检索结果-内蒙古大学图书馆

Open Ceramics 2025年

作者： Compaore Alassane Toure Kicoun Jean-Yves N’Zy Desmond Edem Primus Klenam Abdallah Sarroney Merenga Tabiri Kwayie Asumadu John David Obayemi Nima Rahbar Charles Migwi Winston Oluwole Soboyejo Department of Physics Kenyatta University P.O. Box 43844 Nairobi Kenya Department of Civil Engineering Worcester Polytechnic Institute 100 Institute Road Worcester MA 01609 USA Department of Mechanical Engineering Program in Materials Science and Engineering Worcester Polytechnic Institute Worcester Massachusetts USA Academic Development Unit and School of Chemical and Metallurgical Engineering University of the Witwatersrand Johannesburg South Africa Department of Mechanical Engineering College of Engineering State University of New York (SUNY) Polytechnic Institute Utica New York USA

This paper explores foam concretes produced from cement, sand, water, foaming agents and secondary cementitious materials (SCMs). We examine the effects of these constituents on the microstructure, mechanical/physical properties, workability, and the durability of foam concrete. The contributions of SCMs are assessed based on their pozzolanic activity. Various SCMs, through their pozzolanic reactivity, contribute significantly to pore refinement, matrix densification, and the enhancement of mechanical strength, thermal conductivity and durability characteristics, including resistance to water ingress, chloride penetration, and sulfate attack of foam concrete mixes. While the SCMs incorporation leads to improved strength, it may also increase brittleness, which can be balanced with the addition of fibers. Furthermore, the workability is greatly affected by the incorporation of SCMs, which often have a negative effect on reducing it. The paper highlights the opportunities to use metakaolin as an SCM for the optimization of foam concrete mechanical, durability and thermal properties.

关键词： foam concrete microstructure thermal conductivity mineral admixtures compressive strength

来源：评论

学校读者我要写书评

暂无评论

Reconstruction of Fragmented Trajectories of Collective Motion using Hadamard Deep Autoencoders

arXiv

引用

arXiv 2021年

作者： Gajamannage, Kelum Park, Yonggi Paffenroth, Randy Jayasumana, Anura P. Department of Mathematics and Statistics Texas A&M University–Corpus Christi Corpus ChristiTX78412 United States Department of Mathematical Sciences Department of Computer Science Data Science Program Worcester Polytechnic Institute WorcesterMA01609 United States Department of Electrical and Computer Engineering Colorado State University Fort CollinsCO80525 United States

Learning dynamics of collectively moving agents such as fish or humans is an active field in research. Due to natural phenomena such as occlusion and change of illumination, the multi-object methods tracking such dynamics might lose track of the agents where that might result fragmentation in the constructed trajectories. Here, we present an extended deep autoencoder (DA) that we train only on fully observed segments of the trajectories by defining its loss function as the Hadamard product of a binary indicator matrix with the absolute difference between the outputs and the labels. The trajectories of the agents practicing collective motion is low-rank due to mutual interactions and dependencies between the agents that we utilize as the underlying pattern that our Hadamard deep autoencoder (HDA) codes during its training. The performance of our HDA is compared with that of a low-rank matrix completion scheme in the context of fragmented trajectory reconstruction. © 2021, CC BY.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Dimenslon Estlmatlon of Equlty Markets

Dimenslon Estlmatlon of Equlty Markets

引用

2019 IEEE International Conference on Big data, Big data 2019

作者： Bahadur, Nitish Paffenroth, Randy Gajamannage, Kelum Worcester Polytechnic Institute Department of Data Science WorcesterMA01609 United States Texas AM University-Corpus Christi Department of Mathematics and Statistics Corpus ChristiTX78412 United States Worcester Polytechnic Institute Mathematical Sciences Computer Science Data Science WorcesterMA01609 United States

