检索结果-内蒙古大学图书馆

Towards Long-Tailed Recognition for Graph Classification via Collaborative Experts

IEEE Transactions on Big data 2023年第6期9卷 1683-1696页

作者： Yi, Si-Yu Mao, Zhengyang Ju, Wei Zhou, Yong-Dao Liu, Luchen Luo, Xiao Zhang, Ming School of Statistics and Data Science Nankai University Tianjin300071 China School of Computer Science Peking University Beijing100871 China Department of Computer Science University of California Los AngelesCA90095 United States

Graph classification, aiming at learning the graph-level representations for effective class assignments, has received outstanding achievements, which heavily relies on high-quality datasets that have balanced class distribution. In fact, most real-world graph data naturally presents a long-tailed form, where the head classes occupy much more samples than the tail classes, it thus is essential to study the graph-level classification over long-tailed data while still remaining largely unexplored. However, most existing long-tailed learning methods in visions fail to jointly optimize the representation learning and classifier training, as well as neglect the mining of the hard-to-classify classes. Directly applying existing methods to graphs may lead to sub-optimal performance, since the model trained on graphs would be more sensitive to the long-tailed distribution due to the complex topological characteristics. Hence, in this paper, we propose a novel long-tailed graph-level classification framework via Collaborative Multi-expert Learning (CoMe) to tackle the problem. To equilibrate the contributions of head and tail classes, we first develop balanced contrastive learning from the view of representation learning, and then design an individual-expert classifier training based on hard class mining. In addition, we execute gated fusion and disentangled knowledge distillation among the multiple experts to promote the collaboration in a multi-expert framework. Comprehensive experiments are performed on seven widely-used benchmark datasets to demonstrate the superiority of our method CoMe over state-of-the-art baselines. © 2023 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Harmonization of Heart Disease dataset for Accurate Diagnosis:A Machine Learning Approach Enhanced by Feature Engineering

引用

computers, Materials & Continua 2025年第3期82卷 3907-3919页

作者： Ruhul Amin Md.Jamil Khan Tonway Deb Nath Md.Shamim Reza Jungpil Shin Department of Computer Science and Engineering Metropolitan UniversitySylhet3104Bangladesh Department of Statistics Pabna University of Science and TechnologyPabna6600Bangladesh Department of Computer Science & Engineering University of AizuAizu-WakamatsuFukushima956-8580Japan

Heart disease includes a multiplicity of medical conditions that affect the structure,blood vessels,and general operation of the *** researchers have made progress in correcting and predicting early heart disease,but more remains to be *** diagnostic accuracy of many current studies is inadequate due to the attempt to predict patients with heart disease using traditional *** using data fusion from several regions of the country,we intend to increase the accuracy of heart disease prediction.A statistical approach that promotes insights triggered by feature interactions to reveal the intricate pattern in the data,which cannot be adequately captured by a single *** processed the data using techniques including feature scaling,outlier detection and replacement,null and missing value imputation,and more to improve the data ***,the proposed feature engineering method uses the correlation test for numerical features and the chi-square test for categorical features to interact with the *** reduce the dimensionality,we subsequently used PCA with 95%*** identify patients with heart disease,hyperparameter-based machine learning algorithms like RF,XGBoost,Gradient Boosting,LightGBM,CatBoost,SVM,and MLP are utilized,along with ensemble *** model’s overall prediction performance ranges from 88%to 92%.In order to attain cutting-edge results,we then used a 1D CNN model,which significantly enhanced the prediction with an accuracy score of 96.36%,precision of 96.45%,recall of 96.36%,specificity score of 99.51%and F1 score of 96.34%.The RF model produces the best results among all the classifiers in the evaluation matrix without feature interaction,with accuracy of 90.21%,precision of 90.40%,recall of 90.86%,specificity of 90.91%,and F1 score of 90.63%.Our proposed 1D CNN model is 7%superior to the one without feature engineering when compared to the suggested *** illustrates how interaction-focu

关键词： Heart disease harmonization feature interaction PCA model hyper tuning machine learning

来源：评论

学校读者我要写书评

暂无评论

Assessing the Performance of Feedforward Neural Network Models with Random data Split for Time Series data: A Simulation Study

Assessing the Performance of Feedforward Neural Network Mode...

