检索结果-内蒙古大学图书馆

Spin angular momentum engineering within highly localized focal fields: from simple orientation to complex topologies

引用

Photonics Research 2025年第4期13卷 995-1009页

作者： YONGXI ZENG YANZHONG YU JIAN CHEN HOUAN TENG MUSHENG CHEN PINGHUI WU QIWEN ZHAN College of Physics and Information Engineering Quanzhou Normal University School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Fujian Provincial Key Laboratory for Advanced Micro-nano Photonics Technology and Devices & Key Laboratory of Information Functional Material for Fujian Higher Education

Optical skyrmions, as quasiparticles with non-trivial topological structures, have garnered significant attention in recent years. This paper proposes a method for customized spin angular momentum (SAM) distribution in highly localized focal fields, thereby enabling the generation of SAM skyrmion and bimeron topologies. The skyrmionic SAM textures can be flexibly controlled, such as polarity, vorticity, and helicity. In addition, the two-dimensional projection plane can be arbitrarily oriented within three-dimensional space.

关键词： Bose Einstein condensates Circular polarization information processing Light matter interactions Optical fields Optical manipulation

来源：评论

学校读者我要写书评

暂无评论

Intrusion detection system using soft computing techniques in 5G communication systems

Intrusion detection system using soft computing techniques i...

引用

International Conference on Artificial Intelligence, Blockchain, Computing and Security, ICABCS 2023

作者： Dhanya, D. Shankari Kathir, I. Kuchipudi, Ramu Thamarai, I. Kumar, E. Rajesh Department of Computer Science and Engineering Mar Ephraem College of Engineering and Technology Tamil Nadu Kanyakumari India Department of Computer Science and Engineering RMK College of Engineering and Technology Tamil Nadu Thiruvallur India Department of Electrical and Electronics Engineering V.S.B. Engineering College Tamil Nadu Karur India Department of Information Technology Chaitanya Bharathi Institute of Technology Telangana Hyderabad India Department of Computer Science and Engineering Panimalar Engineering College Chennai City Campus Tamil Nadu Chennai India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India

ISBN: (纸本)9781032669663

The research deals with a thorough survey and starts by reviewing the fundamental knowledge of fuzzy systems over 5G communication. Future directions and scope can be used to demonstrate the desire for 5G communication networks to provide access to new applications and widespread connection. Therefore, the difficulties with the underlying technologies and hardware supporting them should allow for a greater level of service quality. The goal of this study is to create an intrusion detection system that employs fuzzy logic. This study proposes a model for a real-time intrusion detection expert system that seeks to find a variety of security breaches, from outsiders trying to break in to insiders breaking in and abusing the system. Analysis has also been done on the impact of changing the learning algorithms and membership function. The structure can manage very sizeable amount of data with the aid of data collection, storage, retrieval, and analysis, and it integrates the big data stream inside the network to enhance performance of the network. © 2024 The Author(s).

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Rapid Chaotic-based Image Encryption by Combining Chaotic and Non-Chaotic Scrambling Techniques 7

Rapid Chaotic-based Image Encryption by Combining Chaotic an...

引用

7th International Conference on Computing Methodologies and Communication, ICCMC 2023

作者： Siva Malar, R. Uma Perumal Umi Salma, B. Komarasamy, Dinesh Department of Information Technology Jazan University Ministry of Higher Education Jazan Saudi Arabia Department of Computer Science Jazan University Ministry of Higher Education Jazan Saudi Arabia Department of Computer Science and Engineering Kongu Engineering College Tamil Nadu Perunthurai India

ISBN: (纸本)9781665464086

Image encryption has been an appealing and exciting area for researchers recently. Many techniques attempt to enhance the security of images for storing in social media. Chaos theory is frequently used for image encryption due to its unpredictable nature. The classical chaotic based encryption methods are complex in structure and difficult to implement for providing high level securities. In order to solve these issues, anew method for encrypting images using Chaotic Maps (CMs) is proposed in this paper. Initially, a Logistic-S ine-Cosine (LS C)based CM is employed to generate various scrambling functions, such as Zigzag transform, Magic confusion, and Row confusion, and then these scrambling functions are used to modify pixel values to identify a linearity element. Then, these adjusted values are mixed with additional arbitrary sequence generated using the Logistic Cubic Cosine (LCC) based CM. Finally, the pre - encrypted images are combined together so that the generated randomness is dispersed uniformly throughout them. The combination of CM with scrambling functions not only improves security but also accelerates the speed of encryption. © 2023 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Compression-Based Image Retrieval for Efficient Networked Applications 15

