Occupancy Estimation Research Articles

A tapestry of habitats: exploring abundance and habitat preferences of the Northern Red Muntjac (Muntiacus vaginalis) across the Central Himalayan landscape

Abstract Understanding the occupancy and density estimate of Northern Red Muntjac (Muntiacus vaginalis) at a landscape scale is crucial due to their significant ecological impact on ecosystems, particularly as prey for large predators. This study employed a single-season site occupancy model to assess the occupancy and density of Northern Red Muntjac using camera traps in the east Sikkim and Darjeeling hills Central Himalayan landscape from 2018 to 2020. A total of 513 photo captures of Northern Red Muntjac were obtained from 3150 trap nights with a naive occupancy estimate of 0.64 for the Central Himalayan landscape. The top model revealed positive influences of broadleaved forest (β = 0.93 ± 0.26), mixed forest (β = 0.6 ± 0.47), and slope (β = 0.2 ± 0.24) on the occupancy probability, while elevation (β = −0.08 ± 0.24) and ruggedness (β = −0.53 ± 0.23) had negative influences. Similarly, broadleaved forest (β = 1.3 ± 0.24), mixed forest (β = 0.74 ± 0.39), and ruggedness (β = 0.62 ± 0.25) positively influenced the detection probability, whereas elevation (β = −0.3 ± 0.22) and slope (β = −1.13 ± 1.21) had negative effects. The study estimated a total abundance of 169.23 ± 20.77 individuals with a density of 0.33 per square kilometre in the landscape. This study is a pioneering effort and provides a foundation for future investigations into the occupancy and density estimate of Northern Red Muntjac in the Central Himalayas.

Efficient quality assurance and quality control for passive acoustic monitoring data: reducing and documenting false-positive and false-negative errors

ABSTRACT Autonomous Recording Units (ARUs) are widely used to survey for a variety of taxa. This survey method allows for high spatial and temporal coverage but will typically include identification errors that can bias estimates of occupancy. In some instances, verifying all individual detections is prohibitive. To direct verification effort, we developed a model to estimate the probability that transcribers would agree on an identification. Agreement probability was positively influenced by transcriber skill, identification confidence, species commonness and some song types. In contrast, agreement probability was lower when an acoustic signal was classified as a trill. We evaluated our model on independent data where all species detections were verified, and verification effort (time) was quantified. Our model performed well at predicting transcriber agreement on independent data (AUC = 0.71). We applied the model to randomised subsets of the independent data to compare the cost benefit of three approaches to verification under varying effort. We show how modelling probability of transcriber agreement can be used to more efficiently direct verification of species acoustic tags. Our approach could be adapted elsewhere to quantify and reduce species misidentifications in unverified passive acoustic monitoring data for either manual processing or detections from automated classifiers.

The Burnout PRedictiOn Using Wearable aNd ArtIficial IntelligEnce (BROWNIE) study: a decentralized digital health protocol to predict burnout in registered nurses

BackgroundWhen job demand exceeds job resources, burnout occurs. Burnout in healthcare workers extends beyond negatively affecting their functioning and physical and mental health; it also has been associated with poor medical outcomes for patients. Data-driven technology holds promise for the prediction of occupational burnout before it occurs. Early warning signs of burnout would facilitate preemptive institutional responses for preventing individual, organizational, and public health consequences of occupational burnout. This protocol describes the design and methodology for the decentralized Burnout PRedictiOn Using Wearable aNd ArtIficial IntelligEnce (BROWNIE) Study. This study aims to develop predictive models of occupational burnout and estimate burnout-associated costs using consumer-grade wearable smartwatches and systems-level data.MethodsA total of 360 registered nurses (RNs) will be recruited in 3 cohorts. These cohorts will serve as training, testing, and validation datasets for developing predictive models. Subjects will consent to one year of participation, including the daily use of a commodity smartwatch that collects heart rate, step count, and sleep data. Subjects will also complete online baseline and quarterly surveys assessing psychological, workplace, and sociodemographic factors. Routine administrative systems-level data on nursing care outcomes will be abstracted weekly.DiscussionThe BROWNIE study was designed to be decentralized and asynchronous to minimize any additional burden on RNs and to ensure that night shift RNs would have equal accessibility to study resources and procedures. The protocol employs novel engagement strategies with participants to maintain compliance and reduce attrition to address the historical challenges of research using wearable devices.Trial RegistrationNCT05481138.

