检索结果-内蒙古大学图书馆

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Muhammad Umair Raza Jie Chen Li Wang Adil Nawaz Victor C.M. Leung Jianqiang Li College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

The challenge of interpretability remains a significant barrier to adopting deep neural networks in healthcare domains. Although tree regularization aims to align a deep neural network’s decisions with a single axis-aligned decision tree, however, relying on one tree for all inputs often leads to sub-optimal performance and interoperability. To address this limitation, we propose an enhanced tree regularization method that integrates a post-hoc visual explainable model such as Grad-CAM. This approach guides the deep model to be well-approximated by decision trees tailored to the salient regions identified by Grad-CAM in the input space. We rigorously validate the effectiveness of this framework on two cancer cell datasets: CNMC, which focuses on acute lymphoblastic leukemia cells, and ISBI2016, which comprises benign and malignant skin lesions. The results demonstrate that the proposed method delivers simpler and more interpretable explanations without compromising accuracy, thereby advancing the interpretability of deep learning models in critical healthcare applications.

关键词： Visualization Accuracy Decision making Artificial neural networks Predictive models Skin Decision trees Lesions Biological cells Cancer

来源：评论

学校读者我要写书评

暂无评论

Discrete Geometric Coded Data Layout for Large-scale Object Storage systems 21

Discrete Geometric Coded Data Layout for Large-scale Object ...

引用

21st IEEE International Symposium on Parallel and Distributed Processing with Applications, 13th IEEE International Conference on Big Data and Cloud Computing, 16th IEEE International Conference on Social Computing and Networking and 13th International Conference on Sustainable Computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Tian, Yi Xu, Guangping Yang, Hongzhang Ni, Yue Cao, JiaXin Yang, Lei Tianjin University of Technology School of Computer Science and Engineering Tianjin China Novel Software Technology Tianjin Key Laboratory of Intelligence Computing Tianjin China Key Laboratory of Computer Vision and System Ministry of Education China Information Technology Co. Ltd. China

ISBN: (纸本)9798350329223

Regenerating codes are new network codes proposed to reduce the data required for fault repair, which can improve the recovery efficiency of faulty nodes in data storage systems. However, unlike Reed-Solomon code, which repairs at the granularity of bytes, regenerating codes require data stored in large chunks but leads to severe read amplification, which reads out excess data when degraded read objects and increases degraded read time. That reflects a mutual constraint between improving recovery efficiency and degraded read performance, as manifested in the amplification of data reads, a vital issue considered in this *** solve this problem, we propose a new type of data layout - discrete geometric, which splits the object into a series of geometric sequences of data blocks. They are placed discretely into corresponding containers on the disks at different nodes, with containers of the same size made into a strip for encoding. The discrete characteristic ensures lower repair costs for degraded reads. The geometric characteristic ensures the repair performance of regenerating codes by large blocks, and read amplification can be mitigated through small blocks. To reduce IOPS for discrete geometric, we propose Discrete Geometric-Locally Regenerating Codes (DG-LRCs), guaranteeing lower degraded read latency while improving recovery *** results show that the degraded read time of DG-LRCs compared to regenerating codes combined with geometric partitioning is 22.56% lower at 2Gbpsand 60.56% lower at 4Gbps, and the recovery performance is 7.04 times better than that of RS code. © 2023 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Diversified Sequential Recommendation via Evolutionary Multi-Objective Transfer Optimization

Diversified Sequential Recommendation via Evolutionary Multi...

