm to censor non-informative and irrelevant data in big data problems. For this purpose, we employ the probability distribution function of the additive noise in the desired signal and the excess of the meansquared error (EMSE) in steady-state to evaluate the threshold parameter of the single -threshold set-membership affine projection (ST-SM-AP) algorithm intending to obtain the desired update percentage. In addition, we propose the double-threshold set-membership affine projection (DT-SM-AP) algorithm to detect very large errors caused by unrelated data (such as outliers). The DT-SM-AP algorithm is capable of censoring non-informative and unrelated data in big data problems, and it will promote the misalignment and convergence speed of the learning procedure with low computational complexity. The synthetic examples and real-life experiments substantiate the superior performance of the proposed algorithms as compared to traditional algorithms.
    Źródło:
    Computer Science; 2020, 21 (1); 43-57
    1508-2806
    2300-7036
    Pojawia się w:
    Computer Science
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Clothing Image Classification with a Dragonfly Algorithm Optimised Online Sequential Extreme Learning Machine
    Klasyfikacja obrazu odzieży za pomocą zoptymalizowanego algorytmu Dragonfly sekwencyjnej maszyny uczącej się
    Autorzy:
    Li, Jianqiang
    Shi, Weimin
    Yang, Donghe
    Powiązania:
    https://bibliotekanauki.pl/articles/1419412.pdf
    Data publikacji:
    2021
    Wydawca:
    Sieć Badawcza Łukasiewicz - Instytut Biopolimerów i Włókien Chemicznych
    Tematy:
    Dragonfly algorithm
    Online Sequential Extreme Learning Machine
    clothing image classification
    optimised parameter
    algorytm Dragonfly
    OSELM
    maszyna ucząca się
    klasyfikacja obrazu odzieży
    parametr zoptymalizowany
    Opis:
    This study proposes a solution for the issue of the low classification accuracy of clothing images. Using Fashion-MNIST as the clothing image dataset, we propose a clothing image classification technology based on an online sequential extreme learning machine (OSELM) optimised by the dragonfly algorithm (DA). First, we transform the Fashion-MNIST dataset into a data set that we extract from the corresponding grey image. Then, considering that the input weight and hidden layer bias of an OSELM are generated randomly, a DA is proposed to optimise the input weight and hidden layer bias of the OSELM to reduce the influence of random generation on the classification results. Finally, the optimised OSELM is applied to the clothing image classification. Compared to the other seven types of classification algorithms, the proposed clothing image classification model with the DA-optimised OSELM reached 93.98% accuracy when it contained 350 hidden nodes. Its performance was superior to other algorithms that were configured with the same number of hidden nodes. From a stability analysis of the box-plot, it was found that there were no outliers exhibited by the DA-OSELM model, whereas some other models had outliers or had lower stability compared to the model proposed, thereby validating the efficacy of the solution proposed.
    W pracy zaproponowano rozwiązanie problemu niskiej dokładności klasyfikacyjnej obrazów odzieży. Wykorzystując Fashion-MNIST jako zbiór danych obrazu odzieży, zaproponowano technologię klasyfikacji obrazów odzieży w oparciu o sekwencyjną maszynę uczącą się (OSELM) zoptymalizowaną przez algorytm Dragonfly (DA). Najpierw przekształcono zbiór danych Fashion-MNIST w zestaw danych, który wyodrębniono z obrazu. Następnie, biorąc pod uwagę, że waga wejściowa i odchylenie warstwy ukrytej OSELM były generowane losowo, w celu zmniejszenia wpływu generowania losowego na wyniki klasyfikacji zaproponowano DA w celu optymalizacji wagi wejściowej i obciążenia warstwy ukrytej OSELM. Następnie, zoptymalizowany OSELM zastosowano do klasyfikacji obrazu odzieży. W porównaniu z pozostałymi siedmioma typami algorytmów klasyfikacji, proponowany model klasyfikacji obrazu odzieży ze zoptymalizowanym przez DA OSELM osiągnął dokładność 93,98%. Jego wydajność przewyższyła inne algorytmy. Na podstawie analizy stabilności wykresu stwierdzono, że nie było wartości odstających wykazywanych przez model DA-OSELM, podczas gdy niektóre inne modele miały wartości odstające lub miały niższą stabilność w porównaniu z proponowanym modelem, potwierdzono w ten sposób skuteczność proponowanego rozwiązania.
    Źródło:
    Fibres & Textiles in Eastern Europe; 2021, 3 (147); 91-96
    1230-3666
    2300-7354
    Pojawia się w:
    Fibres & Textiles in Eastern Europe
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    A real-valued genetic algorithm to optimize the parameters of support vector machine for classification of multiple faults in NPP
    Autorzy:
    Amer, F. Z.
    El-Garhy, A. M.
    Awadalla, M. H.
    Rashad, S. M.
    Abdien, A. K.
    Powiązania:
    https://bibliotekanauki.pl/articles/147652.pdf
    Data publikacji:
    2011
    Wydawca:
    Instytut Chemii i Techniki Jądrowej
    Tematy:
    support vector machine (SVM)
    fault classification
    multi fault classification
    genetic algorithm (GA)
    machine learning
    Opis:
    Two parameters, regularization parameter c, which determines the trade off cost between minimizing the training error and minimizing the complexity of the model and parameter sigma (σ) of the kernel function which defines the non-linear mapping from the input space to some high-dimensional feature space, which constructs a non-linear decision hyper surface in an input space, must be carefully predetermined in establishing an efficient support vector machine (SVM) model. Therefore, the purpose of this study is to develop a genetic-based SVM (GASVM) model that can automatically determine the optimal parameters, c and sigma, of SVM with the highest predictive accuracy and generalization ability simultaneously. The GASVM scheme is applied on observed monitored data of a pressurized water reactor nuclear power plant (PWRNPP) to classify its associated faults. Compared to the standard SVM model, simulation of GASVM indicates its superiority when applied on the dataset with unbalanced classes. GASVM scheme can gain higher classification with accurate and faster learning speed.
