检索结果-内蒙古大学图书馆

A numerical magnitude aware multi-channel hierarchical encoding network for math word problem solving

Neural Computing and Applications 2025年第3期37卷 1651-1672页

作者： Xu, Junjie Chen, Yuzhong Xiao, Lingsheng Liao, Hongmiao Zhong, Jiayuan Dong, Chen College of Computer and Data Science Fuzhou University Fujian Province Fuzhou350108 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fujian Province Fuzhou350108 China

Math word problem (MWP) represents a critical research area within reading comprehension, where accurate comprehension of math problem text is crucial for generating math expressions. However, current approaches still grapple with unresolved challenges in grasping the sensitivity of math problem text and delineating distinct roles across various clause types, and enhancing numerical representation. To address these challenges, this paper proposes a Numerical Magnitude Aware Multi-Channel Hierarchical Encoding Network (NMA-MHEA) for math expression generation. Firstly, NMA-MHEA implements a multi-channel hierarchical context encoding module to learn context representations at three different channels: intra-clause channel, inter-clause channel, and context-question interaction channel. NMA-MHEA constructs hierarchical constituent-dependency graphs for different levels of sentences and employs a Hierarchical Graph Attention Neural Network (HGAT) to learn syntactic and semantic information within these graphs at the intra-clause and inter-clause channels. NMA-MHEA then refines context clauses using question information at the context-question interaction channel. Secondly, NMA-MHEA designs a number encoding module to enhance the relative magnitude information among numerical values and type information of numerical values. Experimental results on two public benchmark datasets demonstrate that NMA-MHEA outperforms other state-of-the-art models. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Research on Spares Optimization Method of the Complex Electronic Information System Based on Monte Carlo Simulation

Research on Spares Optimization Method of the Complex Electr...

引用

2024 International Conference on Mechatronics and Intelligent Control, ICMIC 2024

作者： Lu, Yanchun Yang, Hongqi Lei, Ting Pan, Yong CEPREI Guangzhou510610 China Key Laboratory of Industrial Equipment Quality Big Data MIIT Guangzhou510610 China Guangdong Provincial Engineering Technology Research Center for Quality Big Data of High-end Equipment Guangzhou510610 China

ISBN: (数字)9781510686847

ISBN: (纸本)9781510686830

In order to solve the problems such as high maintenance cost and difficult spare parts optimization of the complex electronic information system, considering advantages of the generalized stochastic Petri Net (GSPN) in characterization and analysis of dynamic change process of complex system, the process and method of spare parts optimization based on Monte Carlo simulation are studied to achieve the best balance between the rate of mission success and the cost of maintenance. © 2025 SPIE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Liquid metal assistant self-propagating high-temperature synthesis of S-containing high-entropy MAX-phase materials

引用

材料科学技术（英文版） 2025年第6期209卷 1-8页

作者： Donglong Bai Qiang Wang Bin Deng Yang Li Ao Huang Zitong Cheng Yun Zhao Jing Li Wei Yao Jianguang Xu School of Materials and Energy Shanghai Key Laboratory of Engineering Materials Application and EvaluationShanghai Polytechnic UniversityShanghai 201209China Shanghai Thermophysical Properties Big Data Professional Technical Service Platform Shanghai Engineering Research Center of Advanced Thermal Functional MaterialsShanghai 201209China School of Materials Science and Engineering Yancheng Institute of TechnologyYancheng 224000China School of Materials and Energy Shanghai Key Laboratory of Engineering Materials Application and EvaluationShanghai Polytechnic UniversityShanghai 201209China

