检索结果-内蒙古大学图书馆

Superpixel Graph Contrastive Clustering with Semantic-Invariant Augmentations for Hyperspectral Images

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Qi, Jianhan Jia, Yuheng Liu, Hui Hou, Junhui The School of Software Engineering Southeast University Nanjing210096 China The School of Computer Science and Engineering Southeast University Nanjing210096 China The Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications [Southeast University Ministry of Education China The School of Computing Information Sciences Caritas Institute of Higher Education Hong Kong The Department of Computer Science City University of Hong Kong Hong Kong

Hyperspectral images (HSI) clustering is an important but challenging task. The state-of-the-art (SOTA) methods usually rely on superpixels, however, they do not fully utilize the spatial and spectral information in HSI 3-D structure, and their optimization targets are not clustering-oriented. In this work, we first use 3-D and 2-D hybrid convolutional neural networks to extract the high-order spatial and spectral features of HSI through pre-training, and then design a superpixel graph contrastive clustering (SPGCC) model to learn discriminative superpixel representations. Reasonable augmented views are crucial for contrastive clustering, and conventional contrastive learning may hurt the cluster structure since different samples are pushed away in the embedding space even if they belong to the same class. In SPGCC, we design two semantic-invariant data augmentations for HSI superpixels: pixel sampling augmentation and model weight augmentation. Then sample-level alignment and clustering-center-level contrast are performed for better intra-class similarity and inter-class dissimilarity of superpixel embeddings. We perform clustering and network optimization alternatively. Experimental results on several HSI datasets verify the advantages of the proposed method, e.g., on India Pines, our model improves the clustering accuracy from 58.79% to 67.59% compared to the SOTA method. © 2024, CC BY.

关键词： Embeddings

A computer INTEGRATED engineering SYSTEM FOR DESIGN AND LIFE-CYCLE MANAGEMENT

学校读者我要写书评

暂无评论

NAVAL ENGINEERS JOURNAL 1986年第3期98卷 115-121页

作者： NICKODEMUS, GH YANUS, ID Irwin D. Yanusgraduated from the University of Pennsylvania with a bachelor's degree in arts and science in 1960 and a bachelor of science degree in mechanical engineering in 1961. In 1963 he received a master of science degree in mechanical engineering from Carnegie-Mellon University. Mr. Yanus is presently the manager of naval systems engineering in the Computer Aided Engineering Department of the Plant Engineering Division of Westinghouse Electric Corporation. His prior experience includes 19 years at the Bettis Atomic Power Laboratory where he performed assignments of increasing responsibility in design analysis development and procurement of nuclear reactor components for naval applications. As the manager of reactor mechanical design he was responsible for the mechanical design of theNimitzclass reactor components and control drive mechanism technology development. Mr. Yanus is a member of the American Society of Mechanical Engineers and the Society of Naval Architects and Marine Engineers. Glen H. Nickodemusgraduated from Michigan State University in 1964 with a bachelor of science degree in civil engineering. He joined the Pittsburgh-Des Moines Corporation in July of the same year. A master of science degree in civil engineering was obtained from Carnegie-Mellon University in 1973. In 1969 Mr. Nickodemus joined the Advanced Reactors Division of the Westinghouse Electric Corporation where he performed design and structural analysis functions for the development of the Fast Flux Test Facility and Clinch River Breeder Reactor Plant (CRBRP). As manager of CRBRP reactor engineering stress analysis he was responsible for the reactor vessel internals closure head control rod drivelines and miscellaneous guard vessels and head access area components. He is currently the manager of software development for the Computer Aided Engineering Department of the Plant Engineering Division. Mr. Nickodemus is a member of the American Society of Mechanical Engineers and is a registered professional engineer in Penn

This paper describes a computer integrated engineering system for design and life cycle management of weapons systems, ships and other multidisciplined systems. All engineering data are stored in a central engineering database. Individual application databases define and process information necessary for specific discipline evaluations. Interface modules between the application databases and the engineering database ensure that the entered data are complete, consistent, compatible, and in compliance with requirements. Conflicts are immediately identified and efficiently resolved. Implementation of the system improves design quality and reduces costs by minimizing the number of design iterations, reducing the effort to implement changes, providing effective storage and retrieval, and reducing the need for ship checks prior to modifications and alterations.

