Article
Engineering, Geological
Zening Zhao, Surya Sarat Chandra Congress, Guojun Cai, Wei Duan
Summary: The study proposed a Bayesian inference approach combined with total probability theorem to obtain the updated distributions of c(h) from a limited number of test data, recommending the use of model M-2 for calculating c(h).
Article
Engineering, Mechanical
P. L. Green, L. J. Devlin, R. E. Moore, R. J. Jackson, J. Li, S. Maskell
Summary: This paper discusses the optimization of the 'L-kernel' in Sequential Monte Carlo samplers to improve performance, resulting in reduced variance of estimates and fewer resampling requirements.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Computer Science, Interdisciplinary Applications
Kuhwan Jeong, Minwoo Chae, Yongdai Kim
Summary: The Dirichlet process (DP) mixture model is commonly used for clustering and density estimation. Despite the development of Markov chain Monte Carlo algorithms, the computational costs of DP mixture models make them impractical for analyzing large data. To address this, we propose a novel mini-batch online learning algorithm based on assumed density filtering, which improves performance relative to existing online algorithms based on variational inference by leveraging available computing resources.
COMPUTATIONAL STATISTICS & DATA ANALYSIS
(2023)
Article
Computer Science, Artificial Intelligence
Oriol Abril-Pla, Virgile Andreani, Colin Carroll, Larry Dong, Christopher J. Fonnesbeck, Maxim Kochurov, Ravin Kumar, Junpeng Lao, Christian C. Luhmann, Osvaldo A. Martin, Michael Osthege, Ricardo Vieira, Thomas Wiecki, Robert Zinkov
Summary: PyMC is a Python library for probabilistic programming that facilitates the construction and fitting of Bayesian models. It features an intuitive and readable syntax, similar to the natural language used by statisticians to describe models. PyMC leverages the symbolic computation library PyTensor, allowing it to be compiled into various computational backends, such as C, JAX, and Numba, providing access to different computational architectures including CPU, GPU, and TPU. With its versatility and ease of use, PyMC supports a wide range of models including hierarchical linear regression and classification, time series, ODEs, and non-parametric models like Gaussian processes (GPs). Examples demonstrating PyMC's capabilities are provided, along with a discussion on its positive impact in the open-source ecosystem for probabilistic programming.
PEERJ COMPUTER SCIENCE
(2023)
Article
Construction & Building Technology
Zhibin Li, Wenping Gong, Tianzheng Li, C. Hsein Juang, Jun Chen, Lei Wang
Summary: The Bayesian theory provides a method for updating uncertainties in geotechnical systems, with the new probabilistic back analysis method considering all uncertainties and incorporating multiple observations to improve reliability. The posterior distributions of uncertain variables are derived through MCMC simulation based on the Hamiltonian Monte Carlo algorithm, showing efficiency and effectiveness in updating statistical information stage by stage.
TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY
(2021)
Article
Engineering, Mechanical
Karthik Reddy Lyathakula, Fuh-Gwo Yuan
Summary: The paper presents an efficient and robust probabilistic fatigue life prediction framework for adhesively bonded joints, calibrating the fatigue life model with experimental data and utilizing probabilistic assessment and neural networks for prediction. This framework allows rapid simulation of fatigue degradation and quantification of uncertainties for probabilistic fatigue life prediction in various joint configurations.
INTERNATIONAL JOURNAL OF FATIGUE
(2021)
Article
Engineering, Mechanical
Adolphus Lye, Alice Cicirello, Edoardo Patelli
Summary: This tutorial paper reviews the use of advanced Monte Carlo sampling methods in Bayesian model updating for engineering applications, introducing different methods and comparing their performance. Three case studies demonstrate the advantages and limitations of these sampling techniques in parameter identification, posterior distribution sampling, and stochastic identification of model parameters.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2021)
Article
Engineering, Civil
Partha Sengupta, Subrata Chakraborty
Summary: This study aims to explore the effectiveness of the Bayesian approach of model parameters updating using Markov Chain Monte Carlo (MCMC) technique considering the prediction error variances for both the frequencies and mode shapes. The prior distributions of prediction error variances of modal evidences are implemented through inverse gamma distribution to assess the effectiveness of estimation of posterior values of model parameters, and a regularization technique is adopted to deal with the issue of incomplete data.
STRUCTURAL ENGINEERING AND MECHANICS
(2022)
Article
Engineering, Geological
Jiabao Xu, Lulu Zhang, Jinhui Li, Zijun Cao, Haoqing Yang, Xiangyu Chen
Summary: This study explores the ability of Bayesian inference using MCMC simulation to accurately estimate the variogram of geotechnical properties with a trend, presenting predictive uncertainty and total uncertainty bounds. Analysis of 200 measurements of q(c) data confirms the accuracy and feasibility of this method.
