检索结果-内蒙古大学图书馆

5th International Conference on data science, Machine Learning and Applications, ICDSMLA 2023

作者： Sivaraman, Himani Tembhre, Sh obhit Mishra, Awakash Gobi, N. Department of Computer Science and Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Navgaon Manduwala Dehradun India School of Computer Science and Engineering Presidency University Karnataka Bengaluru India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Karnataka Bangalore India

ISBN: (纸本)9789819780426

This paper explores the performance of clustered neural community aggregators (CNNA) for time series. Through the years, time collection evaluation has allowed for insights into numerous phenomena, ranging from low cost to environmental and organic and clustered neural networks’ purpose to provide higher outcomes via mixing a couple of neural networks. However, their effectiveness has yet to be thoroughly studied in time collection. In this paper, several CNNA architectures are compared against their non-clustered equivalents, and the results are evaluated across an expansion of time collection datasets. Additionally, the overall performance of different clustering algorithms is studied in terms of clustering first-class and time cost. The outcomes show that, compared to non-clustered fashions, CNNA can substantially enhance the prediction performance of time collection and that the effectiveness of various types of clustering algorithms depends substantially on the kind of time collection analyzed. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： effectiveness fashions substantially

来源：评论

学校读者我要写书评

暂无评论

An Evaluation of Hashing and Other Applied Cryptography Algorithms 5th

An Evaluation of Hashing and Other Applied Cryptography Algo...

引用

5th International Conference on data science, Machine Learning and Applications, ICDSMLA 2023

作者： Mishra, Awakash Haripriya Sharma, Apurva Thomas, Jobin S. Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Karnataka Bengaluru India Department of Computer Science and Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Navgaon Manduwala Dehradun India School of Computer Science and Engineering Presidency University Karnataka Bengaluru India

ISBN: (纸本)9789819780426

In the modern digital world, cryptography is critical in protecting personal statistics. Most of the cryptography algorithms used to ease data, hashing, and other implemented cryptography algorithms are extensively used. Hashing refers to transforming plaintext or every other form of statistics into unreadable ciphertext. This type of encryption is used primarily to store passwords, authentication records, and other touchy records. Other applied cryptography algorithms include symmetric encryption, uneven encryption, and key exchanges. In this paper, an assessment of hashing and different implemented cryptography algorithms is conducted. The evaluation will be conscious of each of those algorithms’ distinctive traits, strengths, weaknesses, and safety concerns. The review also appears in the scenarios wherein one-of-a-kind algorithms can be carried out. It is followed by comparing the one-of-a-kind algorithms about their overall performance, protection, and comfort. Numerous pointers are also discussed regarding the application of these algorithms. Finally, the paper concludes with a standard assessment of the multiple algorithms and their suitability in one-of-a-kind contexts. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Encryption algorithms

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of Tokopedia Product Reviews Using Naïve Bayes Algorithm 1st

Sentiment Analysis of Tokopedia Product Reviews Using Naïve...

引用

1st International Conference on Computation of Artificial Intelligence and Machine Learning, ICCAIML 2024

作者： Lita, Mario Gracius Krishna Mardhiyyah, Alya Dhiya’ Maharani, I. Gusti Ayu Ngurah Stita Mulia, Angelina Patience Maulana, Fairuz Iqbal Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia

ISBN: (纸本)9783031714832

Sentiment analysis is a method for classifying text using a Natural Language Processing (NLP) machine learning approach. Sentiment analysis can be utilized in various sectors to help obtain information on customer satisfaction based on positive and negative categories. This study aims to conduct sentiment analysis on customer satisfaction based on product quality, goods delivery service, and seller response in a popular e-commerce application in Indonesia, Tokopedia. This research uses a dataset containing 29 product categories on Tokopedia. Modeling of this dataset will be analyzed using the Naïve Bayes approach and other data processing processes. Based on the analysis process, the researcher found that there were 52.9% negative reviews and the Naïve Bayes approach had good performance for negative sentiment and good precision of 0.99. However, this approach still has shortcomings in terms of generating recall and F1-Score for negative sentiment while positive sentiment shows a balanced performance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Emphasis Interaction Based Industry 5.0 Smart city Digital Twin's Technology 7

Emphasis Interaction Based Industry 5.0 Smart city Digital T...

