检索结果-内蒙古大学图书馆

Robust white matter hyperintensity segmentation on unseen domain

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhao, Xingchen Sicilia, Anthony Minhas, Davneet S. O’Connor, Erin E. Aizenstein, Howard J. Klunk, William E. Tudorascu, Dana L. Hwang, Seong Jae Intelligent Systems Program University of Pittsburgh Department United States Computer Science Radiology Psychiatry - University of Pittsburgh United States Department of Diagnostic Radiology Nuclear Medicine University of Maryland Baltimore United States

Typical machine learning frameworks heavily rely on an underlying assumption that training and test data follow the same distribution. In medical imaging which increasingly begun acquiring datasets from multiple sites or scanners, this identical distribution assumption often fails to hold due to systematic variability induced by site or scanner dependent factors. Therefore, we cannot simply expect a model trained on a given dataset to consistently work well, or generalize, on a dataset from another distribution. In this work, we address this problem, investigating the application of machine learning models to unseen medical imaging data. Specifically, we consider the challenging case of Domain Generalization (DG) where we train a model without any knowledge about the testing distribution. That is, we train on samples from a set of distributions (sources) and test on samples from a new, unseen distribution (target). We focus on the task of white matter hyperintensity (WMH) prediction using the multi-site WMH Segmentation Challenge dataset and our local in-house dataset. We identify how two mechanically distinct DG approaches, namely domain adversarial learning and mix-up, have theoretical synergy. Then, we show drastic improvements of WMH prediction on an unseen target domain. © 2021, CC BY.

关键词： Image segmentation

Bayesian quantum phase estimation with fixed photon states

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhou, Boyu Guha, Saikat Gagatsos, Christos N. Department of Physics The University of Arizona 1118 E 4th St TucsonAZ85721 United States Department of Electrical and Computer Engineering University of Maryland 2410 A.V. Williams Building College ParkMD20742 United States Wyant College of Optical Sciences The University of Arizona 1630 E University Blvd TucsonAZ85721 United States Department of Electrical and Computer Engineering The University of Arizona 1230 E Speedway Blvd TucsonAZ85721 United States Program in Applied Mathematics The University of Arizona 617 N. Santa Rita TucsonAZ85721 United States

We consider a two-mode bosonic state with fixed photon number n ∈ N, whose upper and lower modes pick up a phase and − respectively. We compute the optimal Fock coefficients of the input state, such that the mean square error (MSE) for estimating is minimized while the minimum MSE is always attainable by a measurement. Our setting is Bayesian, i.e., we consider to be a random variable that follows a prior probability distribution function (PDF). Initially, we consider the flat prior PDF and we discuss the well-known fact that the MSE is not an informative tool for estimating a phase when the variance of the prior PDF is large. Therefore, we move on to study truncated versions of the flat prior in both single-shot and adaptive approaches. For our adaptive technique we consider n = 1 and truncated prior PDFs. Each subsequent step utilizes as prior PDF the posterior probability of the previous step and at the same time we update the optimal state and optimal measurement. Copyright © 2023, The Authors. All rights reserved.

关键词： Distribution functions

Synthetic helicoidal rotation of a quasielectrostatic ring resonator for ultrabroadband magnet-free nonreciprocity

学校读者我要写书评

暂无评论

Physical Review Applied 2024年第6期22卷 064020-064020页

作者： Aravind Nagulu Ahmed Mekawy Mykhailo Tymchenko Dimitrios Sounas Harish Krishnaswamy Andrea Alù Department of Electrical and Systems Engineering Washington University in St. Louis St. Louis Missouri 63130 USA Photonics Initiative Advanced Science Research Center City University of New York New York New York 10031 USA Department of Electrical and Computer Engineering The University of Texas at Austin Austin Texas 78712 USA Department of Electrical Engineering Wayne State University Detroit Michigan 48202 USA Department of Electrical Engineering Columbia University New York New York 10027 USA Physics Program Graduate Center City University of New York New York New York 10016 USA

Suitably tailored forms of spatiotemporal modulation in electronic circuit networks have been recently employed to overcome fundamental challenges in modern electronic systems, including breaking reciprocity, squeezing the footprint of high-Q resonators, and overcoming the delay-bandwidth limit. Rotating patterns of temporal modulations have been used to synthesize angular momentum, which replaces magnetic bias to break reciprocity in integrated circuits. However, this approach is limited by trade-offs between modulation speed, footprint, and bandwidth of operation. Rotating switching patterns in commutated capacitor networks also enables compact filters and quasielectrostatic wave propagation, overcoming the delay-bandwidth limit. In this paper, we combine these mechanisms in an integrated-circuit ring that synthetically rotates in two dimensions, realizing an effective helicoidal motion that provides ultrabroadband quasielectrostatic nonreciprocal responses fitting within a theoretically infinitesimal size. We also analyze the impact of modulation signal noise on time-modulated nonreciprocal components and unveil the role of a dynamic noise mechanism based on which the noise level increases in the presence of a strong signal passing through the component, along with methods to mitigate this effect. We experimentally verify these principles in a three-port integrated circulator based on a 65-nm CMOS process that operates from dc to 1 GHz with a miniaturization factor of 2 × 106.

