检索结果-内蒙古大学图书馆

Visual Classification by 1-Hypergraph Modeling

IEEE Transactions on Knowledge and Data engineering 2015年第9期27卷 2564-2574页

作者： Wang, Meng Liu, Xueliang Wu, Xindong School of Computer Science and Information Engineering Hefei University of Technology Hefei China Department of Computer Science University of Vermont BurlingtonVT05405 United States

Visual classification has attracted considerable research interests in the past decades. In this paper, a novel 1-hypergraph model for visual classification is proposed. Hypergraph learning, as a natural extension of graph model, has been widely used in many machine learning tasks. In previous work, hypergraph is usually constructed by attribute-based or neighborhood-based methods. That is, a hyperedge is generated by connecting a set of samples sharing a same feature attribute or in a neighborhood. However, these methods are unable to explore feature space globally or sensitive to noises. To address these problems, we propose a novel hypergraph construction approach that leverages sparse representation to generate hyperedges and learns the relationship among hyperedges and their vertices. First, for each sample, a hyperedge is generated by regarding it as the centroid and linking it as well as its nearest neighbors. Then, the sparse representation method is applied to represent the centroid vertex by other vertices within the same hyperedge. The vertices with zero coefficients are removed from the hyperedge. Finally, the representation coefficients are used to define the incidence relation between the hyperedge and the vertices. In our approach, we also optimize the hyperedge weights to modulate the effects of different hyperedges. We leverage the prior knowledge on the hyperedges so that the hyperedges sharing more vertices can have closer weights, where a graph Laplacian is used to regularize the optimization of the weights. Our approach is named 1-hypergraph since the 1 sparse representation is employed in the hypergraph construction process. The method is evaluated on various visual classification tasks, and it demonstrates promising performance. © 1989-2012 IEEE.

关键词： Knowledge management

来源：评论

学校读者我要写书评

暂无评论

A courseware authoring tool for achieving interoperability among various e-learning specifications based on Web 2.0 technologies

A courseware authoring tool for achieving interoperability a...

引用

2007 International Conference on Parallel Processing Workshops, ICPPW 2007

作者： Wang, Te-Hua Yen, Neil Y. Du, Yue-Lin Shih, Timothy K. Department of Information Management Chihlee Institute of Technology Department of Computer Science and Information Engineering Tamkang University

ISBN: (纸本)0769529348

With the trend of the Internet applications, e-Learning has shown its significance along with various learning activities in more convenient ways. Followed by this tendency, many well-known e-learning specifications were proposed to regulate those digitalized learning activities in a standardized manner. However, with respect to the interoperability among various e-learning specifications nowadays, some of them were designed to support particular domains. And this will lead to the result of poor shareability of existing learning resources. On the other hand, the courseware authoring could be considered as the fundamental process while realizing an e-learning environment. As a result, the applicable scope and the user-friendliness should be taken into account for supporting efficient learning contents development. In this paper, we will like to propose a courseware authoring tool to achieve the interpretability among different e-learning specifications based on Web 2.0 technologies in an efficient way. © 2007 IEEE.

关键词： Specifications

来源：评论

学校读者我要写书评

暂无评论

Hybrid Segmentation Approach for Different Medical Image Modalities

引用

computers, Materials & Continua 2022年第11期73卷 3454-3471页

作者： Walid El-Shafai Amira A.Mahmoud El-Sayed M.El-Rabaie Taha E.Taha Osama F.Zahran Adel S.El-Fishawy Naglaa F.Soliman Amel A.Alhussan Fathi E.Abd El-Samie Department Electronics and Electrical Communications Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Security Engineering Laboratory Department of Computer SciencePrince Sultan UniversityRiyadh11586Saudi Arabia Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadhSaudi Arabia

The segmentation process requires separating the image region into sub-regions of similar *** sub-region has a group of pixels having the same characteristics,such as texture or *** paper suggests an efficient hybrid segmentation approach for different medical image modalities based on particle swarm optimization(PSO)and improved fast fuzzy C-means clustering(IFFCM)*** extensive comparative study on different medical images is presented between the proposed approach and other different previous segmentation *** existing medical image segmentation techniques incorporate clustering,thresholding,graph-based,edge-based,active contour,region-based,and watershed *** paper extensively analyzes and summarizes the comparative investigation of these ***,a prediction of the improvement involves the combination of these techniques is *** obtained results demonstrate that the proposed hybrid medical image segmentation approach provides superior outcomes in terms of the examined evaluation metrics compared to the preceding segmentation techniques.