引用

7th International Conference on Circuit Power and Computing Technologies, ICCPCT 2024

作者： Ramal, P. Janaki Anbalagan, E. Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350372816

The proposed research endeavours to establish a symbiotic relationship between Interaction-Based Industry 5.0 and smart cities, emphasizing the transformative capabilities inherent in Digital Twin technology. Digital Twin, as a central focus, provides a virtual replica of physical entities, allowing for real-time monitoring and analysis of industrial processes and urban environments. By seamlessly integrating Digital Twin with Industry 5.0 principles, this paper aims to empower smart cities in effectively managing the voluminous data generated by Internet of Things (IoT) devices. The research emphasizes the pivotal role of cloud computing in harnessing and processing the extensive datasets, ensuring that smart cities can derive actionable insights for informed decision-making. A key aspect of the proposed approach is the development of a hybrid infrastructure, leveraging diverse resources to enhance both efficiency and reliability. The envisioned synergy between Interaction-Based Industry 5.0, Digital Twin, and cloud computing is poised to revolutionize urban planning, administration, and overall intelligence in smart cities. The anticipated outcomes of this research promise to shape a more resilient and technologically advanced future for urban landscapes © 2024 IEEE.

关键词： Artificial Intelligence Big data Analytics Cloud Computing Digital Twin Hybrid System Interaction-Based Technology Smart City Urban Planning

来源：评论

学校读者我要写书评

暂无评论

Exploring the Power of Deep Learning in Anomaly Detection: A Comprehensive Review and Analysis 12th

Exploring the Power of Deep Learning in Anomaly Detection: A...

引用

12th International Conference on Soft Computing for Problem Solving, SocProS 2023

作者： Kumar, Gaurav Kumar, Ankit Pandy, Saroj Kumar Singh, Kamred Udham Singh, Teekam Kumar, Lalan Choudhury, Tanupriya Department of Computer Engineering and Applications GLA University UP Mathura India School of Computing Graphic Era Hill University Dehradun India Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India Department of Master of Computer Application GL Bajaj Institute of Technology and Management Greater Noida India Department of Computer Science and Engineering University of Petroleum and Energy Studies Dehradun India

ISBN: (纸本)9789819732913

This paper aims to provide a comprehensive overview of existing and state-of-the-art fraud and intrusion detection strategies, specifically focusing on incorporating neural networks. We begin by discussing the fundamental concept of data mining and its significance in detecting anomalies. By leveraging advanced machine learning and neural network techniques, we can effectively uncover subtle patterns and irregularities within complex datasets. We explore how the development of anomalies has enhanced our ability to identify and mitigate various threats, such as malware attacks and unlawful practices. Traditional detection strategies have proven effective, but as deep learning progresses, we uncover new opportunities and insights that can significantly enhance the accuracy and efficiency of anomaly detection systems. Throughout this study, we delve into the most cutting-edge approaches, ranging from broad neural networks to shallower architectures, and their applicability to fraud and intrusion detection. We analyze the strengths and limitations of these strategies, shedding light on their performance characteristics, scalability, and interpretability. By addressing these key issues, we aim to provide a comprehensive summary of the latest fraud and intrusion detection advancements driven by deep learning methodologies. This research contributes to the broader understanding of data mining's potential in uncovering anomalies and bolstering security measures across diverse domains. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Proximal Alternating-Direction-Method-of-Multipliers-Incorporated Nonnegative Latent Factor Analysis

