检索结果-内蒙古大学图书馆

5th International Conference on Inventive research in Computing Applications, ICIRCA 2023

作者： Tanwar, Shashi Thokala, Rishi Reddy Thapak, Sonika Maranan, Ramya Kumar, Sudheer Sravanthi, S. Aravali College of Engineering and Management Department of Computer Science and Engineering Haryana Faridabad India Srm Institute of Science and Technology Computer Science Engineering India Ies Collage of Technology Computer Science and Engineering India Saveetha School of Engineering Simats Department of Research and Innovation Tamil Nadu Chennai602105 India Piet Parul University Computer Science & Engineering Gujrat Vadodara India St. Martin's Engineering College Department of Computer Science Engineering secunderabad India

ISBN: (纸本)9798350321425

It is crucial for network security to be able to detect a variety of threats and unusual network traffic. In order to accomplish aberrant traffic detection, existing detection methods required enormous volumes of data. However, there are rare circumstances in which even a fewshot attack sample can be stopped. The shift in feature attitude will also have an impact on traffic attribute discrimination. However, the standard neural network model is unable to recognize this shift in perspective. As a result, few-shot sample anomalous traffic detection has poor accuracy and efficiency. This research has proposed a strategy for detecting unusual network traffic with a small number of samples. Multi-scale Deep-CapsNet and adversarial-reconstruction (MDAR) made up the system. To begin, the Deep-CapsNet's EM vector clustering is revamped. The prediction is finalized by transforming low-level to high-level features using the attitude transformation matrix. Second, the Deep-CapsNet was improved with the help of a multi-scale convolutional capsule. Finally, a reconstruction classification network (ARCN) that is vulnerable to adversarial input is proposed. Classification of the supervised source data and reconstruction of the unsupervised target data are both completed. In addition, an adversarial training technique that reduced the impact of noise on the reconstruction process is suggested. Using a mixture of MDAR, classification is obtained from a small number of samples (point 4). The results are tested on the ICSX2012 and CICIDS2017 datasets. The experimental outcomes validate the superior training performance of the approach. Additionally, its accuracy is unparalleled in both two- and multi-classification tasks. It is especially useful for real-time few-shot aberrant network traffic detection because to its good anti-noise performance and quick operating time. © 2023 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Driven Possibilistic Clustering with Automatic Cluster Elimination

引用

computers, Materials & Continua 2024年第9期80卷 4917-4945页

作者： Xianghui Hu Yiming Tang Witold Pedrycz Jiuchuan Jiang Yichuan Jiang The School of Computer Science and Engineering Southeast UniversityNanjing211189China The School of Computer and Information Hefei University of TechnologyHefei230601China The Department of Electrical and Computer Engineering University of AlbertaEdmontonAB T6R 2V4Canada The Systems Research Institute Polish Academy of SciencesWarsaw00-901Poland The School of Information Engineering Nanjing University of Finance and EconomicsNanjing210023China

Traditional Fuzzy C-Means(FCM)and Possibilistic C-Means(PCM)clustering algorithms are data-driven,and their objective function minimization process is based on the available numeric ***,knowledge hints have been introduced to formknowledge-driven clustering algorithms,which reveal a data structure that considers not only the relationships between data but also the compatibility with knowledge ***,these algorithms cannot produce the optimal number of clusters by the clustering algorithm itself;they require the assistance of evaluation ***,knowledge hints are usually used as part of the data structure(directly replacing some clustering centers),which severely limits the flexibility of the algorithm and can lead to *** solve this problem,this study designs a newknowledge-driven clustering algorithmcalled the PCM clusteringwith High-density Points(HP-PCM),in which domain knowledge is represented in the form of so-called high-density ***,a newdatadensitycalculation function is *** Density Knowledge Points Extraction(DKPE)method is established to filter out high-density points from the dataset to form knowledge ***,these hints are incorporated into the PCM objective function so that the clustering algorithm is guided by high-density points to discover the natural data ***,the initial number of clusters is set to be greater than the true one based on the number of knowledge ***,the HP-PCM algorithm automatically determines the final number of clusters during the clustering process by considering the cluster elimination *** experimental studies,including some comparative analyses,the results highlight the effectiveness of the proposed algorithm,such as the increased success rate in clustering,the ability to determine the optimal cluster number,and the faster convergence speed.

关键词： Fuzzy C-Means(FCM) possibilistic clustering optimal number of clusters knowledge-driven machine learning fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Accelerating Medical Visual Question Answering by Image Rearrangement 21

Accelerating Medical Visual Question Answering by Image Rear...

