Search

Calibrating simulation models that take large quantities of multi-dimensional data as input is a hard simulation optimization problem. Existing adaptive sampling strategies offer a methodological solution. However, they may not sufficiently reduce the computational cost for estimation and solution algorithm's progress within a limited budget due to extreme noise levels and heteroskedasticity of system responses. We propose integrating stratification with adaptive sampling for the purpose of efficiency in optimization. Stratification can exploit local dependence in the simulation inputs and outputs. Yet, the state-of-the-art does not provide a full capability to adaptively stratify the data as different solution alternatives are evaluated. We devise two procedures for data-driven calibration problems that involve a large dataset with multiple covariates to calibrate models within a fixed overall simulation budget. The first approach dynamically stratifies the input data using binary trees, while the second approach uses closed-form solutions based on linearity assumptions between the objective function and concomitant variables. We find that dynamical adjustment of stratification structure accelerates optimization and reduces run-to-run variability in generated solutions. Our case study for calibrating a wind power simulation model, widely used in the wind industry, using the proposed stratified adaptive sampling, shows better-calibrated parameters under a limited budget.

This paper presents a robust version of the stratified sampling method when multiple uncertain input models are considered for stochastic simulation. Various variance reduction techniques have demonstrated their superior performance in accelerating simulation processes. Nevertheless, they often use a single input model and further assume that the input model is exactly known and fixed. We consider more general cases in which it is necessary to assess a simulation's response to a variety of input models, such as when evaluating the reliability of wind turbines under nonstationary wind conditions or the operation of a service system when the distribution of customer inter-arrival time is heterogeneous at different times. Moreover, the estimation variance may be considerably impacted by uncertainty in input models. To address such nonstationary and uncertain input models, we offer a distributionally robust (DR) stratified sampling approach with the goal of minimizing the maximum of worst-case estimator variances among plausible but uncertain input models. Specifically, we devise a bi-level optimization framework for formulating DR stochastic problems with different ambiguity set designs, based on the $L_2$-norm, 1-Wasserstein distance, parametric family of distributions, and distribution moments. In order to cope with the non-convexity of objective function, we present a solution approach that uses Bayesian optimization. Numerical experiments and the wind turbine case study demonstrate the robustness of the proposed approach.

In comparison to the original Tolman VII model, Exact Modified Tolman VII (EMTVII) with one additional parameter can increase the compactness of compact object. When the compactness is in the ultracompact regime, the quasinormal modes~(QNMs) of the trapped mode as well as the gravitational echoes become more viable. Starting with the EMTVII model, we introduce nonlocality into the matter sector and analyze the effective potential, the QNMs, and the gravitational echoes of the compact and ultracompact object in the nonlocal model. The nonlocal gravity version of EMTVII~(NEMTVII) is parametrized by the nonlocal parameter~($ \beta $), modified Tolman VII parameter ($ \alpha $), and the compactness ($ \mathcal{C}$). It is found that the nonlocal profile produces the smeared surface and consequently reduce the compactness. The maximum compactness $\mathcal{C}_{max}=0.4$ occurs when $\alpha=0=\beta$, i.e., EMTVII with no smearing. For relatively small value of $\beta = 0.01$ and the compactness $ \mathcal{C} \lesssim 0.2667$~(with $M=2.14$ solar masses, $R=11.835$ km at $\alpha=1.4$), the causality condition and the dominant energy condition~(DEC) are satisfied. The quasinormal modes of the gravitational perturbation are calculated using Bohr-Sommerfeld (BS) fitting and we find that the nonlocality produces less trapped modes than the original (EMTVII) counterpart. At high compactness, gravitational echoes are simulated numerically. Echoes are found to exist in the parameter space where the dominant energy condition and the causality condition are violated., Comment: 35 pages, 12 figures, 4 tables

Accurate lung nodule segmentation is crucial for early-stage lung cancer diagnosis, as it can substantially enhance patient survival rates. Computed tomography (CT) images are widely employed for early diagnosis in lung nodule analysis. However, the heterogeneity of lung nodules, size diversity, and the complexity of the surrounding environment pose challenges for developing robust nodule segmentation methods. In this study, we propose an efficient end-to-end framework, the multi-encoder-based self-adaptive hard attention network (MESAHA-Net), for precise lung nodule segmentation in CT scans. MESAHA-Net comprises three encoding paths, an attention block, and a decoder block, facilitating the integration of three types of inputs: CT slice patches, forward and backward maximum intensity projection (MIP) images, and region of interest (ROI) masks encompassing the nodule. By employing a novel adaptive hard attention mechanism, MESAHA-Net iteratively performs slice-by-slice 2D segmentation of lung nodules, focusing on the nodule region in each slice to generate 3D volumetric segmentation of lung nodules. The proposed framework has been comprehensively evaluated on the LIDC-IDRI dataset, the largest publicly available dataset for lung nodule segmentation. The results demonstrate that our approach is highly robust for various lung nodule types, outperforming previous state-of-the-art techniques in terms of segmentation accuracy and computational complexity, rendering it suitable for real-time clinical implementation.

