Showing papers on "Occupancy published in 2022"

Review on occupancy detection and prediction in building simulation

Abstract: Energy simulation results for buildings have significantly deviated from actual consumption because of the uncertainty and randomness of occupant behavior. Such differences are mainly caused by the inaccurate estimation of occupancy in buildings. Therefore, the error between reality and prediction could be largely reduced by improving the accuracy level of occupancy prediction. Although various studies on occupancy have been conducted, there are still many differences in the approaches to detection, prediction, and validation. Reports published within this domain are reviewed in this article to discover the advantages and limitations of previous studies, and gaps in the research are identified for future investigation. Six methods of monitoring and their combinations are analyzed to provide effective guidance in choosing and applying a method. The advantages of deterministic schedules, stochastic schedules, and machine-learning methods for occupancy prediction are summarized and discussed to improve prediction accuracy in future work. Moreover, three applications of occupancy models—improving building simulation software, facilitating building operation control, and managing building energy use—are examined. This review provides theoretical guidance for building design and makes contributions to building energy conservation and thermal comfort through the implementation of intelligent control strategies based on occupancy monitoring and prediction.

A review on occupancy prediction through machine learning for enhancing energy efficiency, air quality and thermal comfort in the built environment

Abstract: The occupants' presence, activities, and behaviour can significantly impact the building's performance and energy efficiency. Currently, heating, ventilation, and air-conditioning (HVAC) systems are often run based on assumed occupancy levels and fixed schedules, or manually set by occupants based on their comfort needs. However, the unpredictability and variability of occupancy patterns can lead to over/under the conditioning of space when using such approaches, affecting indoor air quality and comfort. As a result, machine learning-based models and methodologies are progressively being used to forecast occupancy behaviour and routines in buildings, which may subsequently be used to aid in the design and operation of building systems. The present work reviews recent studies employing machine learning methods to predict occupancy behaviour and patterns, with a special focus on its related applications and benefits to building systems, improving energy efficiency, indoor air quality and thermal comfort. The review provides insight into the workflow of a machine learning-based occupancy prediction model, including data collection, prediction, and validation. An organised evaluation of the applicability or suitability of the different data collection methods, machine learning algorithms, and validation methods was carried out.

Hospital Occupancy and Emergency Department Boarding During the COVID-19 Pandemic

Abstract: This cross-sectional study uses national benchmarking data to evaluate hospital occupancy and emergency department boarding during the COVID-19 pandemic.

A three-year dataset supporting research on building energy management and occupancy analytics

Abstract: This paper presents the curation of a monitored dataset from an office building constructed in 2015 in Berkeley, California. The dataset includes whole-building and end-use energy consumption, HVAC system operating conditions, indoor and outdoor environmental parameters, as well as occupant counts. The data were collected during a period of three years from more than 300 sensors and meters on two office floors (each 2,325 m2) of the building. A three-step data curation strategy is applied to transform the raw data into research-grade data: (1) cleaning the raw data to detect and adjust the outlier values and fill the data gaps; (2) creating the metadata model of the building systems and data points using the Brick schema; and (3) representing the metadata of the dataset using a semantic JSON schema. This dataset can be used in various applications-building energy benchmarking, load shape analysis, energy prediction, occupancy prediction and analytics, and HVAC controls-to improve the understanding and efficiency of building operations for reducing energy use, energy costs, and carbon emissions.

Climate change winners and losers among North American bumblebees

Abstract: Mounting evidence suggests that climate change, agricultural intensification and disease are impacting bumblebee health and contributing to species’ declines. Identifying how these factors impact insect communities at large spatial and temporal scales is difficult, partly because species may respond in different ways. Further, the necessary data must span large spatial and temporal scales, which usually means they comprise aggregated, presence-only records collected using numerous methods (e.g. diversity surveys, educational collections, citizen-science projects, standardized ecological surveys). Here, we use occupancy models, which explicitly correct for biases in the species observation process, to quantify the effect of changes in temperature, precipitation and floral resources on bumblebee site occupancy over the past 12 decades in North America. We find no evidence of genus-wide declines in site occupancy, but do find that occupancy is strongly related to temperature, and is only weakly related to precipitation or floral resources. We also find that more species are likely to be climate change ‘losers’ than ‘winners’ and that this effect is primarily associated with changing temperature. Importantly, all trends were highly species-specific, highlighting that genus or community-wide measures may not reflect diverse species-specific patterns that are critical in guiding allocation of conservation resources.

