检索结果-内蒙古大学图书馆

International CSI computer Conference, CSICC

作者： Farzaneh Kazemzadeh Ali Asghar Safaei Mitra Mirzarezaee Department of Computer Engineering Science and Research branch Islamic Azad University Tehran Iran Department of Medical Informatics Faculty of Medical Sciences Tarbiat Modares University Tehran Iran

The influence maximization problem (IMP) has been proposed in social networks. Nowadays, it is considered an important and practical problem due to the earnings potential by identifying a set of influential nodes, and therefore, it has been attracted by many researchers. This problem seeks to identify a set with K nodes among the social network nodes to maximize the influence and diffusion of information in that community. Algorithms proposed by other researchers have many shortcomings in terms of accuracy and run time of the algorithm. Hence, this article aimed to find the best, most accurate, and fastest solution to the *** article presented the UXM algorithm and used the User Experience criterion for the first time to solve this problem. At first, taking into account the reach club phenomenon and using criteria such as clustering coefficient, degree and also using user experience, nodes with more influence have been selected as the primary candidate set. Then, according to the component nodes, K final influential nodes have been selected. In this way, it could identify the set of nodes as accurately as possible with high efficiency in the shortest possible time. The evaluation of this algorithm and its comparison with other algorithms indicated excellent results in terms of run time and accuracy in selecting the set of nodes by the proposed algorithm.

关键词： Social networking (online) Network topology Clustering algorithms Diffusion processes User experience

来源：评论

学校读者我要写书评

暂无评论

Round-optimal n-Block Broadcast Schedules in Logarithmic Time

arXiv

引用

arXiv 2023年

作者： Träff, Jesper Larsson TU Wien Faculty of Informatics Institute of Computer Engineering Research Group Parallel Computing 191-4 Treitlstrasse 3 5th Floor Vienna1040 Austria

We give optimally fast O(log p) time (per processor) algorithms for computing round-optimal broadcast schedules for message-passing parallel computing systems. This affirmatively answers the questions posed in Träff (2022). The problem is to broadcast n indivisible blocks of data from a given root processor to all other processors in a (subgraph of a) fully connected network of p processors with fully bidirectional, one-ported communication capabilities. In this model, n − 1 + ⌈log2 p⌉ communication rounds are required. Our new algorithms compute for each processor in the network receive and send schedules each of size ⌈log2 p⌉ that determine uniquely in O(1) time for each communication round the new block that the processor will receive, and the already received block it has to send. Schedule computations are done independently per processor without communication. The broadcast communication subgraph is the same, easily computable, directed, ⌈log2 p⌉-regular circulant graph used in Träff (2022) and elsewhere. We show how the schedule computations can be done in optimal time and space of O(log p), improving significantly over previous results of O(p log2 p) and O(log3 p). The schedule computation and broadcast algorithms are simple to implement, but correctness and complexity are not obvious. All algorithms have been implemented, compared to previous algorithms, and briefly evaluated on a small 36 × 32 processor-core cluster. © 2023, CC BY-NC-ND.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

Mobile Game Development Using Unity Engine 13th

Mobile Game Development Using Unity Engine

引用

13th International Conference on Methodologies and Intelligent Systems for Technology Enhanced Learning, mis4TEL 2023

作者： Sapundzhi, Fatima Kitanov, Anton Lazarova, Meglena Georgiev, Slavi Department of Communication and Computer Engineering Faculty of Engineering South-West University "Neofit Rilski" 66 Ivan Mihailov Street Blagoevgrad2700 Bulgaria Faculty of Applied Mathematics and Informatics Technical University of Sofia 8 Kliment Ohridski Blvd. Sofia1000 Bulgaria Institute of Mathematics and Infromatics Bulgarian Academy of Sciences 8 Acad. Georgi Bonchev Street Sofia1113 Bulgaria Department of Applied Mathematics and Statistics University of Ruse "Angel Kanchev" 8 Studentska Street Ruse7004 Bulgaria

ISBN: (纸本)9783031421334

Unity is a popular game development platform. Various industries are inspired by it and this can be a positive impact on the learning motivation, career growth and job opportunities. The aim of this paper is to develop and implement a 3D game application for education promoting through innovation and digital skills. The game consists of two parts. The first part of the developed application is a maze that the player must overcome. In this labyrinth the player has to collect a certain number of specific bags that contain pieces of the needed puzzle. The second part is a puzzle that the player begins to arrange. If the puzzle is arranged correctly, then the player can read an interesting fact about what is seen on the picture. The theme given on the picture is an educational theme and it main aim is to develop the educational and mental abilities of the playersp who may also be students. The game is suitable for a wide range of potential players as it can be interesting and educational for children, teenagers and even adults. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Image processing

来源：评论

学校读者我要写书评

暂无评论

Robust hypersphere-based weight imprinting for few-shot learning 28

Robust hypersphere-based weight imprinting for few-shot lear...