引用

2024 International Research Conference on Smart Computing and Systems Engineering, SCSE 2024

作者： Basnayake, B.R.P.M. Chandrasekara, N.V. Department of Statistics and Computer Science University of Kelaniya Kelaniya Sri Lanka Department of Statistics and Computer Science University of Peradeniya Peradeniya Sri Lanka

ISBN: (纸本)9798350375688

The majority of findings and conclusions related to the application of artificial neural networks (ANNs) for time series data have been derived through non-random data-splitting procedures. In this methodology, the initial set of observations in the dataset is employed for model training, followed by a subsequent set of observations for validation and the final set of observations for testing. However, this study presents a comprehensive simulation study on assessing the performance of Feedforward neural networks (FFNN) with the random data split procedure. For this purpose, eight nonlinear models from the literature were employed to generate multiple series where they represent different features available in the time series data. The complexity of the selected models was further improved by introducing Poisson processes with different jump sizes. From each selected time series model, 30 replications were generated using distinct initial random seeds for the error term. The data were randomly partitioned, allocating 80% for training, 10% for validation, and 10% for testing purposes. The FFNN models were fitted incorporating the inputs from past observations and moving average values. Moreover, each individual fitted model was trained 30 times to obtain a statistically robust evaluation of model performance through the averaging of predictive values. The findings reveal that the FFNN models performed well with the random data split procedures for time series data with lower minimum error values. The same idea was observed by graphs fitted between the actual test values and the average of the forecasted values. The results obtained from this simulation study are important, as they provide valuable insights into the broader utilization of FFNNs with regard to the effectiveness of random data split procedures in time series forecasting. © 2024 IEEE.

关键词： Feedforward neural networks

来源：评论

学校读者我要写书评

暂无评论

Berry-Esseen bounds for degenerate U-statistics with application to distance correlation Dedicated to the Memory of Professor Xiru Chen on the Twentieth Anniversary of His Passing

引用

science China Mathematics 2025年

作者： Song-Hao Liu Qi-Man Shao Hao Shi Department of Statistics and Data Science Southern University of Science and Technology Shenzhen International Center for Mathematics Southern University of Science and Technology Department of Statistics The Chinese University of Hong Kong

Let X1, X2,..., X_n be independent and identically distributed random vectors, Tn =Tn（X1, X2,..., X_n） be a degenerate U-statistic, and ?n = ?n（X1, X2,..., X_n） be a remainder term. In this paper, we establish a Berry-Esseen-type theorem for Tn+ ?n by an exchangeable pair approach. As an application, a sharp error bound of normal distribution approximation for the distance correlation is obtained,which improves some results in Gao et al.（2021）.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SMART AGRICULTURE: INTEGRATING AIR QUALITY MONITORING WITH DEEP LEARNING FOR PROCESS OPTIMIZATION*

引用

Scalable Computing 2025年第3期26卷 1005-1016页

作者： Shobana, J. Subramanian, A Venkata Balamurugan, P. Perumal, Sivakumar Sankari, V. Eldho, K.J. Nareshkumar, R. Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Tamilnadu Kattankulathur India Department of Computer Science and Engineering GITAM University Bengaluru India Department of Computer Science and Engineering J N N Institute of Enginering India Saveetha university Chennai India Department of Computer Science and Engineering Sasi Institute of Technology and Engineering Andhra Pradesh Tadepalligudem India Department of Artificial Intelligence and Data Science K.Ramakrishnan College of Engineering Kariyamanickam Rd Tamil Nadu Samayapuram India PG and Research Department of Computer Science Mary Matha Arts and Science College Kerala Mananthavady India Department of Networking and Communications School of Computing College of Engineering and Technology SRM Institute of Science and Technology Tamilnadu Kattankulathur India