引用

21st International computer Conference on Wavelet Active Media technology and Information Processing, ICCWAMTIP 2024

作者： Han, Wang Lei, Zhao Center for Future Media The School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu610000 China Sichuan Artificial Intelligence Research Institute Yibin China

ISBN: (纸本)9798331519254

Medical Visual Question Answering is designed for supporting clinical diagnosis by leveraging advanced language and visual comprehension ability. While Large Vision-Language Models offer medical visual question answering powerful generative and interpretative capabilities, they encounter significant computational challenges due to quadratic complexity that scales with sequence length, especially as image embeddings dominate the input sequence. To address this, we propose an Image Rearrangement algorithm, which reduces the number of image embeddings with minimal impact on model performance. The Image Rearrangement algorithm aggregates similar image embeddings based on their relative alignment to text embeddings. We evaluate the Image Rearrangement algorithm method across three distinct datasets using two medical visual question answering models, observing that the Image Rearrangement algorithm achieves substantial computational savings while maintaining diagnostic accuracy. © 2024 IEEE.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Effective Traffic Model for Intelligent Traffic Monitoring Enabled Deep RNN Algorithm for Autonomous Vehicles Surveillance Systems 4

Effective Traffic Model for Intelligent Traffic Monitoring E...

引用

4th International Conference on Smart Electronics and Communication, ICOSEC 2023

作者： Leelavathy, S. Nithya, M. Dhaya, R. Muthuselvan, S. Kanthavel, R. Rajakumari, K. Department of Computer Science and Engineering Chennai India Salem India Department of Computer Science and Engineering Salem India Kcg College of Technology Department of Information Technology Chennai India School of Cse Hindustan Institute of Technology of Science and Technology Chennai India Bharath Institute of Higher Education and Research Chennai India

ISBN: (纸本)9798350300888

Regardless of the terrain, weather, visibility, or road surface conditions, improving detection and forecast accuracy is a critical priority for autonomous cars. Little shifts in the images to be collected should be understood even in low-light settings because the vehicle needs more data to make a binding judgment. As a subfield of AI and DL, Recurrent Neural Networks (RNNs) are structured with temporally aware connections between their nodes. As a result, the network can engage in sequential action driven entirely by internal incentives for an extended period. Moreover, cars require enormous computational capacity and a substantial quantity of data sets in an autonomous environment, such as unexpected events, opposing movement, lane conditions, and indestructible barriers. This study presents an effective deep recurrent neural network (Deep RNN) technique for autonomous cars to meet the need for recurrent nodes and capture sequence patterns within the acquired data. In addition, this study shows how to use deep RNN for efficient data annotation. Simulated findings show a significant drop in error when the proposed Deep RNN is utilized in autonomous cars. © 2023 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

AI-Enhanced Virtual Twin Modelling for Strengthening IoT Software Security Protocols 1

AI-Enhanced Virtual Twin Modelling for Strengthening IoT Sof...

引用

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

作者： Kumara, Bharath Barmola, Pareshwar Prasad Arora, Renuka Parikh, Swapnil M Maranan, Ramya Ramaiah University of Applied Science Department of Electronics and Communication Engineering Bengaluru India Graphic Era Deemed to Be University Department of Computer Science and Engineering Dehradun India Jagannath University Department of Computer Science and Engineering Haryana India Parul Institute of Engineering and Technology Parul University Faculty of Computer Science and Engineering Vadodara India Simats Saveetha School of Engineering Department of Research and Innovation Chennai India

ISBN: (纸本)9798350352931

To fortify security mechanisms in software systems for the Internet of Things (IoT), this article presents a framework for AI-Enhanced Virtual Twin Modelling. In order to track and examine the actions of IoT devices in real-time, the suggested method makes use of virtual twin technology that is combined with machine learning techniques. Automated response generation, continuous threat assessment, and anomaly detection are made possible by creating a digital clone of the actual IoT network using the virtual twin paradigm. By combining deep learning models like CNNs and LSTMs, it becomes easier to forecast possible security risks in network traffic data by seeing intricate spatial and temporal patterns. When tested in a virtual Internet of Things (IoT) setting, the suggested framework outperforms conventional rule-based approaches by a wide margin, reducing reaction time by 35% while achieving an accuracy of 9 6. 2 %in threat identification. © 2024 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Quantified Analysis of Highly Efficient Halide Perovskite Solar Cell 8

Quantified Analysis of Highly Efficient Halide Perovskite So...