关键词： MILITARY engineering

Assessing Cybersecurity Awareness among The Hashemite University Students In Terms Of computer Usage

学校读者我要写书评

暂无评论

Assessing Cybersecurity Awareness among The Hashemite Univer...

International Conference on Electronics, computers and Artificial Intelligence (ECAI)

作者： Ashraf H. Aljammal Ahmad Qawasmeh Salah Taamneh Fadi Wedyan Mamoon Obiedat Hani Bani Salameh Department of Computer Science and Applications Prince Al Hussein bin Abdullah II Faculty of Information Technology The Hashemite University Zarqa Jordan Department of Engineering Computing and Mathematical Sciences Lewis University Romeoville Illinois USA Department of Information Technology Prince Al Hussein bin Abdullah II Faculty of Information Technology The Hashemite University Zarqa Jordan Department of Software Engineering Prince Al Hussein bin Abdullah II Faculty of Information Technology The Hashemite University Zarqa Jordan

ISBN: (数字)9798350371154

ISBN: (纸本)9798350371161

Internet usage among information technology users has expanded substantially, as have cybercrimes with potentially disastrous repercussions. Therefore, internet users have to employ the available security measures and policies during internet usage. Nowadays, University students make up a sizable portion of internet users. This study assesses the cybersecurity awareness among The Hashemite University students In terms of computer Usage. A questionnaire survey is used to assess students’ cybersecurity knowledge while using their PCs and connecting to the internet, concentrating on their behaviors and use of security measures.

关键词： Surveys Malware Internet computer security Information technology computer crime Artificial intelligence

Phonetic temporal neural model for language identification

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Tang, Zhiyuan Wang, Dong Chen, Yixiang Li, Lantian Abel, Andrew Chengdu Institute of Computer Applications Chinese Academy of Sciences and University of Chinese Academy of Sciences Beijing100049 China Center for Speech and Language Technologies Tsinghua University Beijing100084 China Tsinghua National Laboratory for Information Science and Technology and the Center for Speech and Language Technologies Tsinghua University Beijing100084 China Department of Computer Science and Software Engineering Xi'an Jiaotong-Liverpool University Suzhou215123 China

Deep neural models, particularly the LSTM-RNN model, have shown great potential for language identification (LID). However, the use of phonetic information has been largely overlooked by most existing neural LID methods, although this information has been used very successfully in conventional phonetic LID systems. We present a phonetic temporal neural model for LID, which is an LSTM-RNN LID system that accepts phonetic features produced by a phone-discriminative DNN as the input, rather than raw acoustic features. This new model is similar to traditional phonetic LID methods, but the phonetic knowledge here is much richer: it is at the frame level and involves compacted information of all phones. Our experiments conducted on the Babel database and the AP16-OLR database demonstrate that the temporal phonetic neural approach is very effective, and significantly outperforms existing acoustic neural models. It also outperforms the conventional i-vector approach on short utterances and in noisy conditions. Copyright © 2017, The Authors. All rights reserved.

关键词： Deep neural networks

Cybersecurity Threats in the Era of AI: Detection of Phishing Domains Through Classification Rules

学校读者我要写书评

暂无评论

Cybersecurity Threats in the Era of AI: Detection of Phishin...

Electrical, Energy, and Artificial Intelligence (EICEEAI), International engineering Conference on

作者： Mohammad Aljaidi Ayoub Alsarhan Dimah Al-Fraihat Ahmed Al-Arjan Bashar Igried Subhieh M. El-Salhi Muhammad Khalid Qais Al-Na'amneh Department of Computer Science Faculty of Information Technology Zarqa University Zarqa Jordan Department of Information Technology The Hashemite University Jordan Department of Software Engineering Faculty of Information Technology Isra University Amman Jordan Department of Information Technology Faculty of Prince AL-Hussein bin Abdullah II of Information Technology The Hashemite University Jordan Department of Computer Science and Applications The Hashemite University Zarqa Jordan The Hashemite University Zarqa Jordan Department of Computer Sciences and Technology University of Hull Kingston upon Hull UK Dep. of Cyber Security Applied Science Private University Amman Jordan

