Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Powiadomienia systemowe

Sesja wygasła!
Sesja wygasła!

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: K-nearest neighbour method

Sortuj według:

Ogranicz wyniki do:

An adaptive k nearest neighbour method for imputation of missing traffic data based on two similarity metrics

Wang Yang, Xiao Yu, Lai Jianhui, Chen Yanyan

Archives of Transport

2020

Vol. 54, iss. 2

59--73

Traffic flow is one of the fundamental parameters for traffic analysis and planning. With the rapid development of intelligent transportation systems, a large number of various detectors have been deployed in urban roads and, consequently, huge amount of data relating to the traffic flow are accumulatively available now. However, the traffic flow data detected through various detectors are often degraded due to the presence of a number of missing data, which can even lead to erroneous analysis and decision if no appropriate process is carried out. To remedy this issue, great research efforts have been made and subsequently various imputation techniques have been successively proposed in recent years, among which the k nearest neighbour algorithm (kNN) has received a great popularity as it is easy to implement and impute the missing data effectively. In the work presented in this paper, we firstly analyse the stochastic effect of traffic flow, to which the suffering of the kNN algorithm can be attributed. This motivates us to make an improvement, while eliminating the requirement to predefine parameters. Such a parameter-free algorithm has been realized by introducing a new similarity metric which is combined with the conventional metric so as to avoid the parameter setting, which is often determined with the requirement of adequate domain knowledge. Unlike the conventional version of the kNN algorithm, the proposed algorithm employs the multivariate linear regression model to estimate the weights for the final output, based on a set of data, which is smoothed by a Wavelet technique. A series of experiments have been performed, based on a set of traffic flow data reported from serval different countries, to examine the adaptive determination of parameters and the smoothing effect. Additional experiments have been conducted to evaluate the competent performance for the proposed algorithm by comparing to a number of widely-used imputing algorithms.

The application of the ‘K-nearest neighbour’ method to evaluate pressure loss in water supply lines

Biedugnis S., Czapczuk A.

Technical Transactions

2018

Vol. 115, iss. 1

141--149

Water supply systems are complex engineering structures; certainly, the most important part is the water distribution network. The design of this element requires calculations and many analyses to arrive at the best solution. The main task of the calculation is to determine the flow rates through pipes, to determine pressure losses, height of tanks, pressure required in the supply pumping station, pressure levels in the individual nodes of the network. Correct execution of the calculations requires careful evaluation of the results obtained and accuracy in the solutions applied. The issue of controlling the results of calculations is difficult to present in algorithmic form as these are mainly based on the experience and knowledge of the designer. Classes of decisions describing the problems of pressure loss in the pipework were established in order to evaluate the results of calculations. Numerical experiments were carried out in this paper to show how the ‘K-nearest neighbour’ method can be used to evaluate pressure loss in water pipes.

Systemy zaopatrzenia w wodę są skomplikowanymi układami obiektów inżynierskich, które pełnią różnorodną rolę w funkcjonowaniu całości. Najważniejszym elementem jest z pewnością system dystrybucji wody. W zawiązku z powyższym projektowanie systemów dystrybucji wymaga przeprowadzenia obliczeń oraz wielu analiz mających na celu doprowadzenie do najlepszego rozwiązania. Podstawowym celem obliczeń jest wyznaczenie natężeń przepływów przez przewody, określenie strat ciśnienia, wysokości zbiorników, wymaganego ciśnienia na zasilaniu oraz ciśnienia w poszczególnych węzłach sieci. Poprawne zrealizowanie obliczeń wymaga wnikliwej oceny uzyskanych wyników oraz poprawności zastosowanych rozwiązań. Zagadnienia kontroli rezultatów obliczeń trudno jest ująć w postaci algorytmicznej, gdyż oparte są głównie na doświadczeniu i wiedzy projektanta. Do oceny wyników obliczeń zdefiniowano klasy decyzyjne opisujące problemy związane ze stratami ciśnienia w przewodach. W pracy przeprowadzono eksperymenty numeryczne pokazujące, w jaki sposób może być zastosowana metoda K-najbliższych sąsiadów do oceny strat ciśnienia w przewodach wodociągowych.