引用

IEEE/CAA Journal of Automatica Sinica 2023年第6期10卷 1388-1406页

作者： Fanghui Bi Xin Luo Bo Shen Hongli Dong Zidong Wang the Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciencesand also with the Chongqing SchoolUniversity of Chinese Academy of SciencesChongqing 400714China the College of Computer and Information Science Southwest UniversityChongqing 400715China the College of Information Science and Technology Donghua UniversityShanghai 201620China the Artificial Intelligence Energy Research Institute Northeast Petroleum UniversityDaqing 163318China the Department of Computer Science Brunel University LondonUxbridge UB83PHUnited Kingdom

High-dimensional and incomplete(HDI)data subject to the nonnegativity constraints are commonly encountered in a big data-related application concerning the interactions among numerous nodes.A nonnegative latent factor analysis(NLFA)model can perform representation learning to HDI data ***,existing NLFA models suffer from either slow convergence rate or representation accuracy *** address this issue,this paper proposes a proximal alternating-directionmethod-of-multipliers-based nonnegative latent factor analysis(PAN)model with two-fold ideas:(1)adopting the principle of alternating-direction-method-of-multipliers to implement an efficient learning scheme for fast convergence and high computational efficiency;and(2)incorporating the proximal regularization into the learning scheme to suppress the optimization fluctuation for high representation learning accuracy to HDI *** studies verify that PAN converges to a Karush-KuhnTucker(KKT)stationary point of its nonnegativity-constrained learning objective with its learning *** results on eight HDI matrices from real applications demonstrate that the proposed PAN model outperforms several state-of-the-art models in both estimation accuracy for missing data of an HDI matrix and computational efficiency.

关键词： nonnegative representation convergence

来源：评论

学校读者我要写书评

暂无评论

Research on video synopsis optimization method based on Two-stage abnormal behavior recognition 6

Research on video synopsis optimization method based on Two-...

引用

6th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2023

作者： Wang, Fudan Zhu, Zhixiang Wang, Chenwu Wang, Pei Zhang, Lei Mu, Pengyuan School of Computer Science Xi'an University of Posts and Telecommunications Xi'an China School of Modern Post Xi'an University of Posts and Telecommunications Xi'an China School of Computer Science Northwestern Polytechnical University Xi'an China Data Operations Department Shaanxi Information Engineering Research Institute Shaanxi Xi'an710065 China

ISBN: (纸本)9798400707674

Video synopsis techniques shift the moving target in the time axis to achieve the purpose of displaying as much effective information as possible in the shortest possible time, usually the abnormal behavior in the video contains more effective information, and most of the existing video synopsis methods do not consider the processing of abnormal behavior. To solve this problem, this paper proposes a video synopsis method based on two-stage abnormal behavior recognition. First, the abnormal frames containing abnormal behaviors in surveillance video are detected using a spatiotemporal autoencoder method, and then an improved R(2+1)D network model is used to identify the abnormal targets and abnormal behavior classes in the abnormal frames of surveillance video. Finally, the abnormal priority concentration loss term is added to the video synopsis optimization objective loss function to make the abnormal targets appear more preferentially and centrally in the generated synopsis video by the multi-objective optimization algorithm. Through a large number of experimental results, the method proposed in this article not only prioritizes the appearance of abnormal targets in the synopsis video, but also accurately observes the specific abnormal behavior of abnormal targets. © 2023 ACM.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Visual–Semantic Graph Matching Net for Zero-Shot Learning

引用

IEEE Transactions on Neural Networks and Learning Systems 2024年第6期36卷 10171-10185页

作者： Bowen Duan Shiming Chen Yufei Guo Guo-Sen Xie Weiping Ding Yisong Wang School of Computer Science and Technology and the Institute for Artificial Intelligence Guizhou University Guiyang Guizhou China Department of Computer Vision Mohamed bin Zayed University of AI Abu Dhabi United Arab Emirates Intelligent Science and Technology Academy CASIC Beijing China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Artificial Intelligence and Computer Science Nantong University Nantong China Faculty of Data Science City University of Macau Macau China

