检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhang, Jin Liu, Ze Lian, Defu Chen, Enhong School of Artificial Intelligence and Data Science University of Science and Technology of China China School of Computer Science and Technology University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence Anhui Hefei China

Two-stage recommender systems play a crucial role in efficiently identifying relevant items and personalizing recommendations from a vast array of options. This paper, based on an error decomposition framework, analyzes the generalization error for two-stage recommender systems with a tree structure, which consist of an efficient tree-based retriever and a more precise yet time-consuming ranker. We use the Rademacher complexity to establish the generalization upper bound for various tree-based retrievers using beam search, as well as for different ranker models under a shifted training distribution. Both theoretical insights and practical experiments on real-world datasets indicate that increasing the branches in tree-based retrievers and harmonizing distributions across stages can enhance the generalization performance of two-stage recommender systems. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Simple models are all you need: Ensembling stylometric, part-of-speech, and information-theoretic models for the ALTA 2024 Shared Task 22nd

Simple models are all you need: Ensembling stylometric, part...

引用

22nd Annual Workshop of the Australasian Language Technology Association, ALTA 2024

作者： Thomas, Joel Hoang, Gia Bao Mitchell, Lewis School of Computer and Mathematical Sciences Adelaide Data Science Centre The University of Adelaide SA5005 Australia

The ALTA 2024 shared task concerned automated detection of AI-generated text. Large language models (LLM) were used to generate hybrid documents, where individual sentences were authored by either humans or a state-of-the-art LLM. Rather than rely on similarly computationally expensive tools like transformer-based methods, we decided to approach this task using only an ensemble of lightweight "traditional" methods that could be trained on a standard desktop machine. Our approach used models based on word counts, stylometric features, readability metrics, part-of-speech tagging, and an information-theoretic entropy estimator to predict authorship. These models, combined with a simple weighting scheme, performed well on a held-out test set, achieving an accuracy of 0.855 and a kappa score of 0.695. Our results show that relatively simple, interpretable models can perform effectively at tasks like authorship prediction, even on short texts, which is important for democratisation of AI as well as future applications in edge computing. © 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

See Detail Say Clear: Towards Brain CT Report Generation via Pathological Clue-driven Representation Learning

See Detail Say Clear: Towards Brain CT Report Generation via...

引用

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

作者： Zheng, Chengxin Ji, Junzhong Shi, Yanzhao Zhang, Xiaodan Qu, Liangqiong College of Computer Science Beijing University of Technology Beijing China Department of Statistics and Actuarial Science School of Computing and Data Science The University of Hong Kong Hong Kong

ISBN: (纸本)9798891761681

Brain CT report generation is significant to aid physicians in diagnosing cranial diseases. Recent studies concentrate on handling the consistency between visual and textual pathological features to improve the coherence of report. However, there exist some challenges: 1) Redundant visual representing: Massive irrelevant areas in 3D scans distract models from representing salient visual contexts. 2) Shifted semantic representing: Limited medical corpus causes difficulties for models to transfer the learned textual representations to generative layers. This study introduces a Pathological Clue-driven Representation Learning (PCRL) model to build cross-modal representations based on pathological clues and naturally adapt them for accurate report generation. Specifically, we construct pathological clues from perspectives of segmented regions, pathological entities, and report themes, to fully grasp visual pathological patterns and learn cross-modal feature representations. To adapt the representations for the text generation task, we bridge the gap between representation learning and report generation by using a unified large language model (LLM) with task-tailored instructions. These crafted instructions enable the LLM to be flexibly fine-tuned across tasks and smoothly transfer the semantic representation for report generation. Experiments demonstrate that our method outperforms previous methods and achieves SoTA performance. Our code is available at https://***/ChaunceyJheng/PCRL-MRG. © 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

Automated heart disease prediction using improved explainable learning-based technique

引用

Neural Computing and Applications 2024年第26期36卷 16289-16318页

作者： Bizimana, Pierre Claver Zhang, Zuping Hounye, Alphonse Houssou Asim, Muhammad Hammad, Mohamed El-Latif, Ahmed A. Abd School of Computer Science and Engineering Central South University Changsha410083 China School of Mathematics and Statistics Central South University Changsha410008 China EIAS Data Science Lab College of Computer and Information Sciences and Center of Excellence in Quantum and Intelligent Computing Prince Sultan University Riyadh11586 Saudi Arabia School of Computer Science and Technology Guangdong University of Technology Guangzhou510006 China Department of Mathematics and Computer Science Faculty of Science Menoufia University Shebin El-Koom Egypt Information Technology Department Faculty of Computers and Information Menoufia University Shebin El-Koom Egypt

