Search

The Higher Education Emergency Relief (HEER) Fund had two main purposes: (1) to ensure that colleges could continue to provide education to students in the wake of the pandemic and (2) to provide emergency financial assistance through colleges directly to students. Four years after the onset of the pandemic, this ARCC Network brief uses college financial data--including data recently released for fiscal year 2022--to look at what happened to college finances and to assess the importance of HEER funding for the financial solvency of community colleges over the course of the pandemic. The authors find that during the peak years of the pandemic (2020-2022), community colleges lost huge numbers of students: On average, colleges lost 580 full-time-equivalent (FTE) students or 15% of pre-pandemic year-on-year enrollment, whereas college enrollments typically fluctuate by +/-2% each year. The authors also find that federal HEER funding saved community colleges from massive losses in tuition revenue during the pandemic. Instead of losing revenue, HEER funding increased total revenue per college from $81 million to $84 million, covering lost tuition and offsetting new costs associated with the pandemic. HEER funding also provided $4 million in student aid per college, on average, making up for lost resources students experienced during the pandemic. The authors--who also wrote an associated blog post that includes an interactive dashboard on this topic--contend that community colleges are confronting new fiscal challenges post-pandemic. As HEER funding has ended, many community colleges are faced with a difficult fiscal outlook, with increased costs due to inflation and decreased overall enrollments relative to pre-pandemic levels. Navigating these new fiscal realities will be extremely challenging for community colleges, raising new concerns about the viability of many colleges in the post-pandemic era. [This report was written with the Accelerating Recovery in Community Colleges (ARCC) Network.]

The benefits of participating in one of these programs have been well documented, but so too have the gaps in been well documented, but so too have the gaps in participation among Black and Hispanic students, English participation among Black and Hispanic students, English learners, students with disabilities, and other groups not well learners, students with disabilities, and other groups not well served in the high school-to-college transition. served in the high school-to-college transition. This report offers guidance for state leaders drawn from the implications of what we are learning from college and K-12 practitioners working to broaden the benefits of dual enrollment. It presents policy recommendations pertaining to three areas of practice that describe how practitioners are working to improve dual enrollment (DE): (1) expanding access to DE, (2) strengthening DE as an on-ramp to high-opportunity postsecondary pathways, and (3) building and sustaining DE partnerships between K-12 leaders and colleges that are grounded in a shared vision emphasizing access, quality, and success.

Each year, more than a million high school students nationally take college dual enrollment courses, which have been shown to increase college access and success among participants. Yet racial/ethnic and other equity gaps in dual enrollment participation are widespread. To broaden the benefits of dual enrollment, the state of Ohio passed legislation in 2017 establishing the Innovative Programs (IP) policy, allowing waivers to test-based eligibility requirements--a frequently identified barrier to equitable access--for specific high school-college partnerships providing expanded outreach and support for students underrepresented in the state's dual enrollment program. This paper describes a multiple methods study of IP we conducted to examine how these partnerships were implemented to address the needs of underrepresented students and to evaluate whether the partnerships were successful in broadening access to and success in dual enrollment, as measured by course participation, pass rates, and college matriculation after high school. We find that the IP increased participation in dual enrollment among Black and Hispanic students. And while the implementation of the policy broadened access without changing course outcomes, the impacts on college enrollment after high school were mixed. Our results underscore the importance of pairing increased access to dual enrollment with adequate financial, advising, and academic resources to promote student success in and beyond dual enrollment courses.

Numerical weather prediction (NWP) models often underperform compared to simpler climatology-based precipitation forecasts in northern tropical Africa, even after statistical postprocessing. AI-based forecasting models show promise but have avoided precipitation due to its complexity. Synoptic-scale forcings like African easterly waves and other tropical waves (TWs) are important for predictability in tropical Africa, yet their value for predicting daily rainfall remains unexplored. This study uses two machine-learning models--gamma regression and a convolutional neural network (CNN)--trained on TW predictors from satellite-based GPM IMERG data to predict daily rainfall during the July-September monsoon season. Predictor variables are derived from the local amplitude and phase information of seven TW from the target and up-and-downstream neighboring grids at 1-degree spatial resolution. The ML models are combined with Easy Uncertainty Quantification (EasyUQ) to generate calibrated probabilistic forecasts and are compared with three benchmarks: Extended Probabilistic Climatology (EPC15), ECMWF operational ensemble forecast (ENS), and a probabilistic forecast from the ENS control member using EasyUQ (CTRL EasyUQ). The study finds that downstream predictor variables offer the highest predictability, with downstream tropical depression (TD)-type wave-based predictors being most important. Other waves like mixed-Rossby gravity (MRG), Kelvin, and inertio-gravity waves also contribute significantly but show regional preferences. ENS forecasts exhibit poor skill due to miscalibration. CTRL EasyUQ shows improvement over ENS and marginal enhancement over EPC15. Both gamma regression and CNN forecasts significantly outperform benchmarks in tropical Africa. This study highlights the potential of ML models trained on TW-based predictors to improve daily precipitation forecasts in tropical Africa.