Corridor-Level Auto Occupancy in Mobility Monitoring Efforts: A Crash-Based Approach

Vehicle occupancy (the number of persons per vehicle) is fundamental to evaluations of transportation system performance focused on the movement of people rather than solely vehicles. Historically, obtaining detailed estimates of occupancy has required manual (expensive) field data collection. This paper reports on a crash-based approach for estimating occupancy. Because some characteristics, such as the presence of multiple passengers aged 16 to 21, may affect the likelihood of crash involvement, the study examined ways to control possible crash bias using two methods. The first—heuristic bias correction, which entails synthesizing missing samples—is useful for smaller jurisdictions where there is no ground truth value readily available but an area-wide occupancy measure is needed. The second—statistical bias correction, which uses manual observations for calibration followed by the creation of a model—is suitable for obtaining occupancy at the corridor level. The approach is demonstrated with 12 years of fall and spring crash data for the Hampton Roads region of southeastern Virginia, U.S., representing 1.7 million people and 50,000 crashes. Testing showed estimated occupancies were within roughly 0.05 of true occupancy when corridor-specific calibration was performed. Further, the larger number of samples used for an area-wide occupancy means that heuristic bias correction is not always necessary: for cities with more than 200 samples, the difference between uncorrected and corrected occupancies was 0.02. For states that report the number of occupants for crashes with and without injury, this approach holds promise for estimating vehicle occupancy for both corridors and regions.

Ecologically informed priors improve Bayesian model estimates of species richness and occupancy for undetected species.

Detection error can bias observations of ecological processes, especially when some species are never detected during sampling. In many communities, the probable identity of these missing species is known from previous research and natural history collections, but this information is rarely incorporated into subsequent models. Here, I present prior aggregation as a method for including information from external sources in Bayesian hierarchical detection models. Prior aggregation combines information from multiple prior distributions, in this case, an ecologically informative, species-level prior, and an uninformative community-level prior. This approach incorporates external information into the model without sacrificing the advantages of modeling species in the context of the community. Using simulated data supplied to a multispecies occupancy model, I demonstrated that prior aggregation improves estimates of (1) metacommunity richness and (2) environmental covariates were associated with species-specific occupancy probabilities. When applied to a dataset of small mammals in Vermont, prior aggregation allowed the model to estimate occupancy correlates of the Eastern cottontail Sylvilagus floridanus, a species observed at several sites in the region but never captured. Prior aggregation can be used to improve the analysis of several important metrics in population and community ecology, including abundance, survivorship, and diversity.

SSIOE: Self-Supervised Indoor Occupancy Estimation for Intelligent Building Management

This paper aims to estimate indoor occupancy given the real-time observed signals from the existing sensors; next, as a practical application, we build a dynamic control schedule for energy saving based on the estimated indoor occupancy. However, several issues need to be addressed. First, it is impossible to train the model with rich labels due to the expensive labeling cost. Second, manual annotation of the continuous occupancy rate is complex. Third, the mapping relationship between sensor data and occupancy will change in the long run. In this paper, we proposed a new algorithm named Self-Supervised Indoor Occupancy Estimation (SSIOE) to overcome the challenges. Specifically, our training scheme aims to (I) generate a set of pseudo labels in a simple way to mark the time periods believed to be either in a high or low occupancy state and (II) utilize these sparse labels for training a network to infer the continuous occupancy ratio. By reformulating the problem as a Wasserstein-distance-like estimation, SSIOE is a novel learning-based method that can rely only on the weak/sparse labels of either “high-occupancy” or “low-occupancy” and learn to estimate the continuous occupancy ratio. Furthermore, to deal with the scarce annotation problem, we proposed a novel physical constraint loss to model the physical prior. (III) Last but not least, to strengthen the adaptability, we integrated Model-Agnostic Meta-Learning (MAML) to train the model for dynamic model updating. Experimental results show that SSIOE can provide reliable occupancy estimation and flexibly adapt to various control modes without retraining the model. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This paper is motivated by the real-time occupancy estimation problem, which is crucial for building management systems to arrange lighting and air conditioning. A dynamic schedule adapted to the occupancy would help balance the user’s comfort and energy saving; however, installing the occupancy sensors raises additional costs. Therefore, this paper proposes SSIOE, a label-free machine learning algorithm that can learn to estimate the continuous occupancy ratio given the sensor status in real time. Prior works trained upon supervised machine learning methods suffer from heavy manual annotation workload, while the unsupervised machine learning approaches fail to provide continuous occupancy estimation values. This paper addresses the above challenges by proposing a novel self-supervised training scheme. Preliminary experiments suggest that this approach is feasible to work in real-world buildings. However, it should be noted that the occupancy estimated by SSIOE is a ratio (0.0-1.0), which is relative to the maximum and minimum occupancy of the training data (or fine-tuning data). For example, if the maximum number of occupants in the training data is 200 and the minimum number of occupants is 50, then the estimated occupancy value of 1.0 is about 200 occupants, and the occupancy value of 0.0 is about 50 occupants. When the maximum and minimum occupants of the space change, the model needs to be updated to capture the new mapping of the estimated occupancy ratio to the number of occupants. In future research, we plan to further improve and simplify the adaptation ability of SSIOE by continuously and automatically updating the system with the latest collected as the system runs.