GEORISK-ASSESSMENT AND MANAGEMENT OF RISK FOR ENGINEERED SYSTEMS AND GEOHAZARDS
(2021)
Article
Computer Science, Interdisciplinary Applications
Karthik Reddy Lyathakula, Fuh-Gwo Yuan
Summary: This work presents a framework for online prognostics in adhesive joints by using hybrid physics models and vectorized sequential Monte Carlo simulations. The framework integrates a physics-based damage degradation model and uncertainty quantification techniques to estimate probabilistic fatigue failure life and remaining useful life. The results demonstrate the effectiveness of the framework in estimating fatigue failure life and remaining useful life, and the parallelization of the sampling process significantly reduces computational time and enables real-time prediction. The framework is also portable and can be deployed on a Raspberry Pi cluster.
ADVANCES IN ENGINEERING SOFTWARE
(2023)
Article
Construction & Building Technology
Hai-Bin Huang, Wei Zhang, Zhi-Guo Sun, Dong-Sheng Wang
Summary: In this study, a probabilistic approach is proposed to improve the predictive accuracy and uncertainty quantification of existing deterministic bond strength models for EB FRP-to-concrete joints. Through evaluation and calibration using an experimental database, the proposed probabilistic models are capable of accurately predicting the bond strength of EB FRP-to-concrete joints and quantifying the corresponding uncertainties.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Engineering, Geological
Chao Zhao, Wenping Gong, Tianzheng Li, C. Hsein Juang, Huiming Tang, Hui Wang
Summary: Accurate characterization of subsurface stratigraphic configuration is crucial to geotechnical engineering work, but uncertainty can be significant due to complexity and limited data availability. This paper presents a method for characterizing subsurface stratigraphy with limited borehole data, demonstrating its effectiveness and advantages through comparative analyses and a case study in Western Australia.
ENGINEERING GEOLOGY
(2021)
Review
Statistics & Probability
Christopher Nemeth, Paul Fearnhead
Summary: MCMC algorithms are considered the gold standard technique for Bayesian inference, but the computational cost can be prohibitive for large datasets, leading to the development of scalable Monte Carlo algorithms. One type of these algorithms is SGMCMC, which reduces per-iteration cost by utilizing data subsampling techniques.
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
(2021)
Article
Environmental Sciences
Yu-Syuan Luo
Summary: Monitoring programs have been implemented globally to assess fipronil residues in food, but previous exposure assessments have often focused on specific food categories or subsets, resulting in limited insights into the overall health risks. To address these issues, a probabilistic exposure assessment and dose-response analysis were adopted in this study, considering the sample distribution below the detection limit to better characterize uncertainties and population variability in health risk assessments. By incorporating the uncertainties in exposure and dose-response data, a more comprehensive understanding of the health risks associated with fipronil exposure in the Taiwanese population has been achieved.
Article
Construction & Building Technology
Qi-Sen Chen, Bo Yu, Bing Li
Summary: This study updated probabilistic models based on Bayesian theory and Markov Chain Monte Carlo, calibrated deterministic models for concrete axial compressive behavior, and evaluated performance under different conditions while individually analyzing different types of FRP, providing an efficient approach to enhance the confidence level and computational accuracy of deterministic models in literature.
