检索结果-内蒙古大学图书馆

2024 International Conference on Intelligent Systems for Cybersecurity, ISCS 2024

作者： Singhi, Nitika Verma, Ankush Agrawal, Atul Khan, Irfan Computer Science Engineering Shri Vaishnav Vidhyapeeth Vishwavidyalava Indore India Data Analytics and Information System Prestige Institute of Management and Research Indore India Computer Science Engineering Sushila Devi Bansal College of Technology Indore India Computer Science Engineering Bansal Institute of Science and Technology Bhopal India

ISBN: (纸本)9798350375237

In past few year designs thinking has worked on several new effective problem and has generated innovative solution for new business model. For the scenario of today's demand, to better understand how design thinking can work on different perspectives in business models and how it can bring new innovative solutions for any problem is essential However, studies of existing literature explore the application, potential, and challenges of Design Thinking towards the comprehensive aim of this paper, which regards business model innovation as a fundamental subject of Design Thinking. The paper provides practical tools for exploring Design Thinking along with various critical aspects for the researchers to explore how Design Thinking can be applied to innovative business models. The main focus of this paper is to explain the basics of Design Thinking, how to frame the mind through different techniques used, the Design Techniques used for a business model, the methodology of a design thinker, and different tools like BPM, Blue Work Live, Mind Mapping, Brainstorming, and RICPS. © 2024 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Decentralized Metaverse: Towards a Secure, Autonomous, and Inclusive Virtual World

Decentralized Metaverse: Towards a Secure, Autonomous, and I...

引用

2023 IEEE International Conference on Electrical, Computer and Energy Technologies, ICECET 2023

作者： Alsamhi, Saeed Hamood Hawbani, Ammar Kumar, Santosh Porwol, Lukasz Curry, Edward Insight Centre for Data Analytics University of Galway Galway Ireland School of Computer Science Shenyang Aerospace University Shenyang China Computer Science and Engineering Iiit Naya Raipur Chhattisgarh India

ISBN: (纸本)9798350327816

The metaverse is a universal and immersive virtual world, which are components of cyber-physical-social systems (CPSS). The traditional centralized approach to building a metaverse poses risks to user privacy, security, and autonomy. A growing movement towards a decentralized metaverse, built on blockchain and distributed networks, has emerged as a response. This paper presents a conceptual framework for building a de-centralized metaverse emphasising security, user autonomy, and inclusivity within situation-aware CPSS. Drawing on literature from blockchain, virtual worlds, and decentralized systems, we explore the technical and regulatory challenges that must be addressed to create a more secure, autonomous, and inclusive virtual world. Our framework highlights the importance of community-driven governance and transparent data management for building a decentralized metaverse that empowers users and promotes collaboration. © 2023 IEEE.

关键词： Blockchain Cyber-Physical-Social Systems Decentralization Metaverse Situation Awareness

来源：评论

学校读者我要写书评

暂无评论

An Adaptive and Image-guided Fusion for Stereo Satellite Image Derived Digital Surface Models

引用

Journal of Geodesy and Geoinformation Science 2022年第4期5卷 1-9页

作者： Hessah ALBANWAN Rongjun QIN Department of Civil Engineering Kuwait UniversityKuwait 72504Kuwait Geospatial Data Analytics Lab The Ohio State UniversityColumbus 43210USA Department of Civil Environmental and Geodetic EngineeringThe Ohio State UniversityColumbus 43210USA Department of Electrical and Computer Engineering The Ohio State UniversityColumbus 43210USA Translational Data Analytics Institute The Ohio State UniversityColumbus 43210USA

The accuracy of Digital Surface Models(DSMs)generated using stereo matching methods varies due to the varying acquisition conditions and configuration parameters of stereo *** has been a good practice to fuse these DSMs generated from various stereo pairs to achieve enhanced,in which multiple DSMs are combined through computational approaches into a single,more accurate,and complete ***,accurately characterizing detailed objects and their boundaries still present a challenge since most boundary-ware fusion methods still struggle to achieve sharpened depth discontinuities due to the averaging effects of different ***,we propose a simple and efficient adaptive image-guided DSM fusion method that applies k-means clustering on small patches of the orthophoto to guide the pixel-level fusion adapted to the most consistent and relevant elevation *** experiment results show that our proposed method has outperformed comparing methods in accuracy and the ability to preserve sharpened depth edges.

