检索结果-内蒙古大学图书馆

SSRN 2025年

作者： Li, Botao Yang, Huguang Xia, Chenglong Zheng, Han Wulamu, Aziguli Zhang, Taohong Beijing100083 China Department of Guangxi Zhuang Autonomous Region Key Laboratory of AI and Information Processing [Hechi University Guangxi546300 China Beijing Key Laboratory of Knowledge Engineering for Materials Science Beijing100083 China

In recent years, models based on DETR (Detection Transformer) have made significant progress in the field of object detection. However, the encoder and decoder in DETR and its variants still face several critical challenges. Specifically, the high computational complexity and limited adaptability of the encoder restrict its performance across diverse datasets, while the query initialization process in the decoder leads to slower model *** address this issue, we propose a new framework—Adaptive DETR—that features dynamic adjustment of the number of sampling points and feature-guided adaptive feature *** main innovations include: First, we introduce a new attention update strategy that dynamically calculates weights based on the features of the output image, determining the frequency of features, thereby enhancing detection accuracy. Second, to address the issue of poor model adaptability caused by fixed sampling points in the deformable attention module of the DETR model, we implement dynamic adjustment of the number of sampling points, improving the model's generalization ability in complex scenes. Finally, we optimize the DETR decoder by performing attention calculations between queries responsible for bounding boxes and those responsible for semantic information during the query initialization phase, By effectively injecting semantic information while accelerating the model's convergence speed, the model's localization accuracy can also be *** experimental results demonstrate that Adaptive DETR achieves the best performance on the COCO、UAVDT、VisDrone and RSOD datasets, showcasing its efficiency and adaptability. © 2025, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Intelligent elevator system based on the Internet of Things: improving elevator safety and management efficiency

Intelligent elevator system based on the Internet of Things:...

引用

2024 International Conference on Smart Transportation and City engineering, STCE 2024

作者： Huang, Lingbo Chen, Yihong Zhao, Kun The Internet of Things Perception and Big Data Analysis Key Laboratory of Nanchong City China West Normal University Nanchong 637002 China School of Electronic Information Engineering China West Normal University Nanchong 637002 China

ISBN: (纸本)9781510690585

The number of elevators in China's urbanization process has increased significantly, yet they face safety problems such as aging and insufficient maintenance. This paper introduces an intelligent IoT elevator system, comprising a data acquisition terminal and a cloud platform, utilizing a hierarchical architecture and a variety of key technologies. The system can monitor elevator operations in real time, collect and analyze large amounts of data to predict failures, and provide maintenance plans. It also features real-time alarm, rescue management, and maintenance management functions. These improvements enhance rescue efficiency, reduce maintenance costs, ensure the safe operation of elevators, and improve the efficiency and transparency of safety management. © 2025 SPIE.

关键词： China's Urbanization elevator safety Failure prediction intelligent management Internet of Things elevator system

来源：评论

学校读者我要写书评

暂无评论

Differential-Trust-Mechanism Based Trade-off Method Between Privacy and Accuracy in Recommender Systems

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 5054-5068页

作者： Xu, Guangquan Feng, Shicheng Xi, Hao Yan, Qingyang Li, Wenshan Wang, Cong Wang, Wei Liu, Shaoying Tian, Zhihong Zheng, Xi Qingdao Huanghai University School of Big Data Qingdao China Tianjin University College of Intelligence and Computing Tianjin300350 China KLISS and School of Software Beijing100084 China Sichuan University School of Cyber Science and Engineering Chengdu610207 China Xi’an Jiaotong University School of Cyber Science and Engineering Xi’an710049 China East China Normal University Shanghai200062 China Hiroshima University School of Informatics and Data Science Higashihiroshima739-8511 Japan Guangzhou University Cyberspace Institute of Advanced Technology Guangdong Key Laboratory of Industrial Control System Security Huangpu Research School of Guangzhou University China Macquarie University School of Computing SydneyNSW2109 Australia