CONSTRUCTION AND BUILDING MATERIALS
(2021)
Article
Multidisciplinary Sciences
Rakshit Kothari, Zhizhuo Yang, Christopher Kanan, Reynold Bailey, Jeff B. Pelz, Gabriel J. Diaz
SCIENTIFIC REPORTS
(2020)
Article
Ophthalmology
Preethi Vaidyanathan, Emily Prud'hommeaux, Cecilia O. Alm, Jeff B. Pelz
Article
Health Care Sciences & Services
Christopher Michael Homan, J. Nicolas Schrading, Raymond W. Ptucha, Catherine Cerulli, Cecilia Ovesdotter Alm
JOURNAL OF MEDICAL INTERNET RESEARCH
(2020)
Article
Computer Science, Information Systems
Christopher Bondy, Linlin Chen, Pamela Grover, Vicki Hanson, Rui Li, Pengcheng Shi
Summary: This paper introduces a cross-disciplinary evaluation method - Collaborative Space - Analysis Framework (CS-AF), designed to evaluate technology-mediated collaborative workflows. Through a 5-step meta-process, the CS-AF systematically analyzes gains and gaps of collaborative workflows, providing critical data for continuous workflow improvement.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2021)
Article
Biology
Zhaotao Wu, Jia Wei, Jiabing Wang, Rui Li
Summary: This study introduces a novel frame-interpolation-based method for slice imputation to improve segmentation accuracy for anisotropic 3D medical images. Unlike previous methods, this study focuses on improving the smoothness of the interpolated 3D medical volumes in all three directions: axial, sagittal, and coronal. The proposed method incorporates a smoothness loss function to evaluate the smoothness in the through-plane direction and improves the resolution and isotropy of the interpolated volumes, leading to better segmentation performance.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Biology
Zecheng Liu, Jia Wei, Rui Li, Jianlong Zhou
Summary: Brain cancer is highly dangerous due to the importance of the brain as the primary command center. Automatic segmentation of brain tumors from multi-modal images is crucial for diagnosis and treatment. This study proposes a novel curriculum disentanglement learning framework for unimodal segmentation using limited paired images, which outperforms competing models on unimodal segmentation and demonstrates improved multi-modal segmentation performance.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
A'di Dust, Carola Gonzalez-Lebron, Shannon Connell, Saurav Singh, Reynold Bailey, Cecillia Ovesdotter Alm, Jamison Heard
Summary: With the development of industry 4.0, research is focusing on understanding the differences in interaction between hearing and deaf and hard of hearing individuals when collaborating with cobots. This understanding can lead to inclusive designs and strategies for more effective human-cobot interaction.
COMPANION OF THE ACM/IEEE INTERNATIONAL CONFERENCE ON HUMAN-ROBOT INTERACTION, HRI 2023
(2023)
Proceedings Paper
Computer Science, Theory & Methods
Cecilia O. Alm, Reynold Bailey, Hannah Miller
Summary: This paper provides an experience report on a remote framework for early undergraduate research experiences focused on sensing humans computationally. The framework consists of three components: team-based research cycle, professional development activities, and cohort-networking programming. The authors discuss the challenges and opportunities of remote training and evaluate its effectiveness through reflections and interviews.
PROCEEDINGS OF THE 53RD ACM TECHNICAL SYMPOSIUM ON COMPUTER SCIENCE EDUCATION (SIGCSE 2022), VOL 1
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Farhad Akhbardeh, Cecilia Ovesdotter Alm, Marcos Zampieri, Travis Desell
Summary: Technical logbooks are challenging text types in automated event identification due to their short length, non-standard yet technical language, and class imbalance issues. This paper introduces a feedback strategy from computer vision to handle extreme class imbalance, which significantly improves technical issue classification across various domains and datasets. This generic feedback strategy could be applied to any learning problem with substantial class imbalances.
59TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 11TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (ACL-IJCNLP 2021), VOL 1
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Cecilia O. Alm, Alex Hedges
Summary: This study explores the use of open-source NLP capabilities in a web interface to enhance undergraduate students' understanding of formal natural language structures, encouraging critical thinking and evaluation of AI systems. The research emphasizes inclusivity in education resources and the importance of making AI systems interpretable for multi-disciplinary interest.
THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE
(2021)
Proceedings Paper
Computer Science, Cybernetics
Natalie Maus, Dalton Rutledge, Sedeeq Al-Khazraji, Reynold Bailey, Cecilia Ovesdotter Alm, Kristen Shinohara
CHI'20: EXTENDED ABSTRACTS OF THE 2020 CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Devarth Parikh, Yawen Lu, Yuan Xin, Di Wu, Jeff Pelz, Guoyu Lu
2019 7TH IEEE GLOBAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING (IEEE GLOBALSIP)
(2019)
Proceedings Paper
Computer Science, Interdisciplinary Applications
Preethi Vaidyanathan, Emily Prud'hommeaux, Jeff B. Pelz, Cecilia O. Alm
PROCEEDINGS OF THE 56TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 2
(2018)
Article
Ophthalmology
Aayush K. Chaudhary, Jeff B. Pelz
JOURNAL OF EYE MOVEMENT RESEARCH
(2019)
Article
Computer Science, Artificial Intelligence
Chenglong Li, Xiaobin Yang, Guohao Wang, Aihua Zheng, Chang Tan, Jin Tang