    Źródło:
    Nukleonika; 2011, 56, 4; 323-332
    0029-5922
    1508-5791
    Pojawia się w:
    Nukleonika
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    A rule based machine learning approach to the nonlinear multifingered robot gripper problem
    Autorzy:
    Abu-Zitar, R.
    Al-Fahed Nuseirat, A. M.
    Powiązania:
    https://bibliotekanauki.pl/articles/970099.pdf
    Data publikacji:
    2005
    Wydawca:
    Polska Akademia Nauk. Instytut Badań Systemowych PAN
    Tematy:
    zacisk robota
    programowanie ewolucyjne
    komputerowe uczenie się
    robot gripper
    nonlinear complementarity problem (NCP)
    Evolutionary Programming (EP)
    machine learning
    nearest-classifier-algorithm
    Opis:
    In this paper, we present a novel method that utilizes the accumulation of knowledge in a rule base for solving the nonlinear frictional gripper problem for both the isotropic and orthotropic cases. The knowledge is discovered and accumulated in a rule base with the aid of a genetic based machine learning mechanism. This machine learning mechanism extracts rules for solving the problem with the help of the Evolutionary Programming [EP) algorithm. The retrievals are done using the nearest-classifier-algorithm. This approach provides online solutions for the problem, and establishes a dynamic and evolving environment that adapts with new and sudden changes on the grip specifications or on the external forces. The resulting grasping forces using the presented method are compared with grasping forces obtained using other methods, such as the Complementarity Problems. The proposed online method could update the needed grasping forces to keep firm grip if the configuration of the forces externally applied to the object is changed. Numerical examples that illustrate the proposed method are presented.
    Źródło:
    Control and Cybernetics; 2005, 34, 2; 553-573
    0324-8569
    Pojawia się w:
    Control and Cybernetics
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    A comprehensive study on the application of firefly algorithm in prediction of energy dissipation on block ramps
    Autorzy:
    Mahdavi-Meymand, Amin
    Sulisz, Wojciech
    Zounemat-Kermani, Mohammad
    Powiązania:
    https://bibliotekanauki.pl/articles/2087026.pdf
    Data publikacji:
    2022
    Wydawca:
    Polska Akademia Nauk. Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne PAN
    Tematy:
    firefly algorithm
    machine learning
    energy dissipation
    block ramp
    Opis:
    In this study novel integrative machine learning models embedded with the firefly algorithm (FA) were developed and employed to predict energy dissipation on block ramps. The used models include multi-layer perceptron neural network (MLPNN), adaptive neuro-fuzzy inference system (ANFIS), group method of data handling (GMDH), support vector regression (SVR), linear equation (LE), and nonlinear regression equation (NE). The investigation focused on the evaluation of the performance of standard and integrative models in different runs. The performances of machine learning models and the nonlinear equation are higher than the linear equation. The results also show that FA increases the performance of all applied models. Moreover, the results indicate that the ANFIS-FA is the most stable integrative model in comparison to the other embedded methods and reveal that GMDH and SVR are the most stable technique among all applied models. The results also show that the accuracy of the LE-FA technique is relatively low, RMSE=0.091. The most accurate results provide SVR-FA, RMSE=0.034.
    Źródło:
    Eksploatacja i Niezawodność; 2022, 24, 2; 200--210
    1507-2711
    Pojawia się w:
    Eksploatacja i Niezawodność
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    A new algorithm for generation of decision trees
    Autorzy:
    Grzymała-Busse, J. W.
    Hippe, Z. S.
    Knap, M.
    Mroczek, T.
    Powiązania:
    https://bibliotekanauki.pl/articles/1965778.pdf
    Data publikacji:
    2004
    Wydawca:
    Politechnika Gdańska
    Tematy:
    artificial intelligence
    supervised machine learning
    decision trees
    Bayes networks
    Opis:
    A new algorithm for development of quasi-optimal decision trees, based on the Bayes theorem, has been created and tested. The algorithm generates a decision tree on the basis of Bayesian belief networks, created prior to the formation of the decision tree. The efficiency of this new algorithm was compared with three other known algorithms used to develop decision trees. The data set used for the experiments was a set of cases of skin lesions, histopatolgically verified.
    Źródło:
    TASK Quarterly. Scientific Bulletin of Academic Computer Centre in Gdansk; 2004, 8, 2; 243-247
    1428-6394
    Pojawia się w:
    TASK Quarterly. Scientific Bulletin of Academic Computer Centre in Gdansk
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Sequential Classification of Palm Gestures Based on A* Algorithm and MLP Neural Network for Quadrocopter Control
    Autorzy:
    Wodziński, M.
    Krzyżanowska, A.
    Powiązania:
    https://bibliotekanauki.pl/articles/221525.pdf
    Data publikacji:
    2017
    Wydawca:
    Polska Akademia Nauk. Czytelnia Czasopism PAN
    Tematy:
    machine learning
    shortest path
    sequential data
    quadrocopter
    GPU
    CUDA
    Opis:
    This paper presents an alternative approach to the sequential data classification, based on traditional machine learning algorithms (neural networks, principal component analysis, multivariate Gaussian anomaly detector) and finding the shortest path in a directed acyclic graph, using A* algorithm with a regression-based heuristic. Palm gestures were used as an example of the sequential data and a quadrocopter was the controlled object. The study includes creation of a conceptual model and practical construction of a system using the GPU to ensure the realtime operation. The results present the classification accuracy of chosen gestures and comparison of the computation time between the CPU- and GPU-based solutions.
    Źródło:
    Metrology and Measurement Systems; 2017, 24, 2; 265-276
    0860-8229
    Pojawia się w:
    Metrology and Measurement Systems
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Prediction of ship's speed through ground using the previous voyage's drift speed
    Autorzy:
    Yamane, D.
