检索结果-内蒙古大学图书馆

A Review of Field Text Analysis

学校读者我要写书评

暂无评论

A Review of Field Text Analysis

Telecommunications, Optics and Computer Science (TOCS), IEEE Conference on

作者： Zhuolun Li Fei Kang Pu Yu Hui Shu School of Software Zhengzhou University Zhengzhou China State Key Laboratory of Mathematical Engineering and Advanced Computing MEAC Zhengzhou China

ISBN: (纸本)9781665424998

Field text analysis is the process of using natural language processing technology to understand the Text and extract information from unstructured text data. In recent years, due to the increasing maturity of machine learning technology, higher requirements have been put forward for field text analysis. This review first introduces the process of Text preprocessing and the development of text representation. Secondly, it summarizes the four typical techniques of text analysis, including named entity recognition, relation extraction, extractive text summarization, and text classification. Finally, for each typical technology, it introduces the commonly used methods and part of the researcher’s exploration of this technology.

关键词： Computer science Text analysis Text recognition Conferences Text categorization Machine learning Optics

A quantum-classical hybrid algorithm with Ising model for the learning with errors problem

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zheng, Muxi Zeng, Jinfeng Yang, Wentao Chang, Pei-Jie Yan, Bao Zhang, Haoran Wang, Min Wei, Shijie Long, Gui-Lu Beijing Academy of Quantum Information Sciences Beijing100193 China State Key Laboratory of Low-Dimensional Quantum Physics Department of Physics Tsinghua University Beijing100084 China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou450001 China Division of Physics and Applied Physics School of Physical and Mathematical Sciences Nanyang Technological University Singapore Singapore Frontier Science Center for Quantum Information Beijing100084 China Beijing National Research Center for Information Science and Technology Beijing100084 China

The Learning-With-Errors (LWE) problem is a crucial computational challenge with significant implications for post-quantum cryptography and computational learning theory. Here we propose a quantum-classical hybrid algorithm with Ising model (HAWI) to address the LWE problem. Our approach involves transforming the LWE problem into the Shortest Vector Problem (SVP), using variable qubits to encode lattice vectors into an Ising Hamiltonian. We then identify the low-energy levels of the Hamiltonian to extract the solution, making it suitable for implementation on current noisy intermediate-scale quantum (NISQ) devices. We prove that the number of qubits required is less than m(3m -1)/2, where m is the number of samples in the algorithm. Our algorithm is heuristic, and its time complexity depends on the specific quantum algorithm employed to find the Hamiltonian's low-energy levels. If the Quantum Approximate Optimization Algorithm (QAOA) is used to solve the Ising Hamiltonian problem, and the number of iterations satisfies y © 2024, CC BY-NC-ND.

关键词： Qubits

Real-Time Source-Independent Quantum Random Number Generator Based on a Cloud Superconducting Quantum Computer

学校读者我要写书评

暂无评论

Research Square

Research Square 2021年

作者： Li, Yuanhao Fei, Yangyang Wang, Weilong Meng, Xiangdong Wang, Hong Duan, Qianheng Ma, Zhi State Key Laboratory of Mathematical Engineering and Advanced Computing Henan Zhengzhou450001 China Henan Key Laboratory of Network Cryptography Technology Henan Zhengzhou450001 China

Quantum random number generator (QRNG) relies on the intrinsic randomness of quantum mechanics to produce true random numbers which are important in information processing tasks. Due to the presence of the superposition state, quantum computer can be used as a true random number generator. However, in practice, the implementation of quantum computer is subject to various noise sources which affect the randomness of the generated random numbers. To solve this problem, we propose a source-independent QRNG (SI-QRNG) scheme based on quantum computer which is motivated by the SI-QRNG scheme in quantum optics. The scheme can provide certified randomness by estimating the preparation error of superposition states in real time even when the source is untrusted, under the assumption that the measurement operation is trusted. Our analysis takes into account the readout error of quantum state and further gives the final extracted number of random bits. And the estimation method of preparation error of superposition state in randomness source. We also provide a parameter optimization method to increase the generation rate of random bits. In addition, by utilizing the cloud superconducting quantum computer of IBM, we experimentally demonstrate the practicality of our SI-QRNG scheme and achieve the generation of true random numbers. © 2021, CC BY.

