An official website of the United States government
Opportunistic Physics-mining Transfer Mapping Architecture (OPTMA) is a hybrid architecture that combines fast simplified physics models with neural networks in order to provide significantly improved generalizability and explainability compared to pure data-driven machine learning (ML) models. However, training OPTMA remains computationally inefficient due to its dependence on gradient-free solvers or back-propagation with supervised learning over expensively pre-generated labels. This paper presents two extensions of OPTMA that are not only more efficient to train through standard back-propagation but are readily deployable through the state-of-the-art library, PyTorch. The first extension, OPTMA-Net, presents novel manual reprogramming of the simplified physics model, expressing it in Torch tensor compatible form, thus naturally enabling PyTorch's in-built Auto-Differentiation to be used for training. Since manual reprogramming can be tedious for some physics models, a second extension called OPTMA-Dual is presented, where a highly accurate internal neural net is trained apriori on the fast simplified physics model (which can be generously sampled), and integrated with the transfer model. Both new architectures are tested on analytical test problems and the problem of predicting the acoustic field of an unmanned aerial vehicle. The interference of the acoustic pressure waves produced by multiple monopoles form the basis of the simplified physics for this problem statement. An indoor noise monitoring setup in motion capture environment provided the ground truth for target data. Compared to sequential hybrid and pure ML models, OPTMA-Net/Dual demonstrate several fold improvement in performing extrapolation, while providing orders of magnitude faster training times compared to the original OPTMA.
more »
« less
Novel Physics-Based Machine-Learning Models for Indoor Air Quality Approximations
Cost-effective sensors are capable of real-time capturing a variety of air quality-related modalities from different pollutant concentrations to indoor/outdoor humidity and temperature. Machine learning (ML) models are capable of performing air-quality "ahead-of-time" approximations. Undoubtedly, accurate indoor air quality approximation significantly helps provide a healthy indoor environment, optimize associated energy consumption, and offer human comfort. However, it is crucial to design an ML architecture to capture the domain knowledge, so-called problem physics. In this study, we propose six novel physics-based ML models for accurate indoor pollutant concentration approximations. The proposed models include an adroit combination of state-space concepts in physics, Gated Recurrent Units, and Decomposition techniques. The proposed models were illustrated using data collected from five offices in a commercial building in California. The proposed models are shown to be less complex, computationally more efficient, and more accurate than similar state-of-the-art transformer-based models. The superiority of the proposed models is due to their relatively light architecture (computational efficiency) and, more importantly, their ability to capture the underlying highly nonlinear patterns embedded in the often contaminated sensor-collected indoor air quality temporal data.
more »
« less
- Award ID(s):
- 1922666
- PAR ID:
- 10542100
- Publisher / Repository:
- https://doi.org/10.48550/arXiv.2308.01438
- Date Published:
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Accurate air pollution monitoring is critical to understand and mitigate the impacts of air pollution on human health and ecosystems. Due to the limited number and geographical coverage of advanced, highly accurate sensors monitoring air pollutants, many low-cost and low-accuracy sensors have been deployed. Calibrating low-cost sensors is essential to fill the geographical gap in sensor coverage. We systematically examined how different machine learning (ML) models and open-source packages could help improve the accuracy of particulate matter (PM) 2.5 data collected by Purple Air sensors. Eleven ML models and five packages were examined. This systematic study found that both models and packages impacted accuracy, while the random training/testing split ratio (e.g., 80/20 vs. 70/30) had minimal impact (0.745% difference for R2). Long Short-Term Memory (LSTM) models trained in RStudio and TensorFlow excelled, with high R2 scores of 0.856 and 0.857 and low Root Mean Squared Errors (RMSEs) of 4.25 µg/m3 and 4.26 µg/m3, respectively. However, LSTM models may be too slow (1.5 h) or computation-intensive for applications with fast response requirements. Tree-boosted models including XGBoost (0.7612, 5.377 µg/m3) in RStudio and Random Forest (RF) (0.7632, 5.366 µg/m3) in TensorFlow offered good performance with shorter training times (<1 min) and may be suitable for such applications. These findings suggest that AI/ML models, particularly LSTM models, can effectively calibrate low-cost sensors to produce precise, localized air quality data. This research is among the most comprehensive studies on AI/ML for air pollutant calibration. We also discussed limitations, applicability to other sensors, and the explanations for good model performances. This research can be adapted to enhance air quality monitoring for public health risk assessments, support broader environmental health initiatives, and inform policy decisions.more » « less
-