关键词： Metamaterials Non-reciprocal transmission Photonics Topolectrical circuits

A robust optimization approach for measuring efficiency in stochastic DEA

学校读者我要写书评

暂无评论

AIP Conference Proceedings 2023年第1期2714卷

作者： Hengki Tamando Sihotang Syahril Efendi Muhammad Zarlis Herman Mawengkang Doctoral Program Faculty of Computer Science and Information Technology Universitas Sumatera Utara. FEBO Indonesia Faculty of Computer Science and Information Technology Universitas Sumatera Utara. FEBO Indonesia Faculty of Mathematics and Natural Sciences Universitas Sumatera Utara. FEBO Indonesia

The classic data envelopment analysis (DEA) concept assumes that decision making unit (DMU) inputs and outputs can be clearly measured because they have definite values. However, there are times when there is uncertainty in a situation. This study looks at how to build a DEA model with input and output uncertainty. In the DEA model, the uncertainty situation is approached using a stochastic concept. Furthermore, the robust optimization method, which can solve the uncertainty problem, is introduced. As a result, at the conclusion of this study, a robust optimization model based on the Stochastic DEA concept is introduced.

关键词：

Nonsaturated large magnetoresistance and transport dynamics in a n-doped cryogenic WSe2 field-effect device

学校读者我要写书评

暂无评论

Physical Review B 2025年第12期111卷 125307-125307页

作者： Wei-Chen Lin Ching-Chen Yeh Jia-Zhu Zou Nhat Anh Nguyen Phan Inayat Uddin Hai Yen Le Thi Kenji Watanabe Takashi Taniguchi Gil-Ho Kim Department of Engineering and System Science National Tsing Hua University Hsinchu 300 Taiwan Taiwan International Graduate Program Academia Sinica Taipei 115 Taiwan Department of Physics National Taiwan University Taipei 106 Taiwan Department of Electrical and Computer Engineering Sungkyunkwan University (SKKU) Suwon 164 Republic of Korea Sungkyunkwan Advanced Institute of Nano Technology (SAINT) Sungkyunkwan University (SKKU) Suwon 16419 Republic of Korea Research Center for Electronic and Optical Materials National Institute for Materials Science 1-1 Namiki Tsukuba 305-0044 Japan Research Center for Materials Nanoarchitectonics National Institute for Materials Science 1-1 Namiki Tsukuba 305-0044 Japan

Interest in the two-dimensional (2D) semiconducting transition metal dichalcogenides (TMDs) continues to intensify, driven by their suitable band gaps to supplant silicon as next-generation semiconductor materials. Among various TMDs, tungsten diselenide (WSe2) is renowned for its superior electrical properties in carrier density and mobility under ambient conditions. Despite its notable attributes, the behavior of monolayer WSe2 in the electron-doped regime under cryogenic conditions remains largely uncharted, particularly concerning its magnetotransport properties. In this study, we reveal the transport mechanisms of monolayer WSe2 from high temperatures down to the cryogenic regime. As evident by Efros–Shklovskii variable-range hopping (E-S VRH) in the cryogenic regime, strong Coulomb interactions arise between electrons. Above 8 K, an uncommon nonsaturated quadratic large magnetoresistance (MR) can be explained by the wave-function shrinkage model, which is consistent with the E-S VRH transport mechanism. Notably, the nonsaturated quadratic large MR shows a magnitude up to 1740% at 13 T. These findings underscore the potential applications for monolayer WSe2 in cryogenic field-effect devices, magnetic sensors, and memory devices and mark a significant advance in magnetotransport research.

关键词： Monolayers

Distributionally Robust Chance-Constrained Optimal Transmission Switching for Renewable Integration

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhou, Yuqi Zhu, Hao Hanasusanto, Grani A. The Department of Electrical & Computer Engineering The University of Texas at Austin AustinTX78712 United States The Graduate Program in Operations Research & Industrial Engineering The University of Texas at Austin AustinTX78712 United States

Increasing integration of renewable generation poses significant challenges to ensure robustness guarantees in real-time energy system decision-making. This work aims to develop a robust optimal transmission switching (OTS) framework that can effectively relieve grid congestion and mitigate renewable curtailment. We formulate a two-stage distributionally robust chance-constrained (DRCC) problem that assures limited constraint violations for any uncertainty distribution within an ambiguity set. Here, the second-stage recourse variables are represented as linear functions of uncertainty, yielding an equivalent reformulation involving linear constraints only. We utilize moment-based (mean-mean absolute deviation) and distance-based (∞-Wasserstein distance) ambiguity sets that lead to scalable mixed-integer linear program (MILP) formulations. Numerical experiments on the IEEE 14-bus and 118-bus systems have demonstrated the performance improvements of the proposed DRCC-OTS approaches in terms of guaranteed constraint violations and reduced renewable curtailment. In particular, the computational efficiency of the moment-based MILP approach, which is scenario-free with fixed problem dimensions, has been confirmed, making it suitable for real-time grid operations. Copyright © 2021, The Authors. All rights reserved.