关键词： Digital Surface Model(DSM) DSM Fusion adaptive fusion satellite stereo images

来源：评论

学校读者我要写书评

暂无评论

Optimal clustering with bandit feedback

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 8799-8852页

作者： Junwen Yang Zixin Zhong Vincent Y. F. Tan Institute of Operations Research and Analytics National University of Singapore Singapore Thrust of Data Science and Analytics Hong Kong University of Science and Technology (Guangzhou) Guangzhou Guangdong China Department of Mathematics Department of Electrical and Computer Engineering Institute of Operations Research and Analytics National University of Singapore Singapore

This paper considers the problem of online clustering with bandit feedback. A set of arms (or items) can be partitioned into various groups that are unknown. Within each group, the observations associated to each of the arms follow the same distribution with the same mean vector. At each time step, the agent queries or pulls an arm and obtains an independent observation from the distribution it is associated to. Subsequent pulls depend on previous ones as well as the previously obtained samples. The agent's task is to uncover the underlying partition of the arms with the least number of arm pulls and with a probability of error not exceeding a prescribed constant δ. The problem proposed finds numerous applications from clustering of variants of viruses to online market segmentation. We present an instance-dependent information-theoretic lower bound on the expected sample complexity for this task, and design a computationally efficient and asymptotically optimal algorithm, namely Bandit Online Clustering (BOC). The algorithm includes a novel stopping rule for adaptive sequential testing that circumvents the need to exactly solve any NP-hard weighted clustering problem as its subroutines. We show through extensive simulations on synthetic and real-world datasets that BOC's performance matches the lower bound asymptotically, and significantly outperforms a non-adaptive baseline algorithm.

关键词： clustering K-means online learning multi-armed bandits pure exploration

来源：评论

学校读者我要写书评

暂无评论

On the Transferability of Learning Models for Semantic Segmentation for Remote Sensing data

arXiv

引用

arXiv 2023年

作者： Qin, Rongjun Zhang, Guixiang Tang, Yang The Geospatial Data Analytics Lab Department of Civil Environment and Geodetic Engineering The Department of Electrical and Computer Engineering Translational Data Analytics Institute The Ohio state University Columbus United States The Geospatial Data Analytics Lab Department of Electrical and Computer Engineering The Ohio State University Columbus United States The Geospatial Data Analytics Lab Department of Civil Environment and Geodetic Engineering The Ohio State University Columbus United States

Recent deep learning-based methods outperform traditional learning methods on remote sensing (RS) semantic segmentation/classification tasks. However, they require large training datasets and are generally known for lack of transferability due to the highly disparate RS image content across different geographical regions. Yet, there is no comprehensive analysis of their transferability, i.e., to which extent a model trained on a source domain can be readily applicable to a target domain. Therefore, in this paper, we aim to investigate the raw transferability of traditional and deep learning (DL) models, as well as the effectiveness of domain adaptation (DA) approaches in enhancing the transferability of the DL models (adapted transferability). By utilizing four highly diverse RS datasets, we train six models with and without three DA approaches to analyze their transferability between these datasets quantitatively. Furthermore, we developed a straightforward method to quantify the transferability of a model using the spectral indices as a medium and have demonstrated its effectiveness in evaluating the model transferability at the target domain when the labels are unavailable. Our experiments yield several generally important yet not well-reported observations regarding the raw and adapted transferability. Moreover, our proposed label-free transferability assessment method is validated to be better than posterior model confidence. The findings can guide the future development of generalized RS learning models. The trained models are released under this link: https://***/GDAOSU/Transferability-Remote-Sensing. Copyright © 2023, The Authors. All rights reserved.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

