An occupancy model makes use of data that are structured as sets of repeated visits to each of many sites, in order estimate the actual probability of occupancy (i.e., proportion of occupied sites) after correcting for imperfect detection using the information contained in the sets of repeated observations. We explore the conditions under which preexisting, volunteer-collected data from the citizen science project eBird can be used for fitting occupancy models. The data archived here are used to explore two ways in which the single-visit records could be used in occupancy models. First, we use empirical data contained within this archive to assess the potential for space-for-time substitution: aggregating single-visit records from different locations within a region into pseudo-repeat visits. The archived data are used to illustrate that the locations chosen for data collection by observers were not always representative of the habitat in the surrounding area, which would lead to biased...

AbstractHistorical museum records provide potentially useful data for identifying drivers of change in species occupancy. However, because museum records are typically obtained via many collection methods, methodological developments are needed in order to enable robust inferences. Occupancy-detection models, a relatively new and powerful suite of statistical methods, are a potentially promising avenue because they can account for changes in collection effort through space and time. We use simulated datasets to identify how and when patterns in data and/or modelling decisions can bias inference. We focus primarily on the consequences of contrasting methodological approaches for dealing with species' ranges and inferring species' non-detections in both space and time. We find that not all datasets are suitable for occupancy-detection analysis but, under the right conditions (namely, datasets that are broken into more time periods for occupancy inference and that contain a high fraction of community-wide collections, or collection events that focus on communities of organisms), models can accurately estimate trends. Finally, we present a case-study on eastern North American odonates where we calculate long-term trends of occupancy by using our most robust workflow. These results indicate that occupancy-detection models are a suitable framework for some research cases and expand the suite of available tools for macroecological analysis available to researchers, especially where structured datasets are unavailable., MethodsWe simulated multiple unstructured datasets to test the behavior of occupancy-detection models when applied to natural history museum data. Also included are data from the Global Biodiversity Information Facility for eastern North American odonates., Usage notesWe strongly recommend using a computing cluster to reproduce this analysis.

Data for review of occupancy estimtaion methods by Goldstein et al.

Please see the accompanying manuscript for full methodology. We will link to it when the manuscript is published.

This upload contains three datasets: "binary_scores_phase1.csv", "binary_scores_phase2.csv" and "modsel_results.csv". Each is a .csv file containing data from a survey of occupancy estimation practices. Each row represents one peer-reviewed paper, while each column represents a characteristic of the paper. Most columns are TRUE/FALSE, indicating whether or not the paper satisfied the relevant criterion.

One additional raw resource is provided. The .zip file "all_papers_2022-04-07.zip" contains 6 .xls files giving the full set of papers returned by the original Web of Science search. These are unmodified from the initial search.

All datasets contain the column:

ID - A unique ID for each paper; it most cases, a DOI. When Web of Science returned an invalid DOI, the ID is set to the paper title instead.

Note that all papers in Phase 2 are also in Phase 1, and all model selection papers are in both Phase 1 and Phase 2. The ID column can be used to join datasets.

Across both datasets, if all options in a category are FALSE or if a field is NA, that may mean that the review team was unable to determine what choices the authors made.

binary_scores_phase1.csv gives the results of Phase 2 of the review. It contains the following columns:

coll_newdata - Did the authors analyze newly collected data?

coll_existing - Did the authors analyze existing, previously published data?

coll_longterm - Did the authors analyze data produced by a long-term monitoring program?

coll_particip - Did the authors analyze participatory science data?

eco_frshwtr - Was the study system a freshwater ecosystem?

eco_marine - Was the study system a marine ecosystem?

eco_terra - Was the study system a terrestrial ecosystem?

region_USA - Were the data collected in the USA?

region_NoAm - Were the data collected in North America?

region_CenAm - Were the data collected in Central America?

region_SoAm - Were the data collected in South America?

region_Africa - Were the data collected in Africa?

region_Eur - Were the data collected in Europe?

region_Asia - Were the data collected in Asia?

region_Oceania - Were the data collected in Oceania?

framework_MLE - Did the authors estimate models in a maximum likelihood framework?

framework_ML - Did the authors estimate models in a machine learning framework?

framework_Bayes - Did the authors estimate models in a Bayesian framework?

gof_AUC - Did the authors use area-under-the-curve to evaluate their models?

gof_CV - Did the authors use cross validation to evaluate their models?

gof_PPC - Did the authors use poserior predictive checks to evaluate their models?

gof_parboot - Did the authors use parametric bootstrapping to evaluate their models?

gof_bayespv - Did the authors use Bayesian p-values to evaluate their models?

gof_any - Did the authors conduct any model checking?

