检索结果-内蒙古大学图书馆

A Neural Computing-Based Access Control Protocol for AI-Driven Intelligent Flying Vehicles in Industry 5.0-Assisted Consumer Electronics

引用

IEEE Transactions on Consumer Electronics 2024年第1期70卷 3573-3581页

作者： Mahmood, Khalid Tariq, Tayyaba Sangaiah, Arun Kumar Ghaffar, Zahid Saleem, Muhammad Asad Shamshad, Salman National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Douliu64002 Taiwan National Yunlin University of Science and Technology Department of Computer Science and Information Engineering Douliu64002 Taiwan National Yunlin University of Science and Technology International Graduate School of AI Douliu64002 Taiwan Lebanese American University Department of Electrical and Computer Engineering Byblos1102 2801 Lebanon University of Electronic Science and Technology of China School of Computer Science and Engineering Sichuan Chengdu611731 China The University of Lahore Department of Software Engineering Lahore54590 Pakistan

The continuous revolution in Artificial Intelligence (AI) has played a significant role in the development of key consumer applications, including Industry 5.0, autonomous decision-making, fault diagnosis, etc. In practice, autonomous and intelligent robots and flying vehicles (i.e., drones) are also becoming the integral part of Industry 5.0. These vehicles are attaining significant importance nowadays because of their applications in consumer electronics. However, there may be numerous privacy issues in such an infrastructure. Nevertheless, neural computing-driven security solutions have played a significant role in overcoming the security and privacy issues of AI-driven intelligent flying vehicles. Motivated by these facts, this article presents a neural computing-based access control protocol for AI-driven flying vehicles to prevent all possible security threats. A detailed security evaluation of the devised protocol is done formally using the extensively recognized Real-Or-Random (ROR) oracle model. Similarly, the informal security analysis ensures the resistance of our scheme against various potential attacks under the assumptions of CK and DY adversarial models. Moreover, detailed performance scrutiny of the devised protocol with various existing schemes shows the robustness and supremacy of our scheme in terms of computation, communication overhead, and security attributes. © 1975-2011 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Research on Semantic Matching of Thesis Themes Based on Comparative Learning and Adversarial Training 7

Research on Semantic Matching of Thesis Themes Based on Comp...

引用

7th International Conference on Advanced Algorithms and Control Engineering, ICAACE 2024

作者： Zhang, Xu Shao, Zengzhen Li, Zhuangzhuang Han, Shuai Sun, Yajing Shandong Normal University Department Of Information Science And Engineering Jinan China Shandong Women's College Department Of Data Science And Computer Science Jinan China

ISBN: (纸本)9798350361445

At the doctoral level in the field of computer science, the domain of literature plagiarism detection encompasses numerous plagiarism detection algorithms, but relatively fewer have focused on methods specifically designed for topic-based plagiarism detection. To address this research gap, this paper introduces a text semantic matching algorithm based on contrastive learning and adversarial training, which we have named 'Comparative Adversarial Training (CAT).' Specifically, during the fine-tuning process, we generate affirmative and negative sentences using paper titles and keywords and optimize the model's performance through contrastive learning. Simultaneously, we generate adversarial samples by perturbing the word embedding matrix of the model and then employ these adversarial samples for adversarial training. Through experiments conducted on our proprietary internal dataset, the fine-tuned BERT model exhibited an average performance improvement of 3.71% compared to the baseline BERT model. Similarly, the fine-tuned RoBERTa model demonstrated a performance enhancement of 3.18% relative to the RoBERTa baseline model. Based on these experimental results, our algorithm's effectiveness has been thoroughly validated. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Enhanced Multimodal Hate Video Detection via Channel-wise and Modality-wise Fusion 24

Enhanced Multimodal Hate Video Detection via Channel-wise an...

