检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第10期5卷 5340-5351页

作者： Chen, Lili Gan, Wensheng Chen, Chien-Ming Tongji University Department of Computer Science and Technology Shanghai200082 China Jinan University College of Cyber Security Guangzhou510632 China Pazhou Laboratory Guangzhou510330 China Nanjing University of Information Science and Technology School of Artificial Intelligence Nanjing210044 China

The goal of high-utility sequential pattern mining (HUSPM) is to efficiently discover profitable or useful sequential patterns in a large number of sequences. However, simply being aware of utility-eligible patterns is insufficient for making predictions. To compensate for this deficiency, high-utility sequential rule mining (HUSRM) is designed to explore the confidence or probability of predicting the occurrence of consequence sequential patterns based on the appearance of premise sequential patterns. It has numerous applications, such as product recommendation and weather prediction. However, the existing algorithm, known as HUSRM, is limited to extracting all eligible rules while neglecting the correlation between the generated sequential rules. To address this issue, we propose a novel algorithm called correlated high-utility sequential rule miner (CoUSR) to integrate the concept of correlation into HUSRM. The proposed algorithm requires not only that each rule be correlated but also that the patterns in the antecedent and consequent of the high-utility sequential rule be correlated. The algorithm adopts a utility-list structure to avoid multiple database scans. Additionally, several pruning strategies are used to improve the algorithm's efficiency and performance. Based on several real-world datasets, subsequent experiments demonstrated that CoUSR is effective and efficient in terms of operation time and memory consumption. All codes are accessible on GitHub: https://***/DSI-Lab1/CoUSR. © 2020 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Optical Microsphere Nano-Imaging:Progress and Challenges

引用

Engineering 2024年第5期36卷 102-123页

作者： Guangxing Wu Minghui Hong Department of Electrical and Computer Engineering National University of SingaporeSingapore 117576Singapore Pen-Tung Sah Institute of Micro-Nano Science and Technology Xiamen UniversityXiamen 361005China Innovation Laboratory for Sciences and Technologies of Energy Materials of Fujian Province(IKKEM) Xiamen 361005China

The optical diffraction effect imposes a radical obstacle preventing conventional optical microscopes from achieving an imaging resolution beyond the Abbe diffraction limit and thereby restricting their usage in a multitude of nanoscale *** the past decade,the optical microsphere nanoimaging technique has been demonstrated to be a cost-effective solution for overcoming the diffraction limit and has achieved an imaging resolution of up to about k6k8 in a real-time and label-free manner,making it highly competitive among numerous super-resolution imaging *** this review,we summarize the underlying nano-imaging mechanisms of the microsphere nanoscope and key advancements aimed at imaging performance enhancement:first,to change the working environment or modify the peripheral hardware of a single microsphere nanoscope at the system level;second,to compose the microsphere compound lens;and third,to engineer the geometry or ingredients of *** also analyze challenges yet to be overcome in optical microsphere nano-imaging,followed by an outlook of this technique.

关键词： Microsphere Nano-imaging Virtual imaging Microsphere compound lens Engineered microsphere

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Subgraph Extraction: Methods, Applications and Challenges 49th

Machine Learning for Subgraph Extraction: Methods, Applicati...

引用

49th International Conference on Very Large Data Bases, VLDB 2023

作者： Yow, Kai Siong Liao, Ningyi Luo, Siqiang Cheng, Reynold School of Computer Science and Engineering Nanyang Technological University Singapore Department of Computer Science Guangdong-Hong Kong-Macau Joint Laboratory HKU Musketeers Foundation Institute of Data Science The University of Hong Kong Hong Kong

