检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2024

作者： Kandan, M. Sarkar, Swagata Sharma, Meenakshi Rajeswari, V. Poonkuzhali, P. Srimathi, S. SRM Institute of Science and Technology School of Computing Faculty of Engineering and Technology Department of Computing Technologies Kattankulathur India Sri Sairam Engineering College Artificial Intelligence and Data Science Chennai India Global Group of Institute Department of CSE Amritsar India Panimalar Engineering College Information Technology India R.M.D Engineering College Kavaraipettai India Saveetha School of Engineering SIMATS Department of Bio Technology Tamilnadu Chennai India

ISBN: (纸本)9798350317558

Earthquakes, one of the greatest natural catastrophes, kill people and harm the economy. Heavy earthquakes and tsunamis may kill thousands and cost millions. Globally, predicting major earthquakes is important. Because earthquake prediction is difficult, researchers employ machine learning to improve forecasts. Many countries have early earthquake warning systems to save lives. Temporal rather than geographical characteristics dominated previous research. A similarity between earthquake and non-seismic signals makes real-time earthquake detection with cellphones or IoT devices problematic. This system may change entity interactions using ML and an IoT network. EEWS metrics are tracked using IoT. However, ML can assess these actions and determine smart city risk reduction and catastrophe management strategies. A deep learning approach for continuous earthquake forecasting utilising past seismic events is proposed. This research predicts earthquakes by position and depth using machine learning and deep learning. ConvLSTM, a Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN), extracts important waveform elements to make the classifier reliable in earthquake parameters. © 2024 IEEE.

关键词： Convolutional Neural Network Deep Learning Earthquake LSTM Machine Learning

来源：评论

学校读者我要写书评

暂无评论

Skeleton Based Action Quality Assessment of Figure Skating Videos 11

Skeleton Based Action Quality Assessment of Figure Skating V...

引用

11th International Conference on Information technology in Medicine and Education, ITME 2021

作者： Li, Hui-Ying Lei, Qing Zhang, Hong-Bo Du, Ji-Xiang Huaqiao University Department of Computer Science and Technology Xiamen China Huaqiao University Fujian Key Laboratory of Big Data Intelligence and Security Xiamen China

ISBN: (纸本)9781665406796

Action quality assessment(AQA) aims at achieving automatic evaluation the performance of human actions in video. Compared with action recognition problem, AQA focuses more on subtle differences both in spatial and temporal dimensions during the whole executing process of actions. However, most existing AQA methods tried to extract features directly from RGB videos through a 3D ConvNets, which makes the features mixed with useless scene information. To overcome this problem, We propose a deep pose feature learning AQA method that captured detailed and meaningful representations for skeleton information to discover the subtle motion difference of AQA problem. We first apply pose estimation method to obtain human skeleton data from RGB videos. Then a spatio-temporal graph convolutional network (ST-GCN) is employed to extract the dynamic changes of skeleton data and obtain the representative pose features. Finally, a regressor composed of three fully connected layers is developed to reduce the dimension of the obtained pose features and predict the final score. Experiments on MIT figure skating dataset have been extensively conducted, and the results demonstrate that the proposed method has achieved improvements that outperformed current state-of-the-art methods. © 2021 IEEE.

关键词： Musculoskeletal system

来源：评论

学校读者我要写书评

暂无评论

Signs to Speech

Signs to Speech

引用

Networking and Communications (ICNWC), International Conference on

作者： Harsh Vardhan Harsavardhan S M Lakshmi Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and TechnologyKattankulathur Chennai India

ISBN: (数字)9798350365269

ISBN: (纸本)9798350365276

This research introduces an innovative Sign Language to Speech Conversion Model using Convolutional Neural Networks (CNNs) to address communication barriers for the people who are deaf and unable to hear properly. The model employs deep learning for the automatic extraction of spatial patterns from sign language images. A diverse sign language dataset is carefully curated, undergoing Pre-processing for improved quality. The CNN architecture, designed for adaptability, captures local and global features, enabling accurate *** the training phase, the model learns to map sign language gestures to spoken language representations. Performance evaluation methods which include accuracy, recall, precision and F1 score, demonstrate the effectiveness of the model. Results underscore the significance for the deaf community. The discussion explores broader implications in education, healthcare, and social interactions, acknowledging limitations and proposing future research *** conclusion, the Sign Language to Speech Conversion Model contributes to sign language recognition, offering an advanced solution for communication barriers and promoting inclusivity in diverse social settings.

