Completeness of data is vital for the decision making and forecasting on Building Management Systems (BMS) as missing data can result in biased decision making down the line. This study creates a guideline for imputing the gaps in BMS datasets by comparing four methods: K Nearest Neighbour algorithm (KNN), Recurrent Neural Network (RNN), Hot Deck (HD) and Last Observation Carried Forward (LOCF). The guideline contains the best method per gap size and scales of measurement. The four selected methods are from various backgrounds and are tested on a real BMS and metereological dataset. The focus of this paper is not to impute every cell as accurately as possible but to impute trends back into the missing data. The performance is characterised by a set of criteria in order to allow the user to choose the imputation method best suited for its needs. The criteria are: Variance Error (VE) and Root Mean Squared Error (RMSE). VE has been given more weight as its ability to evaluate the imputed trend is better than RMSE. From preliminary results, it was concluded that the best K‐values for KNN are 5 for the smallest gap and 100 for the larger gaps. Using a genetic algorithm the best RNN architecture for the purpose of this paper was determined to be GatedRecurrent Units (GRU). The comparison was performed using a different training dataset than the imputation dataset. The results show no consistent link between the difference in Kurtosis or Skewness and imputation performance. The results of the experiment concluded that RNN is best for interval data and HD is best for both nominal and ratio data. There was no single method that was best for all gap sizes as it was dependent on the data to be imputed.
MULTIFILE
In deze studie wordt het stadsdeel Oost van Amsterdam onderzocht. Het krachtwijkonderzoek is een onderdeel van een reeks van projecten van de afgelopen 4 jaar vanuit het onderzoek van het lectoraat Meervoudig Intensief Ruimtegebruik, binnen het onderzoeksprogramma ‘De Stad’ Domein Techniek van de Hogeschool van Amsterdam. Op basis van de aanduiding ‘Vogelaarwijk’ zijn intensive investeringen en sociaal economische programma’s uit gezet voor het verbeteren van dat type wijken. Het is wonderlijk te kunnen spreken van vitale steden terwijl tegelijk delen van die steden onder de categorie krachtwijk vallen. Tegelijk is uit recent evaluatieonderzoek gebleken dat met name die sociaal-economische investeringen nauwelijks een duurzame verbetering hebben opgeleverd. Wij vinden dat geen onlogische conclusie daar wij er door ons onderzoek van overtuigd zijn dat deze wijken grote fysiek ruimtelijke tekortkomingen hebben waardoor deze wijken uiteindelijk tot krachtwijk zijn geworden.
“Being completely circular by 2050” that is the goal for the Dutch economy. The transition towards the circular and biobased economy for energy and materials is essential to reach that goal. Sustainably produced materials based on renewable sources like biomass should be developed. One of the industries which recognizes the need for transition is the building industry. Currently, there are a couple of biobased building concepts available which claim to be more than 95% biobased. Since the current resins and adhesives, used to produce panel boards (like cross laminated timber (CLT)), are all produced synthetically, one of the missing links for the building industry to become 100% biobased are biobased resins and adhesives (and binders). In literature, there are several solutions described for resins/adhesives/binders which are based on the biomolecules lignin and cellulose which are abundantly present in fibrous biomass, but these products are not (yet) available on the market. At the same time, there are several fibrous biomass side streams available for which higher added value applications are demanded. These side streams are perfect sources of lignin and cellulose and are, therefore, very suitable sources to form the basis for biobased resins/adhesives/binders. However, they need modification to obtain the desired functionalities. The problem statement of this project, based on the request for valorization of fibrous side streams and the need for biobased building materials, is “How can we valorize fibrous biomass (side streams) into biobased building applications.” This problem statement is translated into the research goal. The aim of this research is to develop a biobased resin, adhesive or binder for the production of panel boards based on the side streams of fibrous/lignocellulosic biomass which meets the requirement of the building industry with respect to VOC emissions, and water resistance so that it contributes to a healthy living environment.
The reclaiming of street spaces for pedestrians during the COVID-19 pandemic, such as on Witte de Withstraat in Rotterdam, appears to have multiple benefits: It allows people to escape the potentially infected indoor air, limits accessibility for cars and reduces emissions. Before ordering their coffee or food, people may want to check one of the many wind and weather apps, such as windy.com: These apps display the air quality at any given time, including, for example, the amount of nitrogen dioxide (NO2), a gas responsible for an increasing number of health issues, particularly respiratory and cardiovascular diseases. Ships and heavy industry in the nearby Port of Rotterdam, Europe’s largest seaport, exacerbate air pollution in the region. Not surprisingly, in 2020 Rotterdam was ranked as one of the unhealthiest cities in the Netherlands, according to research on the health of cities conducted by Arcadis. Reducing air pollution is a key target for the Port Authority and the City of Rotterdam. Missing, however, is widespread awareness among citizens about how air pollution links to socio-spatial development, and thus to the future of the port city cluster of Rotterdam. To encourage awareness and counter the problem of "out of sight - out of mind," filmmaker Entrop&DeZwartFIlms together with ONSTV/NostalgieNet, and Rotterdam Veldakademie, are collaborating with historians of the built environment and computer science and public health from TU Delft and Erasmus University working on a spatial data platform to visualize air pollution dynamics and socio-economic datasets in the Rotterdam region. Following discussion of findings with key stakeholders, we will make a pilot TV-documentary. The documentary, discussed first with Rotterdam citizens, will set the stage for more documentaries on European and international cities, focusing on the health effects—positive and negative—of living and working near ports in the past, present, and future.