关键词： Image segmentation ultrasonic images X-ray images CT images PET images MR images fuzzy c-mean morphological operations active contour

来源：评论

学校读者我要写书评

暂无评论

Concurrent error detection and correction in dual basis multiplier over GF(2m)

引用

IET Circuits, Devices and Systems 2009年第1期3卷 22-40页

作者： Chiou, C.W. Lee, C.-Y. Lin, J.-M. Hou, T.-W. Chang, C.-C. Department of Computer Science and Information Engineering Ching Yun University 229 Chien-Hsin Road Chung-Li 320 Taiwan Department of Computer Information and Network Engineering Lunghwa University of Science and Technology Taoyuan County 333 Taiwan Department of Information Engineering and Computer Science Feng Chia University Taichung City 407 Taiwan Department of Engineering Science National Cheng Kung University Tainan City 701 Taiwan

Fault-based side-channel cryptanalysis is a useful technique against symmetrical and asymmetrical encryption/decryption algorithms. Thus, eliminating cryptographic computation errors become critical in preventing such kind of attacks. A simple way to eliminating cryptographic computation errors is to output correct or corrected ciphers. Multiplication is the most important finite field arithmetic operation in the cryptographic computations. By using time redundancy technique, a novel dual basis (DB) multiplier over Galois fields (2m) will be presented with lower space complexity and feedback-free property. Based on the proposed feedback-free DB multiplier, the DB multiplier with a concurrent error detection (CED) capability is also easily developed. Compared with the existing DB multiplier with CED capability, the proposed one saves about 90 of time-area complexity. No existing DB multiplier in the literature has concurrent error correction (CEC) capability. Based on the proposed DB multiplier, a novel DB multiplier with CEC capability is easily designed. The proposed DB multiplier with CEC capability requires only about 3 of extra space complexity and 15 of time complexity when compared with the proposed DB multiplier without CEC. © The Institution of engineering and technology 2009.

关键词： Error correction

来源：评论

学校读者我要写书评

暂无评论

Macro liveness graph and liveness of ω-independent unbounded nets

引用

Science China(information Sciences) 2015年第3期58卷 132-141页

作者： WANG ShouGuang GAN MengDi ZHOU MengChu School of Information and Electronic Engineering Zhejiang Gongshang University Key Laboratory of Embedded System and Service Computing Ministry of EducationTongji University Department of Electrical and Computer Engineering New Jersey Institute of Technology

Liveness is a basic property of a system and the liveness issue of unbounded Petri nets remains one of the most difficult problems in this *** work proposes a novel method to decide the liveness of a class of unbounded generalized Petri nets calledω-independent unbounded nets,breaking the existing limits to one-place-unbounded *** algorithm to construct a macro liveness graph(MLG)is developed and a critical condition based on MLG deciding the liveness ofω-independent unbounded nets is *** are provided to demonstrate its effectiveness.

关键词： discrete event system(DES) Petri nets complex systems liveness property analysis

来源：评论

学校读者我要写书评

暂无评论

A comparative study on transformation of UML/OCL to other specifications

引用

Recent Advances in computer Science and Communications 2020年第2期13卷 256-264页

作者： Thangaraj, Jagadeeswaran Ulaganathan, Senthilkumaran Department of Computer Science Maynooth University Maynooth Ireland School of Information Technology & Engineering VIT University VelloreTamilNadu India

