1,721,135 research outputs found
A machine learning practice of predicting CO2 levels with the measurement data from university departmental offices
No full textIntroduction: In office spaces, users spend around 1/3 of their daily time, thus maintaining good air quality is an important aspect of keeping a healthy and efficient working environment. As office occupants usually have a regular daily and weekly schedule, machine learning can be a useful method to find the air quality pattern. Its result can benefit the indoor activities to improve the indoor activities and even further development on the smart buildings when the building infrastructure is ready.
In a department area of Politecnico di Milano, multiple low-cost air quality sensors have been installed since September 2023 which measure parameters mainly including temperature, humidity, radon, CO2, VOCs, air pressure and light. In this research, the CO2 data measured in the selected offices are used in this analysis practice.
This research aims to explore how machine learning can benefit long-term monitoring in improving air quality in the offices, taking CO2 as a practice, and how the existing monitoring system in the building can be improved to response to the changing indoor air quality (IAQ) level according to the model training process and the prediction performance.
Methodology: This research tried to apply the regression learner from MATLAB to train the models based on the data collected from the selected offices respectively in the past 1 year (from 2023 Sep 05 to 2024 Sep 05). The training used the basic information as a predictor including the date of the year, time of day, room code, and day of week. Meanwhile, the level of CO2 is selected as the response in training. After the comparison of the results in RMSE (Root-mean-square Error) with different models, the training eventually selected the bagged tree model in terms of its performance and the total training time.
The trained model then was optimized by the Experiment Manager tools from MATLAB with 50 trials by tuning the 4 hyperparameters of the bagged tree model, including method, number of learning cycles, learn rate and min leaf size. The one with the best performance in RMSE was selected in the validation session.
The validation was the comparison between the measured data from Sep 06 to Oct 30 2024 and the prediction from the trained and optimized model. The performance of validation and the model were interpreted in terms of its RMSE, residuals and Coefficient of determination (R2).
Result: The model of rooms has RMSE results between 14.95 to 16.09 after the training and optimization varying from different rooms. Then, in comparisons between the original and model predicted CO2 values, the predicted CO2 levels basically follow the schedule of the rooms, with similar variation rates at the beginning and end of the working hours. This means that the model is able to catch the features of CO2 level variations in the selected offices based on the historical data.
However, the predictions show differences from the measurements with the dates as predictors in 2024, with RMSE from 100.52 to 107.74. These differences lay in the daily variations, especially the peaks of several days are much higher than the prediction results. These are due to several realistic reasons such as the number of occupants in 2024 being more than in 2023 and the schedule of occupants changing each week, etc. which are not included in monitoring and training.
Conclusion: In general, the performance of this model currently is limited by the predictor parameters from the historical data monitored in the past 1 year, but it can already be useful in reflecting the CO2 variations in these offices. The training process also shows the 3 types of information that could be added to the monitoring system to help benefit and respond to the IAQ level changes more smoothly and accurately, including the daily number of people, the occupancy schedule, and the ventilations by window operations.
During this training, it can be found that, in the model training for CO2 level in these offices, the number of occupants and their ventilation behaviours are the 2 influential factors that are important but not measured in the existing monitoring system, especially the number of occupants which dynamic during the year and highly related to the CO2 increasing rate and the peak level. The number of occupants and the schedule can be added as one monitoring parameter in the future to make the prediction more accurate.
On the other hand, other factors such as the dimensions of the room are less influential and can be simulated based on the calculation with the CO2 historical records and the number of occupants.
In addition, this method can be used in spaces with more occupants, such as classrooms, open offices or shopping centres with large numbers of occupants by minimizing the influence of the changes on the average number of occupants on the CO2 prediction
UN MODELLO DI CONOSCENZA PER LA RAPPRESENTAZIONE DEL PATRIMONIO COSTRUITO
No full textNell’ambito del processo edilizio dei beni culturali, inteso come un sistema strutturato di attività finalizzate alla ricerca, la conservazione e la gestione dei beni architettonici, tutte le operazioni compiute dai diversi attori coinvolti sono profondamente influenzate dalla conoscenza derivata da una fase complessa di documentazione e l'eventuale mancanza o errata interpretazione dei dati possono portare a decisioni sbagliate e danni anche irreparabili al manufatto. Nella pratica corrente, la rappresentazione e la gestione della conoscenza legata al patrimonio costruito hanno mostrato diverse limitazioni per la difficoltà di trattare grandi quantità di dati estremamente eterogenei.
Su tali basi, la presente ricerca ha come obbiettivo quello di estendere gli approcci e le tecnologie proprie del web semantico alla modellazione della conoscenza relativa al patrimonio architettonico al fine di fornire una rappresentazione integrata e multidisciplinare del manufatto e delle conoscenze necessarie per supportare qualsiasi decisione o qualsiasi attività di indagine, interpretazione, intervento e gestione.
Per questo scopo, è stato sviluppato un sistema basato su ontologie, per rappresentare la conoscenza relativa al manufatto e suoi contesti attraverso la formalizzazione di entità specifiche per il dominio d’interesse e delle relazioni che intercorrono tre di esse. Questo approccio permette di includere in un modello coerente ed omogeneo sia le conoscenze raccolte attraverso campagne d’indagine dirette sia quelle non direttamente deducibili dal manufatto ma riconducibili ad esso (ad es. informazioni storiche o di contesto).