In the era where Web3.0 values data security and privacy, adopting groundbreaking methods to enhance privacy in recommender systems is crucial. Recommender systems need to balance privacy and accuracy, while also having the ability to overcome cold start problems. The Differential Trust Mechanism (DTM) introduced in this paper is such an approach. The DTM provides a unique use of Gaussian distributions in modeling trust relationships within data, offering a novel way to balance recommendation accuracy with user privacy. This mechanism innovatively applies differential privacy principles, using Gaussian noise addition to protect individual user data from inference attacks, while maintaining the integrity and utility of the overall dataset. Unlike traditional anonymization techniques that often compromise data utility or vulnerability to reverse engineering, DTM provides a robust solution by dynamically adjusting privacy levels based on the trustworthiness of data requests. By combining DTM with existing mainstream recommendation algorithms, the prediction accuracy of MAE and RMSE increases by at least 6.60% and 2.69%, respectively. This dual benefit positions DTM as a significant advancement in secure data processing, especially relevant for online businesses and platforms where personalized recommendations are crucial yet privacy concerns are paramount. © 2005-2012 IEEE.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Experimental and Modeling Study on Void Fraction Using Thermal Distribution Sensor in Horizontal Annular Flow

引用

IEEE Sensors Journal 2025年第10期25卷 17640-17649页

作者： Zhao, Ning Chen, Xiangyi Sun, Mingcong Song, Yajing Fang, Lide Li, Zhibin Hebei University College of Quality and Technical Supervision Hebei Baoding071000 China National and Local Joint Engineering Research Center of Metrology Instrument and System Hebei Baoding071002 China CCIC North China Metrology Company Ltd. Beijing100070 China Chengdu University of Information Technology School of Software Engineering Chengdu610225 China Sichuan University of Arts and Science Dazhou Key Laboratory of Government Data Security Sichuan Dazhou635000 China Xinjiang Technical Institute of Physics and Chemistry Chinese Academy of Sciences Urumqi830011 China

The void fraction is an important parameter to characterize the characteristics of annular flow, which is an important precondition for calculating the flow velocity, average density, pressure gradient, and analyzing the flow status. Based on the principle of convective heat transfer, the effects of the void fraction α and the liquid Froude number Frl on the heat transfer coefficient h of annular flow are analyzed. The thermal distribution sensor of constant power type is designed in this article. Air-water annular flow experiments have been conducted in a stainless-steel tubular test section having an inside diameter of 17.0 mm on the high-precision small-diameter two-phase flow experimental device of Hebei University. The 75 sets of temperature T at four angles (0°, 90°, 180°, and 270°) of pipe circumference and entrainment E under different flow conditions were collected. Utilizing the S. L. Smith correlation, the void fraction is calculated. By introducing dimensionless heat transfer coefficient h+ , the prediction correlation of void fraction α , which could acceptably handle the data, is proposed. laboratory results indicate that the relative error of 99% of the data is within the ±3% error band, the mean absolute percentage error (MAPE) of the correlation is 0.63%, and the root-mean-square error (RMSE) is 0.76%. © 2001-2012 IEEE.

关键词： Void fraction

来源：评论

学校读者我要写书评

暂无评论

Generating Targeted Universal Adversarial Perturbation against Automatic Speech Recognition via Phoneme Tailoring

Generating Targeted Universal Adversarial Perturbation again...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhang, Yujun Chen, Yanqu Wang, Jiakai Hu, Jin Tao, Renshuai Liu, Xianglong State Key Laboratory of Complex & Critical Software Environment Beihang University China School of Computer Science and Engineering Beihang University China College of Computer Science Beijing University of Technology China Zhongguancun Laboratory China School of Computer and Information Technology Beijing Jiaotong University China Institute of Data Space Hefei Comprehensive National Science Center China

ISBN: (纸本)9798350368741

There is a growing concern about adversarial attacks against automatic speech recognition (ASR) systems. Although research into targeted universal adversarial examples (AEs) has progressed, current methods are constrained by inefficient exploitation of audio features, demonstrating insufficient attack ability and robustness in the physical world. To solve this problem, we propose a phoneme-tailored attack (PTA) to improve the quality of the generated AEs. Specifically, to improve attack ability, we propose a Diverse Audio Composition Enrichment method, which enhances the utilization of audio features through phoneme-level slicing and recombination. To adapt AEs to complex environments, we propose a Natural Noise Pattern Guidance method to align AEs with natural noise patterns to improve their robustness. Experiments show that our method achieves an average accuracy of more than 72.34% and 98% with and without a norm constraint, and also demonstrates excellent performance in terms of generalization across datasets and resilience to MP3 compression. © 2025 IEEE.

关键词： Automatic speech recognition natural noise pattern phoneme-level targeted universal adversarial examples

来源：评论

学校读者我要写书评

暂无评论

Dual-Network Cross-Learning for Metabolite-Disease Association Prediction

IEEE Transactions on Computational Biology and Bioinformatic...