MACHINE LEARNING PRACTICES DURING THE OPERATIONAL PHASE OF BUILDINGS: A CRITICAL REVIEW

Machine Learning (ML) is gaining attention in civil engineering especially within operational phase of building life cycle. This phase is crucial for managing every energy aspect while ensuring occupant comfort. Previous ML experiments have explored occupant behavior, occupancy estimation, load prediction, defect detection, and Heating, Ventilation, and Air Conditioning (HVAC) system diagnostics. However, challenges such as ML transferability and limited literature on ML components for the operational phase hinder broader industry adoption. This critical review aims to assess the potential of ML in building operations, focusing on energy consumption, big data control, reinforcement learning, and thermal comfort modeling. By identifying knowledge gaps, the study recommends further research to leverage ML for sustainable energy consumption and occupant comfort. It highlights ML’s promising role in striking a balance between energy efficiency and occupant wellbeing.

A Comprehensive Framework for 3D Occupancy Estimation in Autonomous Driving

A Comprehensive Framework for 3D Occupancy Estimation in Autonomous Driving

АВТОМАТИЧНИЙ АНАЛІЗ ЗАВАНТАЖЕНОСТІ РАДІОЧАСТОТНОГО СПЕКТРА ТА СЕЛЕКЦІЯ СИГНАЛІВ

Constant increasing of radio-electronic devices number leads to an increase of spectrum occupancy and complication of radio-electronic environment. In such conditions, it is necessary to use automatic algorithms for prompt detection and selection of radio signals in radio monitoring systems. The purpose of the article is to develop algorithms and recommendations for their practical implementation to automate the process of radio frequency spectrum occupancy analysis and signal selection in a wide dynamic range with high occupancy of analyzed frequency band in conditions of a priori uncertainty of noise level. To achieve the stated goal were developed generalized algorithm for radio frequency spectrum analysis, algorithm of frequency domain processing and algorithm for frequency channels analysis. Examples of spectrum bands analysis with high occupancy and recommendations for developed algorithms implementation were represented. Depending on variability of noise power in analyzed frequency band an adaptive change of estimation time interval is provided, which will reduce the computational complexity. In conditions of no uniform noise level or a wide dynamic range of signals, it is proposed to use special test statistics to determine fullness of analyzed frequency channels. In the course of experimental studies, the analysis of recordings in frequency bands of 900 MHz, 1800 MHz and 2100 MHz was carried out. It was established that the developed algorithms provide a correct estimation of radio frequency spectrum occupancy and selection of signals with a dynamic range of at least 35 dB and occupancy of up to 92%. Developed algorithms do not require calibration of the equipment in case of fluctuations in characteristics of separate system elements and changes in radio-electronic environment and can be implemented in existing and perspective automatic radio monitoring systems. Keywords: radio frequency spectrum; spectrum occupancy; signal selection; test statistics; frequency channel.