    Kano, T.
    Powiązania:
    https://bibliotekanauki.pl/articles/24201461.pdf
    Data publikacji:
    2023
    Wydawca:
    Uniwersytet Morski w Gdyni. Wydział Nawigacyjny
    Tematy:
    machine learning
    weather routing
    ship's speed estimation
    drift speed
    algorithm
    route planning
    tidal current
    Opis:
    In recent years, 'weather routing' has been attracting increasing attention as a means of reducing costs and environmental impact. In order to achieve high-quality weather routing, it is important to accurately predict the ship's speed through ground during a voyage from ship control variables and predicted data on weather and sea conditions. Because sea condition forecasts are difficult to produce in-house, external data is often used, but there is a problem that the accuracy of sea condition forecasts is not sufficient and it is impossible to improve the accuracy of the forecasts because the data is external. In this study, we propose a machine learning method for predicting speed through ground by considering the actual values of the previous voyage’s drift speed for ships that regularly operate on the same route, such as ferries. Experimental results showed that this method improves the prediction performance of ship’s speed through ground.
    Źródło:
    TransNav : International Journal on Marine Navigation and Safety of Sea Transportation; 2023, 17, 1; 129--137
    2083-6473
    2083-6481
    Pojawia się w:
    TransNav : International Journal on Marine Navigation and Safety of Sea Transportation
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    A machine learning method for soil conditioning automated decision-making of EPBM : hybrid GBDT and Random Forest Algorithm
    Autorzy:
    Lin, Lin
    Guo, Hao
    Lv, Yancheng
    Liu, Jie
    Tong, Changsheng
    Yang, Shuqin
    Powiązania:
    https://bibliotekanauki.pl/articles/2087007.pdf
    Data publikacji:
    2022
    Wydawca:
    Polska Akademia Nauk. Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne PAN
    Tematy:
    soil conditioning
    automated decision-making
    hybrid algorithm
    geological parameters
    drive parameters
    feature selection
    Opis:
    There lacks an automated decision-making method for soil conditioning of EPBM with high accuracy and efficiency that is applicable to changeable geological conditions and takes drive parameters into consideration. A hybrid method of Gradient Boosting Decision Tree (GBDT) and random forest algorithm to make decisions on soil conditioning using foam is proposed in this paper to realize automated decision-making. Relevant parameters include decision parameters (geological parameters and drive parameters) and target parameters (dosage of foam). GBDT, an efficient algorithm based on decision tree, is used to determine the weights of geological parameters, forming 3 parameters sets. Then 3 decision-making models are established using random forest, an algorithm with high accuracy based on decision tree. The optimal model is obtained by Bayesian optimization. It proves that the model has obvious advantages in accuracy compared with other methods. The model can realize real-time decision-making with high accuracy under changeable geological conditions and reduce the experiment cost.
    Źródło:
    Eksploatacja i Niezawodność; 2022, 24, 2; 237--247
    1507-2711
    Pojawia się w:
    Eksploatacja i Niezawodność
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Prognozowanie dziennych obrotów przedsiębiorstwa za pomocą algorytmu XGBoost – studium przypadku
    Forecasting daily turnover using XGBoost algorithm – a case study
    Autorzy:
    Wójcik, Filip
    Powiązania:
    https://bibliotekanauki.pl/articles/586257.pdf
    Data publikacji:
    2018
    Wydawca:
    Uniwersytet Ekonomiczny w Katowicach
    Tematy:
    Prognozowanie
    Sztuczna inteligencja
    Uczenie maszynowe
    Artificial intelligence
    Forecasting
    Machine learning
    Opis:
    Celem niniejszego artykułu było zbadanie możliwości wykorzystania algorytmu Extreme Gradient Boosting (XGBoost) jako narzędzia prognozowania obrotów przedsiębiorstwa. Na studium przypadku wybrano udostępnione przez firmę Rossmann (wraz z prośbą o opracowanie innowacyjnej metody prognozowania) dane, obejmujące informacje z mikro- i makrootoczenia oraz obrotów 1115 oddziałów. Działanie algorytmu porównano z klasycznymi modelami SARIMAX i Holta–Wintersa, wykorzystując walidację krzyżową oraz testy statystycznej istotności różnic trafności predykcji. Badano metryki średniego błędu procentowego, współczynnik Theila oraz skorygowany współczynnik determinacji. Wyniki przekazano do weryfikacji firmie Rossmann. Potwierdzono, iż XGBoost po zastosowaniu odpowiedniej obróbki danych i sposobu uczenia osiąga lepsze rezultaty niż modele klasyczne.
    The goal of this paper was to investigate use of the Extreme Gradient Boosting XGBoost algorithm as a forecasting tool. The data provided by the Rossman Company, with a request to design an innovative prediction method, has been used as a base for this case study. The data contains details about micro- and macro-environment, as well as turnover of 1115 stores. Performance of the algorithm was compared to classical forecasting models SARIMAX and Holt–Winters, using time-series cross validation and tests for statistical importance in prediction quality differences. Metrics of root mean squared percentage error (RMSPE), Theil’s coefficient and adjusted correlation coefficient were analyzed. Results where then passed to Rossman for verification on a separate validation set, via Kaggle.com platform. Study results confirmed, that XGBoost, after using proper data preparation and training method, achieves better results than classical models.
    Źródło:
    Studia Ekonomiczne; 2018, 375; 121-140
    2083-8611
    Pojawia się w:
    Studia Ekonomiczne
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    CCR: A combined cleaning and resampling algorithm for imbalanced data classification
    Autorzy:
    Koziarski, M.
    Woźniak, M.