Due to their high-entropy effects,the high-entropy(HE)MAX-phase materials improve the comprehen-sive performance of MAX phases,opening up more possibilities for practical engineering ***,it is still challenging to obtain S-containing high-entropy MAX phases because of the high volatilization behavior of sulfur,suffering from issues such as high reaction temperature and long re-action time of traditional synthesis *** paper proposes a novel process named as liquid metal assistant self-propagating high-temperature synthesis(LMA-SHS)for efficient synthesis of high-purity S-containing high-entropy MAX-phase ***-melting-point metal(Sn or In)has been introduced into the raw mixture and melted into a liquid phase during the early stage of the SHS *** serv-ing as a"binder"between transition metal atoms of the M-site due to the negative mixing enthalpy,this liquid phase can accelerate mass and heat transfer during the SHS process,ensuring a uniform solid solution of each element and realizing the synthesis of high-purity(TiNbVZr)2SC in an extremely short *** synthesis method for high-entropy MAX-phase materials developed in this study,i.e.,LMA-SHS,showing very short reaction time,low energy consumption,high yield,and low cost,has the promise to be a general energy-and resource-efficient route towards high-purity HE materials.

关键词： High-entropy S-containing MAX phases Liquid metal LMA-SHS

来源：评论

学校读者我要写书评

暂无评论

Robust primary quantization step estimation on resized and double JPEG compressed images

引用

Multimedia Tools and Applications 2025年第12期84卷 11097-11118页

作者： Zhang, Lei Chen, XuGuang Niu, YaKun Zuo, XianYu Wang, Huaqing School of Computer and Information Engineering Henan Kaifeng475004 China Henan Key Laboratory of Big Data Analysis and Processing Kaifeng Henan Henan Kaifeng475004 China National Internet Emergency Center Henan Zhengzhou450000 China

As one of the most important forensic tasks, reconstruction of the original information in tampered images is a key step for tampering detection and localization. Currently, a number of methods have been designed to estimate the primary quantization steps of double compressed JPEG images. However, the estimation in the presence of resizing operation remains a challenge. In this paper, we propose a robust primary quantization steps estimation method on resized and double JPEG compressed images. Specifically, the distribution of Discrete Cosine Transform (DCT) coefficients is firstly analyzed on the inverse resized image. Then, a maximum likelihood function together with a filtering strategy is designed to obtain the primary quantization step on Alternating Current (AC) bands. In addition, we find the prominent peak in the Discrete Fourier Transform (DFT) spectrum of the distribution of Direct Current (DC) coefficients is nonlinearly related to the step. Based on this observation, a mapping function derived from the geometric fitting is proposed to estimate the step on DC band. Experimental results demonstrate the proposed method provides superior estimation performance. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

LDMOS-Based Doherty Power Amplifier Design in 5G Mobile Micro Base Stations 5

LDMOS-Based Doherty Power Amplifier Design in 5G Mobile Micr...

引用

5th IEEE International Conference on Power, Electronics and Computer Applications, ICPECA 2025

作者： Gao, Mingming Wang, Xinyu Wang, Congying Zhang, Zhongxiang Shan, Shiquan Song, Yonghui College of Electronics and Information Engineering Liaoning Technicial University Liaoning Key Laboratory of Radio Frequency and Big Data for Intelligent Applications Liaoning Huludao China

ISBN: (纸本)9798331533694

A Doherty Power Amplifier (DPA) has been designed and optimized specifically for compact mobile base station deployment, operating within a frequency range of 3.3 GHz to 3.6 GHz. The amplifier utilizes the proprietary DS10-2092 LDMOS transistors developed by the company for both the carrier and peak power amplifiers. Physical test results indicate that the DPA achieves saturated output power meeting the specified requirements, with a maximum saturated drain efficiency of 41%. The drain efficiency remains stable between 26.3% and 30.7% over a 6 dB power back-off range, demonstrating its superior performance in high-efficiency and broadband applications. © 2025 IEEE.

