检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Yan, Xu Fan, Xiaoliang Yang, Peizhen Wu, Zonghan Pan, Shirui Chen, Longbiao Zang, Yu Wang, Cheng Fujian Key Laboratory of Sensing and Computing for Smart Cities School of Informatics Computer Science & Technology Department Xiamen University Xiamen China Centre for Artificial Intelligence FEIT University of Technology Sydney Australia Department of Data Science and AI Faculty of Information Technology Monash University Australia

—Representation learning on temporal interaction graphs (TIG) is to model complex networks with the dynamic evolution of interactions arising in a broad spectrum of problems. Existing dynamic embedding methods on TIG discretely update node embeddings merely when an interaction occurs. They fail to capture the continuous dynamic evolution of embedding trajectories of nodes. In this paper, we propose a two-module framework named ConTIG, a continuous representation method that captures the continuous dynamic evolution of node embedding trajectories. With two essential modules, our model exploit three-fold factors in dynamic networks which include latest interaction, neighbor features and inherent characteristics. In the first update module, we employ a continuous inference block to learn the nodes’ state trajectories by learning from time-adjacent interaction patterns between node pairs using ordinary differential equations. In the second transform module, we introduce a self-attention mechanism to predict future node embeddings by aggregating historical temporal interaction information. Experiments results demonstrate the superiority of ConTIG on temporal link prediction, temporal node recommendation and dynamic node classification tasks compared with a range of state-of-the-art baselines, especially for long-interval interactions prediction. © 2021, CC BY.

关键词： Ordinary differential equations

来源：评论

学校读者我要写书评

暂无评论

Modeling Multiple Views via Implicitly Preserving Global Consistency and Local Complementarity

arXiv

引用

arXiv 2022年

作者： Li, Jiangmeng Qiang, Wenwen Zheng, Changwen Su, Bing Razzak, Farid Wen, Ji-Rong Xiong, Hui The University of Chinese Academy of Sciences Beijing China The Science & Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences Beijing China The New York University Columbia University New York United States The Beijing Key Laboratory of Big Data Management and Analysis Methods Gaoling School of Artificial Intelligence Renmin University of China Beijing100872 China Guangzhou China Department of Computer Science & Engineering The Hong Kong University of Science and Technology Hong Kong

While self-supervised learning techniques are often used to mine hidden knowledge from unlabeled data via modeling multiple views, it is unclear how to perform effective representation learning in a complex and inconsistent context. To this end, we propose a new multi-view self-supervised learning method, namely consistency and complementarity network (CoCoNet), to comprehensively learn global inter-view consistent and local cross-view complementarity-preserving representations from multiple views. To capture crucial common knowledge which is implicitly shared among views, CoCoNet employs a global consistency module that aligns the probabilistic distribution of views by utilizing an efficient discrepancy metric based on the generalized sliced Wasserstein distance. To incorporate cross-view complementary information, CoCoNet proposes a heuristic complementarity-aware contrastive learning approach, which extracts a complementarity-factor jointing cross-view discriminative knowledge and uses it as the contrast to guide the learning of view-specific encoders. Theoretically, the superiority of CoCoNet is verified by our information-theoretical-based analyses. Empirically, our thorough experimental results show that CoCoNet outperforms the state-of-the-art self-supervised methods by a significant margin, for instance, CoCoNet beats the best benchmark method by an average margin of 1.1% on ImageNet. Copyright © 2022, The Authors. All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Information Fusion and Decoupled Representation Learning for Robust Microbe-Disease Interaction Prediction

引用

Journal of Pharmaceutical Analysis 2024年

作者： Wentao Wang Qiaoying Yan Qingquan Liao Xinyuan Jin Yinyin Gong Linlin Zhuo Xiangzheng Fu Dongsheng Cao School of Data Science and Artificial Intelligence Wenzhou University of Technology 325027 Wenzhou China College of Computer Science and Electronic Engineering Hunan University 410012 Changsha China Department of Xiangya School of Pharmaceutical Sciences Central South University 410003 Changsha P.R. China

Research indicates that microbe activity within the human body significantly influences health by being closely linked to various diseases. Accurately predicting microbe-disease interactions (MDIs) offers critical insights for disease intervention and pharmaceutical research. Current advanced AI-based technologies automatically generate robust representations of microbes and diseases, enabling effective MDI predictions. However, these models continue to face significant challenges. A major issue is their reliance on complex feature extractors and classifiers, which substantially diminishes the models’ generalizability. To address this, we introduce a novel graph autoencoder framework that utilizes decoupled representation learning and multi-scale information fusion strategies to efficiently infer potential MDIs. Initially, we randomly mask portions of the input microbe-disease graph based on Bernoulli distribution to boost self-supervised training and minimize noise-related performance degradation. Secondly, we employ decoupled representation learning technology, compelling the graph neural network (GNN) to independently learn the weights for each feature subspace, thus enhancing its expressive power. Finally, we implement multi-scale information fusion technology to amalgamate the multi-layer outputs of GNN, reducing information loss due to occlusion. Extensive experiments on public datasets demonstrate that our model significantly surpasses existing top MDI prediction models. This indicates that our model can accurately predict unknown MDIs and is likely to aid in disease discovery and precision pharmaceutical research. Code and data are accessible at: https://***/shmildsj/MDI-IFDRL .