    Powiązania:
    https://bibliotekanauki.pl/articles/329869.pdf
    Data publikacji:
    2017
    Wydawca:
    Uniwersytet Zielonogórski. Oficyna Wydawnicza
    Tematy:
    machine learning
    classification algorithms
    imbalanced data
    preprocessing
    oversampling
    uczenie maszynowe
    algorytm klasyfikacji
    dane niezrównoważone
    wstępne przetwarzanie danych
    Opis:
    Imbalanced data classification is one of the most widespread challenges in contemporary pattern recognition. Varying levels of imbalance may be observed in most real datasets, affecting the performance of classification algorithms. Particularly, high levels of imbalance make serious difficulties, often requiring the use of specially designed methods. In such cases the most important issue is often to properly detect minority examples, but at the same time the performance on the majority class cannot be neglected. In this paper we describe a novel resampling technique focused on proper detection of minority examples in a two-class imbalanced data task. The proposed method combines cleaning the decision border around minority objects with guided synthetic oversampling. Results of the conducted experimental study indicate that the proposed algorithm usually outperforms the conventional oversampling approaches, especially when the detection of minority examples is considered.
    Źródło:
    International Journal of Applied Mathematics and Computer Science; 2017, 27, 4; 727-736
    1641-876X
    2083-8492
    Pojawia się w:
    International Journal of Applied Mathematics and Computer Science
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Machine Learning-Aided Architectural Design for Carbon Footprint Reduction
    Wspomagane uczeniem maszynowym projektowanie architektury w celu zmniejszenia śladu węglowego
    Autorzy:
    Płoszaj-Mazurek, Mateusz
    Powiązania:
    https://bibliotekanauki.pl/articles/129265.pdf
    Data publikacji:
    2020
    Wydawca:
    PWB MEDIA Zdziebłowski
    Tematy:
    ocena cyklu życia
    optymalizacja parametryczna
    ślad węglowy
    uczenie maszynowe
    sztuczna inteligencja
    algorytm
    emisja ghg
    architektura zrównoważona
    zbiór danych duży
    life cycle assessment
    parametric optimization
    carbon footprint
    artificial intelligence
    algorithm
    ghg emissions
    sustainable architecture
    big data
    machine learning
    Opis:
    The built environment is considered responsible for at least 20-40% of greenhouse gases emission. The way we design may exert an impact on this percentage. A new paradigm, namely artificial intelligence, is arriving. More and more tasks are becoming automated via algorithms. How could this power be applied in order to strengthen our knowledge about the ways we design buildings? The author of the following paper presents a study in which carbon footprint yielded by a multifamily building is analysed. ML has been used to generate an extensive overview of the possible design solutions. This, in turn, made it possible to observe correlations between various parameters that resulted in a reduced carbon footprint.
    Środowisko zabudowane odpowiada za co najmniej 20 do 40% emisji gazów cieplarnianych, a sposób, w jaki projektujemy, może wpłynąć na tę wartość. Coraz więcej zadań zostaje zautomatyzowanych za pomocą algorytmów. Jak możemy wykorzystać to narzędzie, aby wspomóc naszą wiedzę na temat sposobów projektowania budynków? Autor przedstawia badanie analizujące ślad węglowy budynku wielorodzinnego. Algorytm uczenia maszynowego został wykorzystany do wygenerowania obszernego przeglądu możliwych rozwiązań projektowych. Umożliwiło to zaobserwowanie korelacji między różnymi parametrami, co pozwoliło na wybór kombinacji parametrów o najniższym śladzie węglowym.
    Źródło:
    Builder; 2020, 24, 7; 35-39
    1896-0642
    Pojawia się w:
    Builder
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Cost-sensitive feature selection
    Selekcja cech z uwzględnieniem kosztu ich pozyskania
    Autorzy:
    Ciupke, K.
    Powiązania:
    https://bibliotekanauki.pl/articles/327830.pdf
    Data publikacji:
    2006
    Wydawca:
    Polska Akademia Nauk. Polskie Towarzystwo Diagnostyki Technicznej PAN
    Tematy:
    selekcja cech
    algorytm mrówkowy
    uczenie maszynowe
    sztuczna inteligencja
    diagnostyka techniczna
    feature selection
    ant algorithm
    machine learning
    artificial intelligence
    technical diagnostics
    Opis:
    The paper concerns the selection of features in the technical diagnostics domain. The author focused his attention on a wrapper approach. In this approach an application of the ant algorithm as a search engine is proposed. The proposed method of so-called ant wrapper approach is presented. The method takes advantage of cost of features, where the cost is connected with the cost of sensors. The algorithm as a pseudo-code and some results of a verification experiment are shown. The verification was carried out on data derived from an active diagnostic experiment concerning a rotating machine. The obtained results show, that the proposed method could allow to reduce the number of used sensors.
    W artykule opisano metodę selekcji cech z zastosowaniem algorytmu mrówkowego. Metoda pozwala także na uwzględnienie kosztu atrybutu, przy czym jego koszt związany jest z kosztem pozyskanie sygnału diagnostycznego. W przypadku gdy sygnał ten jest już wykorzystywany uznaje się, że koszt wyznaczenia danej cechy jest pomijalnie mały. Metodę przedstawiono w postaci pseudo-kodu i zweryfikowano dla danych pochodzących z czynnego eksperymentu diagnostycznego. Uzyskane wyniki pokazują, że istnieje możliwość ograniczenia liczby stosowanych czujników.