引用

28th European Signal Processing Conference, EUSIPCO 2020

作者： Passalis, Nikolaos Iosifidis, Alexandros Gabbouj, Moncef Tefas, Anastasios Department of Informatics Aristotle University of Thessaloniki Thessaloniki Greece Department of Engineering Electrical and Computer Engineering Aarhus University Denmark Faculty of Information Technology and Communication Sciences Tampere University Tampere Finland

ISBN: (纸本)9789082797053

Performing fast few-shot learning is increasingly important in a number of embedded applications. Among them, a form of gradient-descent free learning known as Weight Imprinting was recently established as an efficient way to perform few-shot learning on Deep Learning (DL) accelerators that do no support back-propagation, such as Edge Tensor Processing Units (Edge TPUs). Despite its efficiency, WI comes with a number of critical limitations. For example, WI cannot effectively handle multimodal novel categories, while it is especially prone to overfitting that can have devastating effects on the accuracy of the models on novel categorizes. To overcome these limitations, in this paper we propose a robust hypersphere-based WI approach that allows for regularizing the training process in an imprinting-aware way. At the same time, the proposed formulation provides a natural way to handle multimodal novel categories. Indeed, as demonstrated through the conducted experiments, the proposed method leads to significant improvements over the baseline WI approach. © 2021 European Signal Processing Conference, EUSIPCO. All rights reserved.

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

Exploratory Study on User Experience (UX) of Public E-Procurement System in Malaysia: A Qualitative Approach

Exploratory Study on User Experience (UX) of Public E-Procur...

引用

HCI and UX Conference in Indonesia (CHIuXiD), International

作者： Emma Nuraihan Mior Ibrahim Amiruddin Kusaini Juhaida Ismail Anis Hasliza Abu Hashim Mudiana Mokhsin Misron College of Computing Informatics and Mathematics Universiti Teknologi MARA Shah Alam Selangor Malaysia Faculty of Electrical Engineering Mathematics and Computer Science University of Twente Hallenweg 15 Netherlands

The public e-Procurement system in Malaysia is a crucial component of the e-Government services. Its primary function is to provide a platform for government agencies to efficiently procure goods and services from business users. The user experience (UX) of this e-Procurement system has emerged as a pivotal factor in the success of the broader e-Government digital transformation. Ensuring that the digitalization of the public e-Procurement system aligns with its objectives and delivers a top-tier Government Electronic Procurement System is imperative. This research aims to gain a comprehensive understanding of the UX issues and challenges faced by stakeholders when using the public e-Procurement system. The study employs a qualitative approach, delving into the perspectives and insights of e-Procurement system users. Data from interview sessions involving nine (9) participants have been meticulously interpreted, coded, and subjected to thematic analysis, revealing five distinct dimensions of issues and challenges: usability, performance, operational, quality, and user satisfaction. To address these identified concerns, we proposed several recommendations. Enhancements in system user interface (UI), navigational aspects, system features, performance, and operational aspects are essential to ensure sustained quality and user satisfaction within the e-Procurement system. The study also explores avenues for future work to further refine and augment these improvements.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Human Action Recognition Using Recurrent Bag-of-Features Pooling 25th

Human Action Recognition Using Recurrent Bag-of-Features Poo...

引用

25th International Conference on Pattern Recognition Workshops, ICPR 2020

作者： Krestenitis, Marios Passalis, Nikolaos Iosifidis, Alexandros Gabbouj, Moncef Tefas, Anastasios Department of Informatics Aristotle University of Thessaloniki Thessaloniki Greece Department of Engineering Electrical and Computer Engineering Aarhus University Aarhus Denmark Faculty of Information Technology and Communication Tampere University Tampere Finland

ISBN: (纸本)9783030688202

Bag-of-Features (BoF)-based models have been traditionally used for various computer vision tasks, due to their ability to provide compact semantic representations of complex objects, e.g., images, videos, etc. Indeed, BoF has been successfully combined with various feature extractions methods, ranging from handcrafted feature extractors to powerful deep learning models. However, BoF, along with most of the pooling approaches employed in deep learning, fails to capture the temporal dynamics of the input sequences. This leads to significant information loss, especially when the informative content of the data is sequentially distributed over the temporal dimension, e.g., videos. In this paper we propose a novel stateful recurrent quantization and aggregation approach in order to overcome the aforementioned limitation. The proposed method is inspired by the well-known Bag-of-Features (BoF) model, but employs a stateful trainable recurrent quantizer, instead of plain static quantization, allowing for effectively encoding the temporal dimension of the data. The effectiveness of the proposed approach is demonstrated using three video action recognition datasets. © 2021, Springer Nature Switzerland AG.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Graph Modeling based Safety Classifier Algorithm for Smart Transportation

引用

Procedia computer Science 2024年 236卷 502-507页

作者： Najib El Karkouri Smail Tigani Rachid Saadane Abdelah Chehri Samuel Pierre Noureddine Neya Mathematics and Informatics Lab Faculty of Sciences University Ibno Toufial Kenitra Morocco Research and Development Unit Accsellium LLC Fez Morocco SIRC-LaGeS Hassania School of Public Labors 20250 Casablanca Morocco Department of Mathematics and Computer Science Royal Military College of Canada Kingston Canada Department of Computer and Software Engineering Polytechnique Montreal Canada

This research introduces a novel Probabilistic Graph Modeling-based Safety Classifier Algorithm designed for the purpose of classifying road safety in smart transportation systems. Leveraging a combination of numerical integration methods and Gaussian kernel density estimation models, the proposed algorithm offers an effective approach to assess and categorizing the safety levels of roads. The integration of these techniques enables a comprehensive analysis, allowing for a more nuanced understanding of the complex interactions within transportation networks. The algorithm's efficacy in road safety classification holds promising implications for enhancing traffic management and promoting safer urban environments.

