Temat: prediction time - Prolib Integro

Skocz do pozycji: 1.

Tytuł:: The impact of the size of the training set on the predictive abilities of neural models on the example of the Day-Ahead Market System of TGE S.A.
Autorzy:: Ruciński, Dariusz
Tematy:: Day Ahead Market
MATLAB environment
Simulink environment
neural modeling
prediction time
electricity prices; Pokaż więcej
Wydawca:: Uniwersytet Przyrodniczo-Humanistyczny w Siedlcach
Powiązania:: https://bibliotekanauki.pl/articles/2175162.pdf Link otwiera się w nowym oknie
Opis:: The main object of the research was to examine the acceptable time horizon that could be predicted by previously learned models of the Day-Ahead Market (DAM) TGE S.A. system. The article contains the results of research on the predicting ability of different ANN models of the DAM TGE S.A. The research was conducted based on data covering the operation of the Polish stock exchange in the period from 2002 to 2019 (the first half of the year). The research was carried out based on the learned ANN models of the DAM system. Data were taken for examination covering the time from 2002 to 2019 (1st half of the year) and was divided into a different period, i.e., a month, a quarter, and a half-year., year, etc. The MSE, MAE, MAPE, and R2 were adopted as the criteria for assessing the ability of individual models to predict electricity prices. The research was carried out by successively expanding forecasting periods in a rolling manner. For example, for a half-year, prediction time intervals were increased from one week to month, two months, quarter, half-year, etc. results for a model representing a given period. A lot of interesting research results were obtained.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 2.

Tytuł:: Prognostics uncertainty reduction by right-time prediction of remaining useful life based on hidden Markov model and proportional hazard model
Autorzy:: Zhiyong, Gao
Jiwu, Li
Rongxi, Wang
Tematy:: RUL
uncertainty
right-time prediction
PHM
HMM; Pokaż więcej
Wydawca:: Polska Akademia Nauk. Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne PAN
Powiązania:: https://bibliotekanauki.pl/articles/1841790.pdf Link otwiera się w nowym oknie
Opis:: Uncertainty is a key problem in remaining useful life (RUL) prediction, and measures to reduce uncertainty are necessary to make RUL prediction truly practical. In this paper, a right-time prediction method is proposed to reduce the prognostics uncertainty of mechanical systems under unobservable degradation. Correspondingly, the whole RUL prediction process is divided into three parts, including offline modelling, online state estimating and online life predicting. In the offline modelling part, hidden Markov model (HMM) and proportional hazard model (PHM) are built to map the whole degradation path. During operation, the degradation state of the object is estimated in real time. Once the last degradation state reached, the degradation characteristics are extracted, and the survival function is obtained with the fitted PHM. The proposed method is demonstrated on an engine dataset and shows higher accuracy than traditional method. By fusing the extracted degradation characteristics, the obtained survival function can be basis for optimal maintenance with lower uncertainty.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 3.

Tytuł:: Prediction capabilities of the LSTM and Perceptron models based on the Day-Ahead Market on the Polish Power Exchange S.A.
Autorzy:: Ruciński, Dariusz
Tematy:: shallow networks
deep networks
Day-Ahead Market
MATLAB
Simulink environment
neural modeling
prediction time
electricity prices; Pokaż więcej
Wydawca:: Uniwersytet Przyrodniczo-Humanistyczny w Siedlcach
Powiązania:: https://bibliotekanauki.pl/articles/27323577.pdf Link otwiera się w nowym oknie
Opis:: The main purpose of the research was to examine the properties of models for two kinds of neural networks, a deep learning models in which the Long Short-Term Memory was chosen and shallow neural model in which the Perceptron Neural Network was chosen. The subject of the examination was the Day-Ahead Market system of PPE S.A. The article presents the learning results of both networks and the results of the predictive abilities of the models. The research was conducted based on data published on the Polish Stock Exchange for the 2018 year. The MATLAB environment was chosen as a tool for providing the examinations. The determination index (R2) and the mean square error (MSE) was adopted as the network evaluation criterion for the learning ability and for the prediction ability of both networks.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 4.