Low-cost data-driven estimation of indoor occupancy based on carbon dioxide (CO2) concentration: A multi-scenario case study

Occupancy levels significantly influence HVAC system operation, making accurate occupancy prediction essential for the advancement of Occupant-Centered HVAC control. This study aims to develop a simple and effective occupant prediction model in buildings using low-cost indoor environmental sensors and artificial intelligence technology. In-situ measurements were taken in two university classrooms in South Korea over a three-month period, collecting data on indoor and outdoor temperature, humidity, and CO2 levels. Five machine learning algorithms, including Linear Regression (LR), Random Forest (RF), Gradient Boosting Regression (GBR), Multi-Layer Perceptron (MLP), and Long Short-Term Memory neural networks (LSTM), were applied to compare models of indoor occupancy. The results demonstrate that, among the five machine learning models evaluated, the LSTM model outperforms the others, achieving an RMSE of 3.43. This result indicates a close match between predicted and actual indoor occupancy based on CO2 concentration. The integration of a multivariate multi-step input method further enhances its accuracy, making it suitable for a variety of real-world scenarios in indoor occupancy prediction. This study reveals that using processed data as input sources leads to improved prediction performance for indoor occupant states. Importantly, this work does not infringe on biometric information, such as human image privacy, and relies on minimal measurement data. Furthermore, it not only emphasizes the model's feasibility and practicality in predicting indoor occupancy but also its potential in HVAC system automation, building energy conservation, and indoor environmental management. This study offers guidance and support for the advancement of smart cities and intelligent buildings in the future.

Unsupervised domain adaptation without source data for estimating occupancy and recognizing activities in smart buildings

Activities Recognition (AR) and Occupancy Estimation (OE) are topics of current interest. AR and OE help many smart building applications such as energy systems and provide good services for occupants. Prior research on AR and OE has typically focused on supervised machine learning methods. For a specific smart building domain, a model is trained using data collected from the current environment (domain). The created model will not generalize well when evaluated in a new related domain due to data distribution differences. Creating a model for each smart building environment is infeasible due to the lack of labeled data. Indeed, data collection is a tedious and time-consuming task. Unsupervised Domain Adaptation (UDA) is a good solution for the considered case. UDA solves the problem of the lack of labeled data in the target domain by allowing knowledge transfer across domains. Most of the previous research in UDA requires having access to source data while creating target models which leads to privacy problems. This work considers techniques that use only a trained source model instead of a huge amount of source data to make domain adaption. This research adapted and tested UDA methods called Source HypOthesis Transfer (SHOT), Higher-Order Moment Matching (HoMM), and Source data Free Domain Adaptation (SFDA) on smart building data. SHOT is a deep learning method that learns a feature encoding module for the target model to align the data representation of the target environment with the data representation of the source environment, and it freezes the hypothesis (classifier) of the source model. Data alignment is done using information maximization and self-supervised pseudo-labeling. HoMM is also a deep learning method, however, it freezes the feature encoding module, and it learns a classifier to perform data alignment. HoMM also performs pseudo-labeling to target samples to enhance data alignment. SFDA is a deep domain adaptation method that optimizes two losses to train the target model without using any source-labeled data. The target model updates its initialized weights from the source model by minimizing a first loss that uses pseudo labels of target samples using the pre-trained source model, and by minimizing a second loss that uses pseudo labels of target samples generated by the trainable target model. To prove the efficiency of SHOT, HoMM, and SFDA, this research tests them on AR and OE datasets for a different number of activities and levels of occupancy. The impressive obtained results, with scores up to 90% for OE and up to 97% for AR, show that the considered approaches can be used to transfer knowledge across different related domains.

Enhancing real-time nonintrusive occupancy estimation in buildings via knowledge fusion network

Real-time nonintrusive occupancy estimation can maximize the use of existing sensors to infer occupant information in buildings with the advantages of fewer privacy concerns and fewer extra device costs. Recently, many deep learning architectures have proven effective in estimating occupancy directly from raw sensor data. However, some handcrafted features manually extracted from statistical and temporal domains might convey additional information for occupancy estimation. In this study, a novel knowledge fusion network for nonintrusive occupancy estimation is proposed to integrate knowledge from two streams, i.e. automatic knowledge stream from a deep learning architecture and handcrafted knowledge stream from manual feature engineering. Moreover, four different fusion modules are investigated to optimize the design of the fusion network. To verify the effectiveness of the proposed network, experiments are conducted in a dataset from the ASHRAE Global Occupant Behavior Database, which is collected from an office space with records of indoor environment parameters, occupant-building interactions, and contextual information. The results demonstrate the superiority of the proposed fusion network, which outperforms five representative algorithms. Furthermore, the ablation study underscores the benefits of knowledge fusion and occupant-building interaction information, showing that the proposed fusion network can enhance the occupancy estimation accuracy by 3.47 % to 9.24 %.