关键词： Computational efficiency

Predicting Stress and Providing Counterfactual Explanations: A Pilot Study on Caregivers

学校读者我要写书评

暂无评论

Predicting Stress and Providing Counterfactual Explanations:...

International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW)

作者： Kei Shibuya Zachary D King Maryam Khalid Han Yu Yufei Shen Khadija Zanna Ryan L Brown Marzieh Majd Christopher P Fagunders Akane Sano Dept. of Electrical and Computer Engineering Rice University Houston U.S. Biometrics Research Laboratories. NEC Corporation Tokyo Japan Dept. of Electrical and Computer Engineering The University of Texas Austin U.S Dept. of Psychiatry and Behavioral Sciences University of California San Francisco San Francisco U.S Dept. of Psychiatry Harvard Medical School Boston U.S Dept. of Psychiatry Mood and Psychosis Research Program Brigham and Women’s Hospital Boston U.S Dept. of Psychological Science Rice University Houston U.S

Caregiving for spouses with Alzheimer’s disease or related dementias (ADRD) is one of the most stressful experiences. Evidence-based treatments for caregivers who have a high risk of mental health issues are needed. In this study, we designed models for predicting changes in perceived stress scale (PSS) (increase/not increase) in one week and generated some examples of counterfactual (’what-if’) explanations to change the stress state for helping manage stress. Using self-report (positive and negative affect and sleep quality) and sensor data (heart rate, sleep, and steps) collected in 132 week-long study sessions from 57 participants, we compared explainable PSS change prediction models (Random Forest, XGBoost, LightGBM, EBM, and Neural Network) along with ’what-if’ explanations. First, we developed machine learning models for classifying the change in PSS scores before and after the session period. Second, we identified feature importance using our explainable models. Our results showed that XGBoost performed the best with an accuracy of 0.79 and an F1 score of 0.78 for predicting changes in perceived stress. Our results also showed that minimum heart rate, mean steps per day, and negative affect are the most predictive features. Our preliminary counterfactual examples about sleep parameters would be able to provide suggestions for improving one’s health. We discussed our ideas to provide better suggestions using DiCE.

关键词：

Framework for tackling stochastic DEA based on data-driven approach

学校读者我要写书评

暂无评论

AIP Conference Proceedings 2023年第1期2714卷

作者： Hengki Tamando Sihotang Syahril Efendi Muhammad Zarlis Herman Mawengkang Doctoral Program Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia Faculty of Mathematics and Natural Sciences Universitas Sumatera Utara Medan Indonesia

Data Envelopment Analysis (DEA) is a linear programming-based technique used to evaluate the relative efficiency of multi-input and multi-output decision-making units based on observed data by comparing one decision-making unit (DMU) with another DMU. The efficacy assessment process sometimes involves a stochastic approach due to the uncertainty inherent in many real life problems, so the DEA model discussed in this paper is the stochastic DEA (SDEA) model. Data-driven decision-making is based entirely on the data involved. This paper proposes a framework for the completion of SDEA based on a data-driven approach.

关键词：

Flexible dual-branched message passing neural network for quantum mechanical property prediction with molecular conformation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Jo, Jeonghee Kwak, Bumju Lee, Byunghan Yoon, Sungroh Interdisciplinary Program in Bioinformatics Seoul National University Recommendation Team Kakao Corporation Department of Electronic and IT Media Engineering Seoul National University of Science and Technology Department of Electrical and Computer Engineering Seoul National University

A molecule is a complex of heterogeneous components, and the spatial arrangements of these components determine the whole molecular properties and characteristics. With the advent of deep learning in computational chemistry, several studies have focused on how to predict molecular properties based on molecular configurations. Message passing neural network provides an effective framework for capturing molecular geometric features with the perspective of a molecule as a graph. However, most of these studies assumed that all heterogeneous molecular features, such as atomic charge, bond length, or other geometric features always contribute equivalently to the target prediction, regardless of the task type. In this study, we propose a dual-branched neural network for molecular property prediction based on message-passing framework. Our model learns heterogeneous molecular features with different scales, which are trained flexibly according to each prediction target. In addition, we introduce a discrete branch to learn single atom features without local aggregation, apart from message-passing steps. We verify that this novel structure can improve the model performance with faster convergence in most targets. The proposed model outperforms other recent models with sparser representations. Our experimental results indicate that in the chemical property prediction tasks, the diverse chemical nature of targets should be carefully considered for both model performance and generalizability. © 2021, CC BY.

关键词： Deep learning