引用

24th IEEE International Conference on data Mining Workshops, ICDMW 2024

作者： Zhang, Yinghui Chen, Tailin Zhang, Yuchen Fu, Zeyu University of Exeter Department of Computer Science United Kingdom University of Essex Institute for Analytics and Data Science United Kingdom

ISBN: (纸本)9798331530631

The rapid rise of video content on platforms such as TikTok and YouTube has transformed information dissemination, but it has also facilitated the spread of harmful content, particularly hate videos. Despite significant efforts to combat hate speech, detecting these videos remains challenging due to their often implicit nature. Current detection methods primarily rely on unimodal approaches, which inadequately capture the complementary features across different modalities. While multimodal techniques offer a broader perspective, many fail to effectively integrate temporal dynamics and modality-wise interactions essential for identifying nuanced hate content. In this paper, we present CMFusion, an enhanced multimodal hate video detection model utilizing a novel Channel-wise and Modality-wise Fusion Mechanism. CMFusion first extracts features from text, audio, and video modalities using pre-trained models and then incorporates a temporal cross-attention mechanism to capture dependencies between video and audio streams. The learned features are then processed by channel-wise and modality-wise fusion modules to obtain informative representations of videos. Our extensive experiments on a real-world dataset demonstrate that CMFusion significantly outperforms five widely used baselines in terms of accuracy, precision, recall, and F1 score. Comprehensive ablation studies and parameter analyses further validate our design choices, highlighting the model's effectiveness in detecting hate videos. The source codes will be made publicly available at https://***/EvelynZ10/cmfusion. © 2024 IEEE.

关键词： Hate Video Detection Multimodal Fusion Temporal Cross-Attention

来源：评论

学校读者我要写书评

暂无评论

Market resilience in turbulent times: a proactive approach to predicting stock market responses during geopolitical tensions

引用

Journal of Capital Markets Studies 2024年第2期8卷 173-194页

作者： Maddodi, Srivatsa Kunte, Srinivasa Rao Department of Computer Science Srinivas University Mangaluru India Department of Data Engineering United Airlines Inc Bengaluru India

Purpose: The Indian stock market can be tricky when there's trouble in the world, like wars or big conflicts. It's like trying to read a secret message. We want to figure out what makes investors nervous or happy, because their feelings often affect how they buy and sell stocks. We're building a tool to make prediction that uses both numbers and people's opinions. Design/methodology/approach: Hybrid approach leverages Twitter sentiment, market data, volatility index (VIX) and momentum indicators like moving average convergence divergence (MACD) and relative strength index (RSI) to deliver accurate market insights for informed investment decisions during uncertainty. Findings: Our study reveals that geopolitical tensions' impact on stock markets is fleeting and confined to the short term. Capitalizing on this insight, we built a ground-breaking predictive model with an impressive 98.47% accuracy in forecasting stock market values during such events. Originality/value: To the best of the authors' knowledge, this model's originality lies in its focus on short-term impact, novel data fusion and high accuracy. Focus on short-term impact: Our model uniquely identifies and quantifies the fleeting effects of geopolitical tensions on market behavior, a previously under-researched area. Novel data fusion: Combining sentiment analysis with established market indicators like VIX and momentum offers a comprehensive and dynamic approach to predicting market movements during volatile periods. Advanced predictive accuracy: Achieving the prediction accuracy (98.47%) sets this model apart from existing solutions, making it a valuable tool for informed decision-making. © 2024, Srivatsa Maddodi and Srinivasa Rao Kunte.

关键词： Geopolitical tension LSTM Momentum indicator Sentiment analysis Stock market prediction

来源：评论

学校读者我要写书评

暂无评论

REVISITING ROBUSTNESS IN GRAPH MACHINE LEARNING 11

REVISITING ROBUSTNESS IN GRAPH MACHINE LEARNING

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Gosch, Lukas Sturm, Daniel Geisler, Simon Günnemann, Stephan Department of Computer Science Munich Data Science Institute Technical University of Munich Germany

