In order to design and realise an efficient building refurbishment, it is necessary to carry out an exhaustive investigation of all solutions that form it, ie planimetric and volumetric changes, the elimination of building deterioration and obsolescence, the improvement of architectural and aesthetic appearance and indoor environmental quality, etc). The efficiency level of the considered building's refurbishment depends on many factors, including cost of refurbishment, annual fuel economy after refurbishment, tentative pay‐back time, harm to health of the materials used, aesthetics, maintenance properties, functionality, comfort, sound insulation and longevity, etc. Solutions of an alternative character allow for a more rational and realistic assessment of economic, ecological, legislative, climatic, social and political conditions, traditions and for better satisfaction of architectural, comfort, functional, maintenance and other customer's requirements. They also enable one to cut down on refurbishment costs. The selection of a refurbishment version mostly depends on the needs and existing financial capability of tenants. Based on an analysis of the existing neural networks, information, expert and decision support systems and in order to determine the most efficient versions of building refurbishment, a Multiple Criteria Decision Support Web‐Based System for Building Refurbishment (BR‐DSS) consisting of a database, database management system, model‐base, model‐base management system and a user interface was developed. The developed BR‐DSS and its practical application are described in the paper. Basing oneself on the developed system and database, it is possible to perform the alternative design of a building's refurbishment, multiple criteria analysis and make the selection of the most efficient versions, etc.
A Log-Based Anomaly Detection Method with Efficient Neighbor Searching and Automatic K Neighbor Selection