taxon_mammal - Were some or all of the study species mammals?

taxon_bird - Were some or all of the study species birds?

taxon_herp - Were some or all of the study species herptiles (reptiles and amphibians)?

taxon_fish - Were some or all of the study species fish?

taxon_arthro - Were some or all of the study species arthropods?

taxon_othinv - Were some or all of the study species non-arthropod invertebrates?

soft_unmarked - Did the authors estimate models using the software unmarked?

soft_PRESENCE - Did the authors estimate models using PRESENCE-family software?

soft_MARK - Did the authors estimate models using MARK-family software?

soft_JAGS - Did the authors estimate models using JAGS-family software?

soft_lme4 - Did the authors estimate models using the software lme4?

soft_MaxEnt - Did the authors estimate models using the software MaxEnt?

soft_baseR - Did the authors estimate models using custom models written in base-R?

soft_NR - Did the authors fail to clearly report what software they used to estimate models?

soft_other - Did the authors estimate models using some other software?

nspecies - How many species did the authors study?

nspec_1 - Did the authors analyze data on exactly 1 species?

nspec_2 - Did the authors analyze data on exactly 2 species?

nspec_3_5 - Did the authors analyze data on 3-5 species?

nspec_6_10 - Did the authors analyze data on 6-10 species?

nspec_11_20 - Did the authors analyze data on 11-20 species?

nspec_20plus - Did the authors analyze data on more than 20 species?

compare_avg - Did the authors conduct model averaging?

compare_sel - Did the authors conduct model selection?

compare_other - Did the authors compare multiple models without averaging or selecting between them?

modsel_AICc - Did the authors use AICc in model selection or averaging?

modsel_AIC - Did the authors use AIC in model selection or averaging?

modsel_other - Did the authors use another information criterion in model selection or averaging?

dattype_DND - Were some or all of the data collected as detection-nondetection data?

dattype_count - Were some or all of the data collected as count data?

dattype_PO - Were some or all of the data collected as presence-only data?

dattype_other - Were some or all of the data collected in some other form?

survey_visual - Were some or all of the data collected using in-person visual surveys?

survey_audio - Were some or all of the data collected using in-person audio surveys?

survey_camtrap - Were some or all of the data collected using camera trap surveys?

survey_capture - Were some or all of the data collected using animal capture surveys?

survey_sign - Were some or all of the data collected using sign surveys?

survey_passaudio - Were some or all of the data collected using passive acoustic surveys?

survey_DNA - Were some or all of the data collected using eDNA surveys?

survey_other - Were some or all of the data collected using some other survey protocol?

modtype_SSOM - Did the authors analyze data with an SSOM?

modtype_DynOcc - Did the authors analyze data with a dynamic occupancy model?

modtype_GLM - Did the authors analyze data with a GLM?

modtype_cooccur - Did the authors analyze data with a multispecies co-occurrence model?

modtype_community - Did the authors analyze data with a multispecies community model?

modtype_MaxEnt - Did the authors analyze data with a MaxEnt model?

modtype_other - Did the authors analyze data with another model?

affil_acad - Did any of the authors have an academic affiliation?

affil_govt - Did any of the authors have a government affiliation?

affil_other - Did any of the authors have a private or NGO affiliation?

binary_scores_phase2.csv gives the results of Phase 2 of the review. It contains the following columns:

code_avail - Did we determine that the authors published their model fitting code?

data_avail - Did we determine that the authors published their data?

nsite - At how many sites were data collected?

nsite_lt20 - Were data collected at 20 or fewer sites?

nsite_21_50 - Were data collected at 20-50 sites?

nsite_51_100 - Were data collected at 51-100 sites?

nsite_101p - Were data collected at more than 100 sites?

time_pds - Over how many primary time periods (e.g. sampling seasons) were data collected?

time_pds_1 - Were data collected during a single time period?

time_pds_2_3 - Were data collected during 2-3 time periods?

time_pds_4p - Were data collected during 4 or more time periods?

nrepl - Roughly how many replicate surveys were collected per site?

nrepl_1 - Was only one replicate survey conducted per site?

nrepl_2_3 - Were 2-3 replicate surveys conducted per site?

nrepl_4_5 - Were 4-5 replicate surveys conducted per site?

nrepl_6p - Were 6 or more replicate surveys conducted per site?

window - What sampling window was used to discretize continuous-time sampling? (continuous-time studies only; otherwise NA)

det_window_lt_day - Was a sampling unit of less than one day used to discretize sampling?

det_window_1day - Was a sampling unit of one day used to discretize sampling?

det_window_2_6day - Was a sampling unit of 2-6 days used to discretize sampling?