关键词： Training Performance evaluation Sign language Adaptation models Refining Speech recognition Medical services

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Crack Detection Methods in Ancient Buildings 24

Machine Learning-Based Crack Detection Methods in Ancient Bu...

引用

2024 Guangdong-Hong Kong-Macao Greater Bay Area International Conference on Digital Economy and Artificial Intelligence, DEAI 2024

作者： Fang, Tianke Hui, Zhenxing Rey, William P. Yang, Aihua Liu, Bin He, Yuanrong School of Information Technology Mapua University Manila1200 Philippines School of Computing and Information Engineering Xiamen University of Technology Xiamen Fujian361024 China Big Data Institute of Digital Natural Disaster Monitoring in Fujian Xiamen University of Technology Xiamen Fujian361024 China School of Information Media Zhangzhou Vocational College of Science and Technology Zhangzhou Fujian363200 China College of Software Engineering Xiamen University of Technology Xiamen Fujian361024 China

ISBN: (纸本)9798400717147

This research paper introduces an innovative machine learning-based methodology for detecting cracks in ancient buildings, a vital aspect of architectural heritage conservation. Recognizing the limitations of conventional techniques in addressing the complex nature of historical structures, this study explores the integration of deep learning algorithms with enhanced image processing methods tailored for aged and varied materials typical of ancient architecture. The paper includes a comprehensive process involving meticulous data collection from diverse ancient structures, employing specialized preprocessing methods to handle the unique challenges of old surfaces. The development of a custom machine learning model, designed to adapt to the intricacies of historical construction, is thoroughly detailed. Experimental results demonstrate the model's superior performance in accurately identifying structural cracks compared to traditional methods. This research not only significantly contributes to the preservation of historical buildings but also exemplifies the versatile application of machine learning in the field of architectural conservation. The findings hold promise for revolutionizing the approach to maintaining and restoring our architectural heritage, ensuring longevity and integrity. © 2024 ACM.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Image Based Feature Separation Using RBM Tech with ADBN Tech for Accurate Fruit Classification 5

Image Based Feature Separation Using RBM Tech with ADBN Tech...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Revathi, V. Kavin, Balasubramanian Prabhu Thirumalraj, Arunadevi Gangadevi, E. Balusamy, Balamurugan Gite, Shilpa New Horizon College of Engineering Department of Applied Sciences - Physics Ring Road Bellandur Post Bengaluru India School of Computing Srm Institute of Science and Technology Department of Data Science and Business Systems Chengalpattu Tamil Nadu Kattankulathur603 203 India K.Ramakrishnan College of Technology Department of Computer Science Engineering Tamil Nadu Trichy India Loyola College Department of Computer Science Chennai600034 India Delhi India Symbiosis Institute of Technology Pune Aiml Department Pune412115 India

ISBN: (纸本)9798350383522

One of the fastest-growing subfields of computer vision and picture categorization is fruit identification. The fruit industry could start using a standardised categorization system so that shoppers can easily distinguish between different types and quality levels of fruit. From a health perspective, fruit quality is essential. The task of classifying fruits is crucial in many commercial contexts. A supermarket cashier may use a fruit categorization system to better recognise the varieties of fruit and their associated costs. It might also be used to determine whether or not a given kind of fruit is suitable for a person's diet. The rising use of intelligent imaging equipment may be directly attributed to the proliferation and development of AI software. Deep learning methods, such as CNN, are now being used by researchers for picture categorization. CNN's superior performance may be achieved without using any manually-crafted characteristics, in contrast to the older methods. For automated categorization, it employs a plethora of filters that strip relevant visual information. Classifying fruits accurately is a challenge in the horticulture sector and calls for the knowledge of an expert. For accurately and quantitatively analysing fruits, the currently mentioned categorization techniques fall short. Therefore, it is beneficial to review the latest suggestions for categorizing fruits. To solve this problem, we need a computerised system that can automatically sort fruits into their respective categories. Deep learning models, such as the Restricted Boltzmann Machine (RBM) and the Adam based Deep Belief Network (DBN), are used in this assignment to categorise fruits according to the attributes that have been determined to be optimum and generated. The proposed approach has been shown to have effective accuracy and quantitative analysis outcomes, and this is just the beginning of this realisation. In addition, the suggested scheme's relatively strong computational mo

关键词： Deep Belief Network Fruits Classification Fruits Grading Handcrafted features Restricted Boltzmann Machine

