检索结果-内蒙古大学图书馆

7th IFIP TC 12 International Conference on Computational Intelligence in Data science, ICCIDS 2024

作者： Ranjith Kumar, M. Sudeesh Kumar, V. Tharun Kaarthik, G.K. Chatiyode, Veda Srinivasan Anusha, Janani Revathi, P. School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Chennai600127 India Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Department of Computer Science and Engineering C Abdul Hakeem College of Engineering and Technology Tamil Nadu Melvisharam India

ISBN: (纸本)9783031699856

The use of multi-class Support Vector Machines (SVM) for snowfall prediction is an advanced meteorological application. The study emphasizes how valuable snowfall forecasts are in various contexts, including agriculture, aviation, transportation management, and climate reporting. This approach presents a novel methodology for classifying snowfall types by analyzing various meteorological factors such as temperature range, wind dynamics, and precipitation. A 400-entries of datasets were pulled from GitHub to demonstrate the methodology. The sample is selected to reduce the complexity and to increase the performance. The dataset is split into a testing set (30%) and a training set (70%), which aids in assessing the model’s performance in a wide range of parameters. When the algorithm was first tested, it could distinguish different types of snowfall with a remarkable 83% accuracy rate based on indicators such as Temperature (min & max), Precipitation, Wind Speed, and Wind Gust. By optimizing the SVM configuration through hyper-parameter tuning approaches such as grid search, we were able to further refine our model’s accuracy to an astounding 91%. This improvement in forecast accuracy signifies a significant move away from older, more expensive instrument-based methods and towards data-driven snowfall analysis. Our results show how machine learning can revolutionize weather prediction systems, providing a more effective and economical method of comprehending and predicting snowfall patterns. © IFIP International Federation for Information Processing 2024

关键词： Snow

来源：评论

学校读者我要写书评

暂无评论

Graph Contrastive Learning for Truth Inference 40

Graph Contrastive Learning for Truth Inference

引用

40th IEEE International Conference on Data engineering, ICDE 2024

作者： Liu, Hao Liu, Jiacheng Tang, Feilong Li, Peng Chen, Long Yu, Jiadi Zhu, Yanmin Gao, Min Yang, Yanqin Hou, Xiaofeng Chinese University of Hong Kong Department of Computer Science and Engineering Hong Kong East China Normal University School of Data Science and Engineering Shanghai China Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai China University of Aizu School of Computer Science and Engineering Japan Simon Fraser University School of Computing Science Canada

ISBN: (纸本)9798350317152

Crowdsourcing has become a popular paradigm for collecting large-scale labeled datasets by leveraging numerous annotators. However, these annotators often provide noisy labels due to varying expertise. Truth inference aims to infer accurate consensus labels from noisy crowdsourced annotations. Existing approaches rely heavily on hand-engineered assumptions or ground truth data, limiting their applicability. To address this, we propose GOVERN, a graph contrastive learning framework for truth inference without such external supervision. GOVERN employs a novel graph data augmentation strategy to generate views capturing worker coordination patterns. A contrastive objective then encourages invariant representations across views, enabling the discovery of features related to the hidden consensus. Further, a label correction method based on k-nearest neighbors refines noisy pseudo-labels to supervise model training. Comprehensive experiments on 9 real-world datasets demonstrate that GOVERN outperforms state-of-the-art truth inference techniques. © 2024 IEEE.

关键词： Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

Transformer-Enhanced U-Net with Transfer Learning for Accurate Detection of Eye Coloboma 4

Transformer-Enhanced U-Net with Transfer Learning for Accura...

引用

4th International Conference on Power, Energy, Control and Transmission Systems, ICPECTS 2024

作者： Dhayanithi, A. Bala, K. Bharath Institute of Higher Education and Research School of Computing Department of Computer Science and Engineering Tamil Nadu Chennai600073 India Bharath Institute of Higher Education and Research School of Computing Department of Computer Science and Engineering Tamil Nadu Chennai600073 India