Zero-shot learning (ZSL) aims to leverage additional semantic information to recognize unseen classes. To transfer knowledge from seen to unseen classes, most ZSL methods often learn a shared embedding space by simply aligning visual embeddings with semantic prototypes. However, methods trained under this paradigm often struggle to learn robust embedding space because they align the two modalities in an isolated manner among classes, which ignore the crucial class relationship during the alignment process. To address the aforementioned challenges, this article proposes a visual-semantic graph matching net (VSGMN), which leverages semantic relationships among classes to aid in visual-semantic embedding. VSGMN uses a graph build net (GBN) and a graph matching net (GMN) to achieve two-stage visual-semantic alignment. Specifically, GBN first uses an embedding-based approach to build visual and semantic graphs in the semantic space and align the embedding with its prototype for first-stage alignment. In addition, to supplement unseen class relationships in these graphs, GBN also builds the unseen class nodes based on semantic relationships. In the second stage, GMN continuously integrates neighbor and cross-graph information into the constructed graph nodes and aligns the node relationships between the two graphs under the class relationship constraint. Extensive experiments on three benchmark datasets demonstrate that VSGMN achieves superior performance in both conventional and generalized ZSL (GZSL) scenarios. The implementation of our VSGMN and experimental results are available at github: https://***/dbwfd/VSGMN .

关键词： Semantics Visualization Zero shot learning Prototypes Vectors Manifolds Graph neural networks Benchmark testing Training Space mapping

来源：评论

学校读者我要写书评

暂无评论

Hyper Spectral Image Analysis Integrating Fuzzy C-Means Clustering and Feature Selection 5th

Hyper Spectral Image Analysis Integrating Fuzzy C-Means Clus...

引用

5th International Conference on data science, Machine Learning and Applications, ICDSMLA 2023

作者： Agarwal, Trapty Rengarajan Goyal, Rohit Khan, N. Zafar Ali Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Karnataka Bangalore India Department of Computer Science & Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Navgaon Manduwala Dehradun India School of Computer Science and Engineering Presidency University Karnataka Bengaluru India

ISBN: (纸本)9789819780426

Hyper spectral picture evaluation is an effective tool for analyzing large volumes of excessive-dimensional facts. In this paper, a brand new method to hyper spectral photo analysis is provided that integrates fuzzy C-means clustering and function choice. The proposed approach permits for significant quantification of the exclusive additives within a hyper spectral image and allows for the identification of key spectral functions. Additionally, the fuzzy C-way clustering approach is used to identify awesome clusters within the photograph, supplying a useful method for studying complicated datasets. The characteristic choice technique facilitates to further lessen the data set and to achieve the maximum meaningful capabilities for further evaluation. The overall performance of the proposed technique is evaluated via the use of an actual-international hyper spectral photo, and the effects exhibit the effectiveness of the proposed technique for hyper-spectral photograph analysis. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Image analysis

来源：评论

学校读者我要写书评

暂无评论

Optimal Visualization of Hyper Spectral Time Series Algorithms via Graphical Representations 5th

Optimal Visualization of Hyper Spectral Time Series Algorith...

引用

5th International Conference on data science, Machine Learning and Applications, ICDSMLA 2023

作者： Agarwal, Trapty Karthikeyan, M.P. Adhikari, Manoj S. Ulla, Mohammed Mujeer Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Karnataka Bangalore India Department of Computer Science & Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Navgaon Manduwala Dehradun India School of Computer Science and Engineering Presidency University Karnataka Bengaluru India

ISBN: (纸本)9789819780426

This technical summary describes how using graphical representations can allow for the best visualization of hyper spectral time series algorithms. Hyper spectral time collection algorithms correctly analyze temporal information from satellite- or plane-borne sensors, for instance, to offer an in-intensity expertise of an environment or system. But, such evaluation can regularly be difficult to realize without graphical aid. This research gives a method for correctly visualizing hyper spectral time series algorithms using graphical representations, consisting of line graphs and tree diagrams. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Visualization

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：