引用

Artificial Intelligence (CAI), IEEE Conference on

作者： Wei Zhou Xiaolong Luo Hongyue Bao Zexuan Zhu National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China College of Computer Science and Software Engineering Shenzhen University China

ISBN: (数字)9798350354096

ISBN: (纸本)9798350354102

Sequential Recommendation (SR) intends to model user interests based on historical behavior sequences and suggest the next item. Most existing sequential models primarily focus on learning users’ preferences on the relevance objective of the target item. However, the investigation of personalized preferences on the diversity objective of SR results is usually ignored. Evolutionary algorithms have amply demonstrated effectiveness in solving multi-objective problems but encounter efficiency bottlenecks when applied to multi-objective recommendation tasks due to the limited scalability at the user level. To address the problem, this study proposes to facilitate diversified SR via a multi-objective transfer optimization algorithm, in which each optimization task corresponds to the recommendation for a target user. With the optimization knowledge of user preference transferred within and across tasks, the diversified SR of a set of users can synchronously proceed. The novelty of our proposed algorithm is fully utilizing the outstanding global search capability of evolutionary multi-objective optimization without hindering the efficiency of sequential models.

关键词： Scalability Evolutionary computation Task analysis Artificial intelligence Optimization

来源：评论

学校读者我要写书评

暂无评论

Quantum security analysis of SM4 algorithm 6

Quantum security analysis of SM4 algorithm

引用

6th International Conference on Wireless Communications and Smart Grid, ICWCSG 2024

作者： Yang, Hao Wang, Chunhong Tang, Xueming Cui, Yongquan Lu, Songfeng Cai, Dunbo Qian, Ling Zhang, Runqing Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Wuhan Maritime Communication Research Institute Wuhan430010 China Software Technology Co. Ltd. Suzhou215153 China

ISBN: (纸本)9781510682962

The security of commercial encryption algorithms has always been a focus of attention. The SM4 algorithm, a commercial cryptographic standard, has been recognized by ISO/IEC as an international standard and has shown excellent performance on classical computers. However, with the development of quantum computing, traditional encryption algorithms are facing new challenges. This paper investigates the quantum realization of SM4 algorithm. By applying the Grover algorithm to the SM4 algorithm, we conducted a quantum exhaustive attack and provided an estimation of the required quantum resources. This study offers a novel perspective on the application of quantum computing in breaking commercial encryption algorithms, which holds significant implications for the future development of quantum secure communication and cryptography. © 2024 SPIE.

关键词： Encryption algorithms

来源：评论

学校读者我要写书评

暂无评论

Less Yet Robust: Crucial Region Selection for Scene Recognition

Less Yet Robust: Crucial Region Selection for Scene Recognit...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhang, Jianqi Wang, Mengxuan Wang, Jingyao Si, Lingyu Zheng, Changwen Xu, Fanjiang National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Shien-Ming Wu School of Intelligent Engineering South China University of Technology Guangzhou China

ISBN: (纸本)9798350368741

Scene recognition, particularly for aerial and underwater images, often suffers from various types of degradation, such as blurring or overexposure. Previous works that focus on convolutional neural networks have been shown to be able to extract panoramic semantic features and perform well on scene recognition tasks. However, low-quality images still impede model performance due to the inappropriate use of high-level semantic features. To address these challenges, we propose an adaptive selection mechanism to identify the most important and robust regions with high-level features. Thus, the model can perform learning via these regions to avoid interference. implement a learnable mask in the neural network, which can filter high-level features by assigning weights to different regions of the feature matrix. We also introduce a regularization term to further enhance the significance of key high-level feature regions. Different from previous methods, our learnable matrix pays extra attention to regions that are important to multiple categories but may cause misclassification and sets constraints to reduce the influence of such regions. This is a plug-and-play architecture that can be easily extended to other methods. Additionally, we construct an Underwater Geological Scene Classification dataset to assess the effectiveness of our model. Extensive experimental results demonstrate the superiority and robustness of our proposed method over state-of-the-art techniques on two datasets. © 2025 IEEE.