ISBN: (纸本)9798331508845

Eye coloboma is a type of congenital eye abnormality that causes developmental abnormalities of the eye which may culminate in eye disorders that fundamentally derange eyesight. Fractional and timely diagnosis remains highly important to its proper managing and treating. This work proposes a model with a Transformer-Enhanced U-Net design implemented with Transfer Learning to enhance the ability of the model to detect and segment eye coloboma from medical imaging data. This work builds upon the benefits of U-Net which has shown promising results especially in the biomedical image segmentation problem through addition of transformer modules that introduce long range dependencies and contextual information. This enhancement makes helps the model to pay more attention to such minor aspects as coloboma and general diagnostic accuracy consequently. Thanks to Transfer Learning with a pretrained backbone, for example Efficient Net the system is provided with Feature Representations recovered from large datasets that are already available and training time is drastically cut short while the performance of the system is not compromised at *** approach includes fine-tuning of Transformer-Enhanced U-Net model using a selected set of eye images, labelled for coloboma existence. By including the self-attention mechanism, the model is capable of focusing on the critical regions in the image, increasing its responsiveness to any form of coloboma. Preliminary tests show that this scheme performs better than the standard convolutional networks for segmenting complex regions by minimizing false negatives. Further, the model's flexibility to different imaging conditions demonstrates its suitability in realistic clinical applications. The objective of this research is to come up with a dependable, Auto-Generated diagnostic tool that will help the ophthalmologists in the early diagnosis of the eye related illnesses hence making increased positive outcomes for eye patients. The Transf

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

HPC Application Parameter Autotuning on Edge Devices: A Bandit Learning Approach 31

HPC Application Parameter Autotuning on Edge Devices: A Band...

引用

31st Annual IEEE International Conference on High Performance computing, Data, and Analytics, HiPC 2024

作者： Hossain, Abrar Badawy, Abdel-Hameed A. Islam, Mohammad A. Patki, Tapasya Ahmed, Kishwar Department of Electrical Engineering and Computer Science The University of Toledo United States Department of Electrical and Computer Engineering New Mexico State University United States Department of Computer Science and Engineering The University of Texas Arlington United States Center for Applied Scientific Computing Lawrence Livermore National Laboratory United States

ISBN: (纸本)9798331509095

The growing necessity for enhanced processing capabilities in edge devices with limited resources has led us to develop effective methods for improving high-performance computing (HPC) applications. In this paper, we introduce LASP (Lightweight Autotuning of Scientific Application Parameters), a novel strategy designed to address the parameter search space challenge in edge devices. Our strategy employs a multi-armed bandit (MAB) technique focused on online exploration and exploitation. Notably, LASP takes a dynamic approach, adapting seamlessly to changing environments. We tested LASP with four HPC applications: Lulesh, Kripke, Clomp, and Hypre. Its lightweight nature makes it particularly well-suited for resource-constrained edge devices. By employing the MAB framework to efficiently navigate the search space, we achieved significant performance improvements while adhering to the stringent computational limits of edge devices. Our experimental results demonstrate the effectiveness of LASP in optimizing parameter search on edge devices. © 2024 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

An integrated strategy of AEF attribute evaluation for reliable thunderstorm detection

引用

Digital Communications and Networks 2025年第1期11卷 234-245页

作者： Xu Yang Hongyan Xing Xinyuan Ji Xin Su Witold Pedrycz School of Electronics and Information Engineering Nanjing University of Information Science and TechnologyNanjing 210044China Department of Electrical and Computer Engineering University of AlbertaEdmonton AB T6G 2R3Canada College of Internet of Things Engineering Hohai UniversityChangzhou 213022China Systems Research Institute Polish Academy of Sciences00-901 WarsawPoland Department of Computer Engineering Faculty of Engineering and Natural SciencesIstinye UniversitySariyer/IstanbulTurkey

Thunderstorm detection based on the Atmospheric Electric Field(AEF)has evolved from time-domain models to space-domain *** is especially important to evaluate and determine the particularly Weather Attribute(WA),which is directly related to the detection reliability and *** this paper,a strategy is proposed to integrate three currently competitive WA's evaluation ***,a conventional evaluation method based on AEF statistical indicators is *** evaluation approaches include competing AEF-based predicted value intervals,and AEF classification based on fuzzy *** AEF attributes contribute to a more accurate AEF classification to different *** resulting dynamic weighting applied to these attributes improves the classification *** evaluation method is applied to evaluate the WA of a particular AEF,to obtain the corresponding evaluation *** integration in the proposed strategy takes the form of a score *** cumulative score levels correspond to different final WA *** imaging is performed to visualize thunderstorm activities using those AEFs already evaluated to exhibit thunderstorm *** results confirm that the proposed strategy effectively and reliably images thunderstorms,with a 100%accuracy of WA *** is the first study to design an integrated thunderstorm detection strategy from a new perspective of WA evaluation,which provides promising solutions for a more reliable and flexible thunderstorm detection.