Compression-Based Image Retrieval for Efficient Networked Ap...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Kuppuraj, T. Baxi, Paramjit Velusudha, N.T. Goyal, Samaksh Pavan, P.S. Bagade, Jayashree V. Karpagam Academy of Higher Education Department of Computer Applications Coimbatore India Chitkara University Institute of Engineering and Technology Centre for Interdisciplinary Research for Business and Technology Punjab India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electronics and Communication Engineering Chennai India Quantum University Research Center Quantum University India School of Engineering and Technology Civil Engineering Karnataka Bangalore India Vishwakarma Institute of Information Technology Department of Information Technology Pune India

ISBN: (纸本)9798350370249

Compression-based total photograph retrieval (CBIR) is a method that is used to retrieve pictures from big datasets correctly. Unlike traditional photo retrieval methods, CBIR utilizes lossless or loss compression algorithms to lessen the scale of the image statistics for transmission over a network connection. That is particularly useful in programs wherein transmitting cumbersome image statistics is only sometimes viable. With the aid of compressing the facts related to a photo and sending only the compressed version, transmission instances are significantly decreased, even though nonetheless maintaining the visual first-rate and integrity of the photo. This makes CBIR a possible choice for packages consisting of streaming video, medical imaging, far-flung sensing, and massive-scale surveillance systems. CBIR also has packages in multimedia databases and different networked structures that require efficient image retrieval and viewing. © 2024 IEEE.

关键词： Algorithms Efficient Photograph Retrieve Significantly Traditional

来源：评论

学校读者我要写书评

暂无评论

Analysing Student Depression through Cyber-Activity Patterns Using Heterogeneous Graph Attention Networks 1

Analysing Student Depression through Cyber-Activity Patterns...

引用

1st International Conference on Software, Systems and information technology, SSITCON 2024

作者： Shukla, Tushar Dhar Vanyan, Diana Rizvi, Qaim Mehdi George, Geogen Bhosale, Aryaraj Dattatraya Bhoopathy, V. University Institute of Physical Education & Sports Chandigarh University Department of Physical Education Mohali India Kuban State University Krasnodar Russia Kolkata India University of Technology and Applied Sciences College of Computing and Information Sciences Middle East Ibri Oman Indian Institute of Information Technology Pune India Sree Rama Engineering College Department of Computer Science and Engineering Tirupathi India

ISBN: (纸本)9798350352931

This study focusses on the crucial matter of identifying student sadness by analysing patterns of cyberactivity. The technology utilizes Heterogeneous Graph Attention Networks (HGATs) to represent and examine intricate connections within the data. The dataset used for training and testing the model was obtained from Kaggle. The model achieved an accuracy of 9 6. 8 %, a precision of 9 5. 4 %, a recall of 94.7 %, and an AUC-ROC of 98.3 %. The findings of this study demonstrate a substantial improvement over current models, indicating the high efficacy of HGATs in accurately capturing complex patterns in cyber-activity data. The results indicate that this method can function as a potent instrument for identifying depression at an early stage, with wide-ranging implications for monitoring the mental health of students and implementing intervention techniques. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Bridging Automated Reasoning and Machine Learning for information Analysis 2

Bridging Automated Reasoning and Machine Learning for Inform...

引用

2nd IEEE International Conference on Futuristic Technologies, INCOFT 2023

作者： Joshi, Sarita Murugan, R. Balaji, N.V. Chandrakala, P. Deshmukh, Gopal B. Mathur, Mala Maharishi School of Business Management Maharishi University of Information Technology Uttar Pradesh India Bangalore Department of Computer Science and Information Technology Karnataka India Karpagam Academy of Higher Education Department of Computer Science Coimbatore641021 India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electrical and Electronics Engineering Chennai127 India Vishwakarma Institute of Information Technology Department of Computer Engineering Pune India Vivekananda Global University Department of Civil Engineering Jaipur India

ISBN: (纸本)9798350308846

Recent advances in automated reasoning and system studying have appreciably impacted the automation of statistics evaluation. These technologies facilitate understanding the increasingly more complicated volumes of facts in a ramification of approaches. Automatic reasoning helps decide valid solutions based on structured good judgment, while machines can pick out patterns and developments in massive datasets. Bridging those two technologies improves accuracy and efficiency in automated facts evaluation. This paper will overview present-day research on bridging automated reasoning and device-gaining knowledge for such purposes and gift novel approaches to combining the two technologies for more effective data evaluation. Discussion subjects will encompass integrating neural networks and reasoning engines, methods for addressing records incompleteness and uncertainty, and enhancement of reasoning-driven context-conscious systems. Furthermore, the paper will discover the capacity benefits that can be performed via leveraging the strengths of each automated reasoning and gadget gaining knowledge of to optimize answers for a selection of software scenarios. © 2023 IEEE.

