检索结果-内蒙古大学图书馆

Research on Improved MobileViT Image Tamper Localization Model

Computers, Materials & Continua 2024年第8期80卷 3173-3192页

作者： Jingtao Sun Fengling Zhang Huanqi Liu Wenyan Hou School of Computer Science and Technology Xi’an University of Posts and TelecommunicationsXi’an710121China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’an University of Posts and TelecommunicationsXi’an710121China

As image manipulation technology advances rapidly,the malicious use of image tampering has alarmingly escalated,posing a significant threat to social *** the realm of image tampering localization,accurately localizing limited samples,multiple types,and various sizes of regions remains a multitude of *** issues impede the model’s universality and generalization capability and detrimentally affect its *** tackle these issues,we propose FL-MobileViT-an improved MobileViT model devised for image tampering *** proposed model utilizes a dual-stream architecture that independently processes the RGB and noise domain,and captures richer traces of tampering through dual-stream ***,the model incorporating the Focused Linear Attention mechanism within the lightweight network(MobileViT).This substitution significantly diminishes computational complexity and resolves homogeneity problems associated with traditional Transformer attention mechanisms,enhancing feature extraction diversity and improving the model’s localization *** comprehensively fuse the generated results from both feature extractors,we introduce the ASPP architecture for multi-scale feature *** facilitates a more precise localization of tampered regions of various ***,to bolster the model’s generalization ability,we adopt a contrastive learning method and devise a joint optimization training strategy that leverages fused features and captures the disparities in feature distribution in tampered *** strategy enables the learning of contrastive loss at various stages of the feature extractor and employs it as an additional constraint condition in conjunction with cross-entropy *** a result,overfitting issues are effectively alleviated,and the differentiation between tampered and untampered regions is *** evaluations on five benchmark datasets(IMD-20,CASIA,NIST-16,Columbia and Coverage)validat

关键词： Image tampering localization focused linear attention mechanism MobileViT contrastive loss

来源：评论

学校读者我要写书评

暂无评论

Automatic ocular artifact removal from EEG data using a hybrid CAE-RLS approach

引用

The Journal of China Universities of Posts and Telecommunications 2020年第1期27卷 81-91页

作者： Wang Zhongmin Tian Meng Liang Chen Song Hui School of Computer Science and Technology Xi'an University of Posts and TelecommunicationsXi'an 710121China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an University of Posts and TelecommunicationsXi'an 710121China

Traditional methods for removing ocular artifacts(OAs) from electroencephalography(EEG) signals often involve a large number of EEG electrodes or require electrooculogram(EOG) as the reference, these constraints make subjects uncomfortable during the acquisition process and increase the complexity of brain-computer interfaces(BCI). To address these limitations, a method combining a convolutional autoencoder(CAE) and a recursive least squares(RLS) adaptive filter is proposed. The proposed method consists of offline and online stages. In the offline stage, the peak and local mean of the four-channel EOG signals are automatically extracted to obtain the CAE model. Once the model is trained, the EOG channels are no longer needed. In the online stage, by using the CAE model to identify the OAs from a single-channel raw EEG signal, the identified OAs and the given raw EEG signal are used as the reference and input for an RLS adaptive filter. Experiments show that the root mean square error(RMSE) of the CAE-RLS algorithm and independent component analysis(ICA) are 1.253 3 and 1.254 6 respectively, and the power spectral density(PSD) curve for the CAE-RLS is similar to the original EEG signal. These experimental results indicate that by using only a couple of EEG channels, the proposed method can effectively remove OAs without parallel EOG records and accurately reconstruct the EEG signal. In addition, the processing time of the CAE-RLS is shorter than that of ICA, so the CAE-RLS algorithm is very suitable for BCI system.

关键词： electroencephalography(EEG) electrooculogram(EOG) ocular artifacts(OAs) recursive least squares(RLS) convolutional autoencoder(CAE)

来源：评论

学校读者我要写书评

暂无评论

Remaining Useful Life Prediction of Lithium Battery via Neural network Ensemble 16

Remaining Useful Life Prediction of Lithium Battery via Neur...

引用

16th IEEE International Conference on intelligent Systems and Knowledge Engineering, ISKE 2021

作者： Zhang, Hengshan Wu, Di Wang, Zhongmin Chen, Yanping Xu, Jiaxuan Xi'an University of Posts and Telecommunications School of Computer Science and Technology Xi'an710000 China Shanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an710000 China

ISBN: (纸本)9781665405539

Accurately predicting the Remaining Useful Life (RUL) of lithium-ion batteries is critical for accelerating the technology development. The neural network via data driven can avoid manual feature extraction and release the difficulty of model construction. However, diverse aging mechanisms, significant device variability and dynamic operating conditions have remained major challenges. The single neural network cannot tackle these challenges efficiently. In this paper, the RUL prediction of lithium battery via neural network ensemble is developed to improve the accuracy and generalization of the prediction model. The predicting results of multiple neural networks are considered as the base vectors, and the liner combination on the base vectors are conducted to obtain the ensemble RUL prediction of lithium-ion battery. The experiment is performed on the MIT-Stanford University lithium battery accelerated degradation dataset, and the experimental results show that the developed method has achieved better generalization and higher accuracy comparing with the other methods. © 2021 IEEE.