引用

IEEE Transactions on Computational Biology and Bioinformatics 2025年第2期22卷 545-556页

作者： Yanxin Chen Qiao Ning Yitong Zhang Hui Li Shikai Guo Department of Information Science and Technology Dalian Maritime University Dalian China School of Artificial Intelligence and Computer Science Jiangnan University Wuxi China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China Dalian Key Laboratory of Artificial Intelligence Dalian China

In recent years, increasing evidence has demonstrated a close association between metabolites and various complex human diseases, providing valuable insights for disease diagnosis, treatment, and prevention. Although deep learning-based approaches have achieved certain success in predicting metabolic disease associations, challenges remain in enriching graph information and effectively integrating metabolic and disease features. To address these issues, this paper proposes a model named DCMDA, which extracts deep features of both metabolites and diseases using Dual-network Cross-learning for Metabolite- Disease Association prediction. DCMDA consists of three parts. The data processing module integrates similarity networks with association networks to construct a heterogeneous network. The feature extraction module extracts features from the metabolite-disease association network based on the non-negative matrix factorization method and from the heterogeneous network using graph autoencoder techniques. The feature fusion module combines the association matrix feature with the heterogeneous network feature through a Cross-Attention mechanism, thereby obtaining deep representations of metabolites and diseases. These features are then used to train the model to predict association scores between metabolites and diseases. Experimental results demonstrate that in 5-fold cross-validation, DCMDA achieves an area under the receiver operating characteristic curve (AUC) of 97.8% and an area under the precision-recall curve (AUPR) of 97.9%, outperforming state-of-the-art prediction methods.

关键词： Diseases Feature extraction data mining Semantics Deep learning Kernel Information entropy Prediction algorithms Noise Nearest neighbor methods

来源：评论

学校读者我要写书评

暂无评论

FIRE: combining multi-stage filtering with taint analysis for scalable recurring vulnerability detection 24

FIRE: combining multi-stage filtering with taint analysis fo...

引用

Proceedings of the 33rd USENIX Conference on Security Symposium

作者： Siyue Feng Yueming Wu Wenjie Xue Sikui Pan Deqing Zou Yang Liu Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security Cluster and Grid Computing Lab and School of Cyber Science and Engineering Huazhong University of Science and Technology China Nanyang Technological University Singapore National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security Cluster and Grid Computing Lab and School of Cyber Science and Engineering Huazhong University of Science and Technology China and Jinyinhu Laboratory China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security Cluster and Grid Computing Lab and School of Computer Science and Technology Huazhong University of Science and Technology China

ISBN: (纸本)9781939133441

With the continuous development of software open-sourcing, the reuse of open-source software has led to a significant increase in the occurrence of recurring vulnerabilities. These vulnerabilities often arise through the practice of copying and pasting existing vulnerabilities. Many methods have been proposed for detecting recurring vulnerabilities, but they often struggle to ensure both high efficiency and consideration of semantic information about vulnerabilities and patches. In this paper, we introduce FIRE, a scalable method for large-scale recurring vulnerability detection. It utilizes multi-stage filtering and differential taint paths to achieve precise clone vulnerability scanning at an extensive scale. In our evaluation across ten open-source software projects, FIRE demonstrates a precision of 90.0% in detecting 298 recurring vulnerabilities out of 385 ground truth instance. This surpasses the performance of existing advanced recurring vulnerability detection tools, detecting 31.4% more vulnerabilities than VUDDY and 47.0% more than MOVERY. When detecting vulnerabilities in large-scale software, FIRE outperforms MOVERY by saving about twice the time, enabling the scanning of recurring vulnerabilities on an ultra-large scale.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Forecasting of exchange rate time series based on event-aware transformer mode

引用

Soft Computing 2025年第6期29卷 3035-3045页

作者： Zhang, Siyi Che, Tong Zhu, Zhiliang Luo, Guoli Feng, Ping Virtual Reality and Interactive Techniques Institute East China Jiaotong University Nanchang330013 China Department of Engineering Mathematics University of Bristol Northern Ireland BristolBS8 1TH United Kingdom Guizhou Key Laboratory of Big Data Statistical Analysis Guizhou University of Finance and Economics Guiyang550025 China

