检索结果-内蒙古大学图书馆

Quantifying the weakness of ties with hierarchy-based link centrality

science China(Information sciences) 2025年

作者： Jianhong MOU Longyun WANG Kang WEN Bitao DAI Suoyi TAN Fredrik LILJEROS Petter HOLME Xin LU College of Systems Engineering National University of Defense Technology Department of Sociology Stockholm University Department of Computer Science Aalto University Center for Computational Social Science Kobe University

Quantifying the significance of ties in preserving network connectivity is crucial for identifying weak ties, which often serve as bridges between communities, and for detecting community structures. However, accurately characterizing network connectivity and formalizing the relationship between weak ties and communities remain challenging. In this study, we introduce hierarchy-based link centrality(HLC), a novel metric based on the dissimilarity between the original network and its contracted version, where the terminal nodes of links merge and connect to all their neighbors. This dissimilarity is quantified by variations in the network hierarchy, specifically the nodal distance distributions. In addition to the experiments on weak tie identification and link-based network disintegration, we develop a link-based community detection(LCD) approach that focuses on optimal link ranking to elucidate community structures. Experiments across various networks demonstrate that HLC excels in identifying weak ties, achieving a 2.9% higher accuracy than the second-best metric. It also outperforms others in detecting critical link combinations for network disintegration, reducing the average size of the giant connected component by 7.2% compared to the suboptimal counterpart. Furthermore, HLC enhances community detection, achieving optimal partitioning with an average 5.7% improvement in modularity over five other indices. These results highlight the effectiveness of HLC in quantifying weak ties and suggest broad applications for this innovative approach in network analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhance Performance of Ad-hoc Search via Prompt Learning 1

引用

28th China Conference on Information Retrieval, CCIR 2022

作者： Yang, Shenghao Liu, Yiqun Xie, Xiaohui Zhang, Min Ma, Shaoping Department of Computer Science and Technology Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

ISBN: (数字)9783031247552

ISBN: (纸本)9783031247545

Recently, pre-trained language models (PTM) have achieved great success on ad hoc search. However, the performance decline in low-resource scenarios demonstrates the capability of PTM has not been inspired fully. As a novel paradigm to apply PTM to downstream tasks, prompt learning is a feasible scheme to boost PTM’s performance by aligning the pre-training task and downstream task. This paper investigates the effectiveness of the standard prompt learning paradigm on the ad hoc search task. Based on various PTMs, two types of prompts are tailored for the ad hoc search task. Overall experimental results on the MS Marco dataset show the credible better performance of our prompt learning method than fine-tuning based methods and another previous prompt learning based model. Experiments conducted in various resource scenarios show the stability of prompt learning. RoBERTa and T5 deliver better results compared to BM25 using 100 training queries utilizing prompt learning, while fine-tuning based methods need more data. Further analysis shows the significance of the uniformity of tasks’ format and adding continuous tokens into training in our prompt learning method. © 2023, Springer Nature Switzerland AG.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Esophageal cancer detection in barium esophagram using deformable convolutional network and attention module

Esophageal cancer detection in barium esophagram using defor...

引用

2024 International Conference on Future of Medicine and Biological Information Engineering, MBIE 2024

作者： Pei, Chengdan Zhang, Wenqian She, Yifei Xu, Shengzhou Network Information Center Wuhan Institute of Technology Wuhan430205 China College of Computer Science South-Central Minzu University Wuhan430074 China

ISBN: (纸本)9781510682825

Esophageal cancer is the sixth leading cause of cancer-related mortality worldwide. Barium esophagram is an inexpensive, noninvasive, and widely available procedure. However, the variation in tumor size, the interference of surrounding tissues, and esophageal deformation make tumor detection very challenging. This paper proposes a novel algorithm for detecting esophageal cancer, consisting of a detection network and a classification network. A deformable residual bottleneck block is proposed to replace the residual bottleneck block in ResNet50 to sample the deformed esophagus adaptively. The improved ResNet50 is used as the backbone network of the detection network, which is combined with FPN network to predict tumors of various sizes. Then, regions of interest detected from each image of the barium esophagram by the detection network are used as the input of the classification network. The attention module CBAM is introduced into the classification network to enhance the significance of the esophageal region, and improve the classification accuracy. The algorithm is evaluated on 40 positive (1166 images) and 53 negative cases (1547 images), the accuracy of the algorithm on positive and negative cases are 100% (40/40) and 84.90% (45/53) respectively. The experiment demonstrates that our proposed method yields promising results with the barium esophagram dataset. © 2024 SPIE.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

An Early Detection of Tomato Plant Disease with Deep Reinforcement Learning and CNN 5th

An Early Detection of Tomato Plant Disease with Deep Reinfor...