Subgraphs are obtained by extracting a subset of vertices and a subset of edges from the associated original graphs, and many graph properties are known to be inherited by subgraphs. Subgraphs can be applied in many areas such as social networks, recommender systems, biochemistry and fraud discovery. Researchers from various communities have paid a great deal of attention to investigate numerous subgraph problems, by proposing algorithms that mainly extract important structures of a given graph. There are however some limitations that should be addressed, with regard to the efficiency, effectiveness and scalability of these traditional algorithms. As a consequence, machine learning techniques—one of the most latest trends—have recently been employed in the database community to address various subgraph problems considering that they have been shown to be beneficial in dealing with graphrelated problems. We discuss learning-based approaches for four well known subgraph problems in this tutorial, namely subgraph isomorphism, maximum common subgraph, community detection and community search problems. We give a general description of each proposed model, and analyse its design and performance. To allow further investigations on relevant subgraph problems, we suggest some potential future directions in this area. We believe that this work can be used as one of the primary resources, for researchers who intend to develop learning models in solving problems that are closely related to subgraphs. © 2023, VLDB Endowment. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

A High-Concentration Edge-Nitrogen-Doped Porous Carbon Anode via Template Free Strategy for High-Performance Potassium-Ion Hybrid Capacitors

引用

Energy Material Advances 2024年第1期5卷 517-526页

作者： Zhen Pan Ke Li Lidong Sun Yang Li Zuodong Zhang Yitai Qian Wei Chen Department of Applied Chemistry School of Chemistry and Materials ScienceHefei National Research Center for Physical Sciences at the MicroscaleUniversity of Science and Technology of ChinaHefeiChina Key Laboratory of Agricultural Sensors Ministry of Agriculture and Rural AffairsAnhui Provincial Key Laboratory of Smart Agricultural Technology and EquipmentSchool of Information and ComputerAnhui Agricultural UniversityHefeiChina

Developing facile and economical strategies to fabricate nitrogen-doped porous carbon anode is desirable for dual-carbon potassium ion hybrid capacitors(PIHCs).Here,a high-concentration edge-nitrogen-doped porous carbon(NPC)anode is synthesized by a template-free strategy,in which the total content of pyrrolic nitrogen and pyridinic nitrogen accounts for more than 80%of the nitrogen *** a result,the NPC anode displays a capacity of 315.4 mA h g^(−1)at a current rate of 0.1 A g^(−1)and 189.1 mA h g^(−1)at 5 A g^(−1).Ex situ characterizations and density functional theory calculations demonstrate the high-concentration edge-nitrogen doping enhances K^(+)adsorption and electronic conductivity of carbon materials,resulting in good electrochemical *** assembled NPC//CMK-3 PIHC delivers an energy density of 71.1 W h kg^(−1)at a power density of 771.9 W kg^(−1)over 8,000 cycles.

关键词： potassium ion hybrid capacitors pihcs herea template free strategy pyrrolic nitrogen pyridinic nitrogen high concentration edge nitrogen doped porous carbon porous carbon anode density functional theory calculations potassium ion hybrid capacitors

来源：评论

学校读者我要写书评

暂无评论

New spotted hyena intelligent algorithm for solving small-scale CVRP problem

引用

Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of science and Technology (Natural science Edition) 2024年第2期52卷 77-83页

作者： Wang, Xiaofeng Mo, Chunhui Zhang, Lin Yang, Lan Country Department of Computer Science North Minzu University Yinchuan750021 China The Key Laboratory of Images Graphics Intelligent Processing of State Ethnic Affairs Commission North Minzu University Yinchuan750021 China

A new spotted hyena intelligent optimizer (ISHO) algorithm incorporating multi-strategy improvement was proposed for the characteristics of the capacitated vehicle routing problem (CVRP).A combination of K-means clustering and greedy selection was used for the initialization method. Based on the standard spotted hyena optimizer, the spiral exploration mechanism in the whale optimization algorithm was incorporated to enhance the global search capability of the ***, a variational operator, two crossover operators and reverse operation methods were *** spiral exploration was combined with the cross variational operator to redefine the spotted hyena optimizer in discrete ***, the computational results of ISHO in four different types of a total of 24 international benchmark cases were experimentally compared and which was analyzed with other intelligent optimization *** results show that the ISHO algorithm effectively avoids the drawbacks of falling into local optimum and low quality solutions, and has certain superiority for solving small-scale CVRP problems. © 2024 Huazhong University of science and Technology. All rights reserved.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Context Unaware Knowledge Distillation for Image Retrieval 1