WebAssembly (WASM) is an immensely versatile and increasingly popular compilation target. It executes applications written in several languages (e.g., C/C++) with near-native performance in various domains (e.g., mobile, edge, cloud). Despite WASM's sandboxing feature, which isolates applications from other instances and the host platform, WASM does not inherently provide any memory safety guarantees for applications written in low-level, unsafe languages. To this end, we propose Cage, a hardware-accelerated toolchain for WASM that supports unmodified applications compiled to WASM and utilizes diverse Arm hardware features aiming to enrich the memory safety properties of WASM. Precisely, Cage leverages Arm's Memory Tagging Extension (MTE) to (i)~provide spatial and temporal memory safety for heap and stack allocations and (ii)~improve the performance of WASM's sandboxing mechanism. Cage further employs Arm's Pointer Authentication (PAC) to prevent leaked pointers from being reused by other WASM instances, thus enhancing WASM's security properties. We implement our system based on 64-bit WASM. We provide a WASM compiler and runtime with support for Arm's MTE and PAC. On top of that, Cage's LLVM-based compiler toolchain transforms unmodified applications to provide spatial and temporal memory safety for stack and heap allocations and prevent function pointer reuse. Our evaluation on real hardware shows that Cage incurs minimal runtime ($<5.8\,\%$) and memory ($<3.7\,\%$) overheads and can improve the performance of WASM's sandboxing mechanism, achieving a speedup of over $5.1\,\%$, while offering efficient memory safety guarantees.

Detecting and localizing leakages is a significant challenge for the efficient and sustainable management of water distribution networks (WDN). Leveraging the inherent graph structure of WDNs, recent approaches have used graph-based data-driven methods. However, these methods often learn shortcuts that work well with in-distribution data but fail to generalize to out-of-distribution data. To address this limitation and inspired by the perfect generalization ability of classical algorithms, we propose an algorithm-informed graph neural network (AIGNN). Recognizing that WDNs function as flow networks, incorporating max-flow information can be beneficial for inferring pressures. In the proposed framework, we first train AIGNN to emulate the Ford-Fulkerson algorithm for solving max-flow problems. This algorithmic knowledge is then transferred to address the pressure estimation problem in WDNs. Two AIGNNs are deployed, one to reconstruct pressure based on the current measurements, and another to predict pressure based on previous measurements. Leakages are detected and localized by comparing the outputs of the reconstructor and the predictor. By pretraining AIGNNs to reason like algorithms, they are expected to extract more task-relevant and generalizable features. Experimental results demonstrate that the proposed algorithm-informed approach achieves superior results with better generalization ability compared to GNNs that do not incorporate algorithmic knowledge.

Real-time condition monitoring is crucial for the reliable and efficient operation of complex systems. However, relying solely on physical sensors can be limited due to their cost, placement constraints, or inability to directly measure certain critical parameters. Virtual sensing addresses these limitations by leveraging readily available sensor data and system knowledge to estimate inaccessible parameters or infer system states. The increasing complexity of industrial systems necessitates deployments of sensors with diverse modalities to provide a comprehensive understanding of system states. These sensors capture data at varying frequencies to monitor both rapid and slowly varying system dynamics, as well as local and global state evolutions of the systems. This leads to heterogeneous temporal dynamics, which, particularly under varying operational end environmental conditions, pose a significant challenge for accurate virtual sensing. To address this, we propose a Heterogeneous Temporal Graph Neural Network (HTGNN) framework. HTGNN explicitly models signals from diverse sensors and integrates operating conditions into the model architecture. We evaluate HTGNN using two newly released datasets: a bearing dataset with diverse load conditions for bearing load prediction and a year-long simulated dataset for predicting bridge live loads. Our results demonstrate that HTGNN significantly outperforms established baseline methods in both tasks, particularly under highly varying operating conditions. These results highlight HTGNN's potential as a robust and accurate virtual sensing approach for complex systems, paving the way for improved monitoring, predictive maintenance, and enhanced system performance., Comment: This paper extends our previous conference paper (Best Paper at European Conference of the PHM Society 2024, https://doi.org/10.36001/phme.2024.v8i1.3998)

Accurately modeling the mechanical behavior of materials is crucial for numerous engineering applications. The quality of these models depends directly on the accuracy of the constitutive law that defines the stress-strain relation. Discovering these constitutive material laws remains a significant challenge, in particular when only material deformation data is available. To address this challenge, unsupervised machine learning methods have been proposed. However, existing approaches have several limitations: they either fail to ensure that the learned constitutive relations are consistent with physical principles, or they rely on a predefined library of constitutive relations or manually crafted input features. These dependencies require significant expertise and specialized domain knowledge. Here, we introduce a machine learning approach called uLED, which overcomes the limitations by using the input convex neural network (ICNN) as the surrogate constitutive model. We improve the optimization strategy for training ICNN, allowing it to be trained end-to-end using direct strain invariants as input across various materials. Furthermore, we utilize the nodal force equilibrium at the internal domain as the training objective, which enables us to learn the constitutive relation solely from temporal displacement recordings. We validate the effectiveness of the proposed method on a diverse range of material laws. We demonstrate that it is robust to a significant level of noise and that it converges to the ground truth with increasing data resolution. We also show that the model can be effectively trained using a displacement field from a subdomain of the test specimen and that the learned constitutive relation from one material sample is transferable to other samples with different geometries. The developed methodology provides an effective tool for discovering constitutive relations.