det_window_7_14day - Was a sampling unit of l7-14 days used to discretize sampling?

det_window_15p_day - Was a sampling unit of 15 days or more used to discretize sampling?

homerange_is_bigger - Did the authors describe their survey area per site as bigger than the target species' home range?

homerange_is_smaller -Did the authors describe their survey area per site as smaller than the target species' home range?

informative_priors - Did the authors use informative priors in a Bayesian analysis?

time_in_mod_as_covar - Did the authors include primary time periods in the model as a covariate?

time_in_mod_separate_model - Did the authors use separate models to analyze data collected during different primary time periods?

time_in_mod_other - Did the authors include primary time periods in the model in some other way?

ncovar_det - How many covariates were included in the best model's detection

This data set includes certificates of occupancy issued through the New York City Department of Buildings' DOB NOW: Certificate of Occupancy module. This module was released in March of 2021, anbd from that point onward this data set should be utilized instead of the "DOB Certificate of Occupancy" data set. The data is collected because the Department of Buildings tracks Certificates of Occupancies issued. This data include items such as job filing name, job filing label, BIN, Address, and Certificate of Occupancy status, sequence, label, and issuance date.

"A Certificate of Occupancy (CO) states a legal use and/or type of permitted occupancy of a building. New buildings must have a CO, and existing buildings must have a current or amended CO when there is a change in use, egress or type of occupancy. No one may legally occupy a building until the Department has issued a CO or Temporary Certificate of Occupancy (TCO).

A CO confirms that the completed work complies with all applicable laws, all paperwork has been completed, all fees owed to the Department have been paid, all relevant violations have been resolved, and all necessary approvals have been received from other City Agencies. The Department issues a final CO when the completed work matches the submitted plans for new buildings or major alterations."

Occupancy Detection System for High Occupancy Toll (HOT) Lanes Market Outlook

The global market size for Occupancy Detection Systems for High Occupancy Toll (HOT) Lanes was valued at approximately USD 1.9 billion in 2023 and is projected to reach over USD 4.5 billion by 2032, growing at a compound annual growth rate (CAGR) of 10.2% during the forecast period. The growth of this market is primarily driven by the increasing need for efficient traffic management solutions, technological advancements in sensing technologies, and the global shift towards smart city initiatives. As urban centers expand and the demand for sustainable transportation solutions grows, the implementation of HOT lanes equipped with advanced occupancy detection systems becomes a crucial element in modernizing infrastructure and optimizing road usage.

One of the primary growth factors for the market is the rapid urbanization and population growth in metropolitan areas, which has escalated traffic congestion issues. To alleviate these traffic challenges, governments and transportation agencies are increasingly turning to HOT lanes, which require effective detection systems to monitor and manage vehicle occupancy. The demand for these systems is further propelled by the integration of intelligent transportation systems (ITS) that aim to improve the efficiency of existing road networks. As cities aim to enhance connectivity and reduce carbon footprints, the adoption of occupancy detection systems in HOT lanes is anticipated to witness significant growth.

Technological advancements play a pivotal role in the growth of the occupancy detection system market. Innovations in sensor technologies, such as infrared, ultrasonic, and video-based systems, have improved the accuracy and reliability of vehicle occupancy detection. These technologies allow for real-time data collection and analysis, enhancing the decision-making processes for traffic management and toll collection. Additionally, the integration of artificial intelligence and machine learning into detection systems has enabled more sophisticated analytics capabilities, further driving market growth. The continuous development in these technological domains is expected to create new avenues for market expansion.

The increasing focus on sustainability and reducing environmental impact also contributes to the market's growth. HOT lanes, supported by advanced occupancy detection systems, promote carpooling and the use of high-occupancy vehicles, which helps reduce the number of single-occupancy vehicles on roads, leading to decreased emissions and fuel consumption. This aligns with global environmental goals and regulatory mandates aimed at curbing pollution and promoting energy efficiency. As a result, the commitment to environmental sustainability is expected to bolster the demand for occupancy detection systems in HOT lanes.

Regionally, North America remains a dominant player in the market, driven by substantial investments in infrastructure development and the presence of advanced transportation systems. Europe follows closely, benefiting from stringent regulatory frameworks promoting smart transportation solutions. The Asia Pacific region is poised to exhibit significant growth due to rapid urbanization and government initiatives to improve transportation infrastructure. Meanwhile, Latin America and the Middle East & Africa are gradually adopting these technologies, with growth expected as infrastructure projects and smart city initiatives gain momentum. The regional dynamics underscore a diverse demand landscape, with North America and Europe leading in terms of market share.

