检索结果-内蒙古大学图书馆

IEEE MIT Undergraduate Research Technology Conference (URTC)

作者： Duncan Soiffer Tuomas Pyorre David Kenney Andrew Teixeira Department of Computer Science and Mathematical Sciences Worcester Polytechnic Institute Worcester MA United States Department of Robotics Engineering Worcester Polytechnic Institute Worcester MA United States Department of Chemical Engineering Worcester Polytechnic Institute Worcester MA United States

ISBN: (数字)9798350309652

ISBN: (纸本)9798350309669

Per- and polyfluoroalkyl substances (PFAS) are a group of chemicals used for their impressive stability, a property which has also led them to be found polluting virtually every sector of the environment-including our own bodies. Presently, our ability to destroy PFAS is limited largely to incineration, whose products and side effects are poorly understood. Research on PFAS incineration is constrained by high experimental costs and difficulty in accurately measuring reaction products. This presents an opportunity for computer simulation and machine learning to provide valuable assistance. In this study, three kinds of thermal PFAS decomposition are simulated. Further, to broaden physical understanding of PFAS incineration products, a recent in-house machine learning model for predicting the octanol-water partition coefficient (LogP) of chemicals is improved and applied to simulation results. A decrease in LogP is observed in all treatments, with the most dramatic effect (-2 average LogP) observed in oxidative pyrolysis.

关键词： Costs Incineration computer simulation Thermal decomposition Machine learning Predictive models Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Principled penalty-based methods for bilevel reinforcement learning and RLHF 24

Principled penalty-based methods for bilevel reinforcement l...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Han Shen Zhuoran Yang Tianyi Chen Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute Department of Statistics and Data Science Yale University

Bilevel optimization has been recently applied to many machine learning tasks. However, their applications have been restricted to the supervised learning setting, where static objective functions with benign structures are considered. But bilevel problems such as incentive design, inverse reinforcement learning (RL), and RL from human feedback (RLHF) are often modeled as dynamic objective functions that go beyond the simple static objective structures, which pose significant challenges of using existing bilevel solutions. To tackle this new class of bilevel problems, we introduce the first principled algorithmic framework for solving bilevel RL problems through the lens of penalty formulation. We provide theoretical studies of the problem landscape and its penalty-based (policy) gradient algorithms. We demonstrate the effectiveness of our algorithms via simulations in the Stackelberg game and RLHF.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hands-On Learning: Teaching Parallel and Distributed Computing through Unplugged Activities in Undergraduate CS Courses

Hands-On Learning: Teaching Parallel and Distributed Computi...

引用

High Performance Computing, Networking, Storage and Analysis, SC-W: Workshops of the International Conference for

作者： Anurag Dasgupta Venkat Margapuri Simon Shamoun Shubbhi Taneja Matthew Toups Computer Science and Engineering Technology Valdosta State University Valdosta GA Department of Computing Sciences Villanova University Villanova PA Department of Computer Science Hofstra University Hempstead NY Department of Computer Science Worcester Polytechnic Institute Worcester Massachusetts Computer Science Department Tulane University New Orleans LA

ISBN: (数字)9798350355543

ISBN: (纸本)9798350355550

The authors present and evaluate an unplugged activity to introduce parallel computing concepts to undergraduate students. Students in five CS classrooms used a deck of playing cards in small groups to consider how parallelization can improve performance and how improvement decreases with increased parallelization. Before and after the activity, students took a short survey about their solution and their ideas about parallelism. The authors carried out this activity in seven courses at five institutions in the 2023-2024 academic year. The results showed that students had an increased appreciation for parallelization and this type of activity.

关键词： Surveys High performance computing Conferences Education Parallel processing Distributed computing

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Crowdsourcing for data Labeling with Heterogeneous Crowd 39

Hierarchical Crowdsourcing for Data Labeling with Heterogene...