引用

5th International Symposium on Signal and Image Processing, ISSIP 2024

作者： Singh, Jagendra Saraswat, Mala Ramesh, Gopisetty Alsahlanee, Abbas Thajeel Rhaif Shaik, Nazeer Murugesan, Ashok School of Computer Science Engineering and Technology Bennett University Greater Noida India School of Computer Science Engineering & Technology Bennett University Greater Noida India Department of EIE CVR College of Engineering Telangana Ibrahimpatnam India Development and Continuous Education Center University of Thi-Qar Thi-Qar Iraq Department of Computer Science & Engineering Srinivasa Ramanujan Institute of Technology Autonomous Anantapur India Department of Computer Science and Engineering Rajalakshmi Institute of Technology Kuthambakkam India

ISBN: (纸本)9789819795147

Machine learning models have been tested in the current research for detecting and classifying tomato diseases at their early stages. This is one of the core tasks of modern agriculture, being extremely beneficial in maintaining the health and, accordingly, the production of tomatoes. In order to achieve this, a dataset of 3450 images was totaled, containing both the diseased and healthy leaves of tomato. The dataset was split with a 70% portion for training and the rest 30% for testing. Therefore, the current research seeks to train and evaluate the performance of several machine learning models, including Convolutional Neural networks (CNN), K-Nearest Neighbors (KNN), Recurrent Neural networks (RNN), and VGG-16 architecture;the results showed that the CNN model had the highest measure over the precision, recall, F1 score, and accuracy that averaged over 96.8%, 96.5%, 96.6%, and 96.77%, respectively. The KNN model showed particularly high performance over the metrics of interest with precision, recall, F1 score, and accuracy of 94.3%, 94.0%, 94.1%, and 94.32%, respectively. The RNN model depicted some excellent indicators that pointed to the ability to catch the sequential dependencies with a precision, recall, F1 score, and accuracy of 88.2%, 83.5%, 85.7%, and 85.60%, respectively, which was still lower than CNN and KNN. Finally, the VGG-16 architecture showed quite competitive results over the precision, recall, F1 score, and accuracy—91.7%, 93.2%, 92.4%, and 92.20%, respectively. Therefore, it is evident that the current research provided clear evidence that the employment of ML was effective as pertaining to the accurate detection and classification of the tomato diseases with the CNN model displaying robustness and being highly potential. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

FreeNet: Liberating Depth-Wise Separable Operations for Building Faster Mobile Vision Architectures 39

FreeNet: Liberating Depth-Wise Separable Operations for Buil...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Yu, Hao Chen, Haoyu Peng, Wei Cheng, Xu Zhao, Guoying Center for Machine Vision and Signal Analysis University of Oulu Finland Department of Psychiatry and Behavioral Sciences Stanford University United States School of Computer Science Nanjing University of Information Science and Technology China Department of Computer Science Aalto University Finland

ISBN: (纸本)157735897X

In the pursuit of efficient vision architectures, substantial efforts have been devoted to optimizing operator efficiency. Depth-wise separable operators, such as DWConv, are found cheap in both FLOPs and parameters. As a result, they are increasingly incorporated into efficient backbones, trading for deeper and wider architectures to enhance performance. However, separable operators are not really fast on devices due to the discontinuous memory access requirements. In this paper, we propose FreeNets, a family of simple and efficient backbones that free the separable operation to further accelerate the running speed. We introduce sparse sampling mixers (S2-Mixer) to supersede existing separable token mixers. The S2-Mixer samples multiple segments of partially continuous signals across spatial and channel dimensions for convolutional processing, achieving extremely fast on-device speed. The sparse sampling also enables S2-Mixer to capture long-range pixel relationships from dynamic receptive fields. Furthermore, we introduce a Shift Feed-Forward network (ShiftFFN) as a faster alternative to existing channel mixers. It utilizes a shift neck architecture that aggregates global information to shift features, enabling faster channel mixing while incorporating global pixel information. Extensive experiments demonstrate that FreeNet offers a superior accuracy-efficiency tradeoff compared to the latest efficient models. On ImageNet-1k, FreeNet-S2 outperforms the StarNet-S4 by 0.4% in top-1 accuracy, while running around 40% faster on desktop GPU and 15% faster on Mobile GPU. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Memory architecture

