检索结果-内蒙古大学图书馆

IEEE International Conference on Big data

作者： Dongyu Zhang Ruofan Hu Dandan Tao Hao Feng Elke Rundensteiner AML ByteDance San Jose USA Worcester Polytechnic Institute Data Science Program Worcester Polytechnic Institute Worcester USA Vanke School of Public Health Tsinghua University Beijing China College of Ag&Environ Sciences North Carolina A&T State University Greensboro USA Computer Science/Data Science Program Worcester Polytechnic Institute Worcester USA

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

Foodborne illnesses pose a threat to public health, leading to morbidity, mortality, and economic burden annually. Social media, while providing a rich timely source for training AI models for surveillance, requires effective tools for annotation. While Large Language Models (LLMs) have shown promise for generating simple labels, here hierarchical labels composed of entity types like food type and symptom (at individual word level) and the foodborne illness event (at complete post level) are required. For this, we introduce ICL2FID, the first LLM-based hierarchical labeling framework designed to annotate social media posts for foodborne illness detection at two levels using only a few demonstration examples. To utilize the interconnection between post and word levels, ICL2FID instructs the LLM to leverage information from one level when predicting the other level. To combat model hallucination and cyclic dependencies, a verification step improves evidence propagation between interconnected word and post-level labeling tasks. Strategies for custom selection of demonstration examples are designed reducing biases and increasing representation. We compare ICL2FID against traditional supervised learning and other LLM methods, demonstrating that it not only achieves superior accuracy but does so at a fraction of the cost and time. These findings highlight ICL2FID’s potential as a viable alternative for hierarchical label generation in scenarios with limited resources and huge data sets. Code is available at https://***/zdy93/ICL2FID.

关键词： Training Social networking (online) Annotations Biological system modeling Surveillance Large language models Supervised learning Mortality Labeling Public healthcare

来源：评论

学校读者我要写书评

暂无评论

On the Continuity of Moore-Penrose Inverse of the Graph Laplacian

On the Continuity of Moore-Penrose Inverse of the Graph Lapl...

引用

IEEE Global Conference on Consumer Electronics (GCCE)

作者： Tse-Yu Lin Yen-lung Tsai Data Science Degree Program National Taiwan University Taipei Taiwan Department of Mathematical Sciences National Chengchi University Taipei Taiwan

ISBN: (数字)9798350355079

ISBN: (纸本)9798350355086

Graph Laplacian is a fundamental tool in various fields such as spectral clustering, network analysis, image processing, and, deep learning recently for studying message passing in graph neural network models. To support the theoretical use of the graph Laplacian in these fields, in this work, we study the continuity of the Moore-Penrose generalized inverse of the graph Laplacian. We provide a graph-theoretical proof of this continuity in terms of the connectivity of the underlying graph associated with a given graph Laplacian matrix.

关键词： Deep learning Analytical models Laplace equations Message passing Image processing Network analyzers Graph neural networks Consumer electronics

来源：评论

学校读者我要写书评

暂无评论

Exploring Drug Repurposing Success Stories Through a Network-based Approach: Insights from a Case Study

Exploring Drug Repurposing Success Stories Through a Network...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Pierini, Elisa Mazza, Ludovica Petti, Manuela Tieri, Paolo Sapienza University of Rome Data Science MSc Program Rome Italy Sapienza University of Rome Diag Dept. Comp. Contr. Manag. Eng. Rome Italy Cnr National Research Council Iac Institute for Applied Computing Rome Italy

ISBN: (纸本)9798350386226

Drug repositioning is a promising strategy to discover new therapeutic applications for existing drugs, significantly reducing the time and costs associated with traditional drug development. This study employs a network medicine approach to analyze successful cases of drug repositioning, focusing on the exploratory hypothesis that the efficacy of repositioning may be determined by functional similarity between between diseases for which the drug was originally designed and diseases for which the same drug is reused. Network medicine tools were employed to investigate the connections between disease-associated genes, proteins, and approved drugs. Biological networks, including protein-protein interactions and functional interactions networks, as well as gene- and drug-disease association data are analyzed to identify functional similarities and possible molecular connections between diseases and treatments. Using clustering techniques and topological analysis, the results reveal a suggestive overlap of involved genes and functional interactions, emphasizing the value of computational methods in accelerating drug repositioning efforts and improving understanding of drug repositioning dynamics for more efficient therapeutic interventions. © 2024 IEEE.

关键词： Network theory (graphs)

来源：评论

学校读者我要写书评

暂无评论

Digital Twin (DT) Smart City for Air Quality Management

引用

Procedia Computer science 2023年 227卷 524-533页

作者： Dedy Ariansyah Mahmud Isnan Reza Rahutomo Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta 11480 Indonesia Information Systems Department School of Information Systems Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program-Master of Computer Science Program Bina Nusantara University Jakarta 11480 Indonesia

Air pollution is a pressing issue in cities, and managing air quality poses a challenge for urban designers and decision-makers. This study proposes a Digital Twin (DT) Smart City integrated with Mixed Reality technology to enhance visualization and collaboration for addressing urban air pollution. The research adopts an applied research approach, with a focus on developing a DT framework. A use case of DT development for Jakarta, the capital of Indonesia, is presented. By integrating air quality data, meteorological information, traffic patterns, and urban infrastructure data, the DT provides a comprehensive understanding of air pollution dynamics. The visualization capabilities of the DT, utilizing Mixed Reality technology, facilitate effective decision-making and the identification of strategies for managing air quality. However, further research is needed to address data management challenges to build a DT for Smart City at scale.

关键词： Digital Twin Smart City Mixed Reality Augmented Reality

来源：评论

学校读者我要写书评

暂无评论

A Multi-step Loss Function for Robust Learning of the Dynamics in Model-based Reinforcement Learning

arXiv

引用

arXiv 2024年

作者： Benechehab, Abdelhakim Thomas, Albert Paolo, Giuseppe Filippone, Maurizio Kégl, Balázs Noah's Ark Lab Huawei Technologies France Department of Data Science EURECOM France Statistics Program KAUST Saudi Arabia

In model-based reinforcement learning, most algorithms rely on simulating trajectories from one-step models of the dynamics learned on data. A critical challenge of this approach is the compounding of one-step prediction errors as the length of the trajectory grows. In this paper we tackle this issue by using a multi-step objective to train one-step models. Our objective is a weighted sum of the mean squared error (MSE) loss at various future horizons. We find that this new loss is particularly useful when the data is noisy (additive Gaussian noise in the observations), which is often the case in real-life environments. To support the multi-step loss, first we study its properties in two tractable cases: i) uni-dimensional linear system, and ii) two-parameter non-linear system. Second, we show in a variety of tasks (environments or datasets) that the models learned with this loss achieve a significant improvement in terms of the averaged R2-score on future prediction horizons. Finally, in the pure batch reinforcement learning setting, we demonstrate that one-step models serve as strong baselines when dynamics are deterministic, while multi-step models would be more advantageous in the presence of noise, highlighting the potential of our approach in real-world applications. © 2024, CC BY.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

Mathematical Modeling and Characterization of a Wearable Soft Robotic Device for Muscle Mechanotherapy 46

Mathematical Modeling and Characterization of a Wearable Sof...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Ticllacuri, Victor Mio, Renato Biomedical Engineering Program PUCP-UPCH Lima Peru Pontificia Universidad Catolica del Peru Laboratory of Biomechanics and Applied Robotics Lima Peru Universidad Peruana Cayetano Heredia Laboratory of Biomedical Engineering Lima Peru University of Bayreuth Digital Health with a Focus on Data Science Germany

ISBN: (纸本)9798350371499

Treatments of disuse-induced muscle atrophy entail unmet clinical needs due to the lack of medical devices capable of mimicking physicians manual therapies. Therefore, in this paper we develop and model a wearable soft pneumatic elastomeric actuator to perform deep cyclic compression stimuli on human soft tissues for muscle rehabilitation by mechanotherapy. Static and dynamic characterization of the prototype demonstrate a 2.5 mm active deformation at 100 kPa with 600 mm3/s and a 5 Hz bandwidth. We estimate the transfer function of the experimentally acquired pressure, flow and deformation signals, processed by a Gaussian kernel-based approach. Our mathematical model accurately describes the actuator behavior and enables to extract its mechanical parameters. Then, through computational simulations, we illustrate its efficacy in emulating multiple complex bio-inspired movements. Our proposed methodology aims to improve the control efficiency in wearable soft robotics for muscle atrophy treatment. © 2024 IEEE.

关键词： Pneumatic actuators

来源：评论

学校读者我要写书评

暂无评论

Predicting Oil and Gas Pipe Wall Thickness Using Machine Learning

Predicting Oil and Gas Pipe Wall Thickness Using Machine Lea...

引用

2021 International Conference on data Analytics for Business and Industry, ICDABI 2021

作者： Mohammed, Abdulrahim Hewahi, Nabil College of Science University of Bahrain Big Data Science and Analytics Program Sakhir Bahrain College of Information Technology University of Bahrain Department of Computer Science Sakhir Bahrain

ISBN: (纸本)9781665416566

Pipeline networks are crucial for process industries transportation and business operation. These vital elements, however, are highly exposed to material degradation due to corrosion that seriously impedes operational profitability, reliability, and safety. Industries usually monitor pipeline corrosion rate by gauging pipe wall thickness. Predicting pipe wall thickness helps industries to identify locations with high corrosion rate at an early stage and take necessary actions. The aim of this research is to predict pipe wall thickness at different locations using different machine learning algorithms including Support Vector Machine (SVM), Random Forest (RF), k-Nearest Neighbor (KNN), fully connected Artificial Neural Network (ANN), and Long Short-Term Memory (LSTM). The data processed and analyzed in this study included six different process variables as well as pipe wall thickness at three different locations in a downstream oil and gas industry. The study findings demonstrated that LSTM with test Root Mean Squared Errors (RMSEs) of 0.019 mm, 0.015 mm, and 0.017 mm for the three selected locations, outperformed the other methods applied and successfully identified the pipe wall thickness pattern. © 2021 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

data mining for epidemiology: The correlation of typhoid fever occurrence and environmental factors

引用

Procedia Computer science 2023年 216卷 284-292页

作者： Faisal Asadi Joko Pebrianto Trinugroho Alam Ahmad Hidayat Reza Rahutomo Bens Pardamean Bioinformatics & Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 Information System Department School of Information System Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta Indonesia 11480

Typhoid fever is an endemic disease that burdens Indonesia and has a potentially fatal infection multisystem. Salmonella typhi bacterium is responsible for typhoid fever disease. Poor sanitation, crowding, and slums are the main factors of increasing typhoid fever incidences. Environmental factors directly connected to meteorological factors are the main factor in breeding the Salmonella typhi bacterium. This study aims to identify the correlation between meteorological parameters and typhoid fever disease occurrence. The study was carried out in Jakarta, Indonesia, and the Bureau of Meteorological, Climatology, and Geophysics (BMKG) provided the meteorological parameter data. In addition, the Jakarta health surveillance office provided information on typhoid fever hospitalizations from 2019 to 2021. Pearson's concept was utilized d to investigate the correlation between typhoid fever incidences and the meteorological parameters. Humidity, precipitation, and wind speed are the meteorological parameters that significantly affect in contribute to the occurrence of typhoid fever disease. These findings might be used as a reference for Indonesia's government in making public policy to prevent typhoid fever in Indonesia.

关键词： typhoid fever salmonella typhi endemic disease meteorological factors

来源：评论

学校读者我要写书评

暂无评论

Federated Approach to Online Pairwise Comparison Ranking Problem

Federated Approach to Online Pairwise Comparison Ranking Pro...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Tse-Yu Lin Yen-Lung Tsai Data Science Degree Program National Taiwan University Taipei Taiwan Department of Mathematical Sciences National Chengchi University Taipei Taiwan

In this work, we propose a federated learning (FL) framework for the online HodgeRank problem to obtain a global ranking based on the pairwise comparison data provided by users while respecting users’ data privacy. HodgeRank is a statistical ranking method that views pairwise comparison data as an edge-weighted directed graph, and, vertex weight function can be viewed as a ranking that recovers edge weight using difference. A critical assumption of the HodgeRank is the connectivity of the comparison graph. This assumption relies on the contribution of users’ data to form a weakly connected directed graph between items to be ranked. In this paper, we aim to find a framework to compute HodgeRank with the minimum usage of users’ data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Lung Cancer Diagnosis Based on Object Detection Technology 14th

Lung Cancer Diagnosis Based on Object Detection Technology

引用

14th International Conference on Frontier Computing, FC 2024

作者： Xu, Jia-Lang Wang, Pei-Yun Huang, Tzu-Hsuan Hsu, Ying-Lin Huang, Kuo-Yang Chen, Mu-Yen Artificial Intelligence Development Center Changhua Christian Hospital Changhua Taiwan Doctoral Program in Data Science and Industrial Analytics National Chung Hsing University Taichung Taiwan Department of Applied Mathematics and Institute of Statistics National Chung Hsing University Taichung Taiwan Division of Chest Medicine Department of Internal Medicine Changhua Christian Hospital Changhua Taiwan Department of Engineering Science National Cheng Kung University Tainan Taiwan

ISBN: (纸本)9789819623945

With the rise of artificial intelligence, many people nowadays use artificial intelligence to help solve some problems in life, and the medical field is also with the rise of artificial intelligence, many people are slowly applying artificial intelligence to medical images to assist in decision-making, this study proposes a Yolov8 algorithm for object tracking of CT images of lung cancer, which can quickly tell the doctor where the cancer is and what the type of cancer is. The results of this study show that the Box_Loss, Cls_Loss, and Dfl_loss of the Yolov8 algorithm in detecting the location of lung cancer are 1.3689, 0.4552, and 1.5569 in the validation data, respectively, and thus this study suggests that this method can help physicians know the location of the tumor and what kind of tumor it belongs to. Therefore, this study suggests that this method can help physicians know the location of the tumor and the type of tumor. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Lung cancer

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：