Machine learning models have proven to be reliable methods in classification tasks. However, little research has been done on classifying dwelling characteristics based on smart meter & weather data before. Gaining insights into dwelling characteristics can be helpful to create/improve the policies for creating new dwellings at NZEB standard. This paper compares the different machine learning algorithms and the methods used to correctly implement the models. These methods include the data pre-processing, model validation and evaluation. Smart meter data was provided by Groene Mient, which was used to train several machine learning algorithms. The models that were generated by the algorithms were compared on their performance. The results showed that Recurrent Neural Network (RNN) 2performed the best with 96% of accuracy. Cross Validation was used to validate the models, where 80% of the data was used for training purposes and 20% was used for testing purposes. Evaluation metrices were used to produce classification reports, which can indicate which of the models work the best for this specific problem. The models were programmed in Python.
DOCUMENT
From the list of content: " Smart sustainable cities & higher education, Essence: what, why & how? Developing learning materials together; The blended learning environment; Teaching on entrepreneurship; Utrecht municipality as a client; International results; Studentexperiences; International relations; City projects in Turku, Alcoy and Utrecht ".
DOCUMENT
Uit het rapport: "In mei 2015 bestaat het Centre of Expertise Smart Sustainable Cities 1 jaar. De founding partners, Ballast Nedam, BJW, Hogeschool Utrecht, Movares, ROC Midden-Nederland, Royal HaskoningDHV, Uneto VNI en Utrecht Sustainability Institute, hebben in het afgelopen jaar hard gewerkt aan de organisatie en projecten. Medewerkers van bedrijven, studenten, docenten en onderzoekers werken samen in multidisciplinaire teams om met nieuwe kennis en inzichten concrete toepassingen te ontwikkelen. Dat is de kern van onze manier van werken. Vanuit een systeemperspectief verbinden we technologische oplossingen aan de vraagstukken van mens en maatschappij. Op de conferentie ‘Samen werken aan Smart Sustainable Cities: het Utrechtse model’ (hu-conferenties.nl) op 5 juni, laten we u graag zien hoe we dat in praktijk brengen. In deze uitgave vindt u een kleine greep uit de projecten van het Centre waarin u ziet wat de meerwaarde is van de verbinding beroepspraktijkonderzoek- onderwijs. Kijkt u voor alle projecten van het Centre of Expertise op onze website: www.smartsustainablecities.hu.nl/projecten. Nadia Verdeyen, Algemeen directeur Centre of Expertise Smart Sustainable Cities"
DOCUMENT
Uitwerking van het smart industry ecosysteem voor onderwijs en arbeid. Hierin aandacht voor Smart Industry en Formeel leren, Leven Lang Leren, flexibilisering en Learning by doing.
DOCUMENT
Author supplied: Within the Netherlands the interest for sustainability is slowly growing. However, most organizations are still lagging behind in implementing sustainability as part of their strategy and in developing performance indicators to track their progress; not only in profit organizations but in higher education as well, even though sustainability has been on the agenda of the higher educational sector since the 1992 Earth Summit in Rio, progress is slow. Currently most initiatives in higher education in the Netherlands have been made in the greening of IT (e.g. more energy efficient hardware) and in implementing sustainability as a competence in curricula. However if we look at the operations (the day to day processes and activities) of Dutch institutions for higher education we just see minor advances. In order to determine what the best practices are in implementing sustainable processes, We have done research in the Netherlands and based on the results we have developed a framework for the smart campus of tomorrow. The research approach consisted of a literature study, interviews with experts on sustainability (both in higher education and in other sectors), and in an expert workshop. Based on our research we propose the concept of a Smart Green Campus that integrates new models of learning, smart sharing of resources and the use of buildings and transport (in relation to different forms of education and energy efficiency). Flipping‐the‐classroom, blended learning, e‐learning and web lectures are part of the new models of learning that should enable a more time and place independent form of education. With regard to smart sharing of resources we have found best practices on sharing IT‐storage capacity among universities, making educational resources freely available, sharing of information on classroom availability and possibilities of traveling together. A Smart Green Campus is (or at least is trying to be) energy neutral and therefore has an energy building management system that continuously monitors the energy performance of buildings on the campus. And the design of the interior of the buildings is better suited to the new forms of education and learning described above. The integrated concept of Smart Green Campus enables less travel to and from the campus. This is important as in the Netherlands about 60% of the CO2 footprint of a higher educational institute is related to mobility. Furthermore we advise that the campus is in itself an object for study by students and researchers and sustainability should be made an integral part of the attitude of all stakeholders related to the Smart Green Campus. The Smart Green Campus concept provides a blueprint that Dutch institutions in higher education can use in developing their own sustainability strategy. Best practices are shared and can be implemented across different institutions thereby realizing not only a more sustainable environment but also changing the attitude that students (the professionals of tomorrow) and staff have towards sustainability.
