本期目录

2023年 30卷 5期 刊出日期：2023-10-31



Special Topic : Digital Human

Joint global constraint and Fisher discrimination based multi-layer dictionary learning for image classification

彭宏 刘耀宗

中国邮电高校学报(英文), 2023, 30 (5). doi： 10.19682/j.cnki.1005-8885.2023.0010

摘要 ( 676 ) PDF (890 KB)( 266 )

参考文献 | 相关文章 | 计量指标

    A multi-layer dictionary learning algorithm that joints global constraints and Fisher discrimination (JGCFD-MDL) for image classification tasks was proposed. The algorithm reveals the manifold structure of the data by learning the global constraint dictionary and introduces the Fisher discriminative constraint dictionary to minimize the intra-class dispersion of samples and increase the inter-class dispersion. To further quantify the abstract features that characterize the data, a multi-layer dictionary learning framework is constructed to obtain high-level complex semantic structures and improve image classification performance. Finally, the algorithm is verified on the multi-label dataset of court costumes in the Ming Dynasty and Qing Dynasty, and better performance is obtained. Experiments show that compared with the local similarity algorithm, the average precision is improved by 3.34% . Compared with the single-layer dictionary learning algorithm, the one-error is improved by 1.00% , and the average precision is improved by 0.54% . Experiments also show that it has better performance on general datasets.

3D reconstruction algorithm for movable cultural relics based on salient region optimization

王文灏 赵海英

中国邮电高校学报(英文), 2023, 30 (5). doi： 10.19682/j.cnki.1005-8885.2023.0012

摘要 ( 410 ) PDF (9159 KB)( 139 )

参考文献 | 相关文章 | 计量指标

   How to protect cultural retics is of great significance to the transmission and dissemination of history and culture. Digital 3-dimensional (3D) modeling of cultural relics is an effective way to preserve them. The efficiency and complexity of cultural relic model reconstruction algorithms are significant challenges due to redundant data. To tackle the above issue, a 3D reconstruction algorithm, named COLMAP + LSH, was proposed for movable cultural relics based on salient region optimization. COLMAP + LSH algorithm introduces saliency region detection and locality-sensetive Hashing (LSH) to achieve efficient, accurate, and robust digital 3D modeling of cultural relics. Specifically, 400 cultural model data were collected through offline and online collection. COLMAP + LSH algorithm detects the salient region interactively and reduces the number of images in the salient region by feature diffusion. Additionally, COLMAP + LSH algorithm utilizes LSH to calculate the image selection scores and employs the image selection scores to reduce the redundant image. The experiments on the self-constructed cultural relics dataset show that COLMAP + LSH algorithm can efficiently achieve image feature diffusion and ensure the quality of artifact reconstruction while selecting most of the redundant image data.

Pointer-prototype fusion network for few-shot named entity recognition

赵海英 郭轩

中国邮电高校学报(英文), 2023, 30 (5). doi： 10.19682/j.cnki.1005-8885.2023.0011

摘要 ( 235 ) PDF (1526 KB)( 140 )

参考文献 | 相关文章 | 计量指标

   Few-shot named entity recognition (NER) aims to identify named entities in new domains using a limited amount of annotated data. Previous methods divided this task into entity span detection and entity classification, achieving good results. However these methods are limited by the imbalance between the entity and non-entity categories due to the use of sequence labeling for entity span detection. To this end, a point-proto network ( PPN) combining pointer and prototypical networks was proposed. Specifically, the pointer network generates the position of entities in sentences in the entity span detection stage. The prototypical network builds semantic prototypes of entity types and classifies entities based on their distance from these prototypes in the entity classification stage. Moreover, the low-rank adaptation ( LoRA) fine-tuning method, which involves freezing the pre-trained weights and injecting a trainable decomposition matrix, reduces the parameters that need to be trained and saved. Extensive experiments on the few-shot NER Dataset (Few-NERD) and Cross-Dataset demonstrate the superiority of PPN in this domain.

Reliable pseudo-labeling prediction framework for new event type induction

杨琪 徐雅静 吕远 肖波 陈光

中国邮电高校学报(英文), 2023, 30 (5). doi： 110.19682/j.cnki.1005-8885.2023.0009

摘要 ( 196 ) PDF (1743 KB)( 99 )

参考文献 | 相关文章 | 计量指标

   As a subtask of open domain event extraction ( ODEE), new event type induction aims to discover a set of unseen event types from a given corpus. Existing methods mostly adopt semi-supervised or unsupervised learning to achieve the goal, which uses complex and different objective functions for labeled and unlabeled data respectively. In order to unify and simplify objective functions, a reliable pseudo-labeling prediction (RPP) framework for new event type induction was proposed. The framework introduces a double label reassignment ( DLR) strategy for unlabeled data based on swap-prediction. DLR strategy can alleviate the model degeneration caused by swap-predication and further combine the real distribution over unseen event types to produce more reliable pseudo labels for unlabeled data. The generated reliable pseudo labels help the overall model be optimized by a unified and simple objective. Experiments show that RPP framework outperforms the state-of-the-art on the benchmark.