Predicting Intensive Care Unit Patients’ Discharge Date with a Hybrid Machine Learning Model That Combines Length of Stay and Days to Discharge

Background: Accurate planning of the duration of stays at intensive care units is of utmost importance for resource planning. Currently, the discharge date used for resource management is calculated only at admission time and is called length of stay. However, the evolution of the treatment may be different from one patient to another, so a recalculation of the date of discharge should be performed, called days to discharge. The prediction of days to discharge during the stay at the ICU with statistical and data analysis methods has been poorly studied with low-quality results. This study aims to improve the prediction of the discharge date for any patient in intensive care units using artificial intelligence techniques. Methods: The paper proposes a hybrid method based on group-conditioned models obtained with machine learning techniques. Patients are grouped into three clusters based on an initial length of stay estimation. On each group (grouped by first days of stay), we calculate the group-conditioned length of stay value to know the predicted date of discharge, then, after a given number of days, another group-conditioned prediction model must be used to calculate the days to discharge in order to obtain a more accurate prediction of the number of remaining days. The study is performed with the eICU database, a public dataset of USA patients admitted to intensive care units between 2014 and 2015. Three machine learning methods (i.e., Random Forest, XGBoost, and lightGBM) are used to generate length of stay and days to discharge predictive models for each group. Results: Random Forest is the algorithm that obtains the best days to discharge predictors. The proposed hybrid method achieves a root mean square error (RMSE) and mean average error (MAE) below one day on the eICU dataset for the last six days of stay. Conclusions: Machine learning models improve quality of predictions for the days to discharge and length of stay for intensive care unit patients. The results demonstrate that the hybrid model, based on Random Forest, improves the accuracy for predicting length of stay at the start and days to discharge at the end of the intensive care unit stay. Implementing these prediction models may help in the accurate estimation of bed occupancy at intensive care units, thus improving the planning for these limited and critical health-care resources.

Effects of forest management on private lands in West Virginia on Cerulean Warblers (Setophaga cerulea) and the avian community

The USDA Natural Resources Conservation Service (NRCS) supports private lands conservation projects across the United States to benefit imperiled focal wildlife species using conservation practices to restore habitat. The Cerulean Warbler Appalachian Forestland Enhancement Project (CWAFEP) was initiated in 2015 to help stabilize or reverse Cerulean Warbler population declines by using forest management to create or enhance breeding habitat on private lands in Appalachian focal areas. We evaluated Cerulean Warbler occupancy on CWAFEP sites treated using NRCS conservation practices to inform adaptive management strategies. We also assessed associated forest focal species’ occupancy and species richness of avian guilds to evaluate the effects of conservation practice implementation on the avian community. We conducted point count surveys at 194 locations on 21 private properties enrolled in the CWAFEP in West Virginia during May – July 2019 and 2020. We compared occupancy among four treatments: reference, pre-treatment, 1-year post-treatment, and 2 – 4 years post-treatment sites. To examine how vegetation structure changes among treatments affected occupancy, we also collected and included vegetation variables. Cerulean Warbler occupancy estimates were not different among treatments, suggesting that post-treatment study sites surveyed did not achieve their goal of increasing Cerulean Warbler occupancy. Cerulean Warbler occupancy decreased by 91 % as elevation increased from 200 to 800 m and increased by 397 % as sapling cover increased from 0 to 100 %. Occupancy for three forest focal species (Blue-gray Gnatcatcher, Eastern Wood-pewee, and Scarlet Tanager) and species richness of four avian guilds also were not different among treatments. Thus, Cerulean Warbler occupancy and selected avian community demographics were not related to recent conservation practice implementation in the short-term (1 – 4 years post-treatment), but there are opportunities to improve NRCS conservation practice implementation for more effective Cerulean Warbler conservation. We suspect that the lack of differences in occupancy and species richness estimates was due to site selection related to ecoregion, small treatment areas, and challenges associated with private lands conservation efforts resulting in insufficient reduction in basal area. If NRCS conservation practices implemented through CWAFEP are going to help reverse Cerulean Warbler population declines, CWAFEP sites need to achieve the recommended basal area range of ∼ 9.2 – 20.7 m 2/ha (40 – 90 ft2/ac) during contract implementation. Our conclusions are critical to updating our knowledge for Cerulean Warbler best management practices and informing future regional conservation implementation.

