检索结果-内蒙古大学图书馆

2nd International Conference on Frontiers of Artificial Intelligence and Machine Learning, FAIML 2023

作者： Chen, Xue Hu, Yuxing Hong, Xiaoxia Zhu, Zhaohan Song, Yang Liu, Juan Song, Peng Xiong, Wei Yan, Meng Chongqing Housing Provident Fund Management Center Chongqing China School of Big Data and Software Engineering Chongqing University Chongqing China School of Eletrical Engineering Southwest Jiaotong University Sichuan China

ISBN: (纸本)9798400707544

With the rapid development of big data and cloud computing, digital technology has been widely used to develop provident funds. We innovatively apply data mining and machine learning methods to analyze the impact factors of provident fund deposits and the recommendation model of the deposit products for flexible employees. After experiments, our model performs well in the performance evaluation index (such as Accuracy, Recall, and F1-score). Through our model and research analysis, the housing provident fund center can comprehensively analyze and mine the real data, promote more popular customer policies, and provide better customer service. © 2023 Copyright held by the owner/author(s).

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Prediction and Analysis of Stroke Risk Based on Ensemble Learning 15th

Prediction and Analysis of Stroke Risk Based on Ensemble Lea...

引用

15th International Conference on Genetic and Evolutionary Computing, ICGEC 2023

作者： Zuo, Xiuji Guo, Xin Yin, Zilong Tseng, Shih-Pang School of Information Science and Technology Sanda University Shanghai201209 China Department of Electronic and Electrical Engineering Shanghai University of Engineering Science Shanghai201620 China School of Software and Big Data Changzhou College of Information Technology Changzhou213164 China

ISBN: (纸本)9789819994113

With the development of science and technology, the application of data mining in medical field is becoming more and more popular. Machine learning methods also plays an important role in disease prediction. Stroke is characterized by high incidence rate, high disability rate, high mortality rate and high recurrence rate, and it is also likely to cause other kinds of complications. In this paper, each feature in the stroke dataset was analyzed in order to find out the factors affecting stroke and conducts classification and prediction research on whether there is a disease risk. Specifically, the PCA (Principal Component Analysis) algorithm is used to extract the main feature components of data, the SMOTE (Synthetic Minority Oversampling Technique) algorithm is used to adjust imbalanced feature categories. Traditional machine learning classification algorithms, such as decision tree, SVM(support vector machines), and various ensemble learning algorithms are used for the prediction of stroke risk, so as to study the relationship between stroke disease and each feature, and the classification prediction model, so that we can prevent strokes in time and reduce the risk of stroke. Among all the models, Bagging (Bootstrap aggregating) has the best performance with an ROC value of 0.97. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Guiding ChatGPT for Better Code Generation: An Empirical Study

Guiding ChatGPT for Better Code Generation: An Empirical Stu...

引用

IEEE International Conference on software Analysis, Evolution and Reengineering (SANER)

作者： Chao Liu Xuanlin Bao Hongyu Zhang Neng Zhang Haibo Hu Xiaohong Zhang Meng Yan School of Big Data and Software Engineering Chongqing University China School of Software Engineering Sun Yat-sen University China

ISBN: (数字)9798350330663

ISBN: (纸本)9798350330670

Automated code generation is a powerful technique for software development, which can significantly reduce developers' effort and time for writing code. Recently, OpenAI's large language model ChatGPT has emerged as a powerful tool for generating human-like responses to a wide range of textual inputs (i.e., prompts), including those related to code generation. However, the effectiveness of ChatGPT in code generation is still not well understood. The code generation performance could also be heavily influenced by the choice of prompts, which should be further explored. In this paper, we report an empirical study on ChatGPT's capabilities for two types of code generation tasks, namely text-to-code and code-to-code generation. We investigate different types of prompts by leveraging the chain-of-thought strategy with multi-step optimizations. Our empirical results show that by carefully designing prompts to guide ChatGPT, the code generation performance can be improved substantially. We also analyze the factors that influence the prompt design and provide insights that could guide future research.

关键词： Codes Large language models Writing Chatbots software Task analysis Optimization

来源：评论

学校读者我要写书评

暂无评论

SAM-MIL: A Spatial Contextual Aware Multiple Instance Learning Approach for Whole Slide Image Classification 24

SAM-MIL: A Spatial Contextual Aware Multiple Instance Learni...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Fang, Heng Huang, Sheng Tang, Wenhao Huangfu, Luwen Liu, Bo School of Big Data & Software Engineering Chongqing University Chongqing China Fowler College of Business San Diego State University San DiegoCA United States School of Computer Science and Information Engineering Hefei University of Technology Hefei China