关键词： Errors

A differential privacy preserving algorithm for greedy decision tree

学校读者我要写书评

暂无评论

A differential privacy preserving algorithm for greedy decis...

Big Data & Artificial Intelligence & Software engineering (ICBASE), International Conference on

作者： Shudan Yang Nan Li Daozhu Sun Qiming Du Wenfu Liu Strategic Support Force Information Engineering University State Key Laboratory of Mathematical Engineering and Advanced Computing College of Cyberspace Security Zhengzhou China

ISBN: (纸本)9781665427104

In recent years, the contradiction between data application and privacy protection has become increasingly prominent, and differential privacy is considered an effective technology to resolve this contradiction. Therefore, we propose a differential privacy protection algorithm for greedy decision trees. Firstly, the privacy budget is allocated according to the structural characteristics of the tree. Secondly, the algorithm meets ϵ-differential privacy by adding Laplacian perturbation to the leaf nodes and exponential mechanism perturbation to the intermediate nodes. Finally, The integration strategy is used to construct random forest to avoid the instability of single tree. Experimental results show that this algorithm achieves a better balance between data availability and invisibility compared with other algorithms.

关键词： Privacy Differential privacy Laplace equations Perturbation methods Stability analysis Classification algorithms Resource management

Function Projective Synchronization of Chaotic PMSMs with Certain and Uncertain System Parameters

学校读者我要写书评

暂无评论

Function Projective Synchronization of Chaotic PMSMs with Ce...

Chinese Automation Congress (CAC)

作者： Mufeng Wang Ke Liu Yangyang Geng Xin Che Jingpei Wang College of Control Science&Engineering Zhejiang University Hangzhou China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

ISBN: (纸本)9781665426480

In recent years, driven by huge engineering demands, industrial Cyber-Physical System (iCPS) has developed rapidly. As an important energy conversion device in iCPS, stable operation of permanent magnet synchronous motor (PMSM) is very important to ensure the availability of the whole iCPS. In this paper, based on Lyapunov stability theory, the function projective synchronization (FPS) of chaotic PMSM systems with certain and uncertain system parameters are investigated, respectively. The proposed control method is proved by using explicit numerical theory and then applied in numerical simulations. From the results of simulations, effectiveness of the control method is obviously. Our study can solve the synchronization and motors coordination problem in industry manufacture.

关键词： Uncertain systems Production Cyber-physical systems Numerical simulation Synchronous motors Permanent magnet motors Motor coordination

Progressive Multi-Stage Feature Mix for Person Re-Identification

学校读者我要写书评

暂无评论

Progressive Multi-Stage Feature Mix for Person Re-Identifica...

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

作者： Yan Zhang Binyu He Li Sun Qingli Li Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai China State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi China

Image features from a small local region often give strong evidence in person re-identification task. However, CNN suffers from paying too much attention on the most salient local areas, thus ignoring other discriminative clues, e.g., hair, shoes or logos on clothes. In this work, we propose a Progressive Multi-stage feature Mix network (PMM), which enables the model to find out the more precise and diverse features in a progressive manner. Specifically, (i) to enforce the model to look for different clues in the image, we adopt a multi-stage classifier and expect that the model is able to focus on a complementary region in each stage. (ii) we propose an Attentive feature Hard-Mix (A-Hard-Mix) to replace the salient feature blocks by the negative example in the current batch, whose label is different from the current sample. (iii) extensive experiments have been carried out on reID datasets such as the Market-1501, DukeMTMC-reID and CUHK03, showing that the proposed method can boost the re-identification performance significantly. Source code¹ has been released.