关键词： Gaining Optimize Reasoning Selection Uncertainty

来源：评论

学校读者我要写书评

暂无评论

TagOOD: A Novel Approach to Out-of-Distribution Detection via Vision-Language Representations and Class Center Learning 24

TagOOD: A Novel Approach to Out-of-Distribution Detection vi...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Li, Jinglun Zhou, Xinyu Jiang, Kaixun Hong, Lingyi Guo, Pinxue Chen, Zhaoyu Ge, Weifeng Zhang, Wenqiang Shanghai Engineering Research Center of Ai & Robotics Academy for Engineering & Technology Fudan University China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Engineering Research Center of Ai & Robotics Ministry of Education Academy for Engineering & Technology Fudan University China

ISBN: (纸本)9798400706868

Multimodal fusion, leveraging data like vision and language, is rapidly gaining traction. This enriched data representation improves performance across various tasks. Existing methods for out-of-distribution (OOD) detection, a critical area where AI models encounter unseen data in real-world scenarios, rely heavily on whole-image features. These image-level features can include irrelevant information that hinders the detection of OOD samples, ultimately limiting overall performance. In this paper, we propose TagOOD, a novel approach for OOD detection that leverages vision language representations to achieve label-free object feature decoupling from whole images. This decomposition enables a more focused analysis of object semantics, enhancing OOD detection performance. Subsequently, TagOOD trains a lightweight network on the extracted object features to learn representative class centers. These centers capture the central tendencies of IND object classes, minimizing the influence of irrelevant image features during OOD detection. Finally, our approach efficiently detects OOD samples by calculating distance-based metrics as OOD scores between learned centers and test samples. We conduct extensive experiments to evaluate TagOOD on several benchmark datasets and demonstrate its superior performance compared to existing OOD detection methods. This work presents a novel perspective for further exploration of multimodal information utilization in OOD detection, with potential applications across various tasks. Code is available at: https://***/Jarvisgivemeasuit/tagood. © 2024 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

GeoNER:Geological Named Entity Recognition with Enriched Domain Pre-Training Model and Adversarial Training

引用

Acta Geologica Sinica(English Edition) 2024年第5期98卷 1404-1417页

作者： MA Kai HU Xinxin TIAN Miao TAN Yongjian ZHENG Shuai TAO Liufeng QIU Qinjun Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering China Three Gorges UniversityYichangHubei 443002China College of Computer and Information Technology China Three Gorges UniversityYichangHubei 443002China Key Laboratory of Geological Survey and Evaluation of Ministry of Education China University of GeosciencesWuhan 430074China School of Computer Science China University of GeosciencesWuhan 430074China Key Laboratory of Quantitative Resource Evaluation and Information Engineering Ministry of Natural ResourcesChina University of GeosciencesWuhan 430074China

As important geological data,a geological report contains rich expert and geological knowledge,but the challenge facing current research into geological knowledge extraction and mining is how to render accurate understanding of geological reports guided by domain *** generic named entity recognition models/tools can be utilized for the processing of geoscience reports/documents,their effectiveness is hampered by a dearth of domain-specific knowledge,which in turn leads to a pronounced decline in recognition *** study summarizes six types of typical geological entities,with reference to the ontological system of geological domains and builds a high quality corpus for the task of geological named entity recognition(GNER).In addition,Geo Wo BERT-adv BGP(Geological Word-base BERTadversarial training Bi-directional Long Short-Term Memory Global Pointer)is proposed to address the issues of ambiguity,diversity and nested entities for the geological *** model first uses the fine-tuned word granularitybased pre-training model Geo Wo BERT(Geological Word-base BERT)and combines the text features that are extracted using the Bi LSTM(Bi-directional Long Short-Term Memory),followed by an adversarial training algorithm to improve the robustness of the model and enhance its resistance to interference,the decoding finally being performed using a global association pointer *** experimental results show that the proposed model for the constructed dataset achieves high performance and is capable of mining the rich geological information.