关键词： Atmospheric electric field(AEF) Thunderstorm Attribute Fuzzy c-means Imaging

来源：评论

学校读者我要写书评

暂无评论

Fire detection method based on improved DETR 4

Fire detection method based on improved DETR

引用

4th International Symposium on AI, ISAI 2024

作者： Ge, Ruize Hu, Xiaoyin Xiao, Duo Zhejiang University College of Contral Science and Engineering China Hangzhou City University School of Information and Electrical Engineering Hangzhou China Hangzhou City University Hangzhou School of Computer and Computing Science China

ISBN: (纸本)9798350342482

Fire, as a type of disaster, poses a significant threat to both life and property safety. Therefore, timely and accurate detection of fire occurrences is of utmost importance. However, current fire detection methods that rely on traditional sensors suffer from limitations such as a high false alarm rate and extended response time. In this manuscript, we propose a novel fire detection method based on an enhanced version of DETR that leverages flame detection. Our approach entails several key modifications. Firstly, we replace the bounding box loss function of the original DETR with the alpha-CIoU loss function. This substitution enhances the accuracy and efficiency of our fire detection method. Secondly, we introduce relative position encoding to replace the sine-cosine position encoding in the transformer module. This adjustment aims to improve the model's ability to capture spatial relationships between flame instances, resulting in more precise detection outcomes. Furthermore, we incorporate multiscale features by modifying the backbone of DETR. This addition enables our algorithm to effectively handle variations in flame sizes and appearances, contributing to improved detection performance across different fire scenarios. Finally, we apply gradient clipping to the DETR optimizer to stabilize the training process and mitigate the potential issue of exploding gradients. To evaluate our proposed method, we train and test the model using a self-generated dataset specifically tailored for flame detection. Experimental results indicate that our improved DETR algorithm achieves an average accuracy of 92.27%, which represents a substantial 3.81% enhancement over the original DETR. Moreover, through ablation experiments, we demonstrate the effectiveness of each individual improvement in our approach. © 2024 IEEE.

关键词： Premixed flames

来源：评论

学校读者我要写书评

暂无评论

Enhanced Detection and Classification of PCB Defects Utilizing Advanced YOLO Architectures 3

Enhanced Detection and Classification of PCB Defects Utilizi...

引用

3rd International Conference on Trends in electrical, Electronics and computer engineering, TEECCON 2024

作者： Roshan, Vidhun Bardia, Viksith Prabu, M. Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Tamil Nadu Chennai India

ISBN: (纸本)9798331505714

In rapidly growing industries, speed and accuracy in manufacturing products has become paramount. In electronics production, particularly in Printed Circuit Boards (PCBs), detecting and classifying defects is crucial to ensuring product reliability and quality. PCBs are highly sophisticated, and defects are often imperceptible to the naked eye. To address this challenge, various data augmentation techniques were applied to the dataset to enhance model training. These techniques enabled the model to learn essential features, facilitating faster defect localization and classification into different categories. This research presents an advanced methodology for PCB defect detection using the latest version of YOLO (You Only Look Once) integrated with specialized enhancements. These enhancements include the Convolutional Block Attention Module (CBAM), an attention mechanism, and an Intersection over Union (IoU) based loss function. These additions significantly improve the model's ability to accurately detect defects by minimizing false negatives. Experimental evaluations were conducted with YOLO versions 8, 9, and 10, demonstrating that integrating CBAM and the IoU loss function yields promising results compared to traditional YOLO models. This paper provides manufacturing companies with a powerful mechanism to enhance efficiency and product quality through automated PCB defect detection techniques. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Control and Stability of Large-scale Power System with Highly Distributed Renewable Energy Generation:Viewpoints from Six Aspects

引用

CSEE Journal of Power and Energy Systems 2023年第1期9卷 8-14页

作者： Qing-Hua Wu Anjan Bose Chanan Singh Joe H.Chow Gang Mu Yuanzhang Sun Zhaoxi Liu Zhigang Li Yang Liu School of Electric Power Engineering South China University of TechnologyGuangzhou 510640China School of Electrical Engineering&Computer Science Washington State UniversityPullmanWA 99164USA Department of Electrical and Computer Engineering Texas A&M UniversityCollege StationTX 77843USA Department of Electrical Computer and Systems EngineeringRensselaer Polytechnic Institute(RPI)TroyNYUSA Key Laboratory of Modern Power System Simulation and Control&Renewable Energy Technology Ministry of Education(Northeast Electric Power University)Jilin 132012China School of Electrical Engineering and Automation Wuhan UniversityWuhan 430072China

Power systems are moving toward a low-carbon or carbon-neutral future where high penetration of renewables is *** conventional fossil-fueled synchronous generators in the transmission network being replaced by renewable energy generation which is highly distributed across the entire grid,new challenges are emerging to the control and stability of large-scale power *** analysis and control methods are needed for power systems to cope with the ongoing *** the CSEE JPES forum,six leading experts were invited to deliver keynote speeches,and the participating researchers and professionals had extensive exchanges and discussions on the control and stability of power ***,potential changes and challenges of power systems with high penetration of renewable energy generation were introduced and explained,and advanced control methods were proposed and analyzed for the transient stability enhancement of power grids.