    Źródło:
    Diagnostyka; 2006, 2(38); 45-48
    1641-6414
    2449-5220
    Pojawia się w:
    Diagnostyka
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Robustness of Support Vector Machines in Algorithmic Trading on Cryptocurrency Market
    Autorzy:
    Ślepaczuk, Robert
    Zenkova, Maryna
    Powiązania:
    https://bibliotekanauki.pl/articles/1356913.pdf
    Data publikacji:
    2019-08-07
    Wydawca:
    Uniwersytet Warszawski. Wydział Nauk Ekonomicznych
    Tematy:
    Machine learning
    support vector machines
    investment algorithm
    algorithmic trading
    strategy
    optimization
    cross-validation
    overfitting
    cryptocurrency market
    technical analysis
    meta parameters
    Opis:
    This study investigates the profitability of an algorithmic trading strategy based on training SVM model to identify cryptocurrencies with high or low predicted returns. A tail set is defined to be a group of coins whose volatility-adjusted returns are in the highest or the lowest quintile. Each cryptocurrency is represented by a set of six technical features. SVM is trained on historical tail sets and tested on the current data. The classifier is chosen to be a nonlinear support vector machine. The portfolio is formed by ranking coins using the SVM output. The highest ranked coins are used for long positions to be included in the portfolio for one reallocation period. The following metrics were used to estimate the portfolio profitability: %ARC (the annualized rate of change), %ASD (the annualized standard deviation of daily returns), MDD (the maximum drawdown coefficient), IR1, IR2 (the information ratio coefficients). The performance of the SVM portfolio is compared to the performance of the four benchmark strategies based on the values of the information ratio coefficient IR1, which quantifies the risk-weighted gain. The question of how sensitive the portfolio performance is to the parameters set in the SVM model is also addressed in this study.
    Źródło:
    Central European Economic Journal; 2018, 5, 52; 186 - 205
    2543-6821
    Pojawia się w:
    Central European Economic Journal
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Analiza istotności cech znamion skórnych dla celów diagnostyki czerniaka złośliwego
    Skin lesion features analysis for malignant melanoma classification
    Autorzy:
    Mikołajczyk, A.
    Grochowski, M.
    Powiązania:
    https://bibliotekanauki.pl/articles/268540.pdf
    Data publikacji:
    2018
    Wydawca:
    Politechnika Gdańska. Wydział Elektrotechniki i Automatyki
    Tematy:
    algorytm ewolucyjny
    uczenie maszynowe
    sieci neuronowe
    systemy wspomagania decyzji
    evolutionary algorithm
    neural networks
    decision support system
    machine learning
    Opis:
    Pomimo dynamicznego rozwoju metod uczenia maszynowego i ich wdrażania do praktyki lekarskiej, automatyczna analiza znamion skórnych wciąż jest nierozwiązanym problemem. Poniższy artykuł proponuje zastosowanie algorytmu ewolucyjnego do zaprojektowania, wytrenowania i przetestowania całych populacji klasyfikatorów (sztucznych sieci neuronowych) oraz ich iteracyjnego udoskonalania w każdej kolejnej populacji, w celu osiągnięcia jak najlepszej dokładności klasyfikacji znamion skórnych. Algorytm zwraca optymalny zestaw cech opisujących obraz dermatoskopowy wraz z proponowaną architekturą sieci neuronowej. Uzyskano dokładność równą 85,83%, swoistość równą 79,07% oraz czułość równą 92,60%.
    Despite the dynamic development of machine learning methods, automatic analysis of skin lesions is still open issue. The following article proposes the use of an evolutionary algorithm to design, train, and to test a whole population of classifiers (artificial neural networks) and to iteratively improve them in each subsequent population, in order to achieve the best possible accuracy in the classification of skin lesions task. The algorithm returns an optimal set of features describing the dermatoscopic image together with the proposed architecture of the neural network. High classification results were obtained, in particular: accuracy equal to 85.83%, specificity 79.07% and sensitivity 92.60%.
    Źródło:
    Zeszyty Naukowe Wydziału Elektrotechniki i Automatyki Politechniki Gdańskiej; 2018, 60; 67-70
    1425-5766
    2353-1290
    Pojawia się w:
    Zeszyty Naukowe Wydziału Elektrotechniki i Automatyki Politechniki Gdańskiej
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Stabilizer design of PSS3B based on the KH algorithm and Q-Learning for damping of low frequency oscillations in a single-machine power system
    Autorzy:
    Mohamadi, Farshid
    Sedaghati, Alireza
    Powiązania:
    https://bibliotekanauki.pl/articles/41190034.pdf
    Data publikacji:
    2023
    Wydawca:
    Politechnika Warszawska, Instytut Techniki Cieplnej
    Tematy:
    3-band power system stabilize
    reinforcement learning
    Q-learning
    system zasilania
    uczenie przez wzmacnianie
    Opis:
    The aim of this study is to use the reinforcement learning method in order to generate a complementary signal for enhancing the performance of the system stabilizer. The reinforcement learning is one of the important branches of machine learning on the area of artificial intelligence and a general approach for solving the Marcov Decision Process (MDP) problems. In this paper, a reinforcement learning-based control method, named Q-learning, is presented and used to improve the performance of a 3-Band Power System Stabilizer (PSS3B) in a single-machine power system. For this end, we first set the parameters of the 3-band power system stabilizer by optimizing the eigenvalue-based objective function using the new optimization KH algorithm, and then its efficiency is improved using the proposed reinforcement learning algorithm based on the Q-learning method in real time. One of the fundamental features of the proposed reinforcement learning-based stabilizer is its simplicity and independence on the system model and changes in the working points of operation. To evaluate the efficiency of the proposed reinforcement learning-based 3-band power system stabilizer, its results are compared with the conventional power system stabilizer and the 3-band power system stabilizer designed by the use of the KH algorithm under different working points. The simulation results based on the performance indicators show that the power system stabilizer proposed in this study underperform the two other methods in terms of decrease in settling time and damping of low frequency oscillations.
    Źródło:
    Journal of Power Technologies; 2023, 103, 4; 230-242
    1425-1353
    Pojawia się w:
    Journal of Power Technologies
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Zastosowanie algorytmów przeszukiwania grafów do analizy obrazów medycznych
    Analysis of medical images based on graph search algorithms
    Autorzy:
    Dimitrova-Grekow, T.
    Dąbkowski, A.
