检索结果-内蒙古大学图书馆

AdaptFRCNet: Semi-supervised adaptation of pre-trained model with frequency and region consistency for medical image segmentation

引用

Medical Image Analysis 2025年 103卷 103626页

作者： Along He Yanlin Wu Zhihong Wang Tao Li Huazhu Fu College of Computer Science Tianjin Key Laboratory of Network and Data Security Technology Nankai University Tianjin 300350 China Haihe Lab of ITAI Tianjin 300459 China Institute of High Performance Computing (IHPC) Agency for Science Technology and Research (A*STAR) 138632 Singapore

Recently, large pre-trained models (LPM) have achieved great success, which provides rich feature representation for downstream tasks. Pre-training and then fine-tuning is an effective way to utilize LPM. However, the application of LPM in the medical domain is hindered by the presence of a large number of parameters and a limited amount of labeled data. In clinical practice, there exists a substantial amount of unlabeled data that remains underutilized. Semi-supervised learning emerges as a promising approach to harnessing these unlabeled data effectively. In this paper, we propose semi-supervised adaptation of pre-trained model with frequency and region consistency (AdaptFRCNet) for medical image segmentation. Specifically, the pre-trained model is frozen and the proposed lightweight attention-based adapters (Att_Adapter) are inserted into the frozen backbone for parameter-efficient fine-tuning (PEFT). We propose two consistency regularization strategies for semi-supervised learning: frequency domain consistency (FDC) and multi-granularity region similarity consistency (MRSC). FDC aids in learning features within the frequency domain, and MRSC aims to achieve multiple region-level feature consistencies, capturing local context information effectively. By leveraging the proposed Att_Adapter along with FDC and MRSC, we can effectively and efficiently harness the powerful feature representation capability of the LPM. We conduct extensive experiments on three medical image segmentation datasets, demonstrating significant performance improvements over other state-of-the-art methods. The code is available at https://***/NKUhealong/AdaptFRCNet .

关键词： Consistency regularization Medical image segmentation Parameter-efficient fine-tuning Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A Self-adaptive Single-Objective Multitasking Optimization Algorithm 1

引用

17th International Conference on Bio-Inspired computing: Theories and Applications, BIC-TA 2022

作者： Li, Xiaoyu Wang, Lei Jiang, Qiaoyong Li, Wei Wang, Bin The Key Laboratory of Network Computing and Security Technology of Shaanxi Province Xi’an University of Technology Xi’an710048 China The Key Laboratory of Industrial Automation of Shaanxi Province Shaanxi University of Technology Hanzhong723001 China School of Electronic and Information Engineering Ankang University Ankang725000 China

ISBN: (数字)9789819915491

ISBN: (纸本)9789819915484

Evolutionary multitasking optimization algorithms have been presented for dealing with multiple tasks simultaneously. Many studies have proved that EMTOs often perform better than conventional single-task evolutionary. Transferring knowledge plays a very important role in multitask optimization algorithms. Many existing methods transfer elite solutions between tasks to improve algorithm performance, however, these methods may or produce negative transfer if inter-task similarity is low or irrelevant. This paper presents a self-adaptive multitasking optimization algorithm, SAMTOA, to find more valuable transferred solutions between tasks. In SAMTOA, the solutions for the next generation transfer are adaptively determined based on the successful transfer solutions of the previous generation. The method can effectively reduce the probability of transferring useless solutions between tasks and effectively utilize valuable solutions in tasks to improve the efficiency of knowledge transfer between tasks. Experimental results on single-objective multitasking optimization benchmark problems indicate that SAMTOA outperforms the other the state-of-the-art EMTO algorithms. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

A Novel Teaching Strategy Based on EduCoder Platform for C Programming Language 5th

A Novel Teaching Strategy Based on EduCoder Platform for C P...

引用

5th International Conference on Computer Science and Educational Informatization, CSEI 2023

作者： Li, Wei Hei, Xinhong Wang, Lei Wang, Yichuan School of Computer Science and Engineering Xi’an University of Technology Xi’an China Shaanxi Key Laboratory for Network Computing and Security Technology Xi’an China School of Mathematics and Computer Science Shaanxi University of Technology Hanzhong China

ISBN: (纸本)9789819994915

Experimental teaching is an important part of the C programming language course, which aims to cultivate students’ Computational thinking ability, problem solving ability and programming ability. However, the existing experimental teaching mode of the C programming language course has been criticized mainly for their: 1) it is difficult for teachers to check all students’ programs within a limited time;2) Limited computer room capacity, fixed time, and other factors make it difficult to meet the personalized requirements of students. In this paper, we put forward the construction scheme of experimental teaching of the C programming language course based on the EduCoder platform, which alleviates all the above two problems. The scheme follows the fundamental law of engineering practice ability training and constructs a LDEI practice teaching closed loop of "learning (L), doing (D), evaluation (E) and improvement (I)". Through specific cases, this paper elaborates the implementation process of this scheme in the experimental teaching of the C programming language course. Finally, a survey are conducted on 64 students from computer science and technology majors. The survey results show that the designed scheme effectively enhances the students’ Computational thinking ability and programming ability. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Anomaly detection of user behavior based on DTMC with states of variable-length sequences

