检索结果-内蒙古大学图书馆

2023 International Conference on Electrical, Computer, Communications and Mechatronics engineering, ICECCME 2023

作者： Shah, Kamen Pantoja, Maria California Polytechnic State University Dept. Computer Science and Software Engineering San Luis Obispo United States

ISBN: (纸本)9798350322972

Global warming has increased large-scale natural disasters at an alarmingly greater frequency. These natural disasters affect humans and the ecosystems that all species rely upon for food and shelter. A significant byproduct of global warming is the emergence of mega-fires, which are wildfires that burn more than 100,000 acres. Mega fires have exhibited the capacity to destroy entire ecosystems and urban areas. Researchers forecast a significant increase in wildfires during the next decade. This is a fundamentally growing problem that mandates modern solutions. Currently, simulation models are employed to predict wildfire propagation and aid firefighters in suppressing them. However, these methods are computationally expensive and often inaccurate. A recent advance in this area is the usage of neural networks (NN), which are systematically more accurate and computationally efficient. This paper focuses on predicting wildfire spread using NN with an attention mechanism to improve spatial recognition and overall performance in neural networks for wildfire spread prediction. We train different models on 12 distinct observational variables derived from the Google Earth Engine catalog. Evaluation is conducted with accuracy, Dice coefficient score, ROC-AUC, and F1-score. Results show that when augmenting segmentation models with attention mechanisms, the attention component improves feature suppression and recognition, improving overall performance. Furthermore, we use ensemble modeling to reduce bias and variation, leading to more consistent and accurate predictions. The architecture presented in this research achieved a ROC-AUC score of 86.2% and an accuracy of 82.1% when inferencing on wildfire propagation at 30-minute intervals. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Logic-based software Tool for Business Process Model Complexity Assessment 4

Fuzzy Logic-based Software Tool for Business Process Model C...

引用

4th IEEE KhPI Week on Advanced Technology, KhPI Week 2023

作者： Kopp, Andrii Orlovskyi, Dmytro Litvinova, Uliya Dept. of Software Engineering and Management Intelligent Technologies National Technical University "Kharkiv Polytechnic Institute" Kharkiv Ukraine

ISBN: (纸本)9798350395532

The high complexity of business process models may negatively impact their quality and usability, and cause errors, costs, or even more serious damage to critical business processes when inefficient models are used. Therefore, in this study, we propose the fuzzy logic-based software tool to assess the complexity of business process models. This software tool uses the fuzzy inference system, in which rules are inferred from the existing business process model complexity metrics and their thresholds. However, the use of the fuzzy logic-based approach outperforms the existing approach based on crisp metric values and the weighted sum model by 30%, when the obtained results are compared to the expert judgment results. Fuzzy inference rules are similar to human reasoning and assume uncertain or borderline metric values by improving assessment results. © 2023 IEEE.

关键词： Computer software

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection of EEG in patients with epilepsy based on Graph Deviation Network 6

Anomaly Detection of EEG in patients with epilepsy based on ...

引用

6th International Conference on Computer Information Science and Application Technology, CISAT 2023

作者： Chen, Ming Liu, Changyu Gao, Huaijin Tao, Haomin Lin, Siyuan Computer Technology and Software Engineering Wuhan Polytechnic Wuhan430074 China Biomedical Engineering and Instrument Science Zhejiang University Hangzhou310027 China

ISBN: (纸本)9781510668546

A chronic neurological condition called epilepsy affects about 50 million people globally. Although there has been a lot of study on deep neural networks to identify seizures, it is still difficult to precisely define the structural relations between electrodes in EEG signals. The difficulty involved may lead to less accurate prediction. We provide a novel method that combines structured learning methods with graph neural networks and incorporates graph convolution to provide explanations for detected anomalies in EEG signals in order to overcome this constraint. Our investigations on the CHB-MIT dataset show that our approach is more effective and efficient than baseline methods and conventional neural network models at identifying the onset of seizures. © 2023 SPIE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Accelerated Vector Normalization for Rendering Tasks 14

Accelerated Vector Normalization for Rendering Tasks

引用

14th International Conference on Advanced Computer Information Technologies, ACIT 2024

作者： Romanyuk, Olexandr Zavalniuk, Yevhen Mykhaylov, Pavlo Chekhmestruk, Roman Titova, Nataliia Romanyuk, Sergey Vinnytsia National Technical University Department of Software Engineering Vinnytsia Ukraine 3D Generation GmbH Dortmund Germany Odessa National Polytechnic University Department of Biomedical Engineering Odessa Ukraine

The purpose of the work is the development of simplified vector normalization expressions for computer graphics tasks, which will allow to increase the productivity of three-dimensional images creation. © 2024 IEEE.

