检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wu, Yusen Chen, Hao Makki, Alex Pissinou Nguyen, Phuong Yesha, Yelena Frost Institute for Data Science and Computing University of Miami MiamiFL United States Department of Radiology University of Miami MiamiFL United States

Distributional drift detection is important in medical applications as it helps ensure the accuracy and reliability of models by identifying changes in the underlying data distribution that could affect diagnostic or treatment decisions. However, current methods have limitations in detecting drift;for example, the inclusion of abnormal datasets can lead to unfair comparisons. This paper presents an accurate and sensitive approach to detect distributional drift in CT-scan medical images by leveraging data-sketching and fine-tuning techniques. We developed a robust baseline library model for real-time anomaly detection, allowing for efficient comparison of incoming images and identification of anomalies. Additionally, we fine-tuned a vision transformer pre-trained model to extract relevant features using breast cancer images as an example, significantly enhancing model accuracy to 99.11%. Combining with data-sketches and fine-tuning, our feature extraction evaluation demonstrated that cosine similarity scores between similar datasets provide greater improvements, from around 50% increased to 100%. Finally, the sensitivity evaluation shows that our solutions are highly sensitive to even 1% salt-and-pepper and speckle noise, and it is not sensitive to lighting noise (e.g., lighting conditions have no impact on data drift). The proposed methods offer a scalable and reliable solution for maintaining the accuracy of diagnostic models in dynamic clinical environments. © 2024, CC BY.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

A Collaborative Filtering Algorithm with Improved User Similarity Calculation for Enhanced Recommendation Accuracy and Personalization 12

A Collaborative Filtering Algorithm with Improved User Simil...

引用

12th International Conference of Information and Communication Technology, ICTech 2023

作者： Ding, Shili Fan, Yue Liu, Jing Zhang, Yonghong Shenyang Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China School of Information Science and Technology Taishan University Shandong Taian China Shandong University Laboratory of Big Data and Artificial Intelligence Technology Jinan China

ISBN: (纸本)9798350332919

The conventional method for calculating user similarity in the collaborative filtering recommendation algorithm based on users fails to address the challenge of variations in the number, value, and popularity of items that are collaboratively rated by multiple users. In order to solve the above problems, a new user similarity calculation method is proposed. By fusing cosine similarity and Jackard similarity, the problem of difference in the number of common scoring items is alleviated, so as to reduce the error of scoring prediction. Finally, experiments were performed on the MovieLens dataset, and the findings demonstrated that the enhanced algorithm outperforms the established benchmark similarity algorithm regarding mean absolute error (MAE). In addition, the improved algorithm has good robustness in predicting the accuracy of user ratings and recommendation quality. © 2023 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Truly Multivariate Structured Additive Distributional Regression

arXiv

引用

arXiv 2023年

作者： Kock, Lucas Klein, Nadja Department of Statistics and Data Science National University of Singapore Singapore Scientific Computing Center Karlsruhe Institute of Technology Germany

Generalized additive models for location, scale and shape (GAMLSS) are a popular extension to mean regression models where each parameter of an arbitrary parametric distribution is modelled through covariates. While such models have been developed for univariate and bivariate responses, the truly multivariate case remains extremely challenging for both computational and theoretical reasons. Alternative approaches to GAMLSS may allow for higher-dimensional response vectors to be modelled jointly but often assume a fixed dependence structure not depending on covariates or are limited with respect to modelling flexibility or computational aspects. We contribute to this gap in the literature and propose a truly multivariate distributional model, which allows one to benefit from the flexibility of GAMLSS even when the response has dimension larger than two or three. Building on copula regression, we model the dependence structure of the response through a Gaussian copula, while the marginal distributions can vary across components. Our model is highly parameterized but estimation becomes feasible with Bayesian inference employing shrinkage priors. We demonstrate the competitiveness of our approach in a simulation study and illustrate how it complements existing approaches along the examples of childhood malnutrition and a yet unexplored data set on traffic detection in Berlin. Copyright © 2023, The Authors. All rights reserved.

关键词： Additives

来源：评论

学校读者我要写书评

暂无评论

Decoding Urban Industrial Complexity: Enhancing Knowledge-Driven Insights via IndustryScopeGPT 24

Decoding Urban Industrial Complexity: Enhancing Knowledge-Dr...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Wang, Siqi Liang, Chao Gao, Yunfan Liu, Yang Li, Jing Wang, Haofen Tongji University Shanghai China Department of Computing The Hong Kong Polytechnic University Hong Kong Guangdong Guodi Institute of Resources and Environment Guangzhou China Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai China College of Design and Innovation Tongji University Shanghai China Research Centre on Data Science & Artificial Intelligence Hong Kong