引用

39th IEEE International Conference on data Engineering, ICDE 2023

作者： Zhang, Haodi Huang, Wenxi Su, Zhenhan Chen, Junyang Jiang, Di Fan, Lixin Zhang, Chen Lian, Defu Wu, Kaishun Shenzhen University College of Computer Science and Software Engineering China Shenzhen University WeBank Institute of Financial Technology China Webank Co. Ltd. China Hong Kong Polytechnic University Department of Computing Hong Kong University of Science and Technology of China School of Data Science China

ISBN: (纸本)9798350322279

With the rapid and continuous development of data-driven technologies such as supervised learning, high-quality labeled data sets are commonly required by many applications. Due to the easiness of crowdsourcing small tasks with low cost, a straightforward solution for label quality improvement is to collect multiple labels from a crowd, and then aggregate the answers. The aggregation strategies include majority voting and its many variants, EM-based approaches, Graph Neural Nets and so on. However, due to the uncertainty information loss and commonly existing task correlations, the aggregated labels usually contain errors and may damnify the downstream model *** address the above problem, we propose a hierarchical crowdsourcing framework1 for data labeling with noisy answers about correlated data. We make use of the heterogeneity of the labeling crowd and form an initialization-checking-update loop to improve the quality of labeled data. We formalize and successfully solve the core optimization problem, namely, selecting a proper set of checking tasks for each round. We prove that maximizing the expected quality improvement is equivalent to minimizing the conditional entropy of the observations given the crowdsourced answer families for the selected task set, which is NP-hard to solve. Therefore, we design an efficient approximation algorithm and conduct a series of experiments on real data. The experimental results show that the proposed method effectively improves the quality of the labeled data sets as well as the SOTA performance, yet without extra human labor costs. © 2023 IEEE.

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

data-Driven Soil Water Content Estimation at Multiple Depths Using SFCW GPR

Data-Driven Soil Water Content Estimation at Multiple Depths...

引用

2023 IEEE International Opportunity Research Scholars Symposium, ORSS 2023

作者： Filardi, Vincent Cheung, Allen Khan, Ruba Mangoubi, Oren Moradikia, Majid Zekavat, Seyed Reza Wilson, Brian Askari, Radwin Petkie, Douglas Worcester MA United States Ann Arbor MI United States Worcester Polytechnic Institute United States Michigan Tech Research Institute United States Michigan Tech University United States Data Science United States Physics Mexico Mathematical Sciences Spain Geological and Mining Engineering and Sciences United States

ISBN: (纸本)9798350337006

This paper provides a cost-effective solution to Soil Water Content (SWC) estimation at multiple root-zone depths using Ground Penetrating Radar (GPR) and Machine Learning (ML) based on an extensive measurement campaign conducted at worcester polytechnic institute (WPI). SWC characterization is critical for optimal industrial farming irrigation and, in turn, impacts water conservation and the mitigation of soil quality degradation. Accurate prediction of the water table and SWC of the root-zone soil is invaluable for precision farming. High-resolution modeling of SWC at varying sub-surface depths can potentially increase irrigation efficiency and the yield of crops such as maize, which has a massive water footprint upwards of 768 billion cubic meters and accounts for an estimated 5% percent of the world's daily calorie intake. Traditional methods of subsurface soil characterization by subsurface probes are invasive, costly, and labor-intensive. Our approach generates an accurate and precise characterization of the soil water content of loamy soil at multiple root level depths using Signal Processing principles and ML applied to a small dataset of size 51 of real field measurements collected between October 20th to 30th 2022. We applied ML algorithms to the preprocessed data collected by a Stepped Frequency Continuous Wave (SFCW) GPR signal and extracted the most relevant features related to SWC prediction at multiple depths. We used these extracted features to achieve a mean absolute percentage error as low as 6% across the four root-zone depths of our field data. This study was conducted within the 0.4 to 2.0 GHz frequency range, and provides an analysis of frequencies key to root-zone SWC characterization. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