ISBN: (纸本)9781728108582

Financial markets are comprised of many instruments, are complex, and are constantly changing. However, it is interesting to consider what, if any, commonalities persist in markets over long time horizons. In particular, one can study financial markets under nominal and stressed market conditions, and attempt to discern which market parameters remain invariant and which market parameters change. Herein, we study financial markets from the perspective of low-dimensional manifolds that capture the inherent characteristics of the high-dimensional data that represent the market performance. Using Russe113000 constituents, we estimate intrinsic dimension of the US equity market over 30 years (1986-2016) and analyze those times where the change in dimension is abnormal. In particular, our focus in on novel applications of nonlinear techniques such as Isomap and autoencoders, as opposed to linear technique such as principal component analysis (PCA). Such ideas have many applications, including portfolio diversification and market crash analysis. © 2019 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Perspectives on How To Conduct Responsible Anti-Human Trafficking Research in Operations and Analytics

arXiv

引用

arXiv 2020年

作者： Konrad, Renata A. Maass, Kayse Lee Dimas, Geri L. Trapp, Andrew C. School of Business Worcester Polytechnic Institute 100 Institute Road WorcesterMA01609 United States Department of Mechanical and Industrial Engineering Northeastern University 360 Huntington Ave BostonMA02115 United States Data Science Program Worcester Polytechnic Institute 100 Institute Road WorcesterMA01609 United States

Human trafficking, the commercial exploitation of individuals, is a gross violation of human rights;harming societies, economies, health and development. The related disciplines of Operations Research (OR) and Analytics are uniquely positioned to support trafficking prevention and intervention efforts by efficiently evaluating a plethora of decision alternatives and providing quantitative, actionable insights. As operations and analytical efforts in the counter-trafficking field emerge, it is imperative to grasp subtle, yet distinctive, nuances associated with human trafficking. This paper is intended to inform those practitioners working in the Operations and Analytics fields by highlighting key features of human trafficking activity. We grouped ten themes around two broad categories: (1) representation of human trafficking and (2) consideration of survivors and communities. These insights are derived from our collective experience in working in this area and substantiated by domain expertise. Based on these areas, we then suggest avenues for future work. © 2020, CC BY-NC-SA.

关键词： Operations research

来源：评论

学校读者我要写书评

暂无评论

Patient-level Classification on Clinical Note Sequences Guided by Attributed Hierarchical Attention

Patient-level Classification on Clinical Note Sequences Guid...

引用

IEEE International Conference on Big data

作者： Cansu Sen Thomas Hartvigsen Xiangnan Kong Elke Rundensteiner Computer Science Department Worcester Polytechnic Institute Worcester MA USA Data Science Program Worcester Polytechnic Institute Worcester MA USA

ISBN: (数字)9781728108582

ISBN: (纸本)9781728108599

In spite of clinical notes in Electronic Health Records (EHR) providing abundant information about patient health, effective modeling of clinical notes remains in its infancy. A patient's clinical notes correspond to a sequence of free-form texts generated by health care professionals over time; with each note in turn containing a sequence of words. Additionally, notes are accompanied by external attributes at multiple layers such as the time at which each note was created (note level) or the demographics of the patient (patient level). Thus, EHR notes correspond to a nested structure of text sequences augmented with external multi-layer attributes. To model this complex problem, we propose an Attributed Hierarchical Attention model, named HAC-RNN, that integrates multiple RNN layers that encode nested sequential notes with contextual and temporal attention layers that are conditioned on the external attributes. While the bottom layer of HAC-RNN is responsible for contextual summarization of the note content, the top layer combs through the entire timeline of notes to focus on those which are most relevant. These attention layers, which are each conditioned on layer-specific hierarchical attributes, allow personalized predictions through inferring patient *** evaluate HAC-RNN using three real-world medical tasks, detecting in-hospital acquired infections and predicting patient mortality using critical care database MIMIC-III. Our results demonstrate that our model significantly outperforms state-of-the-art techniques for all tasks.