关键词： Doherty amplifiers

来源：评论

学校读者我要写书评

暂无评论

Efficient Urban Tree Species Classification Via Multi-Representation Fusion of Mobile Laser Scanning data

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 11451-11468页

作者： Ma, Yinchi Luan, Peng Zhang, Yujie Liu, Bo Zhang, Lijie Hebei Agricultural University College of Information Science and Technology Baoding071001 China Hebei Key Laboratory of Agricultural Big Data Baoding071001 China Hebei Agricultural University College of Mechatronical and Electrical Engineering Baoding071000 China

Urban tree species identification is crucial for forest management and ecosystem assessment. Mobile Laser Scanning (MLS) provides significant advantages for this task through its flexibility in navigating complex urban environments with spatial constraints. However, MLS-based classification faces challenges such as intricate canopy structures, incomplete point clouds from urban occlusions, and intra-species variations. This study presents Tree Morphology Multi-Representation Fusion Network (TM2F), integrating 3D point cloud data with 2D projections for enhanced tree species classification. The framework employs a backpack-mounted MLS system to capture high-quality point cloud data. The core architecture features an Adaptive Hierarchical Sampling (AHS) module extracting multi-scale geometric features, followed by a Cross-View Fusion (CVF) module that implements stage- wise fusion of 3D structural information with 2D representations. This fusion strategy not only leverages established 2D feature extraction pipelines, but also addresses sparsity issues in point cloud projections. The method was validated on a diverse dataset of eight urban tree species (seven broadleaf and one coniferous species). Quantitative assessment yielded 98.57% F1-score and 98.77% Overall Accuracy with moderate computational resources (2.25M parameters, 1.11G FLOPs), demonstrating significant improvements over existing methods. The proposed workflow achieves a balance between classification accuracy and processing efficiency, making it suitable for large-scale urban tree inventory applications. © 2008-2012 IEEE.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Enhancing Extractive Question Answering in Multiparty Dialogues with Logical Inference Memory Network 31

Enhancing Extractive Question Answering in Multiparty Dialog...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Zhou, Shu Zhao, Rui Zhou, Zhengda Yi, Haohan Zheng, Xuhui Wang, Hao Nanjing University China Key Laboratory of Data Engineering and Knowledge Services in Jiangsu Provincial Universities Nanjing University China University of Technology Sydney Australia

ISBN: (纸本)9798891761964

Multiparty dialogue question answering (QA) within machine reading comprehension (MRC) presents significant challenges due to the complex interplay of information across multiple speakers and the need for advanced logical reasoning. While existing models often focus on separating dialogue information based on speakers and utterances, they rarely address the crucial aspect of logical inference, leading to suboptimal performance in understanding and answering questions. To bridge this gap, we introduce the Logical Inference Memory Network (LIMN), a novel architecture designed for extractive QA in multiparty dialogues. LIMN incorporates a unique inference module pretrained on plain text QA datasets (like SQuAD 2.0), enabling it to transfer robust logical reasoning abilities to the dialogue domain. This module generates representations that are specifically attuned to logical inference, which are then integrated into the dialogue context. Furthermore, we propose a key-utterance-based interaction mechanism that dynamically focuses on the most relevant utterances within the dialogue, enhancing the model's ability to pinpoint answers. To ensure robust performance, LIMN employs a multitask learning strategy that jointly optimizes for answer extraction, answerability prediction, key-utterance identification, and masked speaker prediction. Extensive experiments on the Molweni and FriendsQA benchmarks, encompassing 25,000 and 10,000 questions respectively, demonstrate that LIMN achieves state-of-the-art results, affirming the effectiveness of incorporating logical inference in multiparty dialogue QA. © 2025 Association for Computational Linguistics.

关键词： Memory architecture

来源：评论

学校读者我要写书评

暂无评论

Source Characteristics and Induced Hazards of the 2025 M6.8 Dingri Earthquake,Xizang,China,Revealed by Imaging Geodesy

引用

Journal of Earth Science 2025年第2期36卷 847-851页

作者： Chen Yu Zhenhong Li Xiaoning Hu Chuang Song Suju Li Haihui Liu Jie Li Bingquan Han Zhenjiang Liu Ming Liu Shuang Zhu Xiaoye Hao Zhiyuan Li Jianbing Peng College of Geological Engineering and Geomatics Chang'an UniversityXi'an 710054China Key Laboratory of Loess Xi'an 710054China Key Laboratory of Western China's Mineral Resources and Geological Engineering Ministry of EducationXi'an 710054China Big Data Center for Geosciences and Satellites Chang'an UniversityXi'an 710054China National Disaster Reduction Center of China Beijing 100124China