引用

8th IEEE International Conference for Convergence in technology, I2CT 2023

作者： Pharne, Indrajit D. Patil, Santosh V. Rana, Ashish D. Bhargava, Kshitij Institute of Infrastructure Technology Research and Management Department of Electrica & Computer Science Engineering Ahmedabad380026 India Sanjay Ghodawat University Kolhapur416118 India Institute of Infrastructure Technology Research and Management Department of Electrical & Computer Science Engineering Ahmedabad380026 India Annasaheb Dange College of Engineering and Technology Maharashtra Ashta416301 India

ISBN: (纸本)9798350334012

This study focuses on designing of lead halide-based perovskite solar cell (PSC). PSCs have achieved an efficiency above 20% within 10-12 years of active research. Methyl ammonium lead iodide (MAPbI3) based PSCs have emerged as a promising replacement for silicon solar cells [1], [2]. The electron and hole transport layers (ETLs and HTLs) have an important role in the performance of PSCs. Here, we investigate the effect of various combinations of ETLs and HTLs for achieving optimized high-efficiency MAPbI3-based PSCs using SCAPS-1D. The selected ETLs were SnO2, TiO2, PCBM, WS2, and ZnO and HTLs were Cu2O, CuI, CuSCN, PEDOT: PSS, Spiro-OMeTAD. A total of 25 cells were analyzed to achieve maximum power conversion efficiency. The best efficiency of 23.7% was yielded by a cell having PCBM as ETL and Cu2O as HTL. The simulated J-V characteristics and performance metrics are shown in Figure. © 2023 IEEE.

关键词： Lead compounds

来源：评论

学校读者我要写书评

暂无评论

Surface flashover in 50 years:Theoretical models and competing mechanisms

引用

High Voltage 2023年第5期8卷 853-877页

作者： Zhen Li Ji Liu Yoshimichi Ohki George Chen He Gao Shengtao Li Key Laboratory of Engineering Dielectrics and Its Application Ministry of EducationHarbin University of Science and TechnologyHarbinChina State Key Laboratory of Electrical Insulation and Power Equipment Xi'an Jiaotong UniversityXi'anChina Research Institute for Materials Science and Technology Waseda UniversityShinjuku‐kuJapan School of Electronics and Computer Science University of SouthamptonSouthamptonUK

Surface flashover is a devastating electronic avalanche along the gas–solid interface when a high electric field is applied,which is a potential issue that threatens the safe operations of advanced power electronic,electrical,and spacecraft ***,the underlying physical mechanisms for surface flashover development are still under investigation owing to the complex charge transport processes through the gas phase,solid phase,and gas–solid *** this study,the history of surface flashover theory in the last 50 years is introduced,and several key questions are reviewed from the perspective of the competing mechanisms of charge transport:the role of each phase in a surface flashover,the origin of surface charging,and effects of traps in solid on surface ***,some suggestions involve charge transport processes in each phase,and their correlations are put forward,and a predictable‘charge transport competitive flashover model’is proposed by clarifying the competing mechanisms of charge transport processes through multiple *** study summarises the history and hot topics of physical mechanisms of surface flashover proposed based on classic and recent progress and offers promising routes for developing a more precise surface flashover theory and improving surface flashover performances.

关键词： flash transport charge

来源：评论

学校读者我要写书评

暂无评论

Parameterized Complexity of Shortest Path with Positive Disjunctive Constraints 17th

Parameterized Complexity of Shortest Path with Positive Di...

引用

17th International Conference on Combinatorial Optimization and Applications, COCOA 2024

作者： Bandopadhyay, Susobhan Banerjee, Suman Majumdar, Diptapriyo Panolan, Fahad National Institute of Science Education and Research An OCC of Homi Bhabha National Institute Odisha Bhubaneswar India Department of Computer Science and Engineering Indian Institute of Technology Jammu India Indraprastha Institute of Information Technology Delhi New Delhi India School of Computer Science University of Leeds Leeds United Kingdom

ISBN: (纸本)9789819644476

We study the Shortest Path problem subject to positive binary disjunctive constraints. In positive disjunctive constraints, there are certain pairs of edges such that at least one edge from every pair must be part of every feasible solution. We initiate the study of Shortest Path with binary positive disjunctive constrains from the perspective of parameterized complexity. Formally, the input instance is a simple unidirected graph G=(V,E), a forcing graph Gf=(E,E′), two vertices s,t∈V(G) and an integer k. Note that the vertex set of Gf is the same as the edge set of G. The goal is to find a set S of at most k edges from G such that there is a path from s to t in the subgraph G=(V,S) and S is a vertex cover in Gf. In this paper, we consider two different natural parameterizations for this problem. One natural parameter is the solution size, i.e. k for which we provide FPT algorithms and polynomial kernelization results. The other natural parameters are structural parameterisations of Gf, i.e. the size of a modulator X⊆E(G)=V(Gf) such that Gf-X belongs to some hereditary graph class. We discuss the parameterized complexity of this problem under some structural parameterizations. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Zebra Optimization Algorithm with Chaotic Sinusoidal Map for Versatile Optimization