Tytuł:: Prognostics uncertainty reduction by right-time prediction of remaining useful life based on hidden Markov model and proportional hazard model
Autorzy:: Zhiyong, Gao
Jiwu, Li
Rongxi, Wang
Tematy:: RUL
uncertainty
right-time prediction
PHM
HMM; Pokaż więcej
Wydawca:: Polska Akademia Nauk. Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne PAN
Powiązania:: https://bibliotekanauki.pl/articles/1841766.pdf Link otwiera się w nowym oknie
Opis:: Uncertainty is a key problem in remaining useful life (RUL) prediction, and measures to reduce uncertainty are necessary to make RUL prediction truly practical. In this paper, a right-time prediction method is proposed to reduce the prognostics uncertainty of mechanical systems under unobservable degradation. Correspondingly, the whole RUL prediction process is divided into three parts, including offline modelling, online state estimating and online life predicting. In the offline modelling part, hidden Markov model (HMM) and proportional hazard model (PHM) are built to map the whole degradation path. During operation, the degradation state of the object is estimated in real time. Once the last degradation state reached, the degradation characteristics are extracted, and the survival function is obtained with the fitted PHM. The proposed method is demonstrated on an engine dataset and shows higher accuracy than traditional method. By fusing the extracted degradation characteristics, the obtained survival function can be basis for optimal maintenance with lower uncertainty.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 5.

Tytuł:: Solution implementation based on modified kalman filter for purpose of bus arrival time prediction
Implementacja filtru Kalmana do prognozowania czasu przybycia autobusów
Autorzy:: Ledziński, D.
Jezierski, M.
Marciniak, B.
Marciniak, T.
Tematy:: filtr Kalmana
prognozowanie czasu
Kalman filter
time prediction; Pokaż więcej
Wydawca:: Politechnika Bydgoska im. Jana i Jędrzeja Śniadeckich. Wydawnictwo PB
Powiązania:: https://bibliotekanauki.pl/articles/389834.pdf Link otwiera się w nowym oknie
Opis:: This paper describes use of Kalman's filter for prediction of time of arrival of bus. Kalman filter is recursive algorithm determining the minimum-variance estimate of the state vector of dynamic system, based on the measurement of inputs and outputs of the system. Three prediction algorithms used: difference algorithm, traditional Kalman filter and Kalman filter with changing weights of input data. Authors studied the bus arrival time predictions. Used for this purpose data send by radio from vehicles to prediction server. The smallest average prediction error obtained for the Kalman filter with variable weights.
W pracy przedstawiono zastosowanie filtru Kalmana do prognozowania czasu przybycia autobusów. Filtr Klamana to algorytm rekurencyjnego wyznaczania minimalno-wariancyjnej estymaty wektora stanu układu dynamicznego, na podstawie pomiaru wejść i wyjść tego układu. Zbadano trzy algorytmy predykcji: algorytm różnicowy, tradycyjny filtr Kalmana oraz filtr Kalmana ze zmiennymi współczynnikami. Autorzy badali odchylenie od prognozowanego czasu przyjazdu autobusów. Używano do tego celu danych przesyłanych drogą radiową z autobusów do serwera predykcji. Najlepsze wyniki uzyskano dla filtru Kalmana ze zmiennymi współczynnikami.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 6.

