Wyniki wyszukiwania - BazTech

1

Predykcja zużycia ciepła w lokalu mieszkalnym na podstawie danych historycznych z ciepłomierzy mieszkaniowych

Bartnicki Grzegorz, Nowak Bogdan

Instal

|

2020

|

nr 12

15--20

PL

Koszty zakupu ciepła, paliwa gazowego i energii elektrycznej na potrzeby ogrzewania budynków wielorodzinnych dzielone są na poszczególne lokale mieszkalne i użytkowe. Do pomiaru zużycia ciepła do ogrzewania mieszkań stosowane są m.in. ciepłomierze. Urządzenie to może jednak ulec awarii, która uniemożliwia odczyt danych. W artykule opisano analizę możliwości wykorzystania danych historycznych do oszacowania udziału w kosztach ogrzewania całego budynku takiego lokalu, w którym stwierdzona została awaria ciepłomierza. Zaproponowano, aby w tym celu wyodrębnić na podstawie danych z poprzednich okresów rozliczeniowych grupę mieszkań jednorodnych z mieszkaniem z uszkodzonym ciepłomierzem. Zamiast oszacowania na podstawie uśrednionych wskaźników jednostkowych wyznaczonych w oparciu o pomiary dla wszystkich mieszkań, można wówczas wyznaczyć brakujący odczyt zużycia na podstawie wartości wyznaczonych dla tej grupy mieszkań jednorodnych. Artykuł opisuje praktyczne wykorzystanie tej metody, na przykładzie systemu zaopatrzenia w ciepło grupy budynków mieszkalnych na jednym z wrocławskich osiedli.

EN

The purchase costs of heat, gas fuel or electricity for the dwelling heating are divided into individual residential and commercial premises. For example, heat meters are used to measure the heat consumption for heating individual apartments. However, this device may be damaged and the data cannot be read. The article describes an analysis of the possibility of using historical data to estimate the share in the heating costs of this premise in which a heat meter failure has been found. For this purpose, it was proposed to distinguish a group of homogeneous flats from a flat with a damaged heat meter on the basis of data from previous billing periods. Instead of estimating on the basis of average unit indicators calculated on the basis of records from all apartments, it is possible to determine the missing consumption reading based on the values calculated for this group of homogeneous apartments. The article describes the practical use of this method, on the example of a heat supply system for a group of residential buildings in one of Wrocław’s housing estates.

2

Rule based networks : an efficient and interpretable representation of computational models

Liu H., Gegov A., Cocea M.

Journal of Artificial Intelligence and Soft Computing Research

|

2017

|

Vol. 7, No. 2

111--123

EN

Due to the vast and rapid increase in the size of data, data mining has been an increasingly important tool for the purpose of knowledge discovery to prevent the presence of rich data but poor knowledge. In this context, machine learning can be seen as a powerful approach to achieve intelligent data mining. In practice, machine learning is also an intelligent approach for predictive modelling. Rule learning methods, a special type of machine learning methods, can be used to build a rule based system as a special type of expert systems for both knowledge discovery and predictive modelling. A rule based system may be represented through different structures. The techniques for representing rules are known as rule representation, which is significant for knowledge discovery in relation to the interpretability of the model, as well as for predictive modelling with regard to efficiency in predicting unseen instances. This paper justifies the significance of rule representation and presents several existing representation techniques. Two types of novel networked topologies for rule representation are developed against existing techniques. This paper also includes complexity analysis of the networked topologies in order to show their advantages comparing with the existing techniques in terms of model interpretability and computational efficiency.

3

A Formalism for the Description of Protein Interaction Dedicated to Jerzy Tiuryn on the Occasion of His Sixty Birthday

Barbuti R., Dezani-Ciancaglini M., Maggiolo-Schettini A., Milazzo P., Troina A.

Fundamenta Informaticae

|

2010

|

Vol. 103, nr 1-4

1-29

EN

The Calculus of Looping Sequences is a formalism for describing evolution of biological systems by means of term rewriting rules. We propose to enrich this calculus by labelling elements of sequences. Since two elements with the same label are considered to be linked, this allows us to represent protein interaction at the domain level. Well-formedness of terms are ensured by both a syntactic constraint and a type system: we discuss the differences between these approaches through the description of a biological system, namely the EGF pathway.