关键词： Distributed energy resources high converter penetration power system control renewable energy generation stability control transient stability

来源：评论

学校读者我要写书评

暂无评论

Early-Stage Disease Prediction in Chilli Plant Using YOLO Models 2

Early-Stage Disease Prediction in Chilli Plant Using YOLO Mo...

引用

2nd IEEE International Conference on Advances in Information Technology, ICAIT 2024

作者： Manoj, R. Girish, Sandra Pushpa, B.R. Rani, N. Shobha Sangamesha, D. Department of Computer Science School of Computing Amrita Vishwa Vidyapeetham Mysuru India Department of Computer Science and Engineering Gitam School of Technology Gitam University Bengaluru India Department of Chemistry The National Institute of Engineering Mysore India

ISBN: (纸本)9798350383867

Agriculture is an important component of every country's economy, supplying the necessary resources to farmers and their families. The livelihoods of farmers are greatly threatened by crop diseases, which highlights the importance of early identification of diseases in chilli plants at the right stage of growth is crucial for timely fertilizer recommendation. This paper presents an intelligent transfer learning technique to detect thrips and viruses in chilli plants in the early stages of development. Stage-by-stage datasets are collected from chilli plant orchards around Mysore district, Karnataka, to carry out the training using the YOLO model. The dataset consists of three growth stages of chilli plants (15, 25, and 35 days) that are captured in diverse environmental settings with multiple-resolution smart phones. The annotations are created for the diseases healthy, viruses, and thrips at leaf level from whole plants for all three stages. Hyperparameters such as learning rate, the learning optimization algorithm, batch size, epochs, and loss functions are employed to fine-tune the YOLO v5, v6, and v7 models. To achieve high generalisation and reduce overfitting, a weight decay (weight_decay) of 0.0005 is employed. From the evaluation, it was noticed that YOLOv7 outperformed other YOLO models. A mAP score of 0.80 is achieved in stage 1, 0.82 in stage 2, and 0.73 in stage 3 with minimal validation loss and remarkable inference speed. © 2024 IEEE.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Sleep Stage Classification With Two-Stream Encoder-Decoder

引用

IEEE Transactions on Neural Systems and Rehabilitation engineering 2024年 32卷 2096-2105页

作者： Zhang, Zhao Lin, Bor-Shyh Peng, Chih-Wei Lin, Bor-Shing Wuyi University College of Mechanical and Electrical Engineering Fujian Wuyishan354300 China National Taipei University College of Electrical Engineering and Computer Science Department of Computer Science and Information Engineering New Taipei City237303 Taiwan Institute of Imaging and Biomedical Photonics National Yang Ming Chiao Tung University Tainan71150 Taiwan Taipei Medical University School of Biomedical Engineering College of Biomedical Engineering School of Gerontology and Long-Term Care College of Nursing Taipei11031 Taiwan National Taipei University Department of Computer Science and Information Engineering New Taipei City237303 Taiwan

Sleep staging serves as a fundamental assessment for sleep quality measurement and sleep disorder diagnosis. Although current deep learning approaches have successfully integrated multimodal sleep signals, enhancing the accuracy of automatic sleep staging, certain challenges remain, as follows: 1) optimizing the utilization of multi-modal information complementarity, 2) effectively extracting both long- and short-range temporal features of sleep information, and 3) addressing the class imbalance problem in sleep data. To address these challenges, this paper proposes a two-stream encode-decoder network, named TSEDSleepNet, which is inspired by the depth sensitive attention and automatic multi-modal fusion (DSA2F) framework. In TSEDSleepNet, a two-stream encoder is used to extract the multiscale features of electrooculogram (EOG) and electroencephalogram (EEG) signals. And a self-attention mechanism is utilized to fuse the multiscale features, generating multi-modal saliency features. Subsequently, the coarser-scale construction module (CSCM) is adopted to extract and construct multi-resolution features from the multiscale features and the salient features. Thereafter, a Transformer module is applied to capture both long- and short-range temporal features from the multi-resolution features. Finally, the long- and short-range temporal features are restored with low-layer details and mapped to the predicted classification results. Additionally, the Lovász loss function is applied to alleviate the class imbalance problem in sleep datasets. Our proposed method was tested on the Sleep-EDF-39 and Sleep-EDF-153 datasets, and it achieved classification accuracies of 88.9% and 85.2% and Macro-F1 scores of 84.8% and 79.7%, respectively, thus outperforming conventional traditional baseline models. These results highlight the efficacy of the proposed method in fusing multi-modal information. This method has potential for application as an adjunct tool for diagnosing sleep disorde

关键词： Sleep research

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：