来源：评论

学校读者我要写书评

暂无评论

A novel transformers-based external attention framework for breast cancer diagnosis

引用

Biomedical Signal Processing and Control 2025年 110卷

作者： Xi, Rui Ahmed, Awais Zeng, Xiaoyang Hou, Mengshu School of Computer Science and Engineering University of Electronic Science and Technology of China Sichuan611731 China School of Computer Science China West Normal University Sichuan637001 China School of Big Data and Artificial Intelligence Chengdu Technological University Sichuan611730 China

Breast cancer remains a leading cause of female mortality globally, creating a significant burden on healthcare systems and underscoring the need for precise AI-driven diagnostic solutions. Whole Slide Images (WSI) are central to breast cancer diagnosis but require substantial storage for high-resolution features, complicating their efficient use in medical applications. Vision Transformers (ViT) offer a promising approach for WSI patch processing, yet traditional ViT-based methods are computationally intensive and overlook cross-sample correlations. To address these limitations, we propose B-EANet, a novel framework that integrates ViT with an external attention mechanism for improved image classification in multi-modal breast cancer diagnosis. B-EANet's architecture includes PatchExtract, which efficiently extracts patches from mammograms, and PatchEmbedding, which reduces intermediate feature maps. The external attention mechanism reduces time complexity to linear, capturing intra-modality relationships while preserving computational efficiency. We evaluated B-EANet on three publicly available datasets, including BreakHis, CAMELYON 2017, and BACH 2018. The proposed approach achieved state-of-the-art results on all three datasets. BreakHis dataset achieved an F1-score of 96.2% and an AUC of 99.9%, while CAMELYON 2017 demonstrated an F1-Score of 93.89%, and AUC of 96.32%, and BACH 2018 recorded an F1-Score of 94.37% and an AUC of 97.71%. The B-EANet utilized only 4.35 MB of memory with 1.1×106 parameters. This framework significantly enhances the efficiency and effectiveness of automated breast cancer diagnosis, making deep learning more accessible to medical practice as well as it fulfills demands for resource-constrained clinical scenarios. © 2025 Elsevier Ltd

关键词： And breast cancer diagnosis Effective cross-sample correlations External attention Vision transformers Whole slide images

来源：评论

学校读者我要写书评

暂无评论

Graph Neural Networks for Vulnerability Detection: A Counterfactual Explanation

arXiv

引用

arXiv 2024年

作者： Chu, Zhaoyang Wan, Yao Li, Qian Wu, Yang Zhang, Hongyu Sui, Yulei Xu, Guandong Jin, Hai School of Computer Science and Technology Huazhong University of Science and Technology China School of Electrical Engineering Computing and Mathematical Sciences Curtin University Australia School of Big Data and Software Engineering Chongqing University China School of Computer Science and Engineering University of New South Wales Australia School of Computer Science University of Technology Sydney Australia National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology Wuhan430074 China

Vulnerability detection is crucial for ensuring the security and reliability of software systems. Recently, Graph Neural Networks (GNNs) have emerged as a prominent code embedding approach for vulnerability detection, owing to their ability to capture the underlying semantic structure of source code. However, GNNs face significant challenges in explainability due to their inherently black-box nature. To this end, several factual reasoning-based explainers have been proposed. These explainers provide explanations for the predictions made by GNNs by analyzing the key features that contribute to the outcomes. We argue that these factual reasoning-based explanations cannot answer critical what-if questions: "What would happen to the GNN's decision if we were to alter the code graph into alternative structures?" Inspired by advancements of counterfactual reasoning in artificial intelligence, we propose CFExplainer, a novel counterfactual explainer for GNN-based vulnerability detection. Unlike factual reasoning-based explainers, CFExplainer seeks the minimal perturbation to the input code graph that leads to a change in the prediction, thereby addressing the what-if questions for vulnerability detection. We term this perturbation a counterfactual explanation, which can pinpoint the root causes of the detected vulnerability and furnish valuable insights for developers to undertake appropriate actions for fixing the vulnerability. Extensive experiments on four GNN-based vulnerability detection models demonstrate the effectiveness of CFExplainer over existing state-of-the-art factual reasoning-based explainers. © 2024, CC BY.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Polarization Reconfigurable Magneto-Electric Dipole Antenna Array

Polarization Reconfigurable Magneto-Electric Dipole Antenna ...