Background: Static verification is a sound programming methodology that permits auto-mated reasoning about the correctness of an implementation with respect to its formal specification before its execution. Unified Modelling Language is most commonly used modelling language which describes the client’s requirement. Object Constraint Language is a formal language which allows users to express textual constraints regarding the UML model. Therefore, UML/OCL express formal specification and helps the developers to implement the code according to the client’s requirement through software design. Objective: This paper aims to compare the existing approaches generating Java, C++, C# code or JML, Spec# specifications from UML/OCL. Method: Nowadays, software system is developed via automatic code generation from software design to implementation when using formal specification and static analysis. In this paper, the study considers transformation from design to implementation and vice versa using model transformation, code generation or other techniques. Results: The related tools, which generate codes, do not support verification at the implementation phase. On the other hand, the specification generation tools do not generate all the required properties which are needed for verification at the implementation phase. Conclusion: If the generated system supports the verification with all required properties, code de-veloper needs less efforts to produce correct software system. Therefore, this study recommends in-troducing a new framework which can act as an interface between design and implementation to generate verified software systems. © 2020 Bentham Science Publishers.

关键词： Formal specification

来源：评论

学校读者我要写书评

暂无评论

Former-HGR: Hand Gesture Recognition With Hybrid Feature-Aware Transformer

IEEE Sensors Letters

引用

IEEE Sensors Letters 2025年第6期9卷

作者： Verma, Monu Gopalani, Garvit Bharara, Saiyam Vipparthi, Santosh Kumar Murala, Subrahmanyam Abdel-Mottaleb, Mohamed Indiana University Department of Computer Science Indianapolis 46202 IN United States Manipal Institute of Technology Department of Information Technology India Microsoft IDC Hyderabad India Indian Institute of Technology Ropar School of Artificial Intelligence and Data Engineering (sAIDE) 14001 India Trinity College Dublin School of Computer Science and Statistics Ireland

Hand Gesture Recognition (HGR) systems, using cameras and sensors, offer an intuitive method for human-machine interaction, sparking interest across various applications. However, these systems face challenges from environmental factors like variations in illumination, complex backgrounds, diverse hand shapes, and similarities between different gesture classes. Achieving accurate gesture recognition under such conditions remains a complex task, necessitating robust solutions to ensure reliable performance. This letter proposes a novel approach named Former-HGR, a hybrid feature-aware transformer for HGR. Unlike traditional transformer-based HGR systems that heavily rely on computationally intensive self-attention mechanisms, Former-HGR enhances global feature perception by applying self-attention across channels through the integration of Multi-Dconv Head Transposed Attention (MDTA). Additionally, Former-HGR improves feature extraction by incorporating multi-scale features and effectively filters redundant information using a Hybrid Feature-Aware Network (HFAN). Extensive experiments conducted on three data sets: NUSII, OUHANDS, and MUGD, demonstrate that Former-HGR outperforms recent benchmark HGR approaches, achieving accuracy improvements of up to 14% in person-independent validation schemes. © 2017 IEEE.

关键词： Hand gesture recognition using imaging/Optical sensors hybrid feature-aware transformer transformer

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Enabled Mitigation Strategies for Distributed Denial of Service Attacks in IoT Sensor Networks:An Experimental Approach

引用

computers, Materials & Continua 2024年第12期81卷 3679-3705页

作者： Kithmini Godewatte Arachchige Mohsin Murtaza Chi-Tsun Cheng Bader M.Albahlal Cheng-Chi Lee Department of Engineering Technologies School of ScienceComputing and Engineering TechnologiesSwinburne UniversityMelbourne3122Australia School of Engineering Science Technology Engineering and Mathematics CollegeRMIT UniversityMelbourneVIC 3001Australia Department of Information Technology College of Computer and Information SciencesImam Mohammad Ibn Saud Islamic University(IMSIU)Riyadh11432Saudi Arabia Department of Library and Information Science Fu Jen Catholic UniversityNew Taipei City24205TaiwanChina Department of Computer Science and Information Engineering Asia UniversityTaichung City41354TaiwanChina