引用

The Journal of China Universities of Posts and Telecommunications 2011年第6期18卷 106-115页

作者： XIAO Xi XIA Shu-tao TIAN Xin-guang ZHAI Qi-bin Graduate School at Shenzhen Tsinghua University Shenzhen 518055 China State Key Laboratory of Information Security Graduate University of Chinese Academy of Sciences Beijing 100049 China Key Laboratory of Network Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China

In anomaly detection, a challenge is how to model a user＇s dynamic behavior. Many previous works represent the user behavior based on fixed-length models. To overcome their shortcoming, we propose a novel method based on discrete-time Markov chains （DTMC） with states of variable-length sequences. The method firstly generates multiple shell command streams of different lengths and combines them into the library of general sequences. Then the states are defined according to variable-length behavioral patterns of a valid user, which improves the precision and adaptability of user profiling. Subsequently the transition probability matrix is created. In order to reduce computational complexity, the classification values are determined only by the transition probabilities, then smoothed with sliding windows, and finally used to discriminate between normal and abnormal behavior. Two empirical evaluations on datasets from Purdue University and AT＆T Shannon Lab show that the proposed method can achieve higher detection accuracy and require less memory than the other traditional methods.

关键词： intrusion detection anomaly detection shell command discrete-time Markov chain (DTMC)

来源：评论

学校读者我要写书评

暂无评论

A novel image security protection method based on DCT compression theory and hyper-chaotic mapping

A novel image security protection method based on DCT compre...

引用

2021 International Conference on Information technology and Mechanical Engineering, ITME 2021

作者： Xue, Xianglian Jin, Haiyan School of Computer Science and Engineering Xi’an University of Technology Shaanxi Xi’an710077 China Shaanxi University of Chinese Medicine Shaanxi Xianyang712046 China Shaanxi Key Laboratory for Network Computing and Security Technology Xi’an University of Technology Shaanxi Xi’an710077 China

This paper studies the current situation of image compression encryption and analyzes the influence of low frequency (DC coefficient) and high frequency (AC coefficient) on image structure in DCT transformation. Based on this, a novel image security protection method based on DCT compression theory and hyper-chaotic mapping is proposed. First, the position of the pixel of the original image is disturbed, and converts the image from spatial domain into frequency domain by the two-dimensional DCT transformation and quantization. Second, change the pixel values by modifying the values of the sign bit of AC coefficient and DC coefficient. At last, the encrypted image is obtained by carrying out inverse quantization, inverse transformation and reverse operation by bit. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Cryptography

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

Prediction of miRNA family based on class-incremental learning

Prediction of miRNA family based on class-incremental learni...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Liu, Yajun Qiu, Lulu Li, Aimin Fei, Rong Li, Junhuai Wu, Fang-Xiang Xi'an University of Technology Shaanxi Key Laboratory for Network Computing and Security Technology Xi'an China Division of Biomedical Engineering Department of Mechanical Engineering Department of Computer Science Saskatoon Canada

ISBN: (纸本)9798350386226

With the development of deep sequencing, recent studies indicate that a miRNA precursor can generate multiple miRNA isoforms (isomiRs). The family prediction of canonical miRNAs and isomiRs could provide a basis for miRNA functional research. In this study, we propose a novel method for family identification of canonical miRNA and isomiRs based on incremental learning. First, a benchmark dataset is constructed by processing data based on miRNA sequences and their family annotation. Moreover, sequence embedding and RNN are used for capturing essential features and inherent dependencies within a sequence. Finally, incremental learning is applied to accommodate the continuous influx of miRNA sequencing data, enabling RNN to stay relevant and effective over time. Comparative experiments and ablation studies illustrate the effectiveness of our model, which can help to comprehensively understand miRNA's function. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Edge computing Task Scheduling with Joint Blockchain and Task Caching in Industrial Internet

引用

Computers, Materials & Continua 2023年第4期75卷 2101-2117页

作者： Yanping Chen Xuyang Bai Xiaomin Jin Zhongmin Wang Fengwei Wang Li Ling 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’an710121China Xi’an Key Laboratory of Big Data and Intelligent Computing Xi’anShaanxi710121China ZTE Corporation Shenzhen51805China