来源：评论

学校读者我要写书评

暂无评论

Residual Scheduling: A New Reinforcement Learning Approach to Solving Job Shop Scheduling Problem

引用

IEEE Access 2024年 12卷 14703-14718页

作者： Ho, Kuo-Hao Cheng, Jui-Yu Wu, Ji-Han Chiang, Fan Chen, Yen-Chi Wu, Yuan-Yu Wu, I-Chen National Yang Ming Chiao Tung University Department of Computer Science Hsinchu30010 Taiwan Academia Sinica Research Center for Information Technology Innovation Taipei11529 Taiwan

Job-shop scheduling problem (JSP) is a mathematical optimization problem widely used in industries like manufacturing, and flexible JSP (FJSP) is also a common variant. Since they are NP-hard, it is intractable to find the optimal solution for all cases within reasonable times. Thus, it becomes important to develop efficient heuristics to solve JSP/FJSP. A kind of method of solving scheduling problems is construction heuristics, which constructs scheduling solutions via heuristics. Recently, many methods for construction heuristics leverage deep reinforcement learning (DRL) with graph neural networks (GNN). In this paper, we propose a new approach, named residual scheduling, to solving JSP/FJSP. In this new approach, we remove irrelevant machines and jobs such as those finished, such that the states include the remaining (or relevant) machines and jobs only. Our experiments show that our approach reaches state-of-the-art (SOTA) among all known construction heuristics on most well-known open JSP and FJSP benchmarks. In addition, we also observe that even though our model is trained for scheduling problems of smaller sizes, our method still performs well for scheduling problems of large sizes in terms of makespan. Interestingly in our experiments, our approach even reaches zero makespan gap for 49 among 60 JSP instances whose job numbers are more than 100 on 15 machines. © 2013 IEEE.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Based-on computer Vision Applications for Bus Stop Passenger Detection System 3

Based-on Computer Vision Applications for Bus Stop Passenger...

引用

3rd IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2023

作者： Chang, Yu-Cheng Tsai, Hua-Wen Huang, Chao-Yi Wu, Zong-Rong Department of Computer Information and Network Engineer Lunghwa University of Science and Technology Taiwan Department of Bachelor's Program in Intelligent Robot National Yunlin University of Science and Technology Taiwan

ISBN: (纸本)9798350333862

Passenger transport is one of the most common ways of commuting in Taiwan. It plays an important role in the transportation system due to its large number of stations, dense frequency, and cheap transportation. Due to the unfriendly transportation environment and a large number of passengers, a blind spot of passenger transportation exists, which leads to traffic accidents at the station. We research to make the Bus Stop Passenger Detection System. Taking the object detection of Wheelchairs into consideration, it is more convenient to assist the disabled to find the passenger transportation system, which makes Taiwan's transportation system more convenient. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Exploring the Characteristics of Popular Deep Learning GitHub Repositories∗ 2

Exploring the Characteristics of Popular Deep Learning GitHu...

引用

2nd International Conference on Intelligent Computing and Next Generation networks, ICNGN 2023

作者： Zhou, Yiren Qiao, Yu Xu, Tao University of Aeronautics and Astronautics College of Computer Science and Technology Nanjing China Network Center Zaozhuang University Zaozhuang China

