检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Jun-Yi Hang Min-Ling Zhang School of Computer Science and Engineering Southeast University Nanjing China and Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China

Semi-supervised learning (SSL) is a classical machine learning paradigm dealing with labeled and unlabeled data. However, it often suffers performance degradation in real-world open-set scenarios, where unlabeled data contains outliers from novel categories that do not appear in labeled data. Existing studies commonly tackle this challenging open-set SSL problem with detect-and-filter strategy, which attempts to purify unlabeled data by detecting and filtering outliers. In this paper, we propose a novel binary decomposition strategy, which refrains from error-prone procedure of outlier detection by directly transforming the original open-set SSL problem into a number of standard binary SSL problems. Accordingly, a concise yet effective approach named BDMatch is presented. BDMatch confronts two attendant issues brought by binary decomposition, i.e. class-imbalance and representation-compromise, with adaptive logit adjustment and label-specific feature learning respectively. Comprehensive experiments on diversified benchmarks clearly validate the superiority of BDMatch as well as the effectiveness of our binary decomposition strategy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Early Prediction of Heart Disease via LSTM-XGBoost 23

Early Prediction of Heart Disease via LSTM-XGBoost

引用

9th International Conference on Computing and Artificial Intelligence, ICCAI 2023

作者： Zang, Xiaodong Du, Jin Song, Yuansheng School of Cyber Science and Engineering Qufu Normal University Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University Nanjing211189 China School of Cyber Science and Engineering Qufu Normal University China

ISBN: (纸本)9781450399029

With the development of information and technology, especially with the boom in big data, healthcare support systems are becoming much better. However, an early diagnosis is not an easy task because it is hard to find out the hidden patterns in the disease. The symptoms of heart failure are usually non-specific. Therefore, this study aims to devise an early prediction model for incident heart disease based on machine learning algorithms. In this study, we compared several powerful models, including support vector machines (SVM), k-nearest neighbor (KNN), decision tree, extreme gradient boosting (XGBoost), random forest, gradient boosting decision tree (GBDT), categorical boosting (CatBoost), light gradient boosting machine (LightGBM), and choose two best models, namely, XGBoost and LSTM as our prediction model. The XGBoost algorithm was used to extract a subset from the data of patients, which will be fed into the LSTM-XGBoost model for training. An experiment comparison is conducted based on the data from Kaggle. Experimental results demonstrate that the LSTM-XGBoost model can operate effectively with a prediction accuracy achieving 0.9896 and a loss rate achieving 0.0105, which is much better than XGBoost or LSTM, respectively. © 2023 Copyright held by the owner/author(s).

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Research on the Application of Digital Signature in University Electronic Government System 6

Research on the Application of Digital Signature in Universi...

引用

6th International Conference on computer network, Electronic and Automation, ICCNEA 2023

作者： Wang, Tianma Zhao, Dongmei Qi, Jianjun North China Electric Power University International Education Institute Beijing China Hebei Normal University College of Computer and Cyber Security Shijiazhuang China Key Laboratory of Network and Information Security in Hebei Province Shijiazhuang China

ISBN: (纸本)9798350305388

This article analyzes the principles and processes of digital signature technology, as well as its application methods in the university e-government system. On the one hand, it meets the business management needs of university, and on the other hand, the application of digital signature and timestamp electronic signature ensures the security of university e-government SystemThe university e-government management system based on digital signature technology verifies the identity of users such as the sender and receiver of files, and issues digital certificates. The sender uses digital certificates for system authorization. Signs and encrypts confidential files such as documents through digital signatures to protecting the security of electronic file transmission. Upload the digitally signed and encrypted documents to the system, which completes the sending and receiving of the documents. On the one hand, the recipient downloads documents through the system and uses digital signatures to verify the integrity and authenticity of the documents. On the other hand, digitally sign the document and upload it to the system. Both parties complete the distribution and upload of documents through the system. © 2023 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Classification of Zhuang Dialect combined with Bert and SimAM