Technology Analysis

The technology segment is critical in defining the market dynamics for occupancy detection systems in HOT lanes. Infrared sensors, a pivotal component of this segment, utilize thermal imaging to detect vehicle occupancy. These sensors are highly effective in low-light conditions and are relatively cost-effective, making them a popular choice among transportation agencies. Despite their advantages, infrared sensors can be sensitive to environmental factors, requiring periodic calibration and maintenance to ensure accuracy. However, technological advancements are continually enhancing their robustness and reliability, thus maintaining their relevance in the market.

Ultrasonic sensors represent another key technology within the market. These sensors work by emitting sound waves that bounce off objects and return, allowing the system to calculate the number of occupants in a vehicle. Ultrasonic sensors are known for their precision and are less af

The availability of the building’s operation data and occupancy information has been crucial to support the evaluation of existing models and development of new data driven approaches. This paper describes a comprehensive dataset consisting of indoor environmental conditions, Wi-Fi connected devices, energy consumption of end uses (i.e., HVAC, lighting, plug loads and fans), HVAC operations, and outdoor weather conditions collected through various heterogeneous sensors together with the ground truth occupant presence and count information for five rooms located in a university environment. The five rooms include two different-sized lecture rooms, an office space for administrative staff, an office space for researchers, and a library space accessible to all students. A total of 181 days of data was collected from all five rooms at a sampling resolution of 5 minutes. This dataset can be used for benchmarking and supporting data-driven approaches in the field of occupancy prediction and occupant behaviour modelling, building simulation and control, energy forecasting and various building analytics.

If you are interested in using this dataset, please cite our work as follows: Tekler, Zeynep Duygu, et al. "ROBOD, room-level occupancy and building operation dataset." Building Simulation. Tsinghua University Press, 2022. https://doi.org/10.1007/s12273-022-0925-9

This data collection provides information on the characteristics of a national sample of housing units, including apartments, single-family homes, mobile homes, and vacant housing units. Unlike previous years, the data are presented in nine separate parts: Part 1, Work Done Record (Replacement or Additions to the House), Part 2, Housing Unit Record (Main Record), Part 3, Worker Record, Part 4, Mortgages (Owners Only), Part 5, Manager and Owner Record (Renters Only), Part 6, Person Record, Part 7, Mover Group Record, Part 8, Recodes (One Record per Housing Unit), and Part 9, Weights. Data include year the structure was built, type and number of living quarters, occupancy status, access, number of rooms, presence of commercial establishments on the property, and property value. Additional data focus on kitchen and plumbing facilities, types of heating fuel used, source of water, sewage disposal, heating and air-conditioning equipment, and major additions, alterations, or repairs to the property. Information provided on housing expenses includes monthly mortgage or rent payments, cost of services such as utilities, garbage collection, and property insurance, and amount of real estate taxes paid in the previous year. Also included is information on whether the household received government assistance to help pay heating or cooling costs or for other energy-related services. Similar data are provided for housing units previously occupied by respondents who had recently moved. Additionally, indicators of housing and neighborhood quality are supplied. Housing quality variables include privacy of bedrooms, condition of kitchen facilities, basement or roof leakage, breakdowns of plumbing facilities and equipment, and overall opinion of the structure. For quality of neighborhood, variables include use of exterminator services, existence of boarded-up buildings, and overall quality of the neighborhood. In addition to housing characteristics, some demographic data are provided on household members, such as age, sex, race, marital status, income, and relationship to householder. Additional data provided on the householder include years of school completed, Spanish origin, length of residence, and length of occupancy. (Source: downloaded from ICPSR 7/13/10)

Please Note: This dataset is part of the historical CISER Data Archive Collection and is also available at ICPSR -- https://doi.org/10.3886/ICPSR02912.v2. We highly recommend using the ICPSR version as they made this dataset available in multiple data formats.

README.MD contains an overview of the R scripts.

Occupancy Monitoring Market Outlook

The global market size for occupancy monitoring was valued at USD 2.5 billion in 2023 and is projected to reach USD 6.8 billion by 2032, growing at a CAGR of 11.6% during the forecast period. The growth of this market is being driven by the increasing need for energy efficiency and space utilization optimization in commercial and industrial buildings.

One of the primary growth factors for the occupancy monitoring market is the rising demand for energy efficiency. As businesses and governments worldwide strive to reduce energy consumption and carbon footprints, occupancy monitoring systems have become essential tools. These systems help in optimizing heating, ventilation, and air conditioning (HVAC) systems, lighting, and other energy-consuming processes based on the actual occupancy data. This not only reduces energy consumption but also lowers operational costs, making it an attractive proposition for businesses.