关键词： high-level semantic features remote sensing robust method Scene recognition underwater images

来源：评论

学校读者我要写书评

暂无评论

Effective and Imperceptible Adversarial Textual Attack Via Multi-objectivization

引用

ACM Transactions on Evolutionary Learning and Optimization 2024年第3期4卷 1-23页

作者： Liu, Shengcai Lu, Ning Hong, Wenjing Qian, Chao Tang, Ke Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen College of Engineering South Tower 1088 Xueyuan Avenue Guangdong Shenzhen518055 China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong999077 Hong Kong National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen 10F Zhizhen Building Canghai Campus 3688 Nanhai Avenue Guangdong Shenzhen China National Key Laboratory for Novel Software Technology School of Artificial Intelligence Nanjing University Nanjing International College Area Xianlin Campus 163 Xianlin Avenue Jiangsu Nanjing China

The field of adversarial textual attack has significantly grown over the past few years, where the commonly considered objective is to craft adversarial examples (AEs) that can successfully fool the target model. However, the imperceptibility of attacks, which is also essential for practical attackers, is often left out by previous studies. In consequence, the crafted AEs tend to have obvious structural and semantic differences from the original human-written text, making them easily perceptible. In this work, we advocate leveraging multi-objectivization to address such an issue. Specifically, we reformulate the problem of crafting AEs as a multi-objective optimization problem, where the attack imperceptibility is considered as an auxiliary objective. Then, we propose a simple yet effective evolutionary algorithm, dubbed HydraText, to solve this problem. HydraText can be effectively applied to both score-based and decision-based attack settings. Exhaustive experiments involving 44,237 instances demonstrate that HydraText consistently achieves competitive attack success rates and better attack imperceptibility than the recently proposed attack approaches. A human evaluation study also shows that the AEs crafted by HydraText are more indistinguishable from human-written text. Finally, these AEs exhibit good transferability and can bring notable robustness improvement to the target model by adversarial training. © 2024 Copyright held by the owner/author(s).

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

HairDiffusion: vivid multi-colored hair editing via latent diffusion 24

HairDiffusion: vivid multi-colored hair editing via latent d...

引用

Proceedings of the 38th International Conference on Neural Information Processing systems

作者： Yu Zeng Yang Zhang Jiachen Liu Linlin Shen Kaijun Deng Weizhao He Jinbao Wang Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University and Shenzhen Institute of Artificial Intelligence and Robotics for Society and National Engineering Laboratory for Big Data System Computing Technology Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University and Guangdong Provincial Key Laboratory of Intelligent Information Processing

ISBN: (纸本)9798331314385

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

User-level failure detection and auto-recovery of parallel programs in HPC systems

引用

Frontiers of Computer Science 2021年第6期15卷 31-42页

作者： Guozhen ZHANG Yi LIU Hailong YANG Jun XU Depei QIAN State Key Laboratory of Software Development Environment Beijing 100191China Sino-German Joint Software Institute Beihang UniversityBeijing 100191China School of Computer Science and Engineering Beihang UniversityBeijing 100191China Science and Technology on Space System Simulation Laboratory Beijing Simulation Center Beijing 100854China

As the mean-time-between-failures(MTBF)continues to decline with the increasing number of components on large-scale high performance computing(HPC)systems,program failures might occur during the execution period with high *** successful execution of the HPC programs has become an issue that the unprivileged users should be *** the user perspective,if the program failure cannot be detected and handled in time,it would waste resources and delay the progress of program ***,the unprivileged users are unable to perform program state checking due to execution control by the job management system as well as the limited ***,automated tools for supporting user-level failure detection and autorecovery of parallel programs in HPC systems are *** paper proposes an innovative method for the unprivileged user to achieve failure detection of job execution and automatic resubmission of failed *** state checker in our method is encapsulated as an independent job to reduce interference with the user *** addition,we propose a dual-checker mechanism to improve the robustness of our *** implement the proposed method as a tool named automatic re-launcher(ARL)and evaluate it on the Tianhe-2 *** results show that ARL can detect the execution failures effectively on Tianhe-2 *** addition,the communication and performance overhead caused by ARL is *** good scalability of ARL makes it applicable for large-scale HPC systems.