0 *** to the China Earthquake Networks Center,an M6.8 earthquake struck Dingri County,Xizang Autonomous Region,China,on 7 January 2025 at 9:05 *** *** epicenter is located at 28.5°N,87.45°E,with a depth of~1... 详细信息

关键词： source characteristics M earthquake Xizang imaging geodesy induced hazards Dingri China

来源：评论

学校读者我要写书评

暂无评论

Fake Face Detection Based on Fusion of Spatial Texture and High-Frequency Noise

引用

Chinese Journal of Electronics 2025年第1期34卷 212-221页

作者： Dengyong Zhang Feifan Qi Jiahao Chen Jiaxin Chen Rongrong Gong Yuehong Tian Lebing Zhang Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation School of Computer and Communication Engineering Changsha University of Science and Technology School of Computer and Communication Engineering Changsha University of Science and Technology Changsha Social Work College Changkuangao Beijing Technology Co. Ltd. School of Computer and Artificial Intelligence Huaihua University

The rapid development of the Internet has led to the widespread dissemination of manipulated facial images, significantly impacting people's daily lives. With the continuous advancement of Deepfake technology, the generated counterfeit facial images have become increasingly challenging to distinguish. There is an urgent need for a more robust and convincing detection method. Current detection methods mainly operate in the spatial domain and transform the spatial domain into other domains for analysis. With the emergence of transformers, some researchers have also combined traditional convolutional networks with transformers for detection. This paper explores the artifacts left by Deepfakes in various domains and, based on this exploration, proposes a detection method that utilizes the steganalysis rich model to extract high-frequency noise to complement spatial features. We have designed two main modules to fully leverage the interaction between these two aspects based on traditional convolutional neural networks. The first is the multi-scale mixed feature attention module, which introduces artifacts from high-frequency noise into spatial textures, thereby enhancing the model's learning of spatial texture features. The second is the multi-scale channel attention module, which reduces the impact of background noise by weighting the features. Our proposed method was experimentally evaluated on mainstream datasets, and a significant amount of experimental results demonstrate the effectiveness of our approach in detecting Deepfake forged faces, outperforming the majority of existing methods.

关键词： Deepfakes Adaptation models Attention mechanisms Noise Transforms Transformers Feature extraction Internet Convolutional neural networks Faces

来源：评论

学校读者我要写书评

暂无评论

MS-SAM: Multi-scale SAM Based on Dynamic Weighted Agent Attention 31st

MS-SAM: Multi-scale SAM Based on Dynamic Weighted Agent Att...

引用

31st International Conference on Multimedia Modeling, MMM 2025

作者： Yang, Enhui Zhang, Zhibin Engineering Research Center of Ecological Big Data Ministry of Education Key Laboratory of Wireless Networks and Mobile Computing Inner Mongolia University Hohhot010021 China

ISBN: (纸本)9789819620630

The Segment Anything Model (SAM), introduced in 2023, has made significant advancements in the field of computer vision. However, SAM faces two major challenges: limitations related to single-scale processing and high computational demands for large-scale data handling, which restrict its widespread adoption in practical applications. Therefore, we propose MS-SAM to achieve better segmentation performance at a lower cost. We introduce a multi-scale image encoder to handle images of varying scales and complexities. Additionally, we propose a dynamic weighted agent attention, which can flexibly and efficiently adjust attention distribution while reducing computational costs. We train MS-SAM on a 1/20 subset of the SA-1B dataset for instance segmentation using points or boxes as prompts. The results show that we maintain the accuracy with the SAM method while reducing the parameters by about 6 times. We give sufficient experimental results to demonstrate its effectiveness. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

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：