关键词： Task analysis Predictive models Medical services Medical diagnostic imaging Feature extraction Computer science Context modeling

来源：评论

学校读者我要写书评

暂无评论

Predicting Protein Interaction Network Perturbation by Alternative Splicing with Semi-Supervised Learning

SSRN

引用

SSRN 2020年

作者： Narykov, Oleksandr Johnson, Nathan Korkin, Dmitry Department of Computer Science Bioinformatics and Computational Biology Program Worcester Polytechnic Institute WorcesterMA United States Harvard Program in Therapeutic Sciences Harvard Medical School Breast Tumor Immunology Laboratory Dana-Farber Cancer Institute BostonMA United States Department of Computer Science Bioinformatics and Computational Biology Program Worcester Polytechnic Institute WorcesterMA United States

Alternative splicing introduces a new layer of protein diversity and complexity in regulating cellular functions that can be specific to the tissue and cell type, physiological state of a cell, or disease phenotype. In particular, recent high-throughput experimental studies have illuminated the functional role of splicing events through rewiring protein-protein interactions, yet the extent to which the macromolecular interactions are affected by alternative splicing has to be fully understood. In silico methods provide a fast and cheap alternative to interrogating functional characteristics of thousands of alternatively spliced isoforms. Here we develop an accurate feature-based machine learning approach that predicts if a protein-protein interaction carried out by a reference isoform is perturbed by an alternatively spliced isoform. Our method called ALTernatively Spliced INteractions prediction (ALT-IN) Tool was compared with the state-of-the-art PPI prediction tools and showed superior performance, achieving 0.92 in precision and recall values. © 2020, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Learning Temporal Relevance in Longitudinal Medical Notes

Learning Temporal Relevance in Longitudinal Medical Notes

引用

IEEE International Conference on Big data

ISBN: (数字)9781728108582

ISBN: (纸本)9781728108599

Clinical notes correspond to sequences of reports about patients written over time by health-care professionals. With the availability of massive Electronic Health Record (EHR) datasets composed of such clinical notes, machine learning models on these rich text data series are being developed for patient outcome prediction from infection diagnosis to mortality. While current models focus on content in these unstructured clinical notes, we postulate that timing of the medical events that are explained in the notes are equally crucial. We thus propose a novel attention mechanism composed of dual-attention blocks based on a rich diversity of time representations. We then pair this mechanism with an LSTM, resulting in our proposed time-aware recurrent network TEND-LSTM. TEND-LSTM learns an integrated set of attention weights, with the first attention based on the content of the clinical notes and the second based on when the notes were taken. Together, they are combined using a deep-attention network layer. The proposed dual attention mechanism not only learns a function of time incorporating different aspects of the temporal nature of note instances but also automatically finds a balance between how much attention to put on content versus time. We evaluate our model on six medical tasks using data sets from the publicly-available MIMIC III database from the Beth Israel Deaconess Medical Center. Our results demonstrate that TEND-LSTM outperforms state-of-the-art methods by a large margin.

关键词： Task analysis Medical diagnostic imaging Predictive models Timing Indexes Neural networks Computer science

来源：评论

学校读者我要写书评

暂无评论

Reducing Uncertainty in Pose Estimation under Complex Contacts via Force Forecast

Reducing Uncertainty in Pose Estimation under Complex Contac...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Huitan Mao Jing Xiao Department of Computer Science University of North Carolina Charlotte NC USA Robotics Engineering Program and Department of Computer Science Worcester Polytechnic Institute Worcester MA USA

ISBN: (数字)9781728173955

ISBN: (纸本)9781728173962

How to reduce uncertainty in object pose estimation under complex contacts is crucial to autonomous robotic manipulation and assembly. In this paper, we introduce an approach through forecasting contact force from simulated complex contacts with calibration based on real force sensing. A constraint-based haptic simulation algorithm is used with sphere-tree representation of contacting objects to compute contact poses and forces, and through matching the computed forces to measured real force data via a regression model, the least-uncertain estimate of the relative contact pose is obtained. Our approach can handle multi-region complex contacts and does not make any assumption about contact types or contact locations. It also does not have restriction on object shapes. We have applied the force forecast approach to reducing uncertainty in estimating object poses in challenging peg-in-hole robotic assembly tasks and demonstrate the effectiveness of the approach by successful completion of contact-rich two-pin and three-pin real peg-in-hole assembly tasks with complex shapes of pins and holes.

