检索结果-内蒙古大学图书馆

Solving key challenges in collider physics with foundation models

Physical Review D 2025年第5期111卷 L051504-L051504页

作者： Vinicius Mikuni Benjamin Nachman National Energy Research Scientific Computing Center Berkeley Lab Berkeley California 94720 USA Physics Division Lawrence Berkeley National Laboratory Berkeley California 94720 USA Berkeley Institute for Data Science University of California Berkeley California 94720 USA

Foundation models are neural networks that are capable of simultaneously solving many problems. Large language foundation models like ChatGPT have revolutionized many aspects of daily life, but their impact for science is not yet clear. In this paper, we use a new foundation model for hadronic jets to solve three key challenges in collider physics. In particular, we show how experiments can (1) save significant computing power when developing reconstruction algorithms, (2) perform a complete uncertainty quantification for high-dimensional measurements, and (3) search for new physics with model agnostic methods using low-level inputs. In each case, there are significant computational or methodological challenges with current methods that limit the science potential of deep learning algorithms. By solving each problem, we take jet foundation models beyond proof-of-principle studies and into the toolkit of practitioners.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Hand Gesture-Operated System for Rehabilitation Using an End-to-End Detection Framework

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第2期5卷 698-708页

作者： Dutta, H Pallab Jyoti Bhuyan, M.K. Neog, Debanga Raj Macdorman, Karl F. Laskar, R.H. Department of Electronics and Electrical Engineering Indian Institute of Technology Assam Guwahati781039 India Department of Electronics and Electrical Engineering and Mehta Family School of Data Science and Artificial Intelligence Indian Institute of Technology Assam Guwahati781039 India Mehta Family School of Data Science and Artificial Intelligence Indian Institute ofTechnology Assam Guwahati781039 India School of Informatics and Computing Indiana University IN46202 United States Department of Electronics and Communication Engineering National Institute of Technology Assam Silchar788010 India

In this article, we propose a hand gesture-operated system as an AI application to relieve discomfort and restore function in hand and arm movements caused by injuries and nerve and muscle complications. The system trains patients with hand exercises, such as performing hand gestures accurately, traversing within specified bounds, and operating a hand gesture calculator. However, the system requires accurate hand gesture detection, which is impeded by background clutter and variations in illumination and in the hand's size and angle. To address this, we developed a robust hand detection module that uses a single-stage transformer deep network. The transformer network encodes global information and uses bipartite matching to reduce the frequency of spurious detections. It drives a regression head and a classification head to localize the hand gesture in a bounding box and assign it a class label. Hand keypoints are also detected to support drawing, path traversal, and calculator use. The approach is evaluated on two benchmark datasets: 1) OUHANDS and 2) NUS. The method yields 89.6% accuracy for OUHANDS and 100% for NUS. These results indicate that precise hand detection can support a robust system for rehabilitation through hand exercises. Our experiments confirm that the users' hand function progressively improved. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

LINKAGE: Listwise Ranking among Varied-Quality References for Non-Factoid QA Evaluation via LLMs

LINKAGE: Listwise Ranking among Varied-Quality References fo...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Yang, Sihui Bi, Keping Cui, Wanqing Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798891761681

Non-Factoid (NF) Question Answering (QA) is challenging to evaluate due to diverse potential answers and no objective criterion. The commonly used automatic evaluation metrics like ROUGE or BERTScore cannot accurately measure semantic similarities or answers from different perspectives. Recently, Large Language Models (LLMs) have been resorted to for NFQA evaluation due to their compelling performance on various NLP tasks. Common approaches include pointwise scoring of each candidate answer and pairwise comparisons between answers. Inspired by the evolution from pointwise to pairwise to listwise in learning-to-rank methods, we propose a novel listwise NFQA evaluation approach, that utilizes LLMs to rank candidate answers in a list of reference answers sorted by descending quality. Moreover, for NF questions that do not have multi-grade or any golden answers, we leverage LLMs to generate the reference answer list of various quality to facilitate the listwise evaluation. Extensive experimental results on three NFQA datasets, i.e., ANTIQUE, the TREC-DL-NF, and WebGLM show that our method has significantly higher correlations with human annotations compared to automatic scores and common pointwise and pairwise approaches. Our code and dataset can be found at https://***/babyyang525/LINKAGE-Listwise-NFQA-Evaluation. © 2024 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Causal Discovery Inspired Unsupervised Domain Adaptation for Emotion-Cause Pair Extraction

Causal Discovery Inspired Unsupervised Domain Adaptation for...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Hua, Yuncheng Huang, Yujin Huang, Shuo Feng, Tao Qu, Lizhen Bain, Chris Bassed, Richard Haffari, Gholamreza Department of Data Science & AI Monash University Australia Department of Human Centred Computing Monash University Australia Victorian Institute of Forensic Medicine Melbourne Australia