ISBN: (纸本)9798400706868

Multiple Instance Learning (MIL) represents the predominant framework in Whole Slide Image (WSI) classification, covering aspects such as sub-typing, diagnosis, and beyond. Current MIL models predominantly rely on instance-level features derived from pretrained models such as ResNet. These models segment each WSI into independent patches and extract features from these local patches, leading to a significant loss of global spatial context and restricting the model's focus to merely local features. To address this issue, we propose a novel MIL framework, named SAM-MIL, that emphasizes spatial contextual awareness and explicitly incorporates spatial context by extracting comprehensive, image-level information. The Segment Anything Model (SAM) represents a pioneering visual segmentation foundational model that can capture segmentation features without the need for additional fine-tuning, rendering it an outstanding tool for extracting spatial context directly from raw WSIs. Our approach includes the design of group feature extraction based on spatial context and a SAM-Guided Group Masking strategy to mitigate class imbalance issues. We implement a dynamic mask ratio for different segmentation categories and supplement these with representative group features of categories. Moreover, SAM-MIL divides instances to generate additional pseudo-bags, thereby augmenting the training set, and introduces consistency of spatial context across pseudo-bags to further enhance the model's performance. Experimental results on the CAMELYON-16 and TCGA Lung Cancer datasets demonstrate that our proposed SAM-MIL model outperforms existing mainstream methods in WSIs classification. Our open-source implementation code is is available at https://***/FangHeng/SAM-MIL. © 2024 ACM.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Labelrepair: Sequence Labelling for Compilation Errors Repair 31

Labelrepair: Sequence Labelling for Compilation Errors Repai...

引用

31st IEEE International Conference on software Analysis, Evolution and Reengineering, SANER 2024

作者： Wu, Zhenyu Yang, Deheng Lei, Yan Xie, Huan Tang, Minghua Li, Maojin Academy of Military Sciences Beijing China School of Big Data & Software Engineering Chongqing University Chongqing China Peng Cheng Laboratory Shenzhen China Kunming University of Science and Technology Kunming China

ISBN: (纸本)9798350330663

Manual fixing of compilation errors could be a tedious and time-consuming task for novice programmers, and even for experienced ones. In recent years, an increasing number of automated repair techniques have been proposed to guide novice programmers and improve the efficiency of software development. Among them, learning-based automated repair techniques have achieved promising results in terms of repair accuracy. However, existing approaches neglect the time efficiency of patch generation, and often treat the compilation errors repair as a neural machine translation task. The end-to-end repair model decoding cannot be parallelized during the inference stage and suffers from redundant decoding search space. Furthermore, the large search space brought by the model poses a potential risk of semantic tampering. To this end, we propose Labelrepair, a novel repair technique that treats the repair of compilation errors as a sequence labelling task. Labelrepair discards the decoding model and converts the search for patches to a search for the error mapping actions between broken code and patch code pairs. In this way, the search space for patch tokens is plum-meted from the entire vocabulary to the size of edit action labels, and the logical semantics of the original program are preserved to some extent. The time complexity of inference is reduced from O(n) to O (1) owing to the parallel generation of edit action labels. Through a comprehensive evaluation of Labelrepair on two datasets, we demonstrate that Labelrepair is able to generate patches instantly (0.71ms on average), which is 28 times faster than existing end-to-end repair models. Compared with existing edit-based repair models, Labelrepair achieves the state-of-art repair accuracy. © 2024 IEEE.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Thermal-Aware Approximate Real-Time Task Scheduling for Multicore Embedded Systems

Thermal-Aware Approximate Real-Time Task Scheduling for Mult...

引用

2023 China Automation Congress, CAC 2023

作者： Peng, Chujun Mo, Lei Liu, Ji Niu, Dan School of Software Engineering Southeast University Suzhou215123 China School of Automation Southeast University Nanjing210096 China Baidu Research Big Data Laboratory Beijing100085 China

ISBN: (纸本)9798350303759

High temperature affects the processing performance of chips and accelerates electronic component aging, leading to reliability issues. This paper proposes a two-stage temperature-aware scheduling scheme for approximate tasks based on homoge-neous multicore platforms, solving approximate task scheduling problem under time, energy, reliability, and temperature constraints. In the first stage, we design a heuristic scheduling algorithm to perform task-to-processor assignment and preliminarily task frequency selection to minimize energy and makespan. In the second stage, we design a temperature optimization algorithm that combines DVFS and slack distribution to ensure that processor temperature is lower than the temperature threshold. Compared with the existing methods, the experimental simulations show that our method achieves 97.6% runtime reduction and 14.9% peak temperature reduction. © 2023 IEEE.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Massively parallel algorithms for fully dynamic all-pairs shortest paths

引用

Frontiers of Computer Science 2024年第4期18卷 201-203页

作者： Chilei WANG Qiang-Sheng HUA Hai JIN Chaodong ZHENG National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China State Key Laboratory for Novel Software Technology Nanjing UniversityNanjing 210023China

1 Introduction In recent years,the Massively Parallel Computation(MPC)model has gained significant ***,most of distributed and parallel graph algorithms in the MPC model are designed for static graphs[1].In fact,the graphs in the real world are constantly *** size of the real-time changes in these graphs is smaller and more *** graph algorithms[2,3]can deal with graph changes more efficiently[4]than the corresponding static graph ***,most studies on dynamic graph algorithms are limited to the single machine ***,a few parallel dynamic graph algorithms(such as the graph connectivity)in the MPC model[5]have been proposed and shown superiority over their parallel static counterparts.