Another significant growth factor is the increasing adoption of smart building technologies. With the rapid urbanization and the emergence of smart cities, there is a growing need for intelligent building solutions that can enhance the efficiency and productivity of spaces. Occupancy monitoring systems play a crucial role in smart buildings by providing real-time data on space utilization, which can be used to improve building management and enhance the overall experience of occupants. The integration of these systems with other IoT devices and building management systems is further propelling their adoption.

Furthermore, the COVID-19 pandemic has accelerated the adoption of occupancy monitoring solutions. With the need for social distancing and ensuring the safety of occupants in various establishments, these systems have gained prominence. They help in monitoring and controlling the number of people in a given space, ensuring compliance with safety regulations. This has led to increased investments in occupancy monitoring technologies, particularly in sectors such as healthcare, retail, and corporate.

From a regional perspective, North America holds the largest market share in the occupancy monitoring market, driven by the early adoption of advanced technologies and stringent energy efficiency regulations. Europe follows closely, with significant growth driven by the increasing focus on sustainability and smart building initiatives. The Asia Pacific region is expected to witness the highest growth rate during the forecast period, owing to rapid urbanization, infrastructure development, and the growing adoption of smart city projects in countries like China and India.

Component Analysis

The component segment of the occupancy monitoring market is categorized into hardware, software, and services. Hardware components include sensors, cameras, and other devices that detect and monitor occupancy. Software components involve the platforms and applications that analyze and present the data collected by the hardware. Services include installation, maintenance, and other support services provided by vendors.

Hardware components constitute a significant portion of the occupancy monitoring market. Sensors, in particular, are critical as they serve as the primary data collection points. Advanced sensors with features such as real-time monitoring, high accuracy, and low power consumption are driving the growth of this segment. Additionally, the increasing demand for wireless and battery-operated sensors is further propelling the market.

Software solutions for occupancy monitoring are gaining traction with the growing need for data analytics and insights. These solutions enable businesses to analyze occupancy trends, predict space utilization, and make informed decisions. The integration of AI and machine learning technologies in occupancy monitoring software is enhancing their capabilities, making them more efficient and accurate. Cloud-based software solutions are particularly popular due to their scalability, ease of deployment, and lower upfront costs.

Services play a crucial role in the successful implementation and operation of occupancy monitoring systems. Installation services ensure proper setup and integration of hardware and software components. Maintenance services are essential for the smooth functioning of these systems, as they involve regular checks, updates, and troubleshooting. Consulting services help businesses in selecting the right solutions and optimizing their use. The growing complexity of occupancy monitoring systems is dr

The emergence of continental to global scale biodiversity data has led to growing understanding of patterns in species distributions, and the determinants of these distributions, at large spatial scales. However, identifying the specific mechanisms, including demographic processes, and determining species distributions remains difficult, as large-scale data are typically restricted to observations of only species presence. New remote automated approaches for collecting data, such as automated recording units (ARUs), provide a promising avenue towards direct measurement of demographic processes, such as reproduction, that cannot feasibly be measured at scale by traditional survey methods. In this study, we analyze data collected by ARUs from 452 survey points across an approximately 1500 km study region to compare patterns in adult and juvenile distributions in the Great Horned Owl (Bubo virginianus). We specifically examine whether habitat associated with successful reproduction is the same as that associated with adult presence. We postulated that congruence between these two distributions would suggest that all areas of the species’ range contribute equally to maintenance of the population, whereas significant differences would suggest more specificity in the species’ requirements for successful reproduction. We filtered adult and juvenile calls of the species for manual review using automated classification and constructed single season occupancy models to compare land cover and vegetation covariates which significantly predicted presence of each life stage. We found that habitat use by adults was significantly predicted by increasing amounts of forest cover, reduced forest basal area, and lower elevations whereas juvenile presence was significantly predicted only by decreasing amounts of forest cover, a pattern opposite that of adults. These results show that presence of adult Great Horned Owls is not a sufficient proxy for locations at which reproduction occurs, and also demonstrate a highly scalable workflow that could be used for similar analyses in other sound-producing species. Methods Owl surveys: Nighttime autonomous acoustic recordings were collected from 452 survey locations across 1500 km of the eastern United States. Two Convolutional Neural Networks were developed to classify the adult song and juvenile begging call of the Great Horned Owl (Bubo virginianus). These classifiers were run on the recordings and the highest scoring ten five-second clips occurring on ten separate days at each survey location were extracted. These clips were manually reviewed by a human listener to ensure they contained the relevant owl sounds. Presence/absence was translated into 1/0 detection histories to be used in occupancy models. Covariates: GPS coordinates were collected at each survey location (these are not provided to protect landowner identity). National Land Cover Database information was extracted for the amount of forest and agricultural land cover within a 1750 m radius of each survey location for use as occupancy covariates. Tree basal area and < 10 cm DBH stem density were estimated for each survey location for use as occupancy covariates. The elevation at each survey location was extracted from the GMTED 2010 for use as occupancy covariates. Latitude was used as a detection covariate. All covariates were centered and scaled before deposit.