ISBN: (纸本)9798891761681

This paper tackles the task of emotion-cause pair extraction in the unsupervised domain adaptation *** problem is challenging as the distributions of the events causing emotions in target domains are dramatically different than those in source domains, despite the distributions of emotional expressions between domains are *** by causal discovery, we propose a novel deep latent model in the variational autoencoder (VAE) framework, which not only captures the underlying latent structures of data but also utilizes the easily transferable knowledge of emotions as the bridge to link the distributions of events in different *** facilitate knowledge transfer across domains, we also propose a novel variational posterior regularization technique to disentangle the latent representations of emotions from those of events in order to mitigate the damage caused by the spurious correlations related to the events in source *** extensive experiments, we demonstrate that our model outperforms the strongest baseline by approximately 11.05% on a Chinese benchmark and 2.45% on a English benchmark in terms of weighted-average F1 *** have released our source code and the generated dataset publicly at: https://***/tk1363704/CAREL-VAE. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Customer Churn Prediction Using Machine Learning Approaches

Customer Churn Prediction Using Machine Learning Approaches

引用

2023 International Conference on Artificial Intelligence and Knowledge Discovery in Concurrent Engineering, ICECONF 2023

作者： Srinivasan, R. Rajeswari, D. Elangovan, G. SRM Institute of Science and Technology Department of Computing Technologies Kattankulathur603 203 India SRM Institute of Science and Technology Department of Data Science and Business Systems Kattankulathur603 203 India

ISBN: (纸本)9798350334357

Customer Churn (CC) is a major issue and important concerns for large organizations and businesses alike. Telecom industries are attempting to improve methods to predict possible customer churn due to the immediate impact on revenue, particularly in the telecom sector. This paper discusses the various ML algorithms used to construct the churn model that helps telecom operators to predict customers who are likely to churn. The experimental results are compared to predict the best model among various techniques. As a result, the use of the Random Forest combined with SMOTE-ENN outperforms best result than other in terms of Fl-score. According to our analysis, the maximum prediction is 95 percent based on Fl-score. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Detecting the Traceability Issues in Supply chain Industries using Blockchain Technology

Detecting the Traceability Issues in Supply chain Industries...

引用

2022 IEEE International Conference on Advances in computing, Communication and Applied Informatics, ACCAI 2022

作者： Subashini, B. Hemavathi, D. School of Computing SRM Institute of Science and Technology Department of Data Science and Business Systems India

ISBN: (纸本)9781665495295

Today, agriculture remains the most important economic activity in the world. Food care is a major concern for the whole society. For agriculture-based supply chain management, traceability is considered as the major requirement. Traceability helps in providing quality assurance and transparency to the end user. The antiquated traceability system has the complications of centralized systems, non-Transparency of information, unpredictable data, and the very easy formation of false data. The World Health Organization (WHO) reports that one out of ten people is affected by having tainted food. Globalization involving different food production processes and automation pushes the food supply chain into a complicated web. Numerous advancements have been investigated lately to determine food vulnerability and carry productivity to food related issues. One of the expected advances is block chain, which is as of now being effectively executed in monetary areas, for example, bit coin. Block chain can also be used in the food supply chain industries to improve traceability and help in the danger decrease of fakes and different types of unlawful occupation. This paper presents a systematic survey on agrifood supply chain traceability issues using various block chain platforms such as Ethereum and Hyperledger, as well as IOT techniques such as barcodes, RFID, NFC, and QR codes. The performance of several consensus algorithms is also investigated. © 2022 IEEE.

关键词： Transparency

来源：评论

学校读者我要写书评

暂无评论

LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image Recognition 38

LF-ViT: Reducing Spatial Redundancy in Vision Transformer fo...

引用

38th AAAI Conference on Artificial Intelligence, AAAI 2024

作者： Hu, Youbing Cheng, Yun Lu, Anqi Cao, Zhiqiang Wei, Dawei Liu, Jie Li, Zhijun AIoT Lab Faculty of Computing Harbin Institute of Technology China Swiss Data Science Center Zurich Switzerland School of Cyber Engineering Xidian University China

ISBN: (纸本)1577358872

The Vision Transformer (ViT) excels in accuracy when handling high-resolution images, yet it confronts the challenge of significant spatial redundancy, leading to increased computational and memory requirements. To address this, we present the Localization and Focus Vision Transformer (LF-ViT). This model operates by strategically curtailing computational demands without impinging on performance. In the Localization phase, a reduced-resolution image is processed;if a definitive prediction remains elusive, our pioneering Neighborhood Global Class Attention (NGCA) mechanism is triggered, effectively identifying and spotlighting class-discriminative regions based on initial findings. Subsequently, in the Focus phase, this designated region is used from the original image to enhance recognition. Uniquely, LF-ViT employs consistent parameters across both phases, ensuring seamless end-to-end optimization. Our empirical tests affirm LF-ViT's prowess: it remarkably decreases Deit-S's FLOPs by 63% and concurrently amplifies throughput twofold. Code of this project is at https://***/edgeai1/***. Copyright © 2024, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Beyond Precision: A Study on Recall of Initial Retrieval with Neural Representations 1