When Babies Teach Babies: Can student knowledge sharing outperform Teacher-Guided Distillation on small datasets

arXiv

引用

arXiv 2024年

作者： Iyer, Srikrishna Artificial Intelligence - Data Analytics Strategic Technology Center ST Engineering IHQ Ltd. Singapore

We present our submission12 to the BabyLM challenge, aiming to push the boundaries of data-efficient language model pretraining. Our method builds upon deep mutual learning, introducing a student model search for diverse initialization. We address the limitation of treating students equally by formulating weighted mutual learning as a bi-level optimization problem. The inner loop learns compact students through online distillation, while the outer loop optimizes weights for better knowledge distillation from diverse students. This dynamic weighting strategy eliminates the need for a teacher model, reducing computational requirements. Our evaluations show that teacher-less methods can match or surpass teacher-supervised approaches. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Moral Storytelling Model Using Artificial Intelligence-Driven Image-to-Text Synthesis 2

Moral Storytelling Model Using Artificial Intelligence-Drive...

引用

2nd IEEE International Conference on data Science and Network Security, ICDSNS 2024

作者： Rao, Abhishek S. Rakesh Kumar, B. Ranganatha, K. Poojary, Ramaprasad Karthik Pai, B.H. Lisa Bojamma, M.S. Jaleesh, Jeeva Nmam Institute of Technology Department of Information Science and Engineering Nitte India St. Aloysius Deemed to Be University Department of M.Sc Big Data Analytics Aimit Mangaluru India Canara Engineering College Department of Information Science & Engineering Benjanapadavu India School of Engineering & It Manipal Academy of Higher Education Dubai United Arab Emirates

ISBN: (纸本)9798350373110

Artificial intelligence in storytelling often struggles with conveying complex moral narratives due to its reliance on short and simplistic captions. This study introduces a novel approach to overcome this challenge by developing a model designed to craft more extensive and profound moral stories. Utilizing unsupervised deep learning techniques, the proposed model autonomously learns from a diverse corpus of short stories and images to generate extended narratives without requiring explicit human guidance. The study highlights three primary contributions: the creation of an autonomous model for generating moral stories with minimal human intervention, the development of a substantial reservoir of moral narratives for comprehensive training, and the empirical validation of the model's superior ability to produce innovative and captivating stories compared to existing methodologies. The proposed model exhibits remarkable accuracy, achieving 91.0% on the COCO dataset and 88% on the Flickr30K dataset, outperforming models such as Encoder-Decoder, Informative Cross-modal, LSTM, and AESOP. Additionally, the model's performance was evaluated using the BLEU and CIDEr scores, yielding 0.81 and 0.75, respectively. This model not only enhances the depth and quality of AI-generated moral stories but also has potential applications in education, entertainment, and virtual assistants, providing richer and more engaging content for users. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

The Connections Between the Approximate Three-Way Concept Lattice and the Three-Way Approximate Concept Lattice 11th

The Connections Between the Approximate Three-Way Concept L...

引用

11th International Joint Conference on Rough Sets, IJCRS 2025

作者： Li, Mei-Zheng Li, Lei-Jun Mi, Ju-Sheng Hebei Normal University Hebei Shijiazhuang 050024 China Hebei Provincial Engineering Research Center for Supply Chain Big Data Analytics and Data Security Shijiazhuang 050024 China Hebei Key Laboratory of Computational Mathematics and Applications Shijiazhuang 050024 China

ISBN: (纸本)9783031927430

The approximate three-way concept lattice (ATWL), a novel model for conflict analysis, is an extension of classical concept lattice in formal concept analysis. However, little effort has been devoted on the connections between the ATWL and other existing three-way concept lattice models, which will be of great help to construct the ATWL efficiently. This paper reveals the connections between the ATWL and the three-way approximate concept lattice (TWAL) of an incomplete formal context from the viewpoints of concept fusion. Furthermore, the construct algorithm for ATWL based on TWAL is presented. The obtained results are finally demonstrated and verified by an example. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Approximate concept construction Concept lattice Incomplete formal context Three-way decisions

来源：评论

学校读者我要写书评

暂无评论

A Novel Breast Cancer Detection and Classification Using Enhanced ANN Classification 5

A Novel Breast Cancer Detection and Classification Using Enh...