Estimation of target occupancy in repeated dosing design studies using positron emission tomography: Biases due to target upregulation.

Positron emission tomography (PET) has become indispensable in the quantification of target engagement by brain targeting medications. The relationship between the drug plasma concentration (or drug dose administered) and target occupancy determined during a PET occupancy study has provided valuable information for the assessment of novel pharmaceuticals in the early phases of drug development. Such information is also critical for the understanding of the mechanisms of action and side-effect profile of approved medication commonly used in the clinic. Occupancy studies conducted following repeated drug dosing (RD) can produce systematic differences from those conducted following single drug dose (SD), differences that have not been adequately explored. We have hypothesised that when differences are observed between RD and SD studies, they are related to changes in target density induced by repeated drug accumulation. We have developed a modified occupancy model to account for potential changes in target density and tested it on a sample dataset. We found that target upregulation can parsimoniously explain the differences in drug affinity estimated in SD and RD studies. Our findings have implications for the interpretation of RD occupancy data in the literature and the relationship between specific target occupancy levels and drug efficacy and tolerability.

Occupancy-based one-year-ahead heating, ventilation, and air-conditioning electricity consumption optimization using machine learning

The world is increasingly urbanized. While, more than a half of its population lives in big cities, buildings are responsible for nearly the 40 % of the global annual energy consumption. Recent advances in smart grids and the high penetration of renewable energy sources have increased the need for long-term buildings' electricity consumption prediction to support operational decision making, demand response, and the installation of distributed generation systems. In addition, to meet international environmental goals, electric utilities usually offer financial incentives to reduce consumption levels. Heating, ventilation, and air-conditioning (HVAC) systems use the half of the buildings' energy to maintain users' comfort. In this scenario, predicting and optimizing their long-term electricity consumption without neglecting comfort conditions become vital to negotiate beneficious service-level agreements (SLAs) within the framework of demand-side management strategies. In this paper, we predict and optimize the one-year-ahead HVAC electricity consumption profile of a reference office building based on a machine learning approach. Although the occupants' number influences the HVAC electricity consumption, there has long been a lack of high-resolution, non-Boolean, long-term occupancy estimators. In this context, we first forecast the one-year-ahead occupants' number schedule and then use it, together with traditionally used historical weather data, to predict the one-year-ahead HVAC electricity consumption. The consumption profile is then optimized based on the estimated one-year-ahead occupants’ count schedule. The best results, obtained with a feedforward neural network, achieve 33 % annual electricity saving without neglecting summer cooling conditions in a hot zone like Miami, being efficient even in energetic-demanding scenarios such as extended working hours.

Occupancy of the Ethiopian endemic Moorland Francolin in pristine and degraded Afroalpine biome using a camera trap approach.

Occupancy modeling is an essential tool for understanding species-habitat associations, thereby helping to plan the conservation of rare and threatened wildlife species. The conservation status and ecology of several avian species, particularly ground-dwelling birds, are poorly known in Ethiopia. We used camera trap-based occupancy modeling to investigate habitat covariate influence on occupancy (Ψ) and detection probability (ρ) estimates of Moorland Francolins Scleroptila psilolaema from spatially replicated surveys across both relatively pristine and disturbed landscapes in the Afroalpine biome of Ethiopia. Model-averaged estimate of across all sites was 0.76 (SD = 0.28) and was 0.77 (SD = 0.13) in the pristine landscape. The of the species in the disturbed landscape was 0.56 (SD = 0.19) and was 0.48 (SD = 0.06). As hypothesized, based on our model-averaged beta coefficient estimates (βmean ± SE), predators significantly negatively influenced the occupancy of Moorland Francolins in pristine habitat. We also found a significant positive association of occupancy with herb species richness. Contrary to our prediction, distance to road significantly negatively influence the occupancy of the species, suggesting that occupancy probability was highest in proximity to roadsides and trails in the pristine habitat. There was no significant influence of habitat covariates on the occupancy of the species in the disturbed habitat. The most important covariates that significantly influence the detectability of the species in pristine habitat included sampling occasion and precipitation. The greater occupancy and detectability of this endemic species in the pristine habitat could be linked with the particular conservation status and management of this biodiversity hotspot in the central highlands of Ethiopia. Our results suggest that strict legal enforcement is required to sustainably preserve Moorland Francolins and the ecological integrity of the entire Afroalpine biome. We recommend using camera traps in order to develop realistic and effective conservation and management strategies for rare, sensitive, cryptic, and ground-dwelling animals in the region.