ISBN: (纸本)9798400706868

Industrial parks are critical to urban economic growth. Yet, their development often encounters challenges stemming from imbalances between industrial requirements and urban services, underscoring the need for strategic planning and operations. This paper introduces IndustryScopeKG, a pioneering large-scale multi-modal, multi-level industrial park knowledge graph, which integrates diverse urban data including street views, corporate, socio-economic, and geospatial information, capturing the complex relationships and semantics within industrial parks. Alongside this, we present the IndustryScopeGPT framework, which leverages Large Language Models (LLMs) with Monte Carlo Tree Search to enhance tool-augmented reasoning and decision-making in Industrial Park Planning and Operation (IPPO). Our work significantly improves site recommendation and functional planning, demonstrating the potential of combining LLMs with structured datasets to advance industrial park management. This approach sets a new benchmark for intelligent IPPO research and lays a robust foundation for advancing urban industrial development. The dataset and related code are available at https://***/Tongji-KGLLM/IndustryScope. © 2024 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

GroupDiff: Diffusion-based Group Portrait Editing

arXiv

引用

arXiv 2024年

作者： Jiang, Yuming Zhao, Nanxuan Liu, Qing Singh, Krishna Kumar Yang, Shuai Loy, Chen Change Liu, Ziwei College of Computing and Data Science Nanyang Technological University Singapore Adobe Research United States Wangxuan Institute of Computer Technology Peking University China

Group portrait editing is highly desirable since users constantly want to add a person, delete a person, or manipulate existing persons. It is also challenging due to the intricate dynamics of human interactions and the diverse gestures. In this work, we present GroupDiff, a pioneering effort to tackle group photo editing with three dedicated contributions: 1) data Engine: Since there is no labeled data for group photo editing, we create a data engine to generate paired data for training. The training data engine covers the diverse needs of group portrait editing. 2) Appearance Preservation: To keep the appearance consistent after editing, we inject the images of persons from the group photo into the attention modules and employ skeletons to provide intra-person guidance. 3) Control Flexibility: Bounding boxes indicating the locations of each person are used to reweight the attention matrix so that the features of each person can be injected into the correct places. This inter-person guidance provides flexible manners for manipulation. Extensive experiments demonstrate that GroupDiff exhibits state-of-the-art performance compared to existing methods. GroupDiff offers controllability for editing and maintains the fidelity of the original photos. Copyright © 2024, The Authors. All rights reserved.

关键词： Photography

来源：评论

学校读者我要写书评

暂无评论

Structured multi-track accompaniment arrangement via style prior modelling 24

Structured multi-track accompaniment arrangement via style p...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Jingwei Zhao Gus Xia Ziyu Wang Ye Wang Institute of Data Science NUS and Integrative Sciences and Engineering Programme NUS Graduate School Machine Learning Department MBZUAI and Computer Science Department NYU Shanghai Computer Science Department NYU Shanghai and Machine Learning Department MBZUAI School of Computing NUS and Institute of Data Science NUS and Integrative Sciences and Engineering Programme NUS Graduate School

ISBN: (纸本)9798331314385

In the realm of music AI, arranging rich and structured multi-track accompaniments from a simple lead sheet presents significant challenges. Such challenges include maintaining track cohesion, ensuring long-term coherence, and optimizing computational efficiency. In this paper, we introduce a novel system that leverages prior modelling over disentangled style factors to address these challenges. Our method presents a two-stage process: initially, a piano arrangement is derived from the lead sheet by retrieving piano texture styles; subsequently, a multi-track orchestration is generated by infusing orchestral function styles into the piano arrangement. Our key design is the use of vector quantization and a unique multi-stream Transformer to model the long-term flow of the orchestration style, which enables flexible, controllable, and structured music generation. Experiments show that by factorizing the arrangement task into interpretable sub-stages, our approach enhances generative capacity while improving efficiency. Additionally, our system supports a variety of music genres and provides style control at different composition hierarchies. We further show that our system achieves superior coherence, structure, and overall arrangement quality compared to existing baselines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on the Application of Business data Fusion in the Engineering Management of Oil and Gas Storage and Transportation Station 4

Research on the Application of Business Data Fusion in the E...

引用

4th International Conference on Computer science and Management Technology, ICCSMT 2023

作者： Xie, Rui Fan, Bo Ma, Jianlin Pan, Meng Southwest Pipeline Ltd. PipeChina ChengDu610213 China School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu610031 China Chengdu Aerospace Science and Industry Big Data Institute Ltd. Casic Chengdu610213 China National Engineering Laboratory of Industrial Big-Data Application Technology Casic Chengdu610218 China

ISBN: (纸本)9798400709517

Due to challenges such as complex contractor personnel, a large amount of scattered form data, a cumbersome business implementation process, low levels of digitalization and security, and difficult management in the engineering management business of oil and gas storage and transportation stations, this paper proposes a study on business data fusion application in the engineering management of oil and gas storage and transportation stations. Focused on the business processes and data of engineering management in oil and gas storage and transportation stations, this research establishes and analyzes an architecture for engineering management business in these stations. Using an Artifact-centric data fusion method, the research constructs an information model for the engineering management business, identifying the data topics for this area. Finally, the research applies and verifies the study of business data fusion through real-world business management scenarios. As researchers in the field of business data fusion, this study utilizes digital technologies and methods to enhance the overall safety management of engineering operations, thereby promoting the transformation and upgrading of engineering management business in oil and gas storage and transportation stations © 2023 ACM.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