关键词： Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

Moving Forward Together: A Multi-User Pattern Extraction Neural Model for Sequential Recommendations 6

Moving Forward Together: A Multi-User Pattern Extraction Neu...

引用

6th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2023

作者： Du, Xiangpeng Li, Xiaoge Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xian University of Posts and Telecommunications Shaanxi Xi'an710121 China

ISBN: (纸本)9798400707674

The sequential recommendation is a very important task in recommendation systems. The aim of it is to dynamic predict user's interests based on their historical behaviors. Despite recent progress, most of deep learning approaches focus on extracting the behavioral patterns of a single user. Pulling multiple users can increase the diversity of historical information. In this paper, we propose multi-user behavioral pattern extraction model (TMGN) via a combination of traditional behavioral pattern extraction and graph convolutional aggregation. Concretely, TMGN first learns the graph structure of users and items. Then it performs graph convolution aggregation to derive a representation of users to extract user interest features. We recall the users with the highest similarity by calculating the cosine similarity of each candidate user. Finally, we inject multiple users' sequence patterns and time information into the muti-head attention mechanism. Experiments on actual data (Movielens1m, Movielen20m and Amazon beauty) show that the proposed method outperforms current state-of-the-art sequential recommendation methods. TMGN achieves an average improvement of 5.67%, 5.75%, 7.32%, and 7.19% over the most robust baseline in Hit@5, Hit@10, NDCG@5, and NDCG@10, respectively. We provide extensive ablation studies to analyze the impact of each model component on TMGN. © 2023 ACM.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Multi-objective test case prioritization based on epistatic particle swarm optimization

引用

International Journal of Performability Engineering 2018年第10期14卷 2441-2448页

作者： Sun, Jiaze Chen, Jingmin Wang, Gang School of Computer Science and Technology Xi’an University of Posts and Telecommunications Xi’an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’an University of Posts and Telecommunications Xi’an710121 China

To address the Multi-Objective Test Case Prioritization (MOTCP) problem, an Epistatic Particle Swarm Optimization (EPSO) algorithm is presented. The epistasis in biology is introduced into the new algorithm, and the particles are updated based on the crossover of Epistatic Test Case Segment (ETS) in the test case sequence. The average coverage percentage of program entity and effective execution time of the test case sequence are set as two objective fitness functions in EPSO. The experiment selects four typical open12 source projects as benchmark programs. We adopted Average Percentage of Branch Coverage (APBC) and Effective Execution Time (EET) as objective fitness. The four classical Java testing projects results show that the EPSO is more effective and more diverse than single-point PSO and order PSO. The EPSO algorithm efficiently solves the MOTCP problem by promoting early detection of software defects and reducing software testing costs in regression testing. © 2018 Totem Publisher, Inc. All rights reserved.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

PSO with reverse edge for multi-objective software module clustering

引用

International Journal of Performability Engineering 2018年第10期14卷 2423-2431页

作者： Sun, Jiaze Xu, Yang Wang, Shuyan School of Computer Science and Technology Xi’an University of Posts and Telecommunications Xi’an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’an University of Posts and Telecommunications Xi’an710121 China

The multi-objective software module clustering problem (MOSMCP) divides the complex software system into subsystems to obtain a perfect structure, which is based on the relations between modules to meet the conflicting software refactor objectives as much as possible. The modularization quality (MQ) and reverse edges number between clusters are considered as evaluation objectives, and a novel particle swarm optimization (PSO) with reverse edge, called REPSO, is proposed. First, the module dependency graph (MDG) in software system under clustering is constructed, and then the multi-objective particle swarm optimization (MOPSO) is improved to cluster the MDG. The exploring approach is used to update the particle locations. Four typical open source projects for module clustering are selected to verify the effectiveness of the REPSO. The laboratorial results prove that the REPSO algorithm is very effective and stable, and the diversity of the optimal solution is good. The REPSO algorithm provides an efficient engineering method for MOSMCP, which enhances the software structure and maintainability. © 2018 Totem Publisher, Inc. All rights reserved.

关键词： Modular construction

来源：评论

学校读者我要写书评

暂无评论

SolBERT: Advancing solidity smart contract similarity analysis via self-supervised pre-training and contrastive fine-tuning

引用

Information and Software Technology 2025年 184卷

作者： Zhenzhou Tian Yudong Teng Xianqun Ke Yanping Chen Lingwei Chen School of Computer Science and Technology Xi’an University of Posts and Telecommunications Xi’an 710121 Shaanxi China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’an University of Posts and Telecommunications Xi’an 710121 Shaanxi China Xi’an Key Laboratory of Big Data and Intelligent Computing Xi’an University of Posts and Telecommunications Xi’an 710121 Shaanxi China Department of Computer Science and Engineering Wright State University Dayton 45435 OH USA