information security has emerged as a crucial consideration over the past decade due to escalating cyber security threats,with Internet of Things(IoT)security gaining particular attention due to its role in data communication across various ***,IoT devices,typically low-powered,are susceptible to cyber ***,blockchain has emerged as a robust solution to secure these devices due to its decentralised ***,the fusion of blockchain and IoT technologies is challenging due to performance bottlenecks,network scalability limitations,and blockchain-specific security ***,on the other hand,is a recently emerged information security solution that has great potential to secure low-powered IoT *** study aims to identify blockchain-specific vulnerabilities through changes in network behaviour,addressing a significant research gap and aiming to mitigate future cybersecurity *** blockchain and IoT technologies presents challenges,including performance bottlenecks,network scalability issues,and unique security *** paper analyses potential security weaknesses in blockchain and their impact on network *** developed a real IoT test system utilising three prevalent blockchain applications to conduct *** results indicate that Distributed Denial of Service(DDoS)attacks on low-powered,blockchain-enabled IoT sensor networks cause measurable anomalies in network and device performance,specifically:(1)an average increase in CPU core usage to 34.32%,(2)a reduction in hash rates by up to 66%,(3)an increase in batch timeout by up to 14.28%,and(4)an increase in block latency by up to 11.1%.These findings suggest potential strategies to counter future DDoS attacks on IoT networks.

关键词： Blockchain cyber intrusions DDoS IoT low powered sensors vulnerabilities wireless network

来源：评论

学校读者我要写书评

暂无评论

Non-Local DWI Image Super-Resolution with Joint information Based on GPU Implementation

引用

computers, Materials & Continua 2019年第9期61卷 1205-1215页

作者： Yanfen Guo Zhe Cui Zhipeng Yang Xi Wu Shaahin Madani Chengdu Institute of Computer Application University of Chinese Academy of SciencesChengdu610041China Department of Computer Science Chengdu University of Information TechnologyChengdu610225China Department of Electronic Engineering Chengdu University of Information TechnologyChengdu610225China Department of Computer Science and IT RMIT University124 La Trobe StreetMelbourne VIC3000Australia

Since the spatial resolution of diffusion weighted magnetic resonance imaging(DWI)is subject to scanning time and other constraints,its spatial resolution is relatively *** view of this,a new non-local DWI image super-resolution with joint information method was proposed to improve the spatial *** on the non-local strategy,we use the joint information of adjacent scan directions to implement a new weighting *** quantitative and qualitative comparison of the datasets of synthesized DWI and real DWI show that this method can significantly improve the resolution of ***,the algorithm ran slowly because of the joint *** order to apply the algorithm to the actual scene,we compare the proposed algorithm on CPU and GPU *** is found that the processing time on GPU is much less than on CPU,and that the highest speedup ratio to the traditional algorithm is more than 26 *** raises the possibility of applying reconstruction algorithms in actual workplaces.

关键词： Super-resolution non-local means parallel computing GPU

来源：评论

学校读者我要写书评

暂无评论

Development of 3D virtual math games on Second Life

Development of 3D virtual math games on Second Life

引用

19th International Conference on computers in Education, ICCE 2011

作者： Hsiao, Indy Y.T. Li, Irene Y.S. Huang, Jeff J.S. Yang, Stephen J.H. Fu, Ellis S.J. Department of Computer Science and Information Engineering National Central University Taiwan Department of Computer Science and Information Engineering Hwa Hsia Institute of Technology Taiwan

ISBN: (纸本)9786161201883

Mathematical education in elementary school is the key fundamental of math learning. It plays an important role of pupils' future math learning. This study tries to combine information technology and mathematics to build a mathematical learning environment in Second Life. We expect to create a new learning style for mathematical education in elementary school. While Second Life has got a lot of empirical results in education, some researches indicate that students need guidance or teaching aids to learn in such environments. In order to improve the pupil's learning outcomes, this study proposes a problem-based learning approach with teaching aids and embeds mathematical learning materials in the built virtual classrooms facilitating teaching as well as learning.

关键词： Teaching

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：