Universal approaches have not sufficiently improved higher education outcomes for Black, Latino, and Indigenous students, and students from low-income backgrounds because these broad interventions are not targeted toward specific populations. Student voices and interests must be centered in policy and practice, and higher education leaders and institutions that work with and on behalf of Black, Latino, or Indigenous students are well positioned to identify the programs, partnerships, and investments that will most benefit those students. Having clear alignment on the high impact policy and programmatic priorities of these higher education leaders helps funders, policymakers, and technical assistance providers make investments that are more racially equitable. The Education Trust convened key leaders from a number of intermediary higher education organizations to discuss policy and programmatic priorities that would support the equitable distribution and implementation of public and private higher education funding. Panelists and participants repeatedly highlighted five priorities that will help to ensure equity in these higher education investments: (1) Put student voices first; (2) Rely on existing experts and invest in building expertise; (3) Build cultural competence and show humility toward students, their communities, and the organizations that represent them; (4) Interrogate data and reevaluate underlying assumptions and metrics; and (5) Focus on flexible dollars that institutions can use to address students' greatest needs.

In this study, we propose a lung nodule detection scheme which fully incorporates the clinic workflow of radiologists. Particularly, we exploit Bi-Directional Maximum intensity projection (MIP) images of various thicknesses (i.e., 3, 5 and 10mm) along with a 3D patch of CT scan, consisting of 10 adjacent slices to feed into self-distillation-based Multi-Encoders Network (MEDS-Net). The proposed architecture first condenses 3D patch input to three channels by using a dense block which consists of dense units which effectively examine the nodule presence from 2D axial slices. This condensed information, along with the forward and backward MIP images, is fed to three different encoders to learn the most meaningful representation, which is forwarded into the decoded block at various levels. At the decoder block, we employ a self-distillation mechanism by connecting the distillation block, which contains five lung nodule detectors. It helps to expedite the convergence and improves the learning ability of the proposed architecture. Finally, the proposed scheme reduces the false positives by complementing the main detector with auxiliary detectors. The proposed scheme has been rigorously evaluated on 888 scans of LUNA16 dataset and obtained a CPM score of 93.6\%. The results demonstrate that incorporating of bi-direction MIP images enables MEDS-Net to effectively distinguish nodules from surroundings which help to achieve the sensitivity of 91.5% and 92.8% with false positives rate of 0.25 and 0.5 per scan, respectively.

Most recent studies have shown several vulnerabilities to attacks with the potential to jeopardize the integrity of the model, opening in a few recent years a new window of opportunity in terms of cyber-security. The main interest of this paper is directed towards data poisoning attacks involving label-flipping, this kind of attacks occur during the training phase, being the aim of the attacker to compromise the integrity of the targeted machine learning model by drastically reducing the overall accuracy of the model and/or achieving the missclassification of determined samples. This paper is conducted with intention of proposing two new kinds of data poisoning attacks based on label-flipping, the targeted of the attack is represented by a variety of machine learning classifiers dedicated for malware detection using mobile exfiltration data. With that, the proposed attacks are proven to be model-agnostic, having successfully corrupted a wide variety of machine learning models; Logistic Regression, Decision Tree, Random Forest and KNN are some examples. The first attack is performs label-flipping actions randomly while the second attacks performs label flipping only one of the 2 classes in particular. The effects of each attack are analyzed in further detail with special emphasis on the accuracy drop and the misclassification rate. Finally, this paper pursuits further research direction by suggesting the development of a defense technique that could promise a feasible detection and/or mitigation mechanisms; such technique should be capable of conferring a certain level of robustness to a target model against potential attackers., Comment: arXiv admin note: substantial text overlap with arXiv:2202.10276

Accurate segmentation of mandibular canals in lower jaws is important in dental implantology. Medical experts determine the implant position and dimensions manually from 3D CT images to avoid damaging the mandibular nerve inside the canal. In this paper, we propose a novel dual-stage deep learning-based scheme for the automatic segmentation of the mandibular canal. Particularly, we first enhance the CBCT scans by employing the novel histogram-based dynamic windowing scheme, which improves the visibility of mandibular canals. After enhancement, we design 3D deeply supervised attention U-Net architecture for localizing the volumes of interest (VOIs), which contain the mandibular canals (i.e., left and right canals). Finally, we employed the multi-scale input residual U-Net architecture (MS-R-UNet) to segment the mandibular canals using VOIs accurately. The proposed method has been rigorously evaluated on 500 scans. The results demonstrate that our technique outperforms the current state-of-the-art segmentation performance and robustness methods., Comment: 7 Pages

Here, we correlate the nanoscale morphology and chemical composition of solid electrolyte interphases (SEI) with the electrochemical property of graphite-based composite electrodes. Using electrochemical strain microscopy (ESM) and X-ray photoelectron spectroscopy (XPS), changes of chemical composition and morphology (Li and F distribution) in SEI layers on the electrodes as a function of solid electrolyte contents are analyzed. As a result, we find a strong correlation between morphological variations on the electrode, Li and F distribution in SEI layer, and Coulomb efficiency. This correlation determines the optimum composition of the composite electrode surface that can maximize the physical and chemical uniformity of the solid electrolyte on the electrode, which is a key parameter to increase electrochemical performance in solid-state batteries., Comment: 35 pages, 13 figures