Identity-based proxy re-encryption scheme from RLWE assumption with ciphertext evolution

孟慧 任利娜 赵宗渠

中国邮电高校学报(英文), 2023, 30 (5). doi： 10.19682/j.cnki.1005-8885.2023.0006

摘要 ( 293 ) PDF (468 KB)( 104 )

参考文献 | 相关文章 | 计量指标

   Proxy re-encryption (PRE) allows users to transfer decryption rights to the data requester via proxy. Due to the current PRE schemes from lattice ( LPRE) cannot fulfill chosen-ciphertext attack ( CCA) security, an identity-based PRE (IB-PRE) scheme from learning with errors over ring ( RLWE) assumption with ciphertext evolution (IB-LPRE-CE) was proposed. IB-LPRE-CE generates the private key using the preimage sampling algorithm (SamplePre) and completes the ciphertext delegation using the re-encryption algorithm. In addition, for the problem of ciphertext delegation change caused by the long-term secret key update, the idea of PRE is used to complete ciphertext evolution and the modification of ciphertext delegation, which improves the efficiency of secure data sharing. In terms of security, IB-LPRE-CE is CCA security based on RLWE assumption. Compared with the current LPRE schemes, IB-LPRE-CE offers greater security and improves the computational efficiency of the encryption algorithm.

Heuristic multistep attack scenarios construction based on kill chain

Jie Cheng 张茹 Jiahui Wei Chen Lu Zhishuai Lv Bingjie Lin Ang Xia

中国邮电高校学报(英文), 2023, 30 (5). doi： 10.19682/j.cnki.1005-8885.2023.0003

摘要 ( 289 ) PDF (1630 KB)( 88 )

参考文献 | 相关文章 | 计量指标

 Network attacks evolved from single-step and simple attacks to complex multistep attacks. Current methods of multistep attack detection usually match multistep attacks from intrusion detection systems (IDS) alarms based on the correlation between attack steps. However, IDS has false negatives and false positives, which leads to incomplete or incorrect multistep attacks. Association based on simple similarity is difficult to obtain an accurate attack cluster, while association based on prior knowledge such as attack graphs is difficult to guarantee a complete attack knowledge base. To solve the above problems, a heuristic multistep attack scenarios construction method based on the kill chain (HMASCKC) model was proposed. The attack model graph can be obtained from dual data sources and heuristic multistep attack scenarios can be obtained through graph matching. The model graph of the attack and the predicted value of the next attack are obtained by calculating the matching value. And according to the purpose of the multistep attack, the kill chain model is used to define the initial multistep attack model, which is used as the initial graph for graph matching. Experimental results show that HMASCKC model can better fit the multistep attack behavior, the effect has some advantages over the longest common subsequence (LCS) algorithm, which can close to or match the prediction error of judge evaluation of attack intension ( JEAN) system. The method can make multistep attack model matching for unknown attacks, so it has some advantages in practical application.

Wireless

Review of reader antennas for UHF RFID systems

牛耀辉 李秀萍 赵文禹

中国邮电高校学报(英文), 2023, 30 (5). doi： 10.19682/j.cnki.1005-8885.2023.0008

摘要 ( 267 ) PDF (5205 KB)( 181 )

参考文献 | 相关文章 | 计量指标

 Radio-frequency identification (RFID) antennas are critical components in wireless communication networks for the Internet of things (IoT). The RFID systems make it possible to realize the dynamic interconnection of various things. To better summarize the operating principles of the RFID antennas and associate antennas with specific complex applications, a review of RFID systems and antennas is necessary. In this paper, a review of reader antennas for ultra-high frequency ( UHF) RFID systems is presented, and the categories of RFID systems are summarized for the first time. The antennas are classified according to the reading region and operating principle. The reading region determines the most crucial performance that should be concentrated on when designing an antenna, while the operating principle affects the current distribution on the surface of the antenna, and further the electromagnetic radiation. By the summary of the RFID systems and antennas, the understanding of future researchers on the operating principles of the RFID antennas could be facilitated, which can be helpful in the advanced design and implementation of RFID antennas. In addition, taking engineering requirements into account, the future prospective of RFID applications is discussed, as well as the challenges to be addressed.

Weighted semidefinite programming scheme for wireless positioning with lognormal shadowing

田克冈 徐文波 王思野 陈湘森

中国邮电高校学报(英文), 2023, 30 (5). doi： 10.19682/j.cnki.1005-8885.2023.0007

摘要 ( 279 ) PDF (1029 KB)( 106 )

参考文献 | 相关文章 | 计量指标

Received signal strength (RSS) based positioning schemes ignore the actual environmental feature that the volatility of RSS increases as signal propagation distance grows. Therefore, RSS over long distance generally has relatively large measurement error and degrades the positioning performance. To reduce the negative impact of these RSSs over long distances, a weighted semidefinite programming (WSDP) positioning scheme was proposed. The WSDP positioning scheme first assesses the signal propagation quality using the average variance of all RSS sets. Then appropriate weighting factors are set based on the variance of each RSS set, and a weighted semidefinite programming optimizer is formulated to estimate the positions of target nodes. Simulation results show that the WSDP positioning scheme can effectively improve the positioning performance.