Recent advancements in Machine Learning (ML) have substantially improved its predictive and computational abilities, offering promising opportunities for surrogate modeling in scientific applications. By accurately approximating complex functions with low computational cost, ML-based surrogates can accelerate scientific applications by replacing computationally intensive components with faster model inference. However, integrating ML models into these applications remains a significant challenge, hindering the widespread adoption of ML surrogates as an approximation technique in modern scientific computing. We propose an easy-to-use directive-based programming model that enables developers to seamlessly describe the use of ML models in scientific applications. The runtime support, as instructed by the programming model, performs data assimilation using the original algorithm and can replace the algorithm with model inference. Our evaluation across five benchmarks, testing over 5000 ML models, shows up to 83.6x speed improvements with minimal accuracy loss (as low as 0.01 RMSE)., Comment: 16 pages, 9 figures. Accepted at SC24

Estimating many-body effects that deviate from an independent particle approach, has long been a key research interest in condensed matter physics. Layered cuprates are prototypical systems, where electron-electron interactions are found to strongly affect the dynamics of single-particle excitations. It is however, still unclear how the electron correlations influence charge excitations, such as plasmons, which have been variously treated with either weak or strong correlation models. In this work, we demonstrate the hybridised nature of collective valence charge fluctuations leading to dispersing acoustic-like plasmons in hole-doped La$_{1.84}$Sr$_{0.16}$CuO$_{4}$ and electron-doped La$_{1.84}$Ce$_{0.16}$CuO$_{4}$ using the two-particle probe, resonant inelastic x-ray scattering. We then describe the plasmon dispersions in both systems, within both the weak mean-field Random Phase Approximation (RPA) and strong coupling $t$-$J$-$V$ models. The $t$-$J$-$V$ model, which includes the correlation effects implicitly, accurately describes the plasmon dispersions as resonant excitations outside the single-particle intra-band continuum. In comparison, a quantitative description of the plasmon dispersion in the RPA approach is obtained only upon explicit consideration of re-normalized electronic band parameters. Our comparative analysis shows that electron correlations significantly impact the low-energy plasmon excitations across the cuprate doping phase diagram, even at long wavelengths. Thus, complementary information on the evolution of electron correlations, influenced by the rich electronic phases in condensed matter systems, can be extracted through the study of two-particle charge response., Comment: 6 Figures

This paper focuses on source-free domain adaptation for object detection in computer vision. This task is challenging and of great practical interest, due to the cost of obtaining annotated data sets for every new domain. Recent research has proposed various solutions for Source-Free Object Detection (SFOD), most being variations of teacher-student architectures with diverse feature alignment, regularization and pseudo-label selection strategies. Our work investigates simpler approaches and their performance compared to more complex SFOD methods in several adaptation scenarios. We highlight the importance of batch normalization layers in the detector backbone, and show that adapting only the batch statistics is a strong baseline for SFOD. We propose a simple extension of a Mean Teacher with strong-weak augmentation in the source-free setting, Source-Free Unbiased Teacher (SF-UT), and show that it actually outperforms most of the previous SFOD methods. Additionally, we showcase that an even simpler strategy consisting in training on a fixed set of pseudo-labels can achieve similar performance to the more complex teacher-student mutual learning, while being computationally efficient and mitigating the major issue of teacher-student collapse. We conduct experiments on several adaptation tasks using benchmark driving datasets including (Foggy)Cityscapes, Sim10k and KITTI, and achieve a notable improvement of 4.7\% AP50 on Cityscapes$\rightarrow$Foggy-Cityscapes compared with the latest state-of-the-art in SFOD. Source code is available at https://github.com/EPFL-IMOS/simple-SFOD., Comment: Accepted at ECCV 2024. 19 pages

Eye movements provide a window into human behaviour, attention, and interaction dynamics. Previous research suggests that eye movements are highly influenced by task, setting, and social others; however, most eye tracking research is conducted in single-person, in-lab settings and is yet to be validated in multi-person, naturalistic contexts. One such prevalent real-world context is the collective viewing of a shared scene in social settings, for example, viewing a concert, film, lecture, sports, etc. Here, we apply mobile eye tracking in a real-world multi-person setup and develop a system to stream, record, and analyse synchronised data. We tested our proposed, open-source system while participants (N=60) watched a live concert and a documentary film screening during a public event. We tackled challenges related to networking bandwidth requirements, real-time monitoring, and gaze projection from individual egocentric perspectives to a common coordinate space for shared gaze analysis. Our system achieves precise time synchronisation and accurate gaze projection in challenging dynamic scenes. Further, to illustrate the potential of collective eye-tracking data, we introduce and evaluate novel analysis metrics and visualisations. Overall, our approach contributes to the development and application of versatile multi-person eye tracking systems in real-world social settings. This advancement enables insight into collaborative behaviour, group dynamics, and social interaction, with high ecological validity. Moreover, it paves the path for innovative, interactive tools that promote collaboration and coordination in social contexts., Comment: Please refer to the supplementary video illustrating the proposed approach in this paper here: https://tinyurl.com/multipersonET

The task of open-set domain generalization (OSDG) involves recognizing novel classes within unseen domains, which becomes more challenging with multiple modalities as input. Existing works have only addressed unimodal OSDG within the meta-learning framework, without considering multimodal scenarios. In this work, we introduce a novel approach to address Multimodal Open-Set Domain Generalization (MM-OSDG) for the first time, utilizing self-supervision. To this end, we introduce two innovative multimodal self-supervised pretext tasks: Masked Cross-modal Translation and Multimodal Jigsaw Puzzles. These tasks facilitate the learning of multimodal representative features, thereby enhancing generalization and open-class detection capabilities. Additionally, we propose a novel entropy weighting mechanism to balance the loss across different modalities. Furthermore, we extend our approach to tackle also the Multimodal Open-Set Domain Adaptation (MM-OSDA) problem, especially in scenarios where unlabeled data from the target domain is available. Extensive experiments conducted under MM-OSDG, MM-OSDA, and Multimodal Closed-Set DG settings on the EPIC-Kitchens and HAC datasets demonstrate the efficacy and versatility of the proposed approach. Our source code is available at https://github.com/donghao51/MOOSA., Comment: Accepted by ECCV 2024, code: https://github.com/donghao51/MOOSA