We present MLNav, a learning-enhanced path planning framework for safety-critical and resource-limited systems operating in complex environments, such as rovers navigating on Mars. MLNav makes judicious use of machine learning to enhance the efficiency of path planning while fully respecting safety constraints. In particular, the dominant computational cost in such safety-critical settings is running a model-based safety checker on the proposed paths. Our learned search heuristic can simultaneously predict the feasibility for all path options in a single run, and the model-based safety checker is only invoked on the top-scoring paths. We validate in high-fidelity simulations using both real Martian terrain data collected by the Perseverance rover, as well as a suite of challenging synthetic terrains. Our experiments show that: (i) compared to the baseline ENav path planner on board the Perserverance rover, MLNav can provide a significant improvement in multiple key metrics, such as a 10x reduction in collision checks when navigating real Martian terrains, despite being trained with synthetic terrains; and (ii) MLNav can successfully navigate highly challenging terrains where the baseline ENav fails to find a feasible path before timing out., Comment: IEEE Robotics and Automation Letters (RA-L) and ICRA 2022

Machine learning models have been widely adopted in several fields. However, most recent studies have shown several vulnerabilities from attacks with a potential to jeopardize the integrity of the model, presenting a new window of research opportunity in terms of cyber-security. This survey is conducted with a main intention of highlighting the most relevant information related to security vulnerabilities in the context of machine learning (ML) classifiers; more specifically, directed towards training procedures against data poisoning attacks, representing a type of attack that consists of tampering the data samples fed to the model during the training phase, leading to a degradation in the models accuracy during the inference phase. This work compiles the most relevant insights and findings found in the latest existing literatures addressing this type of attacks. Moreover, this paper also covers several defense techniques that promise feasible detection and mitigation mechanisms, capable of conferring a certain level of robustness to a target model against an attacker. A thorough assessment is performed on the reviewed works, comparing the effects of data poisoning on a wide range of ML models in real-world conditions, performing quantitative and qualitative analyses. This paper analyzes the main characteristics for each approach including performance success metrics, required hyperparameters, and deployment complexity. Moreover, this paper emphasizes the underlying assumptions and limitations considered by both attackers and defenders along with their intrinsic properties such as: availability, reliability, privacy, accountability, interpretability, etc. Finally, this paper concludes by making references of some of main existing research trends that provide pathways towards future research directions in the field of cyber-security.

Asian American and Pacific Islander (AAPI) communities are growing at a faster rate than any other racial group in the United States. The opportunity to address significant inequities impacting this community is hiding in our country's postsecondary data. Collections of data at the U.S. Department of Education and our institutions of higher education aggregate AAPI communities under the umbrella categories of "Asian" or "Native Hawaiian or Other Pacific Islander." As a result, the data mask inequities and decrease efforts to provide intentional student supports. To address this missed opportunity, the Institute for Higher Education Policy (IHEP) and the Southeast Asia Resource Action Center (SEARAC) released "Everyone Deserves to be Seen. Recommendations for Improved Federal Data on Asian Americans and Pacific Islanders." The report sets forth clear policy recommendations for Congress, federal, state, and local agencies, and institutions of higher education. The actionable recommendations look to the race and ethnicity categories used by the U.S. Census Bureau, which are informed by empirical research, collaboration between statistical agencies across the federal government, and engagement of diverse communities. This report is part of IHEP's call for quality data to support evidence-based policymaking and close equity gaps in access to and success in postsecondary education. [Edited by Amanda Janice Roberson. This publication is jointly authored by the Institute for Higher Education Policy (IHEP) and the Southeast Asia Resource Action Center (SEARAC).]

The Internet of Things (IoT) is on the verge of a major paradigm shift. In the IoT system of the future, IoFT, the cloud will be substituted by the crowd where model training is brought to the edge, allowing IoT devices to collaboratively extract knowledge and build smart analytics/models while keeping their personal data stored locally. This paradigm shift was set into motion by the tremendous increase in computational power on IoT devices and the recent advances in decentralized and privacy-preserving model training, coined as federated learning (FL). This article provides a vision for IoFT and a systematic overview of current efforts towards realizing this vision. Specifically, we first introduce the defining characteristics of IoFT and discuss FL data-driven approaches, opportunities, and challenges that allow decentralized inference within three dimensions: (i) a global model that maximizes utility across all IoT devices, (ii) a personalized model that borrows strengths across all devices yet retains its own model, (iii) a meta-learning model that quickly adapts to new devices or learning tasks. We end by describing the vision and challenges of IoFT in reshaping different industries through the lens of domain experts. Those industries include manufacturing, transportation, energy, healthcare, quality & reliability, business, and computing., Comment: Accepted at IEEE