The global occupancy tracking market, valued at $1.21 billion in 2025, is poised for robust growth, projected to expand at a Compound Annual Growth Rate (CAGR) of 29.80% from 2025 to 2033. This significant expansion is driven by several key factors. Increasing demand for energy efficiency in commercial and residential buildings is a primary driver, as occupancy tracking systems optimize energy consumption by adjusting lighting, HVAC, and other systems based on real-time occupancy data. Furthermore, the rising adoption of smart building technologies and the growing need for enhanced security and safety are fueling market growth. The integration of occupancy tracking with Internet of Things (IoT) devices and advanced analytics platforms allows for data-driven insights into building usage patterns, informing better space planning and resource allocation. The market's segmentation reflects diverse application needs, with office buildings, retail spaces, and educational institutions representing significant market segments. The hardware segment, comprising sensors, detectors, and control units, currently holds a substantial market share, but the software and services segments are experiencing faster growth, driven by the increasing demand for sophisticated analytics and data management capabilities. Competitive landscape is marked by the presence of established players like Honeywell, Eaton, Schneider Electric, and Johnson Controls, alongside innovative technology providers. The market's growth trajectory is not without challenges. Initial investment costs for implementing occupancy tracking systems can be a significant barrier to entry for some businesses, particularly smaller organizations. Furthermore, concerns regarding data privacy and security need careful consideration to ensure the responsible deployment of these technologies. However, the long-term cost savings achieved through energy efficiency and improved operational efficiency are expected to outweigh initial investment costs, driving wider market adoption. The Asia-Pacific region is expected to witness significant growth due to increasing urbanization and rising investments in smart city initiatives. North America and Europe, while already relatively mature markets, will continue to demonstrate steady growth driven by ongoing technological advancements and upgrades within existing infrastructure. The forecast period will likely see the emergence of innovative solutions integrating AI and machine learning to enhance accuracy and provide deeper insights into building occupancy patterns. Recent developments include: May 2023 - Honeywell and Arcadis announced a partnership to offer tools and services to help optimize energy use and carbon emissions in commercial buildings globally. Honeywell offers smart-building technologies that utilize machine learning and artificial intelligence (ML/AI)-enabled software to enhance control systems with sensor-driven analytics, occupancy tracking, and predictive maintenance., March 2023 - AVUITY, a significant provider of innovative workplace technology and space utilization solutions, announced the release of its most recent line of sensors, which are expected to revolutionize the industry due to their exceptional accuracy and efficiency. The latest VuAI sensors incorporate cutting-edge technology and advanced algorithms to provide unrivaled real-time data collection and analysis precision. These cutting-edge sensors can detect occupancy and utilization as well as minute variations in temperature, light, noise, and humidity.. Key drivers for this market are: Increasing Need for Space Utilization and Optimization in Buildings, Rising Demand for Energy-efficient Devices. Potential restraints include: Increasing Need for Space Utilization and Optimization in Buildings, Rising Demand for Energy-efficient Devices. Notable trends are: Increase in Office Building Space to Drive the Building Type Segment.

The once-a-decade decennial census was conducted in April 2010 by the U.S. Census Bureau. This count of every resident in the United States was mandated by Article I, Section 2 of the Constitution and all households in the U.S. and individuals living in group quarters were required by law to respond to the 2010 Census questionnaire. The data collected by the decennial census determine the number of seats each state has in the U.S. House of Representatives and is also used to distribute billions in federal funds to local communities. The questionnaire consisted of a limited number of questions but allowed for the collection of information on the number of people in the household and their relationship to the householder, an individual's age, sex, race and Hispanic ethnicity, the number of housing units and whether those units are owner- or renter-occupied, or vacant. Results for sub-state geographic areas in New Mexico were released in a series of data products. These data come from the Demographic Profile 1 (DP-1) Summary File. The geographic coverage for DP-1 SF includes the state, counties, places (both incorporated and unincorporated communities), tribal lands, school districts, census tracts, and other areas. More detailed population and housing characteristics will be released in the summer of 2011 in the Summary File 1 data product. The data in these particular RGIS Clearinghouse tables are for New Mexico and all census tracts in the state. There are two data tables. One provides total counts of housing units, ocupied housing units and vacant housing units, while the other provides counts of total housing uings along with proportions of occupied and vacant housing units. These files, along with file-specific descriptions (in Word and text formats) are available in a single zip file.