ISBN: (纸本)9798350329070

Deep learning (DL) repositories on GitHub platform have a significant growth following the successful application of DL for different domain tasks. How to capture widespread and continued attention from such many DL repositories becomes an urgent concern for researchers and practitioners of DL. While some studies have attempted to explore popular GitHub repositories, they mainly focused on traditional software or academic AI repositories on GitHub. DL repositories are different from traditional software or academic AI repositories, it is necessary to explore the characteristics of popular DL GitHub repositories. Therefore, through a case study of 652 popular and unpopular DL repositories, we study the growth patterns and characteristics of popular DL repositories and the impact of four types of factors (i.e., basic information, DL-related information, README information, and repositories' owner information) on the popularity of DL repositories. We find that: i) different from the four growth patterns in the traditional software repositories, DL repositories have three growth patterns: Faster-then-Slower, Linear, and Explosive growth patterns;ii) various features exert diverse influences on the popularity of repositories within distinct domains;ii) basic information of the GitHub repositories (e.g., number of contributions, and number of topics) and README information (e.g., has-quickexample, has-photo) are more helpful in attracting attention compared with DL-related information. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Shuffled Autoregression for Motion Interpolation 48

Shuffled Autoregression for Motion Interpolation

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Huang, Shuo Jia, Jia Yang, Zongxin Wang, Wei Wu, Haozhe Yang, Yi Xing, Junliang Tsinghua University Department of Computer Science and Technology Beijing100084 China Beijing National Research Center for Information Science and Technology China Zhejiang University Ccai College of Computer Science and Technology China

ISBN: (纸本)9781728163277

This work aims to provide a deep-learning solution for the motion interpolation task. Previous studies solve it with geometric weight functions. Some other works propose neural networks for different problem settings with consecutive pose sequences as input. However, motion interpolation is a more complex problem that takes isolated poses (e.g., only one start pose and one end pose) as input. When applied to motion interpolation, these deep learning methods have limited performance since they do not leverage the flexible dependencies between interpolation frames as the original geometric formulas do. To realize this interpolation characteristic, we propose a novel framework, referred to as Shuffled AutoRegression, which expands the autoregression to generate in arbitrary (shuffled) order and models any inter-frame dependencies as a directed acyclic graph. We further propose an approach to constructing a particular kind of dependency graph, with three stages assembled into an end-to-end spatial-temporal motion Transformer. Experimental results on one of the current largest datasets show that our model generates vivid and coherent motions from only one start frame to one end frame and outperforms competing methods by a large margin. The proposed model is also extensible to multiple keyframes' motion interpolation tasks and other areas' interpolation. © 2023 IEEE.

关键词： animation human motion motion interpolation neural networks transformer

来源：评论

学校读者我要写书评

暂无评论

An Improved Deadlock Recovery Policy of Flexible Manufacturing Systems Based on Resource Flow Graphs

引用

IEEE Access 2024年 12卷 65202-65212页

作者： Tseng, Ching-Yun Chen, Ju-Chin Pan, Yen-Liang National Kaohsiung University of Science and Technology Department of Electronic Engineering Kaohsiung807618 Taiwan R.O.C. Air Force Academy Mathematics and Physics Division General Education Center Gangshan Kaohsiung820009 Taiwan National Kaohsiung University of Science and Technology Department of Computer Science and Information Engineering Kaohsiung807618 Taiwan Chaoyang University of Technology Department of Aeronautical Engineering Taichung413310 Taiwan

The system deadlock problem of the flexible manufacturing system (FMS) needs to be solved urgently. Deadlocks may occur when resources are repeatedly requested by multiple working processes, where such competition causes a lack of resources, and the system cannot get into subsequent processes smoothly. In this paper, we build FMS by using a particular class of Petri Net (PN) model called a system of simple sequential processes with resources (S3PR) net, which features a high utilization rate of resources. When parts of resources are held by related processes and these processes wait for others to release resources to move on, a circular waiting situation occurs. Circular waiting is one of the conditions for system deadlocks occurring, where the system under this situation has a high probability of causing system deadlocks. The resources being held have to be released to break the waiting states. This paper develops a novel control transition-based deadlock recovery policy by combining graph theory and reachability graph analysis technique. The proposed approach firstly builds a subnet of the PN model called resource flow graph (RFG) and finds out all its hold and request circuits (HRCs), which may lead to a circular waiting situation. In addition, we design a new algorithm to obtain the minimal set of control transitions further. We introduce three PN models of FMS to demonstrate the proposed method. Through experimental results and comparison between related works, it is known that the proposed deadlock recovery uses fewer controllers and has the same performance. © 2013 IEEE.

关键词： Frequency modulation

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：