关键词： microbe-disease interactions (MDIs) pharmaceutical research AI-based technologies decoupled representation learning multi-scale information fusion

来源：评论

学校读者我要写书评

暂无评论

A causal linear model to quantify edge flow and edge unfairness for unfair edge prioritization & discrimination removal

arXiv

引用

arXiv 2020年

作者： Ravishankar, Pavan Malviya, Pranshu Ravindran, Balaraman Robert Bosch Centre for Data Science and Artificial Intelligence IIT Madras Chennai India Department of Computer Science and Engineering IIT Madras Chennai India

Law enforcement must prioritize sources of unfairness before mitigating their underlying unfairness, considering that they have limited resources. Unlike previous works that only make cautionary claims of discrimination and de-biases data after its generation, this paper attempts to prioritize unfair sources before mitigating their unfairness in the real-world. We assume that a causal bayesian network, representative of the data generation procedure, along with the sensitive nodes, that result in unfairness, are given. We quantify Edge Flow, which is the belief flowing along an edge by attenuating the indirect path influences and use it to quantify Edge Unfairness. We prove that cumulative unfairness is non-existent in any decision, like judicial bail, towards any sensitive groups, like race, when the edge unfairness is absent, given an error-free linear model of conditional probability. We then measure the potential to mitigate the cumulative unfairness when edge unfairness is decreased. Based on these measures, we propose an unfair edge prioritization algorithm that prioritizes the unfair edges and a discrimination removal procedure that de-biases the generated data distribution. The experimental section validates the specifications used for quantifying the above measures. Copyright © 2020, The Authors. All rights reserved.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

A dual model-based evolutionary framework for dynamic large-scale sparse multiobjective optimization

引用

Swarm and Evolutionary Computation 2025年 97卷

作者： Panpan Zhang Ru Zhang Ye Tian Kay Chen Tan Xingyi Zhang School of Electrical Engineering Xi’an University of Technology Xi’an 710048 China Institutes of Physical Science and Information Technology Anhui University Hefei 230601 China School of Computer Science and Technology Anhui University Hefei 230601 China Department of Data Science and Artificial Intelligence The Hong Kong Polytechnic University Hong Kong Special Administrative Region of China

Recently, there has been a growing interest in dynamic multiobjective optimization problems (DMOPs). Although some evolutionary algorithms have been tailored for DMOPs, their effectiveness is limited when handling large-scale DMOPs, especially those characterized by sparsity, where most variables in Pareto-optimal solutions are equal to zero. To address this issue, this paper proposes a dual model-based evolutionary framework to solve dynamic large-scale sparse multiobjective optimization problems (DSMOPs). Specifically, the proposed framework addresses dynamic changes by predicting a new initial population for a static multiobjective optimization evolutionary algorithm in the new environment. Based on the idea of initial population prediction, the proposed framework transforms the large-scale variable prediction into the small-scale variable prediction, where support vector regression is introduced to predict the sparse distributions of the new initial population to reduce the decision space, and multilayer perceptron is performed on the reduced space to predict its continuous distributions. By integrating the two simplified predictions, a two-layer change response mechanism is constructed to ensure both the sparsity and quality of the obtained solutions. In addition, this paper designs the benchmark and real-world test problems to assess the performance of the proposed framework for tackling large-scale DMOPs. Experimental results demonstrate the superiority of the proposed framework compared with the six state-of-the-art algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Balance Assessment for Double and Single Leg Stance Using FIBOD Balance System 3rd

Balance Assessment for Double and Single Leg Stance Using FI...

引用

3rd International Conference for Innovation in Biomedical engineering and Life sciences, ICIBEL 2020

作者： Khor, Kang Xiang Yeong, Che Fai Su, Eileen Lee Ming Latip, Hadafi Fitri Mohd Khor, Yvonne Yee Woon Chan, Sook Chin Chern, Phei Ming Leow, Mei Lian Abdullah, Najib bin Mustar, Muhammad Farhan bin Halim, Muhammad Nurhakim bin Abdul Skudai Johor81300 Malaysia Center of Artificial Intelligence and Robotics UTM Kuala Lumpur54100 Malaysia School of Biomedical Engineering and Health Science Faculty of Engineering UTM Skudai Johor81310 Malaysia Sports Innovation and Technology Centre UTM Skudai Johor81300 Malaysia UTM Skudai Johor81310 Malaysia MAHSA University Jenjarom Selangor42610 Malaysia Clinical Research Centre Cheras Rehabilitation Hospital Kuala Lumpur56000 Malaysia Faculty of Computer and Mathematical Sciences UiTM Segamat85000 Malaysia