Occupancy-aided ventilation for airborne infection risk control: Continuously or intermittently reduced occupancies?

Abstract: Ventilation is an important engineering measure to control the airborne infection risk of acute respiratory diseases, e.g., Corona Virus Disease 2019 (COVID-19). Occupancy-aided ventilation methods can effectively improve the airborne infection risk control performance with a sacrifice of decreasing working productivity because of the reduced occupancy. This study evaluates the effectiveness of two occupancy-aided ventilation methods, i.e., the continuously reduced occupancy method and the intermittently reduced occupancy method. The continuously reduced occupancy method is determined by the steady equation of the mass conservation law of the indoor contaminant, and the intermittently reduced occupancy method is determined by a genetic algorithm-based optimization. A two-scenarios-based evaluation framework is developed, i.e., one with targeted airborne infection risk control performance (indicated by the mean rebreathed fraction) and the other with targeted working productivity (indicated by the accumulated occupancy). The results show that the improvement in the airborne infection risk control performance linearly and quadratically increases with the reduction in the working productivity for the continuously reduced occupancy method and the intermittently reduced occupancy method respectively. At a given targeted airborne infection risk control performance, the intermittently reduced occupancy method outperforms the continuously reduced occupancy method by improving the working productivity by up to 92%. At a given targeted working productivity, the intermittently reduced occupancy method outperforms the continuously reduced occupancy method by improving the airborne infection risk control performance by up to 38%.

The value of seismic structural health monitoring for post-earthquake building evacuation

Abstract: Abstract In the aftermath of a seismic event, decision-makers have to decide quickly among alternative management actions with limited knowledge on the actual health condition of buildings. Each choice entails different direct and indirect consequences. For example, if a building sustains low damage in the mainshock but people are not evacuated, casualties may occur if aftershocks lead the structure to fail. On the other hand, the evacuation of a structurally sound building could lead to unnecessary financial losses due to business and occupancy interruption. A monitoring system can provide information about the condition of the building after an earthquake that can support the choice between several competing alternatives, targeting the minimization of consequences. This paper proposes a framework for quantifying the benefit of installing a permanent seismic structural health monitoring (S 2 HM) system to support building evacuation operations after a seismic event. Decision-makers can use this procedure to preventively evaluate the benefit of an SHM system and decide about the worthiness of its installation.

Impacts of the COVID‐19 pandemic on grocery retail operations: An analytical model

Abstract: Abstract The COVID‐19 pandemic has had profound effects on grocery retailers, forcing them to make many operational changes in response to public health concerns and the shift in customers' shopping behavior. Grocery retailers need to understand the impact of pandemic conditions on their operations, but the literature has not modeled and analyzed this issue. We bridge this gap through economic models that consider the documented changes in the customers' shopping behavior during the COVID‐19 pandemic, including less frequent in‐store shopping and bulk‐shopping tendency. We capture the impact of occupancy limitation guidelines on grocery retailers' service capacity, customers' shopping behavior, and, consequently, on the retailers' store traffic and profit. We find that though store occupancy limitations reduce the in‐store foot traffic (which helps with curbing the disease spread), interestingly, they do not necessarily result in a profit decline. Under occupancy limitations and when the retailer offers the delivery or curbside pickup service, our analyses highlight the externality impact of online customers on the shopping behavior of in‐store customers. When the retailer adds the delivery service, such externalities may increase the store traffic (higher infection risk inside the grocery store) and reduce the retailer's profit. When the retailer adds the curbside pickup instead, it has more control over the impact of externalities, which helps in lowering the store traffic and increasing the profit. Our results offer valuable insights into how retailers should regard occupancy limitations and health safety measures. Our results also highlight conditions under which various operating modes may help retailers reduce infection risk and achieve higher profit.

Assessment of ventilation rates inside educational buildings in Southwestern Europe: Analysis of implemented strategic measures