ISBN: (数字)9798350373363

ISBN: (纸本)9798350373370

Phishing is a cyber threat where attackers create deceptive websites or emails to exploit individuals for fraudulent purposes such as providing sensitive information like usernames, passwords, or financial details. Hence, detecting phishing emails is of paramount importance to protect sensitive information, preventing financial losses, protecting against identity theft, and maintaining trust. This study employs machine learning techniques to classify and categorize websites that are used for phishing attacks. To achieve this, we proposed a classification model for the detection of phishing domains based on classification rules. These rules were formulated based on analyzing and distributing them into three classifiers: domain name features, search engine opinion (SEO) information of the domain, and security scans by security vendors. A total of eleven classification rules were formulated which were distributed as follows: six rules for the first classifier, four rules for the second classifier, and one rule for the third classifier. Each classifier feeds its results to the main classifier, which then evaluates the received results based on its rules. Domain names from 222 confirmed phishing URLs were used to test the suggested model. The model demonstrated exceptional performance, achieving an impressive accuracy rate of 99.1% during testing.

关键词： Adaptation models Accuracy Phishing Identity theft Refining Machine learning Passwords

F2A2: Flexible Fully-decentralized Approximate Actor-critic for Cooperative Multi-agent Reinforcement Learning

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Wenhao Jin, Bo Wang, Xiangfeng Yan, Junchi Zha, Hongyuan School of Data Science The Chinese University of Hong Kong Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518172 China School of Software Engineering Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai201804 China School of Computer Science and Technology Key Laboratory of Mathematics and Engineering Applications Ministry of Education East China Normal University Shanghai200062 China Department of Computer Science and Engineering Key Laboratory of Artificial Intelligence Ministry of Education Shanghai Jiao Tong University Shanghai200240 China

Traditional centralized multi-agent reinforcement learning (MARL) algorithms are sometimes unpractical in complicated applications due to non-interactivity between agents, the curse of dimensionality, and computation complexity. Hence, several decentralized MARL algorithms are motivated. However, existing decentralized methods only handle the fully cooperative setting where massive information needs to be transmitted in training. The block coordinate gradient descent scheme they used for successive independent actor and critic steps can simplify the calculation, but it causes serious bias. This paper proposes a flexible fully decentralized actor-critic MARL framework, which can combine most of the actor-critic methods and handle large-scale general cooperative multi-agent settings. A primal-dual hybrid gradient descent type algorithm framework is designed to learn individual agents separately for decentralization. From the perspective of each agent, policy improvement and value evaluation are jointly optimized, which can stabilize multi-agent policy learning. Furthermore, the proposed framework can achieve scalability and stability for the large-scale environment. This framework also reduces information transmission by the parameter sharing mechanism and novel modeling-other-agents methods based on theory-of-mind and online supervised learning. Sufficient experiments in cooperative Multiagent Particle Environment and StarCraft II show that the proposed decentralized MARL instantiation algorithms perform competitively against conventional centralized and decentralized methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Gradient methods

Machine Learning Approaches for Efficient Traffic Flow in Smart Cities

学校读者我要写书评

暂无评论

Machine Learning Approaches for Efficient Traffic Flow in Sm...

Electrical Power engineering, Communication and Computing Technology(ODICON), Odisha International Conference on

作者： Aniket Kulkarni P. Anitha John Yesudas Valluri M V Sunena Rose U Hemavathi Omar M. Hussein Software QA Manager Drata Inc San Diego CA USA Department of Computer Applications Kalasalingam Academy of Research and Education Srivilliputhur Tamil Nadu India Faculty of Management Studies CMS Business School Jain (Deemed-to-be University) Bengaluru India Department of Computer Science and Engineering Jain (Deemed-to-be University) Bengaluru India Department of CSE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai India Medical Technical College Medical Instrumentation Engineering Al-Farahidi University Baghdad Iraq

ISBN: (数字)9798350354379

ISBN: (纸本)9798350354386

These days, a lot of towns struggle with traffic jams during peak hours, which increment contamination, commotion, and feelings of anxiety for the general population. Because neural networks (NN) and machine learning (ML) techniques can handle large numbers of parameters in massive amounts of data and dynamic behaviour over time, they are replacing analytical and statistical methods in the solving of real-world problems. This research presents a convergence of machine-learning (ML) and deep-learning (DL) calculations for traffic stream prediction; this paves the way for flexible traffic signals, which can be implemented through the use of a calculation that adjusts the timing in accordance with the anticipated traffic flow or by controlling traffic signals to some degree. The proposed ML and DL models are constructed, validated, and tested using two publicly accessible datasets. The first depicts the total number of cars subjected to checks using various sensors at six junctions over the course of 56 days. In this research, ML and DL models are created using data from four of the six junctions. The excellent performance metrics obtained by all ML and DL computations suggest that their application to intelligent traffic light management is feasible.

