检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Chen, Tao Chen, Qiming Zheng, Qian Li, Zhishan Zhang, Ziyi Xie, Lei Su, Hongye State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou310027 China DAMO Academy Alibaba Group Hangzhou China College of Computer Science and Control Engineering Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China University of Michigan 500 S. State Street Ann ArborMI48109 United States

In this paper, a novel adaptive multi-scale time-frequency network (AMTFN) is proposed to provide high-resolution time-frequency representations for nonstationary signals. AMTFN is an end-to-end deep network, which firstly adaptively learns the comprehensive basis functions to produce time-frequency (TF) feature maps through multi-scale 1D convolutional kernels. Then, the channel attention mechanism is embedded into AMTFN to rescale the TF feature maps selectively. Thus, the subsequent residual encoder-decoder block’s energy concentration performance is greatly improved with these rescaled TF feature maps. Besides, this paper designs a new training strategy to elegantly enable the model to pay more attention to the intersections of instantaneous frequencies trajectories. In the end, a series of simulations as well as real-world cases is studied to demonstrated the effectiveness and advantages of the proposed method. © 2023, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

IPGRN: An Integrated Progressive Gated Refinement Network for Breast Tumor Analysis

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Dai, Zihao Huang, Guoheng Li, Yan He, Jianbin Yuan, Xiaochen Pun, Chi-Man Zhong, Guo Ling, Bingo Wing-Kuen Wu, Yaopan Li, Jiao Guangdong University of Technology School of Computer Science and Technology Guangzhou510006 China Shenzhen Polytechnic University School of Artificial Intelligence Shenzhen518055 China Faculty of Applied Sciences of the Macao Polytechnic University 999078 China Faculty of Science and Technology of the University of Macau 999078 China Guangdong University of Foreign Studies School of Information Science and Technology Guangzhou510006 China Guangdong University of Technology School of Information Engineering Guangzhou510006 China Sun Yat-sen University Cancer Center Guangdong Provincial Clinical Research Center for Cancer Department of Medical Imaging State Key Laboratory of Oncology in South China Guangzhou510060 China

The predictive analysis of disease indicators for breast tumor patients holds significant clinical relevance for physicians in diagnosis and treatment, and can benefit from the integration of consumer health technologies in smart healthcare systems. In clinical practice, vast amounts of monitoring data—such as mammography, breast ultrasound, and magnetic resonance imaging—are generated. Smart healthcare devices and remote monitoring systems facilitate the collection, sharing, and utilization of this data, supporting personalized healthcare. In this context, the selection and utilization of medical data features is a crucial task. While some models have demonstrated effectiveness in this area, they often suffer from limitations such as inadequate feature enhancement, insufficient cross-modal interaction, and poor generalization across diverse datasets. To address these issues, we propose an Integrated Progressive Gated Refinement Network (IPGRN). IPGRN is realized through the fusion of the Progressive Inheritance Shared (PIS) module with the Higher-Dimensional Hierarchical Gated Interactions (HD-HGI) module. This deep fusion network, employing a dual-path architecture, demonstrates outstanding performance in multimodal medical multi-index prediction, while exhibiting strong generalization capabilities. We present experimental results on five authentic datasets, empirically confirming the effectiveness of our proposed IPGRN. © 1975-2011 IEEE.

关键词： Personalized medicine

来源：评论

学校读者我要写书评

暂无评论

In Situ Iodide Passivation Toward Efficient CsPbI_(3) Perovskite Quantum Dot Solar Cells

引用

Nano-Micro Letters 2023年第10期15卷 28-39页

作者： Junwei Shi Ben Cohen‑Kleinstein Xuliang Zhang Chenyu Zhao Yong Zhang Xufeng Ling Junjun Guo Doo‑Hyun Ko Baomin Xu Jianyu Yuan Wanli Ma Department of Materials Science and Engineering Southern University of Science and TechnologyShenzhen 518055People’s Republic of China Institute of Functional Nano&Soft Materials(FUNSOM) Soochow University199 Ren‑Ai RoadSuzhou Industrial ParkSuzhou 215123People’s Republic of China Department of Electrical and Computer Engineering University of British Columbia2329 West MallVancouverBC V6T 1Z4Canada Department of Chemistry Sungkyunkwan UniversitySuwon 16419Republic of Korea Jiangsu Key Laboratory of Advanced Negative Carbon Technologies Soochow University199 Ren‑Ai RoadSuzhou Industrial ParkSuzhou 215123People’s Republic of China Jiangsu Key Laboratory for Carbon‑Based Functional Materials&Devices Soochow University199 Ren‑Ai RoadSuzhou Industrial ParkSuzhou 215123People’s Republic of China