关键词： Probabilistic Graph Numerical Computation Smart Transportation Classification Road Safety

来源：评论

学校读者我要写书评

暂无评论

GENERATING ALL INVERTIBLE MATRICES BY ROW OPERATIONS

arXiv

引用

arXiv 2024年

作者： Gregor, Petr Hoang, Hung P. Merino, Arturo Mička, Ondřej Department of Theoretical Computer Science and Mathematical Logic Charles University Prague Czech Republic Algorithm and Complexity Group Faculty of Informatics TU Wien Austria Engineering Institute Universidad de O'Higgins Rancagua Chile

We show that all invertible n×n matrices over any finite field Fq can be generated in a Gray code fashion. More specifically, there exists a listing such that (1) each matrix appears exactly once, and (2) two consecutive matrices differ by adding or subtracting one row from a previous or subsequent row, or by multiplying or dividing a row by the generator of the multiplicative group of Fq. This even holds in the more general setting where the pairs of rows that can be added or subtracted are specified by an arbitrary transition tree that has to satisfy some mild constraints. Moreover, we can prescribe the first and the last matrix if n ≥ 3, or n = 2 and q > 2. In other words, the corresponding flip graph on all invertible n × n matrices over Fq is Hamilton connected if it is not a cycle. This solves yet another special case of Lovász conjecture on Hamiltonicity of vertex-transitive graphs. © 2024, CC BY-NC-ND.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Attention Swin U-Net: Cross-Contextual Attention Mechanism for Skin Lesion Segmentation

Attention Swin U-Net: Cross-Contextual Attention Mechanism f...

引用

IEEE International Symposium on Biomedical Imaging

作者： Ehsan Khodapanah Aghdam Reza Azad Maral Zarvani Dorit Merhof Department of Electrical Engineering Shahid Beheshti University Tehran Iran Institute of Imaging and Computer Vision RWTH Aachen University Aachen Germany Department of Computer Engineering Alzahra University Tehran Iran Faculty of Informatics and Data Science University of Regensburg Bayern Germany

Melanoma is caused by the abnormal growth of melanocytes in human skin. Like other cancers, this life-threatening skin cancer can be treated with early diagnosis. To support a diagnosis by automatic skin lesion segmentation, several Fully Convolutional Network (FCN) approaches, specifically the U-Net architecture, have been proposed. The U-Net model with a symmetrical architecture has exhibited superior performance in the segmentation task. However, the locality restriction of the convolutional operation incorporated in the U-Net architecture limits its performance in capturing long-range dependency, which is crucial for the segmentation task in medical images. To address this limitation, recently a Transformer based U-Net architecture that replaces the CNN blocks with the Swin Transformer module has been proposed to capture both local and global representation. In this paper, we propose Att-SwinU-Net, an attention-based Swin U-Net extension, for medical image segmentation. In our design, we seek to enhance the feature re-usability of the network by carefully designing the skip connection path. We argue that the classical concatenation operation utilized in the skip connection path can be further improved by incorporating an attention mechanism. By performing a comprehensive ablation study on several skin lesion segmentation datasets, we demonstrate the effectiveness of our proposed attention mechanism.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-based dynamic graph neighborhoods for medical segmentation

arXiv

引用

arXiv 2021年

作者： Demir, Ufuk Ozer, Atahan Sahin, Yusuf H. Unal, Gozde Istanbul Technical University Faculty of Computer and Informatics Engineering Computer Engineering Istanbul34469 Turkey Istanbul Technical University Faculty of Computer and Informatics Engineering AI and Data Engineering Istanbul34469 Turkey

In recent years, deep learning based methods have shown success in essential medical image analysis tasks such as segmentation. Post-processing and refining the results of segmentation is a common practice to decrease the misclassifications originating from the segmentation network. In addition to widely used methods like Conditional Random Fields (CRFs) which focus on the structure of the segmented volume/area, a graph-based recent approach makes use of certain and uncertain points in a graph and refines the segmentation according to a small graph convolutional network (GCN). However, there are two drawbacks of the approach: most of the edges in the graph are assigned randomly and the GCN is trained independently from the segmentation network. To address these issues, we define a new neighbor-selection mechanism according to feature distances and combine the two networks in the training procedure. According to the experimental results on pancreas segmentation from Computed Tomography (CT) images, we demonstrate improvement in the quantitative measures. Also, examining the dynamic neighbors created by our method, edges between semantically similar image parts are observed. The proposed method also shows qualitative enhancements in the segmentation maps, as demonstrated in the visual results. Copyright © 2021, The Authors. All rights reserved.

关键词： Graphic methods

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：