Tytuł:: Comparison of models for predicting thawing times of food - research note
Autorzy:: Goral, D.
Kluza, F.
Tematy:: household condition
food
potato
beef
thawing time prediction; Pokaż więcej
Wydawca:: Instytut Rozrodu Zwierząt i Badań Żywności Polskiej Akademii Nauk w Olsztynie
Powiązania:: https://bibliotekanauki.pl/articles/1372674.pdf Link otwiera się w nowym oknie
Opis:: Six most commonly known models for predicting thawing time of food: Nagaoka's et al., Cleland's et al., Calvelo's, Pham's and Piotrovich were compared when testing Tylose MH 1000 test substance, ground beef, and potato, and relative errors, regression and variance. The Cleland's et al. method, disregarding equivalent heat transfer dimensionality (EHTD) and mean conducting path (MCP) coefficient, was proved to be the best for predicting thawing time. The inclusion of EHTD and MCP to the computations by the Clelaçd's et al. method did not affect the results statistically significantly. The models of Piotrovich, Calvelo and Nagaoka et al. produced the results statistically different from real thawing times.
W pracy wykorzystano wybrane modele analityczno-empiryczne do obliczeniowego wyznaczania czasu rozmrażania żywności. Opierając się na dostępnych, wiarygodnych bazach wyników eksperymentalnych zrealizowano obliczenia dla warunków procesu charakteryzujących te bazy. Dokonano ogólnej analizy uzyskanych rezultatów wykorzystując metody statystyki matematycznej dla realizacji podstawowego celu pracy jakim była weryfikacja jakości modeli ocenianej wartością błędów obliczeń. Wyniki analizy statystycznej względnego błędu obliczeń (tabela 1) jak i analizy regresji obliczonego czasu rozmrażania względem czasu rzeczywistego (tabela 2, rysunek 1), a także badania wariancji (tabela 3) dowiodły, że trzy z sześciu testowanych modeli nie powinny być stosowane ze względu na wysokie błędy obliczeń. Jednocześnie, wyniki badań wskazują na model Clelanda i in. [1986] jako najdokładniejszy spośród badanych.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 7.

Tytuł:: Community Traffic: a technology for the next generation car navigation
Autorzy:: Dembczyński, K.
Gaweł, P.
Jaszkiewicz, A.
Kotłowski, W.
Kubiak, M.
Susmaga, R.
Wesołek, P.
Wojciechowski, A.
Zielniewicz, P.
Tematy:: community traffic
satellite car navigation
reliability analysis
travel time prediction; Pokaż więcej
Wydawca:: Polska Akademia Nauk. Instytut Badań Systemowych PAN
Powiązania:: https://bibliotekanauki.pl/articles/205706.pdf Link otwiera się w nowym oknie
Opis:: The paper presents the NaviExpert’s Community Traffic technology, an interactive, community–based car navigation system. Using data collected from its users, Community Traffic offers services unattainable to earlier systems. On the one hand, the current traffic data are used to recommend the best routes in the navigation phase, during which many potentially unpredictable traffic-delaying and traffic-jamming events, like unexpected roadworks, road accidents, or diversions, can be taken into account and thereby successfully avoided. On the other hand, a number of istinctive features, like immediate location of various traffic dangers, are offered. Using exclusively real-life data, provided by NaviExpert, the paper presents two illustrative case studies concerned with experimental evaluation of solutions to computational problems related to the community-based services offered by the system.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 8.