DOCUMENT
Machine learning models have proven to be reliable methods in classification tasks. However, little research has been conducted on the classification of dwelling characteristics based on smart meter and weather data before. Gaining insights into dwelling characteristics, which comprise of the type of heating system used, the number of inhabitants, and the number of solar panels installed, can be helpful in creating or improving the policies to create new dwellings at nearly zero-energy standard. This paper compares different supervised machine learning algorithms, namely Logistic Regression, Support Vector Machine, K-Nearest Neighbor, and Long-short term memory, and methods used to correctly implement these algorithms. These methods include data pre-processing, model validation, and evaluation. Smart meter data, which was used to train several machine learning algorithms, was provided by Groene Mient. The models that were generated by the algorithms were compared on their performance. The results showed that the Long-short term memory performed the best with 96% accuracy. Cross Validation was used to validate the models, where 80% of the data was used for training purposes and 20% was used for testing purposes. Evaluation metrics were used to produce classification reports, which indicates that the Long-short term memory outperforms the compared models on the evaluation metrics for this specific problem.
DOCUMENT
Contribution to conference magazine https://husite.nl/ssc2017/ Conference ‘Smart Sustainable Cities 2017 – Viable Solutions’ The conference ‘Smart Sustainable Cities 2017 – Viable Solutions’ was held on 14 June 2017 in Utrecht, the Netherlands. Over 250 participants from all over Europe attended the conference.
DOCUMENT
Learning communities worden gezien als een effectieve manier om gezamenlijk te leren en ontwikkelen, werken, innoveren en te onderzoeken. Een manier die mensen verbindt die graag willen leren, ontwikkelen en werken over grenzen van hun organisatie en discipline, en aan een gezamenlijk doel. Het is meer dan af en toe samen komen en met elkaar en van gedachten wisselen, en kan bijdragen aan duurzame inzetbaarheid, persoonlijke ontwikkeling en groei. Maar hoe ziet dat er dan uit? In deze publicatie worden de belangrijkste bouwstenen en handvatten voor een krachtige learning community besproken, en verder toegelicht aan de hand van vier praktijkvoorbeelden: 1) Gas Erop! Learning communities in organisaties, 2) H2Hub Twente - Een learning community tussen meerdere organisaties, 3) Smart Solutions Semester - Een learning community in het onderwijs, en 4) Learning Communities bij HealthTech in Society. Over hoe deze learning communities zijn ontstaan en vormgegeven, hoe zijn gegroeid en wat ze hebben opgeleverd.
MULTIFILE
Deze bijdrage aan "Smart Humanity" (red. W. Bronsgeest en S. de Waart 2020) schetst een beeld van modellen die richting geven aan processen, organisatorische inrichting, en informatievoorziening. AI-toepassingen worden hierbij gezien als onderdeel van de informatievoorziening.
DOCUMENT
B4B is a multi-year, multi-stakeholder project focused on developing methods to harness big data from smart meters, building management systems and the Internet of Things devices, to reduce energy consumption, increase comfort, respond flexibly to user behaviour and local energy supply and demand, and save on installation maintenance costs. This will be done through the development of faster and more efficient Machine Learning and Artificial Intelligence models and algorithms. The project is geared to existing utility buildings such as commercial and institutional buildings.
DOCUMENT