Many works show that node-level predictions of Graph Neural Networks (GNNs) are unrobust to small, often termed adversarial, changes to the graph structure. However, because manual inspection of a graph is difficult, it is unclear if the studied perturbations always preserve a core assumption of adversarial examples: that of unchanged semantic content. To address this problem, we introduce a more principled notion of an adversarial graph, which is aware of semantic content change. Using Contextual Stochastic Block Models (CSBMs) and real-world graphs, our results uncover: i) for a majority of nodes the prevalent perturbation models include a large fraction of perturbed graphs violating the unchanged semantics assumption;ii) surprisingly, all assessed GNNs show over-robustness - that is robustness beyond the point of semantic change. We find this to be a complementary phenomenon to adversarial examples and show that including the label-structure of the training graph into the inference process of GNNs significantly reduces over-robustness, while having a positive effect on test accuracy and adversarial robustness. Theoretically, leveraging our new semantics-aware notion of robustness, we prove that there is no robustness-accuracy tradeoff for inductively classifying a newly added node. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Medicinal Plant Classification Using SVM 2

Medicinal Plant Classification Using SVM

引用

2nd IEEE International Conference on Networks, Multimedia and Information Technology, NMITCON 2024

作者： Kiranagi, Soumya S Patil, Savitha Sharnbasva University Department of Artificial Intelligence and Data Science Kalaburagi India Sharnbasva University Department of Computer Science and Engineering Kalaburagi India

ISBN: (纸本)9798350372892

there are hundreds of kinds of plants on Earth, and many of them have medicinal or curative properties. Approximately 80% of the global population continues to rely on traditional medicine. In Ayurveda, the use of herbs as medicine dates back to Vedic times. Recognizable identification of the medicinal plants is crucial for the efficacy of ayurvedic, social, and homoeopathic treatments. For the treatment of skin conditions, lung infections, asthma, dyspepsia, and other ailments, many people throughout the globe rely on medicinal plants. One of the most important steps in making an Ayurvedic medicine is finding the right medicinal leaf. Misclassification or incorrect identification of medicinal leaves could affect Ayurveda's efficacy. Form, colour, and texture of leaves are the most basic characteristics that must be present to identify a medicinal plant. While the form and venation pattern of individual leaves might vary greatly, members of the same class of leaves tend to have commonalities. In light of this need, here is a model that makes use of an SVM Machine Learning Algorithm to reliably identify and categories medicinal leaves. © 2024 IEEE.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

Adaptive Particle Swarm Optimization of U-net Parameters for Marine Aquaculture Image Segmentation 13

Adaptive Particle Swarm Optimization of U-net Parameters for...

引用

13th International Conference on Intelligent Control and Information Processing, ICICIP 2025

作者： Zhao, Jin Wang, Jun Han, Min Fan, Jianchao School of Computer Science and Engineering Chongqing Three Gorges University Chongqing China Department of Computer Science Department of Data Science City University of HongKong Hong Kong School of Control Science and Engineering Dalian University of Technology Dalian China

ISBN: (纸本)9798331516147

Marine aquaculture image segmentation plays a crucial role in managing aquatic resources and environmental protection. Traditional deep learning models rely on manual parameter tuning for image segmentation, which limits their efficiency and accuracy. This paper proposes an adaptive Particle Swarm Optimization (PSO) algorithm to optimize the parameters of the U-net model automatically. The algorithm dynamically adjusts the PSO parameters based on the population’s entropy and clustering metrics and employs a hill-climbing algorithm to address the issue of the PSO easily falling into local optima, enhancing the algorithm’s adaptability. The proposed algorithm updates and iterates particles to automatically find suitable model parameters. The remote sensing data used in this experiment were from the Yellow Sea aquaculture area near Dalian, China, with a segmentation accuracy of 91.8%. This method improves segmentation accuracy, reduces the burden of manual parameter tuning, and provides an effective solution for optimizing deep learning models. © 2025 IEEE.

关键词： Aquaculture

来源：评论

学校读者我要写书评

暂无评论

Domain Reductions After Preprocessing: Effects on Dynamic Variable Ordering Heuristics in Constraint Satisfaction Search 23rd

Domain Reductions After Preprocessing: Effects on Dynamic V...