Tytuł:: Analysis of spatiotemporal data to predict traffic conditions aiming at a smart navigation system for sustainable urban mobility
Autorzy:: Kyriakou, Kalliopi
Lakakis, Konstantinos
Savvaidis, Paraskevas
Basbas, Socrates
Tematy:: spatio-temporal data
travel time prediction
smart navigation
urban mobility; Pokaż więcej
Wydawca:: Polska Akademia Nauk. Czytelnia Czasopism PAN
Powiązania:: https://bibliotekanauki.pl/articles/223718.pdf Link otwiera się w nowym oknie
Opis:: Urban traffic congestion created by unsustainable transport systems and considered as a crucial problem for the urbanised areas provoking air pollution, heavy economic losses due to the time and fuel wasted and social inequity. The mitigation of this problem can improve efficiency, connectivity, accessibility, safety and quality of life, which are crucial parameters of sustainable urban mobility. Encouraging sustainable urban mobility through smart solutions is essential to make the cities more liveable, sustainable and smarter. In this context, this research aims to use spatiotemporal data that taxi vehicles adequately provide, to develop an intelligent system able to predict traffic conditions and provide navigation based on these predictions. GPS (Global Positioning System) data from taxi are analysed for the case of Thessaloniki city. Trough data mining and map-matching process, the most appropriate data are selected for travel time calculations and predictions. Several algorithms are investigated to find the optimum for traffic states prediction for the specific case study concluding that ANN (Artificial Neural Networks) outperforms. Then, a new road network map is created by producing spatiotemporal models for every road segment under investigation through a linear regression implementation. Moreover, the possibility to predict vehicle emissions from travel times is investigated. Finally, an application with a graphical user interface is developed, that navigates the users with the criteria of the shortest path in terms of trip length, travel time shortest path and “eco” path. The outcome of this research is an essential tool for drivers to avoid congestion spots saving time and fuel, for stakeholders to reveal the problematic of the road network that needs amendments and for emergency vehicles to arrive at the emergency spot faster. Besides that, according to an indicator-based qualitative assessment of the proposed navigation system, it is concluded that it contributes significantly to environmental protection and economy enhancing sustainable urban mobility.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 9.

Tytuł:: Self-learning fuzzy predictor of exploitation system operating time
Autorzy:: Smoczek, J.
Szpytko, J.
Tematy:: operating time prediction
fuzzy logic
recursive least squares algorithm
overhead travelling crane; Pokaż więcej
Wydawca:: Instytut Techniczny Wojsk Lotniczych
Powiązania:: https://bibliotekanauki.pl/articles/247106.pdf Link otwiera się w nowym oknie
Opis:: The probability that a system is capable to operate satisfactorily significantly depends on reliability and maintainability of a system. The disadvantage of classic methods of system availability determining is that the probability of realizing by system tasks with expected quality depends on history of operational states and does not take into consideration actual operational conditions that have strong influence on risk-degree of down-time occurring, while the probability of degradation failure in exploitation system is a function of operating time and actual exploitation conditions. The problem of failures prediction can be solved by applying in diagnostics methods the intelligent computational algorithms. The intelligence computational methods enable to create the diagnosis tools that allow to formulate the prognosis of operating time of a system and predict of failure occurring based on the past and actual information about system's operational state. The paper presents the fuzzy logic approach to forecast the prognoses of the operating time of the exploitation system or its equipments according to the specified exploitation conditions that characterize the system exploitation state at the current time. The fuzzy system was based on the Takagi-Sugeno-Kang type fuzzy implications with singletons specifies in conclusions of rules. The fuzzy inference system input variables are the assumed parameters according to which the current exploitation state of the considered system can be evaluated.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 10.

Tytuł:: Application of long short term memory neural networks for GPS satellite clock bias prediction
Autorzy:: Gnyś, Piotr
Przestrzelski, Paweł
Tematy:: neural networks
LSTM
time series prediction
clock bias
GNSS
machine learning; Pokaż więcej
Wydawca:: Politechnika Gdańska
Powiązania:: https://bibliotekanauki.pl/articles/1987078.pdf Link otwiera się w nowym oknie
Opis:: Satellite-based localization systems like GPS or Galileo are one of the most commonly used tools in outdoor navigation. While for most applications, like car navigation or hiking, the level of precision provided by commercial solutions is satisfactory it is not always the case for mobile robots. In the case of long-time autonomy and robots that operate in remote areas battery usage and access to synchronization data becomes a problem. In this paper, a solution providing a real-time onboard clock synchronization is presented. Results achieved are better than the current state-of-the-art solution in real-time clock bias prediction for most satellites.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Informacja

Wyszukujesz frazę "prediction time" wg kryterium: Temat