关键词： dynamic shortest gained

来源：评论

学校读者我要写书评

暂无评论

Batch Normalization Damages Federated Learning on NON-IID data: Analysis and Remedy 48

Batch Normalization Damages Federated Learning on NON-IID Da...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Wang, Yanmeng Shi, Qingjiang Chang, Tsung-Hui The Chinese University of Hong Kong School of Science and Engineering Shenzhen518172 China Shenzhen Research Institute of Big Data Shenzhen518172 China Tongji University School of Software Engineering Shanghai201804 China

ISBN: (纸本)9781728163277

Batch normalization (BN) has been widely used for accelerating the training of deep neural networks. However, recent findings show that, in the federated learning (FL) scenarios, BN can damage the learning performance when the clients have non-i.i.d. data. While several FL schemes have been proposed to address this issue, they still suffer a significant performance loss compared to the centralized scheme. In addition, none of them have explained how the BN impacts the FL convergence analytically. In this paper, we present the first convergence analysis to show that the mismatched local and global statistical parameters due to non-i.i.d data cause gradient deviation and it leads the algorithm to converge to a biased solution with a slower rate. To remedy this, we further present a new FL algorithm, called FedTAN, based on an iterative layer-wise parameter aggregation procedure. Experiment results are presented to show the superiority of FedTAN. © 2023 IEEE.

关键词： batch normalization convergence analysis Federated learning non-i.i.d. data

来源：评论

学校读者我要写书评

暂无评论

Plausible Heterogeneous Graph k-Anonymization for Social Networks

引用

Tsinghua Science and Technology 2022年第6期27卷 912-924页

作者： Kaiyang Li Ling Tian Xu Zheng Bei Hui School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu 610054China Trusted Cloud Computing and Big Data Key Laboratory of Sichuan Province Chengdu 610000China

The inefficient utilization of ubiquitous graph data with combinatorial structures necessitates graph embedding methods,aiming at learning a continuous vector space for the graph which is amenable to be adopted in traditional machine learning algorithms in favor of vector *** embedding methods build an important bridge between social network analysis and data analytics as social networks naturally generate an unprecedented volume of graph data *** social network data not only bring benefit for public health,disaster response,commercial promotion,and many other applications,but also give birth to threats that jeopardize each individual’s privacy and ***,most existing works in publishing social graph embedding data only focus on preserving social graph structure with less attention paid to the privacy issues inherited from social *** be specific,attackers can infer the presence of a sensitive relationship between two individuals by training a predictive model with the exposed social network *** this paper,we propose a novel link-privacy preserved graph embedding framework using adversarial learning,which can reduce adversary’s prediction accuracy on sensitive links while persevering sufficient non-sensitive information such as graph topology and node attributes in graph *** experiments are conducted to evaluate the proposed framework using ground truth social network datasets.

关键词： social network graph embedding privacy preservation adversarial learning

来源：评论

学校读者我要写书评

暂无评论

DGN-MEF: A DenseNet-Based Multi-Exposure Image Fusion Framework using Adaptive Gabor convolution 43

DGN-MEF: A DenseNet-Based Multi-Exposure Image Fusion Framew...

引用

43rd Chinese Control Conference, CCC 2024

作者： Zhang, Mei Jin, Ye Zhu, Jinhui South China University of Technology School of Automation Science and Engineering Guangzhou510641 China South China University of Technology School of Software Engineering Guangzhou510006 China Key Laboratory of Big Data and Intelligent Robot Ministry of Education Guangzhou510006 China

ISBN: (纸本)9789887581581

Multi-exposure image fusion is a cost-effective method to improve the dynamic range of images. For the problems of inadequate detail extraction in bright and dark areas and the over simplicity of existing fusion rules by current deep learning multi-exposure image fusion algorithms, we propose a DenseNet-based framework using adaptive Gabor convolution. Building on the Dense network architecture, we design an adaptive Gabor convolution module, which the parameters of the Gabor filter can be updated along with the network, enhancing the ability of Gabor to extract image features. Additionally, a cross-domain aggregation attention module is proposed, which effectively aggregates and enhances information. Comparing our method with seven advanced methods on the multi-exposure image fusion benchmark dataset, the subjective and objective evaluations outperform the other methods, proving the effectiveness and superiority of our method. The experiments of different exposure images fusion demonstrate the good generalization performance of our method. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Convolution

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：