Context: Reliable and effective similarity analysis for the smart contracts facilitates the maintenance and quality assurance of the smart contract ecosystem. However, existing signature-based methods and code representation learning-based methods suffer from limitations such as heavy-weight program analysis payloads or suboptimal contract encodings. Objective: This paper aims to design a fully unsupervised language model for better capturing the syntactic and semantic richness of Solidity code, and utilizes it for advancing the effectiveness of smart contract similarity analysis. Methods: Inspired by the impressive semantic learning capability of pre-trained language models (PLMs), we propose SolBERT, a PLM specifically tailored for enhancing Solidity smart contracts similarity detection. To ensure it produces high-quality encodings, SolBERT leverages BERT-style pre-training with the masked language modeling (MLM) and token type prediction (TTP) tasks applied on code-structure-aware token sequences derived from the contracts’ abstract syntax trees (ASTs) through structure-retaining tree linearization and light-weight normalization to learn a base model. On this basis, self-supervised contrastive fine-tuning and unsupervised whitening operations are further performed to optimize contract encoding generation. Results: Experiments are conducted on three contract similarity-related tasks, including contract clone detection, bug detection, and code clustering. The results indicate that SolBERT significantly outperforms state-of-the-art approaches with average absolute gains of 21.33% and 21.50% in terms of F1, and 17.78% and 26.60% in terms of accuracy for the clone detection and bug detection tasks, respectively; and an average absolute gain of 17.97% for code clustering task. When applying both contrastive fine-tuning and whitening optimizations, SolBERT also shows superior performance than the case of lacking any of them. Conclusion: The proposed approach, SolBERT, c

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Clustering Combination Method Using Intuitionistic Fuzzy Similarity in Software Module Clustering

Hierarchical Clustering Combination Method Using Intuitionis...

引用

2023 International Conference on networking and network Applications, NaNA 2023

作者： Xia, Hong Wang, Bo Zhang, Yongkang Chen, Yanping School of Computer Science and Technology Xi'an University of Posts and Telecommunications China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing China Xi 'An Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi'an710121 China

ISBN: (纸本)9798350327380

In order to solve the problem that the similarity method used in software module clustering can produce arbitrary decision, and the description matrix of dendrogram generated by base clustering in hierarchical clustering combination does not consider more characteristics of entities, a hierarchical clustering combination method based on intuitionistic fuzzy similarity (HCC-IFS) was proposed. In the process of entity similarity calculation, the intuitionistic fuzzy set theory and similarity calculation method are used to provide membership and non-membership attributes for each entity, so as to improve the merging efficiency and solve arbitrary decision problems. In the description matrix representation of base clustering, the absolute and relative features obtained from the dendrogram are used to construct the description matrix, and the generated description matrix is combined. Finally, the proposed algorithm is verified by experiments. Experimental results show that HCC-IFS can produce better clustering results and improve the recovery quality of software architecture. © 2023 IEEE.

关键词： Fuzzy set theory

来源：评论

学校读者我要写书评

暂无评论

Blockchain Fragment Expansion Scheme Based on Community Detection and MSR Code 5

Blockchain Fragment Expansion Scheme Based on Community Dete...

引用

5th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2022

作者： Zhai, Sheping Tong, Tong Bai, Xifang Xi'an University of Posts and Telecommunications Shaanxi Provincial Key Laboratory of Network Data Analysis and Intelligent Processing China Xi'an University of Posts and Telecommunications China

ISBN: (纸本)9781450396899

Aiming at the current performance of blockchain system can not meet the actual needs of high-frequency data interaction in the era of information explosion, a blockchain fragment expansion scheme based on community detection and MSR code is proposed. Firstly, based on the random walk community detection algorithm and the blockchain node network, a node grouping method is proposed. Each group of nodes maintains a copy of the blockchain ledger to reduce the storage redundancy of blockchain. Secondly, the block data is divided by minimum storage regenerating codes (MSR), which further reduces the storage pressure of nodes, reduces the amount of data required for block requests, and reduces network pressure. Finally, a blockchain scalable fragment storage scheme is proposed. The simulation experiment and result analysis show that the blockchain fragment expansion scheme based on community detection and MSR has improved in terms of storage scalability, response efficiency and fault tolerance. © 2022 ACM.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Research on Image Description Generation Method Based on G-AoANet 5

Research on Image Description Generation Method Based on G-A...

引用

5th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2022

作者： Qiao, Pingan Shen, Ruixue Li, Yuan Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing School of Computer Science and Technology Xi'an University of Posts and Telecommunications Xi'an710121 China

ISBN: (纸本)9781450396899

Most of the image description generation methods in the attention-based encoder-decoder framework extract local features from images. Despite the relatively high semantic level of local features, it still has two problems to be solved, one is object loss, where some important objects may be lost when generating image descriptions, and the other is prediction error, as an object may be identified in the wrong class. In this paper, a G-AoANet model is proposed to solve the above problems. The model uses an attention mechanism to combine global features with local features. In this way, our model can selectively focus on both object and contextual information, improving the quality of the generated descriptions. Experimental results show that the model improves the initially reported best CIDEr-D and SPICE scores on the MS COCO dataset by 9.3% and 5.1% respectively. © 2022 ACM.

关键词： Semantics

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：