On Rejecting Low Quality Images to Improve Deep Smartphone Wound Assessment

On Rejecting Low Quality Images to Improve Deep Smartphone W...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Apiwat Ditthapron Emmanuel O. Agu Peder Pedersen Clifford Lindsay Bengisu Tulu Diane Strong Computer Science Dept. Worcester Polytechnic Institute (WPI) Worcester MA Electrical and Computer Engineering Dept. Worcester Polytechnic Institute (WPI) Worcester MA Department of Radiology Univ. Massachusetts Medical School Worcester MA Foisie Business School Worcester Polytechnic Institute (WPI) Worcester MA

Automatic assessment of wounds using smartphones can facilitate the tracking of healing progress outside the clinic. Prior work proposed SS-PMG-EfficientNets, a state-of-the-art, multi-scale, convolutional neural network architecture for accurate wound assessment. However, the model was previously only trained and evaluated on high-quality wound images captured in controlled environments. This study systematically evaluated the effects of low-quality images on SS-PMG-EfficientNets, finding that the model's performance and consistency are reduced when input wound images are blurry or captured in adverse lighting (too bright or too dark), two factors previously identified as the most prevalent issues in crowdsourced images. Specifically, SS-PMG-EfficientNet was first trained on three high-quality wound datasets containing images labeled with Photographic Wound Assessment Tool (PWAT) wound healing scores, stages of pressure injury wounds, and wound types, respectively. The model was then evaluated on a test wound dataset that was augmented with real-world image luminance, blur, and image compression effects and found that wound assessment accuracy decreased by up to 27%. To improve model performance, we propose a method for instant image quality assessment on the smartphone, enabling low-quality wound images to be rejected immediately after image capture so that the nurse or patient can be prompted to recapture the image. Our evaluation of the proposed image quality assessment and rejection method showed that it increases average accuracy from 73 % to 87%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey

arXiv

引用

arXiv 2024年

作者： Kuang, Jiayi Xie, Jingyou Luo, Haohao Li, Ronghao Xu, Zhe Cheng, Xianfeng Li, Yinghui Lin, Xika Shen, Ying Sun Yat-sen University China Tsinghua University China Department of Computer Science Worcester Polytechnic Institute United States

Visual Question Answering (VQA) is a challenge task that combines natural language processing and computer vision techniques and gradually becomes a benchmark test task in multimodal large language models (MLLMs). The goal of our survey is to provide an overview of the development of VQA and a detailed description of the latest models with high timeliness. This survey gives an up-to-date synthesis of natural language understanding of images and text, as well as the knowledge reasoning module based on image-question information on the core VQA tasks. In addition, we elaborate on recent advances in extracting and fusing modal information with vision-language pretraining models and multimodal large language models in VQA. We also exhaustively review the progress of knowledge reasoning in VQA by detailing the extraction of internal knowledge and the introduction of external knowledge. Finally, we present the datasets of VQA and different evaluation metrics and discuss possible directions for future work. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Latent Dynamical Model to Characterize Brain Network-Level Rhythmic Dynamics

Latent Dynamical Model to Characterize Brain Network-Level R...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Reza Saadati Fard Navid Ziaei Ali Yousefi Department of Computer Science Worcester Polytechnic Institute Worcester MA USA Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan Iran

Characterizing network-level rhythmic dynamics over multiple spatio-temporal scales can significantly advance our understanding of brain cognitive function and information processing. In this research, we propose a new switching state space model called latent dynamical coherence model or briefly LDCM. In the LDCM, we develop model inference and parameter estimation solutions that facilitate studying network-level rhythmic dynamics at scales. In the proposed framework, we incorporate both continuous and discrete state processes, helping us to capture dynamics of functional connectivity at various rates, such as slow, rapid, or a combination of both. We then demonstrate an application of our model in characterizing circuit dynamics of the anesthetic state in a sample data set, recorded from a patient under anesthesia using 64-channel EEG over the course of two hours.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RVISA: Reasoning and Verification for Implicit Sentiment Analysis