Classification of Zhuang Dialect combined with Bert and SimA...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Min Huang Xuejun Zhang Wenkang Chen School of Computer Electronics and Information Guangxi Key Laboratory of Multimedia Communications and Network Technology Guangxi University Nanning China School of Electrical Engineering Guangxi Key Laboratory of Multimedia Communications and Network Technology Guangxi University Nanning China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Language recognition refers to the automatic recognition of the language type of the given speech segments. Zhuang is an important language in Southeast Asia, with more than 16 million native speakers. Due to the scarcity of data resources, there is relatively little research about Zhuang in the field of natural language processing, especially in the area of speech-level exploration. Because of the existence of a variety of dialects in Zhuang, this paper is the first to create a speech dataset for the study of the Zhuang language. In the experiment, it was observed that the output of different encoder layers of the BERT has an impact on classification, so this paper innovatively proposes to integrate the SimAM attention mechanism with the BERT model. The model uses a phone recognizer to extract phone sequences from speech segments. Then the Bert model combined with the integrated SimAM attention mechanism performs deep feature representation learning on the semantic information and word order of the sequence. Finally, the classifier realizes the efficient classification of the Zhuang language. Compared with Baseline Systems, the accuracy of the dialect recognition model proposed in this paper is 91.37%, which fully proves the effectiveness of the model.

关键词： Representation learning Attention mechanisms Semantics Speech recognition Bidirectional control Signal processing Feature extraction Encoding Natural language processing Speech processing

来源：评论

学校读者我要写书评

暂无评论

NPPlanner: A Tool for National Park Planning at Scale Form Plant Diversity 6

NPPlanner: A Tool for National Park Planning at Scale Form P...

引用

6th IEEE information Technology, networking, Electronic and Automation Control Conference, ITNEC 2023

作者： Hu, Zhilong Meng, Zhen Yi, Xiujuan Wang, Xuezhi Zhao, Lina Ye, Jianfei Chen, Zhiduan Chinese Academy of Sciences Computer Network Information Center Beijing China University of Chinese Academy of Sciences Beijing China Chinese Academy of Sciences State Key Laboratory of Systematic and Evolutionary Botany Institute of Botany Beijing China

ISBN: (纸本)9781665460033

Biodiversity is vital to human survival and has become a global issue. The establishment of national parks is regarded as the most straight and effective means for biodiversity conservation. Although the theory of national park planning has been well studied, there is still a lack of an available national park planning tool. In this paper, NPPlanner, a tool for national park planning at scale is proposed and implemented. It integrates the information of plants and the regional data of China and implements the visualization of plant distribution and the national park planning as a set of microservices by employing WebGIS and other techniques. Meanwhile, the method combining the green index and protective index is presented to better represent the regional biodiversity. The query for plant distribution and planning of national park will be visualized and the results are available to export for further work. NPPlanner is freely accessible at http://***/NPPlanner. © 2023 IEEE.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Consistent Multi-Granular Rationale Extraction for Explainable Multi-hop Fact Verification

arXiv

引用

arXiv 2023年

作者： Si, Jiasheng Zhu, Yingjie Zhou, Deyu School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China

The success of deep learning models on multi-hop fact verification has prompted researchers to understand the behavior behind their veracity. One possible way is erasure search: obtaining the rationale by entirely removing a subset of input without compromising the veracity prediction. Although extensively explored, existing approaches fall within the scope of the single-granular (tokens or sentences) explanation, which inevitably leads to explanation redundancy and inconsistency. To address such issues, this paper explores the viability of multi-granular rationale extraction with consistency and faithfulness for explainable multi-hop fact verification. In particular, given a pretrained veracity prediction model, both the token-level explainer and sentence-level explainer are trained simultaneously to obtain multi-granular rationales via differentiable masking. Meanwhile, three diagnostic properties (fidelity, consistency, salience) are introduced and applied to the training process, to ensure that the extracted rationales satisfy faithfulness and consistency. Experimental results on three multi-hop fact verification datasets show that the proposed approach outperforms some state-of-the-art baselines. Copyright © 2023, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

NL2SQL Generation with Noise Labels based on Multi-task Learning 5

NL2SQL Generation with Noise Labels based on Multi-task Lear...

引用

2022 5th International Symposium on Big Data and Applied Statistics, ISBDAS 2022

作者： Long, Lingli Zhu, Yongjin Shao, Jun Kong, Zheng Li, Jian Xiang, Yanzheng Zhang, Xu Jiangsu Frontier Electric Technology Co. Ltd. China School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China