关键词： geological named entity recognition geological report adversarial training confrontation training global pointer pre-training model

来源：评论

学校读者我要写书评

暂无评论

Optimizing Object Detection Efficiency for Autonomous Vehicles through the Integration of YOLOv4 and EfficientDet Algorithms 2

Optimizing Object Detection Efficiency for Autonomous Vehicl...

引用

2nd IEEE International Conference on Trends in Quantum Computing and Emerging Business Technologies, TQCEBT 2024

作者： Rajan, V. Aravinda Sakhamuri, Sridevi Nayaki, A Periya Agarwal, Swathi Aeron, Anurag Lawanyashri, M. Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Krishnankovil India Department of IoT Koneru Lakshmaiah Education Foundation Vaddeswaram Guntur India Velammal College of Engineering and Technology Department of Information Technology Tamilnadu Madurai India Cvr College of Engineering Department of It Hyderabad India Miet Meerut Department of Cse Meerut India Vellore Institute of Technology Score Vellore India

ISBN: (纸本)9798350384277

Advancements in autonomous vehicles are highly dependent on object detection systems that need to balance accuracy and speed. This paper addresses the comparative analysis of three object detection algorithms such as integrated YOLOv4-EfficientDet model, stand alone YOLOv4, and stand alone EfficientDet for improved efficiency in autonomous vehicles. Yet the integrated YOLOv4-EfficientDet model, which is the result of a merger of real-time capabilities of the YOLOv4 and computational efficiency of the EfficientDet, turns out to be the best one. It attains the best Mean Average Precision (mAP) of 0.85 compared with the other algorithms, which indicates an excellent object detection accuracy. With a slightly decreased inference speed of 45 FPS frames per second, the integrated model shows a good balance between accuracy and speed. However, the standalone YOLOv4, known for its speed of 55 FPS, has a lower mAP value of 0.78. Although it gains a respectable mAP score of 0.82, the Standalone EfficientDet falls behind in inference speed at 35 FPS. Our comparative analysis highlights the utility of the YOLOv4-EfficientDet model in improving the efficiency of object detection for autonomous automobiles. It offers a convincingly accurate solution with a reasonable inference speed. The selection between these algorithms should focus on the unique needs and constraints of the autonomous vehicle system. This study's findings highlight the potential of using integrated models to improve the ability of autonomous vehicles to perceive their environment, making them safe and reliable on the roadways. © 2024 IEEE.

关键词： Autonomous Vehicles Efficiency EfficientDet Integration Object Detection YOLOv4

来源：评论

学校读者我要写书评

暂无评论

Enhancing Lung Disease Identification with Multimodal Data Fusion and Deep Learning CNN Approach 5

Enhancing Lung Disease Identification with Multimodal Data F...

引用

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Grace Shalini, T. Shiny, G. Susan Saranya, R. Suresh Babu, P. Kavitha, R. Atheeswaran, Athiraja Srm Institute of Science and Technology School of Computing Department of Computational Intelligence Chengalpattu Kattankulathur India Sethu Institute of Technology Department of information technology Kariapatti India Velammal college of engineering and technology Department of Eee Madurai India Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Krishnankoil India Bannari Amman Institute Of Technology Department Of Computer Science And Engineering Erode Sathyamangalam India Hyderabad India

ISBN: (纸本)9798331504403

Lung diseases, encompassing a wide spectrum from chronic conditions to acute infections, present a significant burden on global healthcare systems, necessitating precise and timely diagnostic methodologies. In this study, we propose a pioneering approach leveraging multimodal data fusion and deep learning Convolutional Neural Network (CNN) algorithms for enhanced identification of lung diseases. Our methodology integrates diverse data sources including medical images, clinical reports, and patient demographics to capture a comprehensive representation of lung pathology. We employ a state-of-the-art CNN architecture for medical image analysis, trained on a large-scale dataset encompassing various lung diseases and healthy lung tissue. Through extensive experimentation and validation, the approach achieved remarkable performance, with an accuracy of 94%, sensitivity of 92%, specificity of 93%, and an F1-score of 93% in accurately identifying and classifying lung abnormalities. Furthermore, we demonstrate the clinical utility of our method in providing valuable insights to healthcare professionals, aiding in timely diagnosis, prognosis, and treatment planning. Our findings highlight the potential of multimodal data fusion coupled with deep learning CNN algorithms in advancing the field of lung disease identification, offering a promising avenue for improving healthcare practices and patient outcomes in respiratory medicine. © 2024 IEEE.

关键词： Lung cancer

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：