Occupancy estimation using IoT sensors and machine learning: Incorporating ventilation system operating state and preprocessed differential pressure data

Indoor occupancy should be measured to reduce energy consumption in buildings and predict infection risk. Various studies used machine learning to measure occupancy using carbon dioxide concentration, Wi-Fi probes, and camera image data. The carbon dioxide concentration depends on factors such as whether doors and windows are open and whether ventilation systems are running. Carbon dioxide concentrations fluctuate depending on variables, even with the same occupants in the room. We estimated the number of occupants using indoor environmental data for considering the changes in the carbon dioxide concentration caused by these variables. The differential pressure and operating state of a ventilation system were used as input variables for machine learning. Data were acquired from a living lab, which is used for seminars, lectures, etc. For up to 50 people. We used 85,366 data for training and 8418 data for validation without training. The accuracies of Artificial Neural Network (ANN), random forest, and support vector machine models were compared for different input variables. This study considered the carbon dioxide concentration fluctuation due to leakage as an input variable coupled with differential pressure sensor data. We compared whether the accuracy increases when differential pressure data are used. In the ANN model, the lowest root mean squared error is obtained when the carbon dioxide concentration, differential pressure data, and operating state of the ventilation system are used as input variables. In the future, we plan to increase the accuracy by utilizing various Internet of Things sensors and adopt diversify the input variables.

Semisupervised Learning-Based Occupancy Estimation for Real-Time Energy Management Using Ambient Data

Occupancy status information is essential for efficient energy management of deferrable and flexible electricity loads in both residential and commercial sectors. Motivated by the hardness to collect ground-truth occupancy data, we propose a new, semi-supervised learning based occupancy estimator, the Label-expanded Time-series Propensity Weighted Estimator (LTPWE), to improve the prediction accuracy using privacy-preserving ambient sensing data (in temperature, humidity, light, etc.), especially when the labelling frequency (the ratio of the labeled positive instances) is low. The proposed energy management scheme integrates the LTPWE occupancy estimator into a data-driven deep reinforcement learning algorithm, the Soft Actor Critic (SAC), to make real-time scheduling decisions without any prior knowledge on the dynamics of random renewable generation and electricity price. Simulation results on real-world datasets show that compared with multiple state-of-the-art baselines, the proposed energy management scheme can reduce the energy cost by 18.79-55.79% without sacrificing occupants’ thermal comfort.

Occupancy estimation with environmental sensors: The possibilities and limitations

Occupancy detection and estimation in buildings paves the way to improve the utilization of lighting and HVAC systems, induce energy savings and enhance the well-being of the occupants. This paper presents a comparative study of state-of-art machine learning techniques that solve two different occupancy monitoring problems using environmental sensor data. One is the regression problem that estimates the actual count of occupants while the other is the classification problem which estimates the level of occupancy (empty, sparse, full). The results of the best performing machine learning techniques that solve both problems for the open dataset from the University of Southern Denmark, Odense are presented to compare the accuracy of both approaches and the ease of implementation. The impact of CO2, temperature, and humidity features on the occupancy count/levels and detection accuracy (occupied versus unoccupied) are studied. Comprehensive analysis with different combinations of environmental features and other free features such as time-of-day along with different sampling techniques for training and testing are performed to understand how such models can be adapted for actual deployment. Our results indicate detection accuracy between 66% to 82% for different sampling schemes; with day-based sampling showing a better performance while random sampling generically showcasing lower accuracy (66.2%). The occupancy estimation (levels or counts) has accuracy in the range of 69% to 79% for random sampling and 71% to 80% for day-based sampling. Finally, results demonstrate that models based single environmental sensor data streams do not perform as well as the models with sensor fusion.