ODDS Smart Building Depth Dataset

Introduction:

The goal of this dataset is to facilitate research focusing on recognizing objects in smart buildings using the depth sensor mounted at the ceiling. This dataset contains annotations of depth images for eight frequently seen object classes. The classes are: person, backpack, laptop, gun, phone, umbrella, cup, and box.

Data Collection:

We collected data from two settings. We had Kinect mounted at a 9.3 feet ceiling near to a 6 feet wide door. We also used a tripod with a horizontal extender holding the kinect at a similar height looking downwards. We asked about 20 volunteers to enter and exit a number of times each in different directions (3 times walking straight, 3 times walking towards left side, 3 times walking towards right side) holding objects in many different ways and poses underneath the Kinect. Each subject was using his/her own backpack, purse, laptop, etc. As a result, we considered varieties within the same object, e.g., for laptops, we considered Macbooks, HP laptops, Lenovo laptops of different years and models, and for backpacks, we considered backpacks, side bags, and purse of women. We asked the subjects to walk while holding it in many ways, e.g., for laptop, the laptop was fully open, partially closed, and fully closed while carried. Also, people hold laptops in front and side of their bodies, and underneath their elbow. The subjects carried their backpacks in their back, in their side at different levels from foot to shoulder. We wanted to collect data with real guns. However, bringing real guns to the office is prohibited. So, we obtained a few nerf guns and the subjects were carrying these guns pointing it to front, side, up, and down while walking.

Annotated Data Description:

The Annotated dataset is created following the structure of Pascal VOC devkit, so that the data preparation becomes simple and it can be used quickly with different with object detection libraries that are friendly to Pascal VOC style annotations (e.g. Faster-RCNN, YOLO, SSD). The annotated data consists of a set of images; each image has an annotation file giving a bounding box and object class label for each object in one of the eight classes present in the image. Multiple objects from multiple classes may be present in the same image. The dataset has 3 main directories:

1)DepthImages: Contains all the images of training set and validation set.

2)Annotations: Contains one xml file per image file, (e.g., 1.xml for image file 1.png). The xml file includes the bounding box annotations for all objects in the corresponding image.

3)ImagesSets: Contains two text files training_samples.txt and testing_samples.txt. The training_samples.txt file has the name of images used in training and the testing_samples.txt has the name of images used for testing. (We randomly choose 80%, 20% split)

UnAnnotated Data Description:

The un-annotated data consists of several set of depth images. No ground-truth annotation is available for these images yet. These un-annotated sets contain several challenging scenarios and no data has been collected from this office during annotated dataset construction. Hence, it will provide a way to test generalization performance of the algorithm.

Citation:

If you use ODDS Smart Building dataset in your work, please cite the following reference in any publications: @inproceedings{mithun2018odds, title={ODDS: Real-Time Object Detection using Depth Sensors on Embedded GPUs}, author={Niluthpol Chowdhury Mithun and Sirajum Munir and Karen Guo and Charles Shelton}, booktitle={ ACM/IEEE Conference on Information Processing in Sensor Networks (IPSN)}, year={2018}, }

Context

This data were collected and disseminated according to this publication: https://www.nature.com/articles/s41597-019-0273-5

All descriptors below are taken from this publication and are copyright of the authors.

Abstract

Adaptive interactions between building occupants and their surrounding environments affect both energy use and environmental quality, as demonstrated by a large body of modeling research that quantifies the impacts of occupant behavior on building operations. Yet, available occupant field data are insufficient to explore the mechanisms that drive this interaction. This paper introduces data from a one year study of 24 U.S. office occupants that recorded a comprehensive set of possible exogenous and endogenous drivers of personal comfort and behavior over time. The longitudinal data collection protocol merges individual thermal comfort, preference, and behavior information from online daily surveys with datalogger readings of occupants’ local thermal environments and control states, yielding 2503 survey responses alongside tens of thousands of concurrent behavior and environment measurements. These data have been used to uncover links between the built environment, personal variables, and adaptive actions, and the data contribute to international research collaborations focused on understanding the human-building interaction.