All-inorganic CsPbI_3 quantum dots(QDs) have demonstrated promising potential in photovoltaic(PV) applications. However, these colloidal perovskites are vulnerable to the deterioration of surface trap states, leading to a degradation in efficiency and stability. To address these issues, a facile yet effective strategy of introducing hydroiodic acid(HI) into the synthesis procedure is established to achieve high-quality QDs and devices. Through an in-depth experimental analysis, the introduction of HI was found to convert PbI_2 into highly coordinated [PbI_m]~(2-m), enabling control of the nucleation numbers and growth kinetics. Combined optical and structural investigations illustrate that such a synthesis technique is beneficial for achieving enhanced crystallinity and a reduced density of crystallographic defects. Finally, the effect of HI is further reflected on the PV performance. The optimal device demonstrated a significantly improved power conversion efficiency of 15.72% along with enhanced storage stability. This technique illuminates a novel and simple methodology to regulate the formed species during synthesis, shedding light on ofurther understanding solar cell performance, and aiding the design of future novel synthesis protocols for high-performance optoelectronic devices.

关键词： CsPbI_(3)perovskite quantum dots In situ passivation Surface trap states Perovskite solar cell

来源：评论

学校读者我要写书评

暂无评论

A reachability-decidable petri net modeling method and its application to flexible manufacturing systems

A reachability-decidable petri net modeling method and its a...

引用

International Conference on Automation in Manufacturing, Transportation and Logistics (iCaMaL 2023)

作者： Yue Su Liang Qi MengChu Zhou Remigiusz Wiśniewski Faculty of Innovation Engineering Macau University of Science and Technology Macau People's Republic of China College of Computer Science and Engineering Shandong University of Science and Technology Qingdao People's Republic of China Institute of Control and Computation Engineering University of Zielona Góra Poland

ISBN: (数字)9781837242054

Petri nets (PNs) are graphical and mathematical tools used to model various discrete event systems and analyze their properties. Reachability is their fundamental property. When we use a state equation to determine a state’s (marking’s) reachability, the existence of legal firing sequences (LFSs) corresponding to nonnegative integer solutions (NISs) of the state equation needs to be determined. Our previous work has proposed an algorithm to determine the LFSs’ existence in polynomial time. However, when a state equation has an infinite number of NISs, we cannot check all NISs to determine a marking’s reachability. Hence, this work studies the relationship between the structure of an ordinary PN and the number of NISs of its state equation. Then, a method is proposed to modify the structure of the PN such that the state equation has no more than one NIS. The modified PN is used as the final model of the system, which maintains the functions of its modeled system. Its reachability can be determined in polynomial time. This work shows the application of the proposed method to a flexible manufacturing system’s modeling and analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Survey of security, performance, and profitability of Monero: a browser-based cryptocurrency

Survey of security, performance, and profitability of Monero...

引用

Electrical, computer, Communications and Mechatronics engineering (ICECCME), International Conference on

作者： Floarea Pitu Nicoleta Cristina Gaitan Faculty of Electrical Engineering and Computer Science Stefan cel Mare University of Suceava Suceava Romania Faculty of Electrical Engineering and Computer Science Stefan cel Mare University of Suceava Integrated Center for Research Development and Innovation in Advanced Materials Nanotechnologies and Distributed Systems for Fabrication and Control (MANSiD) Suceava Romania

Information is the key to success in every domain; this statement also applies to cryptocurrencies and blockchain domains. Beginning with Bitcoin back in 2009, which the anonymous Japanese Satoshi Nakamoto launched, blockchain technology emerged. This technology has revolutionized and continues to do so in digital transactions. In addition, this technology led to the further development of other cryptocurrencies that are active at these moments on the market. One class of cryptocurrencies obtained differently from classical bitcoin is those obtained due to web-based mining. The most known coins of this type are Monero, Dash, or Electroneum. This paper aims to analyze the web-based mining process of Monero and the whole process’s security. In addition, we want to explore the performance of the mining processes used in the user’s web browser. Moreover, finally, we aim to research the profitability of coins obtained due to web-browser mining, having as an object of study the cryptocurrency Monero.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Haplotype-resolved Chinese male genome assembly based on high-fidelity sequencing