Upward transfer from a community college to a four-year institution is a distinct component of higher education and has long been envisioned as an accessible and affordable route to a bachelor's degree for students who are Latinx, Black, underrepresented Asian American and Native Hawaiian and Pacific Islander, and American Indian/Alaska Native, as well as low-income, English language learners, and from other minoritized populations. Yet, nationally, only 28% of Black adults and 21% of Latinx adults over age 25 hold a bachelor's degree, compared with 42% of white adults. Similarly, only 15% of young adults from the lowest income backgrounds complete a bachelor's degree by age 24, compared with 59% of their wealthier peers. This brief examines the community college-to-university transfer pathway and its critical role in increasing higher education equity. It reviews the major barriers created by institutional policy, ways college leaders can address these barriers to better realize the potential of transfer, and considerations for policy leaders seeking to promote equitable access to a bachelor's degree and beyond for community college students. The authors conclude with a focused look at California's associate degree for transfer (ADT), and the ways in which this new degree pathway is helping fortify the transfer pathway in the state. They then outline recommendations for policymakers at the federal, state, and institutional levels seeking to simplify transfer pathways for students in their colleges and universities. [Eileen and Harold Brown provided additional funding for this series of briefs.]

This brief is part of the Affirming Equity, Ensuring Inclusion, and Empowering Action initiative. This brief summarizes the research on dual enrollment programs--programs which allow high school students to enroll in college coursework through a partnering college or university--and offers policymakers a strategy to increase college enrollment and attainment via such efforts. Dual enrollment represents a promising lever for increasing educational equity, given its large scale and demonstrated effectiveness for increasing college access and success among its participants. Black, Latinx, and other minoritized students benefit from dual enrollment participation, yet these and other groups underrepresented in higher education often do not have meaningful access to such programs. Strong dual enrollment programs have the potential to raise college enrollment rates among high school graduates and improve college-attainment rates for students who participate. [Eileen and Harold Brown provided additional funding for this series of briefs.]

Dual enrollment (DE), in which high school students take college courses and earn both high school and college credit, has great potential to help make the high-school-to-college transition more effective and equitable--and to do so on a large scale. There is strong evidence that DE improves academic outcomes for students, including completing high school, enrolling in college, and completing college degrees. Some of the most compelling evidence comes from research on the impact of Early College High Schools (ECHSs), but these schools operate on a smaller scale than less intensive models of à la carte dual enrollment. The vast majority of high school students participating in DE take à la carte courses on a college campus, online, or in the high school. While there is evidence that this type of DE coursetaking benefits students, students of color, English learners, and students with disabilities are underrepresented in DE overall, and the laissez-faire approach to à la carte DE tends to exacerbate equity gaps in the high-school-to-college-transition. In this report, the authors present dual enrollment equity pathways (DEEP), a model for rethinking dual enrollment as a more equitable on-ramp to college degree programs that prepare underserved students for well-paying, career-path employment in their 20s. The authors draw on emergent efforts by early adopter institutions of whole-college guided pathways reforms and on additional research to outline and describe support for the DEEP model's four areas of practice: (1) outreach to underserved students and schools; (2) alignment to college degrees and careers in fields of interest; (3) early career and academic exploration, advising, and planning; and (4) high-quality college instruction and academic support. The DEEP model reflects a shift in mindset from conventional thinking about DE to a more strategic approach that requires significant changes on the part of both colleges and high schools. The authors conclude by pointing to growing incentives and opportunities for colleges, schools, and state systems to implement DEEP practices at scale and by identifying costs associated with DEEP implementation. [For the companion report, see ED631297.]

Dual enrollment equity pathways (DEEP) is a research-based framework for rethinking dual enrollment as a more equitable on-ramp to college programs of study that lead to family-supporting, career-path jobs for students who might not otherwise pursue education after college. The DEEP approach involves community colleges and K-12 schools partnering in four practice areas to (1) conduct outreach to underserved students and families to encourage their participation in dual enrollment, (2) align dual enrollment course offerings to career-technical associate and bachelor's degree programs in high-opportunity fields, (3) advise students in the exploration of their interests and the development of post-high school education and career path plans, and (4) support students by delivering high-quality instruction to build their confidence as college learners. In this report, the authors describe what they learned through field research at six promising community college--K-12 partnerships in Florida and Texas that have begun to extend guided pathways practices to dual enrollment offerings and that have achieved strong results using dual enrollment to expand college access and opportunities for Black, Hispanic, and low-income high school students. For each of the four practice areas, the authors highlight the problems or shortcomings of the conventional dual enrollment approach and explain what the partnerships are doing to rethink and reform dual enrollment in ways that motivate and prepare students from underserved groups to pursue postsecondary pathways to careers after high school. The authors then discuss two multifaceted DEEP leadership strategies that emerged from their fieldwork for (1) establishing a shared DEEP mindset and (2) enabling DEEP practices at scale. They also provide a set of discussion questions for college leaders to ask their K-12 schools in order to develop a strong partnership and shared vision. [For the companion report, see ED631291.]

The interaction between waves and evolving media challenges traditional conservation laws. We experimentally investigate the behavior of elastic wave packets crossing a moving interface that separates two media with distinct propagation properties, observing the non-conservation of wavelength and frequency. Our experimental setup employs an elastic strip whose local stretching can be dynamically altered by pulling one end at a constant velocity. By demonstrating that this dynamic configuration creates a spatio-temporal interface traveling along the strip, we confirm theoretical predictions regarding observed shifts when a wave packet crosses this interface.