引用

5th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2024

作者： Mathiyalagan, P. Kiruthiga, G. Rasmi, A. Vadivel, M. Mahalakshmi, K.V. Poornappriya, T.S. Sri Ramakrishna Engineering College Department of CSE Coimbatore India Karpagam College of Engineering Dept of Artificial Intelligence and Data Science Coimbatore India RR Institute of Technology Information Science and Engineering Bangalore India Excel Engineering College Department of Information Technology TamilNadu Namakkal India B v Raju Institute of Technology CSE Telangana 502313 India Aspire Systems Pvt Ltd Data and Analytics Karnataka Bengaluru560037 India

ISBN: (纸本)9798331518097

The second most prevalent and leading cause of cancer death is breast cancer, which is the most common malignancy among women. Because the causes of breast cancer are not fully known, there is currently no reliable technique to prevent it. In recent years, breast cancer has become a widespread condition among women. Over the past several years, the issue of breast tumour categorization has become a significant issue. This article offers logical reasoning for the order in which to identify malignant lesions, a significant development in the mammography diagnosis of breast cancer. As a result, we concentrate on studying and analysing cancer imaging, with a particular emphasis on breast cancer. Mammography produces and processes pictures that are used in breast cancer detection. Sensitivity, specificity, and classification accuracy are the metrics used to assess the experimental findings. Results of an improved ANN classifier for differentiating between normal and abnormal cases in pictures from applied advanced mammography. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

A Symbolic Rule Integration Framework with Logic Transformer for Inductive Relation Prediction 24

A Symbolic Rule Integration Framework with Logic Transformer...

引用

33rd ACM Web Conference, WWW 2024

作者： Pan, Yudai Liu, Jun Zhao, Tianzhe Zhang, Lingling Lin, Yun Dong, Jin Song School of Computer Science and Technology Xi'an Jiaotong University Shaanxi Xi'an China National Engineering Lab for Big Data Analytics Xi'an Jiaotong University Shaanxi Xi'an China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Shaanxi Xi'an China Shanghai Jiao Tong University Shanghai China National University of Singapore Singapore Singapore

ISBN: (纸本)9798400701719

Relation prediction in knowledge graphs (KGs) aims at predicting missing relations in incomplete triples, whereas the dominant paradigm by KG embeddings has a limitation to predict the relation between unseen entities. This situation is called an inductive setting, which is more common in the real-world scenario. To handle this issue, implicit symbolic rules have shown great potential in capturing the inductive capability. However, it is still challenging to obtain precise representations of logic rules from KGs. The argument variability and predicate non-commutativity in symbolic rule integration make the modeling of component symbols difficult. To this end, we propose a novel inductive relation prediction model named SymRITa with a logic transformer integrating rules. SymRITa firstly extracts the subgraph, whose embeddings are captured by a graph network. Meanwhile, symbolic rule graphs in the subgraph can be generated. Then, the symbolic rules are modeled by a proposed logic transformer. Specifically, the input format based on the subgraph-based embeddings is to focus on the argument variability in symbolic rules. In addition, a conjunction attention mechanism in the logic transformer can resolve predicate non-commutativity in the symbolic rule integration process. Finally, the subgraph-based and symbol-based embeddings obtained from the previous steps are combined for the training regime, and prediction results as well as rules explaining the reasoning process are explicitly output. Extensive experiments on twelve inductive datasets show that SymRITa achieves outstanding effectiveness compared to state-of-the-art inductive baselines. Moreover, the logic rules with corresponding confidences provide an interpretable paradigm. © 2024 ACM.

关键词： Forecasting

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：