Accurately forecasting exchange rate time series is crucial for effective risk management. The longer the forecast time window and the higher the frequency, the more valuable it is for managers to make timely decisions. In light of the task characteristics of exchange rate forecasting, this paper proposes an improved transformer-based model for addressing long sequence time series forecasting problems. Specifically, we introduce a position embedding method for events, which integrates the traditional coding context vector to perform joint location representation learning. Additionally, we explore a periodic enhancement method of features to jointly enhance the transformer-like model architecture’s ability to adaptively learn the long-term and hidden correlations of long sequence time series data. Extensive experimental results on the prediction of four exchange rate data for pairs of opening, high, low, and closing prices at a frequency of 5 min show that our model outperforms the prediction of the baseline method. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Risk management

来源：评论

学校读者我要写书评

暂无评论

Explainable Application Intent for Zero-Touch Networking: An Incorporation of Hypergraph and Transformer

引用

IEEE Transactions on Communications 2025年

作者： Wu, Bing Zou, Sai Liwang, Minghui Ni, Wei Wang, Xianbin Guizhou University College of Big Data and Information Engineering China National Key Laboratory of Autonomous Intelligent Unmanned Systems Department of Control Science and Engineering China Tongji University Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education Shanghai China Data61 CSIRO Australia Department of Electrical and Computer Engineering Western University Canada

The autonomous interpretation of application intent (APPI) represents the primary step towards achieving closed-loop autonomy in zero-touch networking (ZTN) and also a prerequisite for intent-based networking (IBN). However, understanding APPIs and invoking the corresponding network resources require network professionals with extensive technical expertise to customize network service requests (NSRs), which presents significant challenges for the large-scale deployment of ZTN. This paper investigates an interesting problem of autonomous interpretation of APPIs for ZTN, where a novel mechanism integrating hypergraph and transformer with completeness assurance (HyperTrans-CA) is proposed. In particular, we first involve the Bayesian theory to model APPIs interpretability as maximizing the correct transition probability, where hypergraph is used to describe the complex relationship between application characteristics (e.g., scenario function, and performance) and NSRs, including network devices, virtual network functions (VNFs), and resources. Then, the hypergraph is integrated into the encoder, decoder, and attention mechanisms of Transformer, and a completeness assurance mechanism is designed to improve the prediction accuracy. The convergence of HyperTrans-CA and the corresponding convergence speed of the hypergraph-boosted Transformer in the graph search process are also analyzed. Comprehensive simulations and empirical measurements regarding industrial internet demonstrate that HyperTrans-CA can effectively explain/understand APPIs. Compared to the state-of-the-art Transformer and ChatGPT3.5 models, HyperTrans-CA improves the prediction accuracy of APPIs mapped to VNFs by 23% and 46%, respectively, while raising the prediction accuracy of VNF locations by 8.6 and 17.3 times. © 2025 IEEE.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

An enhanced sparse subset selection model based on adaptive projection distance

引用

Evolutionary Intelligence 2025年第3期18卷 1-15页

作者： Feng, Feng Gao, Erwei Zhi, Xiaobin Zhao, Yichuan School of Science and Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’an University of Posts and Telecommunications Xi’an 710121 China School of Communication and Information Engineering Xi’an University of Posts and Telecommunications Xi’an 710121 China School of Science and Research Center for Intelligent Systems and Data Science Xi’an University of Posts and Telecommunications Xi’an 710121 China Department of Mathematics and Statistics Georgia State University Atlanta 30303 GA United States

Subset selection focuses on identifying representative samples from a large dataset to produce a data subset that can represent the main features of the original data and also reduce the data size in an effective way. Sparse representation theory puts emphasis on enhancing the data sparsity, while subset selection aims to reduce the data size. Sparse subset selection is an important branch of subset selection that incorporates sparse representation theory into the exploration of subset selection. Sparse modeling representative selection model has demonstrated outstanding performance in data classification and video summarization. Nonetheless, it suffers from the issue of poor typicality of the selected representatives. Although some recent works have addressed this problem to some extent by introducing the concept of clustering coding terms, most of the clustering coding terms constructed by these existing methods are implicit, and the model structure is complicated, inefficient, and difficult to be understood. To overcome these difficulties, we propose an adaptive projection distance-based sparse subset selection model. This model constructs a clustering coding item by adaptively calculating the projection distance between data. It can not only eliminate redundant and noisy features in the original data but also ensure that the selected representatives are more typical. To solve the proposed model, an efficient algorithm is developed by virtue of the alternating direction method of multipliers. Extensive experiments with comparative analysis demonstrate that the proposed model outperforms several state-of-the-art models in various tasks including subset selection, cluster analysis, classification, and face image representative selection. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Adaptive projection distance Classification Cluster analysis Sparse representation Subset selection

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：