Trajectory planning for autonomous driving is challenging because the unknown future motion of traffic participants must be accounted for, yielding large uncertainty. Stochastic Model Predictive Control (SMPC)-based planners provide non-conservative planning, but do not rule out a (small) probability of collision. We propose a control scheme that yields an efficient trajectory based on SMPC when the traffic scenario allows, still avoiding that the vehicle causes collisions with traffic participants if the latter move according to the prediction assumptions. If some traffic participant does not behave as anticipated, no safety guarantee can be given. Then, our approach yields a trajectory which minimizes the probability of collision, using Constraint Violation Probability Minimization techniques. Our algorithm can also be adapted to minimize the anticipated harm caused by a collision. We provide a thorough discussion of the benefits of our novel control scheme and compare it to a previous approach through numerical simulations from the CommonRoad database.

Damage to road pavement can develop into cracks, potholes, spallings, and other issues posing significant challenges to the integrity, safety, and durability of the road structure. Detecting and monitoring the evolution of these damages is crucial for maintaining the condition and structural health of road infrastructure. In recent years, researchers have explored various data-driven methods for image-based damage detection in road monitoring applications. The field gained attention with the introduction of the Road Damage Detection Challenge (RDDC2018), encouraging competition in developing object detectors on street-view images from various countries. Leading teams have demonstrated the effectiveness of ensemble models, mostly based on the YOLO and Faster R-CNN series. Data augmentations have also shown benefits in object detection within the computer vision field, including transformations such as random flipping, cropping, cutting out patches, as well as cut-and-pasting object instances. Applying cut-and-paste augmentation to road damages appears to be a promising approach to increase data diversity. However, the standard cut-and-paste technique, which involves sampling an object instance from a random image and pasting it at a random location onto the target image, has demonstrated limited effectiveness for road damage detection. This method overlooks the location of the road and disregards the difference in perspective between the sampled damage and the target image, resulting in unrealistic augmented images. In this work, we propose an improved Cut-and-Paste augmentation technique that is both content-aware (i.e. considers the true location of the road in the image) and perspective-aware (i.e. takes into account the difference in perspective between the injected damage and the target image)., Comment: Extended abstract accepted at ESREL 2024. 2 pages

Fault detection is crucial in industrial systems to prevent failures and optimize performance by distinguishing abnormal from normal operating conditions. Data-driven methods have been gaining popularity for fault detection tasks as the amount of condition monitoring data from complex industrial systems increases. Despite these advances, early fault detection remains a challenge under real-world scenarios. The high variability of operating conditions and environments makes it difficult to collect comprehensive training datasets that can represent all possible operating conditions, especially in the early stages of system operation. Furthermore, these variations often evolve over time, potentially leading to entirely new data distributions in the future that were previously unseen. These challenges prevent direct knowledge transfer across different units and over time, leading to the distribution gap between training and testing data and inducing performance degradation of those methods in real-world scenarios. To overcome this, our work introduces a novel approach for continuous test-time domain adaptation. This enables early-stage robust anomaly detection by addressing domain shifts and limited data representativeness issues. We propose a Test-time domain Adaptation Anomaly Detection (TAAD) framework that separates input variables into system parameters and measurements, employing two domain adaptation modules to independently adapt to each input category. This method allows for effective adaptation to evolving operating conditions and is particularly beneficial in systems with scarce data. Our approach, tested on a real-world pump monitoring dataset, shows significant improvements over existing domain adaptation methods in fault detection, demonstrating enhanced accuracy and reliability., Comment: 11 pages including references

Graph signal processing represents an important advancement in the field of data analysis, extending conventional signal processing methodologies to complex networks and thereby facilitating the exploration of informative patterns and structures across various domains. However, acquiring the underlying graphs for specific applications remains a challenging task. While graph inference based on smooth graph signal representation has become one of the state-of-the-art methods, these approaches usually overlook the unique properties of networks, which are generally derived from domain-specific knowledge. Overlooking this information could make the approaches less interpretable and less effective overall. In this study, we propose a new graph inference method that leverages available domain knowledge. The proposed methodology is evaluated on the task of denoising and imputing missing sensor data, utilizing graph signal reconstruction techniques. The results demonstrate that incorporating domain knowledge into the graph inference process can improve graph signal reconstruction in district heating networks. Our code is available at \href{https://github.com/Keiv4n/IGL}{github.com/Keiv4n/IGL}., Comment: Accepted to EUSIPCO 2024

Visual anomaly detection (AD) inherently faces significant challenges due to the scarcity of anomalous data. Although numerous works have been proposed to synthesize anomalous samples, the generated samples often lack authenticity or can only reflect the distribution of the available training data samples. In this work, we propose CUT: a Controllable, Universal and Training-free visual anomaly generation framework, which leverages the capability of Stable Diffusion (SD) in image generation to generate diverse and realistic anomalies. With CUT, we achieve controllable and realistic anomaly generation universally across both unseen data and novel anomaly types, using a single model without acquiring additional training effort. To demonstrate the effectiveness of our approach, we propose a Vision-Language-based Anomaly Detection framework (VLAD). By training the VLAD model with our generated anomalous samples, we achieve state-of-the-art performance on several benchmark anomaly detection tasks, highlighting the significant improvements enabled by our synthetic data., Comment: 9 pages excluding appendix

Regression models often fail to generalize effectively in regions characterized by highly imbalanced label distributions. Previous methods for deep imbalanced regression rely on gradient-based weight updates, which tend to overfit in underrepresented regions. This paper proposes a paradigm shift towards in-context learning as an effective alternative to conventional in-weight learning methods, particularly for addressing imbalanced regression. In-context learning refers to the ability of a model to condition itself, given a prompt sequence composed of in-context samples (input-label pairs) alongside a new query input to generate predictions, without requiring any parameter updates. In this paper, we study the impact of the prompt sequence on the model performance from both theoretical and empirical perspectives. We emphasize the importance of localized context in reducing bias within regions of high imbalance. Empirical evaluations across a variety of real-world datasets demonstrate that in-context learning substantially outperforms existing in-weight learning methods in scenarios with high levels of imbalance.