引用

Fundamental Research 2022年第6期2卷 946-953页

作者： Xiaofei Yang Xixi Zhao Shoufang Qu Peng Jia Bo Wang Shenghan Gao Tun Xu Wenxin Zhang Jie Huang Kai Ye Genome Institute the First Affiliated Hospital of Xi'an Jiaotong UniversityXi'an 710061ShaanxiChina School of Computer Science and Technology Faculty of Electronic and Information EngineeringXi'an Jiaotong UniversityXi'an 710049ShaanxiChina MOE Key Lab for Intelligent Networks&Networks Security Faculty of Electronic and Information EngineeringXi'an Jiaotong UniversityXi'an 710049ShaanxiChina National Institutes for food and drug Control(NIFDC) No.2Tiantan XiliDongcheng DistrictBeijing 102629China School of Automation Science and Engineering Faculty of Electronic and Information EngineeringXi'an Jiaotong UniversityXi'an 710049ShaanxiChina School of Life Science and Technology Xi'an Jiaotong UniversityXi'an 710049ShaanxiChina Faculty of Science Leiden UniversityLeidenThe Netherlands

The advantages of both the length and accuracy of high-fidelity(HiFi)reads enable chromosome-scale haplotype-resolved genome *** this study,we sequenced a cell line named HJ,established from a Chinese Han male individual by using HiFi and *** assembled two high-quality haplotypes of the HJ genome(haplotype 1(H1):3.1 Gb,haplotype 2(H2):2.9 Gb).The continuity(H1:contig N50=28.2 Mb,H2:contig N50=25.9 Mb)and completeness(BUSCO:H1=94.9%,H2=93.5%)are substantially better than those of other Chinese genomes,for example,HX1,NH1.0,and *** comparing HJ genome with GRCh38,we reported the mutation landscape of HJ and found that 176 and 213 N-gaps were filled in H1 and H2,*** addition,we detected 12.9 Mb and 13.4 Mb novel sequences containing 246 and 135 protein-coding genes in H1 and H2,*** results demonstrate the advantages of HiFi reads in haplotype-resolved genome assembly and provide two high-quality haplotypes of a potential Chinese genome as a reference for the Chinese Han population.

关键词： Genome assembly HiFi reads Human genome Haplotype-resolved Chinese Han Mutation landscape

来源：评论

学校读者我要写书评

暂无评论

FD-SOS: Vision-Language Open-Set Detectors for Bone Fenestration and Dehiscence Detection from Intraoral Images

arXiv

引用

arXiv 2024年

作者： Elbatel, Marawan Liu, Keyuan Yang, Yanqi Li, Xiaomeng Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong Division of Paediatric Dentistry and Orthodontics Faculty of Dentistry The University of Hong Kong Hong Kong HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute Shenzhen China

Accurate detection of bone fenestration and dehiscence (FD) is crucial for effective treatment planning in dentistry. While cone-beam computed tomography (CBCT) is the gold standard for evaluating FD, it comes with limitations such as radiation exposure, limited accessibility, and higher cost compared to intraoral images. In intraoral images, dentists face challenges in the differential diagnosis of FD. This paper presents a novel and clinically significant application of FD detection solely from intraoral images. To achieve this, we propose FD-SOS, a novel open-set object detector for FD detection from intraoral images. FD-SOS has two novel components: conditional contrastive denoising (CCDN) and teeth-specific matching assignment (TMA). These modules enable FD-SOS to effectively leverage external dental semantics. Experimental results showed that our method outperformed existing detection methods and surpassed dental professionals by 35% recall under the same level of precision. Code is available at: https: //***/xmed-lab/FD-SOS. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Reparameterization-Based Textual Adversarial Attack Approach with Multi-Objective Geometric Loss

SSRN

引用

SSRN 2022年

作者： Dong, Huoyuan Wan, Shaohua Dong, Jialiang Yuan, Shuai Guan, Zhitao School of Control and Computer Engineering North China Electric Power University Beijing102206 China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Shenzhen518110 China Brock University ON Canada

Maliciously designed adversarial samples entail severe security threats to the Pre-trained Language Models (PLMs), which are widely deployed in the natural language processing systems. Such systems would benefit from the research line on adversarial sample attacks by improving the adversarial robustness. Most existing literature focuses on achieving a high success rate of attacks in the vanilla model. They do not, however, consider the samples’ semantic consistency and fluency. Furthermore, computational complexity is another issue due to the frequent search on perturbations and queries on target models. In this study, we propose a simple yet effective adversarial attack framework by using the reparameterization methods on discreate token sequence. Particularly, a parameterized adversarial distribution based on the Gumbel distribution is optimized through perplexity regularization and embedding-based constraint, such that adversarial perturbations is obtained. In addition, we introduce the multi-objective geometric loss to address the learning imbalance issue on multiple tasks during optimization. To accommodate the pure black-box scenario, we further extend our framework by incorporating GPT-2 into our framework. Detailed experimental studies of the proposed work have been carried out using six benchmark datasets and four SOTA fine-tuned models. The results demonstrate significant reduction on the accuracy of the target model, while preserving fluency, semantic consistency and similarity under human evaluations. Finally in the hard label black-box settings, high level of performance can also be achieved by our approach with fewer queries in comparison with baseline methods. © 2022, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Sublinear-time reductions for big data computing

arXiv

引用

arXiv 2021年

作者： Gao, Xiangyu Li, Jianzhong Miao, Dongjing Department of Computer Science and Technology Harbin Institute of Technology Harbin China Faculty of Computer Science and Control Engineering Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China