引用

2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio science Meeting, AP-S/URSI 2022

作者： Hu, Jun Wong, Hang Lin, Wei Hefei University of Technology School of Microelectronics Hefei China City University of Hong Kong State Key Laboratory of Terahertz and Millimeter Waves Department of Electrical Engineering Hong Kong Hong Kong Global Big Data Technologies Centre School of Electrical and Data Engineering University of Technology Sydney UltimoNSW2007 Australia

ISBN: (数字)9781665496582

ISBN: (纸本)9781665496582

This paper reports a simple design method for wideband polarization reconfigurable magneto-electric (ME) dipole antenna and array. By only adopting two biasing voltages, the polarization can be switched among four polarizations, e.g., two orthogonal linearly polarized (LP) and two orthogonal circularly polarized (CP). This quad-polarization diversity is realized by systematically integrating a wideband reconfigurable feeding network and a ME dipole with two orthogonal feeding ports. By controlling the states of the switchable feeding network, two orthogonal LP mode corresponding to the two ports can be excited with specific phase difference, thereby generating four different polarizations. Moreover, the reconfigurable feeding network can be extended to array application without increasing any p-i-n diode. For proof of the concept, a 1 × 4 array is designed, fabricated and tested. The measured results confirm the array's capability for four reconfigurable polarizations. Moreover, the array also exhibits exceptional advantages as wide bandwidth and a simple switching topology. © 2022 IEEE.

关键词： Polarization

来源：评论

学校读者我要写书评

暂无评论

A Multi-Stage Vision Transformer for Fine-grained Image Classification 11

A Multi-Stage Vision Transformer for Fine-grained Image Clas...

引用

11th International Conference on Information technology in Medicine and Education, ITME 2021

作者： Huang, Zheng Du, Ji-Xiang Zhang, Hong-Bo Huaqiao University Department of Computer Science and Technology Xiamen China Fujian Key Laboratory of Big Data Intelligence and Security Huaqiao University Xiamen China

ISBN: (纸本)9781665406796

Different from general image classification, Fine-grained visual classification(FGVC) aims at recognizing the subclass of an object. This task is challenging due to the differences between subcategories that might be very small. At present, Vision Transformer(ViT) achieved huge success in traditional classification tasks benefited from its innate attention mechanism. Recent works extend the vision trans-former into the FGVC task and achieve state-of-the-art performance. However, those transformer-based structures inevitably harm the discriminative regions while also requiring a high computational cost. To address these problems, we propose a pooling-based vision transformer model with overlapping patches(OP-ViT), which inserts the pooling layer into a transformer encoder to form a multi-stage hierarchical structure. In particular, the overlapping patches scheme can preserve the informational region effectively. We evaluate the model on two fine-grained mushroom datasets. The experimental results show that the proposed model achieves competitive performance with fewer parameters and computational overhead. © 2021 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Fedward: Flexible Federated Backdoor Defense Framework with Non-IID data

arXiv

引用

arXiv 2023年

作者： Chen, Zekai Wang, Fuyi Zheng, Zhiwei Liu, Ximeng Lin, Yujie College of Computer Science and Big Data Fuzhou University Fuzhou China School of Information Technology Deakin University Waurn Ponds Australia

Federated learning (FL) enables multiple clients to collaboratively train deep learning models while considering sensitive local datasets’ privacy. However, adversaries can manipulate datasets and upload models by injecting triggers for federated backdoor attacks (FBA). Existing defense strategies against FBA consider specific and limited attacker models, and a sufficient amount of noise to be injected only mitigates rather than eliminates FBA. To address these deficiencies, we introduce a Flexible Federated Backdoor Defense Framework (Fedward) to ensure the elimination of adversarial backdoors. We decompose FBA into various attacks, and design amplified magnitude sparsification (AmGrad) and adaptive OPTICS clustering (AutoOPTICS) to address each attack. Meanwhile, Fedward uses the adaptive clipping method by regarding the number of samples in the benign group as constraints on the boundary. This ensures that Fedward can maintain the performance for the Non-IID scenario. We conduct experimental evaluations over three benchmark datasets and thoroughly compare them to state-of-the-art studies. The results demonstrate the promising defense performance from Fedward, moderately improved by 33% ∼ 75% in clustering defense methods, and 96.98%, 90.74%, and 89.8% for Non-IID to the utmost extent for the average FBA success rate over MNIST, FMNIST, and CIFAR10, respectively. Copyright © 2023, The Authors. All rights reserved.

关键词： Network security

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：