Detecting out-of-distribution (OOD) samples is important for deploying machine learning models in safety-critical applications such as autonomous driving and robot-assisted surgery. Existing research has mainly focused on unimodal scenarios on image data. However, real-world applications are inherently multimodal, which makes it essential to leverage information from multiple modalities to enhance the efficacy of OOD detection. To establish a foundation for more realistic Multimodal OOD Detection, we introduce the first-of-its-kind benchmark, MultiOOD, characterized by diverse dataset sizes and varying modality combinations. We first evaluate existing unimodal OOD detection algorithms on MultiOOD, observing that the mere inclusion of additional modalities yields substantial improvements. This underscores the importance of utilizing multiple modalities for OOD detection. Based on the observation of Modality Prediction Discrepancy between in-distribution (ID) and OOD data, and its strong correlation with OOD performance, we propose the Agree-to-Disagree (A2D) algorithm to encourage such discrepancy during training. Moreover, we introduce a novel outlier synthesis method, NP-Mix, which explores broader feature spaces by leveraging the information from nearest neighbor classes and complements A2D to strengthen OOD detection performance. Extensive experiments on MultiOOD demonstrate that training with A2D and NP-Mix improves existing OOD detection algorithms by a large margin. Our source code and MultiOOD benchmark are available at https://github.com/donghao51/MultiOOD., Comment: Code and MultiOOD benchmark: https://github.com/donghao51/MultiOOD

Deep learning approaches have recently been extensively explored for the prognostics of industrial assets. However, they still suffer from a lack of interpretability, which hinders their adoption in safety-critical applications. To improve their trustworthiness, explainable AI (XAI) techniques have been applied in prognostics, primarily to quantify the importance of input variables for predicting the remaining useful life (RUL) using post-hoc attribution methods. In this work, we propose the application of Concept Bottleneck Models (CBMs), a family of inherently interpretable neural network architectures based on concept explanations, to the task of RUL prediction. Unlike attribution methods, which explain decisions in terms of low-level input features, concepts represent high-level information that is easily understandable by users. Moreover, once verified in actual applications, CBMs enable domain experts to intervene on the concept activations at test-time. We propose using the different degradation modes of an asset as intermediate concepts. Our case studies on the New Commercial Modular AeroPropulsion System Simulation (N-CMAPSS) aircraft engine dataset for RUL prediction demonstrate that the performance of CBMs can be on par or superior to black-box models, while being more interpretable, even when the available labeled concepts are limited. Code available at \href{https://github.com/EPFL-IMOS/concept-prognostics/}{\url{github.com/EPFL-IMOS/concept-prognostics/}}., Comment: Under review

A "tropical ideal" is an ideal in the idempotent semiring of tropical polynomials that is also, degree by degree, a tropical linear space. We introduce a construction based on transversal matroids that canonically extends any principal ideal to a tropical ideal. We call this the Macaulay tropical ideal. It has a universal property: any other extension of the given principal ideal to a tropical ideal with the expected Hilbert function is a weak image of the Macaulay tropical ideal. For each $n\geq 2$ and $d\geq 1$ our construction yields a non-realizable degree $d$ hypersurface scheme in $\mathbb{P}^n$. Maclagan-Rinc\'on produced a non-realizable line in $\mathbb{P}^n$ for each $n$, and for $(d,n)=(1,2)$ the two constructions agree. An appendix by Mundinger compares the Macaulay construction with another method for canonically extending ideals to tropical ideals., Comment: Appendix by Joshua Mundinger. 21pp

Distributed ledger technology such as blockchain is considered essential for supporting large numbers of micro-transactions in the Machine Economy, which is envisioned to involve billions of connected heterogeneous and decentralized cyber-physical systems. This stresses the need for performance and scalability of distributed ledger technologies. Sharding divides the blockchain network into multiple committees and is a common approach to improve scalability. However, with current sharding approaches, costly cross-shard verification is needed to prevent double-spending. This paper proposes a novel and more scalable distributed ledger method named ScaleGraph that implements dynamic sharding by using routing and logical proximity concepts from distributed hash tables. ScaleGraph addresses cyber security in terms of integrity, availability, and trust, to support frequent micro-transactions between autonomous devices. Benefits of ScaleGraph include a total storage space complexity of O(t), where t is the global number of transactions (assuming a constant replication degree). This space is sharded over n nodes so that each node needs O(t/n) storage, which provides a high level of concurrency and data localization as compared to other delegated consensus proposals. ScaleGraph allows for a dynamic grouping of validators which are selected based on a distance metric. We analyze the consensus requirements in such a dynamic setting and show that a synchronous consensus protocol allows shards to be smaller than an asynchronous one, and likely yields better performance. Moreover, we provide an experimental analysis of security aspects regarding the required size of the consensus groups with ScaleGraph. Our analysis shows that dynamic sharding based on proximity concepts brings attractive scalability properties in general, especially when the fraction of corrupt nodes is small., Comment: 19 pages, 6 figures, submitted to ACM DLT