Indoor localization is a challenging task. Compared to outdoor environments where GPS is dominant, there is no robust and almost-universal approach. Recently, machine learning (ML) has emerged as the most promising approach for achieving accurate indoor localization. Nevertheless, its main challenge is requiring large datasets to train the neural networks. The data collection procedure is costly and laborious, requiring extensive measurements and labeling processes for different indoor environments. The situation can be improved by Data Augmentation (DA), a general framework to enlarge the datasets for ML, making ML systems more robust and increasing their generalization capabilities. This paper proposes two simple yet surprisingly effective DA algorithms for channel state information (CSI) based indoor localization motivated by physical considerations. We show that the number of measurements for a given accuracy requirement may be decreased by an order of magnitude. Specifically, we demonstrate the algorithms’ effectiveness by experiments conducted with a measured indoor WiFi measurement dataset: As little as 10% of the original dataset size is enough to get the same performance as the original dataset. We also showed that if we further augment the dataset with the proposed techniques, test accuracy is improved more than three-fold.more » « less
-
Indoor localization plays a vital role in applications such as emergency response, warehouse management, and augmented reality experiences. By deploying machine learning (ML) based indoor localization frameworks on their mobile devices, users can localize themselves in a variety of indoor and subterranean environments. However, achieving accurate indoor localization can be challenging due to heterogeneity in the hardware and software stacks of mobile devices, which can result in inconsistent and inaccurate location estimates. Traditional ML models also heavily rely on initial training data, making them vulnerable to degradation in performance with dynamic changes across indoor environments. To address the challenges due to device heterogeneity and lack of adaptivity, we propose a novel embedded ML framework calledFedHIL. Our framework combines indoor localization and federated learning (FL) to improve indoor localization accuracy in device-heterogeneous environments while also preserving user data privacy.FedHILintegrates a domain-specific selective weight adjustment approach to preserve the ML model's performance for indoor localization during FL, even in the presence of extremely noisy data. Experimental evaluations in diverse real-world indoor environments and with heterogeneous mobile devices show thatFedHILoutperforms state-of-the-art FL and non-FL indoor localization frameworks.FedHILis able to achieve 1.62 × better localization accuracy on average than the best performing FL-based indoor localization framework from prior work.more » « less
-
SUPERCHARGE (STEM-based University Pathway Encouraging Relationships with Chicago High schools in Automation, Robotics, and Green Energy) is an NSF-funded after-school STEM program through which an interdisciplinary team of faculty, staff, and students at Illinois State University is collaborating with teachers from four high schools in Chicago, Illinois in the U.S. and four non-profit Community-Based Organizations (CBOs) in the surrounding communities to develop innovative hands-on activities for underrepresented students. These informal educational activities are centered on topics such as robotics, automation, and renewable energy. In the program's inaugural year, one of the four units will focus on assessing air quality, employing the micro:bit microcontroller for programming and the Kitronik Air Quality Board for sensing and data collection. All the air quality unit activities were developed by undergraduate students under the guidance of faculty advisors. High school teachers mentoring the student learners in the afterschool STEM program iteratively reviewed all activities when these activities were developed. These air quality assessment activities are outlined as follows. Activity 1: Students are introduced to the significance of indoor and outdoor air quality. They subsequently learn about air quality components, including temperature, pressure, humidity, air quality index, and CO2 equivalent. Activities 2 & 3: Students collect air quality data from different locations and visualize the collected data to comprehend variations among these locations. An extension activity is available for students interested in collecting air quality data over an extended period, allowing them to evaluate the correlation between indoor conditions and air quality changes. Activity 4: Students learn to program the micro:bit to display air quality status using LED lights on the air quality board. Activity 5: The learning unit concludes by presenting air quality conditions in their neighborhood in collaboration with their CBOs. Students can assess the air quality using the hand-held device they programmed and compare their findings to data collected by existing air quality monitoring sensors in their communities. Preliminary data collected during the testing phase indicate that the developed programs effectively display air quality. These activities were designed to help student learners comprehend coding, microcontroller technology, and data collection and visualization. In the summer of 2023, the SUPERCHARGE team organized two one-day professional development workshops. Teachers who participated in these summer workshops completed a selection of air quality assessment activities. They provided feedback, confirming that the programs on the air quality board work seamlessly. Minor suggestions were received, and the instructions were modified accordingly. This Work in Progress paper aims to document one of the first year’s learning activities of the highly collaborative after-school STEM program, demonstrate the activity development processes, and foster an exchange of ideas and feedback among educators in related fields.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Posted Content:
- The DOI is not currently available.