With the rapid popularization of big data, the dichotomy between tractable and intractable problems in big data computing has been shifted. Sublinear time, rather than polynomial time, has recently been regarded as the new standard of tractability in big data computing. This change brings the demand for new methodologies in computational complexity theory in the context of big data. Based on the prior work for sublinear-time complexity classes [9], this paper focuses on sublineartime reductions specialized for problems in big data computing. First, the pseudo-sublinear-time reduction is proposed and the complexity classes P and PsT are proved to be closed under it. To establish PsT-intractability for certain problems in P, we find the first problem in P \ PsT. Using the pseudo-sublinear-time reduction, we prove that the nearest edge query is in PsT but the algebraic equation root problem is not. Then, the pseudopolylog-time reduction is introduced and the complexity class PsPL is proved to be closed under it. The PsT-completeness under it is regarded as an evidence that some problems can not be solved in polylogarithmic time after a polynomial-time preprocessing, unless PsT = PsPL. We prove that all PsT-complete problems are also P-complete, which gives a further direction for identifying PsT-complete problems. Copyright © 2021, The Authors. All rights reserved.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Feature Selection for Detecting ICMPv6-Based DDoS Attacks Using Binary Flower Pollination Algorithm

引用

computer Systems science & engineering 2023年第10期47卷 553-574页

作者： Adnan Hasan Bdair Aighuraibawi Selvakumar Manickam Rosni Abdullah Zaid Abdi Alkareem Alyasseri Ayman Khallel Dilovan Asaad Zebari Hussam Mohammed Jasim Mazin Mohammed Abed Zainb Hussein Arif National Advanced IPv6 Centre(NAv6) Universiti Sains MalaysiaPenang11800Malaysia Baghdad College of Economic Sciences University BaghdadIraq School of Computer Sciences Universiti Sains MalaysPenang11800Malaysia Information Technology Research and Development Center University of KufaNajafIraq College of Engineering University of Warith Al-AnbiyaaKarbalaIraq Faculty of Computing and Informatics Universiti Malaysia SabahSabahMalaysia Business Administration College of Administration and Financial SciencesImam Ja’afar Al-Sadiq UniversityBaghdad10001Iraq College of Computer Science and Information Technology University of AnbarRamadi AnbarIraq Department of Computer Science College of ScienceNawroz UniversityDuhok42001Kurdistan RegionIraq

Internet Protocol version 6(IPv6)is the latest version of IP that goal to host 3.4×10^(38)unique IP addresses of devices in the ***6 has introduced new features like Neighbour Discovery Protocol(NDP)and Address Auto-configuration ***6 needed several protocols like the Address Auto-configuration Scheme and Internet control Message Protocol(ICMPv6).IPv6 is vulnerable to numerous attacks like Denial of Service(DoS)and Distributed Denial of Service(DDoS)which is one of the most dangerous attacks executed through ICMPv6 messages that impose security and financial ***,an Intrusion Detection System(IDS)is a monitoring system of the security of a network that detects suspicious activities and deals with amassive amount of data comprised of repetitive and inappropriate features which affect the detection rate.A feature selection(FS)technique helps to reduce the computation time and complexity by selecting the optimum subset of *** paper proposes a method for detecting DDoS flooding attacks(FA)based on ICMPv6 messages using a Binary Flower PollinationAlgorithm(BFPA-FA).The proposed method(BFPA-FA)employs FS technology with a support vector machine(SVM)to identify the most relevant,influential ***,The ICMPv6-DDoS dataset was used to demonstrate the effectiveness of the proposed method through different attack *** results show that the proposed method BFPAFA achieved the best accuracy rate(97.96%)for the ICMPv6 DDoS detection with a reduced number of features(9)to half the total(19)*** proven proposed method BFPA-FAis effective in the ICMPv6 DDoS attacks via IDS.

关键词： IPv6 ICMPv6 DDoS feature selection flower pollination algorithm anomaly detection

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：