Background

Humans interact with the built environment in a variety of ways that contribute to both building energy use and environmental quality and thus warrant significant attention in the building design, operation, and retrofit processes. Occupants’ thermally adaptive behaviours such as adjusting thermostats and clothing, opening and closing windows and doors, operating personal heating and cooling devices, are strongly tied to total site energy consumed in residential and commercial buildings in the United States (U.S.). This dataset introduces longitudinal data from a one-year study of occupant thermal comfort and several related behavioural adaptations in an air-conditioned office setting in U.S. Offices. The primary objective of the data collection approach was to record a comprehensive range of exogenous and endogenous factors that may drive personal comfort and behaviour outcomes over time.

Methods

Longitudinal data on building occupant behavior, comfort, and environmental conditions were collected between July 2012 and August 2013 at the Friends Center office building in Center City Philadelphia, Pennsylvania, United States. Data collection proceeded in three stages:

1. Semi-structured interviews Semi-structured interviews identify aspects of behavior that are not yet well known or understood and provide a rich qualitative context for developing and interpreting responses from structured survey instruments. 32 interviews about thermal comfort and related behaviours were first conducted with office occupants from 7 air-conditioned buildings, ranging from aging to recently renovated, around the Philadelphia region

2. Site selection and subject recruitment for the longitudinal study Subject recruitment was initiated through an e-mail message sent to all employees in the Friends Center by its Executive Director. The following question areas were included: (a) demographic information, (b) office characteristics, (c) thermal comfort and preferences, (d) control options, (e) personal values, and f) typical work schedule (arrival, lunch, departure times).

3. Longitudinal survey and datalogger measurements. The final occupant sample participated in a series of subjective and objective measurements of thermal comfort, adaptive behavior, and related items. These measurements were carried via longitudinal online surveys, as well as through parallel datalogger and BAS measurements of the local environment and behavioural actions.

Technical Validation

Several measures were taken to ensure the validity of the collected data, following data collection guidance included in the final report for International Energy Agency Annex 66: Definition and Simulation of Occupant Behavior in Buildings. These measures include survey preparation phase, encourage high response rates, pilot studies, quality control, redundancy and comparison against expected conditions. Details for these measures can be found in the paper.

Usage Notes

• NaNs for certain variables do not generally imply missing data; rather, they indicate that the variable was not being measured for a given occupant at a given time stamp
• The variable “Occupant Number” refers to an occupant ID (e.g., a value between 1 and the 24 occupants who participated in the study); it does not refer to an occupancy (presence/absence) measurement.
• The variable “Occupancy 1” is an expected occupancy (presence/absence) value calculated across all time steps in the study based on the occupant’s responses about typical periods of occupancy on the background survey conducted before the start of the longitudinal measurements. The variable “Occupancy 2” is an expected occupancy state calculated across all time steps that fall under the two week daily surveying window, based on the time of arrival reported in the daily morning survey and recent departures from the office reported in the daily mid-day and afternoon surveys, as well as periods of prolonged absence reported on the retrospective surveys conducted after each two week period.

Please also consider citing this report describing this dataset in detail when using this data:

Schaffer, M., Jensen, R. L., Larsen, T. S., Marszal-Pomianowska, A., Rohde, L., Rubak, E., & Vera-Valdés, J. E. (2025). Residential Household Dataset: Occupancy, Water, and Electricity Data. Department of the Built Environment, Aalborg University. DCE Technical Reports No. 327 https://doi.org/10.54337/aau780546283

This dataset includes:

• One year of manually labelled daily occupancy and hourly water use for 10 single-family houses in Denmark.
  • Labelled by five independent annotators.
• Hourly occupancy, collected via diaries, and hourly water use for 8 residential buildings for 122 days.
  • For 7 of those, hourly electricity use is also available.
  • For 6 of those, information on whether the dishwasher or washing machine was used during the unoccupied period is available.
• All code was performed for processing and data collection.

Please see the reference for a detailed description, including a description of the file structure.
The final dataset is additionally provided as an extra folder (final_data.zip) for convenience.

This CD-ROM contains software that permits users to create their own tabulations from the 1999 American Housing Survey microdata. Data files include statistics on the physical and economic characteristics of housing from the 1999 American Housing Survey. Data include year structure built, type and number of living quarters, occupancy status, number of rooms, and property value. Additional data focus on kitchen and plumbing facilities, type of heating fuel used, source of water, sewage disposa l, heating and air-conditioning equipment, and major additions, alterations, or repairs made to the property. Also furnished is data relating to housing expenses including monthly mortgage or rent payments, utility costs, property insurance costs, and the amount of real estate taxes paid. Note to Users: This CD is part of a collection located in the Data Archive of the Odum Institute for Research in Social Science, at the University of North Carolina at Chapel Hill. The collection is located in Room 10, Manning Hall. Users may check the CDs out subscribing to the honor system. Items can be checked out for a period of two weeks. Loan forms are located adjacent to the collection.