Abstract: The pandemic caused by COVID-19 has highlighted the need to ensure good indoor air quality. Public buildings (educational buildings in particular) have come under the spotlight because students, teachers and staff spend long periods of the day indoors. This study presents a measurement campaign for the assessment of ventilation rate (VR) and ventilation strategies in educational buildings in Southwestern Europe, Portugal and Spain. A representative sample of the teaching spaces of the Azurém Campus (Guimarães, Portugal) and the Fuentenueva Campus (Granada, Spain) have been analyzed. Natural ventilation is the predominant ventilation strategy in these spaces, being the most common strategy in educational buildings in Europe. VR was estimated under different configurations, using the CO2 decay method. Subsequently, the CO2 concentration was estimated according to occupancy and the probability of infection risk was calculated using the Wells-Riley equation. The obtained VR varied between 2.9 and 20.1 air change per hour (ACH) for natural cross ventilation, 2.0 to 5.1 ACH for single-sided ventilation and 1.8 to 3.5 for mechanically ventilated classrooms. Large differences in CO2 concentrations were verified, depending on the analyzed ventilation strategy, ranging from 475 to 3903 ppm for the different scenarios. However, the probability of risk was less than 1% in almost all of the classrooms analyzed. The results obtained from the measurement campaign showed that the selection of an appropriate ventilation strategy can provide sufficient air renewal and maintain a low risk of infection. Ventilation strategies need to be reconsidered as a consequence of the health emergency arising from the COVID-19 pandemic.

Parking Lot Occupancy Detection Using Hybrid Deep Learning CNN-LSTM Approach

Abstract: One of the common challenges facing the smart city is to predict the crowd movement patterns and their application in public transportations. Recently, deep learning, with its advantages, has made great breakthroughs in recognition and cognitive tasks. Based on these advantages, we propose a system to identify the occupied and vacant parking lots using a hybrid deep learning model. The Hybrid-Parking Lot Occupancy Detection (Hybrid-PLO) model combines the superior features of CNNs and LSTM deep learning methods. We did four experiments in two datasets: CRNPark and CRNPark-EXT and compared the results with other models. The proposed model gets the best results in comparison with the others.

Parking Occupancy Prediction Method Based on Multi Factors and Stacked GRU-LSTM

Abstract: With the development of society and the continuous advancement of urbanization, motor vehicles have increased rapidly, which exacerbates the imbalance between parking supply and demand. Therefore, it is very important to excavate knowledge from historical parking data and forecast the parking volume in different time periods so as to optimize parking resource utilization and improve traffic conditions. This paper proposes a new hybrid model that stacks gated recurrent unit (GRU) and long-short term memory (LSTM). The proposed stacked GRU-LSTM model combines LSTM’s advantage in prediction accuracy and GRU’s advantage in prediction efficiency, and uses multi factors, including occupancy, weather conditions and holiday, as input to predict parking availability. When compared against other predictive models such as stacked simple RNN, stacked LSTM-RNN, and stacked LSTM-Bi-LSTM, our experimental results indicate that the stacked GRU-LSTM model has better performance for parking occupancy prediction as it not only improves prediction accuracy, but also reduces prediction time.

A three-year dataset supporting research on building energy management and occupancy analytics

Abstract: This paper presents the curation of a monitored dataset from an office building constructed in 2015 in Berkeley, California. The dataset includes whole-building and end-use energy consumption, HVAC system operating conditions, indoor and outdoor environmental parameters, as well as occupant counts. The data were collected during a period of three years from more than 300 sensors and meters on two office floors (each 2,325 m2) of the building. A three-step data curation strategy is applied to transform the raw data into research-grade data: (1) cleaning the raw data to detect and adjust the outlier values and fill the data gaps; (2) creating the metadata model of the building systems and data points using the Brick schema; and (3) representing the metadata of the dataset using a semantic JSON schema. This dataset can be used in various applications-building energy benchmarking, load shape analysis, energy prediction, occupancy prediction and analytics, and HVAC controls-to improve the understanding and efficiency of building operations for reducing energy use, energy costs, and carbon emissions.

Uncertainty-driven Planner for Exploration and Navigation

Abstract: We consider the problems of exploration and pointgoal navigation in previously unseen environments, where the spatial complexity of indoor scenes and partial observability constitute these tasks challenging. We argue that learning occupancy priors over indoor maps provides significant advantages towards addressing these problems. To this end, we present a novel planning framework that first learns to generate occupancy maps beyond the field-of-view of the agent, and second leverages the model uncertainty over the generated areas to formulate path selection policies for each task of interest. For pointgoal navigation the policy chooses paths with an upper confidence bound policy for efficient and traversable paths, while for exploration the policy maximizes model uncertainty over candidate paths. We perform experiments in the visually realistic environments of Matterport3D using the Habitat simulator and demonstrate: 1) Improved results on exploration and map quality metrics over competitive methods, and 2) The effectiveness of our planning module when paired with the state-of-the-art DD-PPO method for the point-goal navigation task.