    Powiązania:
    https://bibliotekanauki.pl/articles/156629.pdf
    Data publikacji:
    2012
    Wydawca:
    Stowarzyszenie Inżynierów i Techników Mechaników Polskich
    Tematy:
    analiza obrazów medycznych
    algorytmy przeszukiwania grafów
    uczenie maszynowe
    eksploracja danych
    rozpoznawanie choroby
    image analysis
    graph search algorithm
    machine learning
    data mining
    disease recognition
    Opis:
    W artykule przedstawiono wyniki testów niekonwencjonalnego zastosowania metod do przeszukiwania grafów w celu analizy obrazów powstałych z rezonansu magnetycznego głowy. Zaprezentowano GUI do automatycznej obróbki serii obrazów. Zbudowane klasyfikatory wykazały, że metoda BFS analizy plików DICOM, po odpowiednej selekcji cech, pozwala na 100% rozpoznawanie chorych na wodogłowie i ponad 90% zdrowych, co zachęca do dalszych badań i obserwacji, np. czy osoby sklasyfikowane błędnie jako chorzy, po czasie rzeczywiście nie rozwinęli tej choroby.
    There are many methods for image segmentation [1, 2]: threshold, area, edge and hybrid methods. Area methods indicate groups of similar pixels form local regions [3, 4]. Edge methods detect boundaries between homogeneous segments [5, 6, 7]. In this paper we present the results of tests of unconventional implementation of graph search methods for the analysis of images generated from magnetic resonance imaging [8]. We explored the effectiveness of different approaches for dividing areas within a similar gray scale, using adapted graph search algorithms (DFS, BFS) after appropriate modification (Fig. 1). For this purpose, the Weka package (a tool for pre-processing, classification, regression, clustering and data visualization) was used [9]. A training set was generated after analyzing all the series of images from the database. First, we evaluated models created using certain algorithms and compared their efficacy (Tab. 1). This was followed by a selection of attributes (Tab. 2) and a re-evaluation of the models (Tab. 3). Comparison of the results of both evaluations showed that after selection of the relevant product attributes, you can achieve up to 100% detection of patients with hydrocephalus and over 90% proper recognition of healthy persons. This encourages further research and observation, such as whether persons wrongly classified as sick actually developed the disease in time. We designed a web application for the study, written in Windows Azure, as well as a GUI for automatic processing of a series of images (Fig. 2).
    Źródło:
    Pomiary Automatyka Kontrola; 2012, R. 58, nr 7, 7; 578-580
    0032-4140
    Pojawia się w:
    Pomiary Automatyka Kontrola
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    An assessment of machine learning and data balancing techniques for evaluating downgrade truck crash severity prediction in Wyoming
    Autorzy:
    Ampadu, Vincent-Michael Kwesi
    Haq, Muhammad Tahmidul
    Ksaibati, Khaled
    Powiązania:
    https://bibliotekanauki.pl/articles/2176018.pdf
    Data publikacji:
    2022
    Wydawca:
    Fundacja Centrum Badań Socjologicznych
    Tematy:
    crash severity
    performance
    extreme gradient boosting tree
    adaptive boosting tree
    random forest
    gradient boost decision tree
    adaptive synthetic algorithm
    Opis:
    This study involved the investigation of various machine learning methods, including four classification tree-based ML models, namely the Adaptive Boosting tree, Random Forest, Gradient Boost Decision Tree, Extreme Gradient Boosting tree, and three non-tree-based ML models, namely Support Vector Machines, Multi-layer Perceptron and k-Nearest Neighbors for predicting the level of severity of large truck crashes on Wyoming road networks. The accuracy of these seven methods was then compared. The Final ROC AUC score for the optimized random forest model is 95.296 %. The next highest performing model was the k-NN with 92.780 %, M.L.P. with 87.817 %, XGBoost with 86.542 %, Gradboost with 74.824 %, SVM with 72.648 % and AdaBoost with 67.232 %. Based on the analysis, the top 10 predictors of severity were obtained from the feature importance plot. These may be classified into whether safety equipment was used, whether airbags were deployed, the gender of the driver and whether alcohol was involved.
    Źródło:
    Journal of Sustainable Development of Transport and Logistics; 2022, 7, 2; 6--24
    2520-2979
    Pojawia się w:
    Journal of Sustainable Development of Transport and Logistics
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Identyfikacja systemów nieliniowych przy pomocy kernelowego algorytmu LMS z ograniczeniem zasobów
    Identification of nonlinear systems using fixed budget kernel LMS algorithm
    Autorzy:
    Rzepka, D.
    Otfinowski, P.
    Powiązania:
    https://bibliotekanauki.pl/articles/408102.pdf
    Data publikacji:
    2012
    Wydawca:
    Politechnika Lubelska. Wydawnictwo Politechniki Lubelskiej
    Tematy:
    metody kernelowe
    uczenie maszynowe
    regresja nieliniowa
    algorytm LMS
    dobór wektorów nośnych
    kernel methods
    machine learning
    nonlinear regression
    least mean squares
    pruning criterion
    Opis:
    W artykule zaprezentowano zastosowanie nowej, nieliniowej wersji algorytmu LMS wykorzystującej funkcje kernelowe do identyfikacji systemów nieliniowych. Aby ograniczyć ilość wektorów nośnych, będących niezbędnym elementem algorytmów opartych o metody kernelowe zastosowano kryterium selekcji. Nowy wektor wejściowy jest przyjmowany do słownika, a następnie w słowniku wyszukiwany i usuwany jest wektor, który ma najmniejszy wpływ na tworzony model nieliniowy. Przedstawiony przykład identyfikacji systemu nieliniowego potwierdza skuteczność porównywalną do algorytmów wykorzystujących większą liczbę wektorów nośnych.