Deploying task caching at edge servers has become an effectiveway to handle compute-intensive and latency-sensitive tasks on the industrialinternet. However, how to select the task scheduling location to reduce taskdelay and cost while ensuring the data security and reliable communicationof edge computing remains a challenge. To solve this problem, this paperestablishes a task scheduling model with joint blockchain and task cachingin the industrial internet and designs a novel blockchain-assisted cachingmechanism to enhance system security. In this paper, the task schedulingproblem, which couples the task scheduling decision, task caching decision,and blockchain reward, is formulated as the minimum weighted cost problemunder delay constraints. This is a mixed integer nonlinear problem, which isproved to be nonconvex and NP-hard. To solve the optimal solution, thispaper proposes a task scheduling strategy algorithm based on an improvedgenetic algorithm (IGA-TSPA) by improving the genetic algorithm initializationand mutation operations to reduce the size of the initial solutionspace and enhance the optimal solution convergence speed. In addition,an Improved Least Frequently Used algorithm is proposed to improve thecontent hit rate. Simulation results show that IGA-TSPA has a faster optimalsolution-solving ability and shorter running time compared with the existingedge computing scheduling algorithms. The established task scheduling modelnot only saves 62.19% of system overhead consumption in comparison withlocal computing but also has great significance in protecting data security,reducing task processing delay, and reducing system cost.

关键词： Edge computing task scheduling blockchain task caching industrial security

来源：评论

学校读者我要写书评

暂无评论

Channel Drop Out: A Simple Way to Prevent CNN from Overfitting in Motor Imagery Based BCI 7th

Channel Drop Out: A Simple Way to Prevent CNN from Overfitti...

引用

7th International Conference of Pioneering Computer Scientists, Engineers and Educators, ICPCSEE 2021

作者： Luo, Jing Wang, Yaojie Xu, Rong Liu, Guangming Wang, Xiaofan Gong, Yijing Shaanxi Key Laboratory for Network Computing and Security Technology School of Computer Science and Engineering Xi’an University of Technology Xi’an China Shaanxi Province Institute of Water Resources and Electric Power Investigation and Design Xi’an China

ISBN: (纸本)9789811659393

With the development of deep learning, many motor imagery brain-computer interfaces based on convolutional neural networks (CNNs) show outstanding performances. However, the trial number of EEG in the training set is usually limited, and redundancy extensively exists in multiple channel EEG. Thus, overfitting often appears in CNN based motor imagery recognition model and greatly affects the performances of model. In this paper, channel drop out is proposed to address this problem by data augmentation and ensemble learning. Specifically, one of all EEG channels will be dropped and replaced by the mean signal of all EEG channels. In this way, the trial number in the training set was enlarged by channel drop out. And at the testing stage, all the EEG trials processed by channel drop out were fed to the CNN model and the average output probabilities of them were applied to determine the prediction. The experiments were conducted on two popular CNN models applied in motor imagery BCI and BCI Competition IV datasets 2a to verify the performances of the proposed channel drop out approach. The results show that average improvements provided by channel drop out in two-category or four-category motor imagery classification are 2.83% and 2.65% compared with the original CNN model. So the channel drop out approach significantly improves the performances of motor imagery based BCI. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Passive Beamforming Design for Intelligent Reflecting Surface Assisted MIMO Systems

引用

China Communications 2021年第3期18卷 18-28页

作者： Chenghao Feng Wenqian Shen Xinyu Gao Jianping An School of Information and Electronics Beijing Institute of TechnologyBeijing 100081China Shaanxi Key Laboratory of Information Communication Network and Security Xian University of Posts and TelecommunicationsXianShaanxi 710121China Huawei Technologies Co.Ltd. Beijing 100085China

Intelligent reflecting surfaces(IRSs)constitute passive devices,which are capable of adjusting the phase shifts of their reflected signals,and hence they are suitable for passive *** this paper,we conceive their design with the active beamforming action of multiple-input multipleoutput(MIMO)systems used at the access points(APs)for improving the beamforming gain,where both the APs and users are equipped with multiple ***,we decouple the optimization problem and design the active beamforming for a given IRS *** we transform the optimization problem of the IRS-based passive beamforming design into a tractable non-convex quadratically constrained quadratic program(QCQP).For solving the transformed problem,we give an approximate solution based on the technique of widely used semidefinite relaxation(SDR).We also propose a low-complexity iterative *** further prove that it can converge to a locally optimal ***,considering the practical scenario of discrete phase shifts at the IRS,we give the quantization design for IRS elements on basis of the two *** simulation results demonstrate the superiority of the proposed solutions over the relevant benchmarks.

关键词： intelligent reflecting surface MIMO systems passive beamforming

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：