With the rapid development of artificial intelligence technology, semantic recognition technology is becoming more and more mature, providing the preconditions for the development of natural language to SQL (NL2SQL) technology. In the latest research on NL2SQL, the use of pre-trained models as feature extractors for natural language and table schema has led to a very significant improvement in the effectiveness of the models. However, the current models do not take into account the degradation of the noisy labels on the overall SQL statement generation. It is crucial to reduce the impact of noisy labels on the overall SQL generation task and to maximize the return of accurate answers. To address this issue, we propose a restrictive constraint-based approach to mitigate the impact of noise-labeled labels on other tasks. In addition, parameter sharing approach is used in noiseless-labeled labels to capture each part's correlations and improve the robustness of the model. In addition, we propose to use Kullback-Leibler divergence to constrain the discrepancy between hard and soft constrained coding of noisy labels. Our model is compared with some recent state-of-the-art methods, and experimental results show a significant improvement over the approach in this paper. © Published under licence by IOP Publishing Ltd.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

RankMatch: A Novel Approach to Semi-Supervised Label Distribution Learning Leveraging Inter-label Correlations

arXiv

引用

arXiv 2023年

作者： Kou, Zhiqiang Xie, Yucheng Wang, Jing Jia, Yuheng Shi, Boyu Geng, Xin MOE Key Laboratory of Computer Network and Information Integration School of Computer Science and Engineering Southeast University Nanjing China

This paper introduces RankMatch, an innovative approach for Semi-Supervised Label Distribution Learning (SSLDL). Addressing the challenge of limited labeled data, RankMatch effectively utilizes a small number of labeled examples in conjunction with a larger quantity of unlabeled data, reducing the need for extensive manual labeling in Deep Neural network (DNN) applications. Specifically, RankMatch introduces an ensemble learning-inspired averaging strategy that creates a pseudo-label distribution from multiple weakly augmented images. This not only stabilizes predictions but also enhances the model’s robustness. Beyond this, RankMatch integrates a pairwise relevance ranking (PRR) loss, capturing the complex inter-label correlations and ensuring that the predicted label distributions align with the ground truth. We establish a theoretical generalization bound for RankMatch, and through extensive experiments, demonstrate its superiority in performance against existing SSLDL methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

NL2SQL Enhancement through Semantic Representation Aggregation 5

NL2SQL Enhancement through Semantic Representation Aggregati...

引用

5th International Conference on computer information Science and Application Technology, CISAT 2022

作者： Long, Lingli Zhu, Yongjin Shao, Jun Kong, Zheng Li, Jian Liu, Zejie Zhang, Xu Jiangsu Frontier Electric Technology Co. Ltd. China School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China

ISBN: (纸本)9781510660076

Natural Language to SQL (NL2SQL) is a technology that converts natural language into executable SQL statements. For single table tasks, the dominant approach is a slot-filling-based model which actually performs multi-objective prediction. However, in existing multi-objective models, it is difficult to optimize multiple objectives simultaneously. Low correlation or conflict between various objectives can result in the model not being able to learn the parameters effectively. To effectively address this problem, this paper considers redesigning the sharing mechanism between multiple tasks and the specific network structure of individual tasks through a semantic aggregation approach in order to alleviate the above phenomenon. © 2022 SPIE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Vision-language models are strong noisy label detectors 24

Vision-language models are strong noisy label detectors

引用

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

作者： Tong Wei Hao-Tian Li Chun-Shu Li Jiang-Xin Shi Yu-Feng Li Min-Ling Zhang School of Computer Science and Engineering Southeast University Nanjing China and Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education China and National Key Laboratory for Novel Software Technology Nanjing University China School of Computer Science and Engineering Southeast University Nanjing China and Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education China National Key Laboratory for Novel Software Technology Nanjing University China and School of Artificial Intelligence Nanjing University China

ISBN: (纸本)9798331314385

Recent research on fine-tuning vision-language models has demonstrated impressive performance in various downstream tasks. However, the challenge of obtaining accurately labeled data in real-world applications poses a significant obstacle during the fine-tuning process. To address this challenge, this paper presents a Denoising Fine-Tuning framework, called DEFT, for adapting vision-language models. DEFT utilizes the robust alignment of textual and visual features pre-trained on millions of auxiliary image-text pairs to sieve out noisy labels. The proposed framework establishes a noisy label detector by learning positive and negative textual prompts for each class. The positive prompt seeks to reveal distinctive features of the class, while the negative prompt serves as a learnable threshold for separating clean and noisy samples. We employ parameter-efficient fine-tuning for the adaptation of a pre-trained visual encoder to promote its alignment with the learned textual prompts. As a general framework, DEFT can seamlessly fine-tune many pre-trained models to downstream tasks by utilizing carefully selected clean samples. Experimental results on seven synthetic and real-world noisy datasets validate the effectiveness of DEFT in both noisy label detection and image classification tasks. Our source code is available at https://***/HotanLee/DeFT.

关键词：

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：