    In this paper a new version of kernel normalized least mean squares algorithm is applied to identification of nonlinear system. To maintain a fixed amount of support vectors, requisite for practical kernel-based algorithm, a pruning criterion is used. After admitting a new input vector to the dictionary, a least important entry is selected and discarder. A case of nonlinear system identification is presented, proving that algorithm performs well and it can maintain a performance comparable to state-of-the-art algorithms, using smaller number of support vectors.
    Źródło:
    Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska; 2012, 4b; 10-13
    2083-0157
    2391-6761
    Pojawia się w:
    Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Analiza wybranych metod tworzenia sztucznej inteligencji na przykładzie popularnej gry w karty
    Analysis of selected methods of creating artificial intelligence on the example of a popular card game
    Autorzy:
    Gałka, Łukasz
    Dzieńkowski, Mariusz
    Powiązania:
    https://bibliotekanauki.pl/articles/98306.pdf
    Data publikacji:
    2020
    Wydawca:
    Politechnika Lubelska. Instytut Informatyki
    Tematy:
    artificial intelligence
    machine learning
    algorithm efficiency evaluation
    computer games
    sztuczna inteligencja
    uczenie maszynowe
    ocena skuteczności algorytmów
    gry komputerowe
    Opis:
    The aim of the article was to analyze selected methods of creating artificial intelligence in a popular card game. Two experiments were conducted: with a human and with a computer. The following algorithms were analyzed: random, min-max, based on a neural network, statistical and statistical with the use of “cheating” technique. The examined parameters were as follows: efficiency, execution time, number of implementation code lines, implementation time and training duration. The indicator with the greatest impact on the selection of the most optimal method was efficiency. The research has shown no difference in efficiency for the neural network-based algorithm and the statistical algorithm. In other cases, the differences in this feature were significant. The use of the “cheating” technique has increased the efficiency.
    Celem artykułu była analiza wybranych metod tworzenia sztucznej inteligencji w popularnej grze w karty. Zostały przeprowadzone dwa eksperymenty: z człowiekiem oraz z komputerem. Analizie poddano algorytmy: losowy, minmax, bazujący na sieci neuronowej, statystyczny oraz statystyczny z użyciem techniki „oszukiwania”. Zbadano takie parametry jak: skuteczność, czas wykonania, liczbę linii kodu implementacji, czas implementacji oraz czas trwania treningu. Wskaźnikiem mającym największy wpływ na wybór najbardziej optymalnej metody była skuteczność. Badania wykazały brak różnic w skuteczności dla algorytmu bazującego na sieci neuronowej i algorytmu statystycznego. W pozostałych przypadkach różnice tej cechy były istotne. Użycie techniki „oszukiwania” zwiększyło skuteczność.
    Źródło:
    Journal of Computer Sciences Institute; 2020, 16; 233-240
    2544-0764
    Pojawia się w:
    Journal of Computer Sciences Institute
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Power quality analysis in electrical drives and a case study of artificial intelligence prediction algorithm for fault deterrent electrical drives
    Autorzy:
    Kumarasamy, Vishnu Murthy
    Loganathan, Ashok Kumar
    Powiązania:
    https://bibliotekanauki.pl/articles/2173673.pdf
    Data publikacji:
    2022
    Wydawca:
    Polska Akademia Nauk. Czytelnia Czasopism PAN
    Tematy:
    voltage sag
    voltage swell
    voltage imbalance
    machine learning
    inverter drives
    artificial intelligence
    wzrost napięcia
    spadek napięcia
    asymetria napięcia
    uczenie maszynowe
    napędy falownikowe
    sztuczna inteligencja
    Opis:
    Since electrical drives have become an integral element of any industrial sector, power quality difficulties have been well expected, and delivering genuine quality of the same has proven to be a difficult challenge. Since power quality relies on load side non-linearity and high semiconductor technology consumption, it is a serious concern. The efficiency of the drive segment employed in the sector is increasingly becoming a topic of discussion in today’s market. Numerous reviews of available literature have found problems with the load side as well as with electrical drive proficiency, as a result of the issues listed above. A high level of power quality vulnerability is simply too much. Even the most advanced technology has its limits when it comes to drive operation. Research on the grid-side quality issues of electrical drives is the focus of this article. After field testing of grid power quality, each parametric analysis is performed to identify crucial parameters that can cause industrial drives to fail. Based on this discovery, a machine learning strategy was developed and an artificial intelligence technique was proposed to administer the fault deterrent prediction algorithm. An accurate forecast of anomalous behavior on the grid side ensures safe and dependable grid operation such that shutdown or failure probability is minimized to a greater extent by the results. Additional information gleaned from historical data will prove useful to equipment manufacturers in the future, providing a solution to this problem.
    Źródło:
    Bulletin of the Polish Academy of Sciences. Technical Sciences; 2022, 70, 3; art. no. e141180
    0239-7528
    Pojawia się w:
    Bulletin of the Polish Academy of Sciences. Technical Sciences
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Lung cancer detection using an integration of fuzzy K-Means clustering and deep learning techniques for CT lung images
    Autorzy:
    Prasad, J. Maruthi Nagendra
    Chakravarty, S.