Heart disease (HD) stands as a major global health challenge, being a predominant cause of death and demanding intricate and costly detection methods. The widespread impact of heart failure, contributing to increased rates of morbidity and mortality, underscores the urgency for accurate and timely prediction and diagnosis. This is crucial for effective prevention, early detection, and treatment, thereby reducing the threat to individual health. However, the early and precise prediction of HD remains a significant challenge. The complexity of medical data poses a considerable challenge for healthcare professionals, who are required to interpret and utilize this information swiftly for effective intervention. Addressing this gap, our study introduces a novel Improved Explainable Learning-Based Technique (IELBT) for HD prediction. This technique harnesses a strategic combination of feature selection, Venn diagrams, data normalization methods, optimized parameters, and machine learning algorithms, specifically tailored for predicting HD. We evaluated the performance of our model using the Alizadeh Sani HD dataset, aiming to accurately detect the presence or absence of the condition. Our results demonstrate that the IELBT, employing a support vector machine with a robust scaling approach, optimal parameterization, and a data split ratio of 70:30, achieves an impressive accuracy rate of 96.00%. Beyond achieving high accuracy, the IELBT outperforms similar models in existing literature and provides significant interpretability and explanation, essential elements in the field of medical diagnosis. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

FSM: A Fine-grained Splitting and Merging Framework for Dual-balanced Graph Partition 50th

FSM: A Fine-grained Splitting and Merging Framework for Dual...

引用

50th International Conference on Very Large data Bases, VLDB 2024

作者： Liu, Chengjun Peng, Zhuo Zheng, Weiguo Zou, Lei School of Data Science Fudan University China Wangxuan Institute of Computer Technology Peking University China

Partitioning a large graph into smaller subgraphs by minimizing the number of cutting vertices and edges, namely cut size or replication factor, plays a crucial role in distributed graph processing tasks. However, many prior works have primarily focused on optimizing the cut size by considering only vertex balance or edge balance, leading to significant workload imbalance and consequently hindering the performance of downstream tasks. Therefore, in this paper, we address the dual-balanced graph partition problem that minimizes the cut size while simultaneously guaranteeing both vertex and edge balance. We propose a lightweight effective twophase framework, namely fine-grained splitting and merging (FSM), which decomposes the graph into more and smaller partitions and then merges them. FSM offers the flexibility of integrating with various state-of-the-art single-balanced techniques. We develop two efficient algorithms Fast Merging and Precise Merging to enable trade-offs between computational efficiency and partitioning quality. Experimental results on large real-world graphs demonstrate that FSM achieves state-of-the-art cut size while maintaining dual balance. The runtime for downstream tasks PageRank, connected component, and diameter estimation, can be reduced by a large proportion, up to 9.43%, 11.35%, and 17.94%, respectively. © 2024, VLDB Endowment. All rights reserved.

关键词： Merging

来源：评论

学校读者我要写书评

暂无评论

A Combination Model of Periodic and Non-periodic Events for Temporal Knowledge Graph Event Prediction

引用

Chinese Journal of Electronics 2025年第3期34卷 952-961页

作者： School of Computer Science and Information Security Guilin University of Electronic Technology Guilin 541004 China School of Data Science and Software Engineering Wuzhou University Wuzhou 543002 China

Temporal knowledge graph (TKG) reasoning aims to predict missing facts or future events at given timestamps and has attracted more and more attention in recent years. Existing TKG reasoning methods mainly focus on the interactions between entities and ignore the associations between events where the entities involve. In addition, the characteristics of different types of events have not been studied and exploited, which reduces the performance of event prediction. To address these problems, this paper proposes a combination model of periodic and non-periodic events (CM-PNP). Specifically, there are two basic components designed to process different types of events. The periodic component of CM-PNP learns the recurrent pattern of periodic events and encodes the temporal information in the manner of timespan to prevent the unseen timestamp issue. The non-periodic component of CM-PNP introduces extra information (e.g., entity attributes) to represent non-periodic events, and predicts this type of events according to the related historical events. A combination model of multiple sub-models that focus on encoding different parts of the event is used to improve the performance of single model. The periodic and non-periodic components are combined by a gate block. The experimental results on three real-world datasets demonstrate that CM-PNP outperforms the existing baselines.

关键词： Temporal knowledge graph Temporal knowledge graph reasoning Event prediction Embedding learning data mining

来源：评论

学校读者我要写书评

暂无评论

Secure Consumer-Centric Demand Response Management in Resilient Smart Grid as Industry 5.0 Application with Blockchain-Based Authentication

引用

IEEE Transactions on Consumer Electronics 2024年第1期70卷 1370-1379页

作者： Ayub, Muhammad Faizan Li, Xiong Mahmood, Khalid Shamshad, Salman Saleem, Muhammad Asad Omar, Marwan University of Electronic Science and Technology of China School of Computer Science and Engineering Sichuan Chengdu12599 China National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Douliu64002 Taiwan The University of Lahore Department of Software Engineering Lahore54590 Pakistan Illinois Institute of Technology Information Technology and Management ChicagoIL60616 United States