Infine, il modello è stato applicato al processo di ricerca e documentazione del tempio romano di Castore e Polluce a Cori e dell’Oratorio di San Saba a Roma. In questi casi di studio, la conoscenza relativa ai manufatti architettonici è stata formalizzata attraverso l’editor di ontologie Protégé, mentre è stato utilizzato un ambiente BIM per fornire una rappresentazione schematica delle sue caratteristiche fisiche.
L'introduzione di questo ambiente di modellazione vuole migliorare l’attuale rappresentazione e gestione delle informazioni nei processi legati al patrimonio costruito, passando da un approccio document-based a uno model-based. Come risultato, tutti i dati, le informazioni, e le conoscenze relative ad un edificio storico, raccolte e documentate da diverse attività di indagine saranno integrati in un unico modello esaustivo e sempre aggiornato.
Questa esperienza ha illustrato le potenzialità dell'approccio proposto per documentare e analizzare in modo innovativo l'ambiente storico costruito e per sostenere tutte le indagini, le interpretazioni e le attività di intervento ad esso correlate
Ospedali: edifici complessi
No full textTra i manufatti architettonici "complessi e strategici" l'ospedale svol-ge indubbiamente un ruolo determinante nello sviluppo della società in-tegrata, per le particolari eccezionalità spaziali e funzionali che impon-gono sintesi e soluzioni innovative alle concezioni distributive, costrutti-ve, tecnologiche, igienico-sanitarie e gestionali.
Negli ultimi anni si sono infatti consolidati nuovi concetti di salute e di benessere, fortemente influenzati dai progressi scientifici in ambito medico, nonché da una maggiore attenzione alle relazioni tra malattia, contesto ambientale e sfera sociale. Nel quadro di questi nuovi orienta-menti l’intero sistema socio-sanitario si colloca quindi al centro di un processo di trasformazione che riguarda sia gli aspetti gestionali che gli aspetti tecnologici e progettuali. A fronte del livello di obsolescenza e inadeguatezza di ospedali anche di recente realizzazione, una fase di adeguamento e ammodernamento risulta indispensabile quanto partico-larmente delicata, soprattutto nel momento in cui la decisione comporta ingenti spese di ristrutturazione o la realizzazione di nuovi edifici in gra-do di rispondere al meglio alle nuove emergenti esigenze.
Si va quindi sviluppando una crescente attenzione all’architettura ospedaliera, al rapporto fra servizi e il territorio e alla definizione di soluzioni progettuali incentrate sulla funzionalità e sull’efficienza, ma an-che sull’umanizzazione e sul comfort, confermando l’importanza della centralità dell’utente nella progettazione dell’organismo edilizio e della rete del servizio offerto
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Between Research and Practice: a Literature Review Protocol for examining practical implications of EBD Research studies
No full textThe importance of the design of healthcare facilities stems from the impact that the physical
attributes of healthcare settings can have on patients' health outcomes. Decades of research
since Ulrich's groundbreaking 1984 study have shown that the built environment of healthcare
facilities significantly influences numerous health outcomes for patients, visitors, staff and or-
ganisations. While Evidence-Based Design (EBD) studies offer many potential benefits for de-
signing healthcare facilities, the field is sometimes criticised for having a narrow focus and
offering isolated, fragmented and sometimes conflicting results that are difficult to understand
and apply in design practice. To bridge this gap, the researchers often provide implications of
their results for practice in their published articles. This study aims to examine these practical
implications in published EBD research articles in the last ten years. The presented research
protocol outlines the steps that will be adopted to achieve this. The aim of this approach is
threefold: (1) to classify and evaluate the implications for practice presented in research arti-
cles based on built environment variables and outcomes, (2) to provide a synthesis of research
implications for practice to be used by all involved in the process of planning healthcare facil-
ities and (3) to detect research trends during one decade of EBD research. Health Environ-
ments Research & Design (HERD) Journal is the starting point of this investigation as it in-
cludes articles strictly related to healthcare environment design research and requires all au-
thors to submit a bulleted list of implications for practice. The resulting review is expected to
provide insights into the recommendations for practice proposed by EBD researchers based on
their research results
The impact of COVID-19 on healthcare facilities for older adults
No full textIntroduction Covid-19 drown the attention of researchers to health problems in nursing homes and healthcare facilities for older adults. Often, the elderly who live in those settings often have high levels of impairment and chronic illness, so they are more susceptible to coronavirus. Therefore, a Systematic Literature Review was conducted to explore which built environment mostly impacted the health and well-being of residents during the pandemic period. Purpose/Methods Relevant articles were identified by searching on the SCOPUS and Web of Science databases. Studies based on the impact of the built environment on elderly residents living in healthcare facilities during the COVID-19 period were included. Articles focus solely on the clinic aspect was excluded. Results The initial research finds out 197 papers, and, after the application of eligibility criteria and the full-text reading, 13 studies were selected. Almost two-thirds (8) are theoretical studies. Physical health like infection control has emerged as the most common concern (11) as well as mortality. Built environment factors, such as location, size of the facility, type of rooms, number of residents, air quality, temperature, localization of office space, were also presented as risk factors for the health and well-being of users. Conclusions The research shows a lack of studies about mental health, while 11 studies focus on physical health, only 2 mentioned mental perspective, even if it is one of the main factors influencing the well-being of vulnerable people, and consequently, more research with regards to emergency pandemic need to be explored
- …