Small, low-cost radar sensors offer a lighting independent sensing capability for indoor mobile robots that is useful for localization and mapping. Synthetic aperture radar (SAR) offers an attractive way to increase the angular resolution of small radar sensors for use on mobile robots to generate high-resolution maps of the indoor environment. This work quantifies the maximum synthesizable aperture length of our mobile robot measurement setup using radar-inertial odometry localization and offers insights into challenges for robotic millimeter-wave SAR imaging., Comment: 6 pages, 11 figures. This paper was presented at the 15th European Conference on Synthetic Aperture Radar (EUSAR 2024), 23-26 Apr 2024, Munich, Germany

The peak photon detection efficiency (PDE) of silicon photomultipliers (SiPMs) can be as good or better than the PDE of photomultiplier tubes (PMTs). There are experiments where the signal is measured in the presence of a strong, steady background light emission. In these, one needs to accurately evaluate the signal-to-noise ratio. Imaging Atmospheric Cherenkov Telescopes (IACTs) observe in the presence of strong noise induced by the light of the night sky. It is certainly interesting to investigate the SiPM performance under operational conditions of IACTs and to compare it with that of the PMTs. For that purpose, we built a SiPM-based detector module, which was installed in one of the imaging cameras of the two Major Atmospheric Gamma-ray Imaging Cherenkov (MAGIC) telescopes in 2015. The experience gained from that module was used to design the second generation of modules of improved performance. Two such modules were installed in 2017. MAGIC is a system of two IACTs located on the Canary Island of La Palma. The mechanical structure of the MAGIC imaging cameras offers the possibility to install up to 6 additional detector modules of 7 pixels each into the open vertices of the hexagonal-shaped camera. This allows us to directly, without making any assumption, compare the performance of the PMT-based modules with that of the SiPM-based prototype modules, where SiPMs from three different manufacturers are used., Comment: 26 pages, 26 figures, Accepted for publication in Nuclear Instruments and Methods in Physics Research - section A (NIM-A)

Urban Air Mobility (UAM) aims to expand existing transportation networks in metropolitan areas by offering short flights either to transport passengers or cargo. Electric vertical takeoff and landing aircraft powered by lithium-ion battery packs are considered promising for such applications. Efficient mission planning is cru-cial, maximizing the number of flights per battery charge while ensuring completion even under unforeseen events. As batteries degrade, precise mission planning becomes challenging due to uncertainties in the end-of-discharge prediction. This often leads to adding safety margins, reducing the number or duration of po-tential flights on one battery charge. While predicting the end of discharge can support decision-making, it remains insufficient in case of unforeseen events, such as adverse weather conditions. This necessitates health-aware real-time control to address any unexpected events and extend the time until the end of charge while taking the current degradation state into account. This paper addresses the joint problem of mission planning and health-aware real-time control of opera-tional parameters to prescriptively control the duration of one discharge cycle of the battery pack. We pro-pose an algorithm that proactively prescribes operational parameters to extend the discharge cycle based on the battery's current health status while optimizing the mission. The proposed deep reinforcement learn-ing algorithm facilitates operational parameter optimization and path planning while accounting for the degradation state, even in the presence of uncertainties. Evaluation of simulated flights of a NASA concep-tual multirotor aircraft model, collected from Hardware-in-the-loop experiments, demonstrates the algo-rithm's near-optimal performance across various operational scenarios, allowing adaptation to changed en-vironmental conditions.

In this paper, we formalize an optimization framework for analog beamforming in the context of monostatic integrated sensing and communication (ISAC), where we also address the problem of self-interference in the analog domain. As a result, we derive semidefinite programs to approach detection-optimal transmit and receive beamformers, and we devise a superiorized iterative projection algorithm to approximate them. Our simulations show that this approach outperforms the detection performance of well-known design techniques for ISAC beamforming, while it achieves satisfactory self-interference suppression., Comment: 7 pages, 4 figures. Published at IEEE International Conference on Communications (ICC) 2024. IEEE Copyright protected

The Industrial Internet of Things (IIoT) is reshaping manufacturing, industrial processes, and infrastructure management. By fostering new levels of automation, efficiency, and predictive maintenance, IIoT is transforming traditional industries into intelligent, seamlessly interconnected ecosystems. However, achieving highly reliable IIoT can be hindered by factors such as the cost of installing large numbers of sensors, limitations in retrofitting existing systems with sensors, or harsh environmental conditions that may make sensor installation impractical. Soft (virtual) sensing leverages mathematical models to estimate variables from physical sensor data, offering a solution to these challenges. Data-driven and physics-based modeling are the two main methodologies widely used for soft sensing. The choice between these strategies depends on the complexity of the underlying system, with the data-driven approach often being preferred when the physics-based inference models are intricate and present challenges for state estimation. However, conventional deep learning models are typically hindered by their inability to explicitly represent the complex interactions among various sensors. To address this limitation, we adopt Graph Neural Networks (GNNs), renowned for their ability to effectively capture the complex relationships between sensor measurements. In this research, we propose physics-enhanced GNNs, which integrate principles of physics into graph-based methodologies. This is achieved by augmenting additional nodes in the input graph derived from the underlying characteristics of the physical processes. Our evaluation of the proposed methodology on the case study of district heating networks reveals significant improvements over purely data-driven GNNs, even in the presence of noise and parameter inaccuracies., Comment: 14 pages, 10 figures. Accepted to IEEE Internet of Things Journal