引用

28th China Conference on Information Retrieval, CCIR 2022

作者： Xiao, Yan Fan, Yixing Zhang, Ruqing Guo, Jiafeng CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China

ISBN: (数字)9783031247552

ISBN: (纸本)9783031247545

Vocabulary mismatch is a central problem in information retrieval (IR), i.e., the relevant documents may not contain the same (symbolic) terms of the query. Recently, neural representations have shown great success in capturing semantic relatedness, leading to new possibilities to alleviate the vocabulary mismatch problem in IR. However, most existing efforts in this direction have been devoted to the re-ranking stage. That is to leverage neural representations to help re-rank a set of candidate documents, which are typically obtained from an initial retrieval stage based on some symbolic index and search scheme (e.g., BM25 over the inverted index). This naturally raises a question: if the relevant documents have not been found in the initial retrieval stage due to vocabulary mismatch, there would be no chance to re-rank them to the top positions later. Therefore, in this paper, we study the problem how to employ neural representations to improve the recall of relevant documents in the initial retrieval stage. Specifically, to meet the efficiency requirement of the initial stage, we introduce a neural index for the neural representations of documents, and propose two hybrid search schemes based on both neural and symbolic indices, namely the parallel search scheme and the sequential search scheme. Our experiments show that both hybrid index and search schemes can improve the recall of the initial retrieval stage with small overhead. © 2023, Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Cirrhosis Prediction in Chronic Liver Disease Patients Using Machine Learning Techniques 3

Cirrhosis Prediction in Chronic Liver Disease Patients Using...

引用

3rd International Conference on Pervasive computing and Social Networking, ICPCSN 2023

作者： Athish, V.P. Sree Nandha, S.S. Rajeswari, D. School of Computing College of Engineering and Technology Srm Institute of Science and Technology Dept. of Data Science and Business Systems Tamilnadu Kattankulathur603203 India

ISBN: (纸本)9798350322842

Liver failure is a serious medical condition that can have life-threatening consequences. The liver is responsible for filtering blood and performing many other important functions. With the rise of machine learning in healthcare, there is an opportunity to use past datasets to predict liver failure early on. The main focus of this research work is to explore the application of supervised machine learning algorithms in predicting liver failure. The study involved pre-processing techniques such as univariate and bivariate analysis, and data visualization to gain better insights into the features of the dataset. Using these techniques, a multi-class classification model was built with machine learning algorithms, and the performance metrics of accuracy, F1 score, and recall were used to compare the algorithms. The results show that machine learning algorithms can accurately predict liver failure and can be an effective tool in healthcare. This study demonstrates the potential of machine learning in predicting liver failure and can contribute to the development of future models in the field. The results of this research study indicates that the proposed algorithm achieved an accuracy of 94.48%. The proposed work will be beneficial to researchers in this field and inspire them to build more advanced and accurate models. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Deriving Pipeline for Emergency Services Using Natural Language Processing Techniques 11th

Deriving Pipeline for Emergency Services Using Natural Langu...

引用

11th International Conference on Recent Trends in computing, ICRTC 2022

作者： Anand, Akshat Rajeswari, D. Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Chennai603203 India

ISBN: (纸本)9789811988240

Communications have a crucial role in times of crisis, particularly in times of emergency. Whenever a region is affected by any disaster, social media sites such as Twitter, etc., are a great way to get information out to those who need it the most. Our paper suggests that in times of crisis, when people are worried about finding the right emergency contacts or are experiencing a transformation in their psychological response, they should manually enter their experience into an app to obtain contact information for the nearest SOS. Alternatively, the proposed application suggests scraping hashtags from around the world with web scraping scripts to retrieve geo-referenced tweets in real time. In order to gather accurate data, Twitter's API or some third-party application can be used in the development of this software. When there is a major crisis, social media user behavior plays a vital role, owing to its efficiency and high reliability with swift data dissemination. Anxiety over finding the right emergency team contact may cause people to lose their cool and become unclear about which authority they should call when an emergency occurs. Eventually, our application bridges the gap between clients in need of help and the approved agency that can really provide that support in different circumstances. In the case of, for example, a lost child or a flooded area, our application helps you get in touch with an organization that can assist you in dealing with the situation. We have used CNN-1-D + LSTM, CNN-1-D + Bi-LSTMs, and CNN-1-D + LSTM + Glove-100-D to get maximum accuracy for the classification model. It is possible to use the prototype solution in a novel way to organize immediate assistance with authorities in comprehensive administration, while integrating Twitter or other social platforms into the application can make it a feasible platform for preventive intervention and catastrophe management. © 2023, The Author(s), under exclusive license to Springer Nature

关键词： Emergency services

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：