ISBN: (纸本)9783030650919

Physical balance is important to support human motion for almost all activities of daily living such as standing, sitting, cooking, housework or shopping. However, balance tends to drop as human grow older due to the loss of muscle. FIBOD balance system (FBS) is a balance system designed to be portable and easy to use. This study investigates the FBS balance measures with 17 healthy subjects. Results show significant differences in double-leg overall stability index (OSI) and medial-lateral stability index (MLSI) (p = 0.01);double-leg and dominant leg MLSI (p © 2021, Springer Nature Switzerland AG.

关键词： Balance assessment Balance board Instrumented wobble board

来源：评论

学校读者我要写书评

暂无评论

An integrated GIS-based multivariate adaptive regression splines-cat swarm optimization for improving the accuracy of wildfire susceptibility mapping

引用

Geocarto International 2023年第1期38卷

作者： Hai, Tao Theruvil Sayed, Biju Majdi, Ali Zhou, Jincheng Sagban, Rafid Band, Shahab S. Mosavi, Amir School of Computer and Information Qiannan Normal University for Nationalities Guizhou Duyun China Key Laboratory of Complex Systems and Intelligent Optimization of Guizhou Guizhou Duyun China Institute for Big Data Analytics and Artificial Intelligence (IBDAAI) Universiti Teknologi MARA Selangor Shah Alam Malaysia Department of Computer Science Dhofar University Salalah Oman Department of Building and Construction Technologies Engineering Al-Mustaqbal University College Hilla Iraq Department of Computer Technology Engineering Technical Engineering College Al-Ayen University Thi-Qar Iraq Future Technology Research Center National Yunlin University of Science and Technology Yunlin Douliou Taiwan John von Neumann Faculty of Informatics Obuda University Budapest Hungary German Research Center for Artificial Intelligence Oldenburg Germany Institute of the Information Society University of Public Service Budapest Hungary

A hybrid machine learning method is proposed for wildfire susceptibility mapping. For modeling a geographical information system (GIS) database including 11 influencing factors and 262 fire locations from 2013 to 2018 is used for developing an integrated multivariate adaptive regression splines (MARS). The cat swarm optimization (CSO) algorithm tunes the parameters of the MARS in order to generate accurate susceptibility maps. From the Pearson correlation results, it is observed that land use, temperature, and slope angle have strong correlation with the fire severity. The results demonstrate that the prediction capability of the MARS-CSO model outperforms model tree, reduced error pruning tree and MARS. The resulting wildfire risk map using MARS-CSO reveals that 20% of the study areas is categorized in the very low wildfire risk class, whereas 40% is under the very high class of fire hazard. © 2023 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

关键词： artificial intelligence cat swarm optimization geospatial machine learning natural hazard Wildfire susceptibility

来源：评论

学校读者我要写书评

暂无评论

Predicting Eddy current losses in large generator rotor using data-driven short connection deep Gaussian process

引用

engineering Applications of artificial intelligence 2025年 158卷

作者： Guo, Hai Cai, Jinlin Wang, Likun Zhang, Junxing Marignetti, Fabrizio Zhang, Bixian School of Data Science and Artificial Intelligence Wenzhou University of Technology Wen Zhou 325035 China College of Computer Science and Engineering Dalian Minzu University Dalian 116600 China College of Electrical and Electronic Engineering Harbin University of Science and Technology Harbin 150080 China Department of Electrical and Information Engineering University of Cassino and South Lazio Cassino 03043 Italy

In response to the increased prediction errors observed when applying deep Gaussian process (DGP) models to the eddy current loss data of large generator rotors, an explainable artificial intelligence(AI)-based DGP prediction method incorporating short connections design is proposed. This method reparameterizes multivariate normal random variables between layers and concatenates processed input-layer data to construct new inter-layer inputs for the subsequent layer, thereby establishing a short-connected DGP model. This approach effectively mitigates the accumulation of prediction errors due to increased model depth, significantly enhancing the model's adaptability and predictive accuracy in complex data structures. Experimental results demonstrate that the short-connected DGP model achieved exceptional predictive performance for eddy current loss estimation, as evidenced by a coefficient of determination of 0.9886 and a mean squared error of 0.0026. Furthermore, as the number of layers increases, the short-connected DGP model outperforms both existing DGP models and alternative approaches in prediction accuracy. The proposed AI method not only robustly supports high-precision prediction of eddy current losses in the rotor slot filling components of large generators, but also serves as an efficient and reliable modeling tool for their design and optimization, thereby possessing significant theoretical and practical value. © 2025