关键词： Training Hair Conferences Footwear Signal processing Acoustics Task analysis

ARIW-Framework: Adaptive Robust Iterative Watermarking Framework

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wu, Shaowu Lu, Wei Zeng, Liting Luo, Xiangyang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

With the rapid rise of large models, copyright protection for generated image content has become a critical security challenge. Although deep learning watermarking techniques offer an effective solution for digital image copyright protection, they still face limitations in terms of visual quality, robustness and generalization. To address these issues, this paper proposes an adaptive robust iterative watermarking framework (ARIW-Framework) that achieves high-quality watermarked images while maintaining exceptional robustness and generalization performance. Specifically, we introduce an iterative approach to optimize the encoder for generating robust residuals. The encoder incorporates noise layers and a decoder to compute robustness weights for residuals under various noise attacks. By employing a parallel optimization strategy, the framework enhances robustness against multiple types of noise attacks. Furthermore, we leverage image gradients to determine the embedding strength at each pixel location, significantly improving the visual quality of the watermarked images. Extensive experiments demonstrate that the proposed method achieves superior visual quality while exhibiting remarkable robustness and generalization against noise attacks. Copyright © 2025, The Authors. All rights reserved.

关键词： Image watermarking

Diffusion-based Adversarial Identity Manipulation for Facial Privacy Protection

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Liqin Lu, Wei Hu, Qianyue Luo, Xiangyang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

The success of face recognition (FR) systems has led to serious privacy concerns due to potential unauthorized surveillance and user tracking on social networks. Existing methods for enhancing privacy fail to generate natural face images that can protect facial privacy. In this paper, we propose diffusion-based adversarial identity manipulation (DiffAIM) to generate natural and highly transferable adversarial faces against malicious FR systems. To be specific, we manipulate facial identity within the low-dimensional latent space of a diffusion model. This involves iteratively injecting gradient-based adversarial identity guidance during the reverse diffusion process, progressively steering the generation toward the desired adversarial faces. The guidance is optimized for identity convergence towards a target while promoting semantic divergence from the source, facilitating effective impersonation while maintaining visual naturalness. We further incorporate structure-preserving regularization to preserve facial structure consistency during manipulation. Extensive experiments on both face verification and identification tasks demonstrate that compared with the state-of-the-art, DiffAIM achieves stronger black-box attack transferability while maintaining superior visual quality. We also demonstrate the effectiveness of the proposed approach for commercial FR APIs, including Face++ and Aliyun. Copyright © 2025, The Authors. All rights reserved.

关键词： Computer forensics

NOMANet: A Graph Neural Network Enabled Power Allocation Scheme for NOMA

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Hou, Yipu Lu, Yang Chen, Wei Ai, Bo Niyato, Dusit Ding, Zhiguo State Key Laboratory of Advanced Rail Autonomous Operation China School of Computer Science and Technology Beijing Jiaotong University Beijing100044 China School of Electronics and Information Engineering Beijing Jiaotong University Beijing100044 China College of Computing and Data Science Nanyang Technological University 639798 Singapore Department of Electrical Engineering and Computer Science Khalifa University Abu Dhabi127788 United Arab Emirates

This paper proposes a graph neural network (GNN) enabled power allocation scheme for non-orthogonal multiple access (NOMA) networks. In particular, a downlink scenario with one base station serving multiple users over several subchannels is considered, where the number of subchannels is less than the number of users, and thus, some users have to share a subchannel via NOMA. Our goal is to maximize the system energy efficiency subject to the rate requirement of each user and the overall budget. We propose a deep learning based approach termed NOMA net (NOMANet) to address the considered problem. Particularly, NOMANet is GNN-based, which maps channel state information to the desired power allocation scheme for all subchannels. The multi-head attention and the residual/dense connection are adopted to enhance the feature extraction. The output of NOMANet is guaranteed to be feasible via the customized activation function and the penalty method. Numerical results show that NOMANet trained unsupervised achieves performance close to that of the successive convex approximation method but with a faster inference speed by about 700 times. Besides, NOMANet is featured by its scalability to both users and subchannels. © 2025, CC BY.

关键词： Channel state information