    Krishna, M. Vamsi
    Powiązania:
    https://bibliotekanauki.pl/articles/2173683.pdf
    Data publikacji:
    2022
    Wydawca:
    Polska Akademia Nauk. Czytelnia Czasopism PAN
    Tematy:
    fuzzy K-means
    artificial neural networks
    SVM
    support vector machine
    crow search optimization algorithm
    algorytm rozmytych k-średnich
    sztuczne sieci neuronowe
    maszyna wektorów wspierających
    algorytm optymalizacji wyszukiwania kruków
    Opis:
    Computer aided detection systems are used for the provision of second opinion during lung cancer diagnosis. For early-stage detection and treatment false positive reduction stage also plays a vital role. The main motive of this research is to propose a method for lung cancer segmentation. In recent years, lung cancer detection and segmentation of tumors is considered one of the most important steps in the surgical planning and medication preparations. It is very difficult for the researchers to detect the tumor area from the CT (computed tomography) images. The proposed system segments lungs and classify the images into normal and abnormal and consists of two phases, The first phase will be made up of various stages like pre-processing, feature extraction, feature selection, classification and finally, segmentation of the tumor. Input CT image is sent through the pre-processing phase where noise removal will be taken care of and then texture features are extracted from the pre-processed image, and in the next stage features will be selected by making use of crow search optimization algorithm, later artificial neural network is used for the classification of the normal lung images from abnormal images. Finally, abnormal images will be processed through the fuzzy K-means algorithm for segmenting the tumors separately. In the second phase, SVM classifier is used for the reduction of false positives. The proposed system delivers accuracy of 96%, 100% specificity and sensitivity of 99% and it reduces false positives. Experimental results shows that the system outperforms many other systems in the literature in terms of sensitivity, specificity, and accuracy. There is a great tradeoff between effectiveness and efficiency and the proposed system also saves computation time. The work shows that the proposed system which is formed by the integration of fuzzy K-means clustering and deep learning technique is simple yet powerful and was effective in reducing false positives and segments tumors and perform classification and delivers better performance when compared to other strategies in the literature, and this system is giving accurate decision when compared to human doctor’s decision.
    Źródło:
    Bulletin of the Polish Academy of Sciences. Technical Sciences; 2022, 70, 3; art. no. e139006
    0239-7528
    Pojawia się w:
    Bulletin of the Polish Academy of Sciences. Technical Sciences
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Applicability of artificial intelligence in smart healthcare systems for automatic detection of Parkinson’s Disease
    Autorzy:
    Pallathadka, Harikumar
    Padminivalli V., S.J.R.K.
    Vasavi, M.
    Nancy, P.
    Naved, Mohd
    Kumar, Harish
    Ray, Samrat
    Powiązania:
    https://bibliotekanauki.pl/articles/38709253.pdf
    Data publikacji:
    2024
    Wydawca:
    Instytut Podstawowych Problemów Techniki PAN
    Tematy:
    Parkinson’s disease
    detection
    machine learning
    relief algorithm
    LDA algorithm
    SVM-RBF
    accuracy
    sensitivity
    specificity
    choroba Parkinsona
    wykrywanie
    nauczanie maszynowe
    algorytm ulgi
    Algorytm LDA
    dokładność
    wrażliwość
    specyficzność
    Opis:
    Parkinson’s disease is associated with memory loss, anxiety, and depression in the brain. Problems such as poor balance and difficulty during walking can be observed in addition to symptoms of impaired posture and rigidity. The field dedicated to making computers capable of learning autonomously, without having to be explicitly programmed, is known as machine learning. An approach to the diagnosis of Parkinson’s disease, which is based on artificial intelligence, is discussed in this article. The input for this system is provided through photographic examples of Parkinson’s disease patient handwriting. Received photos are preprocessed using the relief feature option to begin the process. This is helpful in the process of selecting characteristics for the identification of Parkinson’s disease. After that, the linear discriminant analysis (LDA) algorithm is employed to reduce the dimensions, bringing down the total number of dimensions that are present in the input data. The photos are then classified via radial basis function-support vector machine (SVM-RBF), k-nearest neighbors (KNN), and naive Bayes algorithms, respectively.
    Źródło:
    Computer Assisted Methods in Engineering and Science; 2024, 31, 2; 175-185
    2299-3649
    Pojawia się w:
    Computer Assisted Methods in Engineering and Science
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Artificial intelligence-powered pulse sequences in nuclear magnetic resonance and magnetic resonance imaging: historical trends, current innovations and perspectives
    Autorzy:
    Tokarz, Paweł
    Powiązania:
    https://bibliotekanauki.pl/articles/35508129.pdf
    Data publikacji:
    2024
    Wydawca:
    Radomskie Towarzystwo Naukowe
    Tematy:
    artificial intelligence
    machine learning
    evolutionary algorithm
    artificial neural network
    nuclear magnetic resonance
    magnetic resonance imaging
    pulse sequence
    shaped pulse
    sztuczna inteligencja
    uczenie maszynowe
    algorytm ewolucyjny
    sztuczna sieć neuronowa
    magnetyczny rezonans jądrowy
    rezonans magnetyczny
    sekwencja impulsów
    impuls ukształtowany
    Opis:
    This review article explores the historical background and recent advances in the application of artificial intelligence (AI) in the development of radiofrequency pulses and pulse sequences in nuclear magnetic resonance spectroscopy (NMR) and imaging (MRI). The introduction of AI into this field, which traces back to the late 1970s, has recently witnessed remarkable progress, leading to the design of specialized frameworks and software solutions such as DeepRF, MRzero, and GENETICS-AI. Through an analysis of literature and case studies, this review tracks the transformation of AI-driven pulse design from initial proof-of-concept studies to comprehensive scientific programs, shedding light on the potential implications for the broader NMR and MRI communities. The fusion of artificial intelligence and magnetic resonance pulse design stands as a promising frontier in spectroscopy and imaging, offering innovative enhancements in data acquisition, analysis, and interpretation across diverse scientific domains.
    Źródło:
    Scientiae Radices; 2024, 3, 1; 30-52
    2956-4808
    Pojawia się w:
    Scientiae Radices
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
      Wyświetlanie 1-41 z 41

      Ta witryna wykorzystuje pliki cookies do przechowywania informacji na Twoim komputerze. Pliki cookies stosujemy w celu świadczenia usług na najwyższym poziomie, w tym w sposób dostosowany do indywidualnych potrzeb. Korzystanie z witryny bez zmiany ustawień dotyczących cookies oznacza, że będą one zamieszczane w Twoim komputerze. W każdym momencie możesz dokonać zmiany ustawień dotyczących cookies