关键词： Measurement Power engineering Machine learning algorithms Statistical analysis Smart cities Transportation Machine learning Prediction algorithms Timing Junctions

What if?.. Fabulating African HCI Futures within the Veil of HCI 23

学校读者我要写书评

暂无评论

What if?.. Fabulating African HCI Futures within the Veil of...

Proceedings of the 4th African Human computer Interaction Conference

作者： Shaimaa Lazem Muhammad Sadi Adamu Yasmeen Abdrabou Chris Muashekele Sheena Erete Jakita Thomas Hafeni Mthoko Heike Winschiers-Teophilus Nicola Bidwell Aderonke Sakpere Anicia Peters City of Scientific Research and Technology Applications (SRTA-City) Egypt Imagination Lancaster Lancaster University United Kingdom School of Computing and Communications Lancaster University United Kingdom Aalborg University Denmark College of Information Studeies University of Maryland USA Department of Computer science and software Engineering (CSSE) Auburn University USA NurtureID8 Namibia Department of Software Engineering Namibia University of Science and Technology Namibia Intenational Uiversity of Management Namibia and University of Melbourne Australia University of Ibadan Nigeria National Commission of Research Sicence and Technology (NCRST) Namibia

ISBN: (纸本)9798400708879

This workshop aims to bring together researchers and practitioners (African and otherwise) engaging with diverse communities and industries to discuss the geopolitics of knowledge production in computing research and design. Our proposal builds on existing works that have explored the modalities of the knowledge economy - particularly as knowledge is created, legitimized, and circulated as objective truth via the exercise of power. For example, engaging indigenous communities in conferences and knowledge fairs have sought to challenge disciplinary silos and boundaries imposed on non-Western academics and practitioners. This workshop, as a platform for interaction and discussion with no “sage on the stage”, is the first of its kind within AfriCHI and it seeks to explore and promote more subtle discussions about HCI knowledge production and dissemination practices.

关键词： African HCI Critical fabulation Decolonizing HCI Indigenous knowledge alt.HCI

A Review of Artificial Fish Swarm Algorithms: Recent Advances and applications

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Pourpanah, Farhad Wang, Ran Lim, Chee Peng Wang, Xi-Zhao Yazdani, Danial College of Mathematics and Statistics Guangdong Key Lab. of Intelligent Information Processing Shenzhen University China Department of Electrical and Computer Engineering University of Windsor Canada College of Mathematics and Statistics Shenzhen Key Lab. of Advanced Machine Learning and Applications Guangdong Key Lab. of Intelligent Information Processing Shenzhen University China Institute for Intelligent Systems Research and Innovation Deakin University Australia College of Computer Science and Software Engineering Guangdong Key Lab. of Intelligent Information Processing Shenzhen University China School of Computer Science and Engineering Southern University of Science and Technology China

The Artificial Fish Swarm Algorithm (AFSA) is inspired by the ecological behaviors of fish schooling in nature, viz., the preying, swarming and following behaviors. Owing to a number of salient properties, which include flexibility, fast convergence, and insensitivity to the initial parameter settings, the family of AFSA has emerged as an effective Swarm Intelligence (SI) methodology that has been widely applied to solve real-world optimization problems. Since its introduction in 2002, many improved and hybrid AFSA models have been developed to tackle continuous, binary, and combinatorial optimization problems. This paper aims to present a concise review of the continuous AFSA, encompassing the original ASFA, its improvements and hybrid models, as well as their associated applications. We focus on articles published in high-quality journals since 2013. Our review provides insights into AFSA parameters modifications, procedure and sub-functions. The main reasons for these enhancements and the comparison results with other hybrid methods are discussed. In addition, hybrid, multi-objective and dynamic AFSA models that have been proposed to solve continuous optimization problems are elucidated. We also analyse possible AFSA enhancements and highlight future research directions for advancing AFSA-based models. Copyright © 2020, The Authors. All rights reserved.

关键词： Multiobjective optimization