Summary: License plate recognition is crucial in various practical applications, however, recognizing license plates of large vehicles is challenging due to low resolution, contamination, low illumination, and occlusion. To address this problem, a novel data generation framework based on the Disentangled Generation Network is proposed to ensure the generation diversity and integrity for robust enlarged license plate recognition.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2024)
Article
Computer Science, Artificial Intelligence
Sara Casao, Alvaro Serra-Gomez, Ana C. Murillo, Wendelin Bohmer, Javier Alonso-Mora, Eduardo Montijano
Summary: This paper presents a hybrid camera system that combines static and mobile cameras, exploiting the cooperation between tracking and control modules to achieve high-level scene understanding. The static camera network provides global awareness, while the mobile cameras enhance the information about the people on the scene.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2024)
Article
Computer Science, Artificial Intelligence
Anh-Dzung Doan, Bach Long Nguyen, Surabhi Gupta, Ian Reid, Markus Wagner, Tat-Jun Chin
Summary: To ensure reliable object detection in autonomous systems, the detector needs to adapt to changes in appearance caused by environmental factors. We propose a selective adaptation approach using domain gap as a criterion to improve the efficiency of the detector's operation.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2024)
Article
Computer Science, Artificial Intelligence
Tianhong Dai, Wei Li, Xilei Cao, Jianzhuang Liu, Xu Jia, Ales Leonardis, Youliang Yan, Shanxin Yuan
Summary: This study proposes a novel frequency-guided deep neural network (FHDRNet) for high dynamic range (HDR) imaging from multiple low dynamic range (LDR) images, aiming to address ghosting artifacts. By conducting HDR fusion in the frequency domain, the network utilizes low-frequency signals to remove specific ghosting artifacts and high-frequency signals to preserve details. Extensive experiments demonstrate that this approach achieves state-of-the-art performance.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2024)
Article
Computer Science, Artificial Intelligence
Guobin Li, Reyer Zwiggelaar
Summary: Breast cancer is the most commonly diagnosed female malignancy worldwide. Recent developments in deep convolutional neural networks have shown promising performance for breast cancer detection and classification. However, biased features can be learned due to variations in appearance and small datasets. To address this issue, a densely connected convolutional network (DenseNet) was trained using texture features representing different physical morphological representations as inputs. The use of connectivity estimation and nearest neighbors improved the network's unbiased prediction. The approach achieved higher diagnostic accuracy and provided visual explanations for model predictions.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2024)
Article
Computer Science, Artificial Intelligence
Yuezun Li, Cong Zhang, Honggang Qi, Siwei Lyu
Summary: Deep Neural Networks (DNNs) are vulnerable to adversarial perturbations, limiting their applicability in safe-critical scenarios. To address this, a new method called AdaNI is proposed to increase feature randomness through adaptive noise injection, improving adversarial robustness. Extensive experiments demonstrate the efficacy of AdaNI against various white-box and black-box attacks, as well as its applicability in DeepFake detection.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2024)
Article
Computer Science, Artificial Intelligence
Chengyin Hu, Weiwen Shi, Ling Tian, Wen Li
Summary: In this study, we introduce a pioneering black-box light-based physical attack called Adversarial Neon Beam (AdvNB). Our method excels in attack modeling, efficient attack simulation, and robust optimization, striking a balance between robustness and efficiency. Through rigorous evaluation, we achieve impressive attack success rates in both digital and real-world scenarios. AdvNB demonstrates its stealthiness through comparisons with baseline samples and consistently achieves high success rates when targeting advanced DNN models.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2024)
Article
Computer Science, Artificial Intelligence
Hang Wang, Zhenyu Ding, Cheng Cheng, Yuhai Li, Hongbin Sun
Summary: Learning-based super resolution has made remarkable progress in improving image quality, but the performance decreases when the degradation kernel changes. Blind SR networks can estimate the degradation kernel and adapt well in realistic scenarios, improving performance and runtime. This paper proposes a design that imposes constraints for the kernel estimation network in both the image domain and kernel domain, resulting in high-quality images and efficient runtime.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2024)
Article
Computer Science, Artificial Intelligence
Yuantao Chen, Runlong Xia, Kai Yang, Ke Zou
Summary: This paper proposes an improved image inpainting network using a multi-scale feature module and improved attention module. The network addresses issues in deep learning-based image inpainting algorithms, such as information loss in deep level features and the neglect of semantic features. The proposed network generates better inpainting results by reducing information loss and enhancing the ability to restore texture and semantic features.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2024)
Article
Computer Science, Artificial Intelligence
Yi-Tung Chan
Summary: This study proposes a novel maritime background subtraction method based on ensemble learning theory to address the challenges posed by dynamic marine environments and noise, improving the detection accuracy and enhancing maritime transportation security for autonomous ships in open waters.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2024)