关键词： high performance computing parallel program failure detection failure auto-recovery

来源：评论

学校读者我要写书评

暂无评论

Time sequential influence maximization algorithm based on neighbor node influence

引用

High Technology Letters 2022年第2期28卷 153-163页

作者： CHEN Jing QI Ziyi LIU Mingxin School of Information Science and Engineering Yanshan UniversityQinhuangdao 066004P.R.China Hebei Key Laboratory of Virtual Technology and System Integration Qinhuangdao 066004P R.China Hebei Key Laboratory of Software Engineering Qinhuangdao 066004P R.China College of Electronic and Information Engineering Guangdong Ocean UniversityZhanjiang 524088P.R.China

In view of the forwarding microblogging,secondhand smoke,happiness,and many other phenomena in real life,the spread characteristic of the secondary neighbor nodes in this kind of phenomenon and network scheduling is extracted,and sequence influence maximization problem based on the influence of neighbor nodes is proposed in this *** is,in the time sequential social network,the propagation characteristics of the second-level neighbor nodes are considered emphatically,and k nodes are found to maximize the information ***,the propagation probability between nodes is calculated by the improved degree estimation ***,the weighted cascade model(WCM) based on static social network is not suitable for temporal social ***,an improved weighted cascade model(IWCM) is proposed,and a second-level neighbors time sequential maximizing influence algorithm(STIM) is put forward based on node *** combines the consideration of neighbor nodes and the problem of overlap of influence scope between nodes,and makes it ***,the experiment verifies that STIM algorithm has stronger practicability,superiority in influence range and running time compared with similar algorithms,and is able to solve the problem of maximizing the timing influence based on the influence of neighbor nodes.

关键词： neighbor node influence time sequential social network influence maximization(IM) information propagation model

来源：评论

学校读者我要写书评

暂无评论

Multipath matching pursuit using a cross-validation technique for sparse direction-of-arrival estimation with an acoustic vector array

引用

Chinese Journal of Acoustics 2023年第2期42卷 153-170页

作者： TAN Peng HU Bo ZHANG Youwen WU Yuquan YANG Desen Acoustic Science and Technology Laboratory Harbin Engineering UniversityHarbin 150001 Key Laboratory of Marine Information Acquisition and Security(Harbin Engineering University) Ministry of Industry and Information TechnologyHarbin 150001 College of Underwater Acoustic Engineering Harbin Engineering UniversityHarbin 150001 School of Electronics and Information Jiangsu University of Science and TechnologyZhenjiang 212100 Science and Technology on Integrated Information System Laboratory Institute of SoftwareChinese Academy of SciencesBeijing 100190

High-resolution direction-of-arrival(DOA)estimations and the starboard ambiguity of moving underwater targets have always been key issues in underwater acoustic array signal *** with sound pressure arrays,vector arrays have natural advantages with respect to solving the starboard ambiguity problem and obtaining higher processing *** high-resolution DOA estimation methods such as Capon have disadvantages such as being unable to resolve coherent sources,requiring multiple snapshot processing,and being sensitive to array manifold ***-resolution DOA estimation and the starboard ambiguity of moving underwater targets have always been challenging research *** one hand,maneuvering underwater targets reduce the coherence time of the received signals,which ultimately leads to poor performance when using high-resolution DOA estimation technologies based on the covariance matrix of the received *** the other hand,traditional DOA estimation technologies based on sound pressure arrays have the problem of port and starboard ambiguity,which can be solved by maneuvering the sonar ***,maneuvering the sonar platform can impair the coherence of the received signal,on which some algorithms *** approach greatly limits the combat effectiveness and performance of the *** the aforementioned problems and taking advantage of the target sparsity,a cross-validation multipath matching pursuit technique based on the sparse DOA estimation of an acoustic vector array is proposed in this article for sonar *** proposed algorithm uses cross-validation technology to achieve a sparse DOA estimation with an unknown number of targets in a sonar observation *** with the conventional acoustic vector array-based Capon algorithm,the proposed algorithm can achieve a sparse DOA estimation and high-resolution capability with small numbers of snapshots or even single *** effectiveness of the proposed

关键词： multipath estimation underwater

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：