Iraqi Journal for Computer Science and Mathematics

引用

Iraqi Journal for computer science and Mathematics 2024年第1期5卷 307-319页

作者： Anand, D. Khalaf, Osamah Ibrahim Chandra, G. Rajesh Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation GreenFileds A.P Vaddeswaram522302 India Department of Solar Al-Nahrain Research Center for Renewable Energy Al-Nahrain University Jadriya Baghdad Iraq Department of Computer Science and Engineeirng KKR & KSR Institute of Technology and Sciences Andhra Pradesh India

In this study, the Chaotic Sinusoidal Map (CSM)-enhanced Zebra Optimization Algorithm (CZOA) is introduced. CZOA combines CSM's integration strengths with ZOA's optimization skills. ZOA already exhibits great optimization capabilities, but the addition of CSM increases its potential even more. This addition greatly strengthens ZOA's exploration and exploitation skills and increases its flexibility for various optimization tasks. CZOA outperforms both the original ZOA and contemporary optimisation methods on 23 benchmark functions, including high-dimensional (FD), multimodal (MM), and unimodal (UM) challenges. Using the chaos of CSM to investigate regional optimal and determine better convergence and exploration-exploitation equilibrium are shown by CZOA, which also shows more profitable solution locations. CZOA demonstrates its resilience and versatility through multiple benchmark activities, underscoring its potential as an adaptable optimisation tool. CZOA becomes a potent metaheuristic by combining biological inspiration and chaotic dynamics to solve difficult optimisation problems. Inspired by the natural behaviour of zebras, the Zebra Optimisation Algorithm (ZOA) is a relatively new optimisation technique. It makes use of a herd behaviour mechanism and the ideas of leadership and following, in which members of the population—zebras in this case—cooperate to solve optimisation issues in the best possible ways. A chaotic sinusoidal map can improve the ZOA's exploitation and exploration capabilities, increasing its adaptability for optimisation across a range of problem *** success of CZOA and its potential as a potent © 2024 College of Education, Al-Iraqia University. All rights reserved.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Quantum Generative Adversarial Network for Autonomous Drone Navigation in Urban Wind Zones 6

Quantum Generative Adversarial Network for Autonomous Drone ...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Swarnalatha, Anumula Archana, Nalluri Mukkapati, Naveen Selvakumar, Subramanian Tamir, Eneyachew Manikandaprabu, P. Department of Aeronautical and Aerospace Engineering KCG College of Technology Tamil Nadu Chennai600097 India Department of Computer Science and Engineering Vignan's Foundation for Science Technology and Research Andhra Pradesh 522213 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh 522502 India Department of Computer Engineering Bahir Dar Institute of Technology Bahir Dar University Bahir Dar Ethiopia Department of Electrical and Computer Engineering Bahir Dar Institute of Technology Bahir Dar University Bahir Dar Ethiopia Department of Mechanical Engineering Sona College of Technology Tamil Nadu Salem636005 India

ISBN: (纸本)9798331522667

Major challenges are observed when autonomous drones fly in the complex, changeable environment such as wind zones regarding accurate path planning, avoiding the object, and completing tasks. Lack of flexibility in different situations reduces the reliability of conventional models in real time. To overcome these difficulties the Savitzky-Golay Denoising CSWin Quantum Generative Adversarial Network with Emperor Penguin Optimizer known as SGDCQGANNet-EPO was developed. The RGB data and GPS-estimated wind forces in this model undergo Savitzky-Golay Denoising;this model does not rely on global data, only RGB camera data and GPS data. Recently a CSWin transformer (CSWin-T) makes feature extraction and obstacles detection as well as wind angle, wind speed and wind position identification easier. Quantum Generative Adversarial Networks (QGANet) are then used for optimized path planning, and the model is enhanced by the Emperor Penguin Optimizer (EPO) to fine tune the generator and discriminator loss functions. More accurate compared to current approaches in accuracy and efficiency, the model achieves an accuracy of 99.28%, a low RMSE of 0.38, a recall of 99.25%, and EVA of 0.95. In Confidence using this new technique, the free roaming and self-organizing drone maneuvers in complex environments achieved remarkable results. © 2025 IEEE.

关键词： Generative adversarial networks

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：