Modernization and intense industrialization have led to a substantial improvement in people’s quality of life. However, the aspiration for achieving an improved quality of life results in environmental contamination. A primary consequence of environmental degradation is air pollution, resulting from rising levels of poisonous chemicals in the atmosphere, which may induce detrimental health conditions in humans. It is harmful to both humans and agriculture. Given that the effects of air pollution on plants may not be readily apparent, it is important to analyse the necessary data and compute the outcomes. Farmers prioritise on pests and plant diseases, frequently neglecting the detrimental impacts of air pollution. Some plant species can withstand high amounts of pollution from suspended particulate matter and accumulated gases, while others are more susceptible to harm. Therefore, plants’ reaction to air pollution is influenced by the kind of harmful compounds, their levels, and the plant’s susceptibility to them. The LSTM +CNN Proposed Ensemble method may be used to analyse the impact of air pollution on agriculture by examining trends in crop production over time and predicting which crop is more resistant based on the pollution data. The initiative created for this aim may assist farmers in determining the most suitable crop to cultivate in their fields to minimize the impact of air pollution on agricultural yield. The findings show deep learning algorithms correctly predict hourly pollutant concentrations such as carbon monoxide, sulphur dioxide, nitrogen dioxide, ground-level ozone, and particulate matter 2.5, along with the hourly Air Quality Index (AQI) for California. A proposed model used test RMSE values as a measure to evaluate prediction performance, achieving the best possible results. © 2025 SCPE.

关键词： Nitrogen oxides

来源：评论

学校读者我要写书评

暂无评论

B-Spline Method for Spatio-Temporal Inverse Model

引用

Journal of Systems science & Complexity 2022年第6期35卷 2336-2360页

作者： WANG Hongxia ZHAO Zihan WU Yuehua LUO Xuehong School of Statistics and Data Science Nanjing Audit UniversityNanjing 211815China Department of Mathematics and Statistics York UniversityTorontoOntarioCanada Department of Statistics and Data Science School of EconomicsXiamen UniversityXiamen 361005China

Inverse models can be used to estimate surface fluxes in terms of the observed atmospheric concentration measurement *** paper proposes a new nonparametric spatio-temporal inverse model and provides the global expressions for the estimates by employing the B-spline *** authors establish the asymptotic normality of the estimators under mild *** authors also conduct numerical studies to evaluate the finite sample performance of the proposed ***,the authors apply the method to anthropogenic carbon dioxide(CO_(2))emission data from different provinces of Canada to illustrate the validity of the proposed techniques.

关键词： Inverse model spatio-temporal heterogeneity spatio-temporal correlation

来源：评论

学校读者我要写书评

暂无评论

Parameter Estimation of Spatial Error Model – Multivariate Adaptive Generalized Poisson Regression Spline

引用

Engineering Letters 2023年第3期31卷 1265-1272页

作者： Yasmirullah, Septia Devi Prihastuti Otok, Bambang Widjanarko Purnomo, Jerry Dwi Trijoyo Prastyo, Dedy Dwi Department of Statistics Faculty of Science and Data Analytics Institut Teknologi Sepuluh Nopember Surabaya Indonesia

The non-parametric regression method becomes an alternative that prioritizes flexibility. Therefore, it is possible to obtain a regression curve model when its shape is not yet known. Multivariate adaptive regression spline (MARS) is one of the non-parametric approaches. In 1991, MARS was introduced by Friedman. The MARS approach, which uses nonparametric regression, can consider additive and interactive effects between predictor variables. MARS modeling has typically been used to model continuous or categorical data. However, researchers in the health sector not only encounter data with continuous or categorical responses but also count data. The original MARS method did not support count data with varying variances and means. Therefore, this study aims to develop the Spatial Error Model—Multivariate Adaptive Generalized Poisson Regression Spline (SEM-MAGPRS), which combines the MARS method with the generalized Poisson regression method with spatial effects. © 2023, International Association of Engineers. All rights reserved.

关键词： Scanning electron microscopy

来源：评论

学校读者我要写书评

暂无评论

FaVEL: Fact Validation Ensemble Learning 24th

FaVEL: Fact Validation Ensemble Learning

引用

24th International Conference on Knowledge Engineering and Knowledge Management, EKAW 2024

作者： Qudus, Umair Pekarou, Franck Lionel Tatkeu da Silva, Ana Alexandra Morim Röder, Michael Ngomo, Axel-Cyrille Ngonga Data Science Group Department of Computer Science Paderborn University Paderborn Germany