We present a novel dynamic model of a flash clay calciner. The model consists of thermophysical properties, reaction kinetics and stoichiometry, transport, mass and energy balances, and algebraic constraints. This gives rise to a system of partial differential-algebraic equations (PDAE). Spatial discretization is performed to convert the PDAEs into a system of differential-algebraic equations (DAE). The model can be used, for example, to perform dynamic simulations with changing inputs, and process design and optimization. Moreover, it can be used to develop model-based control, which is relevant for flexible operation of a clay calcination plant for green cement production., Comment: Accepted for Advanced Control of Chemical Processes (ADCHEM) 2024, Toronto, Canada

The dynamic charge susceptibility, $\chi(q,\omega)$, is a fundamental observable of all materials, in one, two, and three dimensions, quantifying the collective charge modes, the ability of a material to screen charge, as well as its electronic compressibility. Here, we review the current state of efforts to measure this quantity using inelastic electron scattering, which historically has been called electron energy-loss spectroscopy (EELS). We focus on comparison between transmission (T-EELS) and reflection (R-EELS) geometries as applied to a selection of 3D conductors. While a great deal is understood about simple metals, measurements of more strongly interacting and strange metals are currently contradictory, with different groups obtaining fundamentally conflicting results, emphasizing the importance of improved EELS measurements. Further, current opportunities for improvement in EELS techniques are vast, with the most promising future developments being in hemispherical and time-of-flight analyzers, as well as STEM instruments configured for high momentum resolution. We conclude that, despite more than half a century of work, EELS techniques are currently still in their infancy, Comment: 11 pages, 3 figures; submitted to Annual Review of Condensed Matter Physics

The vibrational response of structural components carries valuable information about their underlying mechanical properties, health status and operational conditions. This underscores the need for the development of efficient physics-based inversion algorithms which, given a limited set of sensing data points and in the presence of measurement noise, can reconstruct the response at locations where measurement data is not available and/or identify the unknown mechanical properties. Addressing this challenge, Physics-Informed Neural Networks (PINNs) have emerged as a promising approach. PINNs seamlessly integrate governing equations into their architecture and have gained significant interest in solving inversion problems. In the context of learning and inversion of multimodal, multiscale vibrational responses, this paper introduces a novel spectral extension of PINNs, utilizing Fourier basis functions in the wavenumber domain, commonly known as k-space. The proposed k-space PINN (k-PINN), offers a robust framework for adjusting complexity and wavenumber composition of the response. Notably, the spectral formulation of k-PINN, coupled with the generally sparse representation of vibrations in k-space, facilitate efficient reconstruction and learning of broadband vibrations and alleviate the spectral bias associated with standard PINN. Additionally, the spectral solution space introduced by k-PINN substantially reduces the computational cost associated with computing physics-informed loss terms. We evaluate the effectiveness of the proposed methodology on reconstructing the bending vibrational mode shapes of a thin composite laminate and identifying its effective bending stiffness coefficients. It is shown that the proposed k-PINN methodology outperforms the standard PINN in terms of both learning and computational efficiency., Comment: Revised: References, Figures 3&4, Equation 19&31, and discussions

Pumped-storage hydropower plants (PSH) actively participate in grid power-frequency control and therefore often operate under dynamic conditions, which results in rapidly varying system states. Predicting these dynamically changing states is essential for comprehending the underlying sensor and machine conditions. This understanding aids in detecting anomalies and faults, ensuring the reliable operation of the connected power grid, and in identifying faulty and miscalibrated sensors. PSH are complex, highly interconnected systems encompassing electrical and hydraulic subsystems, each characterized by their respective underlying networks that can individually be represented as graphs. To take advantage of this relational inductive bias, graph neural networks (GNNs) have been separately applied to state forecasting tasks in the individual subsystems, but without considering their interdependencies. In PSH, however, these subsystems depend on the same control input, making their operations highly interdependent and interconnected. Consequently, hydraulic and electrical sensor data should be fused across PSH subsystems to improve state forecasting accuracy. This approach has not been explored in GNN literature yet because many available PSH graphs are limited to their respective subsystem boundaries, which makes the method unsuitable to be applied directly. In this work, we introduce the application of spectral-temporal graph neural networks, which leverage self-attention mechanisms to concurrently capture and learn meaningful subsystem interdependencies and the dynamic patterns observed in electric and hydraulic sensors. Our method effectively fuses data from the PSH's subsystems by operating on a unified, system-wide graph, learned directly from the data, This approach leads to demonstrably improved state forecasting performance and enhanced generalizability., Comment: 11 pages, 8 figures, conference

Accurate bearing load monitoring is essential for their Prognostics and Health Management (PHM), enabling damage assessment, wear prediction, and proactive maintenance. While bearing sensors are typically placed on the bearing housing, direct load monitoring requires sensors inside the bearing itself. Recently introduced sensor rollers enable direct bearing load monitoring but are constrained by their battery life. Data-driven virtual sensors can learn from sensor roller data collected during a batterys lifetime to map operating conditions to bearing loads. Although spatially distributed bearing sensors offer insights into load distribution (e.g., correlating temperature with load), traditional machine learning algorithms struggle to fully exploit these spatial-temporal dependencies. To address this gap, we introduce a graph-based virtual sensor that leverages Graph Neural Networks (GNNs) to analyze spatial-temporal dependencies among sensor signals, mapping existing measurements (temperature, vibration) to bearing loads. Since temperature and vibration signals exhibit vastly different dynamics, we propose Heterogeneous Temporal Graph Neural Networks (HTGNN), which explicitly models these signal types and their interactions for effective load prediction. Our results demonstrate that HTGNN outperforms Convolutional Neural Networks (CNNs), which struggle to capture both spatial and heterogeneous signal characteristics. These findings highlight the importance of capturing the complex spatial interactions between temperature, vibration, and load., Comment: 8 pages, 6 figures