关键词： Current loss prediction Deep gaussian process Explainable artificial intelligence Large generator

来源：评论

学校读者我要写书评

暂无评论

Structure Embedded Nucleus Classification for Histopathology Images

arXiv

引用

arXiv 2023年

作者： Lou, Wei Wan, Xiang Li, Guanbin Lou, Xiaoying Li, Chenghang Gao, Feng Li, Haofeng Shenzhen Research Institute of Big Data Guangdong Provincial Key Laboratory of Big Data Computing The Chinese University of Hong Kong at Shenzhen Shenzhen518172 China Pazhou Lab Guangzhou510330 China The School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China Department of Pathology Guangdong Provincial Key Laboratory of Colorectal and Pelvic Floor Diseases The Sixth Affiliated Hospital of Sun Yat-sen University Guangzhou China Artificial Intelligence Thrust The Hong Kong University of Science and Technology at Guangzhou Guangzhou510030 China Department of Colorectal Surgery Department of General Surgery Guangdong Provincial Key Laboratory of Colorectal and Pelvic Floor Diseases The Sixth Affiliated Hospital Sun Yat-sen University Guangzhou510655 China Shanghai Artificial Intelligence Laboratory Shanghai China

Nuclei classification provides valuable information for histopathology image analysis. However, the large variations in the appearance of different nuclei types cause difficulties in identifying nuclei. Most neural network based methods are affected by the local receptive field of convolutions, and pay less attention to the spatial distribution of nuclei or the irregular contour shape of a nucleus. In this paper, we first propose a novel polygon-structure feature learning mechanism that transforms a nucleus contour into a sequence of points sampled in order, and employ a recurrent neural network that aggregates the sequential change in distance between key points to obtain learnable shape features. Next, we convert a histopathology image into a graph structure with nuclei as nodes, and build a graph neural network to embed the spatial distribution of nuclei into their representations. To capture the correlations between the categories of nuclei and their surrounding tissue patterns, we further introduce edge features that are defined as the background textures between adjacent nuclei. Lastly, we integrate both polygon and graph structure learning mechanisms into a whole framework that can extract intra and inter-nucleus structural characteristics for nuclei classification. Experimental results show that the proposed framework achieves significant improvements compared to the state-of-the-art methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Enhancing skin cancer detection through category representation and fusion of pre-trained models

引用

Information Fusion 2025年

作者： Lingping Kong Juan D. Velasquez Václav Snášel Millie Pant Jeng-Shyang Pan Jana Nowakova Department of Computer Science VSB-Technical University of Ostrava listpodu 17 Czech Republic Department of Industrial Engineering University of Chile Santiago O’Higgins 1058 Chile Instituto Sistemas Complejos de Ingeniería Santiago Chile Department of Applied Mathematics and Scientific Computing Indian Institute of Technology Roorkee Uttarakhand 247667 India Mehta Family School of Data Science and Artificial Intelligence Indian Institute of Technology Roorkee Uttarakhand 247667 India School of Artificial Intelligence Nanjing University of Information Science and Technology 219 Ningliu Road China College of Computer Science and Engineering Shandong University of Science and Technology China

The use of pre-trained models in medical image classification has gained significant attention due to their ability to handle complex datasets and improve accuracy. However, challenges such as domain-specific customization, interpretability, and computational efficiency remain critical, especially in high-stakes applications such as skin cancer detection. In this paper, we introduce a novel interpretability-assisted fine-tuning framework that leverages category representation to enhance both model accuracy and transparency. Using the widely known HAM10000 dataset, which includes seven imbalanced categories of skin cancer, we demonstrate that our method improves the classification accuracy by 2.6% compared to standard pre-trained models. In addition to precision, we also achieve significant improvements in interpretability, with our category representation framework providing more understandable insights into the model’s decision-making process. Key metrics, such as precision and recall, show enhanced performance, particularly for underrepresented skin cancer types such as Melanocytic Nevi (F1 score of 0.94) and Actinic Keratosis (F1 score of 0.66). Furthermore, the prediction accuracy of the proposed model of the top-3 reaches 98. 21%, which is highly significant for medical decision making. This observation in interpredibility underscores the value of top- n predictions, especially in challenging cases, to support more informed and accurate decisions. The proposed fusion framework not only enhances predictive accuracy, but also offers an interpretable model output that can assist clinicians in making informed decisions. This makes our approach particularly relevant in medical applications, where both accuracy and transparency are crucial. Our results highlight the potential of fusing pretrained models with category representation techniques to bridge the gap between performance and interpretability in AI-driven healthcare solutions.

关键词： Pre-trained model Sparse representation Skin cancer data Model interpredibility

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：