ISBN: (纸本)9798350350036

关键词： Chebyshev polynomials

来源：评论

学校读者我要写书评

暂无评论

A multi-objective comprehensive framework for predicting protein-peptide interactions and binding residues

引用

IEEE Journal of Biomedical and Health Informatics 2025年第6期PP卷 PP页

作者： Wang, Ruheng Yang, Xuetong Pang, Chao Wei, Leyi University of Texas Southwestern Medical Center Department of Biomedical Engineering DallasTX United States Shandong University School of Software Jinan China Jinan China Macao Polytechnic University Centre for Artificial Intelligence driven Drug Discovery Faculty of Applied Science China Xiamen University School of Informatics Xiamen China

The identification of protein-peptide interacting pairs and their corresponding binding residues is fundamentally crucial and can greatly facilitate the peptide therapeutics designing and understanding the mechanisms of protein functions. Recently, several computational approaches have been proposed to solve the protein-peptide interaction prediction problem. However, most existing prediction methods cannot directly predict the protein-peptide interacting pairs as well as the binding residues from protein and peptide sequences simultaneously. Here, we developed a Comprehensive Protein-Peptide Interaction prediction Framework (CPPIF), to predict both binary protein-peptide interaction and their binding residues. We also constructed a benchmark dataset containing more than 8,900 protein-peptide interacting pairs with non-covalent interactions and their corresponding binding residues to systematically evaluate the performances of existing models. Comprehensive evaluation on the benchmark datasets demonstrated that CPPIF can successfully predict the non-covalent protein-peptide interactions that cannot be effectively captured by previous prediction methods. Moreover, CPPIF outperformed other state-of-the-art methods in predicting binding residues in the peptides and achieved good performance in the identification of important binding residues in the proteins. © 2025 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Mutual Retinex: Combining Transformer and CNN for Image Enhancement

引用

IEEE Transactions on Emerging Topics in Computational Intelligence 2024年第3期8卷 2240-2252页

作者： Jiang, Kui Wang, Qiong An, Zhaoyi Wang, Zheng Zhang, Cong Lin, Chia-Wen Harbin Institute of Technology School of Computer Science and Technology Harbin150001 China Wuhan University National Engineering Research Center for Multimedia Software School of Computer Science Wuhan430072 China Wuhan Polytechnic University School of Mathematics and Computer Science Wuhan430024 China National Tsing Hua University Department of Electrical Engineering Institute of Communications Engineering Hsinchu30013 Taiwan

Images captured in low-light or underwater environments are often accompanied by significant degradation, which can negatively impact the quality and performance of downstream tasks. While convolutional neural networks (CNNs) and Transformer architectures have made significant progress in computer vision tasks, there are few efforts to harmonize them into a more concise framework for enhancing such images. To this end, this study proposes to aggregate the individual capability of self-attention (SA) and CNNs for accurate perturbation removal while preserving background contents. Based on this, we carry forward a Retinex-based framework, dubbed as Mutual Retinex, where a two-branch structure is designed to characterize the specific knowledge of reflectance and illumination components while removing the perturbation. To maximize its potential, Mutual Retinex is equipped with a new mutual learning mechanism, involving an elaborately designed mutual representation module (MRM). In MRM, the complementary information between reflectance and illumination components are encoded and used to refine each other. Through the complementary learning via the mutual representation, the enhanced results generated by our model exhibit superior color consistency and naturalness. Extensive experiments have shown the significant superiority of our mutual learning based method over thirteen competitors on the low-light task and ten methods on the underwater image enhancement task. In particular, our proposed Mutual Retinex respectively surpasses the state-of-the-art method MIRNet-v2 by 0.90 dB and 2.46 dB in PSNR on the LOL 1000 and FIVEK datasets, while with only 19.8% model parameters. © 2017 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Recursive Confidence Training for Pseudo-Labeling Calibration in Semi-Supervised Few-Shot Learning

引用

IEEE Transactions on Image Processing 2025年 34卷 3194-3208页

作者： Jing, Kunlei Ma, Hebo Zhang, Chen Wen, Lei Zhang, Zhaorui Xi’an Jiaotong University School of Software Engineering National Key Laboratory of Human-Machine Hybrid Augmented Intelligence Xi’an China The Hong Kong Polytechnic University Department of Computing Hong Kong Xi’an Jiaotong University Institute of Science and Education Development Xi’an China The Hong Kong Polytechnic University Department of Computing School of Hotel and Tourism Management Hong Kong Guangzhou China

Semi-Supervised Few-Shot Learning (SSFSL) aims to address the data scarcity in few-shot learning by leveraging both a few labeled support data and abundant unlabeled data. In SSFSL, a classifier trained on scarce support data is often biased and thus assigns inaccurate pseudo-labels to the unlabeled data, which will mislead downstream learning tasks. To combat this issue, we introduce a novel method called Certainty-Aware Recursive Confidence Training (CARCT). CARCT hinges on the insight that selecting pseudo-labeled data based on confidence levels can yield more informative support data, which is crucial for retraining an unbiased classifier to achieve accurate pseudo-labeling—a process we term pseudo-labeling calibration. We observe that accurate pseudo-labels typically exhibit smaller certainty entropy, indicating high-confidence pseudo-labeling compared to those of inaccurate pseudo-labels. Accordingly, CARCT constructs a joint double-Gaussian model to fit the certainty entropies collected across numerous SSFSL tasks. Thereby, A semi-supervised Prior Confidence Distribution (ssPCD) is learned to aid in distinguishing between high-confidence and low-confidence pseudo-labels. During an SSFSL task, ssPCD guides the selection of both high-confidence and low-confidence pseudo-labeled data to retrain the classifier that then assigns more accurate pseudo-labels to the low-confidence pseudo-labeled data. Such recursive confidence training continues until the low-confidence ones are exhausted, terminating the pseudo-labeling calibration. The unlabeled data all receive accurate pseudo-labels to expand the few support data to generalize the downstream learning task, which in return meta-refines the classifier, named self-training, to boost the pseudo-labeling in subsequent tasks. Extensive experiments on basic and extended SSFSL setups showcase the superiority of CARCT versus state-of-the-art methods, and comprehensive ablation studies and visualizations justify our insigh