引用

International Conference on computer Vision and Machine Intelligence, CVMI 2022

作者： Reddy, Bytasandram Yaswanth Dubey, Shiv Ram Sanodiya, Rakesh Kumar Karn, Ravi Ranjan Prasad Department of Computer Science and Engineering Indian Institute of Information Technology Sri City Chittoor India Computer Vision and Biometrics Laboratory Indian Institute of Information Technology Allahabad India

ISBN: (数字)9789811978678

ISBN: (纸本)9789811978661

Existing data-dependent hashing methods use large backbone networks with millions of parameters and are computationally complex. Existing knowledge distillation methods use logits and other features of the deep (teacher) model and as knowledge for the compact (student) model, which requires the teacher’s network to be fine-tuned on the context in parallel with the student model on the context. Training teacher on the target context requires more time and computational resources. In this paper, we propose context unaware knowledge distillation that uses the knowledge of the teacher model without fine-tuning it on the target context. We also propose a new efficient student model architecture for knowledge distillation. The proposed approach follows a two-step process. The first step involves pre-training the student model with the help of context unaware knowledge distillation from the teacher model. The second step involves fine-tuning the student model on the context of image retrieval. In order to show the efficacy of the proposed approach, we compare the retrieval results, no. of parameters, and no. of operations of the student models with the teacher models under different retrieval frameworks, including deep cauchy hashing (DCH) and central similarity quantization (CSQ). The experimental results confirm that the proposed approach provides a promising trade-off between the retrieval results and efficiency. The code used in this paper is released publicly at https://***/satoru2001/CUKDFIR. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Stationary, continuous, and discrete wavelet-based approach for secure medical image transmission

引用

Research on Biomedical Engineering 2023年第1期39卷 167-178页

作者： Sayah, Moad Med Redouane, Kafi Med Amine, Khaldi Electrical Engineering Laboratory Department of Electronics Faculty of Sciences and Technology University of Kasdi Merbah Ouargla30000 Algeria Computer Science Department Faculty of Sciences and Technology University of Kasdi Merbah Ouargla30000 Algeria

Purpose: Watermarking is one of the techniques used to protect multimedia data, and images in particular, from malicious attacks by inserting a signature into these images. However, traditional watermarking schemes encounter limitations for sensitive images such as medical images. Methods: In this work, a robust and blind watermarking approach is proposed to secure medical images exchanged in telemedicine. Marking medical images allows precise authentication of the patient and avoids confusing scans and thus avoiding diagnostic errors that can have serious consequences. In this approach, the frequency content of the image is acquired using three different transforms. Schur decomposition is then applied to the low-frequency sub-bands. Finally, the obtained upper triangular matrix values are modifier to integrate the watermark bits. Result and conclusion: Imperceptibility and robustness experimental results show that the proposed methods adequately maintain a significant quality of watermarked images and are remarkably robust against several conventional attacks. Indeed, the average peak signal-to-noise ratio (PSNR) obtained is 44.90 dB which proves that the integration process generates few distortions to the original image. For the robustness, the obtained results show that the watermark is resistant to the most common attacks used in watermarking with a normalized cross correlation rate higher than 0.9 for the majority of the attacks. © 2023, The Author(s), under exclusive licence to The Brazilian Society of Biomedical Engineering.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Improving ECAPA-TDNN Performance with Coordinate Attention

引用

Journal of Shanghai Jiaotong University (science) 2024年 1-7页

作者： Liu, Shuanghong Song, Zhida He, Liang School of Computer Science and Technology Xinjiang University Urumqi830017 China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China Department of Electronic Engineering and Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