引用

IEEE Transactions on Affective Computing 2025年

作者： Lai, Wenna Xie, Haoran Xu, Guandong Li, Qing Hong Kong Polytechnic University Department of Computing Hong Kong Lingnan University School of Data Science Hong Kong University of Technology Sydney School of Computer Science Data Science Institute SydneyNSW2007 Australia Education University of Hong Kong Hong Kong

Under the context of the increasing social demand for fine-grained sentiment analysis (SA), implicit sentiment analysis (ISA) poses a significant challenge owing to the absence of salient cue words in expressions. Thus, reliable reasoning is required to understand how sentiment is evoked, enabling the identification of implicit sentiments. In the era of large language models (LLMs), encoder-decoder (ED) LLMs have emerged as popular backbone models for SA applications, given their impressive text comprehension and reasoning capabilities across diverse tasks. In comparison, decoder-only (DO) LLMs exhibit superior natural language generation and in-context learning capabilities. However, their responses may contain misleading or inaccurate information. To accurately identify implicit sentiments with reliable reasoning, this study introduces a two-stage reasoning framework named Reasoning and Verification for Implicit Sentiment Analysis (RVISA), which leverages the generation ability of DO LLMs and reasoning ability of ED LLMs to train an enhanced reasoner. The framework involves three-hop reasoning prompting to explicitly furnish sentiment elements as cues. The generated rationales are then used to fine-tune an ED LLM into a skilled reasoner. Additionally, we develop a straightforward yet effective answer-based verification mechanism to ensure the reliability of reasoning learning. Evaluation of the proposed method on two benchmark datasets demonstrates that it achieves state-of-the-art performance in ISA. © 2010-2012 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Loss Distillation via Gradient Matching for Point Cloud Completion with Weighted Chamfer Distance

arXiv

引用

arXiv 2024年

作者： Lin, Fangzhou Liu, Haotian Zhou, Haoying Hou, Songlin Yamada, Kazunori D. Fischer, Gregory S. Li, Yanhua Zhang, Haichong K. Zhang, Ziming Department of Robotics Engineering Worcester Polytechnic Institute WorcesterMA01609 United States Dell Technologies HopkintonMA01748 United States Graduate School of Information Sciences Tohoku University Sendai980-8579 Japan Department of Computer Science Worcester Polytechnic Institute WorcesterMA01609 United States Department of Electrical & Computer Engineering Worcester Polytechnic Institute WorcesterMA01609 United States

3D point clouds enhanced the robot’s ability to perceive the geometrical information of the environments, making it possible for many downstream tasks such as grasp pose detection and scene understanding. The performance of these tasks, though, heavily relies on the quality of data input, as incomplete can lead to poor results and failure cases. Recent training loss functions designed for deep learning-based point cloud completion, such as Chamfer distance (CD) and its variants (e.g. HyperCD [1]), imply a good gradient weighting scheme can significantly boost performance. However, these CD-based loss functions usually require data-related parameter tuning, which can be time-consuming for data-extensive tasks. To address this issue, we aim to find a family of weighted training losses (weighted CD) that requires no parameter tuning. To this end, we propose a search scheme, Loss Distillation via Gradient Matching, to find good candidate loss functions by mimicking the learning behavior in backpropagation between HyperCD and weighted CD. Once this is done, we propose a novel bilevel optimization formula to train the backbone network based on the weighted CD loss. We observe that: (1) with proper weighted functions, the weighted CD can always achieve similar performance to HyperCD, and (2) the Landau weighted CD, namely Landau CD, can outperform HyperCD for point cloud completion and lead to new state-of-the-art results on several benchmark datasets. Our demo code is available at https://***/Zhang-VISLab/ IROS2024-LossDistillationWeightedCD. © 2024, CC0.

关键词： Deep learning

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：