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Named entity recognition method of blockchain patent text based on deep learning 3

Named entity recognition method of blockchain patent text ba...

引用

3rd International Conference on Electronic Information engineering, Big Data, and Computer Technology, EIBDCT 2024

作者： Yang, Guangguang Niu, Sen Dai, Bingrong Zhang, Bofeng Li, Chao Jiang, Yangjing School of Computer and Information Engineering Institute for Artificial Intelligence Shanghai Polytechnic University Shanghai China Shanghai Development Center of Computer Software Technology Shanghai China

ISBN: (纸本)9781510680449

As blockchain technology research continues to advance, named entity recognition within blockchain patent texts has emerged as a fundamental cornerstone for various other tasks. In light of the absence of a publicly accessible corpus within the current realm of blockchain technology, as well as the challenges posed by insufficient text semantic expression, the dearth of semantic features, and the intricacies associated with capturing diverse word vector representations. This paper us of annotated blockchain patent texts and proposes the MBBC MacBert-BiLSTM-CRF MBBC model for named entity recognition in blockchain patents. The model employs embedding the feature layer to vectorize the input text, enriching text information and mitigating polysemy issues. Text feature information is acquired through the long short-term memory network, and the conditional random field model is integrated to enforce label relationships, yielding an optimal label sequence. In this study, the accuracy rate of BAT (Blockchain Application Technology, BAT) on the self-constructed corpus achieves 91%, with a recall rate of 96% and an Fl value of 93%, representing a notable enhancement compared to mainstream models. Ablation experiments further demonstrate that the model in this paper effectively performs named entity recognition tasks associated with blockchain technology and subject content. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Unique Data Balancing Method for Defect Detection in Power Transmission and Transformation 4

Unique Data Balancing Method for Defect Detection in Power T...

引用

4th International Conference on Smart Grid and Energy Internet, SGEI 2024

作者： Liu, Xiaohua He, Weiling Chang, Jiang Chen, Qiuxia School of Artificial Intelligence Shenzhen Polytechnic University Guangdong Shenzhen518055 China School of network Engineering Jiangxi University of Software Professional Technology Jiangxi Nanchang330000 China Institute of Applied Technology Shenzhen Polytechnic University Guangdong Shenzhen518055 China

ISBN: (纸本)9798350368314

This paper presents a unique data balancing approach using power transmission and transformation defect detection as an example. The proposed method achieves a more precise balance compared to traditional oversampling methods. It takes into account specific dataset characteristics and constraints to ensure effective sample adjustment. The experimental results demonstrate the superiority of this approach in enhancing object detection and classification accuracy within the defect detection context, providing a promising solution for improving data quality and model performance in relevant fields. ©2024 IEEE.

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

Fine-Grained Features-based Code Search for Precise Query-Code Matching 31

Fine-Grained Features-based Code Search for Precise Query-Co...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Zhang, Xinting Cheng, Mengqiu Wang, Mengzhen Gong, Songwen Cai, Yi Xie, Jiayuan Li, Qing Department of Computing The Hong Kong Polytechnic University Hong Kong School of Software Engineering South China University of Technology China Department of Mathematics The University of Hong Kong Hong Kong Guangdong Neusoft University China

ISBN: (纸本)9798891761964

Code search aims to quickly locate target code snippets from databases using natural language queries, which promotes code reusability. Existing methods can effectively obtain aligned token-level and query word-level features. However, these studies usually represent the semantics of code and query by averaging the features of each token and word respectively, which makes it difficult to accurately capture the code details that are closely related to the query. To address this issue, we propose a fine-grained code search model that consists of a cross-modal encoder, a mapping layer, and a classification layer. Specifically, we utilize a pre-trained model, GraphCodeBERT, in the cross-modal encoder to align features. In the mapping layer, we introduce a co-attention network to capture the fine-grained interactions between code and query, ensuring a model can precisely identify key code segments relevant to the query. Finally, in the classification layer, we incorporate instruction learning techniques that leverage contextual reasoning to improve the accuracy of query-code matching. Experimental results show that our proposed model significantly outperforms existing methods across multiple programming language datasets. © 2025 Association for Computational Linguistics.

关键词： Structured Query Language

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：