关键词： Force Uncertainty Robot sensing systems Task analysis Calibration

来源：评论

学校读者我要写书评

暂无评论

Investigating the Efficacy of data Mining Techniques for Crowdsourced Biological datasets

Investigating the Efficacy of Data Mining Techniques for Cro...

引用

2019 IEEE MIT Undergraduate Research Technology Conference, URTC 2019

作者： Regan, Ilona Alkurdi, Dany Paisarnsrisomsuk, Sarun Ruiz, Carolina Ryder, Elizabeth F. Gegear, Rob Bioinformatics and Computational Biology Program Worcester Polytechnic Institute WorcesterMA United States Princeton University Department of Near Eastern Studies PrincetonNJ United States Worcester Polytechnic Institute Department of Computer Science WorcesterMA United States Worcester Polytechnic Institute Department of Biology and Biotechnology WorcesterMA United States University of Massachusetts Dartmouth Department of Biology DartmouthMA United States

ISBN: (纸本)9781728158181

The rapid worldwide decline of wild pollinators over recent years poses a significant environmental threat due to the critical keystone role that pollinators play in terrestrial ecosystems. In order to gain insight into the major anthropogenic factors causing these declines, researchers have collected large amounts of ecological data. Yet, they often lack the computational tools needed to analyze the information contained in such datasets. We investigate various data analysis techniques for the Beecology Project, which is a citizen science based effort to rapidly collect data on foraging habits of bumblebee species native to Massachusetts. Different data mining approaches were explored, including association analysis, trend analysis, classification, regression, and clustering. It was found that different techniques were more suitable depending on the biological research question. Future work will focus on making tools utilizing these approaches available online through the Beecology website, where they can be used by the public to determine how best to protect our native pollinators and the diverse ecosystems they support. © 2019 IEEE.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Corrosion Assessment: data Mining for Quantifying Associations between Indoor Accelerated and Outdoor Natural Tests

Corrosion Assessment: Data Mining for Quantifying Associatio...

引用

IEEE International Conference on Big data

作者： Biao Yin Thomas A. Considine Fatemeh Emdad John V. Kelley Robert E. Jensen Elke A. Rundensteiner Data Science Program Worcester Polytechnic Institute Worcester MA USA Weapons and Materials Research Directorate US Army Research Laboratory MD USA Weapons and Materials Research Directorate ARL Northeast Regional Extended Site Burlington MA USA

ISBN: (数字)9781728162515

ISBN: (纸本)9781728162522

Material scientists study corrosion degradation of metallic structures due to its heavy economic and maintenance burdens. Assessing corrosion is both time consuming and labor intensive when utilizing outdoor tests under natural exposure conditions. Accelerated indoor corrosion tests are conducted in laboratory settings by material scientists to gage performance in a shorter period of time than outdoor tests. However, these indoor tests do not always correlate well with the actual performance in outdoor environments. Thus, there is a need to apply data-science methodologies to analyze and establish quantitative associations between indoor accelerated and outdoor exposure assessments to optimize artificially accelerated methods. We work with material experimental records including images, notes, meta-data and human-rated assessments collected over years. We apply data mining methods, such as Canonical Correlation Analysis (CCA) and its variants, to extract latent associations with corresponding feature mappings between the indoor and outdoor assessments in a projected data subspace. We find that CCA provides not only reliable quantitative associations but also interpretive mappings between the indoor and outdoor assessments. Further, three methods applied to control bias due to distinctive coating system stack up yield Pearson's correlation coefficients ranging from 0.70 to 0.83 in the optimized CCA subspaces, respectively. Moreover, predicting outdoor assessments from the CCA-projected indoor test data compared to using the original indoor data is shown to result in an increase in accuracy from 88% to 90% - confirming the effectiveness of our approach. Lastly, our results facilitate interesting domain-relevant discovery that could potentially lead to experimentalists better understanding corrosion resistance.

关键词： Corrosion Life estimation Feature extraction data mining Coatings Reliability Testing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：