引用

23rd EPIA Conference on Artificial Intelligence, EPIA 2024

作者： Wallace, Richard J. Insight Centre for Data Analytics and Department of Computer Science University College Cork Cork Ireland

ISBN: (纸本)9783031734991

We still do not have an adequate understanding of heuristic methods used for solving constraint satisfaction problems (CSPs). An example involves the effects of preprocessing, an essential means of improving CSP search. The traditional explanation for its beneficial effect is that the resulting "problem reduction" leaves fewer possibilities to explore. Recently, however, it was shown that when dynamic variable ordering heuristics are used, other factors related to domain size reduction are much more important. This paper extends this analysis and explores some implications of this new perspective. The key idea is that pattern of domain reductions produced by preprocessing transmits information that guides heuristic decisions. Treating domain reduction as a code and the set of reductions as a message of length n transmitted to the search algorithm, we distinguish two factors, message discriminability and code quality, and show that greater problem reduction enhances both. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Constraint satisfaction problems

来源：评论

学校读者我要写书评

暂无评论

A Reliable Approach for Automatic Grading of Diabetic Retinopathy from Fundus Images using Feature Extraction and Fusion 3

A Reliable Approach for Automatic Grading of Diabetic Retino...

引用

3rd International Conference on Electrical, Electronics, Information and Communication Technologies, ICEEICT 2024

作者： Jasmine, R.Anita Ramla, M. Ramesh, M. Srm Institute of Science and Technology Department of Data Science and Business Systems Chennai Kattankulathur India Srm Institute of Science and Technology Department of Computer Applications Chennai Kattankulathur India Srm Institute of Science and Technology Department of Computer Science Chennai Kattankulathur India

ISBN: (纸本)9798350369083

Diabetic Retinopathy (DR) is widely recognized as the primary cause of visual impairment worldwide. Early intervention is crucial in preventing irreversible vision loss. Ophthalmologists conventionally utilize fundus cameras to capture retinal images and detect indications of diabetic retinopathy, thereby facilitating prompt diagnosis. The progress made in computational intelligence has significantly enhanced our ability to identify, predict, and categorize DR. The focus of this research is to present a proficient framework for the DR grading. The framework proposed employs Laplacian filters to reduce undesirable image distortions and enhance the overall quality of the images. The methodology involves the utilization of transfer learning through the pre-existing VGG19 Convolutional Neural Network architecture to pull out features from diverse pooling layers. The amalgamation of extracted features from multiple layers results in the formation of feature vectors. These vectors are utilized as inputs for training various machine learning algorithms, with the objective of identifying the most effective model for evaluating the severity of DR. Significantly, the research provides a rationale for its forecasts, guaranteeing the transparency of the algorithm and comprehensibility of the model, thereby validating its reliability. The model's exceptional precision renders it a promising candidate for broad implementation in clinical identification and prediction of DR, potentially augmenting global patient outcomes. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

SAMPLING-FREE INFERENCE FOR AB-INITIO POTENTIAL ENERGY SURFACE NETWORKS 11

SAMPLING-FREE INFERENCE FOR AB-INITIO POTENTIAL ENERGY SURFA...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Gao, Nicholas Günnemann, Stephan Department of Computer Science Munich Data Science Institute Technical University of Munich Germany

Recently, it has been shown that neural networks not only approximate the ground-state wave functions of a single molecular system well but can also generalize to multiple geometries. While such generalization significantly speeds up training, each energy evaluation still requires Monte Carlo integration which limits the evaluation to a few geometries. In this work, we address the inference shortcomings by proposing the Potential learning from ab-initio Networks (PlaNet) framework, in which we simultaneously train a surrogate model in addition to the neural wave function. At inference time, the surrogate avoids expensive Monte-Carlo integration by directly estimating the energy, accelerating the process from hours to milliseconds. In this way, we can accurately model high-resolution multi-dimensional energy surfaces for larger systems that previously were unobtainable via neural wave functions. Finally, we explore an additional inductive bias by introducing physically-motivated restricted neural wave function models. We implement such a function with several additional improvements in the new PESNet++ model. In our experimental evaluation, PlaNet accelerates inference by 7 orders of magnitude for larger molecules like ethanol while preserving accuracy. Compared to previous energy surface networks, PESNet++ reduces energy errors by up to 74 %. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Wave functions

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：