The development of the industrial Internet of Things and smart grid networks has emphasized the importance of secure smart grid communication for the future of electric power transmission. However, the current deployment of smart meters and wireless communication methods presents several security concerns that must be addressed to ensure sustainable and resilient smart grid networks for Industry 5.0, with a focus on consumer-centric technologies. In this context, we propose a privacy-focused authentication solution for secure consumer-centric demand response management in smart grid networks, incorporating consumer electronics. Our proposed protocol utilizes blockchain-based authentication to enhance resistance against potential attacks and ensure the integrity of demand response data. Additionally, we have incorporated a PUF to prevent physical attacks. We have conducted informal and formal security analyses to verify the effectiveness of our proposed protocol against various threats and to confirm the session key security. Our comparison study has demonstrated that our protocol provides superior security and added functionalities, with lower computation and communication costs compared to similar protocols. Furthermore, we have measured the computational time for implementing the blockchain component of our protocol while considering the impact of varying numbers of block additions and transactions per block. © 1975-2011 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

The Generalized Fixed Point Iteration Method for AVE

引用

Journal of Mathematical Research with Applications 2024年第6期44卷 837-849页

作者： Changfeng MA Jing KANG School of Data and Computer Science Xiamen Institute of Technology College of Mathematics and Informatics Fujian Normal University

In this paper, based on the previous published work by Ke et al.(2019) and Li et al.(2022), by using the matrix splitting technique, generalized fixed point iteration method(GFPI) is established to solve the absolute value equation(AVE). The proposed method not only includes SOR-like method, FPI method, MFPI method and so on, but also generates some special versions. Some convergence conditions of the proposed method with different iteration error norms are presented. Furthermore, methods corresponding to other splitting methods are studied in detail. The effectiveness and feasibility of the proposed method are confirmed by some numerical experiments.

关键词： absolute value equations fixed point iteration convergence

来源：评论

学校读者我要写书评

暂无评论

Research on Traceable Handwritten Signature Anti-Counterfeiting and Verification System 6

Research on Traceable Handwritten Signature Anti-Counterfeit...

引用

6th International Conference on Machine Learning and Intelligent Systems, MLIS 2024

作者： Ye, Jiahong Ye, Feiyue School of Data Science The Chinese University of HongKong Shenzhen China School of Computer Engineering Jiangsu University of technology China

ISBN: (纸本)9781643685533

Addressing the anti-counterfeiting and verification issues of handwritten signatures, a traceable offline handwritten signature anti-counterfeiting and verification system is proposed. The system consists of four parts: a front-end mobile terminal application system, a database storage system, a backend management system, and a portable dynamic encoding stamp device. The system can achieve traceability of signatures, thereby more effectively preventing counterfeit signatures. The front-end mobile terminal application system can generate a unique two-dimensional code based on the relevant information of the signature file and send it to the database system for storage, while also sending it to the portable dynamic encoding stamp device. The portable dynamic encoding stamp device can receive the dynamic two-dimensional code from the front-end mobile terminal application system and produce a two-dimensional code imprint. The database system can store information such as signature file details, corresponding QR codes, and signature photos, which can be used for traceability queries and verification. The proposed system utilizes the SHA algorithm to generate unique codes and can generate corresponding QR code prints on a portable dynamic encoding device. When signing, a QR code seal is affixed, and during signature verification, the QR code on the signature file can be compared with the information in the database to verify the authenticity of the signature. When needed, signature photos stored in the database can also be used for further verification through machine learning. Compared with traditional signature verification methods, this method has better effectiveness. © 2024 The Authors.

关键词： database systems

来源：评论

学校读者我要写书评

暂无评论

Using analytic hierarchy process to evaluate deep learning for infrared target recognition

引用

Multimedia Tools and Applications 2024年第38期83卷 86229-86245页

作者： Xu, Laixiang Cao, Bingxu Wei, Xinhong Li, Bei Su, Jingfeng Ning, Shiyuan Zhao, Junmin School of Computer and Data Science Henan University of Urban Construction Pingdingshan467036 China School of Information Engineering Luohe Vocational Technology College Henan University of Technology Luohe Institute of Technology Luohe462000 China School of Computer and Data Science Innovation Laboratory of Smart Traffic and Big Data Development of Hainan Province Pingdingshan467036 China School of Computer and Data Science Research Center of Smart City and Big Data Engineering of Henan Province Henan University of Urban Construction Pingdingshan467036 China Department of Software Information China Electronics Technology Group Corporation 36-th Research Institute Jiaxing314033 China School of Computer and Data Science Research Center of Smart City and Big Data Engineering of Henan Province Research Center of Intelligent Campus Application Engineering of Henan Province Innovation Laboratory of Smart Traffic and Big Data Development of Hainan Province Henan University of Urban Construction Pingdingshan467036 China

In order to promote the evaluation performance of deep learning infrared automatic target recognition (ATR) algorithms in the complex environment of air-to-air missile research, we proposed an analytic hierarchy process (AHP) evaluation system consisting of the target recognition ability, the generalization recognition ability, the anti-interference ability, the background suppression ability, and the cost metrics ability. According to detailed quantitative analysis and experimental results, we establish probability evaluation models and get their probability values. Compared with traditional evaluation systems, our proposed method implementation is showing high reliability. Similar superior performances are also achieved, such as quick, comprehensive, and scientific. Through the above research, the key technology of deep learning performance evaluation in automatic target recognition has been broken through, which provides some basis and guidance for the analysis of infrared imaging-guided weapon systems. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Infrared imaging

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：