ISBN: (纸本)9783031777912

Validating assertions before adding them to a knowledge graph is an essential part of its creation and maintenance. Due to the sheer size of knowledge graphs, automatic fact-checking approaches have been developed. These approaches rely on reference knowledge to decide whether a given assertion is correct. Recent hybrid approaches achieve good results by including several knowledge sources. However, it is often impractical to provide a sheer quantity of textual knowledge or generate embedding models to leverage these hybrid approaches. We present FaVEL, an approach that uses algorithm selection and ensemble learning to amalgamate several existing fact-checking approaches that rely solely on a reference knowledge graph and, hence, use fewer resources than current hybrid approaches. For our evaluation, we create updated versions of two existing datasets and a new dataset dubbed FaVEL-DS. Our evaluation compares our approach to 15 fact-checking approaches—including the state-of-the-art approach HybridFC—on 3 datasets. Our results demonstrate that FaVEL outperforms all other approaches significantly by at least 0.04 in terms of the area under the ROC curve. Our source code, datasets, and evaluation results are open-source and can be found at https://***/dice-group/favel. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Deep learning framework for automatic detection and classification of sleep apnea severity from polysomnography signals

引用

Neural Computing and Applications 2024年第28期36卷 17483-17493页

作者： Raja Brundha, A. Lakshmi Sangeetha, A. Balajiganesh, A. Department of Artificial Intelligence and Data Science Sri Sai Ram Engineering College Chennai India Department of Computer Science Engineering Velammal Engineering College Chennai India

Sleep apnea (SA) is a sleep-related breathing disorder characterized by breathing pauses during sleep. A person’s sleep schedule is significantly influenced by that person’s hectic lifestyle, which may include unhealthy eating habits and their line of work. Polysomnographic (PSG) sleep studies examine sleep-related disorders by recording various biosignals from the human body. However, SA classification methods could be more robust in terms of performance because they rely on feature-engineering strategies or employ a particular signal from PSG recording for diagnosis. This study aims to classify the severity of SA according to the apnea–hypopnea index (AHI) into normal, mild, and moderate-to-severe groups using oxygen saturation (SpO2), electroencephalogram (EEG), and electrocardiogram (ECG) signals. The proposed deep neural network (DNN)-bidirectional long short-term memory (DNN-BiLSTM) framework addresses the issue of low detection accuracy in analysis. The DNN-BiLSTM approach employs features extracted from a multiscale dilation attention 1D convolutional neural network (MSDA-1DCNN) as input for detection and classification purposes. The MSDA-1DCNN network extracts deep features from processed SpO2, EEG, and ECG signals. The developed firefly combined electric fish optimization (FCEFO) algorithm improves performance by optimizing the hidden neuron count of the DNN and the learning rate of the BiLSTM framework. The performance measures proved the effectiveness of the model over conventional machine and deep learning approaches. With the integration of deep features, the proposed DNN-BiLSTM model provides enhanced performance in terms of accuracy and precision. Thus, the proposed approach is progressive and can be used for medical diagnosis. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Accelerating multiscale electronic stopping power predictions with timedependent density functional theory and machine learning

引用

npj Computational Materials 2024年第1期10卷 993-1002页

作者： Logan Ward Ben Blaiszik Cheng-Wei Lee Troy Martin Ian Foster AndréSchleife Data Science and Learning Division Argonne National LaboratoryLemontIL60437USA Department of Computer Science The University of ChicagoChicagoIL60637USA Department of Materials Science and Engineering University of Illinois at Urbana-Champaign UrbanaUrbanaIL61801USA

Knowing the rate at which particle radiation releases energy in a material,the“stopping power,”is key to designing nuclear reactors,medical treatments,semiconductor and quantum materials,and many other *** the nuclear contribution to stopping power,i.e.,elastic scattering between atoms,is well understood in the literature,the route for gathering data on the electronic contribution has for decades remained costly and reliant on many simplifying assumptions,including that materials are *** establish a method that combines time-dependent density functional theory(TDDFT)and machine learning to reduce the time to assess new materials to hours on a supercomputer and provide valuable data on how atomic details influence electronic *** approach uses TDDFT to compute the electronic stopping from first principles in several directions and then machine learning to interpolate to other directions at a cost of 10 million times fewer *** demonstrate the combined approach in a study of proton irradiation in aluminum and employ it to predict how the depth of maximum energy deposition,the“Bragg Peak,”varies depending on the incident angle—a quantity otherwise inaccessible to modelers and far outside the scales of quantum mechanical *** lack of any experimental information requirement makes our method applicable to most materials,and its speed makes it a prime candidate for enabling quantum-to-continuum models of radiation *** prospect of reusing valuable TDDFT data for training the model makes our approach appealing for applications in the age of materials data science.

关键词： electronic quantum directions

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：