The current mainstream networks, such as squeeze and excitation residual neural network (SE-ResNet) and emphasized channel attention, propagation and aggregation based time delay neural network (ECAPA-TDNN), enhance the capability of speaker embedding extractors to extract more discriminative speaker embeddings by incorporating squeeze and excitation (SE) attention within the convolutional blocks. However, the SE attention focuses solely on encoding inter-channel information, overlooking the importance of spatial positional information and time-frequency information, which are crucial for the model’s performance. In this paper, we first experimentally compare the effectiveness of several mainstream attention mechanisms in the computer vision domain for the ECAPA-TDNN model. Next, we focus on the substantial improvements that coordinate attention (CA) brings to the ECAPA-TDNN model. The introduction of CA can help the model embed time-frequency information into the channel representation. Even without using AS-Norm, our proposed model achieves relative reductions of about 5.3% equal error rate (EER) and 5.5% minimum detection cost function (minDCF) on both the Voxceleb-O and Voxceleb-H test sets compared to the ECAPA-TDNN baseline model. In addition, the EER is relatively reduced by 9.46% on the CN-Celeb1 test set. This result strongly demonstrates that the CA module can effectively improve the generalization ability of the ECAPA-TDNN model. © Shanghai Jiao Tong University 2024.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Fast target-aware learning for few-shot video object segmentation

引用

science China(Information sciences) 2022年第8期65卷 71-86页

作者： Yadang CHEN Chuanyan HAO Zhi-Xin YANG Enhua WU Engineering Research Center of Digital Forensics Ministry of EducationSchool of Computer and SoftwareNanjing University of Information Science and Technology School of Education Science and Technology Nanjing University of Posts and Telecommunications State Key Laboratory of Internet of Things for Smart City Department of Electromechanical EngineeringUniversity of Macau State Key Laboratory of Computer Science Institute of SoftwareUniversity of Chinese Academy of Sciences Faculty of Science and Technology University of Macau

Few-shot video object segmentation(FSVOS) aims to segment a specific object throughout a video sequence when only the first-frame annotation is given. In this study, we develop a fast target-aware learning approach for FSVOS, where the proposed approach adapts to new video sequences from its firstframe annotation through a lightweight procedure. The proposed network comprises two models. First, the meta knowledge model learns the general semantic features for the input video image and up-samples the coarse predicted mask to the original image size. Second, the target model adapts quickly from the limited support set. Concretely, during the online inference for testing the video, we first employ fast optimization techniques to train a powerful target model by minimizing the segmentation error in the first frame and then use it to predict the subsequent frames. During the offline training, we use a bilevel-optimization strategy to mimic the full testing procedure to train the meta knowledge model across multiple video *** proposed method is trained only on an individual public video object segmentation(VOS) benchmark without additional training sets and compared favorably with state-of-the-art methods on DAVIS-2017, with a J &F overall score of 71.6%, and on YouT ubeVOS-2018, with a J &F overall score of 75.4%. Meanwhile,a high inference speed of approximately 0.13 s per frame is maintained.

关键词： video object segmentation few-shot target-aware meta knowledge bilevel-optimization

来源：评论

学校读者我要写书评

暂无评论

Literature Review on Recommender Systems: Techniques, Trends and Challenges 22nd

Literature Review on Recommender Systems: Techniques, Trends...

引用

22nd International Conference on Hybrid Intelligent Systems, HIS 2022 and the 18th International Conference on Information Assurance and Security, IAS 2022

作者： Fkih, Fethi Rhouma, Delel Department of Computer Science College of Computer Qassim University Buraydah Saudi Arabia MARS Research Laboratory LR17ES05 University of Sousse Sousse Tunisia

ISBN: (纸本)9783031274084

Nowadays, Recommender Systems (RSs) have become a necessity especially with the rapid increasing of the numerical data volume. In fact, internet’s users need an automatic system that help them to filter the huge flow of information provided bay websites or even by research engines. Therefore, a Recommender System can be seen as an Information Retrieval system that can respond to an implicit user’s query. The RS draw this implicit user’s query based on a user’s profile that can be created using some semantic or statistic knowledge. In this paper, we provide an in-depth literature review on main RS approaches. Basically, RS’s techniques can be divide into three classes: collaborative Filtering-based, Content-based and hybrid approaches. Also, we show the challenges and the potential trends in this domain. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Collaborative filtering

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：