A Unified Causal View of Instruction Tuning

arXiv

引用

arXiv 2024年

作者： Chen, Lu Huang, Wei Zhang, Ruqing Chen, Wei 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 China

Instruction tuning on a mixture of tasks has improved zero-shot capabilities in natural language processing (NLP) . Nevertheless, existing methods often learn features that exhibit correlations between instruction-formatted samples and target labels, rather than causal relationships. Termed as "spurious correlation" in statistics, such a correlation may change drastically in a new task, making the effect from the learned features to be misleading. To this end, we develop a meta Structural Causal Model (meta-SCM) to integrate different NLP tasks under a single causal structure of the data. Specifically, the meta-SCM introduces multiple latent factors that represent properties of source context, only some of which causally influence the target labels for a specific task. The key idea is to learn task-required causal factors and only use those to make predictions for a given task. Theoretically, we prove the causal factor can be identified without mixing information from others. Guided by the identifiability, we propose a Structural Instruction Tuning (SIT) method to learn the task-required causal representations that can mimic the causal factors for each task. The utility of our approach is verified by improvements of zero-shot ability on a range of unseen datasets and tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Meta-Path Based Social Relation Reasoning in a Deep and Robust Way 28th

Meta-Path Based Social Relation Reasoning in a Deep and R...

引用

28th International Conference on database Systems for Advanced Applications, DASFAA 2023

作者： Jiang, Xuhui Shen, Yinghan Wang, Yuanzhuo Shen, Huawei Xu, Chengjin Ma, Shengjie Data Intelligent System Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology UCAS Gloucester United Kingdom Big Data Academy Zhongke Zhengzhou China International Digital Economy Academy Shenzhen China Gaoling School of Artificial Intelligence Renmin University of China Beijing China

ISBN: (纸本)9783031306747

Social relation reasoning in heterogeneous social networks (HSNs) should not only infer whether people are connected, but also why they know each other and what their relationship is. This task is challenging because the heterogeneous social network is non-trivial to leverage and the collected data is always noisy and incomplete, which leads that the existing rule-based and representation methods cannot efficiently and accurately reason social relations. To reason social relations in noisy and incomplete HSNs, we shift from simply inferring meta-path based social relations by rule-based methods to reasoning by social relation learning. Then, we present an inductive model named Heterogeneous Graph Variational AutoEncoders (HGVAE) towards robust social relation learning on noisy and incomplete HSN data. In HGVAE, the well-designed heterogeneous graph encoder, multi-signal decoder, and variational inference mechanism bring prominent robustness and significant performance improvement. Extensive experiments are conducted to compare our methods against a set of the most representative baseline methods. The efficiency analysis, robust analysis and ablation studies confirm the value of our proposed approach for modelling meta-path based social relations buried in various HSNs. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

S2CCT: Self-Supervised Collaborative CNN-Transformer for Few-shot Medical Image Segmentation

S2CCT: Self-Supervised Collaborative CNN-Transformer for Few...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhou, Rongzhou Shu, Ziqi Xie, Weixing Yao, Junfeng Hong, Qingqi Xiamen University National Institute for Data Science in Health and Medicine China Xiamen University Center for Digital Media Computing School of Film School of Informatics Xiamen361005 China Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage Fujian and Taiwan Ministry of Culture and Tourism China Xiamen University Institute of Artificial Intelligence Xiamen361005 China

ISBN: (纸本)9798350386226

Self-supervised pre-training followed by fine-tuning is a potent paradigm for few-shot learning, leveraging extensive unlabeled data with remarkable efficacy. Current self-supervised methods often lean towards Vision Transformers (ViTs) rather than CNN-Transformer hybrid architectures, which generally demonstrate superior performance. However, this reliance on ViTs can lead to poor perception of local features by the model. The challenge lies in designing a suitable proxy task for hybrid architectures like CNN-Transformers, which have significant structural differences. Additionally, the current organization of CNN-Transformer hybrid backbones is often sequential, hindering collaboration during pre-training and the acquisition of robust representations. To address these issues, we propose Self-Supervised Collaborative CNN-Transformer (S2CCT) for few-shot medical image segmentation. This framework introduces three innovative designs: (1) a composite proxy task based on image masking and image super-resolution tailored for CNN-Transformer hybrid architectures, enabling the backbone to acquire robust representations during pre-training that can be transferred to downstream tasks;(2) a parallel CNN-Transformer architecture that better attends to multi-scale features in images, making it more suitable for dense prediction tasks like image segmentation;(3) a sparse and dense feature fusion module to enhance collaboration between the two encoders. Experiments demonstrate that S2CCT outperforms previous state-of-the-art methods on two public medical image segmentation benchmarks, i.e., ACDC and KiTs